Skip to content

[AMDGPU] InstCombine llvm.amdgcn.ds.bpermute with uniform arguments #129895

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 6, 2025

Conversation

jayfoad
Copy link
Contributor

@jayfoad jayfoad commented Mar 5, 2025

No description provided.

@llvmbot
Copy link
Member

llvmbot commented Mar 5, 2025

@llvm/pr-subscribers-llvm-transforms

@llvm/pr-subscribers-backend-amdgpu

Author: Jay Foad (jayfoad)

Changes

Full diff: https://github.com/llvm/llvm-project/pull/129895.diff

2 Files Affected:

  • (modified) llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp (+21-3)
  • (modified) llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll (+64-23)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
index ebe740f884ea6..8925f2e974efa 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
@@ -1118,9 +1118,11 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
   }
   case Intrinsic::amdgcn_permlane64:
   case Intrinsic::amdgcn_readfirstlane:
-  case Intrinsic::amdgcn_readlane: {
-    // If the first argument is uniform these intrinsics return it unchanged.
-    const Use &Src = II.getArgOperandUse(0);
+  case Intrinsic::amdgcn_readlane:
+  case Intrinsic::amdgcn_ds_bpermute: {
+    // If the data argument is uniform these intrinsics return it unchanged.
+    unsigned SrcIdx = IID == Intrinsic::amdgcn_ds_bpermute ? 1 : 0;
+    const Use &Src = II.getArgOperandUse(SrcIdx);
     if (isTriviallyUniform(Src))
       return IC.replaceInstUsesWith(II, Src.get());
 
@@ -1152,6 +1154,22 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
       }
     }
 
+    // If the lane argument of bpermute is uniform, change it to readlane. This
+    // generates better code and can enable further optimizations because
+    // readlane is AlwaysUniform.
+    if (IID == Intrinsic::amdgcn_ds_bpermute) {
+      const Use &Lane = II.getArgOperandUse(0);
+      if (isTriviallyUniform(Lane)) {
+        Value *NewLane = IC.Builder.CreateLShr(Lane, 2);
+        Function *NewDecl = Intrinsic::getOrInsertDeclaration(
+            II.getModule(), Intrinsic::amdgcn_readlane, II.getType());
+        II.setCalledFunction(NewDecl);
+        II.setOperand(0, Src);
+        II.setOperand(1, NewLane);
+        return ⅈ
+      }
+    }
+
     return std::nullopt;
   }
   case Intrinsic::amdgcn_writelane: {
diff --git a/llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll b/llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
index 3605c4a929c58..843b436aa1b0f 100644
--- a/llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
+++ b/llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
@@ -66,7 +66,7 @@ define double @test_constant_fold_rcp_f64_43() nounwind {
 
 define float @test_constant_fold_rcp_f32_43_strictfp() nounwind strictfp {
 ; CHECK-LABEL: @test_constant_fold_rcp_f32_43_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.rcp.f32(float 4.300000e+01) #[[ATTR14:[0-9]+]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.rcp.f32(float 4.300000e+01) #[[ATTR17:[0-9]+]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.rcp.f32(float 4.300000e+01) strictfp nounwind readnone
@@ -115,7 +115,7 @@ define half @test_constant_fold_sqrt_f16_0() nounwind {
 
 define float @test_constant_fold_sqrt_f32_0() nounwind {
 ; CHECK-LABEL: @test_constant_fold_sqrt_f32_0(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.sqrt.f32(float 0.000000e+00) #[[ATTR15:[0-9]+]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.sqrt.f32(float 0.000000e+00) #[[ATTR18:[0-9]+]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.sqrt.f32(float 0.0) nounwind readnone
@@ -124,7 +124,7 @@ define float @test_constant_fold_sqrt_f32_0() nounwind {
 
 define double @test_constant_fold_sqrt_f64_0() nounwind {
 ; CHECK-LABEL: @test_constant_fold_sqrt_f64_0(
-; CHECK-NEXT:    [[VAL:%.*]] = call double @llvm.amdgcn.sqrt.f64(double 0.000000e+00) #[[ATTR15]]
+; CHECK-NEXT:    [[VAL:%.*]] = call double @llvm.amdgcn.sqrt.f64(double 0.000000e+00) #[[ATTR18]]
 ; CHECK-NEXT:    ret double [[VAL]]
 ;
   %val = call double @llvm.amdgcn.sqrt.f64(double 0.0) nounwind readnone
@@ -141,7 +141,7 @@ define half @test_constant_fold_sqrt_f16_neg0() nounwind {
 
 define float @test_constant_fold_sqrt_f32_neg0() nounwind {
 ; CHECK-LABEL: @test_constant_fold_sqrt_f32_neg0(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.sqrt.f32(float -0.000000e+00) #[[ATTR15]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.sqrt.f32(float -0.000000e+00) #[[ATTR18]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.sqrt.f32(float -0.0) nounwind readnone
@@ -150,7 +150,7 @@ define float @test_constant_fold_sqrt_f32_neg0() nounwind {
 
 define double @test_constant_fold_sqrt_f64_neg0() nounwind {
 ; CHECK-LABEL: @test_constant_fold_sqrt_f64_neg0(
-; CHECK-NEXT:    [[VAL:%.*]] = call double @llvm.amdgcn.sqrt.f64(double -0.000000e+00) #[[ATTR15]]
+; CHECK-NEXT:    [[VAL:%.*]] = call double @llvm.amdgcn.sqrt.f64(double -0.000000e+00) #[[ATTR18]]
 ; CHECK-NEXT:    ret double [[VAL]]
 ;
   %val = call double @llvm.amdgcn.sqrt.f64(double -0.0) nounwind readnone
@@ -718,7 +718,7 @@ define i1 @test_class_isnan_f32(float %x) nounwind {
 
 define i1 @test_class_isnan_f32_strict(float %x) nounwind strictfp {
 ; CHECK-LABEL: @test_class_isnan_f32_strict(
-; CHECK-NEXT:    [[VAL:%.*]] = call i1 @llvm.is.fpclass.f32(float [[X:%.*]], i32 3) #[[ATTR16:[0-9]+]]
+; CHECK-NEXT:    [[VAL:%.*]] = call i1 @llvm.is.fpclass.f32(float [[X:%.*]], i32 3) #[[ATTR19:[0-9]+]]
 ; CHECK-NEXT:    ret i1 [[VAL]]
 ;
   %val = call i1 @llvm.amdgcn.class.f32(float %x, i32 3) strictfp
@@ -736,7 +736,7 @@ define i1 @test_class_is_p0_n0_f32(float %x) nounwind {
 
 define i1 @test_class_is_p0_n0_f32_strict(float %x) nounwind strictfp {
 ; CHECK-LABEL: @test_class_is_p0_n0_f32_strict(
-; CHECK-NEXT:    [[VAL:%.*]] = call i1 @llvm.is.fpclass.f32(float [[X:%.*]], i32 96) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call i1 @llvm.is.fpclass.f32(float [[X:%.*]], i32 96) #[[ATTR19]]
 ; CHECK-NEXT:    ret i1 [[VAL]]
 ;
   %val = call i1 @llvm.amdgcn.class.f32(float %x, i32 96) strictfp
@@ -2000,7 +2000,7 @@ define i64 @icmp_constant_inputs_false() {
 
 define i64 @icmp_constant_inputs_true() {
 ; CHECK-LABEL: @icmp_constant_inputs_true(
-; CHECK-NEXT:    [[RESULT:%.*]] = call i64 @llvm.read_register.i64(metadata [[META0:![0-9]+]]) #[[ATTR17:[0-9]+]]
+; CHECK-NEXT:    [[RESULT:%.*]] = call i64 @llvm.read_register.i64(metadata [[META0:![0-9]+]]) #[[ATTR20:[0-9]+]]
 ; CHECK-NEXT:    ret i64 [[RESULT]]
 ;
   %result = call i64 @llvm.amdgcn.icmp.i64.i32(i32 9, i32 8, i32 34)
@@ -2707,7 +2707,7 @@ define i64 @fcmp_constant_inputs_false() {
 
