diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
index 6ecb1c8bf6e1d..453d496295748 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
@@ -187,8 +187,12 @@ VmemType getVmemType(const MachineInstr &Inst) {
   const AMDGPU::MIMGInfo *Info = AMDGPU::getMIMGInfo(Inst.getOpcode());
   const AMDGPU::MIMGBaseOpcodeInfo *BaseInfo =
       AMDGPU::getMIMGBaseOpcodeInfo(Info->BaseOpcode);
-  return BaseInfo->BVH ? VMEM_BVH
-                       : BaseInfo->Sampler ? VMEM_SAMPLER : VMEM_NOSAMPLER;
+  // We have to make an additional check for isVSAMPLE here since some
+  // instructions don't have a sampler, but are still classified as sampler
+  // instructions for the purposes of e.g. waitcnt.
+  return BaseInfo->BVH                                         ? VMEM_BVH
+         : (BaseInfo->Sampler || SIInstrInfo::isVSAMPLE(Inst)) ? VMEM_SAMPLER
+                                                               : VMEM_NOSAMPLER;
 }
 
 unsigned &getCounterRef(AMDGPU::Waitcnt &Wait, InstCounterType T) {
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.msaa.load.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.msaa.load.ll
index 1348315e72e7b..8da4855185557 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.msaa.load.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.image.msaa.load.ll
@@ -12,7 +12,7 @@ define amdgpu_ps <4 x float> @load_2dmsaa(<8 x i32> inreg %rsrc, i32 %s, i32 %t,
 ; GFX12-LABEL: load_2dmsaa:
 ; GFX12:       ; %bb.0: ; %main_body
 ; GFX12-NEXT:    image_msaa_load v[0:3], [v0, v1, v2], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D_MSAA unorm ; encoding: [0x06,0x20,0x46,0xe4,0x00,0x00,0x00,0x00,0x00,0x01,0x02,0x00]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
   %v = call <4 x float> @llvm.amdgcn.image.msaa.load.2dmsaa.v4f32.i32(i32 1, i32 %s, i32 %t, i32 %fragid, <8 x i32> %rsrc, i32 0, i32 0)
@@ -32,7 +32,7 @@ define amdgpu_ps <4 x float> @load_2dmsaa_both(<8 x i32> inreg %rsrc, ptr addrsp
 ; GFX12:       ; %bb.0: ; %main_body
 ; GFX12-NEXT:    image_msaa_load v[0:4], [v0, v1, v2], s[0:7] dmask:0x2 dim:SQ_RSRC_IMG_2D_MSAA unorm tfe lwe ; encoding: [0x0e,0x20,0x86,0xe4,0x00,0x01,0x00,0x00,0x00,0x01,0x02,0x00]
 ; GFX12-NEXT:    v_mov_b32_e32 v5, 0 ; encoding: [0x80,0x02,0x0a,0x7e]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    global_store_b32 v5, v4, s[8:9] ; encoding: [0x08,0x80,0x06,0xee,0x00,0x00,0x00,0x02,0x05,0x00,0x00,0x00]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
@@ -53,7 +53,7 @@ define amdgpu_ps <4 x float> @load_2darraymsaa(<8 x i32> inreg %rsrc, i32 %s, i3
 ; GFX12-LABEL: load_2darraymsaa:
 ; GFX12:       ; %bb.0: ; %main_body
 ; GFX12-NEXT:    image_msaa_load v[0:3], [v0, v1, v2, v3], s[0:7] dmask:0x4 dim:SQ_RSRC_IMG_2D_MSAA_ARRAY unorm ; encoding: [0x07,0x20,0x06,0xe5,0x00,0x00,0x00,0x00,0x00,0x01,0x02,0x03]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
   %v = call <4 x float> @llvm.amdgcn.image.msaa.load.2darraymsaa.v4f32.i32(i32 4, i32 %s, i32 %t, i32 %slice, i32 %fragid, <8 x i32> %rsrc, i32 0, i32 0)
@@ -73,7 +73,7 @@ define amdgpu_ps <4 x float> @load_2darraymsaa_tfe(<8 x i32> inreg %rsrc, ptr ad
 ; GFX12:       ; %bb.0: ; %main_body
 ; GFX12-NEXT:    image_msaa_load v[0:4], [v0, v1, v2, v3], s[0:7] dmask:0x8 dim:SQ_RSRC_IMG_2D_MSAA_ARRAY unorm tfe ; encoding: [0x0f,0x20,0x06,0xe6,0x00,0x00,0x00,0x00,0x00,0x01,0x02,0x03]
 ; GFX12-NEXT:    v_mov_b32_e32 v5, 0 ; encoding: [0x80,0x02,0x0a,0x7e]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    global_store_b32 v5, v4, s[8:9] ; encoding: [0x08,0x80,0x06,0xee,0x00,0x00,0x00,0x02,0x05,0x00,0x00,0x00]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
@@ -94,7 +94,7 @@ define amdgpu_ps <4 x float> @load_2dmsaa_glc(<8 x i32> inreg %rsrc, i32 %s, i32
 ; GFX12-LABEL: load_2dmsaa_glc:
 ; GFX12:       ; %bb.0: ; %main_body
