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
101 lines
4.1 KiB
LLVM
101 lines
4.1 KiB
LLVM
; Remove 'S' Scalar Dependencies #119345
|
|
; Scalar dependencies are not handled correctly, so they were removed to avoid
|
|
; miscompiles. The loop nest in this test case used to be interchanged, but it's
|
|
; no longer triggering. XFAIL'ing this test to indicate that this test should
|
|
; interchanged if scalar deps are handled correctly.
|
|
;
|
|
; XFAIL: *
|
|
|
|
; RUN: opt < %s -passes=loop-interchange -cache-line-size=64 -verify-dom-info -verify-loop-info -pass-remarks-output=%t -disable-output
|
|
; RUN: FileCheck -input-file %t %s
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
|
|
@A = common global [100 x [100 x i32]] zeroinitializer
|
|
@B = common global [100 x i32] zeroinitializer
|
|
@C = common global [100 x [100 x i32]] zeroinitializer
|
|
@D = common global [100 x [100 x [100 x i32]]] zeroinitializer
|
|
@T = internal global [100 x double] zeroinitializer, align 4
|
|
@Arr = internal global [1000 x [1000 x i32]] zeroinitializer, align 4
|
|
|
|
; Test that a flow dependency in outer loop doesn't prevent interchange in
|
|
; loops i and j.
|
|
;
|
|
; for (int k = 0; k < 100; ++k) {
|
|
; T[k] = fn1();
|
|
; for (int i = 0; i < 1000; ++i)
|
|
; for(int j = 1; j < 1000; ++j)
|
|
; Arr[j][i] = Arr[j][i]+k;
|
|
; fn2(T[k]);
|
|
; }
|
|
;
|
|
; So, loops InnerLoopId = 2 and OuterLoopId = 1 should be interchanged,
|
|
; but not InnerLoopId = 1 and OuterLoopId = 0.
|
|
;
|
|
; CHECK: --- !Passed
|
|
; CHECK-NEXT: Pass: loop-interchange
|
|
; CHECK-NEXT: Name: Interchanged
|
|
; CHECK-NEXT: Function: interchange_09
|
|
; CHECK-NEXT: Args:
|
|
; CHECK-NEXT: - String: Loop interchanged with enclosing loop.
|
|
; CHECK-NEXT: ...
|
|
; CHECK-NEXT: --- !Missed
|
|
; CHECK-NEXT: Pass: loop-interchange
|
|
; CHECK-NEXT: Name: NotTightlyNested
|
|
; CHECK-NEXT: Function: interchange_09
|
|
; CHECK-NEXT: Args:
|
|
; CHECK-NEXT: - String: Cannot interchange loops because they are not tightly nested.
|
|
; CHECK-NEXT: ...
|
|
; CHECK-NEXT: --- !Missed
|
|
; CHECK-NEXT: Pass: loop-interchange
|
|
; CHECK-NEXT: Name: InterchangeNotProfitable
|
|
; CHECK-NEXT: Function: interchange_09
|
|
; CHECK-NEXT: Args:
|
|
; CHECK-NEXT: - String: Interchanging loops is not considered to improve cache locality nor vectorization.
|
|
; CHECK-NEXT: ...
|
|
|
|
define void @interchange_09(i32 %k) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.cond.cleanup: ; preds = %for.cond.cleanup4
|
|
ret void
|
|
|
|
for.body: ; preds = %for.cond.cleanup4, %entry
|
|
%indvars.iv45 = phi i64 [ 0, %entry ], [ %indvars.iv.next46, %for.cond.cleanup4 ]
|
|
%call = call double @fn1()
|
|
%arrayidx = getelementptr inbounds [100 x double], ptr @T, i64 0, i64 %indvars.iv45
|
|
store double %call, ptr %arrayidx, align 8
|
|
br label %for.cond6.preheader
|
|
|
|
for.cond6.preheader: ; preds = %for.cond.cleanup8, %for.body
|
|
%indvars.iv42 = phi i64 [ 0, %for.body ], [ %indvars.iv.next43, %for.cond.cleanup8 ]
|
|
br label %for.body9
|
|
|
|
for.cond.cleanup4: ; preds = %for.cond.cleanup8
|
|
%tmp = load double, ptr %arrayidx, align 8
|
|
call void @fn2(double %tmp)
|
|
%indvars.iv.next46 = add nuw nsw i64 %indvars.iv45, 1
|
|
%exitcond47 = icmp ne i64 %indvars.iv.next46, 100
|
|
br i1 %exitcond47, label %for.body, label %for.cond.cleanup
|
|
|
|
for.cond.cleanup8: ; preds = %for.body9
|
|
%indvars.iv.next43 = add nuw nsw i64 %indvars.iv42, 1
|
|
%exitcond44 = icmp ne i64 %indvars.iv.next43, 1000
|
|
br i1 %exitcond44, label %for.cond6.preheader, label %for.cond.cleanup4
|
|
|
|
for.body9: ; preds = %for.body9, %for.cond6.preheader
|
|
%indvars.iv = phi i64 [ 1, %for.cond6.preheader ], [ %indvars.iv.next, %for.body9 ]
|
|
%arrayidx13 = getelementptr inbounds [1000 x [1000 x i32]], ptr @Arr, i64 0, i64 %indvars.iv, i64 %indvars.iv42
|
|
%t1 = load i32, ptr %arrayidx13, align 4
|
|
%t2 = trunc i64 %indvars.iv45 to i32
|
|
%add = add nsw i32 %t1, %t2
|
|
store i32 %add, ptr %arrayidx13, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp ne i64 %indvars.iv.next, 1000
|
|
br i1 %exitcond, label %for.body9, label %for.cond.cleanup8
|
|
}
|
|
|
|
declare double @fn1() readnone
|
|
declare void @fn2(double) readnone
|