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
77 lines
2.7 KiB
LLVM
77 lines
2.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefix=SSE
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX
|
|
|
|
define <4 x i32> @load_zmov_4i32_to_0zzz(ptr%ptr) {
|
|
; SSE-LABEL: load_zmov_4i32_to_0zzz:
|
|
; SSE: # %bb.0: # %entry
|
|
; SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: load_zmov_4i32_to_0zzz:
|
|
; AVX: # %bb.0: # %entry
|
|
; AVX-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; AVX-NEXT: retq
|
|
entry:
|
|
%X = load <4 x i32>, ptr %ptr
|
|
%Y = shufflevector <4 x i32> %X, <4 x i32> zeroinitializer, <4 x i32> <i32 0, i32 4, i32 4, i32 4>
|
|
ret <4 x i32>%Y
|
|
}
|
|
|
|
define <2 x i64> @load_zmov_2i64_to_0z(ptr%ptr) {
|
|
; SSE-LABEL: load_zmov_2i64_to_0z:
|
|
; SSE: # %bb.0: # %entry
|
|
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: load_zmov_2i64_to_0z:
|
|
; AVX: # %bb.0: # %entry
|
|
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
|
; AVX-NEXT: retq
|
|
entry:
|
|
%X = load <2 x i64>, ptr %ptr
|
|
%Y = shufflevector <2 x i64> %X, <2 x i64> zeroinitializer, <2 x i32> <i32 0, i32 2>
|
|
ret <2 x i64>%Y
|
|
}
|
|
|
|
define <4 x i32> @load_zmov_4i32_to_0zzz_volatile(ptr%ptr) {
|
|
; SSE-LABEL: load_zmov_4i32_to_0zzz_volatile:
|
|
; SSE: # %bb.0: # %entry
|
|
; SSE-NEXT: movaps (%rdi), %xmm1
|
|
; SSE-NEXT: xorps %xmm0, %xmm0
|
|
; SSE-NEXT: movss {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: load_zmov_4i32_to_0zzz_volatile:
|
|
; AVX: # %bb.0: # %entry
|
|
; AVX-NEXT: vmovaps (%rdi), %xmm0
|
|
; AVX-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; AVX-NEXT: vmovss {{.*#+}} xmm0 = xmm0[0],xmm1[1,2,3]
|
|
; AVX-NEXT: retq
|
|
entry:
|
|
%X = load volatile <4 x i32>, ptr %ptr
|
|
%Y = shufflevector <4 x i32> %X, <4 x i32> zeroinitializer, <4 x i32> <i32 0, i32 4, i32 4, i32 4>
|
|
ret <4 x i32>%Y
|
|
}
|
|
|
|
define <2 x i64> @load_zmov_2i64_to_0z_volatile(ptr%ptr) {
|
|
; SSE-LABEL: load_zmov_2i64_to_0z_volatile:
|
|
; SSE: # %bb.0: # %entry
|
|
; SSE-NEXT: movdqa (%rdi), %xmm0
|
|
; SSE-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: load_zmov_2i64_to_0z_volatile:
|
|
; AVX: # %bb.0: # %entry
|
|
; AVX-NEXT: vmovdqa (%rdi), %xmm0
|
|
; AVX-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
|
; AVX-NEXT: retq
|
|
entry:
|
|
%X = load volatile <2 x i64>, ptr %ptr
|
|
%Y = shufflevector <2 x i64> %X, <2 x i64> zeroinitializer, <2 x i32> <i32 0, i32 2>
|
|
ret <2 x i64>%Y
|
|
}
|