[llvm] [AMDGPU] Emit amdgcn.if.break in the same BB as amdgcn.loop (PR #118081)

via llvm-commits llvm-commits at lists.llvm.org
Fri Nov 29 03:53:28 PST 2024


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: Mariusz Sikora (mariusz-sikora-at-amd)

<details>
<summary>Changes</summary>

Before this change if.break was placed in wrong loop level which resulted in accumulating values only from last iteration of the inner loop.

---
Full diff: https://github.com/llvm/llvm-project/pull/118081.diff


3 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/SIAnnotateControlFlow.cpp (+6-1) 
- (modified) llvm/test/CodeGen/AMDGPU/multilevel-break.ll (+15-11) 
- (modified) llvm/test/CodeGen/AMDGPU/nested-loop-conditions.ll (+76-74) 


``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SIAnnotateControlFlow.cpp b/llvm/lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
index 67012669a6df0c..ecb7f37f5c3a66 100644
--- a/llvm/lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
+++ b/llvm/lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
@@ -224,8 +224,13 @@ Value *SIAnnotateControlFlow::handleLoopCondition(
   if (Instruction *Inst = dyn_cast<Instruction>(Cond)) {
     BasicBlock *Parent = Inst->getParent();
     Instruction *Insert;
-    if (L->contains(Inst)) {
+    if (LI->getLoopFor(Parent) == L) {
+      // Insert IfBreak in the same BB as Cond, which can help
+      // SILowerControlFlow to know that it does not have to insert an
+      // AND with EXEC.
       Insert = Parent->getTerminator();
+    } else if (L->contains(Inst)) {
+      Insert = Term;
     } else {
       Insert = L->getHeader()->getFirstNonPHIOrDbgOrLifetime();
     }
diff --git a/llvm/test/CodeGen/AMDGPU/multilevel-break.ll b/llvm/test/CodeGen/AMDGPU/multilevel-break.ll
index 65c44768d3d88b..6c62f3f225cd9b 100644
--- a/llvm/test/CodeGen/AMDGPU/multilevel-break.ll
+++ b/llvm/test/CodeGen/AMDGPU/multilevel-break.ll
@@ -27,10 +27,10 @@ define amdgpu_vs void @multi_else_break(<4 x float> %vec, i32 %ub, i32 %cont) {
 ; OPT-NEXT:    call void @llvm.amdgcn.end.cf.i64(i64 [[TMP2]])
 ; OPT-NEXT:    [[TMP6]] = call i64 @llvm.amdgcn.if.break.i64(i1 [[TMP5]], i64 [[PHI_BROKEN]])
 ; OPT-NEXT:    [[TMP7:%.*]] = call i1 @llvm.amdgcn.loop.i64(i64 [[TMP6]])
-; OPT-NEXT:    [[TMP8]] = call i64 @llvm.amdgcn.if.break.i64(i1 [[TMP4]], i64 [[PHI_BROKEN2]])
 ; OPT-NEXT:    br i1 [[TMP7]], label [[FLOW1]], label [[LOOP]]
 ; OPT:       Flow1:
 ; OPT-NEXT:    call void @llvm.amdgcn.end.cf.i64(i64 [[TMP6]])
