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
30 lines
1.2 KiB
LLVM
30 lines
1.2 KiB
LLVM
; RUN: llc -mtriple=x86_64-- -mcpu=core-avx2 < %s | FileCheck %s
|
|
;
|
|
; Test multiple peephole-time folds in a single basic block.
|
|
; <rdar://problem/16478629>
|
|
|
|
define <8 x float> @test_peephole_multi_fold(ptr %p1, ptr %p2) {
|
|
entry:
|
|
br label %loopbody
|
|
|
|
loopbody:
|
|
; CHECK: test_peephole_multi_fold:
|
|
; CHECK: vfmadd231ps ({{%rdi|%rcx}}),
|
|
; CHECK: vfmadd231ps ({{%rsi|%rdx}}),
|
|
%vsum1 = phi <8 x float> [ %vsum1.next, %loopbody ], [ zeroinitializer, %entry ]
|
|
%vsum2 = phi <8 x float> [ %vsum2.next, %loopbody ], [ zeroinitializer, %entry ]
|
|
%m1 = load <8 x float>, ptr %p1, align 1
|
|
%m2 = load <8 x float>, ptr %p2, align 1
|
|
%vsum1.next = tail call <8 x float> @llvm.x86.fma.vfmadd.ps.256(<8 x float> %m1, <8 x float> zeroinitializer, <8 x float> %vsum1)
|
|
%vsum2.next = tail call <8 x float> @llvm.x86.fma.vfmadd.ps.256(<8 x float> %m2, <8 x float> zeroinitializer, <8 x float> %vsum2)
|
|
%vsum1.next.1 = extractelement <8 x float> %vsum1.next, i32 0
|
|
%c = fcmp oeq float %vsum1.next.1, 0.0
|
|
br i1 %c, label %loopbody, label %loopexit
|
|
|
|
loopexit:
|
|
%r = fadd <8 x float> %vsum1.next, %vsum2.next
|
|
ret <8 x float> %r
|
|
}
|
|
|
|
declare <8 x float> @llvm.x86.fma.vfmadd.ps.256(<8 x float>, <8 x float>, <8 x float>)
|