[MBP] Move a latch block with conditional exit and multi predecessors…

… to top of loop

Current findBestLoopTop can find and move one kind of block to top, a latch block has one successor. Another common case is:

    * a latch block
    * it has two successors, one is loop header, another is exit
    * it has more than one predecessors

If it is below one of its predecessors P, only P can fall through to it, all other predecessors need a jump to it, and another conditional jump to loop header. If it is moved before loop header, all its predecessors jump to it, then fall through to loop header. So all its predecessors except P can reduce one taken branch.

Differential Revision: https://reviews.llvm.org/D43256

llvm-svn: 363471

llvm/test/CodeGen/AArch64/cmpxchg-idioms.ll

@@ -111,7 +111,7 @@ define i1 @test_conditional2(i32 %a, i32 %b, i32* %c) {
 ; CHECK: mov w22, #2
 ; CHECK-NOT: mov w22, #4
 ; CHECK-NOT: cmn w22, #4
-; CHECK: b [[LOOP2:LBB[0-9]+_[0-9]+]]
+; CHECK: [[LOOP2:LBB[0-9]+_[0-9]+]]: ; %for.cond
 ; CHECK-NOT: b.ne [[LOOP2]]
 ; CHECK-NOT: b {{LBB[0-9]+_[0-9]+}}
 ; CHECK: bl _foo

llvm/test/CodeGen/AArch64/neg-imm.ll

@@ -1,4 +1,4 @@
-; RUN: llc -mtriple=aarch64-linux-gnu -verify-machineinstrs -o - %s | FileCheck %s
+; RUN: llc -mtriple=aarch64-linux-gnu -verify-machineinstrs -disable-block-placement -o - %s | FileCheck %s
 ; LSR used to pick a sub-optimal solution due to the target responding
 ; conservatively to isLegalAddImmediate for negative values.
 

llvm/test/CodeGen/AArch64/tailmerging_in_mbp.ll

@@ -1,9 +1,8 @@
 ; RUN: llc <%s -mtriple=aarch64-eabi -verify-machine-dom-info | FileCheck %s
 
 ; CHECK-LABEL: test:
-; CHECK:       LBB0_7:
-; CHECK:         b.hi	
-; CHECK-NEXT:    b	
+; CHECK-LABEL: %cond.false12.i
+; CHECK:         b.gt	
 ; CHECK-NEXT:  LBB0_8:
 ; CHECK-NEXT:    mov	 x8, x9
 ; CHECK-NEXT:  LBB0_9:

llvm/test/CodeGen/AMDGPU/collapse-endcf.ll

@@ -230,6 +230,11 @@ bb.end:                                           ; preds = %bb.then, %bb
 ; Make sure scc liveness is updated if sor_b64 is removed
 ; ALL-LABEL: {{^}}scc_liveness:
 
+; GCN: %bb10
+; GCN: s_or_b64 exec, exec, s{{\[[0-9]+:[0-9]+\]}}
+; GCN: s_andn2_b64
+; GCN-NEXT: s_cbranch_execz
+
 ; GCN: [[BB1_LOOP:BB[0-9]+_[0-9]+]]:
 ; GCN: s_andn2_b64 exec, exec,
 ; GCN-NEXT: s_cbranch_execnz [[BB1_LOOP]]
@@ -239,10 +244,6 @@ bb.end:                                           ; preds = %bb.then, %bb
 
 ; GCN-NOT: s_or_b64 exec, exec
 
-; GCN: s_or_b64 exec, exec, s{{\[[0-9]+:[0-9]+\]}}
-; GCN: s_andn2_b64
-; GCN-NEXT: s_cbranch_execnz
-
 ; GCN: s_or_b64 exec, exec, s{{\[[0-9]+:[0-9]+\]}}
 ; GCN: buffer_store_dword
 ; GCN: buffer_store_dword