+; OPT-NEXT:    [[TMP8]] = call i64 @llvm.amdgcn.if.break.i64(i1 [[TMP4]], i64 [[PHI_BROKEN2]])
 ; OPT-NEXT:    [[TMP9:%.*]] = call i1 @llvm.amdgcn.loop.i64(i64 [[TMP8]])
 ; OPT-NEXT:    br i1 [[TMP9]], label [[IF:%.*]], label [[LOOP_OUTER]]
 ; OPT:       IF:
@@ -57,33 +57,37 @@ define amdgpu_vs void @multi_else_break(<4 x float> %vec, i32 %ub, i32 %cont) {
 ; GCN-NEXT:  .LBB0_2: ; %LOOP.outer
 ; GCN-NEXT:    ; =>This Loop Header: Depth=1
 ; GCN-NEXT:    ; Child Loop BB0_4 Depth 2
-; GCN-NEXT:    ; implicit-def: $sgpr6_sgpr7
 ; GCN-NEXT:    ; implicit-def: $sgpr2_sgpr3
+; GCN-NEXT:    ; implicit-def: $sgpr8_sgpr9
+; GCN-NEXT:    ; implicit-def: $sgpr6_sgpr7
 ; GCN-NEXT:    s_mov_b64 s[4:5], 0
 ; GCN-NEXT:    s_branch .LBB0_4
 ; GCN-NEXT:  .LBB0_3: ; %Flow
 ; GCN-NEXT:    ; in Loop: Header=BB0_4 Depth=2
-; GCN-NEXT:    s_or_b64 exec, exec, s[8:9]
-; GCN-NEXT:    s_and_b64 s[8:9], exec, s[6:7]
-; GCN-NEXT:    s_or_b64 s[4:5], s[8:9], s[4:5]
+; GCN-NEXT:    s_or_b64 exec, exec, s[10:11]
+; GCN-NEXT:    s_and_b64 s[10:11], exec, s[8:9]
+; GCN-NEXT:    s_or_b64 s[4:5], s[10:11], s[4:5]
+; GCN-NEXT:    s_andn2_b64 s[2:3], s[2:3], exec
+; GCN-NEXT:    s_and_b64 s[10:11], s[6:7], exec
+; GCN-NEXT:    s_or_b64 s[2:3], s[2:3], s[10:11]
 ; GCN-NEXT:    s_andn2_b64 exec, exec, s[4:5]
 ; GCN-NEXT:    s_cbranch_execz .LBB0_1
 ; GCN-NEXT:  .LBB0_4: ; %LOOP
 ; GCN-NEXT:    ; Parent Loop BB0_2 Depth=1
 ; GCN-NEXT:    ; => This Inner Loop Header: Depth=2
 ; GCN-NEXT:    v_cmp_lt_i32_e32 vcc, v0, v4
-; GCN-NEXT:    s_or_b64 s[2:3], s[2:3], exec
 ; GCN-NEXT:    s_or_b64 s[6:7], s[6:7], exec
-; GCN-NEXT:    s_and_saveexec_b64 s[8:9], vcc
+; GCN-NEXT:    s_or_b64 s[8:9], s[8:9], exec
+; GCN-NEXT:    s_and_saveexec_b64 s[10:11], vcc
 ; GCN-NEXT:    s_cbranch_execz .LBB0_3
 ; GCN-NEXT:  ; %bb.5: ; %ENDIF
 ; GCN-NEXT:    ; in Loop: Header=BB0_4 Depth=2
 ; GCN-NEXT:    v_add_i32_e32 v0, vcc, 1, v0
-; GCN-NEXT:    s_andn2_b64 s[2:3], s[2:3], exec
-; GCN-NEXT:    v_cmp_ne_u32_e32 vcc, v5, v0
 ; GCN-NEXT:    s_andn2_b64 s[6:7], s[6:7], exec
-; GCN-NEXT:    s_and_b64 s[10:11], vcc, exec
-; GCN-NEXT:    s_or_b64 s[6:7], s[6:7], s[10:11]
+; GCN-NEXT:    v_cmp_ne_u32_e32 vcc, v5, v0
+; GCN-NEXT:    s_andn2_b64 s[8:9], s[8:9], exec
+; GCN-NEXT:    s_and_b64 s[12:13], vcc, exec
+; GCN-NEXT:    s_or_b64 s[8:9], s[8:9], s[12:13]
 ; GCN-NEXT:    s_branch .LBB0_3
 ; GCN-NEXT:  .LBB0_6: ; %IF
 ; GCN-NEXT:    s_endpgm
diff --git a/llvm/test/CodeGen/AMDGPU/nested-loop-conditions.ll b/llvm/test/CodeGen/AMDGPU/nested-loop-conditions.ll
