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
102 lines
3.2 KiB
LLVM
102 lines
3.2 KiB
LLVM
; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=1 -force-target-supports-scalable-vectors=true -S | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
|
|
; CHECK-LABEL: @test1(
|
|
; CHECK: store <8 x i32>
|
|
; CHECK: ret void
|
|
define void @test1(ptr nocapture %a, i32 %n) #0 {
|
|
entry:
|
|
%cmp4 = icmp sgt i32 %n, 0
|
|
br i1 %cmp4, label %for.body, label %for.end
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
|
|
store i32 42, ptr %arrayidx, 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, %n
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: @test2(
|
|
; CHECK: store <vscale x 8 x i32>
|
|
; CHECK: ret void
|
|
define void @test2(ptr nocapture %a, i32 %n) #0 {
|
|
entry:
|
|
%cmp4 = icmp sgt i32 %n, 0
|
|
br i1 %cmp4, label %for.body, label %for.end
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
|
|
store i32 42, ptr %arrayidx, 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, %n
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !2
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: @test3(
|
|
; CHECK: store <8 x i32>
|
|
; CHECK: ret void
|
|
define void @test3(ptr nocapture %a, i32 %n) #0 {
|
|
entry:
|
|
%cmp4 = icmp sgt i32 %n, 0
|
|
br i1 %cmp4, label %for.body, label %for.end
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
|
|
store i32 42, ptr %arrayidx, 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, %n
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !4
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
; Test that when only the width property is specified, and not the scalable.enable flag,
|
|
; that the hint defaults to 'scalable.enable = false'.
|
|
|
|
; CHECK-LABEL: @test4(
|
|
; CHECK: store <8 x i32>
|
|
; CHECK: ret void
|
|
define void @test4(ptr nocapture %a, i32 %n) #0 {
|
|
entry:
|
|
%cmp4 = icmp sgt i32 %n, 0
|
|
br i1 %cmp4, label %for.body, label %for.end
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
|
|
store i32 42, ptr %arrayidx, 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, %n
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !6
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "less-precise-fpmad"="false" "frame-pointer"="none" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "use-soft-float"="false" }
|
|
|
|
!0 = !{!0, !1, !5}
|
|
!1 = !{!"llvm.loop.vectorize.width", i32 8}
|
|
!2 = !{!2, !1, !3}
|
|
!3 = !{!"llvm.loop.vectorize.scalable.enable", i32 1}
|
|
!4 = !{!4, !1, !5}
|
|
!5 = !{!"llvm.loop.vectorize.scalable.enable", i32 0}
|
|
!6 = !{!6, !7}
|
|
!7 = !{!"llvm.loop.vectorize.width", i32 8}
|