File: arm-neon-fma.c

package info (click to toggle)
llvm-toolchain-4.0 1%3A4.0.1-10~deb9u2
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 493,332 kB
  • sloc: cpp: 2,698,100; ansic: 552,773; asm: 128,821; python: 121,589; objc: 105,054; sh: 21,174; lisp: 6,758; ml: 5,532; perl: 5,311; pascal: 5,245; makefile: 2,083; cs: 1,868; xml: 686; php: 212; csh: 117
file content (22 lines) | stat: -rw-r--r-- 1,044 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
// RUN: %clang_cc1 -triple thumbv7-none-linux-gnueabihf \
// RUN:   -target-abi aapcs \
// RUN:   -target-cpu cortex-a7 \
// RUN:   -mfloat-abi hard \
// RUN:   -ffreestanding \
// RUN:   -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s

#include <arm_neon.h>

// CHECK-LABEL: define <2 x float> @test_fma_order(<2 x float> %accum, <2 x float> %lhs, <2 x float> %rhs) #0 {
// CHECK:   [[TMP6:%.*]] = call <2 x float> @llvm.fma.v2f32(<2 x float> %lhs, <2 x float> %rhs, <2 x float> %accum) #2
// CHECK:   ret <2 x float> [[TMP6]]
float32x2_t test_fma_order(float32x2_t accum, float32x2_t lhs, float32x2_t rhs) {
  return vfma_f32(accum, lhs, rhs);
}

// CHECK-LABEL: define <4 x float> @test_fmaq_order(<4 x float> %accum, <4 x float> %lhs, <4 x float> %rhs) #0 {
// CHECK:   [[TMP6:%.*]] = call <4 x float> @llvm.fma.v4f32(<4 x float> %lhs, <4 x float> %rhs, <4 x float> %accum) #2
// CHECK:   ret <4 x float> [[TMP6]]
float32x4_t test_fmaq_order(float32x4_t accum, float32x4_t lhs, float32x4_t rhs) {
  return vfmaq_f32(accum, lhs, rhs);
}