intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-02-08 17:28:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

AMDGPU/SI: Use amdgpu_kernel calling convention for OpenCL kernels.

Browse Source 
Reviewers: tstellarAMD, arsenm

Subscribers: cfe-commits

Differential Revision: http://reviews.llvm.org/D19918

llvm-svn: 268718
This commit is contained in:
Nikolay Haustov
2016-05-06 09:15:24 +00:00
parent 1f7732abfa
commit 4961ea85d7
3 changed files with 24 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
clang/lib/CodeGen/TargetInfo.cpp
View File

@@ -6826,6 +6826,14 @@ void AMDGPUTargetCodeGenInfo::setTargetAttributes(
if (!FD)
return;
if (M.getLangOpts().OpenCL) {
if (FD->hasAttr<OpenCLKernelAttr>()) {
// Set amdgpu_kernel calling convention for OpenCL kernels.
llvm::Function *Fn = cast<llvm::Function>(GV);
Fn->setCallingConv(llvm::CallingConv::AMDGPU_KERNEL);
}
}
if (const auto Attr = FD->getAttr<AMDGPUNumVGPRAttr>()) {
llvm::Function *F = cast<llvm::Function>(GV);
uint32_t NumVGPR = Attr->getNumVGPR();

12
clang/test/CodeGenOpenCL/amdgpu-calling-conv.cl Normal file
View File

@@ -0,0 +1,12 @@
// REQUIRES: amdgpu-registered-target
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -emit-llvm -o - %s | FileCheck %s
// CHECK: define amdgpu_kernel void @calling_conv_amdgpu_kernel()
kernel void calling_conv_amdgpu_kernel()
{
}
// CHECK: define void @calling_conv_none()
void calling_conv_none()
{
}

8
clang/test/CodeGenOpenCL/amdgpu-num-gpr-attr.cl
View File

@@ -5,23 +5,23 @@
__attribute__((amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void test_num_vgpr64() {
// CHECK: define void @test_num_vgpr64() [[ATTR_VGPR64:#[0-9]+]]
// CHECK: define amdgpu_kernel void @test_num_vgpr64() [[ATTR_VGPR64:#[0-9]+]]
}
__attribute__((amdgpu_num_sgpr(32))) // expected-no-diagnostics
kernel void test_num_sgpr32() {
// CHECK: define void @test_num_sgpr32() [[ATTR_SGPR32:#[0-9]+]]
// CHECK: define amdgpu_kernel void @test_num_sgpr32() [[ATTR_SGPR32:#[0-9]+]]
}
__attribute__((amdgpu_num_vgpr(64), amdgpu_num_sgpr(32))) // expected-no-diagnostics
kernel void test_num_vgpr64_sgpr32() {
// CHECK: define void @test_num_vgpr64_sgpr32() [[ATTR_VGPR64_SGPR32:#[0-9]+]]
// CHECK: define amdgpu_kernel void @test_num_vgpr64_sgpr32() [[ATTR_VGPR64_SGPR32:#[0-9]+]]
}
__attribute__((amdgpu_num_sgpr(20), amdgpu_num_vgpr(40))) // expected-no-diagnostics
kernel void test_num_sgpr20_vgpr40() {
// CHECK: define void @test_num_sgpr20_vgpr40() [[ATTR_SGPR20_VGPR40:#[0-9]+]]
// CHECK: define amdgpu_kernel void @test_num_sgpr20_vgpr40() [[ATTR_SGPR20_VGPR40:#[0-9]+]]
}
__attribute__((amdgpu_num_vgpr(0))) // expected-no-diagnostics