llvm/test/CodeGen/AMDGPU/divergent-branch-uniform-condition.ll

@@ -19,38 +19,39 @@ define amdgpu_ps void @main(i32, float) {
 ; CHECK-NEXT:    v_mov_b32_e32 v1, 0
 ; CHECK-NEXT:    ; implicit-def: $sgpr2_sgpr3
 ; CHECK-NEXT:    ; implicit-def: $sgpr6_sgpr7
-; CHECK-NEXT:  BB0_1: ; %loop
+; CHECK-NEXT:    s_branch BB0_3
+; CHECK-NEXT:  BB0_1: ; in Loop: Header=BB0_3 Depth=1
+; CHECK-NEXT:    ; implicit-def: $vgpr1
+; CHECK-NEXT:  BB0_2: ; %Flow
+; CHECK-NEXT:    ; in Loop: Header=BB0_3 Depth=1
+; CHECK-NEXT:    s_and_b64 s[8:9], exec, s[6:7]
+; CHECK-NEXT:    s_or_b64 s[8:9], s[8:9], s[4:5]
+; CHECK-NEXT:    s_mov_b64 s[4:5], s[8:9]
+; CHECK-NEXT:    s_andn2_b64 exec, exec, s[8:9]
+; CHECK-NEXT:    s_cbranch_execz BB0_7
+; CHECK-NEXT:  BB0_3: ; %loop
 ; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    v_cmp_gt_u32_e32 vcc, 32, v1
 ; CHECK-NEXT:    s_and_b64 vcc, exec, vcc
 ; CHECK-NEXT:    s_or_b64 s[6:7], s[6:7], exec
 ; CHECK-NEXT:    s_or_b64 s[2:3], s[2:3], exec
-; CHECK-NEXT:    s_cbranch_vccz BB0_5
-; CHECK-NEXT:  ; %bb.2: ; %endif1
-; CHECK-NEXT:    ; in Loop: Header=BB0_1 Depth=1
+; CHECK-NEXT:    s_cbranch_vccz BB0_1
+; CHECK-NEXT:  ; %bb.4: ; %endif1
+; CHECK-NEXT:    ; in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    s_mov_b64 s[6:7], -1
 ; CHECK-NEXT:    s_and_saveexec_b64 s[8:9], s[0:1]
 ; CHECK-NEXT:    s_xor_b64 s[8:9], exec, s[8:9]
-; CHECK-NEXT:    ; mask branch BB0_4
-; CHECK-NEXT:  BB0_3: ; %endif2
-; CHECK-NEXT:    ; in Loop: Header=BB0_1 Depth=1
+; CHECK-NEXT:    ; mask branch BB0_6
+; CHECK-NEXT:  BB0_5: ; %endif2
+; CHECK-NEXT:    ; in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    v_add_u32_e32 v1, 1, v1
 ; CHECK-NEXT:    s_xor_b64 s[6:7], exec, -1
-; CHECK-NEXT:  BB0_4: ; %Flow1
-; CHECK-NEXT:    ; in Loop: Header=BB0_1 Depth=1
+; CHECK-NEXT:  BB0_6: ; %Flow1
+; CHECK-NEXT:    ; in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    s_or_b64 exec, exec, s[8:9]
 ; CHECK-NEXT:    s_andn2_b64 s[2:3], s[2:3], exec
-; CHECK-NEXT:    s_branch BB0_6
-; CHECK-NEXT:  BB0_5: ; in Loop: Header=BB0_1 Depth=1
-; CHECK-NEXT:    ; implicit-def: $vgpr1
-; CHECK-NEXT:  BB0_6: ; %Flow
-; CHECK-NEXT:    ; in Loop: Header=BB0_1 Depth=1
-; CHECK-NEXT:    s_and_b64 s[8:9], exec, s[6:7]
-; CHECK-NEXT:    s_or_b64 s[8:9], s[8:9], s[4:5]
-; CHECK-NEXT:    s_mov_b64 s[4:5], s[8:9]
-; CHECK-NEXT:    s_andn2_b64 exec, exec, s[8:9]
-; CHECK-NEXT:    s_cbranch_execnz BB0_1
-; CHECK-NEXT:  ; %bb.7: ; %Flow2
+; CHECK-NEXT:    s_branch BB0_2
+; CHECK-NEXT:  BB0_7: ; %Flow2
 ; CHECK-NEXT:    s_or_b64 exec, exec, s[8:9]
 ; CHECK-NEXT:    v_mov_b32_e32 v1, 0
 ; this is the divergent branch with the condition not marked as divergent

llvm/test/CodeGen/AMDGPU/global_smrd_cfg.ll

@@ -1,27 +1,28 @@
 ; RUN: llc -mtriple amdgcn--amdhsa -mcpu=fiji -amdgpu-scalarize-global-loads=true -verify-machineinstrs  < %s | FileCheck %s
 
-; CHECK-LABEL: %bb11
+; CHECK-LABEL: %bb22
 
-; Load from %arg in a Loop body has alias store
+; Load from %arg has alias store in Loop
 