index a52d9ff526c2ae..bd6ef9e088b12f 100644
--- a/llvm/test/CodeGen/AMDGPU/nested-loop-conditions.ll
+++ b/llvm/test/CodeGen/AMDGPU/nested-loop-conditions.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
 ; RUN: opt -mtriple=amdgcn-- -S -structurizecfg -si-annotate-control-flow %s | FileCheck -check-prefix=IR %s
 ; RUN: llc -mtriple=amdgcn -mcpu=hawaii -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
@@ -46,51 +46,52 @@ define amdgpu_kernel void @reduced_nested_loop_conditions(ptr addrspace(3) nocap
 ; GCN-NEXT:    s_cbranch_vccz .LBB0_6
 ; GCN-NEXT:  .LBB0_7: ; %DummyReturnBlock
 ; GCN-NEXT:    s_endpgm
-; IR-LABEL: @reduced_nested_loop_conditions(
-; IR-NEXT:  bb:
+; IR-LABEL: define amdgpu_kernel void @reduced_nested_loop_conditions(
+; IR-SAME: ptr addrspace(3) nocapture [[ARG:%.*]]) #[[ATTR0:[0-9]+]] {
+; IR-NEXT:  [[BB:.*]]:
 ; IR-NEXT:    [[MY_TMP:%.*]] = tail call i32 @llvm.amdgcn.workitem.id.x() #[[ATTR4:[0-9]+]]
-; IR-NEXT:    [[MY_TMP1:%.*]] = getelementptr inbounds i64, ptr addrspace(3) [[ARG:%.*]], i32 [[MY_TMP]]
+; IR-NEXT:    [[MY_TMP1:%.*]] = getelementptr inbounds i64, ptr addrspace(3) [[ARG]], i32 [[MY_TMP]]
 ; IR-NEXT:    [[MY_TMP2:%.*]] = load volatile i64, ptr addrspace(3) [[MY_TMP1]], align 8
-; IR-NEXT:    br label [[BB5:%.*]]
-; IR:       bb3:
-; IR-NEXT:    br i1 true, label [[BB4:%.*]], label [[BB13:%.*]]
-; IR:       bb4:
-; IR-NEXT:    br label [[FLOW:%.*]]
-; IR:       bb5:
-; IR-NEXT:    [[PHI_BROKEN:%.*]] = phi i64 [ [[TMP6:%.*]], [[BB10:%.*]] ], [ 0, [[BB:%.*]] ]
-; IR-NEXT:    [[MY_TMP6:%.*]] = phi i32 [ 0, [[BB]] ], [ [[TMP5:%.*]], [[BB10]] ]
+; IR-NEXT:    br label %[[BB5:.*]]
+; IR:       [[BB3:.*]]:
+; IR-NEXT:    br i1 true, label %[[BB4:.*]], label %[[BB13:.*]]
+; IR:       [[BB4]]:
+; IR-NEXT:    br label %[[FLOW:.*]]
+; IR:       [[BB5]]:
+; IR-NEXT:    [[PHI_BROKEN:%.*]] = phi i64 [ [[TMP6:%.*]], %[[BB10:.*]] ], [ 0, %[[BB]] ]
+; IR-NEXT:    [[MY_TMP6:%.*]] = phi i32 [ 0, %[[BB]] ], [ [[TMP5:%.*]], %[[BB10]] ]
 ; IR-NEXT:    [[MY_TMP7:%.*]] = icmp eq i32 [[MY_TMP6]], 1
 ; IR-NEXT:    [[TMP0:%.*]] = call { i1, i64 } @llvm.amdgcn.if.i64(i1 [[MY_TMP7]])
 ; IR-NEXT:    [[TMP1:%.*]] = extractvalue { i1, i64 } [[TMP0]], 0
 ; IR-NEXT:    [[TMP2:%.*]] = extractvalue { i1, i64 } [[TMP0]], 1
-; IR-NEXT:    br i1 [[TMP1]], label [[BB8:%.*]], label [[FLOW]]
-; IR:       bb8:
-; IR-NEXT:    br label [[BB13]]
-; IR:       bb9:
-; IR-NEXT:    br i1 false, label [[BB3:%.*]], label [[BB9:%.*]]
-; IR:       bb10:
+; IR-NEXT:    br i1 [[TMP1]], label %[[BB8:.*]], label %[[FLOW]]
+; IR:       [[BB8]]:
+; IR-NEXT:    br label %[[BB13]]
+; IR:       [[BB9:.*]]:
+; IR-NEXT:    br i1 false, label %[[BB3]], label %[[BB9]]
+; IR:       [[BB10]]:
 ; IR-NEXT:    [[TMP3:%.*]] = call i1 @llvm.amdgcn.loop.i64(i64 [[TMP6]])
-; IR-NEXT:    br i1 [[TMP3]], label [[BB23:%.*]], label [[BB5]]
-; IR:       Flow:
-; IR-NEXT:    [[TMP4:%.*]] = phi i1 [ [[MY_TMP22:%.*]], [[BB4]] ], [ true, [[BB5]] ]
-; IR-NEXT:    [[TMP5]] = phi i32 [ [[MY_TMP21:%.*]], [[BB4]] ], [ undef, [[BB5]] ]
+; IR-NEXT:    br i1 [[TMP3]], label %[[BB23:.*]], label %[[BB5]]
+; IR:       [[FLOW]]:
+; IR-NEXT:    [[TMP4:%.*]] = phi i1 [ [[MY_TMP22:%.*]], %[[BB4]] ], [ true, %[[BB5]] ]
+; IR-NEXT:    [[TMP5]] = phi i32 [ [[MY_TMP21:%.*]], %[[BB4]] ], [ undef, %[[BB5]] ]
 ; IR-NEXT:    call void @llvm.amdgcn.end.cf.i64(i64 [[TMP2]])
 ; IR-NEXT:    [[TMP6]] = call i64 @llvm.amdgcn.if.break.i64(i1 [[TMP4]], i64 [[PHI_BROKEN]])
-; IR-NEXT:    br label [[BB10]]
-; IR:       bb13:
-; IR-NEXT:    [[MY_TMP14:%.*]] = phi i1 [ [[MY_TMP22]], [[BB3]] ], [ true, [[BB8]] ]
+; IR-NEXT:    br label %[[BB10]]
+; IR:       [[BB13]]:
+; IR-NEXT:    [[MY_TMP14:%.*]] = phi i1 [ [[MY_TMP22]], %[[BB3]] ], [ true, %[[BB8]] ]
 ; IR-NEXT:    [[MY_TMP15:%.*]] = bitcast i64 [[MY_TMP2]] to <2 x i32>
-; IR-NEXT:    br i1 [[MY_TMP14]], label [[BB16:%.*]], label [[BB20:%.*]]
-; IR:       bb16:
+; IR-NEXT:    br i1 [[MY_TMP14]], label %[[BB16:.*]], label %[[BB20:.*]]
+; IR:       [[BB16]]:
 ; IR-NEXT:    [[MY_TMP17:%.*]] = extractelement <2 x i32> [[MY_TMP15]], i64 1
 ; IR-NEXT:    [[MY_TMP18:%.*]] = getelementptr inbounds i32, ptr addrspace(3) undef, i32 [[MY_TMP17]]
 ; IR-NEXT:    [[MY_TMP19:%.*]] = load volatile i32, ptr addrspace(3) [[MY_TMP18]], align 4
-; IR-NEXT:    br label [[BB20]]
-; IR:       bb20:
-; IR-NEXT:    [[MY_TMP21]] = phi i32 [ [[MY_TMP19]], [[BB16]] ], [ 0, [[BB13]] ]
-; IR-NEXT:    [[MY_TMP22]] = phi i1 [ false, [[BB16]] ], [ [[MY_TMP14]], [[BB13]] ]
-; IR-NEXT:    br label [[BB9]]
-; IR:       bb23:
+; IR-NEXT:    br label %[[BB20]]
+; IR:       [[BB20]]:
+; IR-NEXT:    [[MY_TMP21]] = phi i32 [ [[MY_TMP19]], %[[BB16]] ], [ 0, %[[BB13]] ]
+; IR-NEXT:    [[MY_TMP22]] = phi i1 [ false, %[[BB16]] ], [ [[MY_TMP14]], %[[BB13]] ]
+; IR-NEXT:    br label %[[BB9]]
+; IR:       [[BB23]]:
 ; IR-NEXT:    call void @llvm.amdgcn.end.cf.i64(i64 [[TMP6]])
 ; IR-NEXT:    ret void
 bb:
@@ -188,66 +189,67 @@ define amdgpu_kernel void @nested_loop_conditions(ptr addrspace(1) nocapture %ar
 ; GCN-NEXT:    buffer_store_dword v0, off, s[0:3], 0
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    s_endpgm
-; IR-LABEL: @nested_loop_conditions(
-; IR-NEXT:  bb:
+; IR-LABEL: define amdgpu_kernel void @nested_loop_conditions(
+; IR-SAME: ptr addrspace(1) nocapture [[ARG:%.*]]) #[[ATTR0]] {
+; IR-NEXT:  [[BB:.*]]:
 ; IR-NEXT:    [[MY_TMP1134:%.*]] = load volatile i32, ptr addrspace(1) undef, align 4
 ; IR-NEXT:    [[MY_TMP1235:%.*]] = icmp slt i32 [[MY_TMP1134]], 9
-; IR-NEXT:    br i1 [[MY_TMP1235]], label [[BB14_LR_PH:%.*]], label [[FLOW:%.*]]
-; IR:       bb14.lr.ph:
+; IR-NEXT:    br i1 [[MY_TMP1235]], label %[[BB14_LR_PH:.*]], label %[[FLOW:.*]]
+; IR:       [[BB14_LR_PH]]:
 ; IR-NEXT:    [[MY_TMP:%.*]] = tail call i32 @llvm.amdgcn.workitem.id.x() #[[ATTR4]]
 ; IR-NEXT:    [[MY_TMP1:%.*]] = zext i32 [[MY_TMP]] to i64
-; IR-NEXT:    [[MY_TMP2:%.*]] = getelementptr inbounds i64, ptr addrspace(1) [[ARG:%.*]], i64 [[MY_TMP1]]
+; IR-NEXT:    [[MY_TMP2:%.*]] = getelementptr inbounds i64, ptr addrspace(1) [[ARG]], i64 [[MY_TMP1]]
 ; IR-NEXT:    [[MY_TMP3:%.*]] = load i64, ptr addrspace(1) [[MY_TMP2]], align 16
 ; IR-NEXT:    [[MY_TMP932:%.*]] = load <4 x i32>, ptr addrspace(1) undef, align 16
 ; IR-NEXT:    [[MY_TMP1033:%.*]] = extractelement <4 x i32> [[MY_TMP932]], i64 0
-; IR-NEXT:    br label [[BB14:%.*]]
-; IR:       Flow3:
+; IR-NEXT:    br label %[[BB14:.*]]
+; IR:       [[FLOW3:.*]]:
 ; IR-NEXT:    call void @llvm.amdgcn.end.cf.i64(i64 [[TMP20:%.*]])
 ; IR-NEXT:    [[TMP0:%.*]] = call { i1, i64 } @llvm.amdgcn.if.i64(i1 [[TMP14:%.*]])
 ; IR-NEXT:    [[TMP1:%.*]] = extractvalue { i1, i64 } [[TMP0]], 0
 ; IR-NEXT:    [[TMP2:%.*]] = extractvalue { i1, i64 } [[TMP0]], 1
-; IR-NEXT:    br i1 [[TMP1]], label [[BB4_BB13_CRIT_EDGE:%.*]], label [[FLOW4:%.*]]
-; IR:       bb4.bb13_crit_edge:
-; IR-NEXT:    br label [[FLOW4]]
-; IR:       Flow4:
-; IR-NEXT:    [[TMP3:%.*]] = phi i1 [ true, [[BB4_BB13_CRIT_EDGE]] ], [ false, [[FLOW3:%.*]] ]
+; IR-NEXT:    br i1 [[TMP1]], label %[[BB4_BB13_CRIT_EDGE:.*]], label %[[FLOW4:.*]]
+; IR:       [[BB4_BB13_CRIT_EDGE]]:
+; IR-NEXT:    br label %[[FLOW4]]
+; IR:       [[FLOW4]]:
+; IR-NEXT:    [[TMP3:%.*]] = phi i1 [ true, %[[BB4_BB13_CRIT_EDGE]] ], [ false, %[[FLOW3]] ]
 ; IR-NEXT:    call void @llvm.amdgcn.end.cf.i64(i64 [[TMP2]])
-; IR-NEXT:    br label [[FLOW]]
-; IR:       bb13:
-; IR-NEXT:    br label [[BB31:%.*]]
-; IR:       Flow:
-; IR-NEXT:    [[TMP4:%.*]] = phi i1 [ [[TMP3]], [[FLOW4]] ], [ true, [[BB:%.*]] ]
