derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
75 lines
3.0 KiB
C
75 lines
3.0 KiB
C
// RUN: %clang_cc1 %s -triple x86_64-unknown-linux-gnu -emit-llvm -target-cpu x86-64 -o - | FileCheck %s --check-prefixes=CHECK,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;
|
|
}
|
|
|
|
// CHECK-LABEL: test_a_p(
|
|
// CHECK: call void asm sideeffect "lea ${0:a}, %eax", "p,~{eax},~{dirflag},~{fpsr},~{flags}"(ptr %0)
|
|
// CHECK: call void asm sideeffect "lea ${0:a}, %eax", "p,~{eax},~{dirflag},~{fpsr},~{flags}"(i32 %add)
|
|
void test_a_p(int *ptr, int i) {
|
|
asm("lea %a0, %%eax" :: "p"(ptr) : "eax");
|
|
asm("lea %a0, %%eax" :: "p"(0x1480 + i * 8) : "eax");
|
|
}
|
|
|
|
extern int var, arr[4];
|
|
struct Pair { int a, b; } pair;
|
|
|
|
// CHECK-LABEL: test_Ws(
|
|
// CHECK: call void asm sideeffect "// ${0:p} ${1:p} ${2:p}", "^Ws,^Ws,^Ws,~{dirflag},~{fpsr},~{flags}"(ptr @var, ptr getelementptr inbounds nuw (i8, ptr @arr, i64 12), ptr @test_Ws)
|
|
// CHECK: call void asm sideeffect "// $0", "^Ws,~{dirflag},~{fpsr},~{flags}"(ptr getelementptr inbounds nuw (i8, ptr @pair, i64 4))
|
|
void test_Ws(void) {
|
|
asm("// %p0 %p1 %p2" :: "Ws"(&var), "Ws"(&arr[3]), "Ws"(test_Ws));
|
|
asm("// %0" :: "Ws"(&pair.b));
|
|
}
|