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
137 lines
4.5 KiB
LLVM
137 lines
4.5 KiB
LLVM
; RUN: opt -passes=loop-distribute -enable-loop-distribute=0 -S < %s | FileCheck %s --check-prefix=CHECK --check-prefix=EXPLICIT --check-prefix=DEFAULT_OFF
|
|
; RUN: opt -passes=loop-distribute -enable-loop-distribute=1 -S < %s | FileCheck %s --check-prefix=CHECK --check-prefix=EXPLICIT --check-prefix=DEFAULT_ON
|
|
|
|
; Same loop as in basic.ll. Check that distribution is enabled/disabled
|
|
; properly according to -enable-loop-distribute=0/1 and the
|
|
; llvm.loop.distribute.enable metadata.
|
|
|
|
define void @explicit_on(ptr noalias %a, ptr noalias %b, ptr noalias %c, ptr noalias %d, ptr noalias %e) {
|
|
; CHECK-LABEL: @explicit_on(
|
|
entry:
|
|
br label %for.body
|
|
|
|
; EXPLICIT: for.body.ldist1:
|
|
for.body: ; preds = %for.body, %entry
|
|
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
|
|
|
|
%arrayidxA = getelementptr inbounds i32, ptr %a, i64 %ind
|
|
%loadA = load i32, ptr %arrayidxA, align 4
|
|
|
|
%arrayidxB = getelementptr inbounds i32, ptr %b, i64 %ind
|
|
%loadB = load i32, ptr %arrayidxB, align 4
|
|
|
|
%mulA = mul i32 %loadB, %loadA
|
|
|
|
%add = add nuw nsw i64 %ind, 1
|
|
%arrayidxA_plus_4 = getelementptr inbounds i32, ptr %a, i64 %add
|
|
store i32 %mulA, ptr %arrayidxA_plus_4, align 4
|
|
|
|
%arrayidxD = getelementptr inbounds i32, ptr %d, i64 %ind
|
|
%loadD = load i32, ptr %arrayidxD, align 4
|
|
|
|
%arrayidxE = getelementptr inbounds i32, ptr %e, i64 %ind
|
|
%loadE = load i32, ptr %arrayidxE, align 4
|
|
|
|
%mulC = mul i32 %loadD, %loadE
|
|
|
|
%arrayidxC = getelementptr inbounds i32, ptr %c, i64 %ind
|
|
store i32 %mulC, ptr %arrayidxC, align 4
|
|
|
|
%exitcond = icmp eq i64 %add, 20
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: @explicit_off(
|
|
define void @explicit_off(ptr noalias %a,
|
|
ptr noalias %b,
|
|
ptr noalias %c,
|
|
ptr noalias %d,
|
|
ptr noalias %e) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
; EXPLICIT-NOT: for.body.ldist1:
|
|
for.body: ; preds = %for.body, %entry
|
|
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
|
|
|
|
%arrayidxA = getelementptr inbounds i32, ptr %a, i64 %ind
|
|
%loadA = load i32, ptr %arrayidxA, align 4
|
|
|
|
%arrayidxB = getelementptr inbounds i32, ptr %b, i64 %ind
|
|
%loadB = load i32, ptr %arrayidxB, align 4
|
|
|
|
%mulA = mul i32 %loadB, %loadA
|
|
|
|
%add = add nuw nsw i64 %ind, 1
|
|
%arrayidxA_plus_4 = getelementptr inbounds i32, ptr %a, i64 %add
|
|
store i32 %mulA, ptr %arrayidxA_plus_4, align 4
|
|
|
|
%arrayidxD = getelementptr inbounds i32, ptr %d, i64 %ind
|
|
%loadD = load i32, ptr %arrayidxD, align 4
|
|
|
|
%arrayidxE = getelementptr inbounds i32, ptr %e, i64 %ind
|
|
%loadE = load i32, ptr %arrayidxE, align 4
|
|
|
|
%mulC = mul i32 %loadD, %loadE
|
|
|
|
%arrayidxC = getelementptr inbounds i32, ptr %c, i64 %ind
|
|
store i32 %mulC, ptr %arrayidxC, align 4
|
|
|
|
%exitcond = icmp eq i64 %add, 20
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !2
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
define void @default_distribute(ptr noalias %a, ptr noalias %b, ptr noalias %c, ptr noalias %d,
|
|
ptr noalias %e) {
|
|
; CHECK-LABEL: @default_distribute(
|
|
entry:
|
|
br label %for.body
|
|
|
|
; Verify the two distributed loops.
|
|
|
|
; DEFAULT_ON: for.body.ldist1:
|
|
; DEFAULT_OFF-NOT: for.body.ldist1:
|
|
for.body: ; preds = %for.body, %entry
|
|
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
|
|
|
|
%arrayidxA = getelementptr inbounds i32, ptr %a, i64 %ind
|
|
%loadA = load i32, ptr %arrayidxA, align 4
|
|
|
|
%arrayidxB = getelementptr inbounds i32, ptr %b, i64 %ind
|
|
%loadB = load i32, ptr %arrayidxB, align 4
|
|
|
|
%mulA = mul i32 %loadB, %loadA
|
|
|
|
%add = add nuw nsw i64 %ind, 1
|
|
%arrayidxA_plus_4 = getelementptr inbounds i32, ptr %a, i64 %add
|
|
store i32 %mulA, ptr %arrayidxA_plus_4, align 4
|
|
|
|
%arrayidxD = getelementptr inbounds i32, ptr %d, i64 %ind
|
|
%loadD = load i32, ptr %arrayidxD, align 4
|
|
|
|
%arrayidxE = getelementptr inbounds i32, ptr %e, i64 %ind
|
|
%loadE = load i32, ptr %arrayidxE, align 4
|
|
|
|
%mulC = mul i32 %loadD, %loadE
|
|
|
|
%arrayidxC = getelementptr inbounds i32, ptr %c, i64 %ind
|
|
store i32 %mulC, ptr %arrayidxC, align 4
|
|
|
|
%exitcond = icmp eq i64 %add, 20
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|
|
|
|
!0 = distinct !{!0, !1}
|
|
!1 = !{!"llvm.loop.distribute.enable", i1 true}
|
|
!2 = distinct !{!2, !3}
|
|
!3 = !{!"llvm.loop.distribute.enable", i1 false}
|