File: x86-inline-asm-v-constraint.c

package info (click to toggle)
llvm-toolchain-11 1%3A11.0.1-2~deb10u1
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 995,836 kB
  • sloc: cpp: 4,767,656; ansic: 760,916; asm: 477,436; python: 170,940; objc: 69,804; lisp: 29,914; sh: 23,855; f90: 18,173; pascal: 7,551; perl: 7,471; ml: 5,603; awk: 3,489; makefile: 2,573; xml: 915; cs: 573; fortran: 503; javascript: 452
file content (55 lines) | stat: -rw-r--r-- 2,138 bytes parent folder | download | duplicates (13)
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
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
// RUN: %clang_cc1 %s -triple x86_64-unknown-linux-gnu -emit-llvm -target-cpu x86-64 -o - |FileCheck %s --check-prefix SSE
// RUN: %clang_cc1 %s -triple x86_64-unknown-linux-gnu -emit-llvm -target-cpu skylake -D AVX -o - | FileCheck %s --check-prefixes AVX,SSE
// RUN: %clang_cc1 %s -triple x86_64-unknown-linux-gnu -emit-llvm -target-cpu skylake-avx512 -D AVX512 -D AVX -o - | FileCheck %s --check-prefixes AVX512,AVX,SSE
// RUN: %clang_cc1 %s -triple x86_64-unknown-linux-gnu -emit-llvm -target-cpu knl -D AVX -D AVX512 -o - | FileCheck %s --check-prefixes AVX512,AVX,SSE

typedef float __m128 __attribute__ ((vector_size (16)));
typedef float __m256 __attribute__ ((vector_size (32)));
typedef float __m512 __attribute__ ((vector_size (64)));

// SSE: call <4 x float> asm "vmovhlps $1, $2, $0", "=v,v,v,~{dirflag},~{fpsr},~{flags}"(i64 %0, <4 x float> %1)
__m128 testXMM(__m128 _xmm0, long _l) {
  __asm__("vmovhlps %1, %2, %0" :"=v"(_xmm0) : "v"(_l), "v"(_xmm0));
  return _xmm0;
}

// AVX: call <8 x float> asm "vmovsldup $1, $0", "=v,v,~{dirflag},~{fpsr},~{flags}"(<8 x float> %0)
__m256 testYMM(__m256 _ymm0) {
#ifdef AVX
  __asm__("vmovsldup %1, %0" :"=v"(_ymm0) : "v"(_ymm0));
#endif
  return _ymm0;
}

// AVX512: call <16 x float> asm "vpternlogd $$0, $1, $2, $0", "=v,v,v,~{dirflag},~{fpsr},~{flags}"(<16 x float> %0, <16 x float> %1)
__m512 testZMM(__m512 _zmm0, __m512 _zmm1) {
#ifdef AVX512
  __asm__("vpternlogd $0, %1, %2, %0" :"=v"(_zmm0) : "v"(_zmm1), "v"(_zmm0));
#endif
  return _zmm0;
}

// SSE: call <4 x float> asm "pcmpeqd $0, $0", "=^Yz,~{dirflag},~{fpsr},~{flags}"()
__m128 testXMM0(void) {
  __m128 xmm0;
  __asm__("pcmpeqd %0, %0" :"=Yz"(xmm0));
  return xmm0;
}

// AVX: call <8 x float> asm "vpcmpeqd $0, $0, $0", "=^Yz,~{dirflag},~{fpsr},~{flags}"()
__m256 testYMM0(void) {
  __m256 ymm0;
#ifdef AVX
  __asm__("vpcmpeqd %0, %0, %0" :"=Yz"(ymm0));
#endif
  return ymm0;
}

// AVX512: call <16 x float> asm "vpternlogd $$255, $0, $0, $0", "=^Yz,~{dirflag},~{fpsr},~{flags}"()
__m512 testZMM0(void) {
  __m512 zmm0;
#ifdef AVX512
  __asm__("vpternlogd $255, %0, %0, %0" :"=Yz"(zmm0));
#endif
  return zmm0;
}