diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/lds-misaligned-bug.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/lds-misaligned-bug.ll
index d7d1a4cc819dbf..fc4c3f710c28fe 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/lds-misaligned-bug.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/lds-misaligned-bug.ll
@@ -3,10 +3,13 @@
 ; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1012 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,ALIGNED,ALIGNED-WGP %s
 ; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -mattr=+cumode < %s | FileCheck -check-prefixes=GCN,ALIGNED,ALIGNED-CU %s
 ; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -mattr=+cumode,+unaligned-access-mode < %s | FileCheck -check-prefixes=GCN,UNALIGNED %s
+; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,ALIGNED,ALIGNED-CU %s
+; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs -mattr=+cumode < %s | FileCheck -check-prefixes=GCN,ALIGNED,ALIGNED-CU %s
+; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs -mattr=+cumode,+unaligned-access-mode < %s | FileCheck -check-prefixes=GCN,UNALIGNED %s
 
 ; GCN-LABEL: test_local_misaligned_v2:
-; GCN-DAG: ds_read2_b32
-; GCN-DAG: ds_write2_b32
+; GCN-DAG: ds_{{read2|load_2addr}}_b32
+; GCN-DAG: ds_{{write2|store_2addr}}_b32
 define amdgpu_kernel void @test_local_misaligned_v2(i32 addrspace(3)* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -22,12 +25,12 @@ bb:
 }
 
 ; GCN-LABEL: test_local_misaligned_v4:
-; ALIGNED-DAG: ds_read2_b32
-; ALIGNED-DAG: ds_read2_b32
-; ALIGNED-DAG: ds_write2_b32
-; ALIGNED-DAG: ds_write2_b32
-; UNALIGNED-DAG: ds_read2_b64
-; UNALIGNED-DAG: ds_write2_b64
+; ALIGNED-DAG: ds_{{read2|load_2addr}}_b32
+; ALIGNED-DAG: ds_{{read2|load_2addr}}_b32
+; ALIGNED-DAG: ds_{{write2|store_2addr}}_b32
+; ALIGNED-DAG: ds_{{write2|store_2addr}}_b32
+; UNALIGNED-DAG: ds_{{read2|load_2addr}}_b64
+; UNALIGNED-DAG: ds_{{write2|store_2addr}}_b64
 define amdgpu_kernel void @test_local_misaligned_v4(i32 addrspace(3)* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -47,12 +50,12 @@ bb:
 }
 
 ; GCN-LABEL: test_local_misaligned_v3:
-; ALIGNED-DAG: ds_read2_b32
-; ALIGNED-DAG: ds_read_b32
-; ALIGNED-DAG: ds_write2_b32
-; ALIGNED-DAG: ds_write_b32
-; UNALIGNED-DAG: ds_read_b96
-; UNALIGNED-DAG: ds_write_b96
+; ALIGNED-DAG: ds_{{read2|load_2addr}}_b32
+; ALIGNED-DAG: ds_{{read|load}}_b32
+; ALIGNED-DAG: ds_{{write2|store_2addr}}_b32
+; ALIGNED-DAG: ds_{{write|store}}_b32
+; UNALIGNED-DAG: ds_{{read|load}}_b96
+; UNALIGNED-DAG: ds_{{write|store}}_b96
 define amdgpu_kernel void @test_local_misaligned_v3(i32 addrspace(3)* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -70,8 +73,8 @@ bb:
 }
 
 ; GCN-LABEL: test_local_aligned_v2:
-; GCN-DAG: ds_read_b64
-; GCN-DAG: ds_write_b64
+; GCN-DAG: ds_{{read|load}}_b64
+; GCN-DAG: ds_{{write|store}}_b64
 define amdgpu_kernel void @test_local_aligned_v2(i32 addrspace(3)* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -87,8 +90,8 @@ bb:
 }
 
 ; GCN-LABEL: test_local_aligned_v3:
-; GCN-DAG: ds_read_b96
-; GCN-DAG: ds_write_b96
+; GCN-DAG: ds_{{read|load}}_b96
+; GCN-DAG: ds_{{write|store}}_b96
 define amdgpu_kernel void @test_local_aligned_v3(i32 addrspace(3)* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -106,14 +109,14 @@ bb:
 }
 
 ; GCN-LABEL: test_local_v4_aligned8:
-; ALIGNED-WGP-DAG: ds_read2_b32
-; ALIGNED-WGP-DAG: ds_read2_b32
-; ALIGNED-WGP-DAG: ds_write2_b32
-; ALIGNED-WGP-DAG: ds_write2_b32
-; ALIGNED-CU-DAG: ds_read2_b64
-; ALIGNED-CU-DAG: ds_write2_b64
-; UNALIGNED-DAG: ds_read2_b64
-; UNALIGNED-DAG: ds_write2_b64
+; ALIGNED-WGP-DAG: ds_{{read2|load_2addr}}_b32
+; ALIGNED-WGP-DAG: ds_{{read2|load_2addr}}_b32
+; ALIGNED-WGP-DAG: ds_{{write2|store_2addr}}_b32
+; ALIGNED-WGP-DAG: ds_{{write2|store_2addr}}_b32
+; ALIGNED-CU-DAG: ds_{{read2|load_2addr}}_b64
+; ALIGNED-CU-DAG: ds_{{write2|store_2addr}}_b64
+; UNALIGNED-DAG: ds_{{read2|load_2addr}}_b64
+; UNALIGNED-DAG: ds_{{write2|store_2addr}}_b64
 define amdgpu_kernel void @test_local_v4_aligned8(i32 addrspace(3)* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
diff --git a/llvm/test/CodeGen/AMDGPU/add.v2i16.ll b/llvm/test/CodeGen/AMDGPU/add.v2i16.ll
index 0c2ba16034b37d..7cdaa805749433 100644
--- a/llvm/test/CodeGen/AMDGPU/add.v2i16.ll
+++ b/llvm/test/CodeGen/AMDGPU/add.v2i16.ll
@@ -1,7 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=VI %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GFX9 %s
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GFX10 %s
+; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=VI %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX10 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11 %s
 
 ; FIXME: Need to handle non-uniform case for function below (load without gep).
 ; FIXME: VI or should be unnecessary
@@ -18,16 +19,16 @@ define amdgpu_kernel void @v_test_add_v2i16(<2 x i16> addrspace(1)* %out, <2 x i
 ; VI-NEXT:    v_mov_b32_e32 v3, s1
 ; VI-NEXT:    v_add_u32_e32 v2, vcc, s0, v2
 ; VI-NEXT:    v_addc_u32_e32 v3, vcc, 0, v3, vcc
-; VI-NEXT:    flat_load_dword v0, v[0:1] glc
+; VI-NEXT:    flat_load_dword v4, v[0:1] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
-; VI-NEXT:    flat_load_dword v1, v[2:3] glc
+; VI-NEXT:    flat_load_dword v2, v[2:3] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
-; VI-NEXT:    s_mov_b32 s7, 0xf000
-; VI-NEXT:    s_mov_b32 s6, -1
-; VI-NEXT:    v_add_u16_e32 v2, v0, v1
-; VI-NEXT:    v_add_u16_sdwa v0, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
-; VI-NEXT:    v_or_b32_e32 v0, v2, v0
-; VI-NEXT:    buffer_store_dword v0, off, s[4:7], 0
+; VI-NEXT:    v_mov_b32_e32 v0, s4
+; VI-NEXT:    v_mov_b32_e32 v1, s5
+; VI-NEXT:    v_add_u16_e32 v3, v4, v2
+; VI-NEXT:    v_add_u16_sdwa v2, v4, v2 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; VI-NEXT:    v_or_b32_e32 v2, v3, v2
+; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_test_add_v2i16:
@@ -40,10 +41,9 @@ define amdgpu_kernel void @v_test_add_v2i16(<2 x i16> addrspace(1)* %out, <2 x i
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
 ; GFX9-NEXT:    global_load_dword v2, v0, s[2:3] glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    s_mov_b32 s7, 0xf000
-; GFX9-NEXT:    s_mov_b32 s6, -1
-; GFX9-NEXT:    v_pk_add_u16 v0, v1, v2
-; GFX9-NEXT:    buffer_store_dword v0, off, s[4:7], 0
+; GFX9-NEXT:    v_mov_b32_e32 v0, 0
+; GFX9-NEXT:    v_pk_add_u16 v1, v1, v2
+; GFX9-NEXT:    global_store_dword v0, v1, s[4:5]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: v_test_add_v2i16:
@@ -57,12 +57,27 @@ define amdgpu_kernel void @v_test_add_v2i16(<2 x i16> addrspace(1)* %out, <2 x i
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-NEXT:    global_load_dword v2, v0, s[2:3] glc dlc
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
-; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
-; GFX10-NEXT:    s_mov_b32 s7, 0x31016000
-; GFX10-NEXT:    s_mov_b32 s6, -1
-; GFX10-NEXT:    v_pk_add_u16 v0, v1, v2
-; GFX10-NEXT:    buffer_store_dword v0, off, s[4:7], 0
+; GFX10-NEXT:    v_mov_b32_e32 v0, 0
+; GFX10-NEXT:    v_pk_add_u16 v1, v1, v2
+; GFX10-NEXT:    global_store_dword v0, v1, s[4:5]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: v_test_add_v2i16:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_clause 0x1
+; GFX11-NEXT:    s_load_b128 s[4:7], s[0:1], 0x24
+; GFX11-NEXT:    s_load_b64 s[0:1], s[0:1], 0x34
+; GFX11-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX11-NEXT:    v_mov_b32_e32 v2, 0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    global_load_b32 v1, v0, s[6:7] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    global_load_b32 v0, v0, s[0:1] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    v_pk_add_u16 v0, v1, v0
+; GFX11-NEXT:    global_store_b32 v2, v0, s[4:5]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i32 %tid
   %gep.in0 = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in0, i32 %tid
@@ -79,40 +94,35 @@ define amdgpu_kernel void @s_test_add_v2i16(<2 x i16> addrspace(1)* %out, <2 x i
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x24
 ; VI-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x34
-; VI-NEXT:    s_mov_b32 s3, 0xf000
-; VI-NEXT:    s_mov_b32 s2, -1
-; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    s_load_dword s6, s[6:7], 0x0
-; VI-NEXT:    s_load_dword s7, s[0:1], 0x0
-; VI-NEXT:    s_mov_b32 s0, s4
-; VI-NEXT:    s_mov_b32 s1, s5
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    s_lshr_b32 s4, s6, 16
-; VI-NEXT:    s_lshr_b32 s5, s7, 16
-; VI-NEXT:    s_add_i32 s6, s6, s7
-; VI-NEXT:    s_add_i32 s4, s4, s5
-; VI-NEXT:    s_and_b32 s5, s6, 0xffff
-; VI-NEXT:    s_lshl_b32 s4, s4, 16
-; VI-NEXT:    s_or_b32 s4, s5, s4
+; VI-NEXT:    s_load_dword s2, s[6:7], 0x0
+; VI-NEXT:    s_load_dword s0, s[0:1], 0x0
 ; VI-NEXT:    v_mov_b32_e32 v0, s4
-; VI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; VI-NEXT:    v_mov_b32_e32 v1, s5
+; VI-NEXT:    s_waitcnt lgkmcnt(0)
+; VI-NEXT:    s_lshr_b32 s1, s2, 16
+; VI-NEXT:    s_lshr_b32 s3, s0, 16
+; VI-NEXT:    s_add_i32 s2, s2, s0
+; VI-NEXT:    s_add_i32 s1, s1, s3
+; VI-NEXT:    s_and_b32 s0, s2, 0xffff
+; VI-NEXT:    s_lshl_b32 s1, s1, 16
+; VI-NEXT:    s_or_b32 s0, s0, s1
+; VI-NEXT:    v_mov_b32_e32 v2, s0
+; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: s_test_add_v2i16:
 ; GFX9:       ; %bb.0:
-; GFX9-NEXT:    s_load_dwordx2 s[8:9], s[0:1], 0x34
+; GFX9-NEXT:    s_load_dwordx2 s[2:3], s[0:1], 0x34
 ; GFX9-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x24
-; GFX9-NEXT:    s_mov_b32 s3, 0xf000
-; GFX9-NEXT:    s_mov_b32 s2, -1
+; GFX9-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9-NEXT:    s_load_dword s10, s[8:9], 0x0
-; GFX9-NEXT:    s_load_dword s11, s[6:7], 0x0
-; GFX9-NEXT:    s_mov_b32 s0, s4
-; GFX9-NEXT:    s_mov_b32 s1, s5
+; GFX9-NEXT:    s_load_dword s0, s[2:3], 0x0
+; GFX9-NEXT:    s_load_dword s1, s[6:7], 0x0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9-NEXT:    v_mov_b32_e32 v0, s10
-; GFX9-NEXT:    v_pk_add_u16 v0, s11, v0
-; GFX9-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX9-NEXT:    v_mov_b32_e32 v1, s0
+; GFX9-NEXT:    v_pk_add_u16 v1, s1, v1
+; GFX9-NEXT:    global_store_dword v0, v1, s[4:5]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: s_test_add_v2i16:
@@ -120,15 +130,29 @@ define amdgpu_kernel void @s_test_add_v2i16(<2 x i16> addrspace(1)* %out, <2 x i
 ; GFX10-NEXT:    s_clause 0x1
 ; GFX10-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x24
 ; GFX10-NEXT:    s_load_dwordx2 s[2:3], s[0:1], 0x34
+; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    s_load_dword s0, s[6:7], 0x0
 ; GFX10-NEXT:    s_load_dword s1, s[2:3], 0x0
-; GFX10-NEXT:    s_mov_b32 s7, 0x31016000
-; GFX10-NEXT:    s_mov_b32 s6, -1
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX10-NEXT:    v_pk_add_u16 v0, s0, s1
-; GFX10-NEXT:    buffer_store_dword v0, off, s[4:7], 0
+; GFX10-NEXT:    v_pk_add_u16 v1, s0, s1
+; GFX10-NEXT:    global_store_dword v0, v1, s[4:5]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: s_test_add_v2i16:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_clause 0x1
+; GFX11-NEXT:    s_load_b128 s[4:7], s[0:1], 0x24
+; GFX11-NEXT:    s_load_b64 s[0:1], s[0:1], 0x34
+; GFX11-NEXT:    v_mov_b32_e32 v0, 0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    s_load_b32 s2, s[6:7], 0x0
+; GFX11-NEXT:    s_load_b32 s0, s[0:1], 0x0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    v_pk_add_u16 v1, s2, s0
+; GFX11-NEXT:    global_store_b32 v0, v1, s[4:5]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %a = load <2 x i16>, <2 x i16> addrspace(4)* %in0
   %b = load <2 x i16>, <2 x i16> addrspace(4)* %in1
   %add = add <2 x i16> %a, %b
@@ -141,44 +165,54 @@ define amdgpu_kernel void @s_test_add_self_v2i16(<2 x i16> addrspace(1)* %out, <
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    s_load_dword s4, s[2:3], 0x0
-; VI-NEXT:    s_mov_b32 s3, 0xf000
-; VI-NEXT:    s_mov_b32 s2, -1
+; VI-NEXT:    s_load_dword s2, s[2:3], 0x0
+; VI-NEXT:    v_mov_b32_e32 v0, s0
+; VI-NEXT:    v_mov_b32_e32 v1, s1
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    s_lshr_b32 s5, s4, 16
-; VI-NEXT:    s_and_b32 s4, s4, 0xffff
-; VI-NEXT:    s_add_i32 s4, s4, s4
-; VI-NEXT:    s_add_i32 s5, s5, s5
-; VI-NEXT:    s_lshl_b32 s5, s5, 16
-; VI-NEXT:    s_and_b32 s4, s4, 0xffff
-; VI-NEXT:    s_or_b32 s4, s4, s5
-; VI-NEXT:    v_mov_b32_e32 v0, s4
-; VI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; VI-NEXT:    s_lshr_b32 s0, s2, 16
+; VI-NEXT:    s_and_b32 s1, s2, 0xffff
+; VI-NEXT:    s_add_i32 s1, s1, s1
+; VI-NEXT:    s_add_i32 s0, s0, s0
+; VI-NEXT:    s_lshl_b32 s0, s0, 16
+; VI-NEXT:    s_and_b32 s1, s1, 0xffff
+; VI-NEXT:    s_or_b32 s0, s1, s0
+; VI-NEXT:    v_mov_b32_e32 v2, s0
+; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: s_test_add_self_v2i16:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
+; GFX9-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9-NEXT:    s_load_dword s4, s[2:3], 0x0
-; GFX9-NEXT:    s_mov_b32 s3, 0xf000
-; GFX9-NEXT:    s_mov_b32 s2, -1
+; GFX9-NEXT:    s_load_dword s2, s[2:3], 0x0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9-NEXT:    v_pk_add_u16 v0, s4, s4
-; GFX9-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX9-NEXT:    v_pk_add_u16 v1, s2, s2
+; GFX9-NEXT:    global_store_dword v0, v1, s[0:1]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: s_test_add_self_v2i16:
 ; GFX10:       ; %bb.0:
 ; GFX10-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
+; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    s_load_dword s2, s[2:3], 0x0
-; GFX10-NEXT:    s_mov_b32 s3, 0x31016000
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX10-NEXT:    v_pk_add_u16 v0, s2, s2
-; GFX10-NEXT:    s_mov_b32 s2, -1
-; GFX10-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX10-NEXT:    v_pk_add_u16 v1, s2, s2
+; GFX10-NEXT:    global_store_dword v0, v1, s[0:1]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: s_test_add_self_v2i16:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_load_b128 s[0:3], s[0:1], 0x24
+; GFX11-NEXT:    v_mov_b32_e32 v0, 0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    s_load_b32 s2, s[2:3], 0x0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    v_pk_add_u16 v1, s2, s2
+; GFX11-NEXT:    global_store_b32 v0, v1, s[0:1]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %a = load <2 x i16>, <2 x i16> addrspace(4)* %in0
   %add = add <2 x i16> %a, %a
   store <2 x i16> %add, <2 x i16> addrspace(1)* %out
@@ -190,46 +224,48 @@ define amdgpu_kernel void @s_test_add_v2i16_kernarg(<2 x i16> addrspace(1)* %out
 ; VI-LABEL: s_test_add_v2i16_kernarg:
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
-; VI-NEXT:    s_mov_b32 s7, 0xf000
-; VI-NEXT:    s_mov_b32 s6, -1
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
-; VI-NEXT:    s_mov_b32 s4, s0
-; VI-NEXT:    s_mov_b32 s5, s1
-; VI-NEXT:    s_lshr_b32 s0, s2, 16
-; VI-NEXT:    s_lshr_b32 s1, s3, 16
-; VI-NEXT:    s_add_i32 s0, s0, s1
-; VI-NEXT:    s_add_i32 s1, s2, s3
-; VI-NEXT:    s_lshl_b32 s0, s0, 16
-; VI-NEXT:    s_and_b32 s1, s1, 0xffff
-; VI-NEXT:    s_or_b32 s0, s1, s0
+; VI-NEXT:    s_lshr_b32 s4, s2, 16
+; VI-NEXT:    s_lshr_b32 s5, s3, 16
+; VI-NEXT:    s_add_i32 s2, s2, s3
+; VI-NEXT:    s_add_i32 s4, s4, s5
+; VI-NEXT:    s_and_b32 s2, s2, 0xffff
+; VI-NEXT:    s_lshl_b32 s3, s4, 16
+; VI-NEXT:    s_or_b32 s2, s2, s3
 ; VI-NEXT:    v_mov_b32_e32 v0, s0
-; VI-NEXT:    buffer_store_dword v0, off, s[4:7], 0
+; VI-NEXT:    v_mov_b32_e32 v1, s1
+; VI-NEXT:    v_mov_b32_e32 v2, s2
+; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: s_test_add_v2i16_kernarg:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
-; GFX9-NEXT:    s_mov_b32 s7, 0xf000
-; GFX9-NEXT:    s_mov_b32 s6, -1
+; GFX9-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9-NEXT:    v_mov_b32_e32 v0, s3
-; GFX9-NEXT:    s_mov_b32 s4, s0
-; GFX9-NEXT:    s_mov_b32 s5, s1
-; GFX9-NEXT:    v_pk_add_u16 v0, s2, v0
-; GFX9-NEXT:    buffer_store_dword v0, off, s[4:7], 0
+; GFX9-NEXT:    v_mov_b32_e32 v1, s3
+; GFX9-NEXT:    v_pk_add_u16 v1, s2, v1
+; GFX9-NEXT:    global_store_dword v0, v1, s[0:1]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: s_test_add_v2i16_kernarg:
 ; GFX10:       ; %bb.0:
 ; GFX10-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
-; GFX10-NEXT:    s_mov_b32 s7, 0x31016000
-; GFX10-NEXT:    s_mov_b32 s6, -1
+; GFX10-NEXT:    v_mov_b32_e32 v0, 0
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX10-NEXT:    v_pk_add_u16 v0, s2, s3
-; GFX10-NEXT:    s_mov_b32 s4, s0
-; GFX10-NEXT:    s_mov_b32 s5, s1
-; GFX10-NEXT:    buffer_store_dword v0, off, s[4:7], 0
+; GFX10-NEXT:    v_pk_add_u16 v1, s2, s3
+; GFX10-NEXT:    global_store_dword v0, v1, s[0:1]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: s_test_add_v2i16_kernarg:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_load_b128 s[0:3], s[0:1], 0x24
+; GFX11-NEXT:    v_mov_b32_e32 v0, 0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    v_pk_add_u16 v1, s2, s3
+; GFX11-NEXT:    global_store_b32 v0, v1, s[0:1]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %add = add <2 x i16> %a, %b
   store <2 x i16> %add, <2 x i16> addrspace(1)* %out
   ret void
@@ -241,48 +277,57 @@ define amdgpu_kernel void @v_test_add_v2i16_constant(<2 x i16> addrspace(1)* %ou
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; VI-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; VI-NEXT:    v_mov_b32_e32 v3, 0x1c8
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
 ; VI-NEXT:    v_mov_b32_e32 v1, s3
 ; VI-NEXT:    v_add_u32_e32 v0, vcc, s2, v0
 ; VI-NEXT:    v_addc_u32_e32 v1, vcc, 0, v1, vcc
-; VI-NEXT:    flat_load_dword v0, v[0:1] glc
+; VI-NEXT:    flat_load_dword v2, v[0:1] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
-; VI-NEXT:    v_mov_b32_e32 v1, 0x1c8
-; VI-NEXT:    s_mov_b32 s3, 0xf000
-; VI-NEXT:    s_mov_b32 s2, -1
-; VI-NEXT:    v_add_u16_e32 v2, 0x7b, v0
-; VI-NEXT:    v_add_u16_sdwa v0, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
-; VI-NEXT:    v_or_b32_e32 v0, v2, v0
-; VI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; VI-NEXT:    v_mov_b32_e32 v0, s0
+; VI-NEXT:    v_mov_b32_e32 v1, s1
+; VI-NEXT:    v_add_u16_e32 v4, 0x7b, v2
+; VI-NEXT:    v_add_u16_sdwa v2, v2, v3 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
+; VI-NEXT:    v_or_b32_e32 v2, v4, v2
+; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_test_add_v2i16_constant:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
-; GFX9-NEXT:    s_mov_b32 s4, 0x1c8007b
+; GFX9-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dword v0, v0, s[2:3] glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    s_mov_b32 s3, 0xf000
-; GFX9-NEXT:    s_mov_b32 s2, -1
-; GFX9-NEXT:    v_pk_add_u16 v0, v0, s4
-; GFX9-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX9-NEXT:    s_mov_b32 s2, 0x1c8007b
+; GFX9-NEXT:    v_pk_add_u16 v0, v0, s2
+; GFX9-NEXT:    global_store_dword v1, v0, s[0:1]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: v_test_add_v2i16_constant:
 ; GFX10:       ; %bb.0:
 ; GFX10-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; GFX10-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX10-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    global_load_dword v0, v0, s[2:3] glc dlc
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
-; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
-; GFX10-NEXT:    s_mov_b32 s3, 0x31016000
-; GFX10-NEXT:    s_mov_b32 s2, -1
 ; GFX10-NEXT:    v_pk_add_u16 v0, 0x1c8007b, v0
-; GFX10-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX10-NEXT:    global_store_dword v1, v0, s[0:1]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: v_test_add_v2i16_constant:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_load_b128 s[0:3], s[0:1], 0x24
+; GFX11-NEXT:    v_dual_mov_b32 v1, 0 :: v_dual_lshlrev_b32 v0, 2, v0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    global_load_b32 v0, v0, s[2:3] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    v_pk_add_u16 v0, 0x1c8007b, v0
+; GFX11-NEXT:    global_store_b32 v1, v0, s[0:1]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i32 %tid
   %gep.in0 = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in0, i32 %tid
@@ -298,48 +343,57 @@ define amdgpu_kernel void @v_test_add_v2i16_neg_constant(<2 x i16> addrspace(1)*
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; VI-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; VI-NEXT:    v_mov_b32_e32 v3, 0xfffffc21
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
 ; VI-NEXT:    v_mov_b32_e32 v1, s3
 ; VI-NEXT:    v_add_u32_e32 v0, vcc, s2, v0
 ; VI-NEXT:    v_addc_u32_e32 v1, vcc, 0, v1, vcc
-; VI-NEXT:    flat_load_dword v0, v[0:1] glc
+; VI-NEXT:    flat_load_dword v2, v[0:1] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
-; VI-NEXT:    v_mov_b32_e32 v1, 0xfffffc21
-; VI-NEXT:    s_mov_b32 s3, 0xf000
-; VI-NEXT:    s_mov_b32 s2, -1
-; VI-NEXT:    v_add_u16_e32 v2, 0xfcb3, v0
-; VI-NEXT:    v_add_u16_sdwa v0, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
-; VI-NEXT:    v_or_b32_e32 v0, v2, v0
-; VI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; VI-NEXT:    v_mov_b32_e32 v0, s0
+; VI-NEXT:    v_mov_b32_e32 v1, s1
+; VI-NEXT:    v_add_u16_e32 v4, 0xfcb3, v2
+; VI-NEXT:    v_add_u16_sdwa v2, v2, v3 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
+; VI-NEXT:    v_or_b32_e32 v2, v4, v2
+; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_test_add_v2i16_neg_constant:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
-; GFX9-NEXT:    s_mov_b32 s4, 0xfc21fcb3
+; GFX9-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dword v0, v0, s[2:3] glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    s_mov_b32 s3, 0xf000
-; GFX9-NEXT:    s_mov_b32 s2, -1
-; GFX9-NEXT:    v_pk_add_u16 v0, v0, s4
-; GFX9-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX9-NEXT:    s_mov_b32 s2, 0xfc21fcb3
+; GFX9-NEXT:    v_pk_add_u16 v0, v0, s2
+; GFX9-NEXT:    global_store_dword v1, v0, s[0:1]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: v_test_add_v2i16_neg_constant:
 ; GFX10:       ; %bb.0:
 ; GFX10-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; GFX10-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX10-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    global_load_dword v0, v0, s[2:3] glc dlc
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
-; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
-; GFX10-NEXT:    s_mov_b32 s3, 0x31016000
-; GFX10-NEXT:    s_mov_b32 s2, -1
 ; GFX10-NEXT:    v_pk_add_u16 v0, 0xfc21fcb3, v0
-; GFX10-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX10-NEXT:    global_store_dword v1, v0, s[0:1]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: v_test_add_v2i16_neg_constant:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_load_b128 s[0:3], s[0:1], 0x24
+; GFX11-NEXT:    v_dual_mov_b32 v1, 0 :: v_dual_lshlrev_b32 v0, 2, v0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    global_load_b32 v0, v0, s[2:3] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    v_pk_add_u16 v0, 0xfc21fcb3, v0
+; GFX11-NEXT:    global_store_b32 v1, v0, s[0:1]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i32 %tid
   %gep.in0 = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in0, i32 %tid
@@ -354,47 +408,56 @@ define amdgpu_kernel void @v_test_add_v2i16_inline_neg1(<2 x i16> addrspace(1)*
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; VI-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; VI-NEXT:    v_mov_b32_e32 v3, -1
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
 ; VI-NEXT:    v_mov_b32_e32 v1, s3
 ; VI-NEXT:    v_add_u32_e32 v0, vcc, s2, v0
 ; VI-NEXT:    v_addc_u32_e32 v1, vcc, 0, v1, vcc
-; VI-NEXT:    flat_load_dword v0, v[0:1] glc
+; VI-NEXT:    flat_load_dword v2, v[0:1] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
-; VI-NEXT:    v_mov_b32_e32 v1, -1
-; VI-NEXT:    s_mov_b32 s3, 0xf000
-; VI-NEXT:    s_mov_b32 s2, -1
-; VI-NEXT:    v_add_u16_e32 v2, -1, v0
-; VI-NEXT:    v_add_u16_sdwa v0, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
-; VI-NEXT:    v_or_b32_e32 v0, v2, v0
-; VI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; VI-NEXT:    v_mov_b32_e32 v0, s0
+; VI-NEXT:    v_mov_b32_e32 v1, s1
+; VI-NEXT:    v_add_u16_e32 v4, -1, v2
+; VI-NEXT:    v_add_u16_sdwa v2, v2, v3 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
+; VI-NEXT:    v_or_b32_e32 v2, v4, v2
+; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_test_add_v2i16_inline_neg1:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX9-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dword v0, v0, s[2:3] glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    s_mov_b32 s3, 0xf000
-; GFX9-NEXT:    s_mov_b32 s2, -1
 ; GFX9-NEXT:    v_pk_sub_u16 v0, v0, 1 op_sel_hi:[1,0]
-; GFX9-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX9-NEXT:    global_store_dword v1, v0, s[0:1]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: v_test_add_v2i16_inline_neg1:
 ; GFX10:       ; %bb.0:
 ; GFX10-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; GFX10-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX10-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    global_load_dword v0, v0, s[2:3] glc dlc
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
-; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
-; GFX10-NEXT:    s_mov_b32 s3, 0x31016000
-; GFX10-NEXT:    s_mov_b32 s2, -1
 ; GFX10-NEXT:    v_pk_sub_u16 v0, v0, 1 op_sel_hi:[1,0]
-; GFX10-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX10-NEXT:    global_store_dword v1, v0, s[0:1]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: v_test_add_v2i16_inline_neg1:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_load_b128 s[0:3], s[0:1], 0x24
+; GFX11-NEXT:    v_dual_mov_b32 v1, 0 :: v_dual_lshlrev_b32 v0, 2, v0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    global_load_b32 v0, v0, s[2:3] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    v_pk_sub_u16 v0, v0, 1 op_sel_hi:[1,0]
+; GFX11-NEXT:    global_store_b32 v1, v0, s[0:1]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i32 %tid
   %gep.in0 = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in0, i32 %tid
@@ -413,42 +476,51 @@ define amdgpu_kernel void @v_test_add_v2i16_inline_lo_zero_hi(<2 x i16> addrspac
 ; VI-NEXT:    v_mov_b32_e32 v1, s3
 ; VI-NEXT:    v_add_u32_e32 v0, vcc, s2, v0
 ; VI-NEXT:    v_addc_u32_e32 v1, vcc, 0, v1, vcc
-; VI-NEXT:    flat_load_dword v0, v[0:1] glc
+; VI-NEXT:    flat_load_dword v2, v[0:1] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
-; VI-NEXT:    s_mov_b32 s3, 0xf000
-; VI-NEXT:    s_mov_b32 s2, -1
-; VI-NEXT:    v_and_b32_e32 v1, 0xffff0000, v0
-; VI-NEXT:    v_add_u16_e32 v0, 32, v0
-; VI-NEXT:    v_or_b32_e32 v0, v0, v1
-; VI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; VI-NEXT:    v_mov_b32_e32 v0, s0
+; VI-NEXT:    v_mov_b32_e32 v1, s1
+; VI-NEXT:    v_and_b32_e32 v3, 0xffff0000, v2
+; VI-NEXT:    v_add_u16_e32 v2, 32, v2
+; VI-NEXT:    v_or_b32_e32 v2, v2, v3
+; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_test_add_v2i16_inline_lo_zero_hi:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX9-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dword v0, v0, s[2:3] glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    s_mov_b32 s3, 0xf000
-; GFX9-NEXT:    s_mov_b32 s2, -1
 ; GFX9-NEXT:    v_pk_add_u16 v0, v0, 32
-; GFX9-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX9-NEXT:    global_store_dword v1, v0, s[0:1]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: v_test_add_v2i16_inline_lo_zero_hi:
 ; GFX10:       ; %bb.0:
 ; GFX10-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; GFX10-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX10-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    global_load_dword v0, v0, s[2:3] glc dlc
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
-; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
-; GFX10-NEXT:    s_mov_b32 s3, 0x31016000
-; GFX10-NEXT:    s_mov_b32 s2, -1
 ; GFX10-NEXT:    v_pk_add_u16 v0, v0, 32
-; GFX10-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX10-NEXT:    global_store_dword v1, v0, s[0:1]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: v_test_add_v2i16_inline_lo_zero_hi:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_load_b128 s[0:3], s[0:1], 0x24
+; GFX11-NEXT:    v_dual_mov_b32 v1, 0 :: v_dual_lshlrev_b32 v0, 2, v0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    global_load_b32 v0, v0, s[2:3] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    v_pk_add_u16 v0, v0, 32
+; GFX11-NEXT:    global_store_b32 v1, v0, s[0:1]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i32 %tid
   %gep.in0 = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in0, i32 %tid
@@ -464,47 +536,56 @@ define amdgpu_kernel void @v_test_add_v2i16_inline_fp_split(<2 x i16> addrspace(
 ; VI:       ; %bb.0:
 ; VI-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; VI-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; VI-NEXT:    v_mov_b32_e32 v3, 0x3f80
 ; VI-NEXT:    s_waitcnt lgkmcnt(0)
 ; VI-NEXT:    v_mov_b32_e32 v1, s3
 ; VI-NEXT:    v_add_u32_e32 v0, vcc, s2, v0
 ; VI-NEXT:    v_addc_u32_e32 v1, vcc, 0, v1, vcc
-; VI-NEXT:    flat_load_dword v0, v[0:1] glc
+; VI-NEXT:    flat_load_dword v2, v[0:1] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
-; VI-NEXT:    v_mov_b32_e32 v1, 0x3f80
-; VI-NEXT:    s_mov_b32 s3, 0xf000
-; VI-NEXT:    s_mov_b32 s2, -1
-; VI-NEXT:    v_add_u16_sdwa v1, v0, v1 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
-; VI-NEXT:    v_or_b32_sdwa v0, v0, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
-; VI-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; VI-NEXT:    v_mov_b32_e32 v0, s0
+; VI-NEXT:    v_mov_b32_e32 v1, s1
+; VI-NEXT:    v_add_u16_sdwa v3, v2, v3 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD
+; VI-NEXT:    v_or_b32_sdwa v2, v2, v3 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
+; VI-NEXT:    flat_store_dword v[0:1], v2
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_test_add_v2i16_inline_fp_split:
 ; GFX9:       ; %bb.0:
 ; GFX9-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
-; GFX9-NEXT:    s_mov_b32 s4, 1.0
+; GFX9-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dword v0, v0, s[2:3] glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    s_mov_b32 s3, 0xf000
-; GFX9-NEXT:    s_mov_b32 s2, -1
-; GFX9-NEXT:    v_pk_add_u16 v0, v0, s4
-; GFX9-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX9-NEXT:    s_mov_b32 s2, 1.0
+; GFX9-NEXT:    v_pk_add_u16 v0, v0, s2
+; GFX9-NEXT:    global_store_dword v1, v0, s[0:1]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: v_test_add_v2i16_inline_fp_split:
 ; GFX10:       ; %bb.0:
 ; GFX10-NEXT:    s_load_dwordx4 s[0:3], s[0:1], 0x24
 ; GFX10-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX10-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    global_load_dword v0, v0, s[2:3] glc dlc
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
-; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
-; GFX10-NEXT:    s_mov_b32 s3, 0x31016000
-; GFX10-NEXT:    s_mov_b32 s2, -1
 ; GFX10-NEXT:    v_pk_add_u16 v0, 0x3f80, v0 op_sel:[1,0] op_sel_hi:[0,1]
-; GFX10-NEXT:    buffer_store_dword v0, off, s[0:3], 0
+; GFX10-NEXT:    global_store_dword v1, v0, s[0:1]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: v_test_add_v2i16_inline_fp_split:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_load_b128 s[0:3], s[0:1], 0x24
+; GFX11-NEXT:    v_dual_mov_b32 v1, 0 :: v_dual_lshlrev_b32 v0, 2, v0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    global_load_b32 v0, v0, s[2:3] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    v_pk_add_u16 v0, 0x3f80, v0 op_sel:[1,0] op_sel_hi:[0,1]
+; GFX11-NEXT:    global_store_b32 v1, v0, s[0:1]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.out = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %out, i32 %tid
   %gep.in0 = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in0, i32 %tid
@@ -528,15 +609,15 @@ define amdgpu_kernel void @v_test_add_v2i16_zext_to_v2i32(<2 x i32> addrspace(1)
 ; VI-NEXT:    v_mov_b32_e32 v3, s1
 ; VI-NEXT:    v_add_u32_e32 v2, vcc, s0, v2
 ; VI-NEXT:    v_addc_u32_e32 v3, vcc, 0, v3, vcc
-; VI-NEXT:    flat_load_dword v1, v[0:1] glc
+; VI-NEXT:    flat_load_dword v4, v[0:1] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
-; VI-NEXT:    flat_load_dword v2, v[2:3] glc
+; VI-NEXT:    flat_load_dword v3, v[2:3] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
-; VI-NEXT:    s_mov_b32 s7, 0xf000
-; VI-NEXT:    s_mov_b32 s6, -1
-; VI-NEXT:    v_add_u16_e32 v0, v1, v2
-; VI-NEXT:    v_add_u16_sdwa v1, v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
-; VI-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
+; VI-NEXT:    v_mov_b32_e32 v0, s4
+; VI-NEXT:    v_mov_b32_e32 v1, s5
+; VI-NEXT:    v_add_u16_e32 v2, v4, v3
+; VI-NEXT:    v_add_u16_sdwa v3, v4, v3 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; VI-NEXT:    flat_store_dwordx2 v[0:1], v[2:3]
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_test_add_v2i16_zext_to_v2i32:
@@ -544,17 +625,16 @@ define amdgpu_kernel void @v_test_add_v2i16_zext_to_v2i32(<2 x i32> addrspace(1)
 ; GFX9-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x24
 ; GFX9-NEXT:    s_load_dwordx2 s[2:3], s[0:1], 0x34
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX9-NEXT:    v_mov_b32_e32 v3, 0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dword v1, v0, s[6:7] glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
 ; GFX9-NEXT:    global_load_dword v2, v0, s[2:3] glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    s_mov_b32 s7, 0xf000
-; GFX9-NEXT:    s_mov_b32 s6, -1
 ; GFX9-NEXT:    v_pk_add_u16 v0, v1, v2
 ; GFX9-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
 ; GFX9-NEXT:    v_and_b32_e32 v0, 0xffff, v0
-; GFX9-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
+; GFX9-NEXT:    global_store_dwordx2 v3, v[0:1], s[4:5]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: v_test_add_v2i16_zext_to_v2i32:
@@ -568,14 +648,32 @@ define amdgpu_kernel void @v_test_add_v2i16_zext_to_v2i32(<2 x i32> addrspace(1)
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-NEXT:    global_load_dword v2, v0, s[2:3] glc dlc
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
-; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
-; GFX10-NEXT:    s_mov_b32 s7, 0x31016000
-; GFX10-NEXT:    s_mov_b32 s6, -1
 ; GFX10-NEXT:    v_pk_add_u16 v0, v1, v2
+; GFX10-NEXT:    v_mov_b32_e32 v2, 0
 ; GFX10-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
 ; GFX10-NEXT:    v_and_b32_e32 v0, 0xffff, v0
-; GFX10-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
+; GFX10-NEXT:    global_store_dwordx2 v2, v[0:1], s[4:5]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: v_test_add_v2i16_zext_to_v2i32:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_clause 0x1
+; GFX11-NEXT:    s_load_b128 s[4:7], s[0:1], 0x24
+; GFX11-NEXT:    s_load_b64 s[0:1], s[0:1], 0x34
+; GFX11-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX11-NEXT:    v_mov_b32_e32 v2, 0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    global_load_b32 v1, v0, s[6:7] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    global_load_b32 v0, v0, s[0:1] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    v_pk_add_u16 v0, v1, v0
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
+; GFX11-NEXT:    v_and_b32_e32 v0, 0xffff, v0
+; GFX11-NEXT:    global_store_b64 v2, v[0:1], s[4:5]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.out = getelementptr inbounds <2 x i32>, <2 x i32> addrspace(1)* %out, i32 %tid
   %gep.in0 = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in0, i32 %tid
@@ -602,17 +700,17 @@ define amdgpu_kernel void @v_test_add_v2i16_zext_to_v2i64(<2 x i64> addrspace(1)
 ; VI-NEXT:    v_mov_b32_e32 v3, s1
 ; VI-NEXT:    v_add_u32_e32 v2, vcc, s0, v2
 ; VI-NEXT:    v_addc_u32_e32 v3, vcc, 0, v3, vcc
-; VI-NEXT:    flat_load_dword v4, v[0:1] glc
+; VI-NEXT:    flat_load_dword v6, v[0:1] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
 ; VI-NEXT:    flat_load_dword v2, v[2:3] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
 ; VI-NEXT:    v_mov_b32_e32 v1, 0
-; VI-NEXT:    s_mov_b32 s7, 0xf000
-; VI-NEXT:    s_mov_b32 s6, -1
+; VI-NEXT:    v_mov_b32_e32 v4, s4
+; VI-NEXT:    v_mov_b32_e32 v5, s5
 ; VI-NEXT:    v_mov_b32_e32 v3, v1
-; VI-NEXT:    v_add_u16_e32 v0, v4, v2
-; VI-NEXT:    v_add_u16_sdwa v2, v4, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
-; VI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[4:7], 0
+; VI-NEXT:    v_add_u16_e32 v0, v6, v2
+; VI-NEXT:    v_add_u16_sdwa v2, v6, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; VI-NEXT:    flat_store_dwordx4 v[4:5], v[0:3]
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_test_add_v2i16_zext_to_v2i64:
@@ -626,13 +724,11 @@ define amdgpu_kernel void @v_test_add_v2i16_zext_to_v2i64(<2 x i64> addrspace(1)
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
 ; GFX9-NEXT:    global_load_dword v3, v0, s[2:3] glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    s_mov_b32 s7, 0xf000
-; GFX9-NEXT:    s_mov_b32 s6, -1
 ; GFX9-NEXT:    v_pk_add_u16 v0, v2, v3
 ; GFX9-NEXT:    v_alignbit_b32 v2, 0, v0, 16
 ; GFX9-NEXT:    v_and_b32_e32 v0, 0xffff, v0
 ; GFX9-NEXT:    v_mov_b32_e32 v3, v1
-; GFX9-NEXT:    buffer_store_dwordx4 v[0:3], off, s[4:7], 0
+; GFX9-NEXT:    global_store_dwordx4 v1, v[0:3], s[4:5]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: v_test_add_v2i16_zext_to_v2i64:
@@ -646,16 +742,33 @@ define amdgpu_kernel void @v_test_add_v2i16_zext_to_v2i64(<2 x i64> addrspace(1)
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-NEXT:    global_load_dword v2, v0, s[2:3] glc dlc
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
-; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
-; GFX10-NEXT:    s_mov_b32 s7, 0x31016000
-; GFX10-NEXT:    s_mov_b32 s6, -1
 ; GFX10-NEXT:    v_pk_add_u16 v0, v1, v2
 ; GFX10-NEXT:    v_mov_b32_e32 v1, 0
 ; GFX10-NEXT:    v_alignbit_b32 v2, 0, v0, 16
 ; GFX10-NEXT:    v_and_b32_e32 v0, 0xffff, v0
 ; GFX10-NEXT:    v_mov_b32_e32 v3, v1
-; GFX10-NEXT:    buffer_store_dwordx4 v[0:3], off, s[4:7], 0
+; GFX10-NEXT:    global_store_dwordx4 v1, v[0:3], s[4:5]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: v_test_add_v2i16_zext_to_v2i64:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_clause 0x1
+; GFX11-NEXT:    s_load_b128 s[4:7], s[0:1], 0x24
+; GFX11-NEXT:    s_load_b64 s[0:1], s[0:1], 0x34
+; GFX11-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    global_load_b32 v1, v0, s[6:7] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    global_load_b32 v0, v0, s[0:1] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    v_pk_add_u16 v0, v1, v0
+; GFX11-NEXT:    v_mov_b32_e32 v1, 0
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-NEXT:    v_alignbit_b32 v2, 0, v0, 16
+; GFX11-NEXT:    v_dual_mov_b32 v3, v1 :: v_dual_and_b32 v0, 0xffff, v0
+; GFX11-NEXT:    global_store_b128 v1, v[0:3], s[4:5]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.out = getelementptr inbounds <2 x i64>, <2 x i64> addrspace(1)* %out, i32 %tid
   %gep.in0 = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in0, i32 %tid
@@ -682,17 +795,17 @@ define amdgpu_kernel void @v_test_add_v2i16_sext_to_v2i32(<2 x i32> addrspace(1)
 ; VI-NEXT:    v_mov_b32_e32 v3, s1
 ; VI-NEXT:    v_add_u32_e32 v2, vcc, s0, v2
 ; VI-NEXT:    v_addc_u32_e32 v3, vcc, 0, v3, vcc
-; VI-NEXT:    flat_load_dword v0, v[0:1] glc
+; VI-NEXT:    flat_load_dword v4, v[0:1] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
-; VI-NEXT:    flat_load_dword v1, v[2:3] glc
+; VI-NEXT:    flat_load_dword v2, v[2:3] glc
 ; VI-NEXT:    s_waitcnt vmcnt(0)
-; VI-NEXT:    s_mov_b32 s7, 0xf000
-; VI-NEXT:    s_mov_b32 s6, -1
-; VI-NEXT:    v_add_u16_sdwa v2, v0, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
-; VI-NEXT:    v_add_u16_e32 v0, v0, v1
-; VI-NEXT:    v_bfe_i32 v0, v0, 0, 16
-; VI-NEXT:    v_bfe_i32 v1, v2, 0, 16
-; VI-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
+; VI-NEXT:    v_mov_b32_e32 v0, s4
+; VI-NEXT:    v_mov_b32_e32 v1, s5
+; VI-NEXT:    v_add_u16_sdwa v3, v4, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
+; VI-NEXT:    v_add_u16_e32 v2, v4, v2
+; VI-NEXT:    v_bfe_i32 v2, v2, 0, 16
+; VI-NEXT:    v_bfe_i32 v3, v3, 0, 16
+; VI-NEXT:    flat_store_dwordx2 v[0:1], v[2:3]
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_test_add_v2i16_sext_to_v2i32:
@@ -700,17 +813,16 @@ define amdgpu_kernel void @v_test_add_v2i16_sext_to_v2i32(<2 x i32> addrspace(1)
 ; GFX9-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x24
 ; GFX9-NEXT:    s_load_dwordx2 s[2:3], s[0:1], 0x34
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX9-NEXT:    v_mov_b32_e32 v3, 0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dword v1, v0, s[6:7] glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
 ; GFX9-NEXT:    global_load_dword v2, v0, s[2:3] glc
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    s_mov_b32 s7, 0xf000
-; GFX9-NEXT:    s_mov_b32 s6, -1
 ; GFX9-NEXT:    v_pk_add_u16 v0, v1, v2
 ; GFX9-NEXT:    v_ashrrev_i32_e32 v1, 16, v0
 ; GFX9-NEXT:    v_bfe_i32 v0, v0, 0, 16
-; GFX9-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
+; GFX9-NEXT:    global_store_dwordx2 v3, v[0:1], s[4:5]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: v_test_add_v2i16_sext_to_v2i32:
@@ -724,14 +836,32 @@ define amdgpu_kernel void @v_test_add_v2i16_sext_to_v2i32(<2 x i32> addrspace(1)
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-NEXT:    global_load_dword v2, v0, s[2:3] glc dlc
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
-; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
-; GFX10-NEXT:    s_mov_b32 s7, 0x31016000
-; GFX10-NEXT:    s_mov_b32 s6, -1
 ; GFX10-NEXT:    v_pk_add_u16 v0, v1, v2
+; GFX10-NEXT:    v_mov_b32_e32 v2, 0
 ; GFX10-NEXT:    v_ashrrev_i32_e32 v1, 16, v0
 ; GFX10-NEXT:    v_bfe_i32 v0, v0, 0, 16
-; GFX10-NEXT:    buffer_store_dwordx2 v[0:1], off, s[4:7], 0
+; GFX10-NEXT:    global_store_dwordx2 v2, v[0:1], s[4:5]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: v_test_add_v2i16_sext_to_v2i32:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_clause 0x1
+; GFX11-NEXT:    s_load_b128 s[4:7], s[0:1], 0x24
+; GFX11-NEXT:    s_load_b64 s[0:1], s[0:1], 0x34
+; GFX11-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX11-NEXT:    v_mov_b32_e32 v2, 0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    global_load_b32 v1, v0, s[6:7] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    global_load_b32 v0, v0, s[0:1] glc dlc
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    v_pk_add_u16 v0, v1, v0
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-NEXT:    v_ashrrev_i32_e32 v1, 16, v0
+; GFX11-NEXT:    v_bfe_i32 v0, v0, 0, 16
+; GFX11-NEXT:    global_store_b64 v2, v[0:1], s[4:5]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.out = getelementptr inbounds <2 x i32>, <2 x i32> addrspace(1)* %out, i32 %tid
   %gep.in0 = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in0, i32 %tid
@@ -760,8 +890,8 @@ define amdgpu_kernel void @v_test_add_v2i16_sext_to_v2i64(<2 x i64> addrspace(1)
 ; VI-NEXT:    v_addc_u32_e32 v3, vcc, 0, v3, vcc
 ; VI-NEXT:    flat_load_dword v0, v[0:1]
 ; VI-NEXT:    flat_load_dword v1, v[2:3]
-; VI-NEXT:    s_mov_b32 s7, 0xf000
-; VI-NEXT:    s_mov_b32 s6, -1
+; VI-NEXT:    v_mov_b32_e32 v4, s4
+; VI-NEXT:    v_mov_b32_e32 v5, s5
 ; VI-NEXT:    s_waitcnt vmcnt(0)
 ; VI-NEXT:    v_add_u16_sdwa v2, v0, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1
 ; VI-NEXT:    v_add_u16_e32 v0, v0, v1
@@ -769,7 +899,7 @@ define amdgpu_kernel void @v_test_add_v2i16_sext_to_v2i64(<2 x i64> addrspace(1)
 ; VI-NEXT:    v_bfe_i32 v2, v2, 0, 16
 ; VI-NEXT:    v_ashrrev_i32_e32 v1, 31, v0
 ; VI-NEXT:    v_ashrrev_i32_e32 v3, 31, v2
-; VI-NEXT:    buffer_store_dwordx4 v[0:3], off, s[4:7], 0
+; VI-NEXT:    flat_store_dwordx4 v[4:5], v[0:3]
 ; VI-NEXT:    s_endpgm
 ;
 ; GFX9-LABEL: v_test_add_v2i16_sext_to_v2i64:
@@ -777,11 +907,10 @@ define amdgpu_kernel void @v_test_add_v2i16_sext_to_v2i64(<2 x i64> addrspace(1)
 ; GFX9-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x24
 ; GFX9-NEXT:    s_load_dwordx2 s[2:3], s[0:1], 0x34
 ; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX9-NEXT:    v_mov_b32_e32 v4, 0
 ; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX9-NEXT:    global_load_dword v1, v0, s[6:7]
 ; GFX9-NEXT:    global_load_dword v2, v0, s[2:3]
-; GFX9-NEXT:    s_mov_b32 s7, 0xf000
-; GFX9-NEXT:    s_mov_b32 s6, -1
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
 ; GFX9-NEXT:    v_pk_add_u16 v1, v1, v2
 ; GFX9-NEXT:    v_lshrrev_b32_e32 v2, 16, v1
@@ -789,7 +918,7 @@ define amdgpu_kernel void @v_test_add_v2i16_sext_to_v2i64(<2 x i64> addrspace(1)
 ; GFX9-NEXT:    v_bfe_i32 v2, v2, 0, 16
 ; GFX9-NEXT:    v_ashrrev_i32_e32 v1, 31, v0
 ; GFX9-NEXT:    v_ashrrev_i32_e32 v3, 31, v2
-; GFX9-NEXT:    buffer_store_dwordx4 v[0:3], off, s[4:7], 0
+; GFX9-NEXT:    global_store_dwordx4 v4, v[0:3], s[4:5]
 ; GFX9-NEXT:    s_endpgm
 ;
 ; GFX10-LABEL: v_test_add_v2i16_sext_to_v2i64:
@@ -798,13 +927,11 @@ define amdgpu_kernel void @v_test_add_v2i16_sext_to_v2i64(<2 x i64> addrspace(1)
 ; GFX10-NEXT:    s_load_dwordx4 s[4:7], s[0:1], 0x24
 ; GFX10-NEXT:    s_load_dwordx2 s[2:3], s[0:1], 0x34
 ; GFX10-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX10-NEXT:    v_mov_b32_e32 v4, 0
 ; GFX10-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX10-NEXT:    s_clause 0x1
 ; GFX10-NEXT:    global_load_dword v1, v0, s[6:7]
 ; GFX10-NEXT:    global_load_dword v2, v0, s[2:3]
-; GFX10-NEXT:    s_waitcnt_depctr 0xffe3
-; GFX10-NEXT:    s_mov_b32 s7, 0x31016000
-; GFX10-NEXT:    s_mov_b32 s6, -1
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-NEXT:    v_pk_add_u16 v0, v1, v2
 ; GFX10-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
@@ -812,8 +939,32 @@ define amdgpu_kernel void @v_test_add_v2i16_sext_to_v2i64(<2 x i64> addrspace(1)
 ; GFX10-NEXT:    v_bfe_i32 v2, v1, 0, 16
 ; GFX10-NEXT:    v_ashrrev_i32_e32 v1, 31, v0
 ; GFX10-NEXT:    v_ashrrev_i32_e32 v3, 31, v2
-; GFX10-NEXT:    buffer_store_dwordx4 v[0:3], off, s[4:7], 0
+; GFX10-NEXT:    global_store_dwordx4 v4, v[0:3], s[4:5]
 ; GFX10-NEXT:    s_endpgm
+;
+; GFX11-LABEL: v_test_add_v2i16_sext_to_v2i64:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_clause 0x1
+; GFX11-NEXT:    s_load_b128 s[4:7], s[0:1], 0x24
+; GFX11-NEXT:    s_load_b64 s[0:1], s[0:1], 0x34
+; GFX11-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX11-NEXT:    v_mov_b32_e32 v4, 0
+; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX11-NEXT:    s_clause 0x1
+; GFX11-NEXT:    global_load_b32 v1, v0, s[6:7]
+; GFX11-NEXT:    global_load_b32 v0, v0, s[0:1]
+; GFX11-NEXT:    s_waitcnt vmcnt(0)
+; GFX11-NEXT:    v_pk_add_u16 v0, v1, v0
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_2)
+; GFX11-NEXT:    v_lshrrev_b32_e32 v1, 16, v0
+; GFX11-NEXT:    v_bfe_i32 v0, v0, 0, 16
+; GFX11-NEXT:    v_bfe_i32 v2, v1, 0, 16
+; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-NEXT:    v_ashrrev_i32_e32 v1, 31, v0
+; GFX11-NEXT:    v_ashrrev_i32_e32 v3, 31, v2
+; GFX11-NEXT:    global_store_b128 v4, v[0:3], s[4:5]
+; GFX11-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX11-NEXT:    s_endpgm
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.out = getelementptr inbounds <2 x i64>, <2 x i64> addrspace(1)* %out, i32 %tid
   %gep.in0 = getelementptr inbounds <2 x i16>, <2 x i16> addrspace(1)* %in0, i32 %tid
diff --git a/llvm/test/CodeGen/AMDGPU/atomic_cmp_swap_local.ll b/llvm/test/CodeGen/AMDGPU/atomic_cmp_swap_local.ll
index dd32f9a35b0190..0c9248a7c0bab0 100644
--- a/llvm/test/CodeGen/AMDGPU/atomic_cmp_swap_local.ll
+++ b/llvm/test/CodeGen/AMDGPU/atomic_cmp_swap_local.ll
@@ -1,20 +1,22 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=SI,SICI,SICIVI,GCN %s
-; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=SICI,CIVI,SICIVI,GCN %s
-; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=CIVI,SICIVI,GFX89,GCN %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GFX9,GFX89,GCN %s
+; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefixes=SI,SICI,SICIVI,PREGFX11,GCN %s
+; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefixes=SICI,CIVI,SICIVI,PREGFX11,GCN %s
+; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=CIVI,SICIVI,GFX8PLUS,PREGFX11,GCN %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX9PLUS,GFX8PLUS,PREGFX11,GCN %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -amdgpu-enable-vopd=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11,GFX9PLUS,GFX8PLUS,GCN %s
 
 ; GCN-LABEL: {{^}}lds_atomic_cmpxchg_ret_i32_offset:
-; GFX9-NOT: m0
+; GFX9PLUS-NOT: m0
 ; SICIVI-DAG: s_mov_b32 m0
 
 ; SICI-DAG: s_load_dword [[PTR:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x13
 ; SICI-DAG: s_load_dword [[SWAP:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x1c
-; GFX89-DAG: s_load_dword [[PTR:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x4c
-; GFX89-DAG: s_load_dword [[SWAP:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x70
+; GFX8PLUS-DAG: s_load_{{dword|b32}} [[PTR:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x4c
+; GFX8PLUS-DAG: s_load_{{dword|b32}} [[SWAP:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x70
 ; GCN-DAG: v_mov_b32_e32 [[VCMP:v[0-9]+]], 7
 ; GCN-DAG: v_mov_b32_e32 [[VPTR:v[0-9]+]], [[PTR]]
 ; GCN-DAG: v_mov_b32_e32 [[VSWAP:v[0-9]+]], [[SWAP]]
-; GCN: ds_cmpst_rtn_b32 [[RESULT:v[0-9]+]], [[VPTR]], [[VCMP]], [[VSWAP]] offset:16
+; PREGFX11: ds_cmpst_rtn_b32 [[RESULT:v[0-9]+]], [[VPTR]], [[VCMP]], [[VSWAP]] offset:16
+; GFX11: ds_cmpstore_rtn_b32 [[RESULT:v[0-9]+]], [[VPTR]], [[VSWAP]], [[VCMP]] offset:16
 ; GCN: s_endpgm
 define amdgpu_kernel void @lds_atomic_cmpxchg_ret_i32_offset(i32 addrspace(1)* %out, [8 x i32], i32 addrspace(3)* %ptr, [8 x i32], i32 %swap) nounwind {
   %gep = getelementptr i32, i32 addrspace(3)* %ptr, i32 4
@@ -25,19 +27,20 @@ define amdgpu_kernel void @lds_atomic_cmpxchg_ret_i32_offset(i32 addrspace(1)* %
 }
 
 ; GCN-LABEL: {{^}}lds_atomic_cmpxchg_ret_i64_offset:
-; GFX9-NOT: m0
+; GFX9PLUS-NOT: m0
 ; SICIVI-DAG: s_mov_b32 m0
 
 ; SICI-DAG: s_load_dword [[PTR:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
 ; SICI-DAG: s_load_dwordx2 s[[[LOSWAP:[0-9]+]]:[[HISWAP:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}}, 0xd
-; GFX89-DAG: s_load_dword [[PTR:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x2c
-; GFX89-DAG: s_load_dwordx2 s[[[LOSWAP:[0-9]+]]:[[HISWAP:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}}, 0x34
+; GFX8PLUS-DAG: s_load_{{dword|b32}} [[PTR:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x2c
+; GFX8PLUS-DAG: s_load_{{dwordx2|b64}} s[[[LOSWAP:[0-9]+]]:[[HISWAP:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}}, 0x34
 ; GCN-DAG: v_mov_b32_e32 v[[LOVCMP:[0-9]+]], 7
 ; GCN-DAG: v_mov_b32_e32 v[[HIVCMP:[0-9]+]], 0
 ; GCN-DAG: v_mov_b32_e32 [[VPTR:v[0-9]+]], [[PTR]]
 ; GCN-DAG: v_mov_b32_e32 v[[LOSWAPV:[0-9]+]], s[[LOSWAP]]
 ; GCN-DAG: v_mov_b32_e32 v[[HISWAPV:[0-9]+]], s[[HISWAP]]
-; GCN: ds_cmpst_rtn_b64 [[RESULT:v\[[0-9]+:[0-9]+\]]], [[VPTR]], v[[[LOVCMP]]:[[HIVCMP]]], v[[[LOSWAPV]]:[[HISWAPV]]] offset:32
+; PREGFX11: ds_cmpst_rtn_b64 [[RESULT:v\[[0-9]+:[0-9]+\]]], [[VPTR]], v[[[LOVCMP]]:[[HIVCMP]]], v[[[LOSWAPV]]:[[HISWAPV]]] offset:32
+; GFX11: ds_cmpstore_rtn_b64 [[RESULT:v\[[0-9]+:[0-9]+\]]], [[VPTR]], v[[[LOSWAPV]]:[[HISWAPV]]], v[[[LOVCMP]]:[[HIVCMP]]] offset:32
 ; GCN: [[RESULT]]
 ; GCN: s_endpgm
 define amdgpu_kernel void @lds_atomic_cmpxchg_ret_i64_offset(i64 addrspace(1)* %out, i64 addrspace(3)* %ptr, i64 %swap) nounwind {
@@ -49,10 +52,10 @@ define amdgpu_kernel void @lds_atomic_cmpxchg_ret_i64_offset(i64 addrspace(1)* %
 }
 
 ; GCN-LABEL: {{^}}lds_atomic_cmpxchg_ret_i32_bad_si_offset
-; GFX9-NOT: m0
+; GFX9PLUS-NOT: m0
 ; SI: ds_cmpst_rtn_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; CIVI: ds_cmpst_rtn_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset:16
-; GFX9: ds_cmpst_rtn_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset:16
+; GFX9PLUS: ds_{{cmpst|cmpstore}}_rtn_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset:16
 ; GCN: s_endpgm
 define amdgpu_kernel void @lds_atomic_cmpxchg_ret_i32_bad_si_offset(i32 addrspace(1)* %out, i32 addrspace(3)* %ptr, i32 %swap, i32 %a, i32 %b) nounwind {
   %sub = sub i32 %a, %b
@@ -65,18 +68,19 @@ define amdgpu_kernel void @lds_atomic_cmpxchg_ret_i32_bad_si_offset(i32 addrspac
 }
 
 ; GCN-LABEL: {{^}}lds_atomic_cmpxchg_noret_i32_offset:
-; GFX9-NOT: m0
+; GFX9PLUS-NOT: m0
 ; SICIVI-DAG: s_mov_b32 m0
 
 
 ; SICI-DAG: s_load_dword [[PTR:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x9
 ; SICI-DAG: s_load_dword [[SWAP:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x12
-; GFX89-DAG: s_load_dword [[PTR:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x24
-; GFX89-DAG: s_load_dword [[SWAP:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x48
+; GFX8PLUS-DAG: s_load_{{dword|b32}} [[PTR:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x24
+; GFX8PLUS-DAG: s_load_{{dword|b32}} [[SWAP:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x48
 ; GCN-DAG: v_mov_b32_e32 [[VCMP:v[0-9]+]], 7
 ; GCN-DAG: v_mov_b32_e32 [[VPTR:v[0-9]+]], [[PTR]]
 ; GCN-DAG: v_mov_b32_e32 [[VSWAP:v[0-9]+]], [[SWAP]]
-; GCN: ds_cmpst_b32 [[VPTR]], [[VCMP]], [[VSWAP]] offset:16
+; PREGFX11: ds_cmpst_b32 [[VPTR]], [[VCMP]], [[VSWAP]] offset:16
+; GFX11: ds_cmpstore_b32 [[VPTR]], [[VSWAP]], [[VCMP]] offset:16
 ; GCN: s_endpgm
 define amdgpu_kernel void @lds_atomic_cmpxchg_noret_i32_offset(i32 addrspace(3)* %ptr, [8 x i32], i32 %swap) nounwind {
   %gep = getelementptr i32, i32 addrspace(3)* %ptr, i32 4
@@ -86,19 +90,20 @@ define amdgpu_kernel void @lds_atomic_cmpxchg_noret_i32_offset(i32 addrspace(3)*
 }
 
 ; GCN-LABEL: {{^}}lds_atomic_cmpxchg_noret_i64_offset:
-; GFX9-NOT: m0
+; GFX9PLUS-NOT: m0
 ; SICIVI-DAG: s_mov_b32 m0
 
 ; SICI-DAG: s_load_dword [[PTR:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x9
 ; SICI-DAG: s_load_dwordx2 s[[[LOSWAP:[0-9]+]]:[[HISWAP:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}}, 0xb
-; GFX89-DAG: s_load_dword [[PTR:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x24
-; GFX89-DAG: s_load_dwordx2 s[[[LOSWAP:[0-9]+]]:[[HISWAP:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}}, 0x2c
+; GFX8PLUS-DAG: s_load_{{dword|b32}} [[PTR:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, 0x24
+; GFX8PLUS-DAG: s_load_{{dwordx2|b64}} s[[[LOSWAP:[0-9]+]]:[[HISWAP:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}}, 0x2c
 ; GCN-DAG: v_mov_b32_e32 v[[LOVCMP:[0-9]+]], 7
 ; GCN-DAG: v_mov_b32_e32 v[[HIVCMP:[0-9]+]], 0
 ; GCN-DAG: v_mov_b32_e32 [[VPTR:v[0-9]+]], [[PTR]]
 ; GCN-DAG: v_mov_b32_e32 v[[LOSWAPV:[0-9]+]], s[[LOSWAP]]
 ; GCN-DAG: v_mov_b32_e32 v[[HISWAPV:[0-9]+]], s[[HISWAP]]
-; GCN: ds_cmpst_b64 [[VPTR]], v[[[LOVCMP]]:[[HIVCMP]]], v[[[LOSWAPV]]:[[HISWAPV]]] offset:32
+; PREGFX11: ds_cmpst_b64 [[VPTR]], v[[[LOVCMP]]:[[HIVCMP]]], v[[[LOSWAPV]]:[[HISWAPV]]] offset:32
+; GFX11: ds_cmpstore_b64 [[VPTR]], v[[[LOSWAPV]]:[[HISWAPV]]], v[[[LOVCMP]]:[[HIVCMP]]] offset:32
 ; GCN: s_endpgm
 define amdgpu_kernel void @lds_atomic_cmpxchg_noret_i64_offset(i64 addrspace(3)* %ptr, i64 %swap) nounwind {
   %gep = getelementptr i64, i64 addrspace(3)* %ptr, i32 4
diff --git a/llvm/test/CodeGen/AMDGPU/fdiv.f16.ll b/llvm/test/CodeGen/AMDGPU/fdiv.f16.ll
index fc6751bf5763c3..0cbed25036b3ae 100644
--- a/llvm/test/CodeGen/AMDGPU/fdiv.f16.ll
+++ b/llvm/test/CodeGen/AMDGPU/fdiv.f16.ll
@@ -1,8 +1,9 @@
-; RUN: llc -march=amdgcn -mcpu=tahiti -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
-; RUN: llc -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX8_9_10 %s
-; RUN: llc -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX8_9_10 %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX8_9_10 %s
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-flat-for-global -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX8_9_10 %s
+; RUN: llc -march=amdgcn -mcpu=tahiti -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SI %s
+; RUN: llc -march=amdgcn -mcpu=fiji -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8PLUS %s
+; RUN: llc -march=amdgcn -mcpu=fiji -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8PLUS %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8PLUS %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8PLUS %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8PLUS,GFX11 %s
 
 ; Make sure fdiv is promoted to f32.
 
@@ -22,17 +23,17 @@
 ; SI:     v_div_fixup_f32
 ; SI:     v_cvt_f16_f32
 
-; GFX8_9_10: {{flat|global}}_load_ushort [[LHS:v[0-9]+]]
-; GFX8_9_10: {{flat|global}}_load_ushort [[RHS:v[0-9]+]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[LHS:v[0-9]+]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[RHS:v[0-9]+]]
 
-; GFX8_9_10-DAG: v_cvt_f32_f16_e32 [[CVT_LHS:v[0-9]+]], [[LHS]]
-; GFX8_9_10-DAG: v_cvt_f32_f16_e32 [[CVT_RHS:v[0-9]+]], [[RHS]]
+; GFX8PLUS-DAG: v_cvt_f32_f16_e32 [[CVT_LHS:v[0-9]+]], [[LHS]]
+; GFX8PLUS-DAG: v_cvt_f32_f16_e32 [[CVT_RHS:v[0-9]+]], [[RHS]]
 
-; GFX8_9_10-DAG: v_rcp_f32_e32 [[RCP_RHS:v[0-9]+]], [[CVT_RHS]]
-; GFX8_9_10: v_mul_f32_e32 [[MUL:v[0-9]+]], [[CVT_LHS]], [[RCP_RHS]]
-; GFX8_9_10: v_cvt_f16_f32_e32 [[CVT_BACK:v[0-9]+]], [[MUL]]
-; GFX8_9_10: v_div_fixup_f16 [[RESULT:v[0-9]+]], [[CVT_BACK]], [[RHS]], [[LHS]]
-; GFX8_9_10: {{flat|global}}_store_short v{{.+}}, [[RESULT]]
+; GFX8PLUS-DAG: v_rcp_f32_e32 [[RCP_RHS:v[0-9]+]], [[CVT_RHS]]
+; GFX8PLUS: v_mul_f32_e32 [[MUL:v[0-9]+]], [[CVT_LHS]], [[RCP_RHS]]
+; GFX8PLUS: v_cvt_f16_f32_e32 [[CVT_BACK:v[0-9]+]], [[MUL]]
+; GFX8PLUS: v_div_fixup_f16 [[RESULT:v[0-9]+]], [[CVT_BACK]], [[RHS]], [[LHS]]
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.+}}, [[RESULT]]
 define amdgpu_kernel void @v_fdiv_f16(
     half addrspace(1)* %r,
     half addrspace(1)* %a,
@@ -51,11 +52,11 @@ entry:
 }
 
 ; GCN-LABEL: {{^}}v_rcp_f16:
-; GFX8_9_10: {{flat|global}}_load_ushort [[VAL:v[0-9]+]]
-; GFX8_9_10-NOT: [[VAL]]
-; GFX8_9_10: v_rcp_f16_e32 [[RESULT:v[0-9]+]], [[VAL]]
-; GFX8_9_10-NOT: [[RESULT]]
-; GFX8_9_10: {{flat|global}}_store_short v{{.+}}, [[RESULT]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[VAL:v[0-9]+]]
+; GFX8PLUS-NOT: [[VAL]]
+; GFX8PLUS: v_rcp_f16_e32 [[RESULT:v[0-9]+]], [[VAL]]
+; GFX8PLUS-NOT: [[RESULT]]
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.+}}, [[RESULT]]
 define amdgpu_kernel void @v_rcp_f16(half addrspace(1)* %r, half addrspace(1)* %b) #0 {
 entry:
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
@@ -69,11 +70,11 @@ entry:
 }
 
 ; GCN-LABEL: {{^}}v_rcp_f16_abs:
-; GFX8_9_10: {{flat|global}}_load_ushort [[VAL:v[0-9]+]]
-; GFX8_9_10-NOT: [[VAL]]
-; GFX8_9_10: v_rcp_f16_e64 [[RESULT:v[0-9]+]], |[[VAL]]|
-; GFX8_9_10-NOT: [RESULT]]
-; GFX8_9_10: {{flat|global}}_store_short v{{.+}}, [[RESULT]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[VAL:v[0-9]+]]
+; GFX8PLUS-NOT: [[VAL]]
+; GFX8PLUS: v_rcp_f16_e64 [[RESULT:v[0-9]+]], |[[VAL]]|
+; GFX8PLUS-NOT: [RESULT]]
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.+}}, [[RESULT]]
 define amdgpu_kernel void @v_rcp_f16_abs(half addrspace(1)* %r, half addrspace(1)* %b) #0 {
 entry:
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
@@ -90,12 +91,12 @@ entry:
 ; We could not do 1/b -> rcp_f16(b) under !fpmath < 1ulp.
 
 ; GCN-LABEL: {{^}}reciprocal_f16_rounded:
-; GFX8_9_10: {{flat|global}}_load_ushort [[VAL16:v[0-9]+]], v{{.+}}
-; GFX8_9_10: v_cvt_f32_f16_e32 [[CVT_TO32:v[0-9]+]], [[VAL16]]
-; GFX8_9_10: v_rcp_f32_e32 [[RCP32:v[0-9]+]], [[CVT_TO32]]
-; GFX8_9_10: v_cvt_f16_f32_e32 [[CVT_BACK16:v[0-9]+]], [[RCP32]]
-; GFX8_9_10: v_div_fixup_f16 [[RESULT:v[0-9]+]], [[CVT_BACK16]], [[VAL16]], 1.0
-; GFX8_9_10: {{flat|global}}_store_short v{{.+}}, [[RESULT]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[VAL16:v[0-9]+]], v{{.+}}
+; GFX8PLUS: v_cvt_f32_f16_e32 [[CVT_TO32:v[0-9]+]], [[VAL16]]
+; GFX8PLUS: v_rcp_f32_e32 [[RCP32:v[0-9]+]], [[CVT_TO32]]
+; GFX8PLUS: v_cvt_f16_f32_e32 [[CVT_BACK16:v[0-9]+]], [[RCP32]]
+; GFX8PLUS: v_div_fixup_f16 [[RESULT:v[0-9]+]], [[CVT_BACK16]], [[VAL16]], 1.0
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.+}}, [[RESULT]]
 define amdgpu_kernel void @reciprocal_f16_rounded(half addrspace(1)* %r, half addrspace(1)* %b) #0 {
 entry:
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
@@ -109,11 +110,11 @@ entry:
 }
 
 ; GCN-LABEL: {{^}}v_rcp_f16_afn:
-; GFX8_9_10: {{flat|global}}_load_ushort [[VAL:v[0-9]+]]
-; GFX8_9_10-NOT: [[VAL]]
-; GFX8_9_10: v_rcp_f16_e32 [[RESULT:v[0-9]+]], [[VAL]]
-; GFX8_9_10-NOT: [[RESULT]]
-; GFX8_9_10: {{flat|global}}_store_short v{{.+}}, [[RESULT]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[VAL:v[0-9]+]]
+; GFX8PLUS-NOT: [[VAL]]
+; GFX8PLUS: v_rcp_f16_e32 [[RESULT:v[0-9]+]], [[VAL]]
+; GFX8PLUS-NOT: [[RESULT]]
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.+}}, [[RESULT]]
 define amdgpu_kernel void @v_rcp_f16_afn(half addrspace(1)* %r, half addrspace(1)* %b) #0 {
 entry:
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
@@ -127,11 +128,11 @@ entry:
 }
 
 ; GCN-LABEL: {{^}}v_rcp_f16_neg:
-; GFX8_9_10: {{flat|global}}_load_ushort [[VAL:v[0-9]+]]
-; GFX8_9_10-NOT: [[VAL]]
-; GFX8_9_10: v_rcp_f16_e64 [[RESULT:v[0-9]+]], -[[VAL]]
-; GFX8_9_10-NOT: [RESULT]]
-; GFX8_9_10: {{flat|global}}_store_short v{{.+}}, [[RESULT]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[VAL:v[0-9]+]]
+; GFX8PLUS-NOT: [[VAL]]
+; GFX8PLUS: v_rcp_f16_e64 [[RESULT:v[0-9]+]], -[[VAL]]
+; GFX8PLUS-NOT: [RESULT]]
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.+}}, [[RESULT]]
 define amdgpu_kernel void @v_rcp_f16_neg(half addrspace(1)* %r, half addrspace(1)* %b) #0 {
 entry:
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
@@ -145,11 +146,11 @@ entry:
 }
 
 ; GCN-LABEL: {{^}}v_rsq_f16:
-; GFX8_9_10: {{flat|global}}_load_ushort [[VAL:v[0-9]+]]
-; GFX8_9_10-NOT: [[VAL]]
-; GFX8_9_10: v_rsq_f16_e32 [[RESULT:v[0-9]+]], [[VAL]]
-; GFX8_9_10-NOT: [RESULT]]
-; GFX8_9_10: {{flat|global}}_store_short v{{.+}}, [[RESULT]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[VAL:v[0-9]+]]
+; GFX8PLUS-NOT: [[VAL]]
+; GFX8PLUS: v_rsq_f16_e32 [[RESULT:v[0-9]+]], [[VAL]]
+; GFX8PLUS-NOT: [RESULT]]
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.+}}, [[RESULT]]
 define amdgpu_kernel void @v_rsq_f16(half addrspace(1)* %r, half addrspace(1)* %b) #0 {
 entry:
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
@@ -164,12 +165,13 @@ entry:
 }
 
 ; GCN-LABEL: {{^}}v_rsq_f16_neg:
-; GFX8_9_10: {{flat|global}}_load_ushort [[VAL:v[0-9]+]]
-; GFX8_9_10-NOT: [[VAL]]
-; GFX8_9_10: v_sqrt_f16_e32 [[SQRT:v[0-9]+]], [[VAL]]
-; GFX8_9_10-NEXT: v_rcp_f16_e64 [[RESULT:v[0-9]+]], -[[SQRT]]
-; GFX8_9_10-NOT: [RESULT]]
-; GFX8_9_10: {{flat|global}}_store_short v{{.+}}, [[RESULT]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[VAL:v[0-9]+]]
+; GFX8PLUS-NOT: [[VAL]]
+; GFX8PLUS: v_sqrt_f16_e32 [[SQRT:v[0-9]+]], [[VAL]]
+; GFX11-NEXT: s_waitcnt_depctr 0xfff
+; GFX8PLUS-NEXT: v_rcp_f16_e64 [[RESULT:v[0-9]+]], -[[SQRT]]
+; GFX8PLUS-NOT: [RESULT]]
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.+}}, [[RESULT]]
 define amdgpu_kernel void @v_rsq_f16_neg(half addrspace(1)* %r, half addrspace(1)* %b) #0 {
 entry:
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
@@ -184,13 +186,13 @@ entry:
 }
 
 ; GCN-LABEL: {{^}}v_fdiv_f16_afn:
-; GFX8_9_10: {{flat|global}}_load_ushort [[LHS:v[0-9]+]]
-; GFX8_9_10: {{flat|global}}_load_ushort [[RHS:v[0-9]+]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[LHS:v[0-9]+]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[RHS:v[0-9]+]]
 
-; GFX8_9_10: v_rcp_f16_e32 [[RCP:v[0-9]+]], [[RHS]]
-; GFX8_9_10: v_mul_f16_e32 [[RESULT:v[0-9]+]], [[LHS]], [[RCP]]
+; GFX8PLUS: v_rcp_f16_e32 [[RCP:v[0-9]+]], [[RHS]]
+; GFX8PLUS: v_mul_f16_e32 [[RESULT:v[0-9]+]], [[LHS]], [[RCP]]
 
-; GFX8_9_10: {{flat|global}}_store_short v{{.+}}, [[RESULT]]
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.+}}, [[RESULT]]
 define amdgpu_kernel void @v_fdiv_f16_afn(half addrspace(1)* %r, half addrspace(1)* %a, half addrspace(1)* %b) #0 {
 entry:
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
@@ -206,13 +208,13 @@ entry:
 }
 
 ; GCN-LABEL: {{^}}v_fdiv_f16_unsafe:
-; GFX8_9_10: {{flat|global}}_load_ushort [[LHS:v[0-9]+]]
-; GFX8_9_10: {{flat|global}}_load_ushort [[RHS:v[0-9]+]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[LHS:v[0-9]+]]
+; GFX8PLUS: {{flat|global}}_load_{{ushort|u16}} [[RHS:v[0-9]+]]
 
-; GFX8_9_10: v_rcp_f16_e32 [[RCP:v[0-9]+]], [[RHS]]
-; GFX8_9_10: v_mul_f16_e32 [[RESULT:v[0-9]+]], [[LHS]], [[RCP]]
+; GFX8PLUS: v_rcp_f16_e32 [[RCP:v[0-9]+]], [[RHS]]
+; GFX8PLUS: v_mul_f16_e32 [[RESULT:v[0-9]+]], [[LHS]], [[RCP]]
 
-; GFX8_9_10: {{flat|global}}_store_short v{{.+}}, [[RESULT]]
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.+}}, [[RESULT]]
 define amdgpu_kernel void @v_fdiv_f16_unsafe(half addrspace(1)* %r, half addrspace(1)* %a, half addrspace(1)* %b) #2 {
 entry:
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
@@ -227,11 +229,11 @@ entry:
   ret void
 }
 
-; SI-LABEL: {{^}}div_afn_2_x_pat_f16:
+; GCN-LABEL: {{^}}div_afn_2_x_pat_f16:
 ; SI: v_mul_f32_e32 v{{[0-9]+}}, 0.5, v{{[0-9]+}}
 
-; GFX8_9_10: v_mul_f16_e32 [[MUL:v[0-9]+]], 0.5, v{{[0-9]+}}
-; GFX8_9_10: buffer_store_short [[MUL]]
+; GFX8PLUS: v_mul_f16_e32 [[MUL:v[0-9]+]], 0.5, v{{[0-9]+}}
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.*}}, [[MUL]]
 define amdgpu_kernel void @div_afn_2_x_pat_f16(half addrspace(1)* %out) #0 {
   %x = load half, half addrspace(1)* undef
   %rcp = fdiv afn half %x, 2.0
@@ -239,11 +241,11 @@ define amdgpu_kernel void @div_afn_2_x_pat_f16(half addrspace(1)* %out) #0 {
   ret void
 }
 
-; SI-LABEL: {{^}}div_afn_k_x_pat_f16:
+; GCN-LABEL: {{^}}div_afn_k_x_pat_f16:
 ; SI: v_mul_f32_e32 v{{[0-9]+}}, 0x3dcccccd, v{{[0-9]+}}
 
-; GFX8_9_10: v_mul_f16_e32 [[MUL:v[0-9]+]], 0x2e66, v{{[0-9]+}}
-; GFX8_9_10: buffer_store_short [[MUL]]
+; GFX8PLUS: v_mul_f16_e32 [[MUL:v[0-9]+]], 0x2e66, v{{[0-9]+}}
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.*}}, [[MUL]]
 define amdgpu_kernel void @div_afn_k_x_pat_f16(half addrspace(1)* %out) #0 {
   %x = load half, half addrspace(1)* undef
   %rcp = fdiv afn half %x, 10.0
@@ -251,11 +253,11 @@ define amdgpu_kernel void @div_afn_k_x_pat_f16(half addrspace(1)* %out) #0 {
   ret void
 }
 
-; SI-LABEL: {{^}}div_afn_neg_k_x_pat_f16:
+; GCN-LABEL: {{^}}div_afn_neg_k_x_pat_f16:
 ; SI: v_mul_f32_e32 v{{[0-9]+}}, 0xbdcccccd, v{{[0-9]+}}
 
-; GFX8_9_10: v_mul_f16_e32 [[MUL:v[0-9]+]], 0xae66, v{{[0-9]+}}
-; GFX8_9_10: buffer_store_short [[MUL]]
+; GFX8PLUS: v_mul_f16_e32 [[MUL:v[0-9]+]], 0xae66, v{{[0-9]+}}
+; GFX8PLUS: {{flat|global}}_store_{{short|b16}} v{{.*}}, [[MUL]]
 define amdgpu_kernel void @div_afn_neg_k_x_pat_f16(half addrspace(1)* %out) #0 {
   %x = load half, half addrspace(1)* undef
   %rcp = fdiv afn half %x, -10.0
diff --git a/llvm/test/CodeGen/AMDGPU/flat-address-space.ll b/llvm/test/CodeGen/AMDGPU/flat-address-space.ll
index 63339529ad0fbb..22ccf1f412905b 100644
--- a/llvm/test/CodeGen/AMDGPU/flat-address-space.ll
+++ b/llvm/test/CodeGen/AMDGPU/flat-address-space.ll
@@ -1,41 +1,42 @@
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=bonaire < %s | FileCheck -check-prefixes=CHECK,CIVI %s
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefixes=CHECK,CIVI %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -mattr=-flat-for-global < %s | FileCheck -check-prefixes=CHECK,CIVI,CIVI-HSA %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-flat-for-global < %s | FileCheck -check-prefixes=CHECK,GFX9 %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -mattr=-flat-for-global < %s | FileCheck -check-prefixes=CHECK,GFX10 %s
-
-; CHECK-LABEL: {{^}}store_flat_i32:
-; CHECK-DAG: s_load_dwordx2 s[[[LO_SREG:[0-9]+]]:[[HI_SREG:[0-9]+]]],
-; CHECK-DAG: s_load_dword s[[SDATA:[0-9]+]],
-; CHECK: s_waitcnt lgkmcnt(0)
-; CHECK-DAG: v_mov_b32_e32 v[[DATA:[0-9]+]], s[[SDATA]]
-; CHECK-DAG: v_mov_b32_e32 v[[LO_VREG:[0-9]+]], s[[LO_SREG]]
-; CHECK-DAG: v_mov_b32_e32 v[[HI_VREG:[0-9]+]], s[[HI_SREG]]
-; CHECK: flat_store_dword v[[[LO_VREG]]:[[HI_VREG]]], v[[DATA]]
+; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=bonaire < %s | FileCheck -check-prefixes=GCN,CIVI %s
+; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tonga < %s | FileCheck -check-prefixes=GCN,CIVI %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji < %s | FileCheck -check-prefixes=GCN,CIVI,CIVI-HSA %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN,GFX9 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 < %s | FileCheck -check-prefixes=GCN,GFX10PLUS %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -amdgpu-enable-vopd=0 < %s | FileCheck -check-prefixes=GCN,GFX10PLUS,GFX11 %s
+
+; GCN-LABEL: {{^}}store_flat_i32:
+; GCN-DAG: s_load_{{dwordx2|b64}} s[[[LO_SREG:[0-9]+]]:[[HI_SREG:[0-9]+]]],
+; GCN-DAG: s_load_{{dword|b32}} s[[SDATA:[0-9]+]],
+; GCN: s_waitcnt lgkmcnt(0)
+; GCN-DAG: v_mov_b32_e32 v[[DATA:[0-9]+]], s[[SDATA]]
+; GCN-DAG: v_mov_b32_e32 v[[LO_VREG:[0-9]+]], s[[LO_SREG]]
+; GCN-DAG: v_mov_b32_e32 v[[HI_VREG:[0-9]+]], s[[HI_SREG]]
+; GCN: flat_store_{{dword|b32}} v[[[LO_VREG]]:[[HI_VREG]]], v[[DATA]]
 define amdgpu_kernel void @store_flat_i32(i32 addrspace(1)* %gptr, i32 %x) #0 {
   %fptr = addrspacecast i32 addrspace(1)* %gptr to i32*
   store volatile i32 %x, i32* %fptr, align 4
   ret void
 }
 
-; CHECK-LABEL: {{^}}store_flat_i64:
-; CHECK: flat_store_dwordx2
+; GCN-LABEL: {{^}}store_flat_i64:
+; GCN: flat_store_{{dwordx2|b64}}
 define amdgpu_kernel void @store_flat_i64(i64 addrspace(1)* %gptr, i64 %x) #0 {
   %fptr = addrspacecast i64 addrspace(1)* %gptr to i64*
   store volatile i64 %x, i64* %fptr, align 8
   ret void
 }
 
-; CHECK-LABEL: {{^}}store_flat_v4i32:
-; CHECK: flat_store_dwordx4
+; GCN-LABEL: {{^}}store_flat_v4i32:
+; GCN: flat_store_{{dwordx4|b128}}
 define amdgpu_kernel void @store_flat_v4i32(<4 x i32> addrspace(1)* %gptr, <4 x i32> %x) #0 {
   %fptr = addrspacecast <4 x i32> addrspace(1)* %gptr to <4 x i32>*
   store volatile <4 x i32> %x, <4 x i32>* %fptr, align 16
   ret void
 }
 
-; CHECK-LABEL: {{^}}store_flat_trunc_i16:
-; CHECK: flat_store_short
+; GCN-LABEL: {{^}}store_flat_trunc_i16:
+; GCN: flat_store_{{short|b16}}
 define amdgpu_kernel void @store_flat_trunc_i16(i16 addrspace(1)* %gptr, i32 %x) #0 {
   %fptr = addrspacecast i16 addrspace(1)* %gptr to i16*
   %y = trunc i32 %x to i16
@@ -43,8 +44,8 @@ define amdgpu_kernel void @store_flat_trunc_i16(i16 addrspace(1)* %gptr, i32 %x)
   ret void
 }
 
-; CHECK-LABEL: {{^}}store_flat_trunc_i8:
-; CHECK: flat_store_byte
+; GCN-LABEL: {{^}}store_flat_trunc_i8:
+; GCN: flat_store_{{byte|b8}}
 define amdgpu_kernel void @store_flat_trunc_i8(i8 addrspace(1)* %gptr, i32 %x) #0 {
   %fptr = addrspacecast i8 addrspace(1)* %gptr to i8*
   %y = trunc i32 %x to i8
@@ -54,8 +55,8 @@ define amdgpu_kernel void @store_flat_trunc_i8(i8 addrspace(1)* %gptr, i32 %x) #
 
 
 
-; CHECK-LABEL: load_flat_i32:
-; CHECK: flat_load_dword
+; GCN-LABEL: load_flat_i32:
+; GCN: flat_load_{{dword|b32}}
 define amdgpu_kernel void @load_flat_i32(i32 addrspace(1)* noalias %out, i32 addrspace(1)* noalias %gptr) #0 {
   %fptr = addrspacecast i32 addrspace(1)* %gptr to i32*
   %fload = load volatile i32, i32* %fptr, align 4
@@ -63,8 +64,8 @@ define amdgpu_kernel void @load_flat_i32(i32 addrspace(1)* noalias %out, i32 add
   ret void
 }
 
-; CHECK-LABEL: load_flat_i64:
-; CHECK: flat_load_dwordx2
+; GCN-LABEL: load_flat_i64:
+; GCN: flat_load_{{dwordx2|b64}}
 define amdgpu_kernel void @load_flat_i64(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %gptr) #0 {
   %fptr = addrspacecast i64 addrspace(1)* %gptr to i64*
   %fload = load volatile i64, i64* %fptr, align 8
@@ -72,8 +73,8 @@ define amdgpu_kernel void @load_flat_i64(i64 addrspace(1)* noalias %out, i64 add
   ret void
 }
 
-; CHECK-LABEL: load_flat_v4i32:
-; CHECK: flat_load_dwordx4
+; GCN-LABEL: load_flat_v4i32:
+; GCN: flat_load_{{dwordx4|b128}}
 define amdgpu_kernel void @load_flat_v4i32(<4 x i32> addrspace(1)* noalias %out, <4 x i32> addrspace(1)* noalias %gptr) #0 {
   %fptr = addrspacecast <4 x i32> addrspace(1)* %gptr to <4 x i32>*
   %fload = load volatile <4 x i32>, <4 x i32>* %fptr, align 32
@@ -81,8 +82,8 @@ define amdgpu_kernel void @load_flat_v4i32(<4 x i32> addrspace(1)* noalias %out,
   ret void
 }
 
-; CHECK-LABEL: sextload_flat_i8:
-; CHECK: flat_load_sbyte
+; GCN-LABEL: sextload_flat_i8:
+; GCN: flat_load_{{sbyte|i8}}
 define amdgpu_kernel void @sextload_flat_i8(i32 addrspace(1)* noalias %out, i8 addrspace(1)* noalias %gptr) #0 {
   %fptr = addrspacecast i8 addrspace(1)* %gptr to i8*
   %fload = load volatile i8, i8* %fptr, align 4
@@ -91,8 +92,8 @@ define amdgpu_kernel void @sextload_flat_i8(i32 addrspace(1)* noalias %out, i8 a
   ret void
 }
 
-; CHECK-LABEL: zextload_flat_i8:
-; CHECK: flat_load_ubyte
+; GCN-LABEL: zextload_flat_i8:
+; GCN: flat_load_{{ubyte|u8}}
 define amdgpu_kernel void @zextload_flat_i8(i32 addrspace(1)* noalias %out, i8 addrspace(1)* noalias %gptr) #0 {
   %fptr = addrspacecast i8 addrspace(1)* %gptr to i8*
   %fload = load volatile i8, i8* %fptr, align 4
@@ -101,8 +102,8 @@ define amdgpu_kernel void @zextload_flat_i8(i32 addrspace(1)* noalias %out, i8 a
   ret void
 }
 
-; CHECK-LABEL: sextload_flat_i16:
-; CHECK: flat_load_sshort
+; GCN-LABEL: sextload_flat_i16:
+; GCN: flat_load_{{sshort|i16}}
 define amdgpu_kernel void @sextload_flat_i16(i32 addrspace(1)* noalias %out, i16 addrspace(1)* noalias %gptr) #0 {
   %fptr = addrspacecast i16 addrspace(1)* %gptr to i16*
   %fload = load volatile i16, i16* %fptr, align 4
@@ -111,8 +112,8 @@ define amdgpu_kernel void @sextload_flat_i16(i32 addrspace(1)* noalias %out, i16
   ret void
 }
 
-; CHECK-LABEL: zextload_flat_i16:
-; CHECK: flat_load_ushort
+; GCN-LABEL: zextload_flat_i16:
+; GCN: flat_load_{{ushort|u16}}
 define amdgpu_kernel void @zextload_flat_i16(i32 addrspace(1)* noalias %out, i16 addrspace(1)* noalias %gptr) #0 {
   %fptr = addrspacecast i16 addrspace(1)* %gptr to i16*
   %fload = load volatile i16, i16* %fptr, align 4
@@ -121,11 +122,11 @@ define amdgpu_kernel void @zextload_flat_i16(i32 addrspace(1)* noalias %out, i16
   ret void
 }
 
-; CHECK-LABEL: flat_scratch_unaligned_load:
-; CHECK: flat_load_ubyte
-; CHECK: flat_load_ubyte
-; CHECK: flat_load_ubyte
-; CHECK: flat_load_ubyte
+; GCN-LABEL: flat_scratch_unaligned_load:
+; GCN: flat_load_{{ubyte|u8}}
+; GCN: flat_load_{{ubyte|u8}}
+; GCN: flat_load_{{ubyte|u8}}
+; GCN: flat_load_{{ubyte|u8}}
 define amdgpu_kernel void @flat_scratch_unaligned_load() {
   %scratch = alloca i32, addrspace(5)
   %fptr = addrspacecast i32 addrspace(5)* %scratch to i32*
@@ -133,11 +134,11 @@ define amdgpu_kernel void @flat_scratch_unaligned_load() {
   ret void
 }
 
-; CHECK-LABEL: flat_scratch_unaligned_store:
-; CHECK: flat_store_byte
-; CHECK: flat_store_byte
-; CHECK: flat_store_byte
-; CHECK: flat_store_byte
+; GCN-LABEL: flat_scratch_unaligned_store:
+; GCN: flat_store_{{byte|b8}}
+; GCN: flat_store_{{byte|b8}}
+; GCN: flat_store_{{byte|b8}}
+; GCN: flat_store_{{byte|b8}}
 define amdgpu_kernel void @flat_scratch_unaligned_store() {
   %scratch = alloca i32, addrspace(5)
   %fptr = addrspacecast i32 addrspace(5)* %scratch to i32*
@@ -145,11 +146,11 @@ define amdgpu_kernel void @flat_scratch_unaligned_store() {
   ret void
 }
 
-; CHECK-LABEL: flat_scratch_multidword_load:
+; GCN-LABEL: flat_scratch_multidword_load:
 ; CIVI-HSA: flat_load_dword v
 ; CIVI-HSA: flat_load_dword v
 ; GFX9:  flat_load_dwordx2
-; GFX10: flat_load_dwordx2
+; GFX10PLUS: flat_load_{{dwordx2|b64}}
 ; FIXME: These tests are broken for os = mesa3d, becasue it doesn't initialize flat_scr
 define amdgpu_kernel void @flat_scratch_multidword_load() {
   %scratch = alloca <2 x i32>, addrspace(5)
@@ -158,11 +159,11 @@ define amdgpu_kernel void @flat_scratch_multidword_load() {
   ret void
 }
 
-; CHECK-LABEL: flat_scratch_multidword_store:
+; GCN-LABEL: flat_scratch_multidword_store:
 ; CIVI-HSA: flat_store_dword v
 ; CIVI-HSA: flat_store_dword v
 ; GFX9:  flat_store_dwordx2
-; GFX10: flat_store_dwordx2
+; GFX10PLUS: flat_store_{{dwordx2|b64}}
 ; FIXME: These tests are broken for os = mesa3d, becasue it doesn't initialize flat_scr
 define amdgpu_kernel void @flat_scratch_multidword_store() {
   %scratch = alloca <2 x i32>, addrspace(5)
@@ -171,7 +172,7 @@ define amdgpu_kernel void @flat_scratch_multidword_store() {
   ret void
 }
 
-; CHECK-LABEL: {{^}}store_flat_i8_max_offset:
+; GCN-LABEL: {{^}}store_flat_i8_max_offset:
 ; CIVI: flat_store_byte v{{\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}{{$}}
 ; GFX9: flat_store_byte v{{\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}} offset:4095{{$}}
 define amdgpu_kernel void @store_flat_i8_max_offset(i8* %fptr, i8 %x) #0 {
@@ -180,15 +181,15 @@ define amdgpu_kernel void @store_flat_i8_max_offset(i8* %fptr, i8 %x) #0 {
   ret void
 }
 
-; CHECK-LABEL: {{^}}store_flat_i8_max_offset_p1:
-; CHECK: flat_store_byte v{{\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}{{$}}
+; GCN-LABEL: {{^}}store_flat_i8_max_offset_p1:
+; GCN: flat_store_{{byte|b8}} v{{\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}{{( dlc)?}}{{$}}
 define amdgpu_kernel void @store_flat_i8_max_offset_p1(i8* %fptr, i8 %x) #0 {
   %fptr.offset = getelementptr inbounds i8, i8* %fptr, i64 4096
   store volatile i8 %x, i8* %fptr.offset
   ret void
 }
 
-; CHECK-LABEL: {{^}}store_flat_i8_neg_offset:
+; GCN-LABEL: {{^}}store_flat_i8_neg_offset:
 ; CIVI: flat_store_byte v{{\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}{{$}}
 
 ; GFX9: v_add_co_u32_e64 v{{[0-9]+}}, vcc, -2, s
@@ -200,27 +201,28 @@ define amdgpu_kernel void @store_flat_i8_neg_offset(i8* %fptr, i8 %x) #0 {
   ret void
 }
 
-; CHECK-LABEL: {{^}}load_flat_i8_max_offset:
+; GCN-LABEL: {{^}}load_flat_i8_max_offset:
 ; CIVI: flat_load_ubyte v{{[0-9]+}}, v{{\[[0-9]+:[0-9]+\]}} glc{{$}}
 ; GFX9: flat_load_ubyte v{{[0-9]+}}, v{{\[[0-9]+:[0-9]+\]}} offset:4095 glc{{$}}
 ; GFX10: flat_load_ubyte v{{[0-9]+}}, v{{\[[0-9]+:[0-9]+\]}} glc dlc{{$}}
+; GFX11: flat_load_u8 v{{[0-9]+}}, v{{\[[0-9]+:[0-9]+\]}} offset:4095 glc dlc{{$}}
 define amdgpu_kernel void @load_flat_i8_max_offset(i8* %fptr) #0 {
   %fptr.offset = getelementptr inbounds i8, i8* %fptr, i64 4095
   %val = load volatile i8, i8* %fptr.offset
   ret void
 }
 
-; CHECK-LABEL: {{^}}load_flat_i8_max_offset_p1:
+; GCN-LABEL: {{^}}load_flat_i8_max_offset_p1:
 ; CIVI: flat_load_ubyte v{{[0-9]+}}, v{{\[[0-9]+:[0-9]+\]}} glc{{$}}
 ; GFX9: flat_load_ubyte v{{[0-9]+}}, v{{\[[0-9]+:[0-9]+\]}} glc{{$}}
-; GFX10: flat_load_ubyte v{{[0-9]+}}, v{{\[[0-9]+:[0-9]+\]}} glc dlc{{$}}
+; GFX10PLUS: flat_load_{{ubyte|u8}} v{{[0-9]+}}, v{{\[[0-9]+:[0-9]+\]}} glc dlc{{$}}
 define amdgpu_kernel void @load_flat_i8_max_offset_p1(i8* %fptr) #0 {
   %fptr.offset = getelementptr inbounds i8, i8* %fptr, i64 4096
   %val = load volatile i8, i8* %fptr.offset
   ret void
 }
 
-; CHECK-LABEL: {{^}}load_flat_i8_neg_offset:
+; GCN-LABEL: {{^}}load_flat_i8_neg_offset:
 ; CIVI: flat_load_ubyte v{{[0-9]+}}, v{{\[[0-9]+:[0-9]+\]}} glc{{$}}
 
 ; GFX9: v_add_co_u32_e64 v{{[0-9]+}}, vcc, -2, s
diff --git a/llvm/test/CodeGen/AMDGPU/flat-offset-bug.ll b/llvm/test/CodeGen/AMDGPU/flat-offset-bug.ll
index fc29b0e6374433..cdde9f3cf9e781 100644
--- a/llvm/test/CodeGen/AMDGPU/flat-offset-bug.ll
+++ b/llvm/test/CodeGen/AMDGPU/flat-offset-bug.ll
@@ -1,9 +1,10 @@
-; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9_11 %s
 ; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9_11 %s
 
 ; GCN-LABEL: flat_inst_offset:
-; GFX9:  flat_load_dword v{{[0-9]+}}, v[{{[0-9:]+}}] offset:4
-; GFX9:  flat_store_dword v[{{[0-9:]+}}], v{{[0-9]+}} offset:4
+; GFX9_11: flat_load_{{dword|b32}} v{{[0-9]+}}, v[{{[0-9:]+}}] offset:4
+; GFX9_11: flat_store_{{dword|b32}} v[{{[0-9:]+}}], v{{[0-9]+}} offset:4
 ; GFX10: flat_load_dword v{{[0-9]+}}, v[{{[0-9:]+}}]{{$}}
 ; GFX10: flat_store_dword v[{{[0-9:]+}}], v{{[0-9]+}}{{$}}
 define void @flat_inst_offset(i32* nocapture %p) {
@@ -15,8 +16,8 @@ define void @flat_inst_offset(i32* nocapture %p) {
 }
 
 ; GCN-LABEL: global_inst_offset:
-; GCN: global_load_dword v{{[0-9]+}}, v[{{[0-9:]+}}], off offset:4
-; GCN: global_store_dword v[{{[0-9:]+}}], v{{[0-9]+}}, off offset:4
+; GCN: global_load_{{dword|b32}} v{{[0-9]+}}, v[{{[0-9:]+}}], off offset:4
+; GCN: global_store_{{dword|b32}} v[{{[0-9:]+}}], v{{[0-9]+}}, off offset:4
 define void @global_inst_offset(i32 addrspace(1)* nocapture %p) {
   %gep = getelementptr inbounds i32, i32 addrspace(1)* %p, i64 1
   %load = load i32, i32 addrspace(1)* %gep, align 4
@@ -26,7 +27,7 @@ define void @global_inst_offset(i32 addrspace(1)* nocapture %p) {
 }
 
