This is an archive of the discontinued LLVM Phabricator instance.

Differential D43785

[AMDGPU] Fix lowering OpenCL enqueue_kernel
ClosedPublic

Authored by yaxunl on Feb 26 2018, 2:03 PM.

Details

Reviewers
b-sumner
rampitec
arsenm
Commits
rG46439e8d4a44: [AMDGPU] Fix lowering OpenCL enqueue_kernel
rL326806: [AMDGPU] Fix lowering OpenCL enqueue_kernel
Summary

One addrspacecast disappeared in clang emitted IR for
block invoke function due to adoption of the new
addr space mapping.

Diff Detail

Repository
rL LLVM

Event Timeline

yaxunl created this revision.Feb 26 2018, 2:03 PM
Herald added subscribers: t-tye, Anastasia, tpr and 4 others. · View Herald TranscriptFeb 26 2018, 2:03 PM
nhaehnle removed a subscriber: nhaehnle.Feb 27 2018, 7:59 AM
yaxunl added a comment.Mar 5 2018, 10:07 AM

ping

rampitec accepted this revision.Mar 5 2018, 10:11 AM

LGTM

This revision is now accepted and ready to land.Mar 5 2018, 10:11 AM
Closed by commit rL326806: [AMDGPU] Fix lowering OpenCL enqueue_kernel (authored by yaxunl). · Explain WhyMar 6 2018, 8:06 AM
This revision was automatically updated to reflect the committed changes.

Revision Contents

PathSize
llvm/
trunk/
lib/
Target/
AMDGPU/
52 lines
test/
CodeGen/
AMDGPU/
93 lines

Diff 137198

llvm/trunk/lib/Target/AMDGPU/AMDGPUOpenCLEnqueuedBlockLowering.cpp

Show First 20 Lines • Show All 88 Lines • ▼ Show 20 Lines
} }
bool AMDGPUOpenCLEnqueuedBlockLowering::runOnModule(Module &M) { bool AMDGPUOpenCLEnqueuedBlockLowering::runOnModule(Module &M) {
DenseSet<Function *> Callers; DenseSet<Function *> Callers;
auto &C = M.getContext(); auto &C = M.getContext();
bool Changed = false; bool Changed = false;
for (auto &F : M.functions()) { for (auto &F : M.functions()) {
if (F.hasFnAttribute("enqueued-block")) { if (F.hasFnAttribute("enqueued-block")) {
if (!F.hasOneUse() || !F.user_begin()->hasOneUse() || for (auto U : F.users()) {
!isa<ConstantExpr>(*F.user_begin()) || if (!isa<ConstantExpr>(&*U))
!isa<ConstantExpr>(*F.user_begin()->user_begin())) {
continue; continue;
} auto *BitCast = cast<ConstantExpr>(&*U);
auto *BitCast = cast<ConstantExpr>(*F.user_begin());
auto *AddrCast = cast<ConstantExpr>(*BitCast->user_begin());
auto RuntimeHandle = (F.getName() + "_runtime_handle").str(); auto RuntimeHandle = (F.getName() + "_runtime_handle").str();
auto *GV = new GlobalVariable( auto *GV = new GlobalVariable(
M, Type::getInt8Ty(C)->getPointerTo(AMDGPUAS::GLOBAL_ADDRESS), M, Type::getInt8Ty(C)->getPointerTo(AMDGPUAS::GLOBAL_ADDRESS),
/*IsConstant=*/true, GlobalValue::ExternalLinkage, /*IsConstant=*/true, GlobalValue::ExternalLinkage,
/*Initializer=*/nullptr, RuntimeHandle, /*InsertBefore=*/nullptr, /*Initializer=*/nullptr, RuntimeHandle, /*InsertBefore=*/nullptr,
GlobalValue::NotThreadLocal, AMDGPUAS::GLOBAL_ADDRESS, GlobalValue::NotThreadLocal, AMDGPUAS::GLOBAL_ADDRESS,
/*IsExternallyInitialized=*/true); /*IsExternallyInitialized=*/true);
DEBUG(dbgs() << "runtime handle created: " << *GV << '\n'); DEBUG(dbgs() << "runtime handle created: " << *GV << '\n');
auto *NewPtr = ConstantExpr::getPointerCast(GV, AddrCast->getType()); auto *NewPtr = ConstantExpr::getPointerCast(GV, BitCast->getType());
AddrCast->replaceAllUsesWith(NewPtr); BitCast->replaceAllUsesWith(NewPtr);
F.addFnAttr("runtime-handle", RuntimeHandle); F.addFnAttr("runtime-handle", RuntimeHandle);
F.setLinkage(GlobalValue::ExternalLinkage); F.setLinkage(GlobalValue::ExternalLinkage);
// Collect direct or indirect callers of enqueue_kernel. // Collect direct or indirect callers of enqueue_kernel.
for (auto U : NewPtr->users()) { for (auto U : NewPtr->users()) {
if (auto *I = dyn_cast<Instruction>(&*U)) { if (auto *I = dyn_cast<Instruction>(&*U)) {
auto *F = I->getParent()->getParent(); auto *F = I->getParent()->getParent();
Callers.insert(F); Callers.insert(F);
collectCallers(F, Callers); collectCallers(F, Callers);
} }
} }
Changed = true; Changed = true;
} }
} }
}
for (auto F : Callers) { for (auto F : Callers) {
if (F->getCallingConv() != CallingConv::AMDGPU_KERNEL) if (F->getCallingConv() != CallingConv::AMDGPU_KERNEL)
continue; continue;
F->addFnAttr("calls-enqueue-kernel"); F->addFnAttr("calls-enqueue-kernel");
} }
return Changed; return Changed;
} }

llvm/trunk/test/CodeGen/AMDGPU/enqueue-kernel.ll

; RUN: opt -amdgpu-lower-enqueued-block -S < %s | FileCheck %s ; RUN: opt -data-layout=A5 -amdgpu-lower-enqueued-block -S < %s | FileCheck %s
; CHECK: @__test_block_invoke_kernel_runtime_handle = external addrspace(1) externally_initialized constant i8 addrspace(1)* ; CHECK: @__test_block_invoke_kernel_runtime_handle = external addrspace(1) externally_initialized constant i8 addrspace(1)*
; CHECK: @__test_block_invoke_2_kernel_runtime_handle = external addrspace(1) externally_initialized constant i8 addrspace(1)* ; CHECK: @__test_block_invoke_2_kernel_runtime_handle = external addrspace(1) externally_initialized constant i8 addrspace(1)*
target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
target triple = "amdgcn-amdhsa-amd-opencl"
%struct.ndrange_t = type { i32 } %struct.ndrange_t = type { i32 }
%opencl.queue_t = type opaque %opencl.queue_t = type opaque
; CHECK: define amdgpu_kernel void @non_caller(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr !kernel_arg_addr_space ; CHECK: define amdgpu_kernel void @non_caller(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr !kernel_arg_addr_space
define amdgpu_kernel void @non_caller(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr define amdgpu_kernel void @non_caller(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr
!kernel_arg_addr_space !3 !kernel_arg_access_qual !4 !kernel_arg_type !5 !kernel_arg_base_type !5 !kernel_arg_type_qual !6 { !kernel_arg_addr_space !3 !kernel_arg_access_qual !4 !kernel_arg_type !5 !kernel_arg_base_type !5 !kernel_arg_type_qual !6 {
ret void ret void
} }
; CHECK: define amdgpu_kernel void @caller_indirect(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr #[[AT_CALLER:[0-9]+]] ; CHECK: define amdgpu_kernel void @caller_indirect(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr #[[AT_CALLER:[0-9]+]]
define amdgpu_kernel void @caller_indirect(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr define amdgpu_kernel void @caller_indirect(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr
!kernel_arg_addr_space !3 !kernel_arg_access_qual !4 !kernel_arg_type !5 !kernel_arg_base_type !5 !kernel_arg_type_qual !6 { !kernel_arg_addr_space !3 !kernel_arg_access_qual !4 !kernel_arg_type !5 !kernel_arg_base_type !5 !kernel_arg_type_qual !6 {
call void @caller(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) call void @caller(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d)
ret void ret void
} }
; CHECK: define amdgpu_kernel void @caller(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr #[[AT_CALLER]] ; CHECK: define amdgpu_kernel void @caller(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr #[[AT_CALLER]]
define amdgpu_kernel void @caller(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr define amdgpu_kernel void @caller(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr
!kernel_arg_addr_space !3 !kernel_arg_access_qual !4 !kernel_arg_type !5 !kernel_arg_base_type !5 !kernel_arg_type_qual !6 { !kernel_arg_addr_space !3 !kernel_arg_access_qual !4 !kernel_arg_type !5 !kernel_arg_base_type !5 !kernel_arg_type_qual !6 {
entry: entry:
%block = alloca <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>, align 8 %block = alloca <{ i32, i32, i8 addrspace(1)*, i8 }>, align 8, addrspace(5)
%tmp = alloca %struct.ndrange_t, align 4 %tmp = alloca %struct.ndrange_t, align 4, addrspace(5)
%block2 = alloca <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, align 8 %block2 = alloca <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, align 8, addrspace(5)
%tmp3 = alloca %struct.ndrange_t, align 4 %tmp3 = alloca %struct.ndrange_t, align 4, addrspace(5)
%block.size = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>* %block, i32 0, i32 0 %block.size = getelementptr inbounds <{ i32, i32, i8 addrspace(1)*, i8 }>, <{ i32, i32, i8 addrspace(1)*, i8 }> addrspace(5)* %block, i32 0, i32 0
store i32 25, i32* %block.size, align 8 store i32 25, i32 addrspace(5)* %block.size, align 8
%block.align = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>* %block, i32 0, i32 1 %block.align = getelementptr inbounds <{ i32, i32, i8 addrspace(1)*, i8 }>, <{ i32, i32, i8 addrspace(1)*, i8 }> addrspace(5)* %block, i32 0, i32 1
store i32 8, i32* %block.align, align 4 store i32 8, i32 addrspace(5)* %block.align, align 4
%block.invoke = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>* %block, i32 0, i32 2 %block.captured = getelementptr inbounds <{ i32, i32, i8 addrspace(1)*, i8 }>, <{ i32, i32, i8 addrspace(1)*, i8 }> addrspace(5)* %block, i32 0, i32 2
store i8 addrspace(4)* addrspacecast (i8* bitcast (void (<{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>)* @__test_block_invoke_kernel to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %block.invoke, align 8 store i8 addrspace(1)* %a, i8 addrspace(1)* addrspace(5)* %block.captured, align 8
%block.captured = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>* %block, i32 0, i32 3 %block.captured1 = getelementptr inbounds <{ i32, i32, i8 addrspace(1)*, i8 }>, <{ i32, i32, i8 addrspace(1)*, i8 }> addrspace(5)* %block, i32 0, i32 3
store i8 addrspace(1)* %a, i8 addrspace(1)** %block.captured, align 8 store i8 %b, i8 addrspace(5)* %block.captured1, align 8
%block.captured1 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>* %block, i32 0, i32 4 %tmp1 = bitcast <{ i32, i32, i8 addrspace(1)*, i8 }> addrspace(5)* %block to void () addrspace(5)*
store i8 %b, i8* %block.captured1, align 8 %tmp4 = addrspacecast void () addrspace(5)* %tmp1 to i8*
%tmp1 = bitcast <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>* %block to void ()* %tmp5 = call i32 @__enqueue_kernel_basic(%opencl.queue_t addrspace(1)* undef, i32 0, %struct.ndrange_t addrspace(5)* byval nonnull %tmp,
%tmp2 = bitcast void ()* %tmp1 to i8* i8* bitcast (void (<{ i32, i32, i8 addrspace(1)*, i8 }>)* @__test_block_invoke_kernel to i8*), i8* nonnull %tmp4) #2
%tmp4 = addrspacecast i8* %tmp2 to i8 addrspace(4)* %tmp10 = call i32 @__enqueue_kernel_basic(%opencl.queue_t addrspace(1)* undef, i32 0, %struct.ndrange_t addrspace(5)* byval nonnull %tmp,
%tmp5 = call i32 @__enqueue_kernel_basic(%opencl.queue_t addrspace(1)* undef, i32 0, %struct.ndrange_t* byval nonnull %tmp, i8 addrspace(4)* nonnull %tmp4) #2 i8* bitcast (void (<{ i32, i32, i8 addrspace(1)*, i8 }>)* @__test_block_invoke_kernel to i8*), i8* nonnull %tmp4) #2
%block.size4 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>* %block2, i32 0, i32 0 %block.size4 = getelementptr inbounds <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> addrspace(5)* %block2, i32 0, i32 0
store i32 41, i32* %block.size4, align 8 store i32 41, i32 addrspace(5)* %block.size4, align 8
%block.align5 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>* %block2, i32 0, i32 1 %block.align5 = getelementptr inbounds <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> addrspace(5)* %block2, i32 0, i32 1
store i32 8, i32* %block.align5, align 4 store i32 8, i32 addrspace(5)* %block.align5, align 4
%block.invoke6 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>* %block2, i32 0, i32 2 %block.captured7 = getelementptr inbounds <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> addrspace(5)* %block2, i32 0, i32 2
store i8 addrspace(4)* addrspacecast (i8* bitcast (void (<{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>)* @__test_block_invoke_2_kernel to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %block.invoke6, align 8 store i8 addrspace(1)* %a, i8 addrspace(1)* addrspace(5)* %block.captured7, align 8
%block.captured7 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>* %block2, i32 0, i32 3 %block.captured8 = getelementptr inbounds <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> addrspace(5)* %block2, i32 0, i32 5
store i8 addrspace(1)* %a, i8 addrspace(1)** %block.captured7, align 8 store i8 %b, i8 addrspace(5)* %block.captured8, align 8
%block.captured8 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>* %block2, i32 0, i32 6 %block.captured9 = getelementptr inbounds <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> addrspace(5)* %block2, i32 0, i32 3
store i8 %b, i8* %block.captured8, align 8 store i64 addrspace(1)* %c, i64 addrspace(1)* addrspace(5)* %block.captured9, align 8
%block.captured9 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>* %block2, i32 0, i32 4 %block.captured10 = getelementptr inbounds <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> addrspace(5)* %block2, i32 0, i32 4
store i64 addrspace(1)* %c, i64 addrspace(1)** %block.captured9, align 8 store i64 %d, i64 addrspace(5)* %block.captured10, align 8
%block.captured10 = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>* %block2, i32 0, i32 5 %tmp6 = bitcast <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> addrspace(5)* %block2 to void () addrspace(5)*
store i64 %d, i64* %block.captured10, align 8 %tmp8 = addrspacecast void () addrspace(5)* %tmp6 to i8*
%tmp6 = bitcast <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>* %block2 to void ()* %tmp9 = call i32 @__enqueue_kernel_basic(%opencl.queue_t addrspace(1)* undef, i32 0, %struct.ndrange_t addrspace(5)* byval nonnull %tmp3,
%tmp7 = bitcast void ()* %tmp6 to i8* i8* bitcast (void (<{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>)* @__test_block_invoke_2_kernel to i8*), i8* nonnull %tmp8) #2
%tmp8 = addrspacecast i8* %tmp7 to i8 addrspace(4)*
%tmp9 = call i32 @__enqueue_kernel_basic(%opencl.queue_t addrspace(1)* undef, i32 0, %struct.ndrange_t* byval nonnull %tmp3, i8 addrspace(4)* nonnull %tmp8) #2
ret void ret void
} }
; CHECK: define dso_local amdgpu_kernel void @__test_block_invoke_kernel({{.*}}) #[[AT1:[0-9]+]] ; CHECK: define dso_local amdgpu_kernel void @__test_block_invoke_kernel({{.*}}) #[[AT1:[0-9]+]]
define internal amdgpu_kernel void @__test_block_invoke_kernel(<{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }> %arg) #0 define internal amdgpu_kernel void @__test_block_invoke_kernel(<{ i32, i32, i8 addrspace(1)*, i8 }> %arg) #0
!kernel_arg_addr_space !14 !kernel_arg_access_qual !15 !kernel_arg_type !16 !kernel_arg_base_type !16 !kernel_arg_type_qual !17 { !kernel_arg_addr_space !14 !kernel_arg_access_qual !15 !kernel_arg_type !16 !kernel_arg_base_type !16 !kernel_arg_type_qual !17 {
entry: entry:
%.fca.3.extract = extractvalue <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }> %arg, 3 %.fca.3.extract = extractvalue <{ i32, i32, i8 addrspace(1)*, i8 }> %arg, 2
%.fca.4.extract = extractvalue <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }> %arg, 4 %.fca.4.extract = extractvalue <{ i32, i32, i8 addrspace(1)*, i8 }> %arg, 3
store i8 %.fca.4.extract, i8 addrspace(1)* %.fca.3.extract, align 1 store i8 %.fca.4.extract, i8 addrspace(1)* %.fca.3.extract, align 1
ret void ret void
} }
declare i32 @__enqueue_kernel_basic(%opencl.queue_t addrspace(1)*, i32, %struct.ndrange_t*, i8 addrspace(4)*) local_unnamed_addr declare i32 @__enqueue_kernel_basic(%opencl.queue_t addrspace(1)*, i32, %struct.ndrange_t addrspace(5)*, i8*, i8*) local_unnamed_addr
; CHECK: define dso_local amdgpu_kernel void @__test_block_invoke_2_kernel({{.*}}) #[[AT2:[0-9]+]] ; CHECK: define dso_local amdgpu_kernel void @__test_block_invoke_2_kernel({{.*}}) #[[AT2:[0-9]+]]
define internal amdgpu_kernel void @__test_block_invoke_2_kernel(<{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, define internal amdgpu_kernel void @__test_block_invoke_2_kernel(<{ i32, i32, i8 addrspace(1)*,
i64 addrspace(1)*, i64, i8 }> %arg) #0 !kernel_arg_addr_space !14 !kernel_arg_access_qual !15 i64 addrspace(1)*, i64, i8 }> %arg) #0 !kernel_arg_addr_space !14 !kernel_arg_access_qual !15
!kernel_arg_type !16 !kernel_arg_base_type !16 !kernel_arg_type_qual !17 { !kernel_arg_type !16 !kernel_arg_base_type !16 !kernel_arg_type_qual !17 {
entry: entry:
%.fca.3.extract = extractvalue <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> %arg, 3 %.fca.3.extract = extractvalue <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> %arg, 2
%.fca.4.extract = extractvalue <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> %arg, 4 %.fca.4.extract = extractvalue <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> %arg, 3
%.fca.5.extract = extractvalue <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> %arg, 5 %.fca.5.extract = extractvalue <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> %arg, 4
%.fca.6.extract = extractvalue <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> %arg, 6 %.fca.6.extract = extractvalue <{ i32, i32, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }> %arg, 5
store i8 %.fca.6.extract, i8 addrspace(1)* %.fca.3.extract, align 1 store i8 %.fca.6.extract, i8 addrspace(1)* %.fca.3.extract, align 1
store i64 %.fca.5.extract, i64 addrspace(1)* %.fca.4.extract, align 8 store i64 %.fca.5.extract, i64 addrspace(1)* %.fca.4.extract, align 8
ret void ret void
} }
; CHECK: attributes #[[AT_CALLER]] = { "calls-enqueue-kernel" } ; CHECK: attributes #[[AT_CALLER]] = { "calls-enqueue-kernel" }
; CHECK: attributes #[[AT1]] = {{.*}}"runtime-handle"="__test_block_invoke_kernel_runtime_handle" ; CHECK: attributes #[[AT1]] = {{.*}}"runtime-handle"="__test_block_invoke_kernel_runtime_handle"
; CHECK: attributes #[[AT2]] = {{.*}}"runtime-handle"="__test_block_invoke_2_kernel_runtime_handle" ; CHECK: attributes #[[AT2]] = {{.*}}"runtime-handle"="__test_block_invoke_2_kernel_runtime_handle"
Show All 11 Lines