[llvm] [llvm][OpenMPOpt] Remove no-op ptr-to-ptr bitcast (NFC) (PR #73869)
Youngsuk Kim via llvm-commits
llvm-commits at lists.llvm.org
Wed Nov 29 15:28:20 PST 2023
https://github.com/JOE1994 created https://github.com/llvm/llvm-project/pull/73869
* Remove a call to CreatePointerBitCastOrAddrSpaceCast which merely adds a no-op ptr-to-ptr bitcast.
* Most of the diff is from removing checks for no-op ptr-to-ptr bitcasts in relevant LIT tests
>From 705ec0551b6af5f2c399490479d9d3677a560677 Mon Sep 17 00:00:00 2001
From: Youngsuk Kim <youngsuk.kim at hpe.com>
Date: Wed, 29 Nov 2023 17:17:27 -0600
Subject: [PATCH] [llvm][OpenMPOpt] Remove no-op ptr-to-ptr bitcast (NFC)
* Remove a call to CreatePointerBitCastOrAddrSpaceCast which merely adds a
no-op ptr-to-ptr bitcast.
* Most of the diff is from removing checks for no-op ptr-to-ptr bitcasts in
relevant LIT tests
---
llvm/lib/Transforms/IPO/OpenMPOpt.cpp | 7 +-
.../OpenMP/custom_state_machines.ll | 48 +++----
..._state_machine_function_ptr_replacement.ll | 4 +-
llvm/test/Transforms/OpenMP/spmdization.ll | 120 ++++++------------
.../Transforms/OpenMP/spmdization_guarding.ll | 1 -
.../Transforms/OpenMP/spmdization_indirect.ll | 12 +-
...zation_no_guarding_two_reaching_kernels.ll | 7 +-
7 files changed, 68 insertions(+), 131 deletions(-)
diff --git a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
index 5b42f215fb40ca0..b2665161c090dfb 100644
--- a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
+++ b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
@@ -4527,9 +4527,6 @@ struct AAKernelInfoFunction : AAKernelInfo {
FunctionType *ParallelRegionFnTy = FunctionType::get(
Type::getVoidTy(Ctx), {Type::getInt16Ty(Ctx), Type::getInt32Ty(Ctx)},
false);
- Value *WorkFnCast = BitCastInst::CreatePointerBitCastOrAddrSpaceCast(
- WorkFn, ParallelRegionFnTy->getPointerTo(), "worker.work_fn.addr_cast",
- StateMachineBeginBB);
Instruction *IsDone =
ICmpInst::Create(ICmpInst::ICmp, llvm::CmpInst::ICMP_EQ, WorkFn,
@@ -4576,7 +4573,7 @@ struct AAKernelInfoFunction : AAKernelInfo {
Value *IsPR;
if (I + 1 < E || !ReachedUnknownParallelRegions.empty()) {
Instruction *CmpI = ICmpInst::Create(
- ICmpInst::ICmp, llvm::CmpInst::ICMP_EQ, WorkFnCast, ParallelRegion,
+ ICmpInst::ICmp, llvm::CmpInst::ICMP_EQ, WorkFn, ParallelRegion,
"worker.check_parallel_region", StateMachineIfCascadeCurrentBB);
CmpI->setDebugLoc(DLoc);
IsPR = CmpI;
@@ -4596,7 +4593,7 @@ struct AAKernelInfoFunction : AAKernelInfo {
if (!ReachedUnknownParallelRegions.empty()) {
StateMachineIfCascadeCurrentBB->setName(
"worker_state_machine.parallel_region.fallback.execute");
- CallInst::Create(ParallelRegionFnTy, WorkFnCast, {ZeroArg, GTid}, "",
+ CallInst::Create(ParallelRegionFnTy, WorkFn, {ZeroArg, GTid}, "",
StateMachineIfCascadeCurrentBB)
->setDebugLoc(DLoc);
}
diff --git a/llvm/test/Transforms/OpenMP/custom_state_machines.ll b/llvm/test/Transforms/OpenMP/custom_state_machines.ll
index 1a6624b46f10dc7..b0d1842ca2e8ba4 100644
--- a/llvm/test/Transforms/OpenMP/custom_state_machines.ll
+++ b/llvm/test/Transforms/OpenMP/custom_state_machines.ll
@@ -998,7 +998,6 @@ attributes #9 = { convergent nounwind readonly willreturn }
; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU: worker_state_machine.finished:
@@ -1006,7 +1005,7 @@ attributes #9 = { convergent nounwind readonly willreturn }
; AMDGPU: worker_state_machine.is_active.check:
; AMDGPU-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU: worker_state_machine.parallel_region.check:
-; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__2_wrapper.ID
+; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__2_wrapper.ID
; AMDGPU-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK1:%.*]]
; AMDGPU: worker_state_machine.parallel_region.execute:
; AMDGPU-NEXT: call void @__omp_outlined__2_wrapper(i16 0, i32 [[TMP0]])
@@ -1117,7 +1116,6 @@ attributes #9 = { convergent nounwind readonly willreturn }
; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU: worker_state_machine.finished:
@@ -1125,13 +1123,13 @@ attributes #9 = { convergent nounwind readonly willreturn }
; AMDGPU: worker_state_machine.is_active.check:
; AMDGPU-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU: worker_state_machine.parallel_region.check:
-; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__17_wrapper
+; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__17_wrapper
; AMDGPU-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK1:%.*]]
; AMDGPU: worker_state_machine.parallel_region.execute:
; AMDGPU-NEXT: call void @__omp_outlined__17_wrapper(i16 0, i32 [[TMP0]])
; AMDGPU-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU: worker_state_machine.parallel_region.check1:
-; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION4:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__5_wrapper.ID
+; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION4:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__5_wrapper.ID
; AMDGPU-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION4]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE2:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK3:%.*]]
; AMDGPU: worker_state_machine.parallel_region.execute2:
; AMDGPU-NEXT: call void @__omp_outlined__5_wrapper(i16 0, i32 [[TMP0]])
@@ -1259,7 +1257,6 @@ attributes #9 = { convergent nounwind readonly willreturn }
; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU: worker_state_machine.finished:
@@ -1267,19 +1264,19 @@ attributes #9 = { convergent nounwind readonly willreturn }
; AMDGPU: worker_state_machine.is_active.check:
; AMDGPU-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU: worker_state_machine.parallel_region.check:
-; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__7_wrapper.ID
+; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__7_wrapper.ID
; AMDGPU-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK1:%.*]]
; AMDGPU: worker_state_machine.parallel_region.execute:
; AMDGPU-NEXT: call void @__omp_outlined__7_wrapper(i16 0, i32 [[TMP0]])
; AMDGPU-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU: worker_state_machine.parallel_region.check1:
-; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION4:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__8_wrapper.ID
+; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION4:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__8_wrapper.ID
; AMDGPU-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION4]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE2:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; AMDGPU: worker_state_machine.parallel_region.execute2:
; AMDGPU-NEXT: call void @__omp_outlined__8_wrapper(i16 0, i32 [[TMP0]])
; AMDGPU-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; AMDGPU: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; AMDGPU: worker_state_machine.parallel_region.end:
; AMDGPU-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -1379,7 +1376,6 @@ attributes #9 = { convergent nounwind readonly willreturn }
; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU: worker_state_machine.finished:
@@ -1387,7 +1383,7 @@ attributes #9 = { convergent nounwind readonly willreturn }
; AMDGPU: worker_state_machine.is_active.check:
; AMDGPU-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU: worker_state_machine.parallel_region.check:
-; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__10_wrapper.ID
+; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__10_wrapper.ID
; AMDGPU-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK1:%.*]]
; AMDGPU: worker_state_machine.parallel_region.execute:
; AMDGPU-NEXT: call void @__omp_outlined__10_wrapper(i16 0, i32 [[TMP0]])
@@ -1497,7 +1493,6 @@ attributes #9 = { convergent nounwind readonly willreturn }
; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU: worker_state_machine.finished:
@@ -1505,7 +1500,7 @@ attributes #9 = { convergent nounwind readonly willreturn }
; AMDGPU: worker_state_machine.is_active.check:
; AMDGPU-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU: worker_state_machine.parallel_region.check:
-; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__13_wrapper.ID
+; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__13_wrapper.ID
; AMDGPU-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK1:%.*]]
; AMDGPU: worker_state_machine.parallel_region.execute:
; AMDGPU-NEXT: call void @__omp_outlined__13_wrapper(i16 0, i32 [[TMP0]])
@@ -1686,7 +1681,6 @@ attributes #9 = { convergent nounwind readonly willreturn }
; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU: worker_state_machine.finished:
@@ -1694,7 +1688,7 @@ attributes #9 = { convergent nounwind readonly willreturn }
; AMDGPU: worker_state_machine.is_active.check:
; AMDGPU-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU: worker_state_machine.parallel_region.end:
; AMDGPU-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -1908,7 +1902,6 @@ attributes #9 = { convergent nounwind readonly willreturn }
; NVPTX-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX: worker_state_machine.finished:
@@ -1916,7 +1909,7 @@ attributes #9 = { convergent nounwind readonly willreturn }
; NVPTX: worker_state_machine.is_active.check:
; NVPTX-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX: worker_state_machine.parallel_region.check:
-; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__2_wrapper.ID
+; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__2_wrapper.ID
; NVPTX-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK1:%.*]]
; NVPTX: worker_state_machine.parallel_region.execute:
; NVPTX-NEXT: call void @__omp_outlined__2_wrapper(i16 0, i32 [[TMP0]])
@@ -2026,7 +2019,6 @@ attributes #9 = { convergent nounwind readonly willreturn }
; NVPTX-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX: worker_state_machine.finished:
@@ -2034,13 +2026,13 @@ attributes #9 = { convergent nounwind readonly willreturn }
; NVPTX: worker_state_machine.is_active.check:
; NVPTX-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX: worker_state_machine.parallel_region.check:
-; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__17_wrapper
+; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__17_wrapper
; NVPTX-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK1:%.*]]
; NVPTX: worker_state_machine.parallel_region.execute:
; NVPTX-NEXT: call void @__omp_outlined__17_wrapper(i16 0, i32 [[TMP0]])
; NVPTX-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX: worker_state_machine.parallel_region.check1:
-; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION4:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__5_wrapper.ID
+; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION4:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__5_wrapper.ID
; NVPTX-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION4]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE2:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK3:%.*]]
; NVPTX: worker_state_machine.parallel_region.execute2:
; NVPTX-NEXT: call void @__omp_outlined__5_wrapper(i16 0, i32 [[TMP0]])
@@ -2167,7 +2159,6 @@ attributes #9 = { convergent nounwind readonly willreturn }
; NVPTX-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX: worker_state_machine.finished:
@@ -2175,19 +2166,19 @@ attributes #9 = { convergent nounwind readonly willreturn }
; NVPTX: worker_state_machine.is_active.check:
; NVPTX-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX: worker_state_machine.parallel_region.check:
-; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__7_wrapper.ID
+; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__7_wrapper.ID
; NVPTX-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK1:%.*]]
; NVPTX: worker_state_machine.parallel_region.execute:
; NVPTX-NEXT: call void @__omp_outlined__7_wrapper(i16 0, i32 [[TMP0]])
; NVPTX-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX: worker_state_machine.parallel_region.check1:
-; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION4:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__8_wrapper.ID
+; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION4:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__8_wrapper.ID
; NVPTX-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION4]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE2:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; NVPTX: worker_state_machine.parallel_region.execute2:
; NVPTX-NEXT: call void @__omp_outlined__8_wrapper(i16 0, i32 [[TMP0]])
; NVPTX-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; NVPTX: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; NVPTX: worker_state_machine.parallel_region.end:
; NVPTX-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -2286,7 +2277,6 @@ attributes #9 = { convergent nounwind readonly willreturn }
; NVPTX-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX: worker_state_machine.finished:
@@ -2294,7 +2284,7 @@ attributes #9 = { convergent nounwind readonly willreturn }
; NVPTX: worker_state_machine.is_active.check:
; NVPTX-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX: worker_state_machine.parallel_region.check:
-; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__10_wrapper.ID
+; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__10_wrapper.ID
; NVPTX-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK1:%.*]]
; NVPTX: worker_state_machine.parallel_region.execute:
; NVPTX-NEXT: call void @__omp_outlined__10_wrapper(i16 0, i32 [[TMP0]])
@@ -2403,7 +2393,6 @@ attributes #9 = { convergent nounwind readonly willreturn }
; NVPTX-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX: worker_state_machine.finished:
@@ -2411,7 +2400,7 @@ attributes #9 = { convergent nounwind readonly willreturn }
; NVPTX: worker_state_machine.is_active.check:
; NVPTX-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX: worker_state_machine.parallel_region.check:
-; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__13_wrapper.ID
+; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__13_wrapper.ID
; NVPTX-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK1:%.*]]
; NVPTX: worker_state_machine.parallel_region.execute:
; NVPTX-NEXT: call void @__omp_outlined__13_wrapper(i16 0, i32 [[TMP0]])
@@ -2591,7 +2580,6 @@ attributes #9 = { convergent nounwind readonly willreturn }
; NVPTX-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX: worker_state_machine.finished:
@@ -2599,7 +2587,7 @@ attributes #9 = { convergent nounwind readonly willreturn }
; NVPTX: worker_state_machine.is_active.check:
; NVPTX-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX: worker_state_machine.parallel_region.end:
; NVPTX-NEXT: call void @__kmpc_kernel_end_parallel()
diff --git a/llvm/test/Transforms/OpenMP/gpu_state_machine_function_ptr_replacement.ll b/llvm/test/Transforms/OpenMP/gpu_state_machine_function_ptr_replacement.ll
index 34c7113eda1685a..936f7d1c46781ad 100644
--- a/llvm/test/Transforms/OpenMP/gpu_state_machine_function_ptr_replacement.ll
+++ b/llvm/test/Transforms/OpenMP/gpu_state_machine_function_ptr_replacement.ll
@@ -26,8 +26,8 @@
; CHECK-DAG: @__omp_outlined__1_wrapper.ID = private constant i8 undef
; CHECK-DAG: @__omp_outlined__2_wrapper.ID = private constant i8 undef
-; CHECK-DAG: icmp eq ptr %worker.work_fn.addr_cast, @__omp_outlined__1_wrapper.ID
-; CHECK-DAG: icmp eq ptr %worker.work_fn.addr_cast, @__omp_outlined__2_wrapper.ID
+; CHECK-DAG: icmp eq ptr %worker.work_fn, @__omp_outlined__1_wrapper.ID
+; CHECK-DAG: icmp eq ptr %worker.work_fn, @__omp_outlined__2_wrapper.ID
; CHECK-DAG: call void @__kmpc_parallel_51(ptr @1, i32 %{{.*}}, i32 1, i32 -1, i32 -1, ptr @__omp_outlined__1, ptr @__omp_outlined__1_wrapper.ID, ptr %{{.*}}, i64 0)
diff --git a/llvm/test/Transforms/OpenMP/spmdization.ll b/llvm/test/Transforms/OpenMP/spmdization.ll
index 635dcdc3c52b106..ef95aed24ded446 100644
--- a/llvm/test/Transforms/OpenMP/spmdization.ll
+++ b/llvm/test/Transforms/OpenMP/spmdization.ll
@@ -324,7 +324,6 @@ define internal void @__omp_offloading_fd02_2044372e_sequential_loop_l5__debug()
; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED1-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED1-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED1-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED1: worker_state_machine.finished:
@@ -376,7 +375,6 @@ define internal void @__omp_offloading_fd02_2044372e_sequential_loop_l5__debug()
; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED2-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED2-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED2-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED2: worker_state_machine.finished:
@@ -427,7 +425,6 @@ define internal void @__omp_offloading_fd02_2044372e_sequential_loop_l5__debug()
; NVPTX-DISABLED1-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED1-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED1-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED1-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED1-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED1: worker_state_machine.finished:
@@ -478,7 +475,6 @@ define internal void @__omp_offloading_fd02_2044372e_sequential_loop_l5__debug()
; NVPTX-DISABLED2-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED2-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED2-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED2-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED2-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED2: worker_state_machine.finished:
@@ -530,7 +526,6 @@ define internal void @__omp_offloading_fd02_2044372e_sequential_loop_l5__debug()
; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED: worker_state_machine.finished:
@@ -538,13 +533,13 @@ define internal void @__omp_offloading_fd02_2044372e_sequential_loop_l5__debug()
; AMDGPU-DISABLED: worker_state_machine.is_active.check:
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.check:
-; AMDGPU-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__1_wrapper.ID
+; AMDGPU-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__1_wrapper.ID
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.execute:
; AMDGPU-DISABLED-NEXT: call void @__omp_outlined__1_wrapper(i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-DISABLED-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-DISABLED-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.end:
; AMDGPU-DISABLED-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -582,7 +577,6 @@ define internal void @__omp_offloading_fd02_2044372e_sequential_loop_l5__debug()
; NVPTX-DISABLED-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED: worker_state_machine.finished:
@@ -590,13 +584,13 @@ define internal void @__omp_offloading_fd02_2044372e_sequential_loop_l5__debug()
; NVPTX-DISABLED: worker_state_machine.is_active.check:
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.check:
-; NVPTX-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__1_wrapper.ID
+; NVPTX-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__1_wrapper.ID
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.execute:
; NVPTX-DISABLED-NEXT: call void @__omp_outlined__1_wrapper(i16 0, i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-DISABLED-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-DISABLED-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.end:
; NVPTX-DISABLED-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -998,7 +992,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_stack_var_l2
; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED1-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED1-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED1-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED1: worker_state_machine.finished:
@@ -1050,7 +1043,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_stack_var_l2
; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED2-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED2-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED2-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED2: worker_state_machine.finished:
@@ -1101,7 +1093,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_stack_var_l2
; NVPTX-DISABLED1-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED1-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED1-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED1-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED1-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED1: worker_state_machine.finished:
@@ -1152,7 +1143,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_stack_var_l2
; NVPTX-DISABLED2-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED2-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED2-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED2-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED2-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED2: worker_state_machine.finished:
@@ -1204,7 +1194,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_stack_var_l2
; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED: worker_state_machine.finished:
@@ -1212,13 +1201,13 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_stack_var_l2
; AMDGPU-DISABLED: worker_state_machine.is_active.check:
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.check:
-; AMDGPU-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__3_wrapper.ID
+; AMDGPU-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__3_wrapper.ID
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.execute:
; AMDGPU-DISABLED-NEXT: call void @__omp_outlined__3_wrapper(i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-DISABLED-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-DISABLED-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.end:
; AMDGPU-DISABLED-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -1256,7 +1245,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_stack_var_l2
; NVPTX-DISABLED-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED: worker_state_machine.finished:
@@ -1264,13 +1252,13 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_stack_var_l2
; NVPTX-DISABLED: worker_state_machine.is_active.check:
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.check:
-; NVPTX-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__3_wrapper.ID
+; NVPTX-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__3_wrapper.ID
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.execute:
; NVPTX-DISABLED-NEXT: call void @__omp_outlined__3_wrapper(i16 0, i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-DISABLED-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-DISABLED-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.end:
; NVPTX-DISABLED-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -1695,7 +1683,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_l
; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED1-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED1-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED1-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED1: worker_state_machine.finished:
@@ -1747,7 +1734,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_l
; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED2-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED2-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED2-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED2: worker_state_machine.finished:
@@ -1798,7 +1784,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_l
; NVPTX-DISABLED1-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED1-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED1-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED1-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED1-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED1: worker_state_machine.finished:
@@ -1849,7 +1834,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_l
; NVPTX-DISABLED2-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED2-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED2-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED2-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED2-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED2: worker_state_machine.finished:
@@ -1901,7 +1885,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_l
; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED: worker_state_machine.finished:
@@ -1909,13 +1892,13 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_l
; AMDGPU-DISABLED: worker_state_machine.is_active.check:
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.check:
-; AMDGPU-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__5_wrapper.ID
+; AMDGPU-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__5_wrapper.ID
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.execute:
; AMDGPU-DISABLED-NEXT: call void @__omp_outlined__5_wrapper(i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-DISABLED-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-DISABLED-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.end:
; AMDGPU-DISABLED-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -1953,7 +1936,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_l
; NVPTX-DISABLED-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED: worker_state_machine.finished:
@@ -1961,13 +1943,13 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_l
; NVPTX-DISABLED: worker_state_machine.is_active.check:
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.check:
-; NVPTX-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__5_wrapper.ID
+; NVPTX-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__5_wrapper.ID
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.execute:
; NVPTX-DISABLED-NEXT: call void @__omp_outlined__5_wrapper(i16 0, i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-DISABLED-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-DISABLED-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.end:
; NVPTX-DISABLED-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -2425,7 +2407,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_g
; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED1-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED1-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED1-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED1: worker_state_machine.finished:
@@ -2477,7 +2458,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_g
; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED2-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED2-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED2-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED2: worker_state_machine.finished:
@@ -2528,7 +2508,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_g
; NVPTX-DISABLED1-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED1-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED1-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED1-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED1-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED1: worker_state_machine.finished:
@@ -2579,7 +2558,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_g
; NVPTX-DISABLED2-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED2-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED2-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED2-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED2-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED2: worker_state_machine.finished:
@@ -2631,7 +2609,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_g
; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED: worker_state_machine.finished:
@@ -2639,13 +2616,13 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_g
; AMDGPU-DISABLED: worker_state_machine.is_active.check:
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.check:
-; AMDGPU-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__7_wrapper.ID
+; AMDGPU-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__7_wrapper.ID
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.execute:
; AMDGPU-DISABLED-NEXT: call void @__omp_outlined__7_wrapper(i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-DISABLED-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-DISABLED-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.end:
; AMDGPU-DISABLED-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -2683,7 +2660,6 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_g
; NVPTX-DISABLED-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED: worker_state_machine.finished:
@@ -2691,13 +2667,13 @@ define weak void @__omp_offloading_fd02_2044372e_sequential_loop_to_shared_var_g
; NVPTX-DISABLED: worker_state_machine.is_active.check:
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.check:
-; NVPTX-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__7_wrapper.ID
+; NVPTX-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__7_wrapper.ID
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.execute:
; NVPTX-DISABLED-NEXT: call void @__omp_outlined__7_wrapper(i16 0, i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-DISABLED-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-DISABLED-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.end:
; NVPTX-DISABLED-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3156,7 +3132,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU: worker_state_machine.finished:
@@ -3164,7 +3139,7 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; AMDGPU: worker_state_machine.is_active.check:
; AMDGPU-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU: worker_state_machine.parallel_region.end:
; AMDGPU-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3202,7 +3177,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; NVPTX-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX: worker_state_machine.finished:
@@ -3210,7 +3184,7 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; NVPTX: worker_state_machine.is_active.check:
; NVPTX-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX: worker_state_machine.parallel_region.end:
; NVPTX-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3249,7 +3223,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED1-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED1-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED1-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED1: worker_state_machine.finished:
@@ -3257,7 +3230,7 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; AMDGPU-DISABLED1: worker_state_machine.is_active.check:
; AMDGPU-DISABLED1-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU-DISABLED1: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-DISABLED1-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-DISABLED1-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED1-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU-DISABLED1: worker_state_machine.parallel_region.end:
; AMDGPU-DISABLED1-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3296,7 +3269,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED2-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED2-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED2-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED2: worker_state_machine.finished:
@@ -3304,7 +3276,7 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; AMDGPU-DISABLED2: worker_state_machine.is_active.check:
; AMDGPU-DISABLED2-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU-DISABLED2: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-DISABLED2-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-DISABLED2-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED2-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU-DISABLED2: worker_state_machine.parallel_region.end:
; AMDGPU-DISABLED2-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3342,7 +3314,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; NVPTX-DISABLED1-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED1-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED1-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED1-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED1-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED1: worker_state_machine.finished:
@@ -3350,7 +3321,7 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; NVPTX-DISABLED1: worker_state_machine.is_active.check:
; NVPTX-DISABLED1-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX-DISABLED1: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-DISABLED1-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-DISABLED1-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-DISABLED1-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX-DISABLED1: worker_state_machine.parallel_region.end:
; NVPTX-DISABLED1-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3388,7 +3359,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; NVPTX-DISABLED2-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED2-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED2-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED2-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED2-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED2: worker_state_machine.finished:
@@ -3396,7 +3366,7 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; NVPTX-DISABLED2: worker_state_machine.is_active.check:
; NVPTX-DISABLED2-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX-DISABLED2: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-DISABLED2-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-DISABLED2-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-DISABLED2-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX-DISABLED2: worker_state_machine.parallel_region.end:
; NVPTX-DISABLED2-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3435,7 +3405,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED: worker_state_machine.finished:
@@ -3443,7 +3412,7 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; AMDGPU-DISABLED: worker_state_machine.is_active.check:
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-DISABLED-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-DISABLED-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.end:
; AMDGPU-DISABLED-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3480,7 +3449,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; NVPTX-DISABLED-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED: worker_state_machine.finished:
@@ -3488,7 +3456,7 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_target_l65() #0
; NVPTX-DISABLED: worker_state_machine.is_active.check:
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-DISABLED-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-DISABLED-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.end:
; NVPTX-DISABLED-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3599,7 +3567,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU: worker_state_machine.finished:
@@ -3607,13 +3574,13 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; AMDGPU: worker_state_machine.is_active.check:
; AMDGPU-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU: worker_state_machine.parallel_region.check:
-; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__9_wrapper.ID
+; AMDGPU-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__9_wrapper.ID
; AMDGPU-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; AMDGPU: worker_state_machine.parallel_region.execute:
; AMDGPU-NEXT: call void @__omp_outlined__9_wrapper(i16 0, i32 [[TMP0]])
; AMDGPU-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; AMDGPU: worker_state_machine.parallel_region.end:
; AMDGPU-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3652,7 +3619,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; NVPTX-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX: worker_state_machine.finished:
@@ -3660,13 +3626,13 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; NVPTX: worker_state_machine.is_active.check:
; NVPTX-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX: worker_state_machine.parallel_region.check:
-; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__9_wrapper.ID
+; NVPTX-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__9_wrapper.ID
; NVPTX-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; NVPTX: worker_state_machine.parallel_region.execute:
; NVPTX-NEXT: call void @__omp_outlined__9_wrapper(i16 0, i32 [[TMP0]])
; NVPTX-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; NVPTX: worker_state_machine.parallel_region.end:
; NVPTX-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3706,7 +3672,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED1-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED1-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED1-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED1: worker_state_machine.finished:
@@ -3714,13 +3679,13 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; AMDGPU-DISABLED1: worker_state_machine.is_active.check:
; AMDGPU-DISABLED1-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU-DISABLED1: worker_state_machine.parallel_region.check:
-; AMDGPU-DISABLED1-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__9_wrapper.ID
+; AMDGPU-DISABLED1-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__9_wrapper.ID
; AMDGPU-DISABLED1-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; AMDGPU-DISABLED1: worker_state_machine.parallel_region.execute:
; AMDGPU-DISABLED1-NEXT: call void @__omp_outlined__9_wrapper(i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED1-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU-DISABLED1: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-DISABLED1-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-DISABLED1-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED1-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; AMDGPU-DISABLED1: worker_state_machine.parallel_region.end:
; AMDGPU-DISABLED1-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3760,7 +3725,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED2-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED2-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED2-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED2: worker_state_machine.finished:
@@ -3768,13 +3732,13 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; AMDGPU-DISABLED2: worker_state_machine.is_active.check:
; AMDGPU-DISABLED2-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU-DISABLED2: worker_state_machine.parallel_region.check:
-; AMDGPU-DISABLED2-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__9_wrapper.ID
+; AMDGPU-DISABLED2-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__9_wrapper.ID
; AMDGPU-DISABLED2-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; AMDGPU-DISABLED2: worker_state_machine.parallel_region.execute:
; AMDGPU-DISABLED2-NEXT: call void @__omp_outlined__9_wrapper(i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED2-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU-DISABLED2: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-DISABLED2-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-DISABLED2-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED2-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; AMDGPU-DISABLED2: worker_state_machine.parallel_region.end:
; AMDGPU-DISABLED2-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3813,7 +3777,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; NVPTX-DISABLED1-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED1-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED1-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED1-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED1-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED1-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED1: worker_state_machine.finished:
@@ -3821,13 +3784,13 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; NVPTX-DISABLED1: worker_state_machine.is_active.check:
; NVPTX-DISABLED1-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX-DISABLED1: worker_state_machine.parallel_region.check:
-; NVPTX-DISABLED1-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__9_wrapper.ID
+; NVPTX-DISABLED1-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__9_wrapper.ID
; NVPTX-DISABLED1-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; NVPTX-DISABLED1: worker_state_machine.parallel_region.execute:
; NVPTX-DISABLED1-NEXT: call void @__omp_outlined__9_wrapper(i16 0, i32 [[TMP0]])
; NVPTX-DISABLED1-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX-DISABLED1: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-DISABLED1-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-DISABLED1-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-DISABLED1-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; NVPTX-DISABLED1: worker_state_machine.parallel_region.end:
; NVPTX-DISABLED1-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3866,7 +3829,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; NVPTX-DISABLED2-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED2-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED2-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED2-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED2-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED2-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED2: worker_state_machine.finished:
@@ -3874,13 +3836,13 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; NVPTX-DISABLED2: worker_state_machine.is_active.check:
; NVPTX-DISABLED2-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX-DISABLED2: worker_state_machine.parallel_region.check:
-; NVPTX-DISABLED2-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__9_wrapper.ID
+; NVPTX-DISABLED2-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__9_wrapper.ID
; NVPTX-DISABLED2-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; NVPTX-DISABLED2: worker_state_machine.parallel_region.execute:
; NVPTX-DISABLED2-NEXT: call void @__omp_outlined__9_wrapper(i16 0, i32 [[TMP0]])
; NVPTX-DISABLED2-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX-DISABLED2: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-DISABLED2-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-DISABLED2-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-DISABLED2-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; NVPTX-DISABLED2: worker_state_machine.parallel_region.end:
; NVPTX-DISABLED2-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3920,7 +3882,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU-DISABLED: worker_state_machine.finished:
@@ -3928,13 +3889,13 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; AMDGPU-DISABLED: worker_state_machine.is_active.check:
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.check:
-; AMDGPU-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__9_wrapper.ID
+; AMDGPU-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__9_wrapper.ID
; AMDGPU-DISABLED-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.execute:
; AMDGPU-DISABLED-NEXT: call void @__omp_outlined__9_wrapper(i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-DISABLED-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-DISABLED-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; AMDGPU-DISABLED: worker_state_machine.parallel_region.end:
; AMDGPU-DISABLED-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -3972,7 +3933,6 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; NVPTX-DISABLED-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX-DISABLED: worker_state_machine.finished:
@@ -3980,13 +3940,13 @@ define weak void @__omp_offloading_fd02_2044372e_do_not_spmdize_task_l74() #0 {
; NVPTX-DISABLED: worker_state_machine.is_active.check:
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_CHECK:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.check:
-; NVPTX-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN_ADDR_CAST]], @__omp_outlined__9_wrapper.ID
+; NVPTX-DISABLED-NEXT: [[WORKER_CHECK_PARALLEL_REGION:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], @__omp_outlined__9_wrapper.ID
; NVPTX-DISABLED-NEXT: br i1 [[WORKER_CHECK_PARALLEL_REGION]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.execute:
; NVPTX-DISABLED-NEXT: call void @__omp_outlined__9_wrapper(i16 0, i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-DISABLED-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-DISABLED-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-DISABLED-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END]]
; NVPTX-DISABLED: worker_state_machine.parallel_region.end:
; NVPTX-DISABLED-NEXT: call void @__kmpc_kernel_end_parallel()
diff --git a/llvm/test/Transforms/OpenMP/spmdization_guarding.ll b/llvm/test/Transforms/OpenMP/spmdization_guarding.ll
index c2ca3dc045ac2d9..45e86e4ce2efb04 100644
--- a/llvm/test/Transforms/OpenMP/spmdization_guarding.ll
+++ b/llvm/test/Transforms/OpenMP/spmdization_guarding.ll
@@ -203,7 +203,6 @@ define weak void @__omp_offloading_2a_fbfa7a_sequential_loop_l6(ptr %dyn, ptr %x
; CHECK-DISABLED-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; CHECK-DISABLED-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; CHECK-DISABLED-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; CHECK-DISABLED-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; CHECK-DISABLED-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; CHECK-DISABLED-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; CHECK-DISABLED: worker_state_machine.finished:
diff --git a/llvm/test/Transforms/OpenMP/spmdization_indirect.ll b/llvm/test/Transforms/OpenMP/spmdization_indirect.ll
index d5e864eea0e78db..33885af2f992869 100644
--- a/llvm/test/Transforms/OpenMP/spmdization_indirect.ll
+++ b/llvm/test/Transforms/OpenMP/spmdization_indirect.ll
@@ -390,7 +390,6 @@ define weak void @spmd_and_non_spmd_callee(i1 %c) #0 {
; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU: worker_state_machine.finished:
@@ -398,7 +397,7 @@ define weak void @spmd_and_non_spmd_callee(i1 %c) #0 {
; AMDGPU: worker_state_machine.is_active.check:
; AMDGPU-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU: worker_state_machine.parallel_region.end:
; AMDGPU-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -451,7 +450,6 @@ define weak void @spmd_and_non_spmd_callee(i1 %c) #0 {
; NVPTX-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX: worker_state_machine.finished:
@@ -459,7 +457,7 @@ define weak void @spmd_and_non_spmd_callee(i1 %c) #0 {
; NVPTX: worker_state_machine.is_active.check:
; NVPTX-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX: worker_state_machine.parallel_region.end:
; NVPTX-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -736,7 +734,6 @@ define weak void @spmd_and_non_spmd_callees_metadata(ptr %fp) #0 {
; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_GENERIC:%.*]] = addrspacecast ptr addrspace(5) [[WORKER_WORK_FN_ADDR]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR_GENERIC]])
; AMDGPU-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR_GENERIC]], align 8
-; AMDGPU-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; AMDGPU-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; AMDGPU-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; AMDGPU: worker_state_machine.finished:
@@ -744,7 +741,7 @@ define weak void @spmd_and_non_spmd_callees_metadata(ptr %fp) #0 {
; AMDGPU: worker_state_machine.is_active.check:
; AMDGPU-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; AMDGPU: worker_state_machine.parallel_region.fallback.execute:
-; AMDGPU-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; AMDGPU-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; AMDGPU-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; AMDGPU: worker_state_machine.parallel_region.end:
; AMDGPU-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -796,7 +793,6 @@ define weak void @spmd_and_non_spmd_callees_metadata(ptr %fp) #0 {
; NVPTX-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; NVPTX-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; NVPTX-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; NVPTX-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; NVPTX-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; NVPTX-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; NVPTX: worker_state_machine.finished:
@@ -804,7 +800,7 @@ define weak void @spmd_and_non_spmd_callees_metadata(ptr %fp) #0 {
; NVPTX: worker_state_machine.is_active.check:
; NVPTX-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; NVPTX: worker_state_machine.parallel_region.fallback.execute:
-; NVPTX-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; NVPTX-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; NVPTX-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; NVPTX: worker_state_machine.parallel_region.end:
; NVPTX-NEXT: call void @__kmpc_kernel_end_parallel()
diff --git a/llvm/test/Transforms/OpenMP/spmdization_no_guarding_two_reaching_kernels.ll b/llvm/test/Transforms/OpenMP/spmdization_no_guarding_two_reaching_kernels.ll
index fdfc1cb08442c7b..aad9446a0e289bb 100644
--- a/llvm/test/Transforms/OpenMP/spmdization_no_guarding_two_reaching_kernels.ll
+++ b/llvm/test/Transforms/OpenMP/spmdization_no_guarding_two_reaching_kernels.ll
@@ -88,7 +88,6 @@ define weak void @__omp_offloading_2b_10393b5_spmd_l12(ptr %dyn) #0 {
; CHECK-DISABLE-SPMDIZATION-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; CHECK-DISABLE-SPMDIZATION-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; CHECK-DISABLE-SPMDIZATION-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; CHECK-DISABLE-SPMDIZATION-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; CHECK-DISABLE-SPMDIZATION-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; CHECK-DISABLE-SPMDIZATION-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; CHECK-DISABLE-SPMDIZATION: worker_state_machine.finished:
@@ -166,7 +165,6 @@ define weak void @__omp_offloading_2b_10393b5_generic_l20(ptr %dyn) #0 {
; CHECK-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; CHECK-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; CHECK-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; CHECK-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; CHECK-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; CHECK-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; CHECK: worker_state_machine.finished:
@@ -174,7 +172,7 @@ define weak void @__omp_offloading_2b_10393b5_generic_l20(ptr %dyn) #0 {
; CHECK: worker_state_machine.is_active.check:
; CHECK-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; CHECK: worker_state_machine.parallel_region.fallback.execute:
-; CHECK-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; CHECK-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; CHECK-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; CHECK: worker_state_machine.parallel_region.end:
; CHECK-NEXT: call void @__kmpc_kernel_end_parallel()
@@ -209,7 +207,6 @@ define weak void @__omp_offloading_2b_10393b5_generic_l20(ptr %dyn) #0 {
; CHECK-DISABLE-SPMDIZATION-NEXT: call void @__kmpc_barrier_simple_generic(ptr @[[GLOB1]], i32 [[TMP0]])
; CHECK-DISABLE-SPMDIZATION-NEXT: [[WORKER_IS_ACTIVE:%.*]] = call i1 @__kmpc_kernel_parallel(ptr [[WORKER_WORK_FN_ADDR]])
; CHECK-DISABLE-SPMDIZATION-NEXT: [[WORKER_WORK_FN:%.*]] = load ptr, ptr [[WORKER_WORK_FN_ADDR]], align 8
-; CHECK-DISABLE-SPMDIZATION-NEXT: [[WORKER_WORK_FN_ADDR_CAST:%.*]] = bitcast ptr [[WORKER_WORK_FN]] to ptr
; CHECK-DISABLE-SPMDIZATION-NEXT: [[WORKER_IS_DONE:%.*]] = icmp eq ptr [[WORKER_WORK_FN]], null
; CHECK-DISABLE-SPMDIZATION-NEXT: br i1 [[WORKER_IS_DONE]], label [[WORKER_STATE_MACHINE_FINISHED]], label [[WORKER_STATE_MACHINE_IS_ACTIVE_CHECK:%.*]]
; CHECK-DISABLE-SPMDIZATION: worker_state_machine.finished:
@@ -217,7 +214,7 @@ define weak void @__omp_offloading_2b_10393b5_generic_l20(ptr %dyn) #0 {
; CHECK-DISABLE-SPMDIZATION: worker_state_machine.is_active.check:
; CHECK-DISABLE-SPMDIZATION-NEXT: br i1 [[WORKER_IS_ACTIVE]], label [[WORKER_STATE_MACHINE_PARALLEL_REGION_FALLBACK_EXECUTE:%.*]], label [[WORKER_STATE_MACHINE_DONE_BARRIER:%.*]]
; CHECK-DISABLE-SPMDIZATION: worker_state_machine.parallel_region.fallback.execute:
-; CHECK-DISABLE-SPMDIZATION-NEXT: call void [[WORKER_WORK_FN_ADDR_CAST]](i16 0, i32 [[TMP0]])
+; CHECK-DISABLE-SPMDIZATION-NEXT: call void [[WORKER_WORK_FN]](i16 0, i32 [[TMP0]])
; CHECK-DISABLE-SPMDIZATION-NEXT: br label [[WORKER_STATE_MACHINE_PARALLEL_REGION_END:%.*]]
; CHECK-DISABLE-SPMDIZATION: worker_state_machine.parallel_region.end:
; CHECK-DISABLE-SPMDIZATION-NEXT: call void @__kmpc_kernel_end_parallel()
More information about the llvm-commits
mailing list