+; IR-NEXT:    br label %[[FLOW]]
+; IR:       [[BB13:.*]]:
+; IR-NEXT:    br label %[[BB31:.*]]
+; IR:       [[FLOW]]:
+; IR-NEXT:    [[TMP4:%.*]] = phi i1 [ [[TMP3]], %[[FLOW4]] ], [ true, %[[BB]] ]
 ; IR-NEXT:    [[TMP5:%.*]] = call { i1, i64 } @llvm.amdgcn.if.i64(i1 [[TMP4]])
 ; IR-NEXT:    [[TMP6:%.*]] = extractvalue { i1, i64 } [[TMP5]], 0
 ; IR-NEXT:    [[TMP7:%.*]] = extractvalue { i1, i64 } [[TMP5]], 1
-; IR-NEXT:    br i1 [[TMP6]], label [[BB13:%.*]], label [[BB31]]
-; IR:       bb14:
-; IR-NEXT:    [[PHI_BROKEN:%.*]] = phi i64 [ [[TMP16:%.*]], [[FLOW1:%.*]] ], [ 0, [[BB14_LR_PH]] ]
-; IR-NEXT:    [[MY_TMP1037:%.*]] = phi i32 [ [[MY_TMP1033]], [[BB14_LR_PH]] ], [ [[TMP12:%.*]], [[FLOW1]] ]
-; IR-NEXT:    [[MY_TMP936:%.*]] = phi <4 x i32> [ [[MY_TMP932]], [[BB14_LR_PH]] ], [ [[TMP11:%.*]], [[FLOW1]] ]
+; IR-NEXT:    br i1 [[TMP6]], label %[[BB13]], label %[[BB31]]
+; IR:       [[BB14]]:
+; IR-NEXT:    [[PHI_BROKEN:%.*]] = phi i64 [ [[TMP16:%.*]], %[[FLOW1:.*]] ], [ 0, %[[BB14_LR_PH]] ]
+; IR-NEXT:    [[MY_TMP1037:%.*]] = phi i32 [ [[MY_TMP1033]], %[[BB14_LR_PH]] ], [ [[TMP12:%.*]], %[[FLOW1]] ]
+; IR-NEXT:    [[MY_TMP936:%.*]] = phi <4 x i32> [ [[MY_TMP932]], %[[BB14_LR_PH]] ], [ [[TMP11:%.*]], %[[FLOW1]] ]
 ; IR-NEXT:    [[MY_TMP15:%.*]] = icmp eq i32 [[MY_TMP1037]], 1
 ; IR-NEXT:    [[TMP8:%.*]] = call { i1, i64 } @llvm.amdgcn.if.i64(i1 [[MY_TMP15]])
 ; IR-NEXT:    [[TMP9:%.*]] = extractvalue { i1, i64 } [[TMP8]], 0
 ; IR-NEXT:    [[TMP10:%.*]] = extractvalue { i1, i64 } [[TMP8]], 1
-; IR-NEXT:    br i1 [[TMP9]], label [[BB16:%.*]], label [[FLOW1]]
-; IR:       bb16:
+; IR-NEXT:    br i1 [[TMP9]], label %[[BB16:.*]], label %[[FLOW1]]
+; IR:       [[BB16]]:
 ; IR-NEXT:    [[MY_TMP17:%.*]] = bitcast i64 [[MY_TMP3]] to <2 x i32>
-; IR-NEXT:    br label [[BB18:%.*]]
-; IR:       Flow1:
-; IR-NEXT:    [[TMP11]] = phi <4 x i32> [ [[MY_TMP9:%.*]], [[BB21:%.*]] ], [ undef, [[BB14]] ]
-; IR-NEXT:    [[TMP12]] = phi i32 [ [[MY_TMP10:%.*]], [[BB21]] ], [ undef, [[BB14]] ]
-; IR-NEXT:    [[TMP13:%.*]] = phi i1 [ [[MY_TMP12:%.*]], [[BB21]] ], [ true, [[BB14]] ]
-; IR-NEXT:    [[TMP14]] = phi i1 [ [[MY_TMP12]], [[BB21]] ], [ false, [[BB14]] ]
-; IR-NEXT:    [[TMP15:%.*]] = phi i1 [ false, [[BB21]] ], [ true, [[BB14]] ]
+; IR-NEXT:    br label %[[BB18:.*]]
+; IR:       [[FLOW1]]:
+; IR-NEXT:    [[TMP11]] = phi <4 x i32> [ [[MY_TMP9:%.*]], %[[BB21:.*]] ], [ undef, %[[BB14]] ]
+; IR-NEXT:    [[TMP12]] = phi i32 [ [[MY_TMP10:%.*]], %[[BB21]] ], [ undef, %[[BB14]] ]
