File: builtins-amdgcn.cu

package info (click to toggle)
llvm-toolchain-9 1%3A9.0.1-16
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 882,436 kB
  • sloc: cpp: 4,167,636; ansic: 714,256; asm: 457,610; python: 155,927; objc: 65,094; sh: 42,856; lisp: 26,908; perl: 7,786; pascal: 7,722; makefile: 6,881; ml: 5,581; awk: 3,648; cs: 2,027; xml: 888; javascript: 381; ruby: 156
file content (18 lines) | stat: -rw-r--r-- 767 bytes parent folder | download | duplicates (2) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
 
// RUN: %clang_cc1 -triple amdgcn -fcuda-is-device -emit-llvm %s -o - | FileCheck %s
#include "Inputs/cuda.h"

// CHECK-LABEL: @_Z16use_dispatch_ptrPi(
// CHECK: %[[PTR:.*]] = call i8 addrspace(4)* @llvm.amdgcn.dispatch.ptr()
// CHECK: %{{.*}} = addrspacecast i8 addrspace(4)* %[[PTR]] to i8 addrspace(4)**
__global__ void use_dispatch_ptr(int* out) {
  const int* dispatch_ptr = (const int*)__builtin_amdgcn_dispatch_ptr();
  *out = *dispatch_ptr;
}

// CHECK-LABEL: @_Z12test_ds_fmaxf(
// CHECK: call float @llvm.amdgcn.ds.fmax(float addrspace(3)* @_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
__global__
void test_ds_fmax(float src) {
  __shared__ float shared;
  volatile float x = __builtin_amdgcn_ds_fmaxf(&shared, src, 0, 0, false);
}