 ; GCN-LABEL: load_i16_lo:
-; GFX9:  flat_load_short_d16 v{{[0-9]+}}, v[{{[0-9:]+}}] offset:8{{$}}
+; GFX9_11: flat_load_{{short_d16|d16_b16}} v{{[0-9]+}}, v[{{[0-9:]+}}] offset:8{{$}}
 ; GFX10: flat_load_short_d16 v{{[0-9]+}}, v[{{[0-9:]+}}]{{$}}
 define amdgpu_kernel void @load_i16_lo(i16* %arg, <2 x i16>* %out) {
   %gep = getelementptr inbounds i16, i16* %arg, i32 4
@@ -38,7 +39,7 @@ define amdgpu_kernel void @load_i16_lo(i16* %arg, <2 x i16>* %out) {
 }
 
 ; GCN-LABEL: load_i16_hi:
-; GFX9:  flat_load_short_d16_hi v{{[0-9]+}}, v[{{[0-9:]+}}] offset:8{{$}}
+; GFX9_11: flat_load_{{short_d16_hi|d16_hi_b16}} v{{[0-9]+}}, v[{{[0-9:]+}}] offset:8{{$}}
 ; GFX10: flat_load_short_d16_hi v{{[0-9]+}}, v[{{[0-9:]+}}]{{$}}
 define amdgpu_kernel void @load_i16_hi(i16* %arg, <2 x i16>* %out) {
   %gep = getelementptr inbounds i16, i16* %arg, i32 4
@@ -50,7 +51,7 @@ define amdgpu_kernel void @load_i16_hi(i16* %arg, <2 x i16>* %out) {
 }
 
 ; GCN-LABEL: load_half_lo:
-; GFX9:  flat_load_short_d16 v{{[0-9]+}}, v[{{[0-9:]+}}] offset:8{{$}}
+; GFX9_11: flat_load_{{short_d16|d16_b16}} v{{[0-9]+}}, v[{{[0-9:]+}}] offset:8{{$}}
 ; GFX10: flat_load_short_d16 v{{[0-9]+}}, v[{{[0-9:]+}}]{{$}}
 define amdgpu_kernel void @load_half_lo(half* %arg, <2 x half>* %out) {
   %gep = getelementptr inbounds half, half* %arg, i32 4
@@ -62,7 +63,7 @@ define amdgpu_kernel void @load_half_lo(half* %arg, <2 x half>* %out) {
 }
 
 ; GCN-LABEL: load_half_hi:
-; GFX9:  flat_load_short_d16_hi v{{[0-9]+}}, v[{{[0-9:]+}}] offset:8{{$}}
+; GFX9_11: flat_load_{{short_d16_hi|d16_hi_b16}} v{{[0-9]+}}, v[{{[0-9:]+}}] offset:8{{$}}
 ; GFX10: flat_load_short_d16_hi v{{[0-9]+}}, v[{{[0-9:]+}}]{{$}}
 define amdgpu_kernel void @load_half_hi(half* %arg, <2 x half>* %out) {
   %gep = getelementptr inbounds half, half* %arg, i32 4
@@ -74,7 +75,7 @@ define amdgpu_kernel void @load_half_hi(half* %arg, <2 x half>* %out) {
 }
 
 ; GCN-LABEL: load_float_lo:
-; GFX9:  flat_load_dword v{{[0-9]+}}, v[{{[0-9:]+}}] offset:16{{$}}
+; GFX9_11: flat_load_{{dword|b32}} v{{[0-9]+}}, v[{{[0-9:]+}}] offset:16{{$}}
 ; GFX10: flat_load_dword v{{[0-9]+}}, v[{{[0-9:]+}}]{{$}}
 define amdgpu_kernel void @load_float_lo(float* %arg, float* %out) {
   %gep = getelementptr inbounds float, float* %arg, i32 4
diff --git a/llvm/test/CodeGen/AMDGPU/fmul-2-combine-multi-use.ll b/llvm/test/CodeGen/AMDGPU/fmul-2-combine-multi-use.ll
index c9be3952f01a05..8230fbaf8b866d 100644
--- a/llvm/test/CodeGen/AMDGPU/fmul-2-combine-multi-use.ll
+++ b/llvm/test/CodeGen/AMDGPU/fmul-2-combine-multi-use.ll
@@ -1,8 +1,10 @@
-; XUN: llc -mtriple=amdgcn-amd-amdhsa -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,SI %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,SIVI,VI-DENORM %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,SIVI,VI-FLUSH %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX10,GFX8_10,GFX10-DENORM %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX10,GFX8_10,GFX10-FLUSH %s
+; XUN: llc -mtriple=amdgcn-amd-amdhsa -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,SI %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,VI,SIVI,VI-DENORM %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,VI,SIVI,VI-FLUSH %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10,GFX8_10,GFX10-DENORM %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10,GFX8_10,GFX10-FLUSH %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10,GFX8_10,GFX10-DENORM %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10,GFX8_10,GFX10-FLUSH %s
 
 ; Make sure (fmul (fadd x, x), c) -> (fmul x, (fmul 2.0, c)) doesn't
 ; make add an instruction if the fadd has more than one use.
@@ -44,8 +46,8 @@ define amdgpu_kernel void @multiple_fadd_use_test_f32(float addrspace(1)* %out,
 ; GCN-DAG:   v_add_f32_e64 [[MUL2:v[0-9]+]], [[X:s[0-9]+]], s{{[0-9]+}}
 ; SIVI-DAG:  v_mac_f32_e64 [[MAD:v[0-9]+]], [[X]], 2.0
 ; GFX10-DAG: v_fma_f32 [[MAD:v[0-9]+]], [[X]], 2.0, s{{[0-9]+}}
-; GCN-DAG:   buffer_store_dword [[MUL2]]
-; GCN-DAG:   buffer_store_dword [[MAD]]
+; GCN-DAG:   buffer_store_{{dword|b32}} [[MUL2]]
+; GCN-DAG:   buffer_store_{{dword|b32}} [[MAD]]
 ; GCN:       s_endpgm
 define amdgpu_kernel void @multiple_use_fadd_fmac_f32(float addrspace(1)* %out, float %x, [8 x i32], float %y) #0 {
   %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1
@@ -60,8 +62,8 @@ define amdgpu_kernel void @multiple_use_fadd_fmac_f32(float addrspace(1)* %out,
 ; GCN-DAG:   v_add_f32_e64 [[MUL2:v[0-9]+]], |[[X:s[0-9]+]]|, |s{{[0-9]+}}|
 ; SIVI-DAG:  v_mad_f32 [[MAD:v[0-9]+]], |[[X]]|, 2.0, v{{[0-9]+}}
 ; GFX10-DAG: v_fma_f32 [[MAD:v[0-9]+]], |[[X]]|, 2.0, s{{[0-9]+}}
-; GCN-DAG:   buffer_store_dword [[MUL2]]
-; GCN-DAG:   buffer_store_dword [[MAD]]
+; GCN-DAG:   buffer_store_{{dword|b32}} [[MUL2]]
+; GCN-DAG:   buffer_store_{{dword|b32}} [[MAD]]
 ; GCN:       s_endpgm
 define amdgpu_kernel void @multiple_use_fadd_fmad_f32(float addrspace(1)* %out, float %x, float %y) #0 {
   %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1
@@ -92,7 +94,7 @@ define amdgpu_kernel void @multiple_use_fadd_multi_fmad_f32(float addrspace(1)*
 ; GCN-LABEL: {{^}}fmul_x2_xn2_f32:
 ; GCN: v_mul_f32_e64 [[TMP0:v[0-9]+]], [[X:s[0-9]+]], -4.0
 ; GCN: v_mul_f32_e32 [[RESULT:v[0-9]+]], [[X]], [[TMP0]]
-; GCN: buffer_store_dword [[RESULT]]
+; GCN: buffer_store_{{dword|b32}} [[RESULT]]
 define amdgpu_kernel void @fmul_x2_xn2_f32(float addrspace(1)* %out, float %x, float %y) #0 {
   %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1
   %mul2 = fmul fast float %x, 2.0
@@ -107,7 +109,7 @@ define amdgpu_kernel void @fmul_x2_xn2_f32(float addrspace(1)* %out, float %x, f
 ; SIVI:  v_mul_f32_e32 [[TMP0:v[0-9]+]], [[X:s[0-9]+]], [[K]]
 ; GFX10: v_mul_f32_e64 [[TMP0:v[0-9]+]], 0xc0c00000, [[X:s[0-9]+]]
 ; GCN:   v_mul_f32_e32 [[RESULT:v[0-9]+]], [[X]], [[TMP0]]
-; GCN:   buffer_store_dword [[RESULT]]
+; GCN:   buffer_store_{{dword|b32}} [[RESULT]]
 define amdgpu_kernel void @fmul_x2_xn3_f32(float addrspace(1)* %out, float %x, float %y) #0 {
   %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1
   %mul2 = fmul fast float %x, 2.0
@@ -154,8 +156,8 @@ define amdgpu_kernel void @multiple_fadd_use_test_f16(half addrspace(1)* %out, i
 ; GFX10-FLUSH-DAG:  v_add_f16_e32 [[MAD:v[0-9]+]], s{{[0-9]+}}, [[MUL2]]
 ; GFX10-DENORM-DAG: v_fma_f16 [[MAD:v[0-9]+]], [[X]], 2.0, s{{[0-9]+}}
 
-; GCN-DAG: buffer_store_short [[MUL2]]
-; GCN-DAG: buffer_store_short [[MAD]]
+; GCN-DAG: buffer_store_{{short|b16}} [[MUL2]]
+; GCN-DAG: buffer_store_{{short|b16}} [[MAD]]
 ; GCN: s_endpgm
 define amdgpu_kernel void @multiple_use_fadd_fmac_f16(half addrspace(1)* %out, i16 zeroext %x.arg, i16 zeroext %y.arg) #0 {
   %x = bitcast i16 %x.arg to half
@@ -176,8 +178,8 @@ define amdgpu_kernel void @multiple_use_fadd_fmac_f16(half addrspace(1)* %out, i
 ; GFX10-FLUSH-DAG:  v_add_f16_e32 [[MAD:v[0-9]+]], s{{[0-9]+}}, [[MUL2]]
 ; GFX10-DENORM-DAG: v_fma_f16 [[MAD:v[0-9]+]], |[[X]]|, 2.0, s{{[0-9]+}}
 
-; GCN-DAG: buffer_store_short [[MUL2]]
-; GCN-DAG: buffer_store_short [[MAD]]
+; GCN-DAG: buffer_store_{{short|b16}} [[MUL2]]
+; GCN-DAG: buffer_store_{{short|b16}} [[MAD]]
 ; GCN: s_endpgm
 define amdgpu_kernel void @multiple_use_fadd_fmad_f16(half addrspace(1)* %out, i16 zeroext %x.arg, i16 zeroext %y.arg) #0 {
   %x = bitcast i16 %x.arg to half
@@ -221,7 +223,7 @@ define amdgpu_kernel void @multiple_use_fadd_multi_fmad_f16(half addrspace(1)* %
 ; GCN-LABEL: {{^}}fmul_x2_xn2_f16:
 ; GCN: v_mul_f16_e64 [[TMP0:v[0-9]+]], [[X:s[0-9]+]], -4.0
 ; GCN: v_mul_f16_e32 [[RESULT:v[0-9]+]], [[X]], [[TMP0]]
-; GCN: buffer_store_short [[RESULT]]
+; GCN: buffer_store_{{short|b16}} [[RESULT]]
 define amdgpu_kernel void @fmul_x2_xn2_f16(half addrspace(1)* %out, i16 zeroext %x.arg, i16 zeroext %y.arg) #0 {
   %x = bitcast i16 %x.arg to half
   %y = bitcast i16 %y.arg to half
@@ -238,7 +240,7 @@ define amdgpu_kernel void @fmul_x2_xn2_f16(half addrspace(1)* %out, i16 zeroext
 ; SIVI:  v_mul_f16_e32 [[TMP0:v[0-9]+]], [[X:s[0-9]+]], [[K]]
 ; GFX10: v_mul_f16_e64 [[TMP0:v[0-9]+]], 0xc600, [[X:s[0-9]+]]
 ; GCN:   v_mul_f16_e32 [[RESULT:v[0-9]+]], [[X]], [[TMP0]]
-; GCN:   buffer_store_short [[RESULT]]
+; GCN:   buffer_store_{{short|b16}} [[RESULT]]
 define amdgpu_kernel void @fmul_x2_xn3_f16(half addrspace(1)* %out, i16 zeroext %x.arg, i16 zeroext %y.arg) #0 {
   %x = bitcast i16 %x.arg to half
   %y = bitcast i16 %y.arg to half
diff --git a/llvm/test/CodeGen/AMDGPU/fmuladd.f16.ll b/llvm/test/CodeGen/AMDGPU/fmuladd.f16.ll
index 4623129c2e8859..f2a13f6fc22a10 100644
--- a/llvm/test/CodeGen/AMDGPU/fmuladd.f16.ll
+++ b/llvm/test/CodeGen/AMDGPU/fmuladd.f16.ll
@@ -1,13 +1,18 @@
-; RUN: llc -march=amdgcn -mcpu=fiji -denormal-fp-math=preserve-sign -denormal-fp-math-f32=ieee -fp-contract=on -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI-FLUSH,VI %s
-; RUN: llc -march=amdgcn -mcpu=fiji -denormal-fp-math=preserve-sign -denormal-fp-math-f32=ieee -fp-contract=fast -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI-FLUSH,VI %s
+; RUN: llc -march=amdgcn -mcpu=fiji -denormal-fp-math=preserve-sign -denormal-fp-math-f32=ieee -fp-contract=on -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,VI-FLUSH,VI %s
+; RUN: llc -march=amdgcn -mcpu=fiji -denormal-fp-math=preserve-sign -denormal-fp-math-f32=ieee -fp-contract=fast -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,VI-FLUSH,VI %s
 
-; RUN: llc -march=amdgcn -mcpu=fiji -denormal-fp-math=ieee -denormal-fp-math-f32=ieee -fp-contract=on -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN-DENORM,GCN-DENORM-STRICT,VI-DENORM,VI %s
-; RUN: llc -march=amdgcn -mcpu=fiji -denormal-fp-math=ieee -denormal-fp-math-f32=ieee -fp-contract=fast -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN-DENORM,GCN-DENORM-CONTRACT,VI-DENORM-CONTRACT,VI-DENORM,VI %s
+; RUN: llc -march=amdgcn -mcpu=fiji -denormal-fp-math=ieee -denormal-fp-math-f32=ieee -fp-contract=on -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GCN-DENORM,GCN-DENORM-STRICT,VI-DENORM,VI %s
+; RUN: llc -march=amdgcn -mcpu=fiji -denormal-fp-math=ieee -denormal-fp-math-f32=ieee -fp-contract=fast -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GCN-DENORM,GCN-DENORM-CONTRACT,VI-DENORM-CONTRACT,VI-DENORM,VI %s
 
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=ieee -fp-contract=on -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX10-FLUSH,GFX10 %s
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=ieee -fp-contract=fast -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX10-FLUSH,GFX10 %s
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=ieee -denormal-fp-math-f32=ieee -fp-contract=on -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN-DENORM,GCN-DENORM-STRICT,GFX10-DENORM-STRICT,GFX10-DENORM,GFX10 %s
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=ieee -denormal-fp-math-f32=ieee -fp-contract=fast -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN-DENORM,GCN-DENORM-CONTRACT,GFX10-DENORM-CONTRACT,GFX10-DENORM,GFX10 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=ieee -fp-contract=on -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10-FLUSH,GFX10 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=ieee -fp-contract=fast -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10-FLUSH,GFX10 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=ieee -denormal-fp-math-f32=ieee -fp-contract=on -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GCN-DENORM,GCN-DENORM-STRICT,GFX10-DENORM-STRICT,GFX10-DENORM,GFX10 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=ieee -denormal-fp-math-f32=ieee -fp-contract=fast -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GCN-DENORM,GCN-DENORM-CONTRACT,GFX10-DENORM-CONTRACT,GFX10-DENORM,GFX10 %s
+
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=ieee -fp-contract=on -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10-FLUSH,GFX10 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=ieee -fp-contract=fast -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10-FLUSH,GFX10 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -denormal-fp-math=ieee -denormal-fp-math-f32=ieee -fp-contract=on -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GCN-DENORM,GCN-DENORM-STRICT,GFX10-DENORM-STRICT,GFX10-DENORM,GFX10 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -denormal-fp-math=ieee -denormal-fp-math-f32=ieee -fp-contract=fast -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GCN-DENORM,GCN-DENORM-CONTRACT,GFX10-DENORM-CONTRACT,GFX10-DENORM,GFX10 %s
 
 declare i32 @llvm.amdgcn.workitem.id.x() #1
 declare half @llvm.fmuladd.f16(half, half, half) #1
@@ -73,8 +78,8 @@ define amdgpu_kernel void @fmul_fadd_contract_f16(half addrspace(1)* %out, half
 }
 
 ; GCN-LABEL: {{^}}fmuladd_2.0_a_b_f16
-; GCN: {{buffer|flat|global}}_load_ushort [[R1:v[0-9]+]],
-; GCN: {{buffer|flat|global}}_load_ushort [[R2:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R1:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R2:v[0-9]+]],
 ; VI-FLUSH: v_mac_f16_e32 [[R2]], 2.0, [[R1]]
 ; VI-FLUSH: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, [[R2]]
 
@@ -85,8 +90,8 @@ define amdgpu_kernel void @fmul_fadd_contract_f16(half addrspace(1)* %out, half
 ; GFX10-FLUSH:  v_add_f16_e32 [[RESULT:v[0-9]+]], [[MUL2]], [[R2]]
 
 ; VI-DENORM:    flat_store_short v{{\[[0-9]+:[0-9]+\]}}, [[RESULT]]
-; GFX10-DENORM: global_store_short v{{[0-9]+}}, [[R2]]
-; GFX10-FLUSH:  global_store_short v{{[0-9]+}}, [[RESULT]], s{{\[[0-9]+:[0-9]+\]}}
+; GFX10-DENORM: global_store_{{short|b16}} v{{[0-9]+}}, [[R2]]
+; GFX10-FLUSH:  global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]], s{{\[[0-9]+:[0-9]+\]}}
 
 define amdgpu_kernel void @fmuladd_2.0_a_b_f16(half addrspace(1)* %out, half addrspace(1)* %in) #0 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
@@ -103,8 +108,8 @@ define amdgpu_kernel void @fmuladd_2.0_a_b_f16(half addrspace(1)* %out, half add
 }
 
 ; GCN-LABEL: {{^}}fmuladd_a_2.0_b_f16
-; GCN: {{buffer|flat|global}}_load_ushort [[R1:v[0-9]+]],
-; GCN: {{buffer|flat|global}}_load_ushort [[R2:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R1:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R2:v[0-9]+]],
 ; VI-FLUSH: v_mac_f16_e32 [[R2]], 2.0, [[R1]]
 ; VI-FLUSH: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, [[R2]]
 
@@ -115,8 +120,8 @@ define amdgpu_kernel void @fmuladd_2.0_a_b_f16(half addrspace(1)* %out, half add
 ; GFX10-FLUSH:  v_add_f16_e32 [[RESULT:v[0-9]+]], [[MUL2]], [[R2]]
 
 ; VI-DENORM: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, [[RESULT]]
-; GFX10-DENORM: global_store_short v{{[0-9]+}}, [[R2]]
-; GFX10-FLUSH:  global_store_short v{{[0-9]+}}, [[RESULT]]
+; GFX10-DENORM: global_store_{{short|b16}} v{{[0-9]+}}, [[R2]]
+; GFX10-FLUSH:  global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
 
 define amdgpu_kernel void @fmuladd_a_2.0_b_f16(half addrspace(1)* %out, half addrspace(1)* %in) #0 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
@@ -133,8 +138,8 @@ define amdgpu_kernel void @fmuladd_a_2.0_b_f16(half addrspace(1)* %out, half add
 }
 
 ; GCN-LABEL: {{^}}fadd_a_a_b_f16:
-; GCN: {{buffer|flat|global}}_load_ushort [[R1:v[0-9]+]],
-; GCN: {{buffer|flat|global}}_load_ushort [[R2:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R1:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R2:v[0-9]+]],
 ; VI-FLUSH: v_mac_f16_e32 [[R2]], 2.0, [[R1]]
 ; VI-FLUSH: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, [[R2]]
 
@@ -148,9 +153,9 @@ define amdgpu_kernel void @fmuladd_a_2.0_b_f16(half addrspace(1)* %out, half add
 
 ; GFX10-FLUSH:           v_add_f16_e32 [[MUL2:v[0-9]+]], [[R1]], [[R1]]
 ; GFX10-FLUSH:           v_add_f16_e32 [[RESULT:v[0-9]+]], [[MUL2]], [[R2]]
-; GFX10-FLUSH:           global_store_short v{{[0-9]+}}, [[RESULT]]
-; GFX10-DENORM-STRICT:   global_store_short v{{[0-9]+}}, [[RESULT]]
-; GFX10-DENORM-CONTRACT: global_store_short v{{[0-9]+}}, [[R2]]
+; GFX10-FLUSH:           global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
+; GFX10-DENORM-STRICT:   global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
+; GFX10-DENORM-CONTRACT: global_store_{{short|b16}} v{{[0-9]+}}, [[R2]]
 
 define amdgpu_kernel void @fadd_a_a_b_f16(half addrspace(1)* %out,
                             half addrspace(1)* %in1,
@@ -170,8 +175,8 @@ define amdgpu_kernel void @fadd_a_a_b_f16(half addrspace(1)* %out,
 }
 
 ; GCN-LABEL: {{^}}fadd_b_a_a_f16:
-; GCN: {{buffer|flat|global}}_load_ushort [[R1:v[0-9]+]],
-; GCN: {{buffer|flat|global}}_load_ushort [[R2:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R1:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R2:v[0-9]+]],
 ; VI-FLUSH: v_mac_f16_e32 [[R2]], 2.0, [[R1]]
 ; VI-FLUSH: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, [[R2]]
 
@@ -185,9 +190,9 @@ define amdgpu_kernel void @fadd_a_a_b_f16(half addrspace(1)* %out,
 
 ; GFX10-FLUSH: v_add_f16_e32 [[MUL2:v[0-9]+]], [[R1]], [[R1]]
 ; GFX10-FLUSH: v_add_f16_e32 [[RESULT:v[0-9]+]], [[R2]], [[MUL2]]
-; GFX10-FLUSH: global_store_short v{{[0-9]+}}, [[RESULT]]
-; GFX10-DENORM-STRICT:   global_store_short v{{[0-9]+}}, [[RESULT]]
-; GFX10-DENORM-CONTRACT: global_store_short v{{[0-9]+}}, [[R2]]
+; GFX10-FLUSH: global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
+; GFX10-DENORM-STRICT:   global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
+; GFX10-DENORM-CONTRACT: global_store_{{short|b16}} v{{[0-9]+}}, [[R2]]
 
 define amdgpu_kernel void @fadd_b_a_a_f16(half addrspace(1)* %out,
                             half addrspace(1)* %in1,
@@ -207,8 +212,8 @@ define amdgpu_kernel void @fadd_b_a_a_f16(half addrspace(1)* %out,
 }
 
 ; GCN-LABEL: {{^}}fmuladd_neg_2.0_a_b_f16
-; GCN: {{buffer|flat|global}}_load_ushort [[R1:v[0-9]+]],
-; GCN: {{buffer|flat|global}}_load_ushort [[R2:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R1:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R2:v[0-9]+]],
 ; VI-FLUSH:     v_mac_f16_e32 [[R2]], -2.0, [[R1]]
 ; VI-DENORM:    v_fma_f16 [[RESULT:v[0-9]+]], [[R1]], -2.0, [[R2]]
 ; GFX10-DENORM: v_fmac_f16_e32 [[R2]], -2.0, [[R1]]
@@ -216,8 +221,8 @@ define amdgpu_kernel void @fadd_b_a_a_f16(half addrspace(1)* %out,
 ; VI-DENORM: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, [[RESULT]]
 ; GFX10-FLUSH: v_add_f16_e32 [[MUL2:v[0-9]+]], [[R1]], [[R1]]
 ; GFX10-FLUSH: v_sub_f16_e32 [[RESULT:v[0-9]+]], [[R2]], [[MUL2]]
-; GFX10-FLUSH:  global_store_short v{{[0-9]+}}, [[RESULT]]
-; GFX10-DENORM: global_store_short v{{[0-9]+}}, [[R2]]
+; GFX10-FLUSH:  global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
+; GFX10-DENORM: global_store_{{short|b16}} v{{[0-9]+}}, [[R2]]
 define amdgpu_kernel void @fmuladd_neg_2.0_a_b_f16(half addrspace(1)* %out, half addrspace(1)* %in) #0 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.0 = getelementptr half, half addrspace(1)* %out, i32 %tid
@@ -233,8 +238,8 @@ define amdgpu_kernel void @fmuladd_neg_2.0_a_b_f16(half addrspace(1)* %out, half
 }
 
 ; GCN-LABEL: {{^}}fmuladd_neg_2.0_neg_a_b_f16
-; GCN: {{buffer|flat|global}}_load_ushort [[R1:v[0-9]+]],
-; GCN: {{buffer|flat|global}}_load_ushort [[R2:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R1:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R2:v[0-9]+]],
 ; VI-FLUSH: v_mac_f16_e32 [[R2]], 2.0, [[R1]]
 ; VI-FLUSH: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, [[R2]]
 
@@ -243,10 +248,10 @@ define amdgpu_kernel void @fmuladd_neg_2.0_a_b_f16(half addrspace(1)* %out, half
 
 ; GFX10-FLUSH: v_add_f16_e32 [[MUL2:v[0-9]+]], [[R1]], [[R1]]
 ; GFX10-FLUSH: v_add_f16_e32 [[RESULT:v[0-9]+]], [[R2]], [[MUL2]]
-; GFX10-FLUSH:  global_store_short v{{[0-9]+}}, [[RESULT]]
+; GFX10-FLUSH:  global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
 
 ; GFX10-DENORM: v_fmac_f16_e32 [[R2]], 2.0, [[R1]]
-; GFX10-DENORM: global_store_short v{{[0-9]+}}, [[R2]]
+; GFX10-DENORM: global_store_{{short|b16}} v{{[0-9]+}}, [[R2]]
 define amdgpu_kernel void @fmuladd_neg_2.0_neg_a_b_f16(half addrspace(1)* %out, half addrspace(1)* %in) #0 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.0 = getelementptr half, half addrspace(1)* %out, i32 %tid
@@ -264,8 +269,8 @@ define amdgpu_kernel void @fmuladd_neg_2.0_neg_a_b_f16(half addrspace(1)* %out,
 }
 
 ; GCN-LABEL: {{^}}fmuladd_2.0_neg_a_b_f16
-; GCN: {{buffer|flat|global}}_load_ushort [[R1:v[0-9]+]],
-; GCN: {{buffer|flat|global}}_load_ushort [[R2:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R1:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R2:v[0-9]+]],
 ; VI-FLUSH: v_mac_f16_e32 [[R2]], -2.0, [[R1]]
 ; VI-FLUSH: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, [[R2]]
 
@@ -274,10 +279,10 @@ define amdgpu_kernel void @fmuladd_neg_2.0_neg_a_b_f16(half addrspace(1)* %out,
 
 ; GFX10-FLUSH: v_add_f16_e32 [[MUL2:v[0-9]+]], [[R1]], [[R1]]
 ; GFX10-FLUSH: v_sub_f16_e32 [[RESULT:v[0-9]+]], [[R2]], [[MUL2]]
-; GFX10-FLUSH: global_store_short v{{[0-9]+}}, [[RESULT]]
+; GFX10-FLUSH: global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
 
 ; GFX10-DENORM: v_fmac_f16_e32 [[R2]], -2.0, [[R1]]
-; GFX10-DENORM: global_store_short v{{[0-9]+}}, [[R2]]
+; GFX10-DENORM: global_store_{{short|b16}} v{{[0-9]+}}, [[R2]]
 define amdgpu_kernel void @fmuladd_2.0_neg_a_b_f16(half addrspace(1)* %out, half addrspace(1)* %in) #0 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.0 = getelementptr half, half addrspace(1)* %out, i32 %tid
@@ -295,14 +300,14 @@ define amdgpu_kernel void @fmuladd_2.0_neg_a_b_f16(half addrspace(1)* %out, half
 }
 
 ; GCN-LABEL: {{^}}fmuladd_2.0_a_neg_b_f16
-; GCN: {{buffer|flat|global}}_load_ushort [[R1:v[0-9]+]],
-; GCN: {{buffer|flat|global}}_load_ushort [[R2:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R1:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R2:v[0-9]+]],
 ; VI-FLUSH:   v_mad_f16 [[RESULT:v[0-9]+]], [[R1]], 2.0, -[[R2]]
 ; GCN-DENORM: v_fma_f16 [[RESULT:v[0-9]+]], [[R1]], 2.0, -[[R2]]
 ; VI: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, [[RESULT]]
 ; GFX10-FLUSH: v_add_f16_e32 [[MUL2:v[0-9]+]], [[R1]], [[R1]]
 ; GFX10-FLUSH: v_sub_f16_e32 [[RESULT:v[0-9]+]], [[MUL2]], [[R2]]
-; GFX10:       global_store_short v{{[0-9]+}}, [[RESULT]]
+; GFX10:       global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
 define amdgpu_kernel void @fmuladd_2.0_a_neg_b_f16(half addrspace(1)* %out, half addrspace(1)* %in) #0 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.0 = getelementptr half, half addrspace(1)* %out, i32 %tid
@@ -320,9 +325,9 @@ define amdgpu_kernel void @fmuladd_2.0_a_neg_b_f16(half addrspace(1)* %out, half
 }
 
 ; GCN-LABEL: {{^}}mad_sub_f16:
-; GCN: {{buffer|flat|global}}_load_ushort [[REGA:v[0-9]+]]
-; GCN: {{buffer|flat|global}}_load_ushort [[REGB:v[0-9]+]]
-; GCN: {{buffer|flat|global}}_load_ushort [[REGC:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGA:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGB:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGC:v[0-9]+]]
 
 ; VI-FLUSH: v_mad_f16 [[RESULT:v[0-9]+]], [[REGA]], [[REGB]], -[[REGC]]
 
@@ -335,7 +340,7 @@ define amdgpu_kernel void @fmuladd_2.0_a_neg_b_f16(half addrspace(1)* %out, half
 
 ; GFX10-FLUSH: v_mul_f16_e32 [[TMP:v[0-9]+]], [[REGA]], [[REGB]]
 ; GFX10-FLUSH: v_sub_f16_e32 [[RESULT:v[0-9]+]], [[TMP]], [[REGC]]
-; GFX10:       global_store_short v{{[0-9]+}}, [[RESULT]]
+; GFX10:       global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
 define amdgpu_kernel void @mad_sub_f16(half addrspace(1)* noalias nocapture %out, half addrspace(1)* noalias nocapture readonly %ptr) #1 {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() #0
   %tid.ext = sext i32 %tid to i64
@@ -355,9 +360,9 @@ define amdgpu_kernel void @mad_sub_f16(half addrspace(1)* noalias nocapture %out
 }
 
 ; GCN-LABEL: {{^}}mad_sub_inv_f16:
-; GCN: {{buffer|flat|global}}_load_ushort [[REGA:v[0-9]+]]
-; GCN: {{buffer|flat|global}}_load_ushort [[REGB:v[0-9]+]]
-; GCN: {{buffer|flat|global}}_load_ushort [[REGC:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGA:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGB:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGC:v[0-9]+]]
 ; VI-FLUSH: v_mad_f16 [[RESULT:v[0-9]+]], -[[REGA]], [[REGB]], [[REGC]]
 
 ; GCN-DENORM-CONTRACT: v_fma_f16 [[RESULT:v[0-9]+]], -[[REGA]], [[REGB]], [[REGC]]
@@ -369,7 +374,7 @@ define amdgpu_kernel void @mad_sub_f16(half addrspace(1)* noalias nocapture %out
 
 ; GFX10-FLUSH: v_mul_f16_e32 [[TMP:v[0-9]+]], [[REGA]], [[REGB]]
 ; GFX10-FLUSH: v_sub_f16_e32 [[RESULT:v[0-9]+]], [[REGC]], [[TMP]]
-; GFX10: global_store_short v{{[0-9]+}}, [[RESULT]]
+; GFX10: global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
 define amdgpu_kernel void @mad_sub_inv_f16(half addrspace(1)* noalias nocapture %out, half addrspace(1)* noalias nocapture readonly %ptr) #1 {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() #0
   %tid.ext = sext i32 %tid to i64
@@ -389,9 +394,9 @@ define amdgpu_kernel void @mad_sub_inv_f16(half addrspace(1)* noalias nocapture
 }
 
 ; GCN-LABEL: {{^}}mad_sub_fabs_f16:
-; GCN: {{buffer|flat|global}}_load_ushort [[REGA:v[0-9]+]]
-; GCN: {{buffer|flat|global}}_load_ushort [[REGB:v[0-9]+]]
-; GCN: {{buffer|flat|global}}_load_ushort [[REGC:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGA:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGB:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGC:v[0-9]+]]
 ; VI-FLUSH: v_mad_f16 [[RESULT:v[0-9]+]], [[REGA]], [[REGB]], -|[[REGC]]|
 
 ; GCN-DENORM-CONTRACT: v_fma_f16 [[RESULT:v[0-9]+]], [[REGA]], [[REGB]], -|[[REGC]]|
@@ -403,7 +408,7 @@ define amdgpu_kernel void @mad_sub_inv_f16(half addrspace(1)* noalias nocapture
 
 ; GFX10-FLUSH: v_mul_f16_e32 [[TMP:v[0-9]+]], [[REGA]], [[REGB]]
 ; GFX10-FLUSH: v_sub_f16_e64 [[RESULT:v[0-9]+]], [[TMP]], |[[REGC]]|
-; GFX10:       global_store_short v{{[0-9]+}}, [[RESULT]]
+; GFX10:       global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
 define amdgpu_kernel void @mad_sub_fabs_f16(half addrspace(1)* noalias nocapture %out, half addrspace(1)* noalias nocapture readonly %ptr) #1 {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() #0
   %tid.ext = sext i32 %tid to i64
@@ -424,9 +429,9 @@ define amdgpu_kernel void @mad_sub_fabs_f16(half addrspace(1)* noalias nocapture
 }
 
 ; GCN-LABEL: {{^}}mad_sub_fabs_inv_f16:
-; GCN: {{buffer|flat|global}}_load_ushort [[REGA:v[0-9]+]]
-; GCN: {{buffer|flat|global}}_load_ushort [[REGB:v[0-9]+]]
-; GCN: {{buffer|flat|global}}_load_ushort [[REGC:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGA:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGB:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGC:v[0-9]+]]
 
 ; VI-FLUSH: v_mad_f16 [[RESULT:v[0-9]+]], -[[REGA]], [[REGB]], |[[REGC]]|
 
@@ -439,7 +444,7 @@ define amdgpu_kernel void @mad_sub_fabs_f16(half addrspace(1)* noalias nocapture
 