 define i64 @fcmp_constant_inputs_true() {
 ; CHECK-LABEL: @fcmp_constant_inputs_true(
-; CHECK-NEXT:    [[RESULT:%.*]] = call i64 @llvm.read_register.i64(metadata [[META0]]) #[[ATTR17]]
+; CHECK-NEXT:    [[RESULT:%.*]] = call i64 @llvm.read_register.i64(metadata [[META0]]) #[[ATTR20]]
 ; CHECK-NEXT:    ret i64 [[RESULT]]
 ;
   %result = call i64 @llvm.amdgcn.fcmp.i64.f32(float 2.0, float 4.0, i32 4)
@@ -5845,7 +5845,7 @@ define double @trig_preop_constfold_neg32_segment() {
 
 define double @trig_preop_constfold_strictfp() strictfp {
 ; CHECK-LABEL: @trig_preop_constfold_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call double @llvm.amdgcn.trig.preop.f64(double 3.454350e+02, i32 5) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call double @llvm.amdgcn.trig.preop.f64(double 3.454350e+02, i32 5) #[[ATTR19]]
 ; CHECK-NEXT:    ret double [[VAL]]
 ;
   %val = call double @llvm.amdgcn.trig.preop.f64(double 3.454350e+02, i32 5) strictfp
@@ -6214,7 +6214,7 @@ define half @test_constant_fold_log_f16_neg10() {
 
 define float @test_constant_fold_log_f32_qnan_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_log_f32_qnan_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.log.f32(float 0x7FF8000000000000) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.log.f32(float 0x7FF8000000000000) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.log.f32(float 0x7FF8000000000000) strictfp
@@ -6223,7 +6223,7 @@ define float @test_constant_fold_log_f32_qnan_strictfp() strictfp {
 
 define float @test_constant_fold_log_f32_0_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_log_f32_0_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.log.f32(float 0.000000e+00) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.log.f32(float 0.000000e+00) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.log.f32(float 0.0) strictfp
@@ -6232,7 +6232,7 @@ define float @test_constant_fold_log_f32_0_strictfp() strictfp {
 
 define float @test_constant_fold_log_f32_neg0_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_log_f32_neg0_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.log.f32(float -0.000000e+00) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.log.f32(float -0.000000e+00) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.log.f32(float -0.0) strictfp
@@ -6241,7 +6241,7 @@ define float @test_constant_fold_log_f32_neg0_strictfp() strictfp {
 
 define float @test_constant_fold_log_f32_neg_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_log_f32_neg_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.log.f32(float -1.000000e+01) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.log.f32(float -1.000000e+01) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.log.f32(float -10.0) strictfp
@@ -6258,7 +6258,7 @@ define float @test_constant_fold_log_f32_pinf_strictfp() strictfp {
 
 define float @test_constant_fold_log_f32_ninf_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_log_f32_ninf_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.log.f32(float 0xFFF0000000000000) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.log.f32(float 0xFFF0000000000000) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.log.f32(float 0xFFF0000000000000) strictfp
@@ -6460,7 +6460,7 @@ define half @test_constant_fold_exp2_f16_neg10() {
 
 define float @test_constant_fold_exp2_f32_qnan_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_exp2_f32_qnan_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float 0x7FF8000000000000) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float 0x7FF8000000000000) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.exp2.f32(float 0x7FF8000000000000) strictfp
@@ -6469,7 +6469,7 @@ define float @test_constant_fold_exp2_f32_qnan_strictfp() strictfp {
 
 define float @test_constant_fold_exp2_f32_0_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_exp2_f32_0_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float 0.000000e+00) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float 0.000000e+00) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.exp2.f32(float 0.0) strictfp
@@ -6478,7 +6478,7 @@ define float @test_constant_fold_exp2_f32_0_strictfp() strictfp {
 
 define float @test_constant_fold_exp2_f32_neg0_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_exp2_f32_neg0_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float -0.000000e+00) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float -0.000000e+00) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.exp2.f32(float -0.0) strictfp
@@ -6487,7 +6487,7 @@ define float @test_constant_fold_exp2_f32_neg0_strictfp() strictfp {
 
 define float @test_constant_fold_exp2_f32_1_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_exp2_f32_1_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float 1.000000e+00) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float 1.000000e+00) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.exp2.f32(float 1.0) strictfp
@@ -6496,7 +6496,7 @@ define float @test_constant_fold_exp2_f32_1_strictfp() strictfp {
 
 define float @test_constant_fold_exp2_f32_neg1_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_exp2_f32_neg1_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float -1.000000e+00) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float -1.000000e+00) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.exp2.f32(float -1.0) strictfp
@@ -6505,7 +6505,7 @@ define float @test_constant_fold_exp2_f32_neg1_strictfp() strictfp {
 
 define float @test_constant_fold_exp2_f32_2_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_exp2_f32_2_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float 2.000000e+00) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float 2.000000e+00) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.exp2.f32(float 2.0) strictfp
@@ -6514,7 +6514,7 @@ define float @test_constant_fold_exp2_f32_2_strictfp() strictfp {
 
 define float @test_constant_fold_exp2_f32_neg2_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_exp2_f32_neg2_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float -2.000000e+00) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float -2.000000e+00) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.exp2.f32(float -2.0) strictfp
@@ -6523,7 +6523,7 @@ define float @test_constant_fold_exp2_f32_neg2_strictfp() strictfp {
 
 define float @test_constant_fold_exp2_f32_neg_strictfp() strictfp {
 ; CHECK-LABEL: @test_constant_fold_exp2_f32_neg_strictfp(
-; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float -1.000000e+01) #[[ATTR16]]
+; CHECK-NEXT:    [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float -1.000000e+01) #[[ATTR19]]
 ; CHECK-NEXT:    ret float [[VAL]]
 ;
   %val = call float @llvm.amdgcn.exp2.f32(float -10.0) strictfp
@@ -6571,6 +6571,7 @@ declare i32 @llvm.amdgcn.prng.b32(i32)
 define i32 @prng_undef_i32() {
 ; CHECK-LABEL: @prng_undef_i32(
 ; CHECK-NEXT:    ret i32 undef
+;
   %prng = call i32 @llvm.amdgcn.prng.b32(i32 undef)
   ret i32 %prng
 }
@@ -6578,6 +6579,46 @@ define i32 @prng_undef_i32() {
 define i32 @prng_poison_i32() {
 ; CHECK-LABEL: @prng_poison_i32(
 ; CHECK-NEXT:    ret i32 poison
+;
   %prng = call i32 @llvm.amdgcn.prng.b32(i32 poison)
   ret i32 %prng
 }
+
+; --------------------------------------------------------------------
+; llvm.amdgcn.ds.bpermute
+; --------------------------------------------------------------------
+
+define amdgpu_kernel void @ds_bpermute_uniform_src(ptr addrspace(1) %out, i32 %lane) {
+; CHECK-LABEL: @ds_bpermute_uniform_src(
+; CHECK-NEXT:    store i32 7, ptr addrspace(1) [[OUT:%.*]], align 4
+; CHECK-NEXT:    ret void
+;
+  %v = call i32 @llvm.amdgcn.ds.bpermute(i32 %lane, i32 7)
+  store i32 %v, ptr addrspace(1) %out
+  ret void
+}
+
+define amdgpu_kernel void @ds_bpermute_constant_lane(ptr addrspace(1) %out, i32 %src) {
+; CHECK-LABEL: @ds_bpermute_constant_lane(
+; CHECK-NEXT:    [[V:%.*]] = call i32 @llvm.amdgcn.readlane.i32(i32 [[SRC:%.*]], i32 7)
+; CHECK-NEXT:    store i32 [[V]], ptr addrspace(1) [[OUT:%.*]], align 4
+; CHECK-NEXT:    ret void
+;
+  %v = call i32 @llvm.amdgcn.ds.bpermute(i32 28, i32 %src)
+  store i32 %v, ptr addrspace(1) %out
+  ret void
+}
+
+define amdgpu_kernel void @ds_bpermute_uniform_lane(ptr addrspace(1) %out, i32 %lanearg, i32 %src) {
+; CHECK-LABEL: @ds_bpermute_uniform_lane(
+; CHECK-NEXT:    [[LANE:%.*]] = call i32 @llvm.amdgcn.readfirstlane.i32(i32 [[LANEARG:%.*]])
+; CHECK-NEXT:    [[TMP1:%.*]] = lshr i32 [[LANE]], 2
+; CHECK-NEXT:    [[V:%.*]] = call i32 @llvm.amdgcn.readlane.i32(i32 [[SRC:%.*]], i32 [[TMP1]])
+; CHECK-NEXT:    store i32 [[V]], ptr addrspace(1) [[OUT:%.*]], align 4
+; CHECK-NEXT:    ret void
+;
+  %lane = call i32 @llvm.amdgcn.readfirstlane(i32 %lanearg)
+  %v = call i32 @llvm.amdgcn.ds.bpermute(i32 %lane, i32 %src)
+  store i32 %v, ptr addrspace(1) %out
+  ret void
+}

@@ -6496,7 +6496,7 @@ define float @test_constant_fold_exp2_f32_1_strictfp() strictfp {

define float @test_constant_fold_exp2_f32_neg1_strictfp() strictfp {
; CHECK-LABEL: @test_constant_fold_exp2_f32_neg1_strictfp(
; CHECK-NEXT: [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float -1.000000e+00) #[[ATTR16]]
; CHECK-NEXT: [[VAL:%.*]] = call float @llvm.amdgcn.exp2.f32(float -1.000000e+00) #[[ATTR19]]
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

All the test attribute renumbering is annoying. Does it go away with a regenerate of the base checks?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

All the test attribute renumbering is annoying.