 ; GFX12-NEXT:    image_msaa_load v[0:3], [v0, v1, v2], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D_MSAA unorm th:TH_LOAD_NT ; encoding: [0x06,0x20,0x46,0xe4,0x00,0x00,0x10,0x00,0x00,0x01,0x02,0x00]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
   %v = call <4 x float> @llvm.amdgcn.image.msaa.load.2dmsaa.v4f32.i32(i32 1, i32 %s, i32 %t, i32 %fragid, <8 x i32> %rsrc, i32 0, i32 1)
@@ -111,7 +111,7 @@ define amdgpu_ps <4 x float> @load_2dmsaa_slc(<8 x i32> inreg %rsrc, i32 %s, i32
 ; GFX12-LABEL: load_2dmsaa_slc:
 ; GFX12:       ; %bb.0: ; %main_body
 ; GFX12-NEXT:    image_msaa_load v[0:3], [v0, v1, v2], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D_MSAA unorm th:TH_LOAD_HT ; encoding: [0x06,0x20,0x46,0xe4,0x00,0x00,0x20,0x00,0x00,0x01,0x02,0x00]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
   %v = call <4 x float> @llvm.amdgcn.image.msaa.load.2dmsaa.v4f32.i32(i32 1, i32 %s, i32 %t, i32 %fragid, <8 x i32> %rsrc, i32 0, i32 2)
@@ -128,7 +128,7 @@ define amdgpu_ps <4 x float> @load_2dmsaa_glc_slc(<8 x i32> inreg %rsrc, i32 %s,
 ; GFX12-LABEL: load_2dmsaa_glc_slc:
 ; GFX12:       ; %bb.0: ; %main_body
 ; GFX12-NEXT:    image_msaa_load v[0:3], [v0, v1, v2], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D_MSAA unorm th:TH_LOAD_LU ; encoding: [0x06,0x20,0x46,0xe4,0x00,0x00,0x30,0x00,0x00,0x01,0x02,0x00]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
   %v = call <4 x float> @llvm.amdgcn.image.msaa.load.2dmsaa.v4f32.i32(i32 1, i32 %s, i32 %t, i32 %fragid, <8 x i32> %rsrc, i32 0, i32 3)
@@ -145,7 +145,7 @@ define amdgpu_ps <4 x half> @load_2dmsaa_d16(<8 x i32> inreg %rsrc, i32 %s, i32
 ; GFX12-LABEL: load_2dmsaa_d16:
 ; GFX12:       ; %bb.0: ; %main_body
 ; GFX12-NEXT:    image_msaa_load v[0:1], [v0, v1, v2], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D_MSAA unorm d16 ; encoding: [0x26,0x20,0x46,0xe4,0x00,0x00,0x00,0x00,0x00,0x01,0x02,0x00]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
   %v = call <4 x half> @llvm.amdgcn.image.msaa.load.2dmsaa.v4f16.i32(i32 1, i32 %s, i32 %t, i32 %fragid, <8 x i32> %rsrc, i32 0, i32 0)
@@ -165,7 +165,7 @@ define amdgpu_ps <4 x half> @load_2dmsaa_tfe_d16(<8 x i32> inreg %rsrc, ptr addr
 ; GFX12:       ; %bb.0: ; %main_body
 ; GFX12-NEXT:    image_msaa_load v[0:2], [v0, v1, v2], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D_MSAA unorm tfe d16 ; encoding: [0x2e,0x20,0x46,0xe4,0x00,0x00,0x00,0x00,0x00,0x01,0x02,0x00]
 ; GFX12-NEXT:    v_mov_b32_e32 v3, 0 ; encoding: [0x80,0x02,0x06,0x7e]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    global_store_b32 v3, v2, s[8:9] ; encoding: [0x08,0x80,0x06,0xee,0x00,0x00,0x00,0x01,0x03,0x00,0x00,0x00]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
@@ -186,7 +186,7 @@ define amdgpu_ps <4 x half> @load_2darraymsaa_d16(<8 x i32> inreg %rsrc, i32 %s,
 ; GFX12-LABEL: load_2darraymsaa_d16:
 ; GFX12:       ; %bb.0: ; %main_body
 ; GFX12-NEXT:    image_msaa_load v[0:1], [v0, v1, v2, v3], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D_MSAA_ARRAY unorm d16 ; encoding: [0x27,0x20,0x46,0xe4,0x00,0x00,0x00,0x00,0x00,0x01,0x02,0x03]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
   %v = call <4 x half> @llvm.amdgcn.image.msaa.load.2darraymsaa.v4f16.i32(i32 1, i32 %s, i32 %t, i32 %slice, i32 %fragid, <8 x i32> %rsrc, i32 0, i32 0)
@@ -206,7 +206,7 @@ define amdgpu_ps <4 x half> @load_2darraymsaa_tfe_d16(<8 x i32> inreg %rsrc, ptr
 ; GFX12:       ; %bb.0: ; %main_body
 ; GFX12-NEXT:    image_msaa_load v[0:2], [v0, v1, v2, v3], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D_MSAA_ARRAY unorm tfe d16 ; encoding: [0x2f,0x20,0x46,0xe4,0x00,0x00,0x00,0x00,0x00,0x01,0x02,0x03]
