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
40 lines
1.7 KiB
LLVM
40 lines
1.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=avx512bf16,avx512fp16 | FileCheck %s
|
|
|
|
define void @test(<2 x ptr> %ptr) {
|
|
; CHECK-LABEL: test:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: testb %al, %al
|
|
; CHECK-NEXT: je .LBB0_1
|
|
; CHECK-NEXT: # %bb.2: # %loop.127.preheader
|
|
; CHECK-NEXT: retq
|
|
; CHECK-NEXT: .LBB0_1: # %ifmerge.89
|
|
; CHECK-NEXT: vbroadcastss %xmm0, %xmm0
|
|
; CHECK-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vpbroadcastw (%rax), %xmm2
|
|
; CHECK-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
|
; CHECK-NEXT: vmulps %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vmovlps %xmm0, (%rax)
|
|
entry:
|
|
br label %then.13
|
|
|
|
then.13: ; preds = %entry
|
|
%0 = fpext bfloat poison to float
|
|
br i1 poison, label %loop.127.preheader, label %ifmerge.89
|
|
|
|
ifmerge.89: ; preds = %then.13
|
|
%.splatinsert144 = insertelement <2 x float> poison, float %0, i64 0
|
|
%.splat145 = shufflevector <2 x float> %.splatinsert144, <2 x float> poison, <2 x i32> zeroinitializer
|
|
%1 = tail call <2 x bfloat> @llvm.masked.gather.v2bf16.v2p0(<2 x ptr> undef, i32 2, <2 x i1> <i1 true, i1 true>, <2 x bfloat> poison)
|
|
%2 = fpext <2 x bfloat> %1 to <2 x float>
|
|
%3 = fmul fast <2 x float> %.splat145, %2
|
|
%4 = fadd fast <2 x float> zeroinitializer, %3
|
|
store <2 x float> %4, ptr poison, align 4
|
|
unreachable
|
|
|
|
loop.127.preheader: ; preds = %then.13
|
|
ret void
|
|
}
|
|
|
|
declare <2 x bfloat> @llvm.masked.gather.v2bf16.v2p0(<2 x ptr>, i32 immarg, <2 x i1>, <2 x bfloat>)
|