File: amdgpu-float16.cpp

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 (20 lines) | stat: -rw-r--r-- 715 bytes parent folder | download | duplicates (23) 
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;
}