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
34 lines
1.3 KiB
LLVM
34 lines
1.3 KiB
LLVM
; RUN: llc -mtriple=i686-unknown-unknown -mattr=+sse4.1 < %s | FileCheck %s -check-prefix=X32
|
|
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 < %s | FileCheck %s -check-prefix=X64
|
|
|
|
; Test for case where insertps was folding the load of the insertion element, but a later optimization
|
|
; was then manipulating the load.
|
|
|
|
define <4 x float> @insertps_unfold(ptr %v0, ptr %v1) {
|
|
; X32-LABEL: insertps_unfold:
|
|
; X32: # %bb.0:
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
|
|
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
|
|
; X32-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; X32-NEXT: movaps (%eax), %xmm0
|
|
; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
|
|
; X32-NEXT: addps %xmm1, %xmm0
|
|
; X32-NEXT: retl
|
|
;
|
|
; X64-LABEL: insertps_unfold:
|
|
; X64: # %bb.0:
|
|
; X64-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
|
; X64-NEXT: movaps (%rdi), %xmm0
|
|
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
|
|
; X64-NEXT: addps %xmm1, %xmm0
|
|
; X64-NEXT: retq
|
|
%a = getelementptr inbounds <4 x float>, ptr %v1, i64 0, i64 1
|
|
%b = load float, ptr %a, align 4
|
|
%c = insertelement <4 x float> undef, float %b, i32 0
|
|
%d = load <4 x float>, ptr %v1, align 16
|
|
%e = load <4 x float>, ptr %v0, align 16
|
|
%f = shufflevector <4 x float> %e, <4 x float> %d, <4 x i32> <i32 0, i32 1, i32 2, i32 5>
|
|
%g = fadd <4 x float> %c, %f
|
|
ret <4 x float> %g
|
|
}
|