+; IR-NEXT:    [[TMP13:%.*]] = phi i1 [ [[MY_TMP12:%.*]], %[[BB21]] ], [ true, %[[BB14]] ]
+; IR-NEXT:    [[TMP14]] = phi i1 [ [[MY_TMP12]], %[[BB21]] ], [ false, %[[BB14]] ]
+; IR-NEXT:    [[TMP15:%.*]] = phi i1 [ false, %[[BB21]] ], [ true, %[[BB14]] ]
 ; IR-NEXT:    call void @llvm.amdgcn.end.cf.i64(i64 [[TMP10]])
 ; IR-NEXT:    [[TMP16]] = call i64 @llvm.amdgcn.if.break.i64(i1 [[TMP13]], i64 [[PHI_BROKEN]])
 ; IR-NEXT:    [[TMP17:%.*]] = call i1 @llvm.amdgcn.loop.i64(i64 [[TMP16]])
-; IR-NEXT:    br i1 [[TMP17]], label [[FLOW2:%.*]], label [[BB14]]
-; IR:       bb18:
+; IR-NEXT:    br i1 [[TMP17]], label %[[FLOW2:.*]], label %[[BB14]]
+; IR:       [[BB18]]:
 ; IR-NEXT:    [[MY_TMP19:%.*]] = load volatile i32, ptr addrspace(1) undef, align 4
 ; IR-NEXT:    [[MY_TMP20:%.*]] = icmp slt i32 [[MY_TMP19]], 9
-; IR-NEXT:    br i1 [[MY_TMP20]], label [[BB21]], label [[BB18]]
-; IR:       bb21:
+; IR-NEXT:    br i1 [[MY_TMP20]], label %[[BB21]], label %[[BB18]]
+; IR:       [[BB21]]:
 ; IR-NEXT:    [[MY_TMP22:%.*]] = extractelement <2 x i32> [[MY_TMP17]], i64 1
 ; IR-NEXT:    [[MY_TMP23:%.*]] = lshr i32 [[MY_TMP22]], 16
 ; IR-NEXT:    [[MY_TMP24:%.*]] = select i1 undef, i32 undef, i32 [[MY_TMP23]]
@@ -263,16 +265,16 @@ define amdgpu_kernel void @nested_loop_conditions(ptr addrspace(1) nocapture %ar
 ; IR-NEXT:    [[MY_TMP10]] = extractelement <4 x i32> [[MY_TMP9]], i64 0
 ; IR-NEXT:    [[MY_TMP11:%.*]] = load volatile i32, ptr addrspace(1) undef, align 4
 ; IR-NEXT:    [[MY_TMP12]] = icmp sge i32 [[MY_TMP11]], 9
-; IR-NEXT:    br label [[FLOW1]]
-; IR:       Flow2:
+; IR-NEXT:    br label %[[FLOW1]]
+; IR:       [[FLOW2]]:
 ; IR-NEXT:    call void @llvm.amdgcn.end.cf.i64(i64 [[TMP16]])
 ; IR-NEXT:    [[TMP18:%.*]] = call { i1, i64 } @llvm.amdgcn.if.i64(i1 [[TMP15]])
 ; IR-NEXT:    [[TMP19:%.*]] = extractvalue { i1, i64 } [[TMP18]], 0
 ; IR-NEXT:    [[TMP20]] = extractvalue { i1, i64 } [[TMP18]], 1
-; IR-NEXT:    br i1 [[TMP19]], label [[BB31_LOOPEXIT:%.*]], label [[FLOW3]]
-; IR:       bb31.loopexit:
-; IR-NEXT:    br label [[FLOW3]]
-; IR:       bb31:
+; IR-NEXT:    br i1 [[TMP19]], label %[[BB31_LOOPEXIT:.*]], label %[[FLOW3]]
+; IR:       [[BB31_LOOPEXIT]]:
+; IR-NEXT:    br label %[[FLOW3]]
+; IR:       [[BB31]]:
 ; IR-NEXT:    call void @llvm.amdgcn.end.cf.i64(i64 [[TMP7]])
 ; IR-NEXT:    store volatile i32 0, ptr addrspace(1) undef, align 4
 ; IR-NEXT:    ret void

``````````

</details>


https://github.com/llvm/llvm-project/pull/118081


More information about the llvm-commits mailing list