 ; CHECK: flat_load_dword
 
-; CHECK-LABEL: %bb20
-; CHECK: flat_store_dword
+; #####################################################################
+
+; Load from %arg1 has no-alias store in Loop - arg1[i+1] never alias arg1[i]
+
+; CHECK: s_load_dword
 
 ; #####################################################################
 
-; CHECK-LABEL: %bb22
+; CHECK-LABEL: %bb11
 
-; Load from %arg has alias store in Loop
+; Load from %arg in a Loop body has alias store
 
 ; CHECK: flat_load_dword
 
-; #####################################################################
-
-; Load from %arg1 has no-alias store in Loop - arg1[i+1] never alias arg1[i]
+; CHECK-LABEL: %bb20
 
-; CHECK: s_load_dword
+; CHECK: flat_store_dword
 
 define amdgpu_kernel void @cfg(i32 addrspace(1)* nocapture readonly %arg, i32 addrspace(1)* nocapture %arg1, i32 %arg2) #0 {
 bb:

llvm/test/CodeGen/AMDGPU/hoist-cond.ll

@@ -1,4 +1,4 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -march=amdgcn -verify-machineinstrs -disable-block-placement < %s | FileCheck %s
 
 ; Check that invariant compare is hoisted out of the loop.
 ; At the same time condition shall not be serialized into a VGPR and deserialized later

llvm/test/CodeGen/AMDGPU/i1-copy-from-loop.ll

@@ -3,20 +3,20 @@
 
 ; SI-LABEL: {{^}}i1_copy_from_loop:
 ;
+; SI: ; %Flow
+; SI-DAG:  s_andn2_b64       [[LCSSA_ACCUM:s\[[0-9]+:[0-9]+\]]], [[LCSSA_ACCUM]], exec
+; SI-DAG:  s_and_b64         [[CC_MASK2:s\[[0-9]+:[0-9]+\]]], [[CC_ACCUM:s\[[0-9]+:[0-9]+\]]], exec
+; SI:      s_or_b64          [[LCSSA_ACCUM]], [[LCSSA_ACCUM]], [[CC_MASK2]]
+
 ; SI: ; %for.body
 ; SI:      v_cmp_gt_u32_e64  [[CC_SREG:s\[[0-9]+:[0-9]+\]]], 4,
-; SI-DAG:  s_andn2_b64       [[CC_ACCUM:s\[[0-9]+:[0-9]+\]]], [[CC_ACCUM]], exec
+; SI-DAG:  s_andn2_b64       [[CC_ACCUM]], [[CC_ACCUM]], exec
 ; SI-DAG:  s_and_b64         [[CC_MASK:s\[[0-9]+:[0-9]+\]]], [[CC_SREG]], exec
 ; SI:      s_or_b64          [[CC_ACCUM]], [[CC_ACCUM]], [[CC_MASK]]
 
 ; SI: ; %Flow1
 ; SI:      s_or_b64          [[CC_ACCUM]], [[CC_ACCUM]], exec
 
-; SI: ; %Flow
-; SI-DAG:  s_andn2_b64       [[LCSSA_ACCUM:s\[[0-9]+:[0-9]+\]]], [[LCSSA_ACCUM]], exec
-; SI-DAG:  s_and_b64         [[CC_MASK2:s\[[0-9]+:[0-9]+\]]], [[CC_ACCUM]], exec
-; SI:      s_or_b64          [[LCSSA_ACCUM]], [[LCSSA_ACCUM]], [[CC_MASK2]]
-
 ; SI: ; %for.end
 ; SI:      s_and_saveexec_b64 {{s\[[0-9]+:[0-9]+\]}}, [[LCSSA_ACCUM]]
 

llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll

@@ -630,12 +630,7 @@ define amdgpu_kernel void @insertelement_v16f32_or_index(<16 x float> addrspace(
 ; GCN-LABEL: {{^}}broken_phi_bb:
 ; GCN: v_mov_b32_e32 [[PHIREG:v[0-9]+]], 8
 
-; GCN: s_branch [[BB2:BB[0-9]+_[0-9]+]]
-
-; GCN: {{^BB[0-9]+_[0-9]+}}:
-; GCN: s_mov_b64 exec,
-
-; GCN: [[BB2]]:
+; GCN: [[BB2:BB[0-9]+_[0-9]+]]:
 ; GCN: v_cmp_le_i32_e32 vcc, s{{[0-9]+}}, [[PHIREG]]
 ; GCN: buffer_load_dword
 
