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
59 lines
2.6 KiB
LLVM
59 lines
2.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE-32
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE-64
|
|
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX-32
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX-64
|
|
|
|
define void @PR15298(ptr nocapture %source, ptr nocapture %dest) nounwind noinline {
|
|
; SSE-32-LABEL: PR15298:
|
|
; SSE-32: # %bb.0: # %L.entry
|
|
; SSE-32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; SSE-32-NEXT: movl {{[0-9]+}}(%esp), %ecx
|
|
; SSE-32-NEXT: xorps %xmm0, %xmm0
|
|
; SSE-32-NEXT: xorps %xmm1, %xmm1
|
|
; SSE-32-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,3],mem[0,0]
|
|
; SSE-32-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,2,3,1]
|
|
; SSE-32-NEXT: movups %xmm0, 624(%eax)
|
|
; SSE-32-NEXT: movups %xmm1, 608(%eax)
|
|
; SSE-32-NEXT: retl
|
|
;
|
|
; SSE-64-LABEL: PR15298:
|
|
; SSE-64: # %bb.0: # %L.entry
|
|
; SSE-64-NEXT: xorps %xmm0, %xmm0
|
|
; SSE-64-NEXT: xorps %xmm1, %xmm1
|
|
; SSE-64-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,3],mem[0,0]
|
|
; SSE-64-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,2,3,1]
|
|
; SSE-64-NEXT: movups %xmm0, 624(%rsi)
|
|
; SSE-64-NEXT: movups %xmm1, 608(%rsi)
|
|
; SSE-64-NEXT: retq
|
|
;
|
|
; AVX-32-LABEL: PR15298:
|
|
; AVX-32: # %bb.0: # %L.entry
|
|
; AVX-32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; AVX-32-NEXT: movl {{[0-9]+}}(%esp), %ecx
|
|
; AVX-32-NEXT: vbroadcastss 304(%ecx), %xmm0
|
|
; AVX-32-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; AVX-32-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2],ymm1[3,4,5,6,7]
|
|
; AVX-32-NEXT: vmovups %ymm0, 608(%eax)
|
|
; AVX-32-NEXT: vzeroupper
|
|
; AVX-32-NEXT: retl
|
|
;
|
|
; AVX-64-LABEL: PR15298:
|
|
; AVX-64: # %bb.0: # %L.entry
|
|
; AVX-64-NEXT: vbroadcastss 304(%rdi), %xmm0
|
|
; AVX-64-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; AVX-64-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2],ymm1[3,4,5,6,7]
|
|
; AVX-64-NEXT: vmovups %ymm0, 608(%rsi)
|
|
; AVX-64-NEXT: vzeroupper
|
|
; AVX-64-NEXT: retq
|
|
L.entry:
|
|
%0 = getelementptr inbounds <4 x float>, ptr %source, i32 19
|
|
%1 = load <4 x float>, ptr %0, align 16
|
|
%2 = extractelement <4 x float> %1, i32 0
|
|
%3 = insertelement <8 x float> <float 0.000000e+00, float undef, float undef, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00>, float %2, i32 2
|
|
%4 = insertelement <8 x float> %3, float %2, i32 1
|
|
%5 = getelementptr <8 x float>, ptr %dest, i32 19
|
|
store <8 x float> %4, ptr %5, align 4
|
|
ret void
|
|
}
|