1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
|
// RUN: %clang_cc1 -no-opaque-pointers "-triple" "nvptx-nvidia-cuda" -emit-llvm -fcuda-is-device -o - %s | FileCheck %s
#include "__clang_cuda_builtin_vars.h"
// CHECK: define{{.*}} void @_Z6kernelPi(i32* noundef %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
}
|