@@ -647,6 +642,11 @@ define amdgpu_kernel void @insertelement_v16f32_or_index(<16 x float> addrspace(
 ; IDXMODE: s_set_gpr_idx_off
 
 ; GCN: s_cbranch_execnz [[REGLOOP]]
+
+; GCN: {{^; %bb.[0-9]}}:
+; GCN: s_mov_b64 exec,
+; GCN: s_branch [[BB2]]
+
 define amdgpu_kernel void @broken_phi_bb(i32 %arg, i32 %arg1) #0 {
 bb:
   br label %bb2

llvm/test/CodeGen/AMDGPU/loop_break.ll

@@ -1,5 +1,5 @@
 ; RUN: opt -mtriple=amdgcn-- -S -structurizecfg -si-annotate-control-flow %s | FileCheck -check-prefix=OPT %s
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -march=amdgcn -verify-machineinstrs -disable-block-placement < %s | FileCheck -check-prefix=GCN %s
 
 ; Uses llvm.amdgcn.break
 

llvm/test/CodeGen/AMDGPU/loop_exit_with_xor.ll

@@ -61,9 +61,9 @@ loopexit:
 
 ; GCN-LABEL: {{^}}break_cond_is_arg:
 ; GCN: s_xor_b64 [[REG1:[^ ,]*]], {{[^ ,]*, -1$}}
+; GCN: s_andn2_b64 exec, exec, [[REG3:[^ ,]*]]
 ; GCN: s_and_b64 [[REG2:[^ ,]*]], exec, [[REG1]]
-; GCN: s_or_b64 [[REG3:[^ ,]*]], [[REG2]],
-; GCN: s_andn2_b64 exec, exec, [[REG3]]
+; GCN: s_or_b64 [[REG3]], [[REG2]],
 
 define void @break_cond_is_arg(i32 %arg, i1 %breakcond) {
 entry:

llvm/test/CodeGen/AMDGPU/madmk.ll

@@ -188,9 +188,9 @@ define amdgpu_kernel void @madmk_add_inline_imm_f32(float addrspace(1)* noalias
 }
 
 ; SI-LABEL: {{^}}kill_madmk_verifier_error:
+; SI: s_or_b64
 ; SI: s_xor_b64
 ; SI: v_mac_f32_e32 {{v[0-9]+}}, 0x472aee8c, {{v[0-9]+}}
-; SI: s_or_b64
 define amdgpu_kernel void @kill_madmk_verifier_error() nounwind {
 bb:
   br label %bb2

llvm/test/CodeGen/AMDGPU/multilevel-break.ll

@@ -24,13 +24,29 @@
 ; GCN: ; %main_body
 ; GCN:      s_mov_b64           [[LEFT_OUTER:s\[[0-9]+:[0-9]+\]]], 0{{$}}
 
+; GCN: [[FLOW2:BB[0-9]+_[0-9]+]]: ; %Flow2
+; GCN:      s_or_b64            exec, exec, [[TMP0:s\[[0-9]+:[0-9]+\]]]
+; GCN:      s_and_b64           [[TMP1:s\[[0-9]+:[0-9]+\]]], exec, [[BREAK_OUTER:s\[[0-9]+:[0-9]+\]]]
+; GCN:      s_or_b64            [[TMP1]], [[TMP1]], [[LEFT_OUTER]]
+; GCN:      s_mov_b64           [[LEFT_OUTER]], [[TMP1]]
+; GCN:      s_andn2_b64         exec, exec, [[TMP1]]
+; GCN:      s_cbranch_execz    [[IF_BLOCK:BB[0-9]+_[0-9]+]]
+
 ; GCN: [[OUTER_LOOP:BB[0-9]+_[0-9]+]]: ; %LOOP.outer{{$}}
 ; GCN:      s_mov_b64           [[LEFT_INNER:s\[[0-9]+:[0-9]+\]]], 0{{$}}
 
