File: amdgpu-float16.cpp

package info (click to toggle)
llvm-toolchain-21 1%3A21.1.0-1
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 2,235,796 kB
  • sloc: cpp: 7,617,614; ansic: 1,433,901; asm: 1,058,726; python: 252,096; f90: 94,671; objc: 70,753; lisp: 42,813; pascal: 18,401; sh: 10,032; ml: 5,111; perl: 4,720; awk: 3,523; makefile: 3,401; javascript: 2,272; xml: 892; fortran: 770
file content (20 lines) | stat: -rw-r--r-- 715 bytes parent folder | download | duplicates (24) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
 
// REQUIRES: amdgpu-registered-target
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -target-cpu gfx701 -S -o - %s | FileCheck %s -check-prefix=NOF16
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -target-cpu gfx803 -S -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -target-cpu gfx900 -S -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -target-cpu gfx906 -S -o - %s | FileCheck %s
void f() {
  _Float16 x, y, z;
  // CHECK: v_add_f16_e64
  // NOF16: v_add_f32_e64
  z = x + y;
  // CHECK: v_sub_f16_e64
  // NOF16: v_sub_f32_e64
  z = x - y;
  // CHECK: v_mul_f16_e64
  // NOF16: v_mul_f32_e64
  z = x * y;
  // CHECK: v_div_fixup_f16
  // NOF16: v_div_fixup_f32
  z = x / y;
}