 ; GFX10-FLUSH: v_mul_f16_e32 [[TMP:v[0-9]+]], [[REGA]], [[REGB]]
 ; GFX10-FLUSH: v_sub_f16_e64 [[RESULT:v[0-9]+]], |[[REGC]]|, [[TMP]]
-; GFX10:       global_store_short v{{[0-9]+}}, [[RESULT]]
+; GFX10:       global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
 define amdgpu_kernel void @mad_sub_fabs_inv_f16(half addrspace(1)* noalias nocapture %out, half addrspace(1)* noalias nocapture readonly %ptr) #1 {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() #0
   %tid.ext = sext i32 %tid to i64
@@ -460,9 +465,9 @@ define amdgpu_kernel void @mad_sub_fabs_inv_f16(half addrspace(1)* noalias nocap
 }
 
 ; GCN-LABEL: {{^}}neg_neg_mad_f16:
-; GCN: {{buffer|flat|global}}_load_ushort [[REGA:v[0-9]+]]
-; GCN: {{buffer|flat|global}}_load_ushort [[REGB:v[0-9]+]]
-; GCN: {{buffer|flat|global}}_load_ushort [[REGC:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGA:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGB:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGC:v[0-9]+]]
 
 ; VI-FLUSH: v_mac_f16_e32 [[REGC]], [[REGA]], [[REGB]]
 ; VI-FLUSH: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, [[REGC]]
@@ -476,9 +481,9 @@ define amdgpu_kernel void @mad_sub_fabs_inv_f16(half addrspace(1)* noalias nocap
 
 ; GFX10-FLUSH: v_mul_f16_e32 [[TMP:v[0-9]+]], [[REGA]], [[REGB]]
 ; GFX10-FLUSH: v_add_f16_e32 [[RESULT:v[0-9]+]], [[REGC]], [[TMP]]
-; GFX10-FLUSH:  global_store_short v{{[0-9]+}}, [[RESULT]]
-; GFX10-DENORM-STRICT: global_store_short v{{[0-9]+}}, [[RESULT]]
-; GFX10-DENORM-CONTRACT: global_store_short v{{[0-9]+}}, [[REGC]]
+; GFX10-FLUSH:  global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
+; GFX10-DENORM-STRICT: global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
+; GFX10-DENORM-CONTRACT: global_store_{{short|b16}} v{{[0-9]+}}, [[REGC]]
 define amdgpu_kernel void @neg_neg_mad_f16(half addrspace(1)* noalias nocapture %out, half addrspace(1)* noalias nocapture readonly %ptr) #1 {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() #0
   %tid.ext = sext i32 %tid to i64
@@ -500,9 +505,9 @@ define amdgpu_kernel void @neg_neg_mad_f16(half addrspace(1)* noalias nocapture
 }
 
 ; GCN-LABEL: {{^}}mad_fabs_sub_f16:
-; GCN: {{buffer|flat|global}}_load_ushort [[REGA:v[0-9]+]]
-; GCN: {{buffer|flat|global}}_load_ushort [[REGB:v[0-9]+]]
-; GCN: {{buffer|flat|global}}_load_ushort [[REGC:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGA:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGB:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[REGC:v[0-9]+]]
 
 ; VI-FLUSH: v_mad_f16 [[RESULT:v[0-9]+]], [[REGA]], |[[REGB]]|, -[[REGC]]
 
@@ -515,7 +520,7 @@ define amdgpu_kernel void @neg_neg_mad_f16(half addrspace(1)* noalias nocapture
 
 ; GFX10-FLUSH: v_mul_f16_e64 [[TMP:v[0-9]+]], [[REGA]], |[[REGB]]|
 ; GFX10-FLUSH: v_sub_f16_e32 [[RESULT:v[0-9]+]], [[TMP]], [[REGC]]
-; GFX10:       global_store_short v{{[0-9]+}}, [[RESULT]]
+; GFX10:       global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
 define amdgpu_kernel void @mad_fabs_sub_f16(half addrspace(1)* noalias nocapture %out, half addrspace(1)* noalias nocapture readonly %ptr) #1 {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() #0
   %tid.ext = sext i32 %tid to i64
@@ -536,8 +541,8 @@ define amdgpu_kernel void @mad_fabs_sub_f16(half addrspace(1)* noalias nocapture
 }
 
 ; GCN-LABEL: {{^}}fsub_c_fadd_a_a_f16:
-; GCN: {{buffer|flat|global}}_load_ushort [[R1:v[0-9]+]],
-; GCN: {{buffer|flat|global}}_load_ushort [[R2:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R1:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R2:v[0-9]+]],
 ; VI-FLUSH: v_mac_f16_e32 [[R2]], -2.0, [[R1]]
 ; VI-FLUSH: flat_store_short v{{\[[0-9]+:[0-9]+\]}}, [[R2]]
 
@@ -551,9 +556,9 @@ define amdgpu_kernel void @mad_fabs_sub_f16(half addrspace(1)* noalias nocapture
 
 ; GFX10-FLUSH: v_add_f16_e32 [[TMP:v[0-9]+]], [[R1]], [[R1]]
 ; GFX10-FLUSH: v_sub_f16_e32 [[RESULT:v[0-9]+]], [[R2]], [[TMP]]
-; GFX10-FLUSH:  global_store_short v{{[0-9]+}}, [[RESULT]]
-; GFX10-DENORM-STRICT:   global_store_short v{{[0-9]+}}, [[RESULT]]
-; GFX10-DENORM-CONTRACT: global_store_short v{{[0-9]+}}, [[R2]]
+; GFX10-FLUSH:  global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
+; GFX10-DENORM-STRICT:   global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
+; GFX10-DENORM-CONTRACT: global_store_{{short|b16}} v{{[0-9]+}}, [[R2]]
 define amdgpu_kernel void @fsub_c_fadd_a_a_f16(half addrspace(1)* %out, half addrspace(1)* %in) {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.0 = getelementptr half, half addrspace(1)* %out, i32 %tid
@@ -571,8 +576,8 @@ define amdgpu_kernel void @fsub_c_fadd_a_a_f16(half addrspace(1)* %out, half add
 }
 
 ; GCN-LABEL: {{^}}fsub_fadd_a_a_c_f16:
-; GCN: {{buffer|flat|global}}_load_ushort [[R1:v[0-9]+]],
-; GCN: {{buffer|flat|global}}_load_ushort [[R2:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R1:v[0-9]+]],
+; GCN: {{buffer|flat|global}}_load_{{ushort|u16}} [[R2:v[0-9]+]],
 
 ; VI-FLUSH: v_mad_f16 [[RESULT:v[0-9]+]], [[R1]], 2.0, -[[R2]]
 
@@ -585,7 +590,7 @@ define amdgpu_kernel void @fsub_c_fadd_a_a_f16(half addrspace(1)* %out, half add
 
 ; GFX10-FLUSH: v_add_f16_e32 [[TMP:v[0-9]+]], [[R1]], [[R1]]
 ; GFX10-FLUSH: v_sub_f16_e32 [[RESULT:v[0-9]+]], [[TMP]], [[R2]]
-; GFX10:       global_store_short v{{[0-9]+}}, [[RESULT]]
+; GFX10:       global_store_{{short|b16}} v{{[0-9]+}}, [[RESULT]]
 define amdgpu_kernel void @fsub_fadd_a_a_c_f16(half addrspace(1)* %out, half addrspace(1)* %in) {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep.0 = getelementptr half, half addrspace(1)* %out, i32 %tid
diff --git a/llvm/test/CodeGen/AMDGPU/huge-private-buffer.ll b/llvm/test/CodeGen/AMDGPU/huge-private-buffer.ll
index b58a48dfe41539..aa5450047278e4 100644
--- a/llvm/test/CodeGen/AMDGPU/huge-private-buffer.ll
+++ b/llvm/test/CodeGen/AMDGPU/huge-private-buffer.ll
@@ -1,10 +1,11 @@
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,WAVE64 %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,WAVE32 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,WAVE64 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,WAVE32 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -amdgpu-enable-vopd=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,WAVE32 %s
 
 ; GCN-LABEL: {{^}}scratch_buffer_known_high_masklo14:
 ; GCN: v_mov_b32_e32 [[FI:v[0-9]+]], 4
 ; GCN: v_and_b32_e32 [[MASKED:v[0-9]+]], 0x3ffc, [[FI]]
-; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[MASKED]]
+; GCN: {{flat|global}}_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[MASKED]]
 define amdgpu_kernel void @scratch_buffer_known_high_masklo14() #0 {
   %alloca = alloca i32, align 4, addrspace(5)
   store volatile i32 0, i32 addrspace(5)* %alloca
@@ -17,7 +18,7 @@ define amdgpu_kernel void @scratch_buffer_known_high_masklo14() #0 {
 ; GCN-LABEL: {{^}}scratch_buffer_known_high_masklo16:
 ; GCN: v_mov_b32_e32 [[FI:v[0-9]+]], 4
 ; GCN: v_and_b32_e32 [[MASKED:v[0-9]+]], 0xfffc, [[FI]]
-; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[MASKED]]
+; GCN: {{flat|global}}_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[MASKED]]
 define amdgpu_kernel void @scratch_buffer_known_high_masklo16() #0 {
   %alloca = alloca i32, align 4, addrspace(5)
   store volatile i32 0, i32 addrspace(5)* %alloca
@@ -30,10 +31,10 @@ define amdgpu_kernel void @scratch_buffer_known_high_masklo16() #0 {
 ; GCN-LABEL: {{^}}scratch_buffer_known_high_masklo17:
 ; GCN: v_mov_b32_e32 [[FI:v[0-9]+]], 4
 ; WAVE64-NOT: [[FI]]
-; WAVE64: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[FI]]
+; WAVE64: {{flat|global}}_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[FI]]
 
 ; WAVE32: v_and_b32_e32 [[MASKED:v[0-9]+]], 0x1fffc, [[FI]]
-; WAVE32: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[MASKED]]
+; WAVE32: {{flat|global}}_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[MASKED]]
 define amdgpu_kernel void @scratch_buffer_known_high_masklo17() #0 {
   %alloca = alloca i32, align 4, addrspace(5)
   store volatile i32 0, i32 addrspace(5)* %alloca
@@ -46,7 +47,7 @@ define amdgpu_kernel void @scratch_buffer_known_high_masklo17() #0 {
 ; GCN-LABEL: {{^}}scratch_buffer_known_high_mask18:
 ; GCN: v_mov_b32_e32 [[FI:v[0-9]+]], 4
 ; GCN-NOT: [[FI]]
-; GCN: {{flat|global}}_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[FI]]
+; GCN: {{flat|global}}_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[FI]]
 define amdgpu_kernel void @scratch_buffer_known_high_mask18() #0 {
   %alloca = alloca i32, align 4, addrspace(5)
   store volatile i32 0, i32 addrspace(5)* %alloca
diff --git a/llvm/test/CodeGen/AMDGPU/large-alloca-compute.ll b/llvm/test/CodeGen/AMDGPU/large-alloca-compute.ll
index 66fb529326edfa..4cd9940b014827 100644
--- a/llvm/test/CodeGen/AMDGPU/large-alloca-compute.ll
+++ b/llvm/test/CodeGen/AMDGPU/large-alloca-compute.ll
@@ -1,9 +1,10 @@
 ; RUN: llc -march=amdgcn -mcpu=bonaire -show-mc-encoding < %s | FileCheck --check-prefixes=GCN,CI,ALL %s
 ; RUN: llc -march=amdgcn -mcpu=carrizo --show-mc-encoding < %s | FileCheck --check-prefixes=GCN,VI,ALL %s
 ; RUN: llc -march=amdgcn -mcpu=gfx900 --show-mc-encoding < %s | FileCheck --check-prefixes=GCN,GFX9,ALL %s
-; RUN: llc -march=amdgcn -mcpu=bonaire -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=4 < %s -mattr=-flat-for-global | FileCheck --check-prefixes=GCNHSA,ALL %s
+; RUN: llc -march=amdgcn -mcpu=bonaire -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=4 -mattr=-flat-for-global < %s | FileCheck --check-prefixes=GCNHSA,ALL %s
 ; RUN: llc -march=amdgcn -mcpu=carrizo -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=4 -mattr=-flat-for-global < %s | FileCheck --check-prefixes=GCNHSA,ALL %s
 ; RUN: llc -march=amdgcn -mcpu=gfx1010 -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=4 -mattr=-flat-for-global < %s | FileCheck --check-prefixes=GCNHSA,ALL %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -mtriple=amdgcn-unknown-amdhsa --amdhsa-code-object-version=4 -mattr=-flat-for-global,-architected-flat-scratch,-user-sgpr-init16-bug < %s | FileCheck --check-prefixes=GCNHSA,ALL %s
 
 ; FIXME: align on alloca seems to be ignored for private_segment_alignment
 
@@ -18,8 +19,8 @@
 ; VI-DAG: s_mov_b32 s{{[0-9]+}}, 0xe80000
 ; GFX9-DAG: s_mov_b32 s{{[0-9]+}}, 0xe00000
 
-; GCNHSA: buffer_store_dword {{v[0-9]+}}, {{v[0-9]+}}, s[0:3], 0 offen
-; GCNHSA: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, s[0:3], 0 offen
+; GCNHSA: buffer_store_{{dword|b32}} {{v[0-9]+}}, {{v[0-9]+}}, s[0:3], 0 offen
+; GCNHSA: buffer_load_{{dword|b32}} {{v[0-9]+}}, {{v[0-9]+}}, s[0:3], 0 offen
 
 ; GCNHSA: .amdhsa_kernel large_alloca_compute_shader
 ; GCNHSA:         .amdhsa_group_segment_fixed_size 0
diff --git a/llvm/test/CodeGen/AMDGPU/lds-branch-vmem-hazard.mir b/llvm/test/CodeGen/AMDGPU/lds-branch-vmem-hazard.mir
index 2475304da706d0..7cb311f3bd70d7 100644
--- a/llvm/test/CodeGen/AMDGPU/lds-branch-vmem-hazard.mir
+++ b/llvm/test/CodeGen/AMDGPU/lds-branch-vmem-hazard.mir
@@ -1,8 +1,10 @@
-# RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefix=GCN %s
+# RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefixes=GCN,GFX10 %s
+# RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefixes=GCN %s
 
 # GCN-LABEL: name: hazard_lds_branch_buf
-# GCN:      S_WAITCNT_VSCNT undef $sgpr_null, 0
-# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+# GCN:        bb.1:
+# GFX10-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
+# GCN-NEXT:   BUFFER_LOAD_DWORD_OFFEN
 ---
 name:            hazard_lds_branch_buf
 body:            |
@@ -17,8 +19,9 @@ body:            |
 ...
 
 # GCN-LABEL: name: hazard_buf_branch_lds
-# GCN:      S_WAITCNT_VSCNT undef $sgpr_null, 0
-# GCN-NEXT: DS_READ_B32
+# GCN:        bb.1:
+# GFX10-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
+# GCN-NEXT:   DS_READ_B32
 ---
 name:            hazard_buf_branch_lds
 body:            |
@@ -92,8 +95,8 @@ body:            |
 ...
 
 # GCN-LABEL: name: hazard_lds_branch_buf_loop
-# GCN:      S_WAITCNT_VSCNT undef $sgpr_null, 0
-# GCN-NEXT: DS_READ_B32
+# GFX10:    S_WAITCNT_VSCNT undef $sgpr_null, 0
+# GCN:      DS_READ_B32
 # GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
 ---
 name:            hazard_lds_branch_buf_loop
@@ -106,9 +109,10 @@ body:            |
 ...
 
 # GCN-LABEL: name: single_hazard_lds_branch_buf
-# GCN:      S_WAITCNT_VSCNT undef $sgpr_null, 0
-# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
-# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+# GCN:        bb.1:
+# GFX10-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
+# GCN-NEXT:   BUFFER_LOAD_DWORD_OFFEN
+# GCN-NEXT:   BUFFER_LOAD_DWORD_OFFEN
 ---
 name:            single_hazard_lds_branch_buf
 body:            |
@@ -159,8 +163,10 @@ body:            |
 ...
 
 # GCN-LABEL: name: hazard_lds_branch_vscnt_1_buf
-# GCN:      S_WAITCNT_VSCNT undef $sgpr_null, 0
-# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+# GCN:        bb.1:
+# GCN-NEXT:   S_WAITCNT_VSCNT undef $sgpr_null, 1
+# GFX10-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
+# GCN-NEXT:   BUFFER_LOAD_DWORD_OFFEN
 ---
 name:            hazard_lds_branch_vscnt_1_buf
 body:            |
@@ -194,8 +200,10 @@ body:            |
 ...
 
 # GCN-LABEL: name: hazard_lds_branch_vscnt_s0_buf
-# GCN:      S_WAITCNT_VSCNT undef $sgpr_null, 0
-# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
+# GCN:        bb.1:
+# GCN-NEXT:   S_WAITCNT_VSCNT undef $sgpr0, 0
+# GFX10-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
+# GCN-NEXT:   BUFFER_LOAD_DWORD_OFFEN
 ---
 name:            hazard_lds_branch_vscnt_s0_buf
 body:            |
@@ -228,8 +236,9 @@ body:            |
 ...
 
 # GCN-LABEL: name: hazard_lds_branch_global
-# GCN:      S_WAITCNT_VSCNT undef $sgpr_null, 0
-# GCN-NEXT: GLOBAL_LOAD_DWORD
+# GCN:        bb.1:
+# GFX10-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
+# GCN-NEXT:   GLOBAL_LOAD_DWORD
 ---
 name:            hazard_lds_branch_global
 body:            |
@@ -244,8 +253,9 @@ body:            |
 ...
 
 # GCN-LABEL: name: hazard_lds_branch_scratch
-# GCN:      S_WAITCNT_VSCNT undef $sgpr_null, 0
-# GCN-NEXT: SCRATCH_LOAD_DWORD
+# GCN:        bb.1:
+# GFX10-NEXT: S_WAITCNT_VSCNT undef $sgpr_null, 0
+# GCN-NEXT:   SCRATCH_LOAD_DWORD
 ---
 name:            hazard_lds_branch_scratch
 body:            |
diff --git a/llvm/test/CodeGen/AMDGPU/lds-misaligned-bug.ll b/llvm/test/CodeGen/AMDGPU/lds-misaligned-bug.ll
index 234b57decf5e1b..b5fceed2c105b9 100644
--- a/llvm/test/CodeGen/AMDGPU/lds-misaligned-bug.ll
+++ b/llvm/test/CodeGen/AMDGPU/lds-misaligned-bug.ll
@@ -3,10 +3,13 @@
 ; RUN: llc -march=amdgcn -mcpu=gfx1012 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,ALIGNED,SPLIT %s
 ; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -mattr=+cumode < %s | FileCheck -check-prefixes=GCN,ALIGNED,VECT %s
 ; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -mattr=+cumode,+unaligned-access-mode < %s | FileCheck -check-prefixes=GCN,UNALIGNED,VECT %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,ALIGNED,VECT %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs -mattr=+cumode < %s | FileCheck -check-prefixes=GCN,ALIGNED,VECT %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs -mattr=+cumode,+unaligned-access-mode < %s | FileCheck -check-prefixes=GCN,UNALIGNED,VECT %s
 
 ; GCN-LABEL: test_local_misaligned_v2:
-; GCN-DAG: ds_read2_b32
-; GCN-DAG: ds_write2_b32
+; GCN-DAG: ds_{{read2|load_2addr}}_b32
+; GCN-DAG: ds_{{write2|store_2addr}}_b32
 define amdgpu_kernel void @test_local_misaligned_v2(i32 addrspace(3)* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -22,10 +25,10 @@ bb:
 }
 
 ; GCN-LABEL: test_local_misaligned_v4:
-; GCN-DAG: ds_read2_b32
-; GCN-DAG: ds_read2_b32
-; GCN-DAG: ds_write2_b32
-; GCN-DAG: ds_write2_b32
+; GCN-DAG: ds_{{read2|load_2addr}}_b32
+; GCN-DAG: ds_{{read2|load_2addr}}_b32
+; GCN-DAG: ds_{{write2|store_2addr}}_b32
+; GCN-DAG: ds_{{write2|store_2addr}}_b32
 define amdgpu_kernel void @test_local_misaligned_v4(i32 addrspace(3)* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -45,10 +48,10 @@ bb:
 }
 
 ; GCN-LABEL: test_local_misaligned_v3:
-; GCN-DAG: ds_read2_b32
-; GCN-DAG: ds_read_b32
-; GCN-DAG: ds_write2_b32
-; GCN-DAG: ds_write_b32
+; GCN-DAG: ds_{{read2|load_2addr}}_b32
+; GCN-DAG: ds_{{read|load}}_b32
+; GCN-DAG: ds_{{write2|store_2addr}}_b32
+; GCN-DAG: ds_{{write|store}}_b32
 define amdgpu_kernel void @test_local_misaligned_v3(i32 addrspace(3)* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -66,12 +69,12 @@ bb:
 }
 
 ; GCN-LABEL: test_flat_misaligned_v2:
-; VECT-DAG:  flat_load_dwordx2 v
-; VECT-DAG:  flat_store_dwordx2 v
-; SPLIT-DAG: flat_load_dword v
-; SPLIT-DAG: flat_load_dword v
-; SPLIT-DAG: flat_store_dword v
-; SPLIT-DAG: flat_store_dword v
+; VECT-DAG:  flat_load_{{dwordx2|b64}} v
+; VECT-DAG:  flat_store_{{dwordx2|b64}} v
+; SPLIT-DAG: flat_load_{{dword|b32}} v
+; SPLIT-DAG: flat_load_{{dword|b32}} v
+; SPLIT-DAG: flat_store_{{dword|b32}} v
+; SPLIT-DAG: flat_store_{{dword|b32}} v
 define amdgpu_kernel void @test_flat_misaligned_v2(i32* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -87,16 +90,16 @@ bb:
 }
 
 ; GCN-LABEL: test_flat_misaligned_v4:
-; VECT-DAG:  flat_load_dwordx4 v
-; VECT-DAG:  flat_store_dwordx4 v
-; SPLIT-DAG: flat_load_dword v
-; SPLIT-DAG: flat_load_dword v
-; SPLIT-DAG: flat_load_dword v
-; SPLIT-DAG: flat_load_dword v
-; SPLIT-DAG: flat_store_dword v
-; SPLIT-DAG: flat_store_dword v
-; SPLIT-DAG: flat_store_dword v
-; SPLIT-DAG: flat_store_dword v
+; VECT-DAG:  flat_load_{{dwordx4|b128}} v
+; VECT-DAG:  flat_store_{{dwordx4|b128}} v
+; SPLIT-DAG: flat_load_{{dword|b32}} v
+; SPLIT-DAG: flat_load_{{dword|b32}} v
+; SPLIT-DAG: flat_load_{{dword|b32}} v
+; SPLIT-DAG: flat_load_{{dword|b32}} v
+; SPLIT-DAG: flat_store_{{dword|b32}} v
+; SPLIT-DAG: flat_store_{{dword|b32}} v
+; SPLIT-DAG: flat_store_{{dword|b32}} v
+; SPLIT-DAG: flat_store_{{dword|b32}} v
 define amdgpu_kernel void @test_flat_misaligned_v4(i32* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -116,14 +119,14 @@ bb:
 }
 
 ; GCN-LABEL: test_flat_misaligned_v3:
-; VECT-DAG:  flat_load_dwordx3 v
-; VECT-DAG:  flat_store_dwordx3 v
-; SPLIT-DAG: flat_load_dword v
-; SPLIT-DAG: flat_load_dword v
-; SPLIT-DAG: flat_load_dword v
-; SPLIT-DAG: flat_store_dword v
-; SPLIT-DAG: flat_store_dword v
-; SPLIT-DAG: flat_store_dword v
+; VECT-DAG:  flat_load_{{dwordx3|b96}} v
+; VECT-DAG:  flat_store_{{dwordx3|b96}} v
+; SPLIT-DAG: flat_load_{{dword|b32}} v
+; SPLIT-DAG: flat_load_{{dword|b32}} v
+; SPLIT-DAG: flat_load_{{dword|b32}} v
+; SPLIT-DAG: flat_store_{{dword|b32}} v
+; SPLIT-DAG: flat_store_{{dword|b32}} v
+; SPLIT-DAG: flat_store_{{dword|b32}} v
 define amdgpu_kernel void @test_flat_misaligned_v3(i32* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -141,8 +144,8 @@ bb:
 }
 
 ; GCN-LABEL: test_local_aligned_v2:
-; GCN-DAG: ds_read_b64
-; GCN-DAG: ds_write_b64
+; GCN-DAG: ds_{{read|load}}_b64
+; GCN-DAG: ds_{{write|store}}_b64
 define amdgpu_kernel void @test_local_aligned_v2(i32 addrspace(3)* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -158,8 +161,8 @@ bb:
 }
 
 ; GCN-LABEL: test_local_aligned_v3:
-; GCN-DAG: ds_read_b96
-; GCN-DAG: ds_write_b96
+; GCN-DAG: ds_{{read|load}}_b96
+; GCN-DAG: ds_{{write|store}}_b96
 define amdgpu_kernel void @test_local_aligned_v3(i32 addrspace(3)* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -177,8 +180,8 @@ bb:
 }
 
 ; GCN-LABEL: test_flat_aligned_v2:
-; GCN-DAG: flat_load_dwordx2 v
-; GCN-DAG: flat_store_dwordx2 v
+; GCN-DAG: flat_load_{{dwordx2|b64}} v
+; GCN-DAG: flat_store_{{dwordx2|b64}} v
 define amdgpu_kernel void @test_flat_aligned_v2(i32* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -194,8 +197,8 @@ bb:
 }
 
 ; GCN-LABEL: test_flat_aligned_v4:
-; GCN-DAG: flat_load_dwordx4 v
-; GCN-DAG: flat_store_dwordx4 v
+; GCN-DAG: flat_load_{{dwordx4|b128}} v
+; GCN-DAG: flat_store_{{dwordx4|b128}} v
 define amdgpu_kernel void @test_flat_aligned_v4(i32* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -215,10 +218,10 @@ bb:
 }
 
 ; GCN-LABEL: test_local_v4_aligned8:
-; ALIGNED-DAG: ds_read2_b64
-; ALIGNED-DAG: ds_write2_b64
-; UNALIGNED-DAG: ds_read2_b64
-; UNALIGNED-DAG: ds_write2_b64
+; ALIGNED-DAG: ds_{{read2|load_2addr}}_b64
+; ALIGNED-DAG: ds_{{write2|store_2addr}}_b64
+; UNALIGNED-DAG: ds_{{read2|load_2addr}}_b64
+; UNALIGNED-DAG: ds_{{write2|store_2addr}}_b64
 define amdgpu_kernel void @test_local_v4_aligned8(i32 addrspace(3)* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -238,12 +241,12 @@ bb:
 }
 
 ; GCN-LABEL: test_flat_v4_aligned8:
-; VECT-DAG:  flat_load_dwordx4 v
-; VECT-DAG:  flat_store_dwordx4 v
-; SPLIT-DAG: flat_load_dwordx2 v
-; SPLIT-DAG: flat_load_dwordx2 v
-; SPLIT-DAG: flat_store_dwordx2 v
-; SPLIT-DAG: flat_store_dwordx2 v
+; VECT-DAG:  flat_load_{{dwordx4|b128}} v
+; VECT-DAG:  flat_store_{{dwordx4|b128}} v
+; SPLIT-DAG: flat_load_{{dwordx2|b64}} v
+; SPLIT-DAG: flat_load_{{dwordx2|b64}} v
+; SPLIT-DAG: flat_store_{{dwordx2|b64}} v
+; SPLIT-DAG: flat_store_{{dwordx2|b64}} v
 define amdgpu_kernel void @test_flat_v4_aligned8(i32* %arg) {
 bb:
   %lid = tail call i32 @llvm.amdgcn.workitem.id.x()
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fdot2.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fdot2.ll
index b4bf563725a6de..2425fbb1896257 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fdot2.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fdot2.ll
@@ -2,6 +2,7 @@
 ; RUN: llc -march=amdgcn -mcpu=gfx940 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GCN,GFX9,GFX940
 ; RUN: llc -march=amdgcn -mcpu=gfx1011 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GCN,GFX10
 ; RUN: llc -march=amdgcn -mcpu=gfx1012 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GCN,GFX10
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -amdgpu-enable-vopd=0 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GCN,GFX10
 
 declare float @llvm.amdgcn.fdot2(<2 x half> %a, <2 x half> %b, float %c, i1 %clamp)
 
@@ -25,7 +26,7 @@ entry:
 ; GCN-LABEL: {{^}}test_llvm_amdgcn_fdot2_no_clamp
 ; GFX906: v_dot2_f32_f16 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}{{$}}
 ; GFX940: v_dot2c_f32_f16_e32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}{{$}}
-; GFX10:  v_dot2c_f32_f16_e32 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}{{$}}
+; GFX10:  {{v_dot2c_f32_f16_e32|v_dot2acc_f32_f16}} v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}{{$}}
 define amdgpu_kernel void @test_llvm_amdgcn_fdot2_no_clamp(
     float addrspace(1)* %r,
     <2 x half> addrspace(1)* %a,
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.tbuffer.store.d16.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.tbuffer.store.d16.ll
index bd30de55ae0c05..f3490f45111574 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.tbuffer.store.d16.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.tbuffer.store.d16.ll
@@ -1,15 +1,15 @@
-; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -enable-var-scope -check-prefixes=GCN,UNPACKED,PREGFX10,PREGFX10-UNPACKED %s
-; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,PREGFX10,PREGFX10-PACKED %s
-; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,PREGFX10,PREGFX10-PACKED %s
-; RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefixes=GCN,PACKED,GFX10,GFX10-PACKED %s
-
+; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefixes=GCN,UNPACKED,PREGFX10,PREGFX10-UNPACKED %s
+; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -check-prefixes=GCN,PACKED,PREGFX10,PREGFX10-PACKED %s
+; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefixes=GCN,PACKED,PREGFX10,PREGFX10-PACKED %s
+; RUN: llc < %s -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefixes=GCN,PACKED,GFX10,GFX10-PACKED %s
+; RUN: llc < %s -march=amdgcn -mcpu=gfx1100 -amdgpu-enable-vopd=0 -verify-machineinstrs | FileCheck -check-prefixes=GCN,PACKED,GFX10,GFX10-PACKED %s
 
 ; GCN-LABEL: {{^}}tbuffer_store_d16_x:
-; GCN-DAG: s_load_dwordx4
-; GCN-DAG: s_load_dword s[[S_LO:[0-9]+]]
+; GCN-DAG: s_load_{{dwordx4|b128}}
+; GCN-DAG: s_load_{{dword|b32}} s[[S_LO:[0-9]+]]
 ; GCN-DAG: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[S_LO]]
 ; PREGFX10: tbuffer_store_format_d16_x v[[V_LO]], off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED]
-; GFX10: tbuffer_store_format_d16_x v[[V_LO]], off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_10_11_11_SSCALED]
+; GFX10: tbuffer_store_{{format_d16|d16_format}}_x v[[V_LO]], off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_{{.*}}]
 define amdgpu_kernel void @tbuffer_store_d16_x(<4 x i32> %rsrc, half %data) {
 main_body:
   call void @llvm.amdgcn.raw.tbuffer.store.f16(half %data, <4 x i32> %rsrc, i32 0, i32 0, i32 33, i32 0)
@@ -17,7 +17,7 @@ main_body:
 }
 
 ; GCN-LABEL: {{^}}tbuffer_store_d16_xy:
-; GCN: s_load_dword [[S_DATA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}},
+; GCN: s_load_{{dword|b32}} [[S_DATA:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}},
 ; UNPACKED-DAG: s_lshr_b32 [[SHR:s[0-9]+]], [[S_DATA]], 16
 ; UNPACKED-DAG: s_and_b32 [[MASKED:s[0-9]+]], [[S_DATA]], 0xffff{{$}}
 ; UNPACKED-DAG: v_mov_b32_e32 v[[V_LO:[0-9]+]], [[MASKED]]
@@ -25,7 +25,7 @@ main_body:
 ; PREGFX10-UNPACKED: tbuffer_store_format_d16_xy v[[[V_LO]]:[[V_HI]]], off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED]
 
 ; PREGFX10-PACKED: tbuffer_store_format_d16_xy v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED]
-; GFX10-PACKED: tbuffer_store_format_d16_xy v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_10_11_11_SSCALED]
+; GFX10-PACKED: tbuffer_store_{{format_d16|d16_format}}_xy v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_{{.*}}]
 define amdgpu_kernel void @tbuffer_store_d16_xy(<4 x i32> %rsrc, <2 x half> %data) {
 main_body:
   call void @llvm.amdgcn.raw.tbuffer.store.v2f16(<2 x half> %data, <4 x i32> %rsrc, i32 0, i32 0, i32 33, i32 0)
@@ -33,7 +33,7 @@ main_body:
 }
 
 ; GCN-LABEL: {{^}}tbuffer_store_d16_xyz:
-; GCN-DAG: s_load_dwordx2 s[[[S_DATA_0:[0-9]+]]:[[S_DATA_1:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}},
+; GCN-DAG: s_load_{{dwordx2|b64}} s[[[S_DATA_0:[0-9]+]]:[[S_DATA_1:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}},
 
 ; UNPACKED-DAG: s_lshr_b32 [[SHR0:s[0-9]+]], s[[S_DATA_0]], 16
 ; UNPACKED-DAG: s_and_b32 [[MASKED0:s[0-9]+]], s[[S_DATA_0]], 0xffff{{$}}
@@ -48,7 +48,7 @@ main_body:
 ; PACKED-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], s[[S_DATA_0]]
 ; PACKED-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], [[MASKED0]]
 ; PREGFX10-PACKED: tbuffer_store_format_d16_xyz v[[[LO]]:[[HI]]], off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED]
-; GFX10-PACKED: tbuffer_store_format_d16_xyz v[[[LO]]:[[HI]]], off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_10_11_11_SSCALED]
+; GFX10-PACKED: tbuffer_store_{{format_d16|d16_format}}_xyz v[[[LO]]:[[HI]]], off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_{{.*}}]
 define amdgpu_kernel void @tbuffer_store_d16_xyz(<4 x i32> %rsrc, <4 x half> %data) {
 main_body:
   %data_subvec = shufflevector <4 x half> %data, <4 x half> undef, <3 x i32> <i32 0, i32 1, i32 2>
@@ -57,7 +57,7 @@ main_body:
 }
 
 ; GCN-LABEL: {{^}}tbuffer_store_d16_xyzw:
-; GCN-DAG: s_load_dwordx2 s[[[S_DATA_0:[0-9]+]]:[[S_DATA_1:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}},
+; GCN-DAG: s_load_{{dwordx2|b64}} s[[[S_DATA_0:[0-9]+]]:[[S_DATA_1:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}},
 
