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
61 lines
2.0 KiB
LLVM
61 lines
2.0 KiB
LLVM
; RUN: llc -mtriple=x86_64-pc-linux-gnu -mattr=+sse4.2 < %s | FileCheck %s
|
|
|
|
; CHECK-LABEL: testss:
|
|
; CHECK: movss {{.*}}, %[[XMM0:xmm[0-9]+]]
|
|
; CHECK: xorps %[[XMM1:xmm[0-9]+]], %[[XMM1]]
|
|
; CHECK: roundss $9, %[[XMM0]], %[[XMM1]]
|
|
|
|
define void @testss(ptr nocapture %a, ptr nocapture %b, i32 %k) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds float, ptr %a, i64 %indvars.iv
|
|
%v = load float, ptr %arrayidx, align 4
|
|
%floor = call float @llvm.floor.f32(float %v)
|
|
%sub = fsub float %floor, %v
|
|
%v1 = insertelement <4 x float> undef, float %sub, i32 0
|
|
%br = shufflevector <4 x float> %v1, <4 x float> undef, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
|
|
store volatile <4 x float> %br, ptr %b, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %k
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: testsd:
|
|
; CHECK: movsd {{.*}}, %[[XMM0:xmm[0-9]+]]
|
|
; CHECK: xorps %[[XMM1:xmm[0-9]+]], %[[XMM1]]
|
|
; CHECK: roundsd $9, %[[XMM0]], %[[XMM1]]
|
|
|
|
define void @testsd(ptr nocapture %a, ptr nocapture %b, i32 %k) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds double, ptr %a, i64 %indvars.iv
|
|
%v = load double, ptr %arrayidx, align 4
|
|
%floor = call double @llvm.floor.f64(double %v)
|
|
%sub = fsub double %floor, %v
|
|
%v1 = insertelement <2 x double> undef, double %sub, i32 0
|
|
%br = shufflevector <2 x double> %v1, <2 x double> undef, <2 x i32> <i32 0, i32 0>
|
|
store volatile <2 x double> %br, ptr %b, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %k
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.floor.f32(float) nounwind readnone
|
|
|
|
declare double @llvm.floor.f64(double) nounwind readnone
|
|
|