File: atomics-remarks-gfx90a.cu

package info (click to toggle)
swiftlang 6.0.3-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 2,519,992 kB
  • sloc: cpp: 9,107,863; ansic: 2,040,022; asm: 1,135,751; python: 296,500; objc: 82,456; f90: 60,502; lisp: 34,951; pascal: 19,946; sh: 18,133; perl: 7,482; ml: 4,937; javascript: 4,117; makefile: 3,840; awk: 3,535; xml: 914; fortran: 619; cs: 573; ruby: 573
file content (16 lines) | stat: -rw-r--r-- 594 bytes parent folder | download | duplicates (15) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
 
// RUN: %clang_cc1 %s -triple=amdgcn-amd-amdhsa -fcuda-is-device \
// RUN:   -target-cpu gfx90a -Rpass=atomic-expand -S -o - 2>&1 | \
// RUN:   FileCheck %s --check-prefix=GFX90A-CAS

// REQUIRES: amdgpu-registered-target

#include "Inputs/cuda.h"
#include <stdatomic.h>

// GFX90A-CAS: A compare and swap loop was generated for an atomic fadd operation at system memory scope
// GFX90A-CAS-LABEL: _Z14atomic_add_casPf
// GFX90A-CAS:  flat_atomic_cmpswap
// GFX90A-CAS:  s_cbranch_execnz
__device__ float atomic_add_cas(float *p) {
  return __atomic_fetch_add(p, 1.0f, memory_order_relaxed);
}