 ; UNPACKED-DAG: s_lshr_b32 [[SHR0:s[0-9]+]], s[[S_DATA_0]], 16
 ; UNPACKED-DAG: s_and_b32 [[MASKED0:s[0-9]+]], s[[S_DATA_0]], 0xffff{{$}}
@@ -72,7 +72,7 @@ main_body:
 ; PACKED-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], s[[S_DATA_0]]
 ; PACKED-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], s[[S_DATA_1]]
 ; PREGFX10-PACKED: tbuffer_store_format_d16_xyzw v[[[LO]]:[[HI]]], off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED]
-; GFX10-PACKED: tbuffer_store_format_d16_xyzw v[[[LO]]:[[HI]]], off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_10_11_11_SSCALED]
+; GFX10-PACKED: tbuffer_store_{{format_d16|d16_format}}_xyzw v[[[LO]]:[[HI]]], off, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_{{.*}}]
 define amdgpu_kernel void @tbuffer_store_d16_xyzw(<4 x i32> %rsrc, <4 x half> %data) {
 main_body:
   call void @llvm.amdgcn.raw.tbuffer.store.v4f16(<4 x half> %data, <4 x i32> %rsrc, i32 0, i32 0, i32 33, i32 0)
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.tbuffer.store.d16.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.tbuffer.store.d16.ll
index 01d3d38e48a71a..c85a21fc85eb17 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.tbuffer.store.d16.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.tbuffer.store.d16.ll
@@ -1,15 +1,15 @@
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PREGFX10,UNPACKED,PREGFX10-UNPACKED %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PREGFX10,PACKED,PREGFX10-PACKED %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,PREGFX10,PACKED,PREGFX10-PACKED %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX10,PACKED,GFX10-PACKED %s
-
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,PREGFX10,UNPACKED,PREGFX10-UNPACKED %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx810 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,PREGFX10,PACKED,PREGFX10-PACKED %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,PREGFX10,PACKED,PREGFX10-PACKED %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10,PACKED,GFX10-PACKED %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -amdgpu-enable-vopd=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10,PACKED,GFX10-PACKED %s
 
 ; GCN-LABEL: {{^}}tbuffer_store_d16_x:
-; GCN-DAG: s_load_dwordx4
-; GCN-DAG: s_load_dword{{[x0-2]*}} s[[[S_LO:[0-9]+]]
+; GCN-DAG: s_load_{{dwordx4|b128}}
+; GCN-DAG: s_load_{{dwordx2|b64}} s[[[S_LO:[0-9]+]]
 ; GCN-DAG: v_mov_b32_e32 v[[V_LO:[0-9]+]], s[[S_LO]]
 ; PREGFX10: tbuffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED] idxen
-; GFX10: tbuffer_store_format_d16_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_10_11_11_SSCALED] idxen
+; GFX10: tbuffer_store_{{format_d16|d16_format}}_x v[[V_LO]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_{{.*}}] idxen
 define amdgpu_kernel void @tbuffer_store_d16_x(<4 x i32> %rsrc, half %data, i32 %vindex) {
 main_body:
   call void @llvm.amdgcn.struct.tbuffer.store.f16(half %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 33, i32 0)
@@ -17,7 +17,7 @@ main_body:
 }
 
 ; GCN-LABEL: {{^}}tbuffer_store_d16_xy:
-; GCN: s_load_dwordx2 s[[[S_DATA:[0-9]+]]:{{[0-9]+}}], s{{\[[0-9]+:[0-9]+\]}}, 0x10
+; GCN: s_load_{{dwordx2|b64}} s[[[S_DATA:[0-9]+]]:{{[0-9]+}}], s{{\[[0-9]+:[0-9]+\]}}, 0x10
 ; UNPACKED-DAG: s_lshr_b32 [[SHR:s[0-9]+]], s[[S_DATA]], 16
 ; UNPACKED-DAG: s_and_b32 [[MASKED:s[0-9]+]], s[[S_DATA]], 0xffff{{$}}
 ; UNPACKED-DAG: v_mov_b32_e32 v[[V_LO:[0-9]+]], [[MASKED]]
@@ -25,7 +25,7 @@ main_body:
 ; PREGFX10-UNPACKED: tbuffer_store_format_d16_xy v[[[V_LO]]:[[V_HI]]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED] idxen
 
 ; PREGFX10-PACKED: tbuffer_store_format_d16_xy v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED] idxen
-; GFX10-PACKED: tbuffer_store_format_d16_xy v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_10_11_11_SSCALED] idxen
+; GFX10-PACKED: tbuffer_store_{{format_d16|d16_format}}_xy v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_{{.*}}] idxen
 define amdgpu_kernel void @tbuffer_store_d16_xy(<4 x i32> %rsrc, <2 x half> %data, i32 %vindex) {
 main_body:
   call void @llvm.amdgcn.struct.tbuffer.store.v2f16(<2 x half> %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 33, i32 0)
@@ -33,7 +33,7 @@ main_body:
 }
 
 ; GCN-LABEL: {{^}}tbuffer_store_d16_xyz:
-; GCN-DAG: s_load_dwordx2 s[[[S_DATA_0:[0-9]+]]:[[S_DATA_1:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}}, 0x10
+; GCN-DAG: s_load_{{dwordx2|b64}} s[[[S_DATA_0:[0-9]+]]:[[S_DATA_1:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}}, 0x10
 
 ; UNPACKED-DAG: s_lshr_b32 [[SHR0:s[0-9]+]], s[[S_DATA_0]], 16
 ; UNPACKED-DAG: s_and_b32 [[MASKED0:s[0-9]+]], s[[S_DATA_0]], 0xffff{{$}}
@@ -47,7 +47,7 @@ main_body:
 ; PACKED-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], s[[S_DATA_0]]
 ; PACKED-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], [[MASKED0]]
 ; PREGFX10-PACKED: tbuffer_store_format_d16_xyz v[[[LO]]:[[HI]]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED] idxen
-; GFX10-PACKED: tbuffer_store_format_d16_xyz v[[[LO]]:[[HI]]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_10_11_11_SSCALED] idxen
+; GFX10-PACKED: tbuffer_store_{{format_d16|d16_format}}_xyz v[[[LO]]:[[HI]]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_{{.*}}] idxen
 define amdgpu_kernel void @tbuffer_store_d16_xyz(<4 x i32> %rsrc, <4 x half> %data, i32 %vindex) {
 main_body:
   %data_subvec = shufflevector <4 x half> %data, <4 x half> undef, <3 x i32> <i32 0, i32 1, i32 2>
@@ -56,7 +56,7 @@ main_body:
 }
 
 ; GCN-LABEL: {{^}}tbuffer_store_d16_xyzw:
-; GCN-DAG: s_load_dwordx2 s[[[S_DATA_0:[0-9]+]]:[[S_DATA_1:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}}, 0x10
+; GCN-DAG: s_load_{{dwordx2|b64}} s[[[S_DATA_0:[0-9]+]]:[[S_DATA_1:[0-9]+]]], s{{\[[0-9]+:[0-9]+\]}}, 0x10
 
 ; UNPACKED-DAG: s_lshr_b32 [[SHR0:s[0-9]+]], s[[S_DATA_0]], 16
 ; UNPACKED-DAG: s_and_b32 [[MASKED0:s[0-9]+]], s[[S_DATA_0]], 0xffff{{$}}
@@ -70,7 +70,7 @@ main_body:
 ; PACKED-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], s[[S_DATA_0]]
 ; PACKED-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], s[[S_DATA_1]]
 ; PREGFX10-PACKED: tbuffer_store_format_d16_xyzw v[[[LO]]:[[HI]]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_NUM_FORMAT_USCALED] idxen
-; GFX10-PACKED: tbuffer_store_format_d16_xyzw v[[[LO]]:[[HI]]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_10_11_11_SSCALED] idxen
+; GFX10-PACKED: tbuffer_store_{{format_d16|d16_format}}_xyzw v[[[LO]]:[[HI]]], v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 format:[BUF_FMT_{{.*}}] idxen
 define amdgpu_kernel void @tbuffer_store_d16_xyzw(<4 x i32> %rsrc, <4 x half> %data, i32 %vindex) {
 main_body:
   call void @llvm.amdgcn.struct.tbuffer.store.v4f16(<4 x half> %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 33, i32 0)
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.fmuladd.f16.ll b/llvm/test/CodeGen/AMDGPU/llvm.fmuladd.f16.ll
index 3bb3f0f2c5eba3..183b26bad7a732 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.fmuladd.f16.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.fmuladd.f16.ll
@@ -1,17 +1,19 @@
-; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,SI %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,VI-FLUSH %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,SI %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,VI-DENORM %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,GFX10,GFX10-FLUSH %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope --check-prefixes=GCN,GFX10,GFX10-DENORM %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,SI %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,VI-FLUSH %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,SI %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,VI-DENORM %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX10PLUS,GFX10PLUS-FLUSH %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx1010 -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX10PLUS,GFX10PLUS-DENORM %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx1100 -denormal-fp-math=preserve-sign -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX10PLUS,GFX10PLUS-FLUSH %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx1100 -denormal-fp-math=ieee -denormal-fp-math-f32=preserve-sign -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX10PLUS,GFX10PLUS-DENORM %s
 
 declare half @llvm.fmuladd.f16(half %a, half %b, half %c)
 declare <2 x half> @llvm.fmuladd.v2f16(<2 x half> %a, <2 x half> %b, <2 x half> %c)
 
 ; GCN-LABEL: {{^}}fmuladd_f16
-; GCN: buffer_load_ushort v[[A_F16:[0-9]+]]
-; GCN: buffer_load_ushort v[[B_F16:[0-9]+]]
-; GCN: buffer_load_ushort v[[C_F16:[0-9]+]]
+; GCN: buffer_load_{{ushort|u16}} v[[A_F16:[0-9]+]]
+; GCN: buffer_load_{{ushort|u16}} v[[B_F16:[0-9]+]]
+; GCN: buffer_load_{{ushort|u16}} v[[C_F16:[0-9]+]]
 ; SI:  v_cvt_f32_f16_e32 v[[A_F32:[0-9]+]], v[[A_F16]]
 ; SI:  v_cvt_f32_f16_e32 v[[B_F32:[0-9]+]], v[[B_F16]]
 ; SI:  v_cvt_f32_f16_e32 v[[C_F32:[0-9]+]], v[[C_F16]]
@@ -25,12 +27,12 @@ declare <2 x half> @llvm.fmuladd.v2f16(<2 x half> %a, <2 x half> %b, <2 x half>
 ; VI-DENORM: v_fma_f16 [[RESULT:v[0-9]+]], v[[A_F16]], v[[B_F16]], v[[C_F16]]
 ; VI-DENORM: buffer_store_short [[RESULT]]
 
-; GFX10-FLUSH: v_mul_f16_e32 [[MUL:v[0-9]+]], v[[A_F16]], v[[B_F16]]
-; GFX10-FLUSH: v_add_f16_e32 [[ADD:v[0-9]+]], [[MUL]], v[[C_F16]]
-; GFX10-FLUSH: buffer_store_short [[ADD]]
+; GFX10PLUS-FLUSH: v_mul_f16_e32 [[MUL:v[0-9]+]], v[[A_F16]], v[[B_F16]]
+; GFX10PLUS-FLUSH: v_add_f16_e32 [[ADD:v[0-9]+]], [[MUL]], v[[C_F16]]
+; GFX10PLUS-FLUSH: buffer_store_{{short|b16}} [[ADD]]
 
-; GFX10-DENORM: v_fmac_f16_e32 v[[C_F16]], v[[A_F16]], v[[B_F16]]
-; GFX10-DENORM: buffer_store_short v[[C_F16]],
+; GFX10PLUS-DENORM: v_fmac_f16_e32 v[[C_F16]], v[[A_F16]], v[[B_F16]]
+; GFX10PLUS-DENORM: buffer_store_{{short|b16}} v[[C_F16]],
 
 ; GCN: s_endpgm
 define amdgpu_kernel void @fmuladd_f16(
@@ -47,8 +49,8 @@ define amdgpu_kernel void @fmuladd_f16(
 }
 
 ; GCN-LABEL: {{^}}fmuladd_f16_imm_a
-; GCN: buffer_load_ushort v[[B_F16:[0-9]+]]
-; GCN: buffer_load_ushort v[[C_F16:[0-9]+]]
+; GCN: buffer_load_{{ushort|u16}} v[[B_F16:[0-9]+]]
+; GCN: buffer_load_{{ushort|u16}} v[[C_F16:[0-9]+]]
 ; SI:  v_cvt_f32_f16_e32 v[[B_F32:[0-9]+]], v[[B_F16]]
 ; SI:  v_cvt_f32_f16_e32 v[[C_F32:[0-9]+]], v[[C_F16]]
 ; SI:  v_mac_f32_e32 v[[C_F32]], 0x40400000, v[[B_F32]]
@@ -62,12 +64,12 @@ define amdgpu_kernel void @fmuladd_f16(
 ; VI-DENORM: v_fma_f16 [[RESULT:v[0-9]+]], v[[B_F16]], [[KA]], v[[C_F16]]
 ; VI-DENORM: buffer_store_short [[RESULT]]
 
-; GFX10-FLUSH: v_mul_f16_e32 [[MUL:v[0-9]+]], 0x4200, v[[B_F16]]
-; GFX10-FLUSH: v_add_f16_e32 [[ADD:v[0-9]+]], [[MUL]], v[[C_F16]]
-; GFX10-FLUSH: buffer_store_short [[ADD]]
+; GFX10PLUS-FLUSH: v_mul_f16_e32 [[MUL:v[0-9]+]], 0x4200, v[[B_F16]]
+; GFX10PLUS-FLUSH: v_add_f16_e32 [[ADD:v[0-9]+]], [[MUL]], v[[C_F16]]
+; GFX10PLUS-FLUSH: buffer_store_{{short|b16}} [[ADD]]
 
-; GFX10-DENORM: v_fmac_f16_e32 v[[C_F16]], 0x4200, v[[B_F16]]
-; GFX10-DENORM: buffer_store_short v[[C_F16]],
+; GFX10PLUS-DENORM: v_fmac_f16_e32 v[[C_F16]], 0x4200, v[[B_F16]]
+; GFX10PLUS-DENORM: buffer_store_{{short|b16}} v[[C_F16]],
 
 ; GCN: s_endpgm
 define amdgpu_kernel void @fmuladd_f16_imm_a(
@@ -82,8 +84,8 @@ define amdgpu_kernel void @fmuladd_f16_imm_a(
 }
 
 ; GCN-LABEL: {{^}}fmuladd_f16_imm_b
-; GCN: buffer_load_ushort v[[A_F16:[0-9]+]]
-; GCN: buffer_load_ushort v[[C_F16:[0-9]+]]
+; GCN: buffer_load_{{ushort|u16}} v[[A_F16:[0-9]+]]
+; GCN: buffer_load_{{ushort|u16}} v[[C_F16:[0-9]+]]
 ; SI:  v_cvt_f32_f16_e32 v[[A_F32:[0-9]+]], v[[A_F16]]
 ; SI:  v_cvt_f32_f16_e32 v[[C_F32:[0-9]+]], v[[C_F16]]
 ; SI:  v_mac_f32_e32 v[[C_F32]], 0x40400000, v[[A_F32]]
@@ -97,12 +99,12 @@ define amdgpu_kernel void @fmuladd_f16_imm_a(
 ; VI-DENORM: v_fma_f16 [[RESULT:v[0-9]+]], v[[A_F16]], [[KA]], v[[C_F16]]
 ; VI-DENORM: buffer_store_short [[RESULT]]
 
-; GFX10-FLUSH: v_mul_f16_e32 [[MUL:v[0-9]+]], 0x4200, v[[A_F16]]
-; GFX10-FLUSH: v_add_f16_e32 [[ADD:v[0-9]+]], [[MUL]], v[[C_F16]]
-; GFX10-FLUSH: buffer_store_short [[ADD]]
+; GFX10PLUS-FLUSH: v_mul_f16_e32 [[MUL:v[0-9]+]], 0x4200, v[[A_F16]]
+; GFX10PLUS-FLUSH: v_add_f16_e32 [[ADD:v[0-9]+]], [[MUL]], v[[C_F16]]
+; GFX10PLUS-FLUSH: buffer_store_{{short|b16}} [[ADD]]
 
-; GFX10-DENORM: v_fmac_f16_e32 v[[C_F16]], 0x4200, v[[A_F16]]
-; GFX10-DENORM: buffer_store_short v[[C_F16]],
+; GFX10PLUS-DENORM: v_fmac_f16_e32 v[[C_F16]], 0x4200, v[[A_F16]]
+; GFX10PLUS-DENORM: buffer_store_{{short|b16}} v[[C_F16]],
 
 ; GCN: s_endpgm
 define amdgpu_kernel void @fmuladd_f16_imm_b(
@@ -129,9 +131,9 @@ define amdgpu_kernel void @fmuladd_f16_imm_b(
 ; VI-DENORM: buffer_load_dword v[[B_V2_F16:[0-9]+]]
 ; VI-DENORM: buffer_load_dword v[[C_V2_F16:[0-9]+]]
 
-; GFX10: buffer_load_dword v[[A_V2_F16:[0-9]+]]
-; GFX10: buffer_load_dword v[[B_V2_F16:[0-9]+]]
-; GFX10: buffer_load_dword v[[C_V2_F16:[0-9]+]]
+; GFX10PLUS: buffer_load_{{dword|b32}} v[[A_V2_F16:[0-9]+]]
+; GFX10PLUS: buffer_load_{{dword|b32}} v[[B_V2_F16:[0-9]+]]
+; GFX10PLUS: buffer_load_{{dword|b32}} v[[C_V2_F16:[0-9]+]]
 
 ; SI: v_cvt_f32_f16_e32 v[[A_F32_0:[0-9]+]], v[[A_V2_F16]]
 ; SI: v_lshrrev_b32_e32 v[[A_F16_1:[0-9]+]], 16, v[[A_V2_F16]]
@@ -167,12 +169,12 @@ define amdgpu_kernel void @fmuladd_f16_imm_b(
 ; VI-DENORM-NOT: v_and_b32
 ; VI-DENORM: v_or_b32_e32 v[[R_V2_F16:[0-9]+]], v[[RES0]], v[[R_F16_HI]]
 
-; GFX10-FLUSH: v_pk_mul_f16 [[MUL:v[0-9]+]], v[[A_V2_F16]], v[[B_V2_F16]]
-; GFX10-FLUSH: v_pk_add_f16 v[[R_V2_F16:[0-9]+]], [[MUL]], v[[C_V2_F16]]
+; GFX10PLUS-FLUSH: v_pk_mul_f16 [[MUL:v[0-9]+]], v[[A_V2_F16]], v[[B_V2_F16]]
+; GFX10PLUS-FLUSH: v_pk_add_f16 v[[R_V2_F16:[0-9]+]], [[MUL]], v[[C_V2_F16]]
 
-; GFX10-DENORM: v_pk_fma_f16 v[[R_V2_F16:[0-9]+]], v[[A_V2_F16]], v[[B_V2_F16]], v[[C_V2_F16]]
+; GFX10PLUS-DENORM: v_pk_fma_f16 v[[R_V2_F16:[0-9]+]], v[[A_V2_F16]], v[[B_V2_F16]], v[[C_V2_F16]]
 
-; GCN: buffer_store_dword v[[R_V2_F16]]
+; GCN: buffer_store_{{dword|b32}} v[[R_V2_F16]]
 define amdgpu_kernel void @fmuladd_v2f16(
     <2 x half> addrspace(1)* %r,
     <2 x half> addrspace(1)* %a,
diff --git a/llvm/test/CodeGen/AMDGPU/madak.ll b/llvm/test/CodeGen/AMDGPU/madak.ll
index e9b6c7f8d5fb4b..46dc93f18cdafe 100644
--- a/llvm/test/CodeGen/AMDGPU/madak.ll
+++ b/llvm/test/CodeGen/AMDGPU/madak.ll
@@ -1,9 +1,10 @@
 ; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX6,GFX6_8_9,MAD %s
-; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8,GFX6_8_9,GFX8_9,GFX8_9_10,MAD %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,GFX6_8_9,GFX8_9,GFX8_9_10,MAD %s
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10,GFX8_9_10,GFX10-MAD %s
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -fp-contract=fast < %s | FileCheck -check-prefixes=GCN,GFX10,GFX8_9_10,FMA,GFX10-FMA %s
-; RUN: llc -march=amdgcn -mcpu=gfx940 -verify-machineinstrs -fp-contract=fast < %s | FileCheck -check-prefixes=GCN,GFX9,GFX8_9_10,FMA,GFX940-FMA %s
+; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8,GFX6_8_9,GFX8_9,GFX8PLUS,MAD %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,GFX6_8_9,GFX8_9,GFX8PLUS,MAD %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10PLUS,GFX8PLUS,GFX10PLUS-MAD %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -fp-contract=fast < %s | FileCheck -check-prefixes=GCN,GFX10PLUS,GFX8PLUS,FMA,GFX10PLUS-FMA %s
+; RUN: llc -march=amdgcn -mcpu=gfx940 -verify-machineinstrs -fp-contract=fast < %s | FileCheck -check-prefixes=GCN,GFX9,GFX8PLUS,FMA,GFX940-FMA %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs -fp-contract=fast < %s | FileCheck -check-prefixes=GCN,GFX10PLUS,GFX8PLUS,FMA,GFX10PLUS-FMA %s
 
 declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
 declare float @llvm.fabs.f32(float) nounwind readnone
@@ -15,10 +16,10 @@ declare float @llvm.fabs.f32(float) nounwind readnone
 ; GFX8: {{flat|global}}_load_dword [[VB:v[0-9]+]]
 ; GFX9: {{flat|global}}_load_dword [[VA:v[0-9]+]]
 ; GFX9: {{flat|global}}_load_dword [[VB:v[0-9]+]]
-; GFX10: {{flat|global}}_load_dword [[VA:v[0-9]+]]
-; GFX10: {{flat|global}}_load_dword [[VB:v[0-9]+]]
+; GFX10PLUS: {{flat|global}}_load_{{dword|b32}} [[VA:v[0-9]+]]
+; GFX10PLUS: {{flat|global}}_load_{{dword|b32}} [[VB:v[0-9]+]]
 ; MAD:   v_madak_f32 {{v[0-9]+}}, [[VA]], [[VB]], 0x41200000
-; GFX10-MAD:   v_madak_f32 {{v[0-9]+}}, [[VA]], [[VB]], 0x41200000
+; GFX10PLUS-MAD: v_madak_f32 {{v[0-9]+}}, [[VA]], [[VB]], 0x41200000
 ; FMA:   v_fmaak_f32 {{v[0-9]+}}, [[VA]], [[VB]], 0x41200000
 define amdgpu_kernel void @madak_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in.a, float addrspace(1)* noalias %in.b) #0 {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
@@ -44,16 +45,16 @@ define amdgpu_kernel void @madak_f32(float addrspace(1)* noalias %out, float add
 ; GFX6-DAG:     buffer_load_dword [[VA:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 glc{{$}}
 ; GFX6-DAG:     buffer_load_dword [[VB:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4
 ; GFX6-DAG:     buffer_load_dword [[VC:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:8
-; GFX8_9_10:    {{flat|global}}_load_dword [[VA:v[0-9]+]],
-; GFX8_9_10:    {{flat|global}}_load_dword [[VB:v[0-9]+]],
-; GFX8_9_10:    {{flat|global}}_load_dword [[VC:v[0-9]+]],
+; GFX8PLUS:     {{flat|global}}_load_{{dword|b32}} [[VA:v[0-9]+]],
+; GFX8PLUS:     {{flat|global}}_load_{{dword|b32}} [[VB:v[0-9]+]],
+; GFX8PLUS:     {{flat|global}}_load_{{dword|b32}} [[VC:v[0-9]+]],
 ; GFX6-DAG:     v_mov_b32_e32 [[VK:v[0-9]+]], 0x41200000
 ; GFX8-DAG:     v_mov_b32_e32 [[VK:v[0-9]+]], 0x41200000
 ; GFX6_8_9-DAG: v_madak_f32 {{v[0-9]+}}, [[VA]], [[VB]], 0x41200000
-; GFX10-MAD-DAG:v_madak_f32 {{v[0-9]+}}, [[VA]], [[VB]], 0x41200000
+; GFX10PLUS-MAD-DAG: v_madak_f32 {{v[0-9]+}}, [[VA]], [[VB]], 0x41200000
 ; FMA-DAG:      v_fmaak_f32 {{v[0-9]+}}, [[VA]], [[VB]], 0x41200000
 ; MAD-DAG:      v_mac_f32_e32 [[VK]], [[VA]], [[VC]]
-; GFX10-FMA-DAG:v_fmaak_f32 {{v[0-9]+}}, [[VA]], [[VC]], 0x41200000
+; GFX10PLUS-FMA-DAG: v_fmaak_f32 {{v[0-9]+}}, [[VA]], [[VC]], 0x41200000
 ; GFX940-FMA-DAG:v_fmac_f32_e32 [[VK]], [[VA]], [[VC]]
 ; GCN:          s_endpgm
 define amdgpu_kernel void @madak_2_use_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in) #0 {
@@ -81,9 +82,9 @@ define amdgpu_kernel void @madak_2_use_f32(float addrspace(1)* noalias %out, flo
 }
 
 ; GCN-LABEL: {{^}}madak_m_inline_imm_f32:
-; GCN: {{buffer|flat|global}}_load_dword [[VA:v[0-9]+]]
+; GCN: {{buffer|flat|global}}_load_{{dword|b32}} [[VA:v[0-9]+]]
 ; MAD: v_madak_f32 {{v[0-9]+}}, 4.0, [[VA]], 0x41200000
-; GFX10-MAD: v_madak_f32 {{v[0-9]+}}, 4.0, [[VA]], 0x41200000
+; GFX10PLUS-MAD: v_madak_f32 {{v[0-9]+}}, 4.0, [[VA]], 0x41200000
 ; FMA: v_fmaak_f32 {{v[0-9]+}}, 4.0, [[VA]], 0x41200000
 define amdgpu_kernel void @madak_m_inline_imm_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in.a) #0 {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
@@ -108,10 +109,10 @@ define amdgpu_kernel void @madak_m_inline_imm_f32(float addrspace(1)* noalias %o
 ; GFX8: {{flat|global}}_load_dword [[VB:v[0-9]+]]
 ; GFX9: {{flat|global}}_load_dword [[VA:v[0-9]+]]
 ; GFX9: {{flat|global}}_load_dword [[VB:v[0-9]+]]
-; GFX10: {{flat|global}}_load_dword [[VA:v[0-9]+]]
-; GFX10: {{flat|global}}_load_dword [[VB:v[0-9]+]]
+; GFX10PLUS: {{flat|global}}_load_{{dword|b32}} [[VA:v[0-9]+]]
+; GFX10PLUS: {{flat|global}}_load_{{dword|b32}} [[VB:v[0-9]+]]
 ; MAD:   v_mad_f32 {{v[0-9]+}}, [[VA]], [[VB]], 4.0
-; GFX10-MAD:   v_mad_f32 {{v[0-9]+}}, [[VA]], [[VB]], 4.0
+; GFX10PLUS-MAD: v_mad_f32 {{v[0-9]+}}, [[VA]], [[VB]], 4.0
 ; FMA:   v_fma_f32 {{v[0-9]+}}, [[VA]], [[VB]], 4.0
 define amdgpu_kernel void @madak_inline_imm_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in.a, float addrspace(1)* noalias %in.b) #0 {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
@@ -130,13 +131,13 @@ define amdgpu_kernel void @madak_inline_imm_f32(float addrspace(1)* noalias %out
 
 ; We can't use an SGPR when forming madak
 ; GCN-LABEL: {{^}}s_v_madak_f32:
-; GCN-DAG:      s_load_dword [[SB:s[0-9]+]]
+; GCN-DAG:      s_load_{{dword|b32}} [[SB:s[0-9]+]]
 ; GFX6_8_9-DAG: v_mov_b32_e32 [[VK:v[0-9]+]], 0x41200000
-; GCN-DAG:      {{buffer|flat|global}}_load_dword{{(_addtid)?}} [[VA:v[0-9]+]]
+; GCN-DAG:      {{buffer|flat|global}}_load_{{dword|b32}}{{(_addtid)?}} [[VA:v[0-9]+]]
 ; GCN-NOT:      v_madak_f32
 ; GFX6_8_9:     v_mac_f32_e32 [[VK]], [[SB]], [[VA]]
-; GFX10-MAD:    v_madak_f32 v{{[0-9]+}}, [[SB]], [[VA]], 0x41200000
-; GFX10-FMA:    v_fmaak_f32 v{{[0-9]+}}, [[SB]], [[VA]], 0x41200000
+; GFX10PLUS-MAD: v_madak_f32 v{{[0-9]+}}, [[SB]], [[VA]], 0x41200000
+; GFX10PLUS-FMA: v_fmaak_f32 v{{[0-9]+}}, [[SB]], [[VA]], 0x41200000
 ; GFX940-FMA:   v_fmac_f32_e32 v{{[0-9]+}}, [[SB]], [[VA]]
 define amdgpu_kernel void @s_v_madak_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in.a, float %b) #0 {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
@@ -152,13 +153,13 @@ define amdgpu_kernel void @s_v_madak_f32(float addrspace(1)* noalias %out, float
 }
 
 ; GCN-LABEL: @v_s_madak_f32
-; GCN-DAG:       s_load_dword [[SB:s[0-9]+]]
+; GCN-DAG:       s_load_{{dword|b32}} [[SB:s[0-9]+]]
 ; GFX6_8_9-DAG:  v_mov_b32_e32 [[VK:v[0-9]+]], 0x41200000
-; GCN-DAG:       {{buffer|flat|global}}_load_dword{{(_addtid)?}} [[VA:v[0-9]+]]
+; GCN-DAG:       {{buffer|flat|global}}_load_{{dword|b32}}{{(_addtid)?}} [[VA:v[0-9]+]]
 ; GFX6_8_9-NOT:  v_madak_f32
 ; GFX6_8_9:      v_mac_f32_e32 [[VK]], [[SB]], [[VA]]
-; GFX10-MAD:     v_madak_f32 v{{[0-9]+}}, [[SB]], [[VA]], 0x41200000
-; GFX10-FMA:     v_fmaak_f32 v{{[0-9]+}}, [[SB]], [[VA]], 0x41200000
+; GFX10PLUS-MAD: v_madak_f32 v{{[0-9]+}}, [[SB]], [[VA]], 0x41200000
+; GFX10PLUS-FMA: v_fmaak_f32 v{{[0-9]+}}, [[SB]], [[VA]], 0x41200000
 ; GFX940-FMA:    v_fmac_f32_e32 v{{[0-9]+}}, [[SB]], [[VA]]
 define amdgpu_kernel void @v_s_madak_f32(float addrspace(1)* noalias %out, float %a, float addrspace(1)* noalias %in.b) #0 {
   %tid = tail call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
@@ -176,8 +177,8 @@ define amdgpu_kernel void @v_s_madak_f32(float addrspace(1)* noalias %out, float
 ; GCN-LABEL: {{^}}s_s_madak_f32:
 ; GCN-NOT: v_madak_f32
 ; GFX8_9:  v_mac_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
-; GFX10-MAD: v_mac_f32_e64 {{v[0-9]+}}, {{s[0-9]+}}, {{s[0-9]+}}
-; GFX10-FMA: v_fmac_f32_e64 {{v[0-9]+}}, {{s[0-9]+}}, {{s[0-9]+}}
+; GFX10PLUS-MAD: v_mac_f32_e64 {{v[0-9]+}}, {{s[0-9]+}}, {{s[0-9]+}}
+; GFX10PLUS-FMA: v_fmac_f32_e64 {{v[0-9]+}}, {{s[0-9]+}}, {{s[0-9]+}}
 ; GFX940-FMA: v_fmac_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
 define amdgpu_kernel void @s_s_madak_f32(float addrspace(1)* %out, float %a, float %b) #0 {
   %mul = fmul float %a, %b
@@ -189,11 +190,11 @@ define amdgpu_kernel void @s_s_madak_f32(float addrspace(1)* %out, float %a, flo
 ; GCN-LABEL: {{^}}no_madak_src0_modifier_f32:
 ; GFX6:      buffer_load_dword [[VA:v[0-9]+]]
 ; GFX6:      buffer_load_dword [[VB:v[0-9]+]]
-; GFX8_9_10: {{flat|global}}_load_dword [[VB:v[0-9]+]]
-; GFX8_9_10: {{flat|global}}_load_dword [[VA:v[0-9]+]]
+; GFX8PLUS:  {{flat|global}}_load_{{dword|b32}} [[VB:v[0-9]+]]
+; GFX8PLUS:  {{flat|global}}_load_{{dword|b32}} [[VA:v[0-9]+]]
 ; GFX6_8_9:  v_mad_f32 {{v[0-9]+}}, |{{v[0-9]+}}|, {{v[0-9]+}}, {{[sv][0-9]+}}
-; GFX10-MAD: v_mad_f32 {{v[0-9]+}}, |{{v[0-9]+}}|, {{v[0-9]+}}, 0x41200000
-; GFX10-FMA: v_fma_f32 {{v[0-9]+}}, |{{v[0-9]+}}|, {{v[0-9]+}}, 0x41200000
+; GFX10PLUS-MAD: v_mad_f32 {{v[0-9]+}}, |{{v[0-9]+}}|, {{v[0-9]+}}, 0x41200000
+; GFX10PLUS-FMA: v_fma_f32 {{v[0-9]+}}, |{{v[0-9]+}}|, {{v[0-9]+}}, 0x41200000
 ; GFX940-FMA: v_fma_f32 {{v[0-9]+}}, |{{v[0-9]+}}|, {{v[0-9]+}}, {{s[0-9]+}}
 ; GCN:       s_endpgm
 define amdgpu_kernel void @no_madak_src0_modifier_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in.a, float addrspace(1)* noalias %in.b) #0 {
@@ -216,11 +217,11 @@ define amdgpu_kernel void @no_madak_src0_modifier_f32(float addrspace(1)* noalia
 ; GCN-LABEL: {{^}}no_madak_src1_modifier_f32:
 ; GFX6:      buffer_load_dword [[VA:v[0-9]+]]
 ; GFX6:      buffer_load_dword [[VB:v[0-9]+]]
-; GFX8_9_10: {{flat|global}}_load_dword [[VB:v[0-9]+]]
-; GFX8_9_10: {{flat|global}}_load_dword [[VA:v[0-9]+]]
+; GFX8PLUS:  {{flat|global}}_load_{{dword|b32}} [[VB:v[0-9]+]]
+; GFX8PLUS:  {{flat|global}}_load_{{dword|b32}} [[VA:v[0-9]+]]
 ; GFX6_8_9:  v_mad_f32 {{v[0-9]+}}, {{v[0-9]+}}, |{{v[0-9]+}}|, {{[sv][0-9]+}}
-; GFX10-MAD: v_mad_f32 {{v[0-9]+}}, {{v[0-9]+}}, |{{v[0-9]+}}|, 0x41200000
-; GFX10-FMA: v_fma_f32 {{v[0-9]+}}, {{v[0-9]+}}, |{{v[0-9]+}}|, 0x41200000
+; GFX10PLUS-MAD: v_mad_f32 {{v[0-9]+}}, {{v[0-9]+}}, |{{v[0-9]+}}|, 0x41200000
+; GFX10PLUS-FMA: v_fma_f32 {{v[0-9]+}}, {{v[0-9]+}}, |{{v[0-9]+}}|, 0x41200000
 ; GFX940-FMA: v_fma_f32 {{v[0-9]+}}, {{v[0-9]+}}, |{{v[0-9]+}}|, {{s[0-9]+}}
 ; GCN:       s_endpgm
 define amdgpu_kernel void @no_madak_src1_modifier_f32(float addrspace(1)* noalias %out, float addrspace(1)* noalias %in.a, float addrspace(1)* noalias %in.b) #0 {
@@ -244,17 +245,17 @@ define amdgpu_kernel void @no_madak_src1_modifier_f32(float addrspace(1)* noalia
 ; because the implicit immediate already uses the constant bus.
 ; On GFX10+ we can use two scalar operands.
 ; GCN-LABEL: {{^}}madak_constant_bus_violation:
-; GCN:       {{buffer|flat|global}}_load_dword [[VGPR:v[0-9]+]]
-; GCN:       s_load_dword [[SGPR0:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, {{0x12|0x48}}
+; GCN:       {{buffer|flat|global}}_load_{{dword|b32}} [[VGPR:v[0-9]+]]
+; GCN:       s_load_{{dword|b32}} [[SGPR0:s[0-9]+]], s{{\[[0-9]+:[0-9]+\]}}, {{0x12|0x48}}
 ; MAD:       v_mov_b32_e32 [[MADAK:v[0-9]+]], 0x42280000
 ; MAD:       v_mac_f32_e64 [[MADAK]], [[SGPR0]], 0.5
-; GFX10:     v_mov_b32_e32 [[SGPR0_VCOPY:v[0-9]+]], [[SGPR0]]
-; GFX10-MAD: v_madak_f32 [[MADAK:v[0-9]+]], 0.5, [[SGPR0_VCOPY]], 0x42280000
-; GFX10-FMA: v_fmaak_f32 [[MADAK:v[0-9]+]], 0.5, [[SGPR0_VCOPY]], 0x42280000
+; GFX10PLUS: v_mov_b32_e32 [[SGPR0_VCOPY:v[0-9]+]], [[SGPR0]]
+; GFX10PLUS-MAD: v_madak_f32 [[MADAK:v[0-9]+]], 0.5, [[SGPR0_VCOPY]], 0x42280000
+; GFX10PLUS-FMA: v_fmaak_f32 [[MADAK:v[0-9]+]], 0.5, [[SGPR0_VCOPY]], 0x42280000
 ; GFX940-FMA: v_fmac_f32_e64 [[MADAK:v[0-9]+]], [[SGPR0]], 0.5
 ; GCN:       v_mul_f32_e32 [[MUL:v[0-9]+]], [[MADAK]], [[VGPR]]
 ; GFX6:      buffer_store_dword [[MUL]]
-; GFX8_9_10: {{flat|global}}_store_dword v[{{[0-9:]+}}], [[MUL]]
+; GFX8PLUS:  {{flat|global}}_store_{{dword|b32}} v[{{[0-9:]+}}], [[MUL]]
 define amdgpu_kernel void @madak_constant_bus_violation(i32 %arg1, [8 x i32], float %sgpr0, float %sgpr1) #0 {
 bb:
   %tmp = icmp eq i32 %arg1, 0
diff --git a/llvm/test/CodeGen/AMDGPU/min.ll b/llvm/test/CodeGen/AMDGPU/min.ll
index 74a090c5f673bf..1dfc85d2ece60e 100644
--- a/llvm/test/CodeGen/AMDGPU/min.ll
+++ b/llvm/test/CodeGen/AMDGPU/min.ll
@@ -1,8 +1,9 @@
-; RUN: llc -march=amdgcn -mtriple=amdgcn-amd-amdhsa -mcpu=kaveri -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,CI,FUNC %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,VI,GFX8_9_10,FUNC %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,GFX8_9_10,FUNC %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX10,GFX9_10,GFX8_9_10,FUNC %s
-; RUN: llc -march=r600 -mtriple=r600-- -mcpu=cypress -verify-machineinstrs < %s | FileCheck --check-prefixes=EG,FUNC %s
+; RUN: llc -mtriple=r600-- -mcpu=cypress -verify-machineinstrs < %s | FileCheck --check-prefixes=EG,FUNC %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,CI,FUNC %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,VI,GFX8_9_10,FUNC %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,GFX8_9_10,FUNC %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX10,GFX9_10,GFX8_9_10,FUNC %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -amdgpu-enable-vopd=0 -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX10,GFX9_10,GFX8_9_10,FUNC %s
 
