File: builtins-fp-atomics-gfx8.cl

package info (click to toggle)
llvm-toolchain-14 1%3A14.0.6-16
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 1,496,368 kB
  • sloc: cpp: 5,593,980; ansic: 986,873; asm: 585,869; python: 184,223; objc: 72,530; lisp: 31,119; f90: 27,793; javascript: 9,780; pascal: 9,762; sh: 9,482; perl: 7,468; ml: 5,432; awk: 3,523; makefile: 2,547; xml: 953; cs: 573; fortran: 567
file content (16 lines) | stat: -rw-r--r-- 683 bytes parent folder | download | duplicates (3) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
 
// RUN: %clang_cc1 -O0 -cl-std=CL2.0 -triple amdgcn-amd-amdhsa -target-cpu gfx810 \
// RUN:   %s -S -emit-llvm -o - | FileCheck %s
// RUN: %clang_cc1 -O0 -cl-std=CL2.0 -triple amdgcn-amd-amdhsa -target-cpu gfx810 \
// RUN:   -S -o - %s | FileCheck -check-prefix=GFX8 %s

// REQUIRES: amdgpu-registered-target

// CHECK-LABEL: test_fadd_local
// CHECK: call float @llvm.amdgcn.ds.fadd.f32(float addrspace(3)* %{{.*}}, float %{{.*}}, i32 0, i32 0, i1 false)
// GFX8-LABEL: test_fadd_local$local:
// GFX8: ds_add_rtn_f32 v2, v0, v1
// GFX8: s_endpgm
kernel void test_fadd_local(__local float *ptr, float val){
    float *res;
    *res = __builtin_amdgcn_ds_atomic_fadd_f32(ptr, val);
}