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
62 lines
2.4 KiB
LLVM
62 lines
2.4 KiB
LLVM
; RUN: opt -passes='print<access-info>' -disable-output < %s 2>&1 | FileCheck %s
|
|
|
|
; Test to confirm LAA will find multiple stores to an invariant address in the
|
|
; inner loop.
|
|
;
|
|
; for(; i < itr; i++) {
|
|
; for(; j < itr; j++) {
|
|
; var1[i] = var2[j] + var1[i];
|
|
; var1[i]++;
|
|
; }
|
|
; }
|
|
|
|
; The LAA with the new PM is a loop pass so we go from inner to outer loops.
|
|
|
|
; CHECK: for.body3:
|
|
; CHECK: Non vectorizable stores to invariant address were found in loop.
|
|
; CHECK: for.cond1.preheader:
|
|
; CHECK: Non vectorizable stores to invariant address were not found in loop.
|
|
|
|
define i32 @foo(ptr nocapture %var1, ptr nocapture readonly %var2, i32 %itr) #0 {
|
|
entry:
|
|
%cmp20 = icmp eq i32 %itr, 0
|
|
br i1 %cmp20, label %for.end10, label %for.cond1.preheader
|
|
|
|
for.cond1.preheader: ; preds = %entry, %for.inc8
|
|
%indvars.iv23 = phi i64 [ %indvars.iv.next24, %for.inc8 ], [ 0, %entry ]
|
|
%j.022 = phi i32 [ %j.1.lcssa, %for.inc8 ], [ 0, %entry ]
|
|
%cmp218 = icmp ult i32 %j.022, %itr
|
|
br i1 %cmp218, label %for.body3.lr.ph, label %for.inc8
|
|
|
|
for.body3.lr.ph: ; preds = %for.cond1.preheader
|
|
%arrayidx5 = getelementptr inbounds i32, ptr %var1, i64 %indvars.iv23
|
|
%0 = zext i32 %j.022 to i64
|
|
br label %for.body3
|
|
|
|
for.body3: ; preds = %for.body3, %for.body3.lr.ph
|
|
%indvars.iv = phi i64 [ %0, %for.body3.lr.ph ], [ %indvars.iv.next, %for.body3 ]
|
|
%arrayidx = getelementptr inbounds i32, ptr %var2, i64 %indvars.iv
|
|
%1 = load i32, ptr %arrayidx, align 4
|
|
%2 = load i32, ptr %arrayidx5, align 4
|
|
%add = add nsw i32 %2, %1
|
|
store i32 %add, ptr %arrayidx5, align 4
|
|
%3 = load i32, ptr %arrayidx5, align 4
|
|
%4 = add nsw i32 %3, 1
|
|
store i32 %4, ptr %arrayidx5, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %itr
|
|
br i1 %exitcond, label %for.inc8, label %for.body3
|
|
|
|
for.inc8: ; preds = %for.body3, %for.cond1.preheader
|
|
%j.1.lcssa = phi i32 [ %j.022, %for.cond1.preheader ], [ %itr, %for.body3 ]
|
|
%indvars.iv.next24 = add nuw nsw i64 %indvars.iv23, 1
|
|
%lftr.wideiv25 = trunc i64 %indvars.iv.next24 to i32
|
|
%exitcond26 = icmp eq i32 %lftr.wideiv25, %itr
|
|
br i1 %exitcond26, label %for.end10, label %for.cond1.preheader
|
|
|
|
for.end10: ; preds = %for.inc8, %entry
|
|
ret i32 undef
|
|
}
|
|
|