 ; FUNC-LABEL: {{^}}v_test_imin_sle_i32:
 ; GCN: v_min_i32_e32
@@ -61,8 +62,8 @@ define amdgpu_kernel void @s_test_imin_sle_v4i32(<4 x i32> addrspace(1)* %out, <
 }
 
 ; FUNC-LABEL: {{^}}s_test_imin_sle_i8:
-; GCN: s_load_dword
-; GCN: s_load_dword
+; GCN: s_load_{{dword|b32}}
+; GCN: s_load_{{dword|b32}}
 ; GCN: s_sext_i32_i8
 ; GCN: s_sext_i32_i8
 ; GCN: s_min_i32
@@ -75,9 +76,9 @@ define amdgpu_kernel void @s_test_imin_sle_i8(i8 addrspace(1)* %out, [8 x i32],
 
 ; FIXME: Why vector and sdwa for last element?
 ; FUNC-LABEL: {{^}}s_test_imin_sle_v4i8:
-; GCN-DAG: s_load_dwordx2
-; GCN-DAG: s_load_dword s
-; GCN-DAG: s_load_dword s
+; GCN-DAG: s_load_{{dwordx2|b64}}
+; GCN-DAG: s_load_{{dword|b32}} s
+; GCN-DAG: s_load_{{dword|b32}} s
 ; GCN-NOT: _load_
 
 ; CI: s_min_i32
@@ -107,7 +108,7 @@ define amdgpu_kernel void @s_test_imin_sle_v4i8(<4 x i8> addrspace(1)* %out, [8
 }
 
 ; FUNC-LABEL: {{^}}s_test_imin_sle_v2i16:
-; GCN: s_load_dwordx4 s
+; GCN: s_load_{{dwordx4|b128}} s
 
 ; CI: s_ashr_i32
 ; CI: s_sext_i32_i16
@@ -350,8 +351,8 @@ define amdgpu_kernel void @v_test_umin_ult_i32(i32 addrspace(1)* %out, i32 addrs
 ; CI: {{buffer|flat|global}}_load_ubyte
 ; CI: v_min_u32_e32
 
-; GFX8_9_10: {{flat|global}}_load_ubyte
-; GFX8_9_10: {{flat|global}}_load_ubyte
+; GFX8_9_10: {{flat|global}}_load_{{ubyte|u8}}
+; GFX8_9_10: {{flat|global}}_load_{{ubyte|u8}}
 ; GFX8_9:    v_min_u16_e32
 ; GFX10:     v_min_u16
 
@@ -492,11 +493,11 @@ define amdgpu_kernel void @s_test_umin_ult_v8i16(<8 x i16> addrspace(1)* %out, <
 
 ; Make sure redundant and removed
 ; FUNC-LABEL: {{^}}simplify_demanded_bits_test_umin_ult_i16:
-; GCN-DAG: s_load_dword [[A:s[0-9]+]], {{s\[[0-9]+:[0-9]+\]}}, {{0xa|0x28}}
-; GCN-DAG: s_load_dword [[B:s[0-9]+]], {{s\[[0-9]+:[0-9]+\]}}, {{0x13|0x4c}}
+; GCN-DAG: s_load_{{dword|b32}} [[A:s[0-9]+]], {{s\[[0-9]+:[0-9]+\]}}, {{0xa|0x28}}
+; GCN-DAG: s_load_{{dword|b32}} [[B:s[0-9]+]], {{s\[[0-9]+:[0-9]+\]}}, {{0x13|0x4c}}
 ; GCN: s_min_u32 [[MIN:s[0-9]+]], s{{[0-9]}}, s{{[0-9]}}
-; GCN: v_mov_b32_e32 [[VMIN:v[0-9]+]], s{{[0-9]}}
-; GCN: buffer_store_dword [[VMIN]]
+; GCN: v_mov_b32_e32 [[VMIN:v[0-9]+]], [[MIN]]
+; GCN: {{flat|global}}_store_{{dword|b32}} v{{.+}}, [[VMIN]]
 
 ; EG: MIN_UINT
 define amdgpu_kernel void @simplify_demanded_bits_test_umin_ult_i16(i32 addrspace(1)* %out, [8 x i32], i16 zeroext %a, [8 x i32], i16 zeroext %b) #0 {
@@ -512,14 +513,14 @@ define amdgpu_kernel void @simplify_demanded_bits_test_umin_ult_i16(i32 addrspac
 ; Make sure redundant sign_extend_inreg removed.
 
 ; FUNC-LABEL: {{^}}simplify_demanded_bits_test_min_slt_i16:
-; GCN-DAG: s_load_dword [[A:s[0-9]+]], {{s\[[0-9]+:[0-9]+\]}}, {{0xa|0x28}}
-; GCN-DAG: s_load_dword [[B:s[0-9]+]], {{s\[[0-9]+:[0-9]+\]}}, {{0x13|0x4c}}
+; GCN-DAG: s_load_{{dword|b32}} [[A:s[0-9]+]], {{s\[[0-9]+:[0-9]+\]}}, {{0xa|0x28}}
+; GCN-DAG: s_load_{{dword|b32}} [[B:s[0-9]+]], {{s\[[0-9]+:[0-9]+\]}}, {{0x13|0x4c}}
 ; GCN-DAG: s_sext_i32_i16 [[EXT_A:s[0-9]+]], [[A]]
 ; GCN-DAG: s_sext_i32_i16 [[EXT_B:s[0-9]+]], [[B]]
 
 ; GCN: s_min_i32 [[MIN:s[0-9]+]], [[EXT_A]], [[EXT_B]]
 ; GCN: v_mov_b32_e32 [[VMIN:v[0-9]+]], [[MIN]]
-; GCN: buffer_store_dword [[VMIN]]
+; GCN: {{flat|global}}_store_{{dword|b32}} v{{.+}}, [[VMIN]]
 
 ; EG: MIN_INT
 define amdgpu_kernel void @simplify_demanded_bits_test_min_slt_i16(i32 addrspace(1)* %out, [8 x i32], i16 signext %a, [8 x i32], i16 signext %b) #0 {
diff --git a/llvm/test/CodeGen/AMDGPU/mixed_wave32_wave64.ll b/llvm/test/CodeGen/AMDGPU/mixed_wave32_wave64.ll
index 9ac30e0b8de88a..5977566e2d00ba 100644
--- a/llvm/test/CodeGen/AMDGPU/mixed_wave32_wave64.ll
+++ b/llvm/test/CodeGen/AMDGPU/mixed_wave32_wave64.ll
@@ -1,24 +1,25 @@
-; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX10 %s
+; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN %s
+; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN %s
 ;
 ; Check that PS is wave64
-; GFX10-LABEL: _amdgpu_ps_main:
-; GFX10: s_and_saveexec_b64
+; GCN-LABEL: _amdgpu_ps_main:
+; GCN: s_or_b64 exec, exec
 ;
 ; Check that VS is wave32
-; GFX10-LABEL: _amdgpu_vs_main:
-; GFX10: s_and_saveexec_b32
+; GCN-LABEL: _amdgpu_vs_main:
+; GCN: s_or_b32 exec_lo, exec_lo
 ;
 ; Check that GS is wave32
-; GFX10-LABEL: _amdgpu_gs_main:
-; GFX10: s_and_saveexec_b32
+; GCN-LABEL: _amdgpu_gs_main:
+; GCN: s_or_b32 exec_lo, exec_lo
 ;
 ; Check that HS is wave32
-; GFX10-LABEL: _amdgpu_hs_main:
-; GFX10: s_and_saveexec_b32
+; GCN-LABEL: _amdgpu_hs_main:
+; GCN: s_or_b32 exec_lo, exec_lo
 ;
 ; Check that CS is wave32
-; GFX10-LABEL: _amdgpu_cs_main:
-; GFX10: s_and_saveexec_b32
+; GCN-LABEL: _amdgpu_cs_main:
+; GCN: s_or_b32 exec_lo, exec_lo
 ;
 ; Check that:
 ; PS_W32_EN (bit 15) of SPI_PS_IN_CONTROL (0xa1b6) is 0;
@@ -27,7 +28,7 @@
 ; HS_W32_EN (bit 21) of VGT_SHADER_STAGES_EN (0xa2d5) is 1;
 ; CS_W32_EN (bit 15) of COMPUTE_DISPATCH_INITIATOR (0x2e00) is 1.
 ;
-; GFX10: .amd_amdgpu_pal_metadata{{.*}},0x2e00,0x8000,{{.*}}0xa1b6,0x1,{{.*}},0xa2d5,0xe00000,
+; GCN: .amd_amdgpu_pal_metadata{{.*}},0x2e00,0x8000,{{.*}}0xa1b6,0x1,{{.*}},0xa2d5,0xe00000,
 
 define dllexport amdgpu_ps void @_amdgpu_ps_main(float %arg10) #0 {
 .entry:
diff --git a/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm-gfx10.mir b/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm-gfx10.mir
index a0f970879da0c6..fc1b2c38d6002a 100644
--- a/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm-gfx10.mir
+++ b/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm-gfx10.mir
@@ -1,8 +1,9 @@
-# RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass si-load-store-opt -o - %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass si-load-store-opt -o - %s | FileCheck -check-prefixes=GCN,GFX10 %s
+# RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs -run-pass si-load-store-opt -o - %s | FileCheck -check-prefixes=GCN,GFX11 %s
 
-# GFX10-LABEL: name: diffoporder_add
-# GFX10: %{{[0-9]+}}:vreg_64 = GLOBAL_LOAD_DWORDX2 %{{[0-9]+}}, -2048, 0
-# GFX10: %{{[0-9]+}}:vreg_64 = GLOBAL_LOAD_DWORDX2 %{{[0-9]+}}, 0, 0
+# GCN-LABEL: name: diffoporder_add
+# GCN: %{{[0-9]+}}:vreg_64 = GLOBAL_LOAD_DWORDX2 %{{[0-9]+}}, -2048, 0
+# GCN: %{{[0-9]+}}:vreg_64 = GLOBAL_LOAD_DWORDX2 %{{[0-9]+}}, 0, 0
 
 name: diffoporder_add
 body:             |
@@ -43,19 +44,29 @@ body:             |
 ...
 ---
 
-# GFX10-LABEL: name: LowestInMiddle
+# GCN-LABEL: name: LowestInMiddle
 # GFX10: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 6400
-# GFX10: [[BASE_LO:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_5:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_CO_U32_e64 %{{[0-9]+}}, [[S_MOV_B32_1]]
-# GFX10: [[BASE_HI:%[0-9]+]]:vgpr_32, dead %{{[0-9]+}}:sreg_32_xm0_xexec = V_ADDC_U32_e64 %{{[0-9]+}}, 0, killed [[V_ADD_CO_U32_e64_5]]
-# GFX10: [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[BASE_LO]], %subreg.sub0, [[BASE_HI]], %subreg.sub1
+# GFX11: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 11200
+
+# GCN: [[BASE_LO:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_5:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_CO_U32_e64 %{{[0-9]+}}, [[S_MOV_B32_1]]
+# GCN: [[BASE_HI:%[0-9]+]]:vgpr_32, dead %{{[0-9]+}}:sreg_32_xm0_xexec = V_ADDC_U32_e64 %{{[0-9]+}}, 0, killed [[V_ADD_CO_U32_e64_5]]
+# GCN: [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[BASE_LO]], %subreg.sub0, [[BASE_HI]], %subreg.sub1
 # GFX10: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:vreg_64 = GLOBAL_LOAD_DWORDX2 [[REG_SEQUENCE2]], 1600, 0
+# GFX11: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:vreg_64 = GLOBAL_LOAD_DWORDX2 [[REG_SEQUENCE2]], -3200, 0
+#
+# GFX11: [[S_MOV_B32_2:%[0-9]+]]:sgpr_32 = S_MOV_B32 6400
+# GFX11: [[BASE1_LO:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_7:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_CO_U32_e64 %{{[0-9]+}}, [[S_MOV_B32_2]]
+# GFX11: [[BASE1_HI:%[0-9]+]]:vgpr_32, dead %{{[0-9]+}}:sreg_32_xm0_xexec = V_ADDC_U32_e64 %{{[0-9]+}}, 0, killed [[V_ADD_CO_U32_e64_7]]
+# GFX11: [[REG_SEQUENCE3:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[BASE1_LO]], %subreg.sub0, [[BASE1_HI]], %subreg.sub1
 # GFX10: [[GLOBAL_LOAD_DWORDX2_1:%[0-9]+]]:vreg_64 = GLOBAL_LOAD_DWORDX2 [[REG_SEQUENCE2]], 0, 0,
+# GFX11: [[GLOBAL_LOAD_DWORDX2_1:%[0-9]+]]:vreg_64 = GLOBAL_LOAD_DWORDX2 [[REG_SEQUENCE3]], 0, 0,
 #
 # GFX10: [[S_MOV_B32_2:%[0-9]+]]:sgpr_32 = S_MOV_B32 11200
 # GFX10: [[BASE1_LO:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_7:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_CO_U32_e64 %{{[0-9]+}}, [[S_MOV_B32_2]]
 # GFX10: [[BASE1_HI:%[0-9]+]]:vgpr_32, dead %{{[0-9]+}}:sreg_32_xm0_xexec = V_ADDC_U32_e64 %{{[0-9]+}}, 0, killed [[V_ADD_CO_U32_e64_7]]
 # GFX10: [[REG_SEQUENCE3:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[BASE1_LO]], %subreg.sub0, [[BASE1_HI]], %subreg.sub1
 # GFX10: [[GLOBAL_LOAD_DWORDX2_2:%[0-9]+]]:vreg_64 = GLOBAL_LOAD_DWORDX2 [[REG_SEQUENCE3]], 0, 0,
+# GFX11: [[GLOBAL_LOAD_DWORDX2_2:%[0-9]+]]:vreg_64 = GLOBAL_LOAD_DWORDX2 [[REG_SEQUENCE2]], 0, 0,
 
 name: LowestInMiddle
 body:             |
@@ -101,18 +112,22 @@ body:             |
 ...
 ---
 
-# GFX10-LABEL: name: NegativeDistance
+# GCN-LABEL: name: NegativeDistance
 # GFX10: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 8192
-# GFX10: [[BASE_LO:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_5:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_CO_U32_e64 %{{[0-9]+}}, [[S_MOV_B32_1]]
-# GFX10: [[BASE_HI:%[0-9]+]]:vgpr_32, dead %{{[0-9]+}}:sreg_32_xm0_xexec = V_ADDC_U32_e64 %{{[0-9]+}}, 0, killed [[V_ADD_CO_U32_e64_5]]
-# GFX10: [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[BASE_LO]], %subreg.sub0, [[BASE_HI]], %subreg.sub1
+# GFX11: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 10240
+# GCN: [[BASE_LO:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_5:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_CO_U32_e64 %{{[0-9]+}}, [[S_MOV_B32_1]]
+# GCN: [[BASE_HI:%[0-9]+]]:vgpr_32, dead %{{[0-9]+}}:sreg_32_xm0_xexec = V_ADDC_U32_e64 %{{[0-9]+}}, 0, killed [[V_ADD_CO_U32_e64_5]]
+# GCN: [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[BASE_LO]], %subreg.sub0, [[BASE_HI]], %subreg.sub1
 # GFX10: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:vreg_64 = GLOBAL_LOAD_DWORDX2 [[REG_SEQUENCE2]], -2048, 0
+# GFX11: [[GLOBAL_LOAD_DWORDX2_:%[0-9]+]]:vreg_64 = GLOBAL_LOAD_DWORDX2 [[REG_SEQUENCE2]], -4096, 0
 # GFX10: [[GLOBAL_LOAD_DWORDX2_1:%[0-9]+]]:vreg_64 = GLOBAL_LOAD_DWORDX2 [[REG_SEQUENCE2]], 0, 0
+# GFX11: [[GLOBAL_LOAD_DWORDX2_1:%[0-9]+]]:vreg_64 = GLOBAL_LOAD_DWORDX2 [[REG_SEQUENCE2]], -2048, 0
 # GFX10: [[S_MOV_B32_2:%[0-9]+]]:sgpr_32 = S_MOV_B32 10240
 # GFX10: [[BASE1_LO:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_7:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_CO_U32_e64 %{{[0-9]+}}, [[S_MOV_B32_2]]
 # GFX10: [[BASE1_HI:%[0-9]+]]:vgpr_32, dead %{{[0-9]+}}:sreg_32_xm0_xexec = V_ADDC_U32_e64 %{{[0-9]+}}, 0, killed [[V_ADD_CO_U32_e64_7]]
 # GFX10: [[REG_SEQUENCE3:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[BASE1_LO]], %subreg.sub0, [[BASE1_HI]], %subreg.sub1
 # GFX10: [[GLOBAL_LOAD_DWORDX2_2:%[0-9]+]]:vreg_64 = GLOBAL_LOAD_DWORDX2 [[REG_SEQUENCE3]], 0, 0
+# GFX11: [[GLOBAL_LOAD_DWORDX2_2:%[0-9]+]]:vreg_64 = GLOBAL_LOAD_DWORDX2 [[REG_SEQUENCE2]], 0, 0
 
 name: NegativeDistance
 body:             |
@@ -194,9 +209,9 @@ body:             |
 ...
 ---
 
-# GFX10-LABEL: name: diffoporder_add_store
-# GFX10: GLOBAL_STORE_DWORD %{{[0-9]+}}, %0.sub0, 1000, 0
-# GFX10: GLOBAL_STORE_DWORD %{{[0-9]+}}, %0.sub1, 0, 0
+# GCN-LABEL: name: diffoporder_add_store
+# GCN: GLOBAL_STORE_DWORD %{{[0-9]+}}, %0.sub0, 1000, 0
+# GCN: GLOBAL_STORE_DWORD %{{[0-9]+}}, %0.sub1, 0, 0
 
 name: diffoporder_add_store
 body:             |
diff --git a/llvm/test/CodeGen/AMDGPU/scratch-simple.ll b/llvm/test/CodeGen/AMDGPU/scratch-simple.ll
index 9d8397f640ac32..8ae513783b875a 100644
--- a/llvm/test/CodeGen/AMDGPU/scratch-simple.ll
+++ b/llvm/test/CodeGen/AMDGPU/scratch-simple.ll
@@ -1,13 +1,15 @@
 ; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=verde -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,SI,SIVI,MUBUF %s
 ; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx803 -mattr=-flat-for-global -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,VI,SIVI,MUBUF %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,MUBUF,GFX9-MUBUF,GFX9_10-MUBUF %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9PLUS,MUBUF,GFX9-MUBUF,GFX9_10-MUBUF %s
 ; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx900 -filetype=obj -amdgpu-use-divergent-register-indexing < %s | llvm-readobj -r - | FileCheck --check-prefix=RELS %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx1010 -mattr=-flat-for-global -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,MUBUF,GFX10_W32-MUBUF,GFX9_10-MUBUF %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx1010 -mattr=-flat-for-global,+wavefrontsize64 -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,MUBUF,GFX10_W64-MUBUF,GFX9_10-MUBUF %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx900 -mattr=-flat-for-global,+enable-flat-scratch -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,FLATSCR,GFX9-FLATSCR %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx1030 -mattr=-flat-for-global,+enable-flat-scratch -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,FLATSCR,GFX10-FLATSCR %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn--amdpal -mcpu=gfx900 -mattr=-flat-for-global,+enable-flat-scratch -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,FLATSCR,GFX9-FLATSCR-PAL %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn--amdpal -mcpu=gfx1030 -mattr=-flat-for-global,+enable-flat-scratch -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9_10,FLATSCR,GFX10-FLATSCR-PAL %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx1010 -mattr=-flat-for-global -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9PLUS,MUBUF,GFX10_W32-MUBUF,GFX9_10-MUBUF %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx1010 -mattr=-flat-for-global,+wavefrontsize64 -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9PLUS,MUBUF,GFX10_W64-MUBUF,GFX9_10-MUBUF %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx900 -mattr=-flat-for-global,+enable-flat-scratch -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9PLUS,FLATSCR,GFX9-FLATSCR %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx1030 -mattr=-flat-for-global,+enable-flat-scratch -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9PLUS,FLATSCR,GFX10-FLATSCR %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn--amdpal -mcpu=gfx900 -mattr=-flat-for-global,+enable-flat-scratch -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9PLUS,FLATSCR,GFX9-FLATSCR-PAL %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn--amdpal -mcpu=gfx1030 -mattr=-flat-for-global,+enable-flat-scratch -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9PLUS,FLATSCR,GFX10-FLATSCR-PAL %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn-- -mcpu=gfx1100 -mattr=-flat-for-global,+enable-flat-scratch -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9PLUS,GFX11-FLATSCR %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn--amdpal -mcpu=gfx1100 -mattr=-flat-for-global,+enable-flat-scratch -amdgpu-use-divergent-register-indexing -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,GFX9PLUS,GFX11-FLATSCR %s
 
 ; RELS: R_AMDGPU_ABS32_LO SCRATCH_RSRC_DWORD0
 ; RELS: R_AMDGPU_ABS32_LO SCRATCH_RSRC_DWORD1
@@ -69,14 +71,17 @@
 ; MUBUF-DAG:     v_and_b32_e32 [[CLAMP_IDX:v[0-9]+]], 0x1fc, [[BYTES]]
 ; GFX10-FLATSCR: v_and_b32_e32 [[CLAMP_IDX:v[0-9]+]], 0x1fc, v0
 ; GFX10-FLATSCR-PAL: v_and_b32_e32 [[CLAMP_IDX:v[0-9]+]], 0x1fc, v0
+; GFX11-FLATSCR: v_and_b32_e32 [[CLAMP_IDX:v[0-9]+]], 0x1fc, v0
 ; GCN-NOT: s_mov_b32 s0
 
-; GCN-DAG: v_add{{_|_nc_}}{{i|u}}32_e32 [[HI_OFF:v[0-9]+]],{{.*}} 0x280, [[CLAMP_IDX]]
-; GCN-DAG: v_add{{_|_nc_}}{{i|u}}32_e32 [[LO_OFF:v[0-9]+]],{{.*}} {{v2|0x80}}, [[CLAMP_IDX]]
+; MUBUF-DAG: v_add{{_|_nc_}}{{i|u}}32_e32 [[HI_OFF:v[0-9]+]],{{.*}} 0x280, [[CLAMP_IDX]]
+; MUBUF-DAG: v_add{{_|_nc_}}{{i|u}}32_e32 [[LO_OFF:v[0-9]+]],{{.*}} {{v2|0x80}}, [[CLAMP_IDX]]
+; FLATSCR: v_add{{_|_nc_}}{{u32|b32}}_e32 [[LO_OFF:v[0-9]+]],{{.*}} {{v2|0x80}}, [[CLAMP_IDX]]
 
 ; MUBUF: buffer_load_dword {{v[0-9]+}}, [[LO_OFF]], {{s\[[0-9]+:[0-9]+\]}}, 0 offen
 ; MUBUF: buffer_load_dword {{v[0-9]+}}, [[HI_OFF]], {{s\[[0-9]+:[0-9]+\]}}, 0 offen
 ; FLATSCR: scratch_load_dword {{v[0-9]+}}, [[LO_OFF]], off
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, [[CLAMP_IDX]], off offset:128
 define amdgpu_ps float @ps_main(i32 %idx) {
   %v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
   %v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
@@ -128,6 +133,9 @@ define amdgpu_ps float @ps_main(i32 %idx) {
 ; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
 ; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
 
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, {{v[0-9]+}}, off
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, {{v[0-9]+}}, off
+
 define amdgpu_vs float @vs_main(i32 %idx) {
   %v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
   %v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
@@ -174,6 +182,10 @@ define amdgpu_vs float @vs_main(i32 %idx) {
 
 ; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
 ; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
+
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, {{v[0-9]+}}, off
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, {{v[0-9]+}}, off
+
 define amdgpu_cs float @cs_main(i32 %idx) {
   %v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
   %v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
@@ -196,13 +208,16 @@ define amdgpu_cs float @cs_main(i32 %idx) {
 ; SIVI: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
 
 ; GFX9_10-MUBUF: s_mov_b32 s0, SCRATCH_RSRC_DWORD0
-; GFX9_10-NOT:   s_mov_b32 s5
+; GFX9PLUS-NOT:   s_mov_b32 s5
 ; GFX9_10-MUBUF: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
 ; GFX9_10-MUBUF: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
 
 ; FLATSCR-NOT: SCRATCH_RSRC_DWORD
 ; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
 ; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
+
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, {{v[0-9]+}}, off
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, {{v[0-9]+}}, off
 define amdgpu_hs float @hs_main(i32 %idx) {
   %v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
   %v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
@@ -251,6 +266,9 @@ define amdgpu_hs float @hs_main(i32 %idx) {
 ; FLATSCR-NOT: SCRATCH_RSRC_DWORD
 ; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
 ; FLATSCR: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
+
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, {{v[0-9]+}}, off
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, {{v[0-9]+}}, off
 define amdgpu_gs float @gs_main(i32 %idx) {
   %v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
   %v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
@@ -300,7 +318,7 @@ define amdgpu_gs float @gs_main(i32 %idx) {
 ; SIVI: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
 ; SIVI: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
 
-; GFX9_10-NOT: s_mov_b32 s5
+; GFX9PLUS-NOT: s_mov_b32 s5
 ; GFX9_10-MUBUF-DAG: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
 ; GFX9_10-MUBUF-DAG: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, 0 offen
 
@@ -308,6 +326,9 @@ define amdgpu_gs float @gs_main(i32 %idx) {
 
 ; FLATSCR-DAG: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
 ; FLATSCR-DAG: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
+
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, {{v[0-9]+}}, off
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, {{v[0-9]+}}, off
 define amdgpu_hs <{i32, i32, i32, float}> @hs_ir_uses_scratch_offset(i32 inreg, i32 inreg, i32 inreg, i32 inreg, i32 inreg, i32 inreg %swo, i32 %idx) {
   %v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
   %v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
@@ -360,6 +381,9 @@ define amdgpu_hs <{i32, i32, i32, float}> @hs_ir_uses_scratch_offset(i32 inreg,
 
 ; FLATSCR-DAG: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
 ; FLATSCR-DAG: scratch_load_dword {{v[0-9]+}}, {{v[0-9]+}}, off
+
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, {{v[0-9]+}}, off
+; GFX11-FLATSCR: scratch_load_b32 {{v[0-9]+}}, {{v[0-9]+}}, off
 define amdgpu_gs <{i32, i32, i32, float}> @gs_ir_uses_scratch_offset(i32 inreg, i32 inreg, i32 inreg, i32 inreg, i32 inreg, i32 inreg %swo, i32 %idx) {
   %v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
   %v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
diff --git a/llvm/test/CodeGen/AMDGPU/shift-select.ll b/llvm/test/CodeGen/AMDGPU/shift-select.ll
index d825d14893433a..3c6a07ab05d080 100644
--- a/llvm/test/CodeGen/AMDGPU/shift-select.ll
+++ b/llvm/test/CodeGen/AMDGPU/shift-select.ll
@@ -1,6 +1,7 @@
-; RUN: llc -march=amdgcn -mcpu=tahiti -stop-after=instruction-select -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX6 %s
-; RUN: llc -march=amdgcn -mcpu=fiji -stop-after=instruction-select -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8-10 %s
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -stop-after=instruction-select -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX8-10 %s
+; RUN: llc -march=amdgcn -mcpu=tahiti -stop-after=instruction-select -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX6 %s
+; RUN: llc -march=amdgcn -mcpu=fiji -stop-after=instruction-select -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8PLUS %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -stop-after=instruction-select -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8PLUS %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -amdgpu-enable-vopd=0 -stop-after=instruction-select -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8PLUS %s
 
 ; GCN-LABEL: name:            s_shl_i32
 ; GCN: S_LSHL_B32
@@ -12,7 +13,7 @@ define amdgpu_kernel void @s_shl_i32(i32 addrspace(1)* %out, i32 %lhs, i32 %rhs)
 
 ; GCN-LABEL: name:            v_shl_i32
 ; GFX6: V_LSHL_B32_e32
-; GFX8-10: V_LSHLREV_B32_e32
+; GFX8PLUS: V_LSHLREV_B32_e32
 define amdgpu_kernel void @v_shl_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %b_ptr = getelementptr i32, i32 addrspace(1)* %in, i32 %tid
@@ -33,7 +34,7 @@ define amdgpu_kernel void @s_lshr_i32(i32 addrspace(1)* %out, i32 %lhs, i32 %rhs
 
 ; GCN-LABEL: name:            v_lshr_i32
 ; GFX6: V_LSHR_B32_e32
-; GFX8-10: V_LSHRREV_B32_e64
+; GFX8PLUS: V_LSHRREV_B32_e64
 define amdgpu_kernel void @v_lshr_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %b_ptr = getelementptr i32, i32 addrspace(1)* %in, i32 %tid
@@ -54,7 +55,7 @@ define amdgpu_kernel void @s_ashr_i32(i32 addrspace(1)* %out, i32 %lhs, i32 %rhs
 
 ; GCN-LABEL: name:            v_ashr_i32
 ; GFX6: V_ASHR_I32_e32
-; GFX8-10: V_ASHRREV_I32_e64
+; GFX8PLUS: V_ASHRREV_I32_e64
 define amdgpu_kernel void @v_ashr_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %b_ptr = getelementptr i32, i32 addrspace(1)* %in, i32 %tid
diff --git a/llvm/test/CodeGen/AMDGPU/smem-war-hazard.mir b/llvm/test/CodeGen/AMDGPU/smem-war-hazard.mir
index 6735853f5c7438..d69acde0253bb1 100644
--- a/llvm/test/CodeGen/AMDGPU/smem-war-hazard.mir
+++ b/llvm/test/CodeGen/AMDGPU/smem-war-hazard.mir
@@ -1,9 +1,10 @@
-# RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefix=GCN %s
+# RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefixes=GCN,GFX10 %s
+# RUN: llc -march=amdgcn -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefixes=GCN %s
 
 # GCN-LABEL: name: hazard_smem_war
-# GCN:      S_LOAD_DWORD_IMM
-# GCN:      $sgpr_null = S_MOV_B32 0
-# GCN-NEXT: V_CMP_EQ_F32
+# GCN:        S_LOAD_DWORD_IMM
+# GFX10-NEXT: $sgpr_null = S_MOV_B32 0
+# GCN-NEXT:   V_CMP_EQ_F32
 ---
 name: hazard_smem_war
 body: |
@@ -64,10 +65,10 @@ body: |
 ...
 
 # GCN-LABEL: name: hazard_smem_war_only_smem
-# GCN:      S_LOAD_DWORD_IMM
-# GCN-NEXT: S_LOAD_DWORD_IMM
-# GCN-NEXT: $sgpr_null = S_MOV_B32 0
-# GCN-NEXT: V_CMP_EQ_F32
+# GCN:        S_LOAD_DWORD_IMM
+# GCN-NEXT:   S_LOAD_DWORD_IMM
+# GFX10-NEXT: $sgpr_null = S_MOV_B32 0
+# GCN-NEXT:   V_CMP_EQ_F32
 ---
 name: hazard_smem_war_only_smem
 body: |
@@ -95,10 +96,10 @@ body: |
 ...
 
 # GCN-LABEL: name: hazard_smem_war_only_vmcnt_0
-# GCN:      S_LOAD_DWORD_IMM
-# GCN-NEXT: S_WAITCNT 3952{{$}}
-# GCN-NEXT: $sgpr_null = S_MOV_B32 0
-# GCN-NEXT: V_CMP_EQ_F32
+# GCN:        S_LOAD_DWORD_IMM
+# GCN-NEXT:   S_WAITCNT 3952{{$}}
+# GFX10-NEXT: $sgpr_null = S_MOV_B32 0
+# GCN-NEXT:   V_CMP_EQ_F32
 ---
 name: hazard_smem_war_only_vmcnt_0
 body: |
@@ -111,10 +112,10 @@ body: |
 ...
 
 # GCN-LABEL: name: hazard_smem_war_only_expcnt_0
-# GCN:      S_LOAD_DWORD_IMM
-# GCN-NEXT: S_WAITCNT 53007{{$}}
-# GCN-NEXT: $sgpr_null = S_MOV_B32 0
-# GCN-NEXT: V_CMP_EQ_F32
+# GCN:        S_LOAD_DWORD_IMM
+# GCN-NEXT:   S_WAITCNT 53007{{$}}
+# GFX10-NEXT: $sgpr_null = S_MOV_B32 0
+# GCN-NEXT:   V_CMP_EQ_F32
 ---
 name: hazard_smem_war_only_expcnt_0
 body: |
@@ -157,10 +158,10 @@ body: |
 ...
 
 # GCN-LABEL: name: hazard_smem_war_only_waitcnt_lgkmcnt_1
-# GCN:      S_LOAD_DWORD_IMM
-# GCN-NEXT: S_WAITCNT_LGKMCNT
-# GCN-NEXT: $sgpr_null = S_MOV_B32 0
-# GCN-NEXT: V_CMP_EQ_F32
+# GCN:        S_LOAD_DWORD_IMM
+# GCN-NEXT:   S_WAITCNT_LGKMCNT
+# GFX10-NEXT: $sgpr_null = S_MOV_B32 0
+# GCN-NEXT:   V_CMP_EQ_F32
 ---
 name: hazard_smem_war_only_waitcnt_lgkmcnt_1
 body: |
@@ -173,9 +174,9 @@ body: |
 ...
 
 # GCN-LABEL: name: hazard_smem_war_branch
-# GCN:      S_LOAD_DWORD_IMM
-# GCN:      $sgpr_null = S_MOV_B32 0
-# GCN-NEXT: V_CMP_EQ_F32
+# GCN:   S_LOAD_DWORD_IMM
+# GFX10: $sgpr_null = S_MOV_B32 0
+# GCN:   V_CMP_EQ_F32
 ---
 name: hazard_smem_war_branch
 body: |
@@ -192,14 +193,14 @@ body: |
 ...
 
 # GCN-LABEL: name: hazard_smem_war_cbranch
-# GCN:      S_AND_B64
-# GCN:      S_LOAD_DWORD_IMM
-# GCN:      S_CBRANCH_VCCZ
-# GCN-NOT:  $sgpr_null = S_MOV_B32 0
-# GCN:      V_CMP_EQ_F32
-# GCN:      S_ENDPGM 0
-# GCN:      $sgpr_null = S_MOV_B32 0
-# GCN-NEXT: V_CMP_EQ_F32
+# GCN:       S_AND_B64
+# GCN:       S_LOAD_DWORD_IMM
+# GCN:       S_CBRANCH_VCCZ
+# GFX10-NOT: $sgpr_null = S_MOV_B32 0
+# GCN:       V_CMP_EQ_F32
+# GCN:       S_ENDPGM 0
+# GFX10:     $sgpr_null = S_MOV_B32 0
+# GCN:       V_CMP_EQ_F32
 ---
 name: hazard_smem_war_cbranch
 body: |
@@ -222,16 +223,16 @@ body: |
 ...
 
 # GCN-LABEL: name: hazard_smem_war_cbranch_carry
-# GCN:      S_AND_B64
-# GCN:      S_LOAD_DWORD_IMM
-# GCN:      S_CBRANCH_VCCZ
-# GCN-NOT:  $sgpr_null = S_MOV_B32 0
-# GCN:      V_CMP_EQ_F32
-# GCN-NEXT: S_ENDPGM 0
-# GCN-NOT:  $sgpr_null = S_MOV_B32 0
-# GCN:      V_CMP_EQ_F32
-# GCN:      $sgpr_null = S_MOV_B32 0
-# GCN-NEXT: V_CMP_EQ_F32
+# GCN:       S_AND_B64
+# GCN:       S_LOAD_DWORD_IMM
+# GCN:       S_CBRANCH_VCCZ
+# GFX10-NOT: $sgpr_null = S_MOV_B32 0
+# GCN:       V_CMP_EQ_F32
+# GCN-NEXT:  S_ENDPGM 0
+# GFX10-NOT: $sgpr_null = S_MOV_B32 0
+# GCN:       V_CMP_EQ_F32
+# GFX10:     $sgpr_null = S_MOV_B32 0
+# GCN:       V_CMP_EQ_F32
 ---
 name: hazard_smem_war_cbranch_carry
 body: |
@@ -259,9 +260,9 @@ body: |
 ...
 
 # GCN-LABEL: name: hazard_smem_war_backedge
-# GCN:      $sgpr_null = S_MOV_B32 0
-# GCN-NEXT: V_CMP_EQ_F32
-# GCN:      S_LOAD_DWORD_IMM
+# GFX10: $sgpr_null = S_MOV_B32 0
+# GCN:   V_CMP_EQ_F32
+# GCN:   S_LOAD_DWORD_IMM
 ---
 name: hazard_smem_war_backedge
 body: |
@@ -278,7 +279,7 @@ body: |
 
 # GCN-LABEL: name: hazard_smem_war_impdef
 # GCN:      S_LOAD_DWORD_IMM
-# GCN:      $sgpr_null = S_MOV_B32 0
+# GFX10:    $sgpr_null = S_MOV_B32 0
 # GCN-NEXT: V_CMP_EQ_F32
 ---
 name: hazard_smem_war_impdef
@@ -292,7 +293,7 @@ body: |
 
 # GCN-LABEL: name: hazard_smem_war_readlane
 # GCN:      S_LOAD_DWORD_IMM
-# GCN:      $sgpr_null = S_MOV_B32 0
+# GFX10:    $sgpr_null = S_MOV_B32 0
 # GCN-NEXT: V_READLANE_B32
 ---
 name: hazard_smem_war_readlane
@@ -306,7 +307,7 @@ body: |
 
 # GCN-LABEL: name: hazard_smem_war_readfirstlane
 # GCN:      S_LOAD_DWORD_IMM
-# GCN:      $sgpr_null = S_MOV_B32 0
+# GFX10:    $sgpr_null = S_MOV_B32 0
 # GCN-NEXT: V_READFIRSTLANE_B32
 ---
 name: hazard_smem_war_readfirstlane
diff --git a/llvm/test/CodeGen/AMDGPU/smrd-gfx10.ll b/llvm/test/CodeGen/AMDGPU/smrd-gfx10.ll
index bb52ac8cb39e86..631919afe1d707 100644
--- a/llvm/test/CodeGen/AMDGPU/smrd-gfx10.ll
+++ b/llvm/test/CodeGen/AMDGPU/smrd-gfx10.ll
@@ -1,7 +1,9 @@
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefixes=GCN %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefixes=GCN,GFX10 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefixes=GCN,GFX11 %s
 
 ; GCN-LABEL: {{^}}smrd_imm_dlc:
-; GCN: s_buffer_load_dword s0, s[0:3], 0x0 dlc ; encoding: [0x00,0x40,0x20,0xf4,0x00,0x00,0x00,0xfa]
+; GFX10: s_buffer_load_dword s0, s[0:3], 0x0 dlc ; encoding: [0x00,0x40,0x20,0xf4,0x00,0x00,0x00,0xfa]
+; GFX11: s_buffer_load_b32 s0, s[0:3], 0x0 dlc ; encoding: [0x00,0x20,0x20,0xf4,0x00,0x00,0x00,0xf8]
 define amdgpu_ps float @smrd_imm_dlc(<4 x i32> inreg %desc) #0 {
 main_body:
   %r = call float @llvm.amdgcn.s.buffer.load.f32(<4 x i32> %desc, i32 0, i32 4)
@@ -9,7 +11,8 @@ main_body:
 }
 
 ; GCN-LABEL: {{^}}smrd_sgpr_dlc:
-; GCN: s_buffer_load_dword s0, s[0:3], s4 dlc ; encoding: [0x00,0x40,0x20,0xf4,0x00,0x00,0x00,0x08]
+; GFX10: s_buffer_load_dword s0, s[0:3], s4 dlc ; encoding: [0x00,0x40,0x20,0xf4,0x00,0x00,0x00,0x08]
+; GFX11: s_buffer_load_b32 s0, s[0:3], s4 dlc ; encoding: [0x00,0x20,0x20,0xf4,0x00,0x00,0x00,0x08]
 define amdgpu_ps float @smrd_sgpr_dlc(<4 x i32> inreg %desc, i32 inreg %offset) #0 {
 main_body:
   %r = call float @llvm.amdgcn.s.buffer.load.f32(<4 x i32> %desc, i32 %offset, i32 4)
@@ -17,7 +20,8 @@ main_body:
 }
 
 ; GCN-LABEL: {{^}}smrd_imm_glc_dlc:
-; GCN: s_buffer_load_dword s0, s[0:3], 0x0 glc dlc ; encoding: [0x00,0x40,0x21,0xf4,0x00,0x00,0x00,0xfa]
+; GFX10: s_buffer_load_dword s0, s[0:3], 0x0 glc dlc ; encoding: [0x00,0x40,0x21,0xf4,0x00,0x00,0x00,0xfa]
+; GFX11: s_buffer_load_b32 s0, s[0:3], 0x0 glc dlc ; encoding: [0x00,0x60,0x20,0xf4,0x00,0x00,0x00,0xf8]
 define amdgpu_ps float @smrd_imm_glc_dlc(<4 x i32> inreg %desc) #0 {
 main_body:
   %r = call float @llvm.amdgcn.s.buffer.load.f32(<4 x i32> %desc, i32 0, i32 5)
@@ -25,7 +29,8 @@ main_body:
 }
 
 ; GCN-LABEL: {{^}}smrd_sgpr_glc_dlc:
-; GCN: s_buffer_load_dword s0, s[0:3], s4 glc dlc ; encoding: [0x00,0x40,0x21,0xf4,0x00,0x00,0x00,0x08]
+; GFX10: s_buffer_load_dword s0, s[0:3], s4 glc dlc ; encoding: [0x00,0x40,0x21,0xf4,0x00,0x00,0x00,0x08]
+; GFX11: s_buffer_load_b32 s0, s[0:3], s4 glc dlc ; encoding: [0x00,0x60,0x20,0xf4,0x00,0x00,0x00,0x08]
 define amdgpu_ps float @smrd_sgpr_glc_dlc(<4 x i32> inreg %desc, i32 inreg %offset) #0 {
 main_body:
   %r = call float @llvm.amdgcn.s.buffer.load.f32(<4 x i32> %desc, i32 %offset, i32 5)
diff --git a/llvm/test/CodeGen/AMDGPU/vcmpx-exec-war-hazard.mir b/llvm/test/CodeGen/AMDGPU/vcmpx-exec-war-hazard.mir
index 37b6b0cabe08b7..7a802ed1cac2a6 100644
--- a/llvm/test/CodeGen/AMDGPU/vcmpx-exec-war-hazard.mir
+++ b/llvm/test/CodeGen/AMDGPU/vcmpx-exec-war-hazard.mir
@@ -1,9 +1,10 @@
-# RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefix=GCN %s
+# RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefixes=GCN,GFX10 %s
+# RUN: llc -march=amdgcn -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefix=GCN %s
 
 # GCN-LABEL: name: hazard_vcmpx_smov_exec_lo
-# GCN:      $sgpr0 = S_MOV_B32 $exec_lo
-# GCN-NEXT: S_WAITCNT_DEPCTR 65534
-# GCN-NEXT: V_CMPX_LE_F32_nosdst_e32
+# GCN:        $sgpr0 = S_MOV_B32 $exec_lo
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65534
+# GCN-NEXT:   V_CMPX_LE_F32_nosdst_e32
 ---
 name:            hazard_vcmpx_smov_exec_lo
 body:            |
@@ -19,9 +20,9 @@ body:            |
 ...
 
 # GCN-LABEL: name: hazard_vcmpx_smov_exec
-# GCN:      $sgpr0_sgpr1 = S_MOV_B64 $exec
-# GCN-NEXT: S_WAITCNT_DEPCTR 65534
-# GCN-NEXT: V_CMPX_LE_F32_nosdst_e32
+# GCN:        $sgpr0_sgpr1 = S_MOV_B64 $exec
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65534
+# GCN-NEXT:   V_CMPX_LE_F32_nosdst_e32
 ---
 name:            hazard_vcmpx_smov_exec
 body:            |
@@ -145,9 +146,10 @@ body:            |
 ...
 
 # GCN-LABEL: name: hazard_vcmpx_smov_exec_lo_depctr_effe
-# GCN:      $sgpr0 = S_MOV_B32 $exec_lo
-# GCN:      S_WAITCNT_DEPCTR 65534
-# GCN-NEXT: V_CMPX_LE_F32_nosdst_e32
+# GCN:        $sgpr0 = S_MOV_B32 $exec_lo
+# GCN-NEXT:   S_WAITCNT_DEPCTR 61438
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65534
+# GCN-NEXT:   V_CMPX_LE_F32_nosdst_e32
 ---
 name:            hazard_vcmpx_smov_exec_lo_depctr_effe
 body:            |
diff --git a/llvm/test/CodeGen/AMDGPU/vmem-to-salu-hazard.mir b/llvm/test/CodeGen/AMDGPU/vmem-to-salu-hazard.mir
index c15365e576adec..0f4dfa0f8114b1 100644
--- a/llvm/test/CodeGen/AMDGPU/vmem-to-salu-hazard.mir
+++ b/llvm/test/CodeGen/AMDGPU/vmem-to-salu-hazard.mir
@@ -1,9 +1,10 @@
-# RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefix=GCN %s
+# RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefixes=GCN,GFX10 %s
+# RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefixes=GCN %s
 
 # GCN-LABEL: name: vmem_write_sgpr
-# GCN:      BUFFER_LOAD_DWORD_OFFEN
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        BUFFER_LOAD_DWORD_OFFEN
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_write_sgpr
 body:             |
@@ -15,9 +16,9 @@ body:             |
     $sgpr0 = S_MOV_B32 0
 ...
 # GCN-LABEL: name: vmem_write_exec
-# GCN:      BUFFER_STORE_DWORD_OFFEN_exact
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        BUFFER_STORE_DWORD_OFFEN_exact
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_write_exec
 body:             |
@@ -30,13 +31,13 @@ body:             |
     $exec_lo = S_MOV_B32 -1
 ...
 # GCN-LABEL: name: vmem_write_sgpr_chain
-# GCN:      BUFFER_LOAD_DWORD_OFFEN
-# GCN-NEXT: S_MOV_B32
-# GCN-NEXT: S_MOV_B32
-# GCN-NEXT: S_MOV_B32
-# GCN-NEXT: S_MOV_B32
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        BUFFER_LOAD_DWORD_OFFEN
+# GCN-NEXT:   S_MOV_B32
+# GCN-NEXT:   S_MOV_B32
+# GCN-NEXT:   S_MOV_B32
+# GCN-NEXT:   S_MOV_B32
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_write_sgpr_chain
 body:             |
@@ -53,9 +54,9 @@ body:             |
     $sgpr0 = S_MOV_B32 0
 ...
 # GCN-LABEL: name: vmem_smem_write_sgpr
-# GCN:      BUFFER_LOAD_DWORD_OFFEN
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_LOAD_DWORD_IMM
+# GCN:        BUFFER_LOAD_DWORD_OFFEN
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_LOAD_DWORD_IMM
 ---
 name:            vmem_smem_write_sgpr
 body:             |
@@ -67,10 +68,10 @@ body:             |
     $sgpr0 = S_LOAD_DWORD_IMM $sgpr0_sgpr1, 0, 0
 ...
 # GCN-LABEL: name: vmem_snop_write_sgpr
-# GCN:      BUFFER_LOAD_DWORD_OFFEN
-# GCN-NEXT: S_NOP
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        BUFFER_LOAD_DWORD_OFFEN
+# GCN-NEXT:   S_NOP
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_snop_write_sgpr
 body:             |
@@ -113,10 +114,10 @@ body:             |
     $sgpr0 = S_MOV_B32 0
 ...
 # GCN-LABEL: name: vmem_swait_any_write_sgpr
-# GCN:      BUFFER_LOAD_DWORD_OFFEN
-# GCN-NEXT: S_WAITCNT
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        BUFFER_LOAD_DWORD_OFFEN
+# GCN-NEXT:   S_WAITCNT
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_swait_any_write_sgpr
 body:             |
@@ -129,9 +130,9 @@ body:             |
     $sgpr0 = S_MOV_B32 0
 ...
 # GCN-LABEL: name: vmem_write_exec_impread
-# GCN:      BUFFER_LOAD_DWORD_OFFEN
-# GCN:      S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B64
+# GCN:        BUFFER_LOAD_DWORD_OFFEN
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B64
 ---
 name:            vmem_write_exec_impread
 body:             |
@@ -143,9 +144,9 @@ body:             |
     $exec = S_MOV_B64 7
 ...
 # GCN-LABEL: name: vmem_write_exec_expread
-# GCN:      BUFFER_LOAD_DWORD_OFFEN
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B64
+# GCN:        BUFFER_LOAD_DWORD_OFFEN
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B64
 ---
 name:            vmem_write_exec_expread
 body:             |
@@ -156,9 +157,9 @@ body:             |
     $exec = S_MOV_B64 7
 ...
 # GCN-LABEL: name: ds_write_m0
-# GCN:      DS_READ_B32
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        DS_READ_B32
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            ds_write_m0
 body:             |
@@ -170,9 +171,10 @@ body:             |
     $m0 = S_MOV_B32 7
 ...
 # GCN-LABEL: name: vmem_write_sgpr_fall_through
-# GCN:      BUFFER_LOAD_DWORD_OFFEN
-# GCN:      S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        BUFFER_LOAD_DWORD_OFFEN
+# GCN:        bb.1:
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_write_sgpr_fall_through
 body:             |
@@ -187,10 +189,11 @@ body:             |
     $sgpr0 = S_MOV_B32 0
 ...
 # GCN-LABEL: name: vmem_write_sgpr_branch
-# GCN:      BUFFER_LOAD_DWORD_OFFEN
-# GCN-NEXT: S_BRANCH
-# GCN:      S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        BUFFER_LOAD_DWORD_OFFEN
+# GCN-NEXT:   S_BRANCH
+# GCN:        bb.1:
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_write_sgpr_branch
 body:             |
@@ -206,11 +209,11 @@ body:             |
     $sgpr0 = S_MOV_B32 0
 ...
 # GCN-LABEL: name: vmem_write_sgpr_branch_around
-# GCN:      BUFFER_LOAD_DWORD_OFFEN
-# GCN-NEXT: S_BRANCH
-# GCN:      bb.2:
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        BUFFER_LOAD_DWORD_OFFEN
+# GCN-NEXT:   S_BRANCH
+# GCN:        bb.2:
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_write_sgpr_branch_around
 body:             |
@@ -230,15 +233,15 @@ body:             |
     $sgpr0 = S_MOV_B32 0
 ...
 # GCN-LABEL: name: vmem_write_sgpr_cbranch_around
-# GCN:      BUFFER_LOAD_DWORD_OFFEN
-# GCN-NEXT: S_CBRANCH
-# GCN-NEXT: S_BRANCH
-# GCN:      bb.1:
-# GCN:      S_WAITCNT
-# GCN:      V_ADD_CO_U32
-# GCN:      bb.2:
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        BUFFER_LOAD_DWORD_OFFEN
+# GCN-NEXT:   S_CBRANCH
+# GCN-NEXT:   S_BRANCH
+# GCN:        bb.1:
+# GCN:        S_WAITCNT
+# GCN:        V_ADD_CO_U32
+# GCN:        bb.2:
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_write_sgpr_cbranch_around
 body:             |
@@ -261,9 +264,9 @@ body:             |
     $sgpr0 = S_MOV_B32 0
 ...
 # GCN-LABEL: name: vmem_write_sgpr_branch_backedge
-# GCN:      $vgpr0 = IMPLICIT_DEF
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        $vgpr0 = IMPLICIT_DEF
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_write_sgpr_branch_backedge
 body:             |
@@ -279,9 +282,9 @@ body:             |
     S_BRANCH %bb.0
 ...
 # GCN-LABEL: name: ds_write_exec
-# GCN:      DS_WRITE_B32_gfx9
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        DS_WRITE_B32_gfx9
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            ds_write_exec
 body:             |
@@ -292,9 +295,9 @@ body:             |
     $exec_lo = S_MOV_B32 -1
 ...
 # GCN-LABEL: name: vmem_scratch_exec
-# GCN:      SCRATCH_LOAD_DWORD
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        SCRATCH_LOAD_DWORD
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_scratch_exec
 body:             |
@@ -304,9 +307,9 @@ body:             |
     $exec_lo = S_MOV_B32 -1
 ...
 # GCN-LABEL: name: vmem_flat_exec
-# GCN:      FLAT_LOAD_DWORD
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        FLAT_LOAD_DWORD
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_flat_exec
 body:             |
@@ -317,9 +320,9 @@ body:             |
     $exec_lo = S_MOV_B32 -1
 ...
 # GCN-LABEL: name: vmem_global_exec
-# GCN:      GLOBAL_LOAD_DWORD
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        GLOBAL_LOAD_DWORD
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_global_exec
 body:             |
@@ -330,9 +333,9 @@ body:             |
     $exec_lo = S_MOV_B32 -1
 ...
 # GCN-LABEL: name: vmem_global_atomic_exec
-# GCN: GLOBAL_ATOMIC_ADD_RTN
-# GCN-NEXT: S_WAITCNT_DEPCTR 65507
-# GCN-NEXT: S_MOV_B32
+# GCN:        GLOBAL_ATOMIC_ADD_RTN
+# GFX10-NEXT: S_WAITCNT_DEPCTR 65507
+# GCN-NEXT:   S_MOV_B32
 ---
 name:            vmem_global_atomic_exec
 body:             |
diff --git a/llvm/test/CodeGen/AMDGPU/waitcnt-vscnt.ll b/llvm/test/CodeGen/AMDGPU/waitcnt-vscnt.ll
index e78b5355c2d5d8..f1af64eb9b39df 100644
--- a/llvm/test/CodeGen/AMDGPU/waitcnt-vscnt.ll
+++ b/llvm/test/CodeGen/AMDGPU/waitcnt-vscnt.ll
@@ -1,12 +1,13 @@
 ; RUN: llc -march=amdgcn -mcpu=gfx802  -asm-verbose=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8,GFX8_9 %s
-; RUN: llc -march=amdgcn -mcpu=gfx900  -asm-verbose=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,GFX9_10,GFX8_9 %s
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-back-off-barrier -asm-verbose=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10,GFX9_10 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900  -asm-verbose=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,GFX9PLUS,GFX8_9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-back-off-barrier -asm-verbose=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10PLUS,GFX9PLUS %s
+; RUN: llc -march=amdgcn -mcpu=gfx1100 -mattr=-back-off-barrier -asm-verbose=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10PLUS,GFX9PLUS %s
 
 ; GCN-LABEL: barrier_vmcnt_global:
 ; GFX8:         flat_load_dword
-; GFX9_10:      global_load_dword
+; GFX9PLUS:     global_load_{{dword|b32}}
 ; GFX8:         s_waitcnt vmcnt(0){{$}}
-; GFX9_10:      s_waitcnt vmcnt(0){{$}}
+; GFX9PLUS:     s_waitcnt vmcnt(0){{$}}
 ; GCN-NEXT:     s_barrier
 define amdgpu_kernel void @barrier_vmcnt_global(i32 addrspace(1)* %arg) {
 bb:
@@ -27,10 +28,10 @@ bb:
 
 ; GCN-LABEL: barrier_vscnt_global:
 ; GFX8:       flat_store_dword
-; GFX9_10:    global_store_dword
+; GFX9PLUS:   global_store_{{dword|b32}}
 ; GFX8:       s_waitcnt vmcnt(0){{$}}
 ; GFX9:       s_waitcnt vmcnt(0){{$}}
-; GFX10:      s_waitcnt_vscnt null, 0x0
+; GFX10PLUS:  s_waitcnt_vscnt null, 0x0
 ; GCN-NEXT:   s_barrier
 define amdgpu_kernel void @barrier_vscnt_global(i32 addrspace(1)* %arg) {
 bb:
@@ -53,10 +54,10 @@ bb:
 
 ; GCN-LABEL: barrier_vmcnt_vscnt_global:
 ; GFX8:         flat_load_dword
-; GFX9_10:      global_load_dword
+; GFX9PLUS:     global_load_{{dword|b32}}
 ; GFX8:         s_waitcnt vmcnt(0){{$}}
-; GFX9_10:      s_waitcnt vmcnt(0){{$}}
-; GFX10:        s_waitcnt_vscnt null, 0x0
+; GFX9PLUS:     s_waitcnt vmcnt(0){{$}}
+; GFX10PLUS:    s_waitcnt_vscnt null, 0x0
 ; GCN-NEXT:     s_barrier
 define amdgpu_kernel void @barrier_vmcnt_vscnt_global(i32 addrspace(1)* %arg) {
 bb:
@@ -80,7 +81,7 @@ bb:
 }
 
 ; GCN-LABEL: barrier_vmcnt_flat:
-; GCN:      flat_load_dword
+; GCN:      flat_load_{{dword|b32}}
 ; GCN:      s_waitcnt vmcnt(0) lgkmcnt(0){{$}}
 ; GCN-NEXT: s_barrier
 define amdgpu_kernel void @barrier_vmcnt_flat(i32* %arg) {
@@ -101,10 +102,10 @@ bb:
 }
 
 ; GCN-LABEL: barrier_vscnt_flat:
-; GCN:         flat_store_dword
+; GCN:         flat_store_{{dword|b32}}
 ; GFX8_9:      s_waitcnt vmcnt(0) lgkmcnt(0){{$}}
-; GFX10:       s_waitcnt lgkmcnt(0){{$}}
-; GFX10:       s_waitcnt_vscnt null, 0x0
+; GFX10PLUS:   s_waitcnt lgkmcnt(0){{$}}
+; GFX10PLUS:   s_waitcnt_vscnt null, 0x0
 ; GCN-NEXT:    s_barrier
 define amdgpu_kernel void @barrier_vscnt_flat(i32* %arg) {
 bb:
@@ -126,9 +127,9 @@ bb:
 }
 
 ; GCN-LABEL: barrier_vmcnt_vscnt_flat:
-; GCN:        flat_load_dword
+; GCN:        flat_load_{{dword|b32}}
 ; GCN:        s_waitcnt vmcnt(0) lgkmcnt(0){{$}}
-; GFX10:      s_waitcnt_vscnt null, 0x0
+; GFX10PLUS:  s_waitcnt_vscnt null, 0x0
 ; GCN-NEXT:   s_barrier
 define amdgpu_kernel void @barrier_vmcnt_vscnt_flat(i32* %arg) {
 bb:
@@ -152,11 +153,11 @@ bb:
 }
 
 ; GCN-LABEL: barrier_vmcnt_vscnt_flat_workgroup:
-; GCN:        flat_load_dword
+; GCN:        flat_load_{{dword|b32}}
 ; GFX8_9:     s_waitcnt lgkmcnt(0){{$}}
 ; GFX8_9:     s_waitcnt vmcnt(0){{$}}
-; GFX10:      s_waitcnt vmcnt(0) lgkmcnt(0){{$}}
-; GFX10:      s_waitcnt_vscnt null, 0x0
+; GFX10PLUS:  s_waitcnt vmcnt(0) lgkmcnt(0){{$}}
+; GFX10PLUS:  s_waitcnt_vscnt null, 0x0
 ; GCN-NEXT:   s_barrier
 define amdgpu_kernel void @barrier_vmcnt_vscnt_flat_workgroup(i32* %arg) {
 bb:
@@ -181,10 +182,10 @@ bb:
 
 ; GCN-LABEL: load_vmcnt_global:
 ; GFX8:     flat_load_dword
-; GFX9_10:  global_load_dword
+; GFX9PLUS: global_load_{{dword|b32}}
 ; GFX8:     s_waitcnt vmcnt(0){{$}}
-; GFX9_10:  s_waitcnt vmcnt(0){{$}}
-; GCN-NEXT: {{global|flat}}_store_dword
+; GFX9PLUS: s_waitcnt vmcnt(0){{$}}
+; GCN-NEXT: {{global|flat}}_store_{{dword|b32}}
 define amdgpu_kernel void @load_vmcnt_global(i32 addrspace(1)* %arg) {
 bb:
   %tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -200,10 +201,10 @@ bb:
 }
 
 ; GCN-LABEL: load_vmcnt_flat:
-; GCN:      flat_load_dword
+; GCN:      flat_load_{{dword|b32}}
 ; GCN-NOT:  vscnt
 ; GCN:      s_waitcnt vmcnt(0) lgkmcnt(0){{$}}
-; GCN-NEXT: {{global|flat}}_store_dword
+; GCN-NEXT: {{global|flat}}_store_{{dword|b32}}
 define amdgpu_kernel void @load_vmcnt_flat(i32* %arg) {
 bb:
   %tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
@@ -219,9 +220,9 @@ bb:
 }
 
 ; GCN-LABEL: store_vscnt_private:
-; GCN:         buffer_store_dword
+; GCN:         {{buffer|scratch}}_store_{{dword|b32}}
 ; GFX8_9:      s_waitcnt vmcnt(0)
-; GFX10:       s_waitcnt_vscnt null, 0x0
+; GFX10PLUS:   s_waitcnt_vscnt null, 0x0
 ; GCN-NEXT:    s_setpc_b64
 define void @store_vscnt_private(i32 addrspace(5)* %p) {
   store i32 0, i32 addrspace(5)* %p
@@ -230,9 +231,9 @@ define void @store_vscnt_private(i32 addrspace(5)* %p) {
 
 ; GCN-LABEL: store_vscnt_global:
 ; GFX8:        flat_store_dword
-; GFX9_10:     global_store_dword
+; GFX9PLUS:    global_store_{{dword|b32}}
 ; GFX8_9:      s_waitcnt vmcnt(0)
-; GFX10:       s_waitcnt_vscnt null, 0x0
+; GFX10PLUS:   s_waitcnt_vscnt null, 0x0
 ; GCN-NEXT:    s_setpc_b64
 define void @store_vscnt_global(i32 addrspace(1)* %p) {
   store i32 0, i32 addrspace(1)* %p
@@ -240,10 +241,10 @@ define void @store_vscnt_global(i32 addrspace(1)* %p) {
 }
 
 ; GCN-LABEL: store_vscnt_flat:
-; GCN:         flat_store_dword
+; GCN:         flat_store_{{dword|b32}}
 ; GFX8_9:      s_waitcnt vmcnt(0) lgkmcnt(0){{$}}
-; GFX10:       s_waitcnt lgkmcnt(0){{$}}
-; GFX10:       s_waitcnt_vscnt null, 0x0
+; GFX10PLUS:   s_waitcnt lgkmcnt(0){{$}}
+; GFX10PLUS:   s_waitcnt_vscnt null, 0x0
 ; GCN-NEXT:    s_setpc_b64
 define void @store_vscnt_flat(i32* %p) {
   store i32 0, i32* %p
@@ -252,7 +253,7 @@ define void @store_vscnt_flat(i32* %p) {
 
 ; GCN-LABEL: function_prologue:
 ; GCN:        s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0){{$}}
-; GFX10:      s_waitcnt_vscnt null, 0x0
+; GFX10PLUS:  s_waitcnt_vscnt null, 0x0
 ; GCN-NEXT:   s_setpc_b64
 define void @function_prologue() {
   ret void
diff --git a/llvm/test/CodeGen/AMDGPU/waitcnt-vscnt.mir b/llvm/test/CodeGen/AMDGPU/waitcnt-vscnt.mir
index 80d87c7b7a6a91..d20d7306674af5 100644
--- a/llvm/test/CodeGen/AMDGPU/waitcnt-vscnt.mir
+++ b/llvm/test/CodeGen/AMDGPU/waitcnt-vscnt.mir
@@ -1,8 +1,10 @@
-# RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck -check-prefix=GFX10 %s
+# RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck -check-prefixes=GCN,GFX10 %s
+# RUN: llc -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck -check-prefixes=GCN,GFX11 %s
 
-# GFX10-LABEL: waitcnt-vscnt
-# GFX10: GLOBAL_ATOMIC_ADD_RTN
+# GCN-LABEL: waitcnt-vscnt
+# GCN: GLOBAL_ATOMIC_ADD_RTN
 # GFX10-NEXT: S_WAITCNT 49279
+# GFX11-NEXT: S_WAITCNT 64519
 ---
 name: waitcnt-vscnt
 machineFunctionInfo: