From f7053ec90d0fc56f0837e43c2c759e85b56c21a1 Mon Sep 17 00:00:00 2001 From: Nikolay Haustov Date: Fri, 6 May 2016 09:15:24 +0000 Subject: [PATCH] AMDGPU/SI: Use amdgpu_kernel calling convention for OpenCL kernels. Reviewers: tstellarAMD, arsenm Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D19918 git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@268718 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/CodeGen/TargetInfo.cpp | 8 ++++++++ test/CodeGenOpenCL/amdgpu-calling-conv.cl | 12 ++++++++++++ test/CodeGenOpenCL/amdgpu-num-gpr-attr.cl | 8 ++++---- 3 files changed, 24 insertions(+), 4 deletions(-) create mode 100644 test/CodeGenOpenCL/amdgpu-calling-conv.cl diff --git a/lib/CodeGen/TargetInfo.cpp b/lib/CodeGen/TargetInfo.cpp index 4ee8573049..4448057a37 100644 --- a/lib/CodeGen/TargetInfo.cpp +++ b/lib/CodeGen/TargetInfo.cpp @@ -6826,6 +6826,14 @@ void AMDGPUTargetCodeGenInfo::setTargetAttributes( if (!FD) return; + if (M.getLangOpts().OpenCL) { + if (FD->hasAttr()) { + // Set amdgpu_kernel calling convention for OpenCL kernels. + llvm::Function *Fn = cast(GV); + Fn->setCallingConv(llvm::CallingConv::AMDGPU_KERNEL); + } + } + if (const auto Attr = FD->getAttr()) { llvm::Function *F = cast(GV); uint32_t NumVGPR = Attr->getNumVGPR(); diff --git a/test/CodeGenOpenCL/amdgpu-calling-conv.cl b/test/CodeGenOpenCL/amdgpu-calling-conv.cl new file mode 100644 index 0000000000..7da9d7f4d4 --- /dev/null +++ b/test/CodeGenOpenCL/amdgpu-calling-conv.cl @@ -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() +{ +} diff --git a/test/CodeGenOpenCL/amdgpu-num-gpr-attr.cl b/test/CodeGenOpenCL/amdgpu-num-gpr-attr.cl index d2ecc7a8c6..589d00d1ea 100644 --- a/test/CodeGenOpenCL/amdgpu-num-gpr-attr.cl +++ b/test/CodeGenOpenCL/amdgpu-num-gpr-attr.cl @@ -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 -- 2.40.0