blob: 96de5c451b02ff56c0f48ff8f861627438db9a1c (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
|
// REQUIRES: x86-registered-target
// REQUIRES: nvptx-registered-target
// By default we should fuse multiply/add into fma instruction.
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -disable-llvm-passes -o - %s | FileCheck -check-prefix ENABLED %s
// Explicit -ffp-contract=fast
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -ffp-contract=fast -disable-llvm-passes -o - %s \
// RUN: | FileCheck -check-prefix ENABLED %s
// Explicit -ffp-contract=on -- fusing by front-end.
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -ffp-contract=on -disable-llvm-passes -o - %s \
// RUN: | FileCheck -check-prefix ENABLED %s
// Explicit -ffp-contract=off should disable instruction fusing.
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -ffp-contract=off -disable-llvm-passes -o - %s \
// RUN: | FileCheck -check-prefix DISABLED %s
#include "Inputs/cuda.h"
__host__ __device__ float func(float a, float b, float c) { return a + b * c; }
// ENABLED: fma.rn.f32
// ENABLED-NEXT: st.param.f32
// DISABLED: mul.rn.f32
// DISABLED-NEXT: add.rn.f32
// DISABLED-NEXT: st.param.f32
|