You're telling me! We should switch to printing attributes inline.

Does it go away with a regenerate of the base checks?

Yes. Done.

@jayfoad jayfoad merged commit be5149a into llvm:main Mar 6, 2025
6 of 9 checks passed
@jayfoad jayfoad deleted the instcombine-ds-bpermute branch March 6, 2025 14:32
@llvm-ci
Copy link
Collaborator

llvm-ci commented Mar 6, 2025

LLVM Buildbot has detected a new failure on builder amdgpu-offload-ubuntu-22-cmake-build-only running on rocm-docker-ubu-22 while building llvm at step 4 "annotate".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/203/builds/3742

Here is the relevant piece of the build log for the reference
Step 4 (annotate) failure: '../llvm-zorg/zorg/buildbot/builders/annotated/amdgpu-offload-cmake.py --jobs=32' (failure)
...
[46/60] Building LLVM bitcode Parallelism.cpp-nvptx.bc
[47/60] Building LLVM bitcode Parallelism.cpp-amdgpu.bc
[48/60] Building LLVM bitcode Workshare.cpp-amdgpu.bc
[49/60] Building LLVM bitcode Workshare.cpp-nvptx.bc
[50/60] Linking LLVM bitcode libomptarget-amdgpu.bc
[51/60] Linking LLVM bitcode libomptarget-nvptx.bc
[52/60] Internalizing LLVM bitcode libomptarget-amdgpu.bc
[53/60] Internalizing LLVM bitcode libomptarget-nvptx.bc
/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/opt: WARNING: failed to create target machine for 'nvptx64-nvidia-cuda': unable to get target for 'nvptx64-nvidia-cuda', see --version and --triple.
[54/60] Optimizing LLVM bitcode libomptarget-amdgpu.bc
FAILED: offload/DeviceRTL/libomptarget-amdgpu.bc /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc 
cd /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL && /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
opt: /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/llvm-project/llvm/lib/IR/Intrinsics.cpp:157: std::string getIntrinsicNameImpl(llvm::Intrinsic::ID, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool): Assertion `(Tys.empty() || Intrinsic::isOverloaded(Id)) && "This version of getName is for overloaded intrinsics only"' failed.
PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace.
Stack dump:
0.	Program arguments: /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
1.	Running pass "require<globals-aa>,function(invalidate<aa>),require<profile-summary>,cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide)),function(invalidate<should-not-run-function-passes>),cgscc(devirt<4>())" on module "/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
2.	Running pass "cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide))" on module "/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
3.	Running pass "instcombine<max-iterations=1;no-verify-fixpoint>" on function "ompx_shfl_down_sync_f"
 #0 0x000076d2859e2910 llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/libLLVMSupport.so.21.0git+0x1e2910)
 #1 0x000076d2859dfd0f llvm::sys::RunSignalHandlers() (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/libLLVMSupport.so.21.0git+0x1dfd0f)
 #2 0x000076d2859dfe5a SignalHandler(int, siginfo_t*, void*) Signals.cpp:0:0
 #3 0x000076d285619520 (/lib/x86_64-linux-gnu/libc.so.6+0x42520)
 #4 0x000076d28566d9fc pthread_kill (/lib/x86_64-linux-gnu/libc.so.6+0x969fc)
 #5 0x000076d285619476 gsignal (/lib/x86_64-linux-gnu/libc.so.6+0x42476)
 #6 0x000076d2855ff7f3 abort (/lib/x86_64-linux-gnu/libc.so.6+0x287f3)
 #7 0x000076d2855ff71b (/lib/x86_64-linux-gnu/libc.so.6+0x2871b)
 #8 0x000076d285610e96 (/lib/x86_64-linux-gnu/libc.so.6+0x39e96)
 #9 0x000076d27f83e402 getIntrinsicNameImpl(unsigned int, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool) Intrinsics.cpp:0:0
#10 0x000076d27f83e6a1 llvm::Intrinsic::getOrInsertDeclaration(llvm::Module*, unsigned int, llvm::ArrayRef<llvm::Type*>) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMCore.so.21.0git+0x23e6a1)
#11 0x000076d2843a7aaa llvm::GCNTTIImpl::instCombineIntrinsic(llvm::InstCombiner&, llvm::IntrinsicInst&) const (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x1a7aaa)
#12 0x000076d2826d8c0b llvm::InstCombinerImpl::visitCallInst(llvm::CallInst&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMInstCombine.so.21.0git+0xb4c0b)
#13 0x000076d28267bc57 llvm::InstCombinerImpl::run() (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMInstCombine.so.21.0git+0x57c57)
#14 0x000076d28267d691 combineInstructionsOverFunction(llvm::Function&, llvm::InstructionWorklist&, llvm::AAResults*, llvm::AssumptionCache&, llvm::TargetLibraryInfo&, llvm::TargetTransformInfo&, llvm::DominatorTree&, llvm::OptimizationRemarkEmitter&, llvm::BlockFrequencyInfo*, llvm::BranchProbabilityInfo*, llvm::ProfileSummaryInfo*, llvm::InstCombineOptions const&) InstructionCombining.cpp:0:0
#15 0x000076d28267ead8 llvm::InstCombinePass::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMInstCombine.so.21.0git+0x5aad8)
#16 0x000076d282487aa6 llvm::detail::PassModel<llvm::Function, llvm::InstCombinePass, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMPasses.so.21.0git+0x87aa6)
#17 0x000076d27f8f998f llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMCore.so.21.0git+0x2f998f)
#18 0x000076d2845bbd26 llvm::detail::PassModel<llvm::Function, llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x3bbd26)
#19 0x000076d27fd62944 llvm::CGSCCToFunctionPassAdaptor::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAnalysis.so.21.0git+0x162944)
#20 0x000076d2845bc876 llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::CGSCCToFunctionPassAdaptor, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x3bc876)
#21 0x000076d27fd5b317 llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAnalysis.so.21.0git+0x15b317)
#22 0x000076d282486546 llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMPasses.so.21.0git+0x86546)
#23 0x000076d27fd63bfd llvm::DevirtSCCRepeatedPass::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAnalysis.so.21.0git+0x163bfd)
#24 0x000076d282486596 llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::DevirtSCCRepeatedPass, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMPasses.so.21.0git+0x86596)
#25 0x000076d27fd5e3ce llvm::ModuleToPostOrderCGSCCPassAdaptor::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAnalysis.so.21.0git+0x15e3ce)
#26 0x000076d2824864f6 llvm::detail::PassModel<llvm::Module, llvm::ModuleToPostOrderCGSCCPassAdaptor, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMPasses.so.21.0git+0x864f6)
#27 0x000076d27f8f88ed llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMCore.so.21.0git+0x2f88ed)
#28 0x000076d28201505a llvm::ModuleInlinerWrapperPass::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMipo.so.21.0git+0x21505a)
#29 0x000076d282485906 llvm::detail::PassModel<llvm::Module, llvm::ModuleInlinerWrapperPass, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMPasses.so.21.0git+0x85906)
Step 7 (build cmake config) failure: build cmake config (failure)
...
[46/60] Building LLVM bitcode Parallelism.cpp-nvptx.bc
[47/60] Building LLVM bitcode Parallelism.cpp-amdgpu.bc
[48/60] Building LLVM bitcode Workshare.cpp-amdgpu.bc
[49/60] Building LLVM bitcode Workshare.cpp-nvptx.bc
[50/60] Linking LLVM bitcode libomptarget-amdgpu.bc
[51/60] Linking LLVM bitcode libomptarget-nvptx.bc
[52/60] Internalizing LLVM bitcode libomptarget-amdgpu.bc
[53/60] Internalizing LLVM bitcode libomptarget-nvptx.bc
/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/opt: WARNING: failed to create target machine for 'nvptx64-nvidia-cuda': unable to get target for 'nvptx64-nvidia-cuda', see --version and --triple.
[54/60] Optimizing LLVM bitcode libomptarget-amdgpu.bc
FAILED: offload/DeviceRTL/libomptarget-amdgpu.bc /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc 
cd /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL && /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
opt: /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/llvm-project/llvm/lib/IR/Intrinsics.cpp:157: std::string getIntrinsicNameImpl(llvm::Intrinsic::ID, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool): Assertion `(Tys.empty() || Intrinsic::isOverloaded(Id)) && "This version of getName is for overloaded intrinsics only"' failed.
PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace.
Stack dump:
0.	Program arguments: /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
1.	Running pass "require<globals-aa>,function(invalidate<aa>),require<profile-summary>,cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide)),function(invalidate<should-not-run-function-passes>),cgscc(devirt<4>())" on module "/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
2.	Running pass "cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide))" on module "/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
3.	Running pass "instcombine<max-iterations=1;no-verify-fixpoint>" on function "ompx_shfl_down_sync_f"
 #0 0x000076d2859e2910 llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/libLLVMSupport.so.21.0git+0x1e2910)
 #1 0x000076d2859dfd0f llvm::sys::RunSignalHandlers() (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/libLLVMSupport.so.21.0git+0x1dfd0f)
 #2 0x000076d2859dfe5a SignalHandler(int, siginfo_t*, void*) Signals.cpp:0:0
 #3 0x000076d285619520 (/lib/x86_64-linux-gnu/libc.so.6+0x42520)
 #4 0x000076d28566d9fc pthread_kill (/lib/x86_64-linux-gnu/libc.so.6+0x969fc)
 #5 0x000076d285619476 gsignal (/lib/x86_64-linux-gnu/libc.so.6+0x42476)
 #6 0x000076d2855ff7f3 abort (/lib/x86_64-linux-gnu/libc.so.6+0x287f3)
 #7 0x000076d2855ff71b (/lib/x86_64-linux-gnu/libc.so.6+0x2871b)
 #8 0x000076d285610e96 (/lib/x86_64-linux-gnu/libc.so.6+0x39e96)
 #9 0x000076d27f83e402 getIntrinsicNameImpl(unsigned int, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool) Intrinsics.cpp:0:0
#10 0x000076d27f83e6a1 llvm::Intrinsic::getOrInsertDeclaration(llvm::Module*, unsigned int, llvm::ArrayRef<llvm::Type*>) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMCore.so.21.0git+0x23e6a1)
#11 0x000076d2843a7aaa llvm::GCNTTIImpl::instCombineIntrinsic(llvm::InstCombiner&, llvm::IntrinsicInst&) const (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x1a7aaa)
#12 0x000076d2826d8c0b llvm::InstCombinerImpl::visitCallInst(llvm::CallInst&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMInstCombine.so.21.0git+0xb4c0b)
#13 0x000076d28267bc57 llvm::InstCombinerImpl::run() (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMInstCombine.so.21.0git+0x57c57)
#14 0x000076d28267d691 combineInstructionsOverFunction(llvm::Function&, llvm::InstructionWorklist&, llvm::AAResults*, llvm::AssumptionCache&, llvm::TargetLibraryInfo&, llvm::TargetTransformInfo&, llvm::DominatorTree&, llvm::OptimizationRemarkEmitter&, llvm::BlockFrequencyInfo*, llvm::BranchProbabilityInfo*, llvm::ProfileSummaryInfo*, llvm::InstCombineOptions const&) InstructionCombining.cpp:0:0
#15 0x000076d28267ead8 llvm::InstCombinePass::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMInstCombine.so.21.0git+0x5aad8)
#16 0x000076d282487aa6 llvm::detail::PassModel<llvm::Function, llvm::InstCombinePass, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMPasses.so.21.0git+0x87aa6)
#17 0x000076d27f8f998f llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMCore.so.21.0git+0x2f998f)
#18 0x000076d2845bbd26 llvm::detail::PassModel<llvm::Function, llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x3bbd26)
#19 0x000076d27fd62944 llvm::CGSCCToFunctionPassAdaptor::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAnalysis.so.21.0git+0x162944)
#20 0x000076d2845bc876 llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::CGSCCToFunctionPassAdaptor, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x3bc876)
#21 0x000076d27fd5b317 llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAnalysis.so.21.0git+0x15b317)
#22 0x000076d282486546 llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMPasses.so.21.0git+0x86546)
#23 0x000076d27fd63bfd llvm::DevirtSCCRepeatedPass::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAnalysis.so.21.0git+0x163bfd)
#24 0x000076d282486596 llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::DevirtSCCRepeatedPass, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMPasses.so.21.0git+0x86596)
#25 0x000076d27fd5e3ce llvm::ModuleToPostOrderCGSCCPassAdaptor::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMAnalysis.so.21.0git+0x15e3ce)
#26 0x000076d2824864f6 llvm::detail::PassModel<llvm::Module, llvm::ModuleToPostOrderCGSCCPassAdaptor, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMPasses.so.21.0git+0x864f6)
#27 0x000076d27f8f88ed llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMCore.so.21.0git+0x2f88ed)
#28 0x000076d28201505a llvm::ModuleInlinerWrapperPass::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMipo.so.21.0git+0x21505a)
#29 0x000076d282485906 llvm::detail::PassModel<llvm::Module, llvm::ModuleInlinerWrapperPass, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-ubuntu-22-cmake-build-only/build/bin/../lib/../lib/libLLVMPasses.so.21.0git+0x85906)

@llvm-ci
Copy link
Collaborator

llvm-ci commented Mar 6, 2025

LLVM Buildbot has detected a new failure on builder amdgpu-offload-rhel-9-cmake-build-only running on rocm-docker-rhel-9 while building llvm at step 4 "annotate".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/205/builds/2533

Here is the relevant piece of the build log for the reference
Step 4 (annotate) failure: '../llvm-zorg/zorg/buildbot/builders/annotated/amdgpu-offload-cmake.py --jobs=32' (failure)
...
[46/60] Building LLVM bitcode Parallelism.cpp-nvptx.bc
[47/60] Building LLVM bitcode Parallelism.cpp-amdgpu.bc
[48/60] Building LLVM bitcode Workshare.cpp-amdgpu.bc
[49/60] Building LLVM bitcode Workshare.cpp-nvptx.bc
[50/60] Linking LLVM bitcode libomptarget-amdgpu.bc
[51/60] Linking LLVM bitcode libomptarget-nvptx.bc
[52/60] Internalizing LLVM bitcode libomptarget-amdgpu.bc
[53/60] Internalizing LLVM bitcode libomptarget-nvptx.bc
/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/opt: WARNING: failed to create target machine for 'nvptx64-nvidia-cuda': unable to get target for 'nvptx64-nvidia-cuda', see --version and --triple.
[54/60] Optimizing LLVM bitcode libomptarget-amdgpu.bc
FAILED: offload/DeviceRTL/libomptarget-amdgpu.bc /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc 
cd /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL && /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
opt: /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/llvm-project/llvm/lib/IR/Intrinsics.cpp:157: std::string getIntrinsicNameImpl(llvm::Intrinsic::ID, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool): Assertion `(Tys.empty() || Intrinsic::isOverloaded(Id)) && "This version of getName is for overloaded intrinsics only"' failed.
PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace.
Stack dump:
0.	Program arguments: /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
1.	Running pass "require<globals-aa>,function(invalidate<aa>),require<profile-summary>,cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide)),function(invalidate<should-not-run-function-passes>),cgscc(devirt<4>())" on module "/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
2.	Running pass "cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide))" on module "/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
3.	Running pass "instcombine<max-iterations=1;no-verify-fixpoint>" on function "ompx_shfl_down_sync_f"
 #0 0x000071de1a3d00b1 llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMSupport.so.21.0git+0x1d00b1)
 #1 0x000071de1a3cd6cb llvm::sys::RunSignalHandlers() (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMSupport.so.21.0git+0x1cd6cb)
 #2 0x000071de1a3cd7f2 SignalHandler(int, siginfo_t*, void*) Signals.cpp:0:0
 #3 0x000071de19e0d730 __restore_rt (/lib64/libc.so.6+0x3e730)
 #4 0x000071de19e5aa6c __pthread_kill_implementation (/lib64/libc.so.6+0x8ba6c)
 #5 0x000071de19e0d686 gsignal (/lib64/libc.so.6+0x3e686)
 #6 0x000071de19df7833 abort (/lib64/libc.so.6+0x28833)
 #7 0x000071de19df775b _nl_load_domain.cold (/lib64/libc.so.6+0x2875b)
 #8 0x000071de19e063c6 (/lib64/libc.so.6+0x373c6)
 #9 0x000071de1a82ddd0 getIntrinsicNameImpl(unsigned int, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool) Intrinsics.cpp:0:0
#10 0x000071de1a82df79 llvm::Intrinsic::getOrInsertDeclaration(llvm::Module*, unsigned int, llvm::ArrayRef<llvm::Type*>) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x22df79)
#11 0x000071de1f797b8d llvm::GCNTTIImpl::instCombineIntrinsic(llvm::InstCombiner&, llvm::IntrinsicInst&) const (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x197b8d)
#12 0x000071de1dadb0ca llvm::InstCombinerImpl::visitCallInst(llvm::CallInst&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMInstCombine.so.21.0git+0xad0ca)
#13 0x000071de1da8026c llvm::InstCombinerImpl::run() (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMInstCombine.so.21.0git+0x5226c)
#14 0x000071de1da81c8d combineInstructionsOverFunction(llvm::Function&, llvm::InstructionWorklist&, llvm::AAResults*, llvm::AssumptionCache&, llvm::TargetLibraryInfo&, llvm::TargetTransformInfo&, llvm::DominatorTree&, llvm::OptimizationRemarkEmitter&, llvm::BlockFrequencyInfo*, llvm::BranchProbabilityInfo*, llvm::ProfileSummaryInfo*, llvm::InstCombineOptions const&) InstructionCombining.cpp:0:0
#15 0x000071de1da82fce llvm::InstCombinePass::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMInstCombine.so.21.0git+0x54fce)
#16 0x000071de1d87ee6e llvm::detail::PassModel<llvm::Function, llvm::InstCombinePass, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x7ee6e)
#17 0x000071de1a8e375f llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x2e375f)
#18 0x000071de1f99e61e llvm::detail::PassModel<llvm::Function, llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x39e61e)
#19 0x000071de1ad57d87 llvm::CGSCCToFunctionPassAdaptor::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x157d87)
#20 0x000071de1f99eb4e llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::CGSCCToFunctionPassAdaptor, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x39eb4e)
#21 0x000071de1ad50923 llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x150923)
#22 0x000071de1d87e53e llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x7e53e)
#23 0x000071de1ad58ff3 llvm::DevirtSCCRepeatedPass::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x158ff3)
#24 0x000071de1d87e55e llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::DevirtSCCRepeatedPass, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x7e55e)
#25 0x000071de1ad537f4 llvm::ModuleToPostOrderCGSCCPassAdaptor::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x1537f4)
#26 0x000071de1d87e51e llvm::detail::PassModel<llvm::Module, llvm::ModuleToPostOrderCGSCCPassAdaptor, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x7e51e)
#27 0x000071de1a8e26cc llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x2e26cc)
#28 0x000071de1c801ad5 llvm::ModuleInlinerWrapperPass::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMipo.so.21.0git+0x201ad5)
#29 0x000071de1d87df8e llvm::detail::PassModel<llvm::Module, llvm::ModuleInlinerWrapperPass, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x7df8e)
Step 7 (build cmake config) failure: build cmake config (failure)
...
[46/60] Building LLVM bitcode Parallelism.cpp-nvptx.bc
[47/60] Building LLVM bitcode Parallelism.cpp-amdgpu.bc
[48/60] Building LLVM bitcode Workshare.cpp-amdgpu.bc
[49/60] Building LLVM bitcode Workshare.cpp-nvptx.bc
[50/60] Linking LLVM bitcode libomptarget-amdgpu.bc
[51/60] Linking LLVM bitcode libomptarget-nvptx.bc
[52/60] Internalizing LLVM bitcode libomptarget-amdgpu.bc
[53/60] Internalizing LLVM bitcode libomptarget-nvptx.bc
/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/opt: WARNING: failed to create target machine for 'nvptx64-nvidia-cuda': unable to get target for 'nvptx64-nvidia-cuda', see --version and --triple.
[54/60] Optimizing LLVM bitcode libomptarget-amdgpu.bc
FAILED: offload/DeviceRTL/libomptarget-amdgpu.bc /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc 
cd /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL && /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
opt: /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/llvm-project/llvm/lib/IR/Intrinsics.cpp:157: std::string getIntrinsicNameImpl(llvm::Intrinsic::ID, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool): Assertion `(Tys.empty() || Intrinsic::isOverloaded(Id)) && "This version of getName is for overloaded intrinsics only"' failed.
PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace.
Stack dump:
0.	Program arguments: /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
1.	Running pass "require<globals-aa>,function(invalidate<aa>),require<profile-summary>,cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide)),function(invalidate<should-not-run-function-passes>),cgscc(devirt<4>())" on module "/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
2.	Running pass "cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide))" on module "/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
3.	Running pass "instcombine<max-iterations=1;no-verify-fixpoint>" on function "ompx_shfl_down_sync_f"
 #0 0x000071de1a3d00b1 llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMSupport.so.21.0git+0x1d00b1)
 #1 0x000071de1a3cd6cb llvm::sys::RunSignalHandlers() (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMSupport.so.21.0git+0x1cd6cb)
 #2 0x000071de1a3cd7f2 SignalHandler(int, siginfo_t*, void*) Signals.cpp:0:0
 #3 0x000071de19e0d730 __restore_rt (/lib64/libc.so.6+0x3e730)
 #4 0x000071de19e5aa6c __pthread_kill_implementation (/lib64/libc.so.6+0x8ba6c)
 #5 0x000071de19e0d686 gsignal (/lib64/libc.so.6+0x3e686)
 #6 0x000071de19df7833 abort (/lib64/libc.so.6+0x28833)
 #7 0x000071de19df775b _nl_load_domain.cold (/lib64/libc.so.6+0x2875b)
 #8 0x000071de19e063c6 (/lib64/libc.so.6+0x373c6)
 #9 0x000071de1a82ddd0 getIntrinsicNameImpl(unsigned int, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool) Intrinsics.cpp:0:0
#10 0x000071de1a82df79 llvm::Intrinsic::getOrInsertDeclaration(llvm::Module*, unsigned int, llvm::ArrayRef<llvm::Type*>) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x22df79)
#11 0x000071de1f797b8d llvm::GCNTTIImpl::instCombineIntrinsic(llvm::InstCombiner&, llvm::IntrinsicInst&) const (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x197b8d)
#12 0x000071de1dadb0ca llvm::InstCombinerImpl::visitCallInst(llvm::CallInst&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMInstCombine.so.21.0git+0xad0ca)
#13 0x000071de1da8026c llvm::InstCombinerImpl::run() (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMInstCombine.so.21.0git+0x5226c)
#14 0x000071de1da81c8d combineInstructionsOverFunction(llvm::Function&, llvm::InstructionWorklist&, llvm::AAResults*, llvm::AssumptionCache&, llvm::TargetLibraryInfo&, llvm::TargetTransformInfo&, llvm::DominatorTree&, llvm::OptimizationRemarkEmitter&, llvm::BlockFrequencyInfo*, llvm::BranchProbabilityInfo*, llvm::ProfileSummaryInfo*, llvm::InstCombineOptions const&) InstructionCombining.cpp:0:0
#15 0x000071de1da82fce llvm::InstCombinePass::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMInstCombine.so.21.0git+0x54fce)
#16 0x000071de1d87ee6e llvm::detail::PassModel<llvm::Function, llvm::InstCombinePass, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x7ee6e)
#17 0x000071de1a8e375f llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x2e375f)
#18 0x000071de1f99e61e llvm::detail::PassModel<llvm::Function, llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x39e61e)
#19 0x000071de1ad57d87 llvm::CGSCCToFunctionPassAdaptor::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x157d87)
#20 0x000071de1f99eb4e llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::CGSCCToFunctionPassAdaptor, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x39eb4e)
#21 0x000071de1ad50923 llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x150923)
#22 0x000071de1d87e53e llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x7e53e)
#23 0x000071de1ad58ff3 llvm::DevirtSCCRepeatedPass::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x158ff3)
#24 0x000071de1d87e55e llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::DevirtSCCRepeatedPass, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x7e55e)
#25 0x000071de1ad537f4 llvm::ModuleToPostOrderCGSCCPassAdaptor::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x1537f4)
#26 0x000071de1d87e51e llvm::detail::PassModel<llvm::Module, llvm::ModuleToPostOrderCGSCCPassAdaptor, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x7e51e)
#27 0x000071de1a8e26cc llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x2e26cc)
#28 0x000071de1c801ad5 llvm::ModuleInlinerWrapperPass::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMipo.so.21.0git+0x201ad5)
#29 0x000071de1d87df8e llvm::detail::PassModel<llvm::Module, llvm::ModuleInlinerWrapperPass, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-9-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x7df8e)

@llvm-ci
Copy link
Collaborator

llvm-ci commented Mar 6, 2025

LLVM Buildbot has detected a new failure on builder amdgpu-offload-rhel-8-cmake-build-only running on rocm-docker-rhel-8 while building llvm at step 4 "annotate".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/204/builds/2554

Here is the relevant piece of the build log for the reference
Step 4 (annotate) failure: '../llvm-zorg/zorg/buildbot/builders/annotated/amdgpu-offload-cmake.py --jobs=32' (failure)
...
[46/60] Building LLVM bitcode Workshare.cpp-nvptx.bc
[47/60] Building LLVM bitcode Parallelism.cpp-amdgpu.bc
[48/60] Building LLVM bitcode Workshare.cpp-amdgpu.bc
[49/60] Building LLVM bitcode Parallelism.cpp-nvptx.bc
[50/60] Linking LLVM bitcode libomptarget-amdgpu.bc
[51/60] Linking LLVM bitcode libomptarget-nvptx.bc
[52/60] Internalizing LLVM bitcode libomptarget-amdgpu.bc
[53/60] Internalizing LLVM bitcode libomptarget-nvptx.bc
/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/opt: WARNING: failed to create target machine for 'nvptx64-nvidia-cuda': unable to get target for 'nvptx64-nvidia-cuda', see --version and --triple.
[54/60] Optimizing LLVM bitcode libomptarget-amdgpu.bc
FAILED: offload/DeviceRTL/libomptarget-amdgpu.bc /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc 
cd /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL && /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
opt: /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/llvm-project/llvm/lib/IR/Intrinsics.cpp:158: std::__cxx11::string getIntrinsicNameImpl(llvm::Intrinsic::ID, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool): Assertion `(Tys.empty() || Intrinsic::isOverloaded(Id)) && "This version of getName is for overloaded intrinsics only"' failed.
PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace.
Stack dump:
0.	Program arguments: /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
1.	Running pass "require<globals-aa>,function(invalidate<aa>),require<profile-summary>,cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide)),function(invalidate<should-not-run-function-passes>),cgscc(devirt<4>())" on module "/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
2.	Running pass "cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide))" on module "/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
3.	Running pass "instcombine<max-iterations=1;no-verify-fixpoint>" on function "ompx_shfl_down_sync_f"
 #0 0x00007107f43d4a68 llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMSupport.so.21.0git+0x1d4a68)
 #1 0x00007107f43d214c SignalHandler(int, siginfo_t*, void*) Signals.cpp:0:0
 #2 0x0000710801b5fd10 __restore_rt (/lib64/libpthread.so.0+0x12d10)
 #3 0x00007107f354952f raise (/lib64/libc.so.6+0x4e52f)
 #4 0x00007107f351ce65 abort (/lib64/libc.so.6+0x21e65)
 #5 0x00007107f351cd39 _nl_load_domain.cold.0 (/lib64/libc.so.6+0x21d39)
 #6 0x00007107f3541e86 (/lib64/libc.so.6+0x46e86)
 #7 0x00007107f521430e getIntrinsicNameImpl(unsigned int, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool) Intrinsics.cpp:0:0
 #8 0x00007107f52144c2 llvm::Intrinsic::getOrInsertDeclaration(llvm::Module*, unsigned int, llvm::ArrayRef<llvm::Type*>) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x2144c2)
 #9 0x00007107ffda33d2 llvm::GCNTTIImpl::instCombineIntrinsic(llvm::InstCombiner&, llvm::IntrinsicInst&) const (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x1a33d2)
#10 0x00007107f80a1745 llvm::InstCombinerImpl::visitCallInst(llvm::CallInst&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMInstCombine.so.21.0git+0xa1745)
#11 0x00007107f804e7f1 llvm::InstCombinerImpl::run() (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMInstCombine.so.21.0git+0x4e7f1)
#12 0x00007107f8050080 combineInstructionsOverFunction(llvm::Function&, llvm::InstructionWorklist&, llvm::AAResults*, llvm::AssumptionCache&, llvm::TargetLibraryInfo&, llvm::TargetTransformInfo&, llvm::DominatorTree&, llvm::OptimizationRemarkEmitter&, llvm::BlockFrequencyInfo*, llvm::BranchProbabilityInfo*, llvm::ProfileSummaryInfo*, llvm::InstCombineOptions const&) (.isra.2065) InstructionCombining.cpp:0:0
#13 0x00007107f8050b24 llvm::InstCombinePass::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMInstCombine.so.21.0git+0x50b24)
#14 0x00007107fc083bdd llvm::detail::PassModel<llvm::Function, llvm::InstCombinePass, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x83bdd)
#15 0x00007107f52c8a7c llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x2c8a7c)
#16 0x00007107fff986cd llvm::detail::PassModel<llvm::Function, llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x3986cd)
#17 0x00007107f6562a6f llvm::CGSCCToFunctionPassAdaptor::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x162a6f)
#18 0x00007107fff98b3d llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::CGSCCToFunctionPassAdaptor, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x398b3d)
#19 0x00007107f655aa9a llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x15aa9a)
#20 0x00007107fc0832ad llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x832ad)
#21 0x00007107f655f8f7 llvm::DevirtSCCRepeatedPass::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x15f8f7)
#22 0x00007107fc0832cd llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::DevirtSCCRepeatedPass, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x832cd)
#23 0x00007107f655d863 llvm::ModuleToPostOrderCGSCCPassAdaptor::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x15d863)
#24 0x00007107fc08328d llvm::detail::PassModel<llvm::Module, llvm::ModuleToPostOrderCGSCCPassAdaptor, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x8328d)
#25 0x00007107f52c72a4 llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x2c72a4)
#26 0x00007107fa3f51e3 llvm::ModuleInlinerWrapperPass::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMipo.so.21.0git+0x1f51e3)
#27 0x00007107fc082cfd llvm::detail::PassModel<llvm::Module, llvm::ModuleInlinerWrapperPass, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x82cfd)
#28 0x00007107f52c72a4 llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x2c72a4)
#29 0x0000710801820e8f llvm::runPassPipeline(llvm::StringRef, llvm::Module&, llvm::TargetMachine*, llvm::TargetLibraryInfoImpl*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::StringRef, llvm::ArrayRef<llvm::PassPlugin>, llvm::ArrayRef<std::function<void (llvm::PassBuilder&)>>, llvm::opt_tool::OutputKind, llvm::opt_tool::VerifierKind, bool, bool, bool, bool, bool, bool, bool) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMOptDriver.so.21.0git+0x20e8f)
Step 7 (build cmake config) failure: build cmake config (failure)
...
[46/60] Building LLVM bitcode Workshare.cpp-nvptx.bc
[47/60] Building LLVM bitcode Parallelism.cpp-amdgpu.bc
[48/60] Building LLVM bitcode Workshare.cpp-amdgpu.bc
[49/60] Building LLVM bitcode Parallelism.cpp-nvptx.bc
[50/60] Linking LLVM bitcode libomptarget-amdgpu.bc
[51/60] Linking LLVM bitcode libomptarget-nvptx.bc
[52/60] Internalizing LLVM bitcode libomptarget-amdgpu.bc
[53/60] Internalizing LLVM bitcode libomptarget-nvptx.bc
/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/opt: WARNING: failed to create target machine for 'nvptx64-nvidia-cuda': unable to get target for 'nvptx64-nvidia-cuda', see --version and --triple.
[54/60] Optimizing LLVM bitcode libomptarget-amdgpu.bc
FAILED: offload/DeviceRTL/libomptarget-amdgpu.bc /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc 
cd /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL && /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
opt: /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/llvm-project/llvm/lib/IR/Intrinsics.cpp:158: std::__cxx11::string getIntrinsicNameImpl(llvm::Intrinsic::ID, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool): Assertion `(Tys.empty() || Intrinsic::isOverloaded(Id)) && "This version of getName is for overloaded intrinsics only"' failed.
PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace.
Stack dump:
0.	Program arguments: /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
1.	Running pass "require<globals-aa>,function(invalidate<aa>),require<profile-summary>,cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide)),function(invalidate<should-not-run-function-passes>),cgscc(devirt<4>())" on module "/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
2.	Running pass "cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide))" on module "/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
3.	Running pass "instcombine<max-iterations=1;no-verify-fixpoint>" on function "ompx_shfl_down_sync_f"
 #0 0x00007107f43d4a68 llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMSupport.so.21.0git+0x1d4a68)
 #1 0x00007107f43d214c SignalHandler(int, siginfo_t*, void*) Signals.cpp:0:0
 #2 0x0000710801b5fd10 __restore_rt (/lib64/libpthread.so.0+0x12d10)
 #3 0x00007107f354952f raise (/lib64/libc.so.6+0x4e52f)
 #4 0x00007107f351ce65 abort (/lib64/libc.so.6+0x21e65)
 #5 0x00007107f351cd39 _nl_load_domain.cold.0 (/lib64/libc.so.6+0x21d39)
 #6 0x00007107f3541e86 (/lib64/libc.so.6+0x46e86)
 #7 0x00007107f521430e getIntrinsicNameImpl(unsigned int, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool) Intrinsics.cpp:0:0
 #8 0x00007107f52144c2 llvm::Intrinsic::getOrInsertDeclaration(llvm::Module*, unsigned int, llvm::ArrayRef<llvm::Type*>) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x2144c2)
 #9 0x00007107ffda33d2 llvm::GCNTTIImpl::instCombineIntrinsic(llvm::InstCombiner&, llvm::IntrinsicInst&) const (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x1a33d2)
#10 0x00007107f80a1745 llvm::InstCombinerImpl::visitCallInst(llvm::CallInst&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMInstCombine.so.21.0git+0xa1745)
#11 0x00007107f804e7f1 llvm::InstCombinerImpl::run() (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMInstCombine.so.21.0git+0x4e7f1)
#12 0x00007107f8050080 combineInstructionsOverFunction(llvm::Function&, llvm::InstructionWorklist&, llvm::AAResults*, llvm::AssumptionCache&, llvm::TargetLibraryInfo&, llvm::TargetTransformInfo&, llvm::DominatorTree&, llvm::OptimizationRemarkEmitter&, llvm::BlockFrequencyInfo*, llvm::BranchProbabilityInfo*, llvm::ProfileSummaryInfo*, llvm::InstCombineOptions const&) (.isra.2065) InstructionCombining.cpp:0:0
#13 0x00007107f8050b24 llvm::InstCombinePass::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMInstCombine.so.21.0git+0x50b24)
#14 0x00007107fc083bdd llvm::detail::PassModel<llvm::Function, llvm::InstCombinePass, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x83bdd)
#15 0x00007107f52c8a7c llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x2c8a7c)
#16 0x00007107fff986cd llvm::detail::PassModel<llvm::Function, llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x3986cd)
#17 0x00007107f6562a6f llvm::CGSCCToFunctionPassAdaptor::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x162a6f)
#18 0x00007107fff98b3d llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::CGSCCToFunctionPassAdaptor, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAMDGPUCodeGen.so.21.0git+0x398b3d)
#19 0x00007107f655aa9a llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x15aa9a)
#20 0x00007107fc0832ad llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x832ad)
#21 0x00007107f655f8f7 llvm::DevirtSCCRepeatedPass::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x15f8f7)
#22 0x00007107fc0832cd llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::DevirtSCCRepeatedPass, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x832cd)
#23 0x00007107f655d863 llvm::ModuleToPostOrderCGSCCPassAdaptor::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMAnalysis.so.21.0git+0x15d863)
#24 0x00007107fc08328d llvm::detail::PassModel<llvm::Module, llvm::ModuleToPostOrderCGSCCPassAdaptor, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x8328d)
#25 0x00007107f52c72a4 llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x2c72a4)
#26 0x00007107fa3f51e3 llvm::ModuleInlinerWrapperPass::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMipo.so.21.0git+0x1f51e3)
#27 0x00007107fc082cfd llvm::detail::PassModel<llvm::Module, llvm::ModuleInlinerWrapperPass, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMPasses.so.21.0git+0x82cfd)
#28 0x00007107f52c72a4 llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMCore.so.21.0git+0x2c72a4)
#29 0x0000710801820e8f llvm::runPassPipeline(llvm::StringRef, llvm::Module&, llvm::TargetMachine*, llvm::TargetLibraryInfoImpl*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::StringRef, llvm::ArrayRef<llvm::PassPlugin>, llvm::ArrayRef<std::function<void (llvm::PassBuilder&)>>, llvm::opt_tool::OutputKind, llvm::opt_tool::VerifierKind, bool, bool, bool, bool, bool, bool, bool) (/home/botworker/bbot/amdgpu-offload-rhel-8-cmake-build-only/build/bin/../lib/libLLVMOptDriver.so.21.0git+0x20e8f)

@llvm-ci
Copy link
Collaborator

llvm-ci commented Mar 6, 2025

LLVM Buildbot has detected a new failure on builder openmp-offload-amdgpu-runtime running on omp-vega20-0 while building llvm at step 5 "compile-openmp".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/30/builds/17032

Here is the relevant piece of the build log for the reference
Step 5 (compile-openmp) failure: build (failure)
...
24.414 [40/34/1293] Generating exported symbols for clang_rt.tsan-x86_64
24.884 [39/34/1294] Building CXX object openmp/runtime/src/CMakeFiles/omp.dir/kmp_affinity.cpp.o
24.952 [38/34/1295] Building CXX object compiler-rt/lib/tsan/rtl/CMakeFiles/clang_rt.tsan-dynamic-x86_64.dir/tsan_interceptors_posix.cpp.o
25.019 [37/34/1296] Building CXX object compiler-rt/lib/memprof/CMakeFiles/RTMemprof_dynamic.x86_64.dir/memprof_interceptors.cpp.o
25.094 [36/34/1297] Linking C shared library openmp/runtime/src/libomp.so
25.117 [35/34/1298] Linking CXX shared library /home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/lib/clang/21/lib/x86_64-unknown-linux-gnu/libclang_rt.tsan.so
25.252 [34/34/1299] Linking CXX shared library openmp/libompd/src/libompd.so
25.976 [33/34/1300] Building CXX object compiler-rt/lib/memprof/CMakeFiles/RTMemprof.x86_64.dir/memprof_interceptors.cpp.o
26.070 [32/34/1301] Linking CXX static library /home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/lib/clang/21/lib/x86_64-unknown-linux-gnu/libclang_rt.memprof.a
26.087 [31/34/1302] Optimizing LLVM bitcode libomptarget-amdgpu.bc
FAILED: offload/DeviceRTL/libomptarget-amdgpu.bc /home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc 
cd /home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/runtimes/runtimes-bins/offload/DeviceRTL && /home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
opt: /home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.src/llvm/lib/IR/Intrinsics.cpp:157: std::string getIntrinsicNameImpl(llvm::Intrinsic::ID, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool): Assertion `(Tys.empty() || Intrinsic::isOverloaded(Id)) && "This version of getName is for overloaded intrinsics only"' failed.
PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace.
Stack dump:
0.	Program arguments: /home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt -O3 -openmp-opt-disable -attributor-enable=module -vectorize-slp=false /home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc -o /home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/runtimes/runtimes-bins/offload/DeviceRTL/libomptarget-amdgpu.bc
1.	Running pass "require<globals-aa>,function(invalidate<aa>),require<profile-summary>,cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide)),function(invalidate<should-not-run-function-passes>),cgscc(devirt<4>())" on module "/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
2.	Running pass "cgscc(devirt<4>(inline,function-attrs<skip-non-recursive-function-attrs>,argpromotion,openmp-opt-cgscc,function(amdgpu-promote-kernel-arguments,infer-address-spaces,amdgpu-lower-kernel-attributes,amdgpu-promote-alloca-to-vector),function<eager-inv;no-rerun>(sroa<modify-cfg>,early-cse<memssa>,speculative-execution<only-if-divergent-target>,jump-threading,correlated-propagation,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,aggressive-instcombine,libcalls-shrinkwrap,amdgpu-usenative,amdgpu-simplifylib,tailcallelim,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,reassociate,constraint-elimination,loop-mssa(loop-instsimplify,loop-simplifycfg,licm<no-allowspeculation>,loop-rotate<header-duplication;no-prepare-for-lto>,licm<allowspeculation>,simple-loop-unswitch<nontrivial;trivial>),simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;no-hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;no-sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,loop(loop-idiom,indvars,extra-simple-loop-unswitch-passes,loop-deletion,loop-unroll-full),sroa<modify-cfg>,vector-combine,mldst-motion<no-split-footer-bb>,gvn<>,sccp,bdce,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib,jump-threading,correlated-propagation,adce,memcpyopt,dse,move-auto-init,loop-mssa(licm<allowspeculation>),coro-elide,simplifycfg<bonus-inst-threshold=1;no-forward-switch-cond;switch-range-to-icmp;no-switch-to-lookup;keep-loops;hoist-common-insts;no-hoist-loads-stores-with-cond-faulting;sink-common-insts;speculate-blocks;simplify-cond-branch;no-speculate-unpredictables>,instcombine<max-iterations=1;no-verify-fixpoint>,amdgpu-usenative,amdgpu-simplifylib),function-attrs,function(require<should-not-run-function-passes>),coro-split,coro-annotation-elide))" on module "/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/runtimes/runtimes-bins/offload/DeviceRTL/internalized_libomptarget-amdgpu.bc"
3.	Running pass "instcombine<max-iterations=1;no-verify-fixpoint>" on function "ompx_shfl_down_sync_f"
 #0 0x0000560a6fb4bf3f llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x3b66f3f)
 #1 0x0000560a6fb49464 SignalHandler(int, siginfo_t*, void*) Signals.cpp:0:0
 #2 0x00007f67404db420 __restore_rt (/lib/x86_64-linux-gnu/libpthread.so.0+0x14420)
 #3 0x00007f673ffae00b raise (/lib/x86_64-linux-gnu/libc.so.6+0x4300b)
 #4 0x00007f673ff8d859 abort (/lib/x86_64-linux-gnu/libc.so.6+0x22859)
 #5 0x00007f673ff8d729 (/lib/x86_64-linux-gnu/libc.so.6+0x22729)
 #6 0x00007f673ff9efd6 (/lib/x86_64-linux-gnu/libc.so.6+0x33fd6)
 #7 0x0000560a6f886a92 getIntrinsicNameImpl(unsigned int, llvm::ArrayRef<llvm::Type*>, llvm::Module*, llvm::FunctionType*, bool) Intrinsics.cpp:0:0
 #8 0x0000560a6f886d29 llvm::Intrinsic::getOrInsertDeclaration(llvm::Module*, unsigned int, llvm::ArrayRef<llvm::Type*>) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x38a1d29)
 #9 0x0000560a6cdec8c0 llvm::GCNTTIImpl::instCombineIntrinsic(llvm::InstCombiner&, llvm::IntrinsicInst&) const (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0xe078c0)
#10 0x0000560a6e909878 llvm::InstCombinerImpl::visitCallInst(llvm::CallInst&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x2924878)
#11 0x0000560a6e8aeee0 llvm::InstCombinerImpl::run() (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x28c9ee0)
#12 0x0000560a6e8b08b6 combineInstructionsOverFunction(llvm::Function&, llvm::InstructionWorklist&, llvm::AAResults*, llvm::AssumptionCache&, llvm::TargetLibraryInfo&, llvm::TargetTransformInfo&, llvm::DominatorTree&, llvm::OptimizationRemarkEmitter&, llvm::BlockFrequencyInfo*, llvm::BranchProbabilityInfo*, llvm::ProfileSummaryInfo*, llvm::InstCombineOptions const&) (.isra.0) InstructionCombining.cpp:0:0
#13 0x0000560a6e8b1dd1 llvm::InstCombinePass::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x28ccdd1)
#14 0x0000560a6d78c0e6 llvm::detail::PassModel<llvm::Function, llvm::InstCombinePass, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x17a70e6)
#15 0x0000560a6f93f049 llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x395a049)
#16 0x0000560a6c77b1d6 llvm::detail::PassModel<llvm::Function, llvm::PassManager<llvm::Function, llvm::AnalysisManager<llvm::Function>>, llvm::AnalysisManager<llvm::Function>>::run(llvm::Function&, llvm::AnalysisManager<llvm::Function>&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x7961d6)
#17 0x0000560a6ef50fca llvm::CGSCCToFunctionPassAdaptor::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x2f6bfca)
#18 0x0000560a6cb3c006 llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::CGSCCToFunctionPassAdaptor, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0xb57006)
#19 0x0000560a6ef4902a llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x2f6402a)
#20 0x0000560a6d78b876 llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::PassManager<llvm::LazyCallGraph::SCC, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x17a6876)
#21 0x0000560a6ef4dbad llvm::DevirtSCCRepeatedPass::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x2f68bad)
#22 0x0000560a6d78b8c6 llvm::detail::PassModel<llvm::LazyCallGraph::SCC, llvm::DevirtSCCRepeatedPass, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&>::run(llvm::LazyCallGraph::SCC&, llvm::AnalysisManager<llvm::LazyCallGraph::SCC, llvm::LazyCallGraph&>&, llvm::LazyCallGraph&, llvm::CGSCCUpdateResult&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x17a68c6)
#23 0x0000560a6ef4c018 llvm::ModuleToPostOrderCGSCCPassAdaptor::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x2f67018)
#24 0x0000560a6d78b826 llvm::detail::PassModel<llvm::Module, llvm::ModuleToPostOrderCGSCCPassAdaptor, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x17a6826)
#25 0x0000560a6f93d2d1 llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x39582d1)
#26 0x0000560a6e124a38 llvm::ModuleInlinerWrapperPass::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x213fa38)
#27 0x0000560a6d78aee6 llvm::detail::PassModel<llvm::Module, llvm::ModuleInlinerWrapperPass, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x17a5ee6)
#28 0x0000560a6f93d2d1 llvm::PassManager<llvm::Module, llvm::AnalysisManager<llvm::Module>>::run(llvm::Module&, llvm::AnalysisManager<llvm::Module>&) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x39582d1)
#29 0x0000560a6c68f2e9 llvm::runPassPipeline(llvm::StringRef, llvm::Module&, llvm::TargetMachine*, llvm::TargetLibraryInfoImpl*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::ToolOutputFile*, llvm::StringRef, llvm::ArrayRef<llvm::PassPlugin>, llvm::ArrayRef<std::function<void (llvm::PassBuilder&)>>, llvm::opt_tool::OutputKind, llvm::opt_tool::VerifierKind, bool, bool, bool, bool, bool, bool, bool) (/home/ompworker/bbot/openmp-offload-amdgpu-runtime/llvm.build/bin/opt+0x6aa2e9)

jayfoad added a commit that referenced this pull request Mar 6, 2025
…uments (#129895)"

This reverts commit be5149a.

It caused build failures in the openmp-offload-amdgpu-runtime buildbot
and others.
jayfoad added a commit to jayfoad/llvm-project that referenced this pull request Mar 6, 2025
Reland llvm#129895 with a fix to avoid trying to combine bpermute of
bitcast.
jph-13 pushed a commit to jph-13/llvm-project that referenced this pull request Mar 21, 2025
jph-13 pushed a commit to jph-13/llvm-project that referenced this pull request Mar 21, 2025
…uments (llvm#129895)"

This reverts commit be5149a.

It caused build failures in the openmp-offload-amdgpu-runtime buildbot
and others.
jayfoad added a commit that referenced this pull request Apr 10, 2025
…130133)

Reland #129895 with a fix to avoid trying to combine bpermute of
bitcast.
var-const pushed a commit to ldionne/llvm-project that referenced this pull request Apr 17, 2025
…lvm#130133)

Reland llvm#129895 with a fix to avoid trying to combine bpermute of
bitcast.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants