fd739804e0
For a default visibility external linkage definition, dso_local is set for ELF
-fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar
to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences.
To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition,
which sets dso_local for default visibility external linkage definitions.
To make this flip smooth and enable future (dso_local as definition default),
this patch replaces (function) `define ` with `define{{.*}} `,
(variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
29 lines
1.2 KiB
Plaintext
29 lines
1.2 KiB
Plaintext
// RUN: %clang_cc1 "-triple" "nvptx-nvidia-cuda" -emit-llvm -fcuda-is-device -o - %s | FileCheck %s
|
|
|
|
#include "__clang_cuda_builtin_vars.h"
|
|
|
|
// CHECK: define{{.*}} void @_Z6kernelPi(i32* %out)
|
|
__attribute__((global))
|
|
void kernel(int *out) {
|
|
int i = 0;
|
|
out[i++] = threadIdx.x; // CHECK: call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
|
|
out[i++] = threadIdx.y; // CHECK: call i32 @llvm.nvvm.read.ptx.sreg.tid.y()
|
|
out[i++] = threadIdx.z; // CHECK: call i32 @llvm.nvvm.read.ptx.sreg.tid.z()
|
|
|
|
out[i++] = blockIdx.x; // CHECK: call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
|
|
out[i++] = blockIdx.y; // CHECK: call i32 @llvm.nvvm.read.ptx.sreg.ctaid.y()
|
|
out[i++] = blockIdx.z; // CHECK: call i32 @llvm.nvvm.read.ptx.sreg.ctaid.z()
|
|
|
|
out[i++] = blockDim.x; // CHECK: call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
|
|
out[i++] = blockDim.y; // CHECK: call i32 @llvm.nvvm.read.ptx.sreg.ntid.y()
|
|
out[i++] = blockDim.z; // CHECK: call i32 @llvm.nvvm.read.ptx.sreg.ntid.z()
|
|
|
|
out[i++] = gridDim.x; // CHECK: call i32 @llvm.nvvm.read.ptx.sreg.nctaid.x()
|
|
out[i++] = gridDim.y; // CHECK: call i32 @llvm.nvvm.read.ptx.sreg.nctaid.y()
|
|
out[i++] = gridDim.z; // CHECK: call i32 @llvm.nvvm.read.ptx.sreg.nctaid.z()
|
|
|
|
out[i++] = warpSize; // CHECK: store i32 32,
|
|
|
|
// CHECK: ret void
|
|
}
|