 ; GFX12-NEXT:    v_mov_b32_e32 v3, 0 ; encoding: [0x80,0x02,0x06,0x7e]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    global_store_b32 v3, v2, s[8:9] ; encoding: [0x08,0x80,0x06,0xee,0x00,0x00,0x00,0x01,0x03,0x00,0x00,0x00]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
@@ -229,7 +229,7 @@ define amdgpu_ps <4 x float> @load_2dmsaa_a16(<8 x i32> inreg %rsrc, i16 %s, i16
 ; GFX12:       ; %bb.0: ; %main_body
 ; GFX12-NEXT:    v_perm_b32 v0, v1, v0, 0x5040100 ; encoding: [0x00,0x00,0x44,0xd6,0x01,0x01,0xfe,0x03,0x00,0x01,0x04,0x05]
 ; GFX12-NEXT:    image_msaa_load v[0:3], [v0, v2], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D_MSAA unorm a16 ; encoding: [0x46,0x20,0x46,0xe4,0x00,0x00,0x00,0x00,0x00,0x02,0x00,0x00]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
   %v = call <4 x float> @llvm.amdgcn.image.msaa.load.2dmsaa.v4f32.i16(i32 1, i16 %s, i16 %t, i16 %fragid, <8 x i32> %rsrc, i32 0, i32 0)
@@ -250,7 +250,7 @@ define amdgpu_ps <4 x float> @load_2darraymsaa_a16(<8 x i32> inreg %rsrc, i16 %s
 ; GFX12-NEXT:    v_perm_b32 v2, v3, v2, 0x5040100 ; encoding: [0x02,0x00,0x44,0xd6,0x03,0x05,0xfe,0x03,0x00,0x01,0x04,0x05]
 ; GFX12-NEXT:    v_perm_b32 v0, v1, v0, 0x5040100 ; encoding: [0x00,0x00,0x44,0xd6,0x01,0x01,0xfe,0x03,0x00,0x01,0x04,0x05]
 ; GFX12-NEXT:    image_msaa_load v[0:3], [v0, v2], s[0:7] dmask:0x4 dim:SQ_RSRC_IMG_2D_MSAA_ARRAY unorm a16 ; encoding: [0x47,0x20,0x06,0xe5,0x00,0x00,0x00,0x00,0x00,0x02,0x00,0x00]
-; GFX12-NEXT:    s_wait_loadcnt 0x0 ; encoding: [0x00,0x00,0xc0,0xbf]
+; GFX12-NEXT:    s_wait_samplecnt 0x0 ; encoding: [0x00,0x00,0xc2,0xbf]
 ; GFX12-NEXT:    ; return to shader part epilog
 main_body:
   %v = call <4 x float> @llvm.amdgcn.image.msaa.load.2darraymsaa.v4f32.i16(i32 4, i16 %s, i16 %t, i16 %slice, i16 %fragid, <8 x i32> %rsrc, i32 0, i32 0)
diff --git a/llvm/test/CodeGen/AMDGPU/waitcnt-sample-waw.mir b/llvm/test/CodeGen/AMDGPU/waitcnt-sample-waw.mir
new file mode 100644
index 0000000000000..8eb4be266dd3b
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/waitcnt-sample-waw.mir
@@ -0,0 +1,24 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 4
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck -check-prefix=GFX11 %s
+
+---
+name:            sample_load_msaa
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
+
+    ; GFX11-LABEL: name: sample_load_msaa
+    ; GFX11: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4
+    ; GFX11-NEXT: {{  $}}
+    ; GFX11-NEXT: S_WAITCNT 0
+    ; GFX11-NEXT: renamable $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_V4_V1_gfx11 killed renamable $vgpr0, renamable $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, killed renamable $sgpr8_sgpr9_sgpr10_sgpr11, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s128), addrspace 8)
+    ; GFX11-NEXT: S_WAITCNT 1015
+    ; GFX11-NEXT: renamable $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_MSAA_LOAD_V4_V2_gfx11 killed renamable $vgpr4_vgpr5, killed renamable $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 4, 7, -1, 0, 0, -1, 0, 0, 0, implicit $exec :: (dereferenceable load (s128), addrspace 8)
+    ; GFX11-NEXT: S_WAITCNT 1015
+    ; GFX11-NEXT: SI_RETURN_TO_EPILOG killed $vgpr0, killed $vgpr1, killed $vgpr2, killed $vgpr3
+    renamable $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_V4_V1_gfx11 killed renamable $vgpr0, renamable $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, killed renamable $sgpr8_sgpr9_sgpr10_sgpr11, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s128), addrspace 8)
+    renamable $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_MSAA_LOAD_V4_V2_gfx11 killed renamable $vgpr4_vgpr5, killed renamable $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 4, 7, -1, 0, 0, -1, 0, 0, 0, implicit $exec :: (dereferenceable load (s128), addrspace 8)
+    SI_RETURN_TO_EPILOG killed $vgpr0, killed $vgpr1, killed $vgpr2, killed $vgpr3
+
+...