+; GCN: ; %Flow
+; GCN:      s_or_b64            exec, exec, [[SAVE_EXEC:s\[[0-9]+:[0-9]+\]]]
+; GCN:      s_and_b64           [[TMP0]], exec, [[BREAK_INNER:s\[[0-9]+:[0-9]+\]]]
+; GCN:      s_or_b64            [[TMP0]], [[TMP0]], [[LEFT_INNER]]
+; GCN:      s_mov_b64           [[LEFT_INNER]], [[TMP0]]
+; GCN:      s_andn2_b64         exec, exec, [[TMP0]]
+; GCN:      s_cbranch_execz    [[FLOW2]]
+
 ; GCN: [[INNER_LOOP:BB[0-9]+_[0-9]+]]: ; %LOOP{{$}}
-; GCN:      s_or_b64            [[BREAK_OUTER:s\[[0-9]+:[0-9]+\]]], [[BREAK_OUTER]], exec
-; GCN:      s_or_b64            [[BREAK_INNER:s\[[0-9]+:[0-9]+\]]], [[BREAK_INNER]], exec
-; GCN:      s_and_saveexec_b64  [[SAVE_EXEC:s\[[0-9]+:[0-9]+\]]], vcc
+; GCN:      s_or_b64            [[BREAK_OUTER]], [[BREAK_OUTER]], exec
+; GCN:      s_or_b64            [[BREAK_INNER]], [[BREAK_INNER]], exec
+; GCN:      s_and_saveexec_b64  [[SAVE_EXEC]], vcc
 
 ; FIXME: duplicate comparison
 ; GCN: ; %ENDIF
@@ -43,23 +59,7 @@
 ; GCN-DAG:  s_or_b64            [[BREAK_OUTER]], [[BREAK_OUTER]], [[TMP_EQ]]
 ; GCN-DAG:  s_or_b64            [[BREAK_INNER]], [[BREAK_INNER]], [[TMP_NE]]
 
-; GCN: ; %Flow
-; GCN:      s_or_b64            exec, exec, [[SAVE_EXEC]]
-; GCN:      s_and_b64           [[TMP0:s\[[0-9]+:[0-9]+\]]], exec, [[BREAK_INNER]]
-; GCN:      s_or_b64            [[TMP0]], [[TMP0]], [[LEFT_INNER]]
-; GCN:      s_mov_b64           [[LEFT_INNER]], [[TMP0]]
-; GCN:      s_andn2_b64         exec, exec, [[TMP0]]
-; GCN:      s_cbranch_execnz    [[INNER_LOOP]]
-
-; GCN: ; %Flow2
-; GCN:      s_or_b64            exec, exec, [[TMP0]]
-; GCN:      s_and_b64           [[TMP1:s\[[0-9]+:[0-9]+\]]], exec, [[BREAK_OUTER]]
-; GCN:      s_or_b64            [[TMP1]], [[TMP1]], [[LEFT_OUTER]]
-; GCN:      s_mov_b64           [[LEFT_OUTER]], [[TMP1]]
-; GCN:      s_andn2_b64         exec, exec, [[TMP1]]
-; GCN:      s_cbranch_execnz    [[OUTER_LOOP]]
-
-; GCN: ; %IF
+; GCN: [[IF_BLOCK]]: ; %IF
 ; GCN-NEXT: s_endpgm
 define amdgpu_vs void @multi_else_break(<4 x float> %vec, i32 %ub, i32 %cont) {
 main_body:
@@ -92,12 +92,18 @@ ENDIF:                                            ; preds = %LOOP
 ; GCN-LABEL: {{^}}multi_if_break_loop:
 ; GCN:      s_mov_b64          [[LEFT:s\[[0-9]+:[0-9]+\]]], 0{{$}}
 
+; GCN: ; %Flow4
+; GCN:      s_and_b64          [[BREAK:s\[[0-9]+:[0-9]+\]]], exec, [[BREAK]]
+; GCN:      s_or_b64           [[LEFT]], [[BREAK]], [[OLD_LEFT:s\[[0-9]+:[0-9]+\]]]
+; GCN:      s_andn2_b64        exec, exec, [[LEFT]]
+; GCN-NEXT: s_cbranch_execz
+
 ; GCN: [[LOOP:BB[0-9]+_[0-9]+]]: ; %bb1{{$}}
-; GCN:      s_mov_b64          [[OLD_LEFT:s\[[0-9]+:[0-9]+\]]], [[LEFT]]
+; GCN:      s_mov_b64          [[OLD_LEFT]], [[LEFT]]
 
 ; GCN: ; %LeafBlock1
 ; GCN:      s_mov_b64
-; GCN:      s_mov_b64          [[BREAK:s\[[0-9]+:[0-9]+\]]], -1{{$}}
+; GCN:      s_mov_b64          [[BREAK]], -1{{$}}
 
 ; GCN: ; %case1
 ; GCN:      buffer_load_dword  [[LOAD2:v[0-9]+]],
@@ -118,12 +124,6 @@ ENDIF:                                            ; preds = %LOOP
 ; GCN-DAG:  s_and_b64          [[TMP:s\[[0-9]+:[0-9]+\]]], vcc, exec
 ; GCN:      s_or_b64           [[BREAK]], [[BREAK]], [[TMP]]
 
-; GCN: ; %Flow4
-; GCN:      s_and_b64          [[BREAK]], exec, [[BREAK]]
-; GCN:      s_or_b64           [[LEFT]], [[BREAK]], [[OLD_LEFT]]
-; GCN:      s_andn2_b64        exec, exec, [[LEFT]]
-; GCN-NEXT: s_cbranch_execnz
-
 define amdgpu_kernel void @multi_if_break_loop(i32 %arg) #0 {
 bb:
   %id = call i32 @llvm.amdgcn.workitem.id.x()

llvm/test/CodeGen/AMDGPU/optimize-negated-cond.ll

@@ -3,11 +3,11 @@
 ; GCN-LABEL: {{^}}negated_cond:
 ; GCN: BB0_1:
 ; GCN:   v_cmp_eq_u32_e64 [[CC:[^,]+]],
-; GCN: BB0_2:
+; GCN: BB0_3:
 ; GCN-NOT: v_cndmask_b32
 ; GCN-NOT: v_cmp
 ; GCN:   s_andn2_b64 vcc, exec, [[CC]]
-; GCN:   s_cbranch_vccnz BB0_4
+; GCN:   s_cbranch_vccnz BB0_2
 define amdgpu_kernel void @negated_cond(i32 addrspace(1)* %arg1) {
 bb:
   br label %bb1
@@ -36,11 +36,11 @@ bb4:
 
 ; GCN-LABEL: {{^}}negated_cond_dominated_blocks:
 ; GCN:   v_cmp_eq_u32_e64 [[CC:[^,]+]],
-; GCN: BB1_1:
+; GCN: %bb4
 ; GCN-NOT: v_cndmask_b32
 ; GCN-NOT: v_cmp
 ; GCN:   s_andn2_b64 vcc, exec, [[CC]]
-; GCN:   s_cbranch_vccz BB1_3
+; GCN:   s_cbranch_vccnz BB1_1
 define amdgpu_kernel void @negated_cond_dominated_blocks(i32 addrspace(1)* %arg1) {
 bb:
   br label %bb2

llvm/test/CodeGen/AMDGPU/si-annotate-cf.ll

@@ -96,20 +96,20 @@ declare float @llvm.fabs.f32(float) nounwind readnone
 ; FUNC-LABEL: {{^}}loop_land_info_assert:
 ; SI:      v_cmp_lt_i32_e64 [[CMP4:s\[[0-9:]+\]]], s{{[0-9]+}}, 4{{$}}
 ; SI:      s_and_b64        [[CMP4M:s\[[0-9]+:[0-9]+\]]], exec, [[CMP4]]
-; SI:      s_branch         [[INFLOOP:BB[0-9]+_[0-9]+]]
+
+; SI: [[WHILELOOP:BB[0-9]+_[0-9]+]]: ; %while.cond
+; SI:      s_cbranch_vccz [[FOR_COND_PH:BB[0-9]+_[0-9]+]]
 
 ; SI:      [[CONVEX_EXIT:BB[0-9_]+]]
 ; SI:      s_mov_b64        vcc,
 ; SI-NEXT: s_cbranch_vccnz  [[ENDPGM:BB[0-9]+_[0-9]+]]
-; SI:      s_cbranch_vccnz  [[INFLOOP]]
+
+; SI:      s_cbranch_vccnz  [[WHILELOOP]]
 
 ; SI: ; %if.else
 ; SI:      buffer_store_dword
 
-; SI:      [[INFLOOP]]:
-; SI:      s_cbranch_vccnz [[CONVEX_EXIT]]
-
-; SI: ; %for.cond.preheader
+; SI: [[FOR_COND_PH]]: ; %for.cond.preheader
 ; SI:      s_cbranch_vccz [[ENDPGM]]
 
 ; SI:      [[ENDPGM]]:

llvm/test/CodeGen/AMDGPU/valu-i1.ll

@@ -1,4 +1,4 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs -enable-misched -asm-verbose < %s | FileCheck -check-prefix=SI %s
+; RUN: llc -march=amdgcn -verify-machineinstrs -enable-misched -asm-verbose -disable-block-placement < %s | FileCheck -check-prefix=SI %s
 
 declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone