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
99 lines
4.5 KiB
LLVM
99 lines
4.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
|
|
; RUN: opt < %s -passes=loop-interchange -cache-line-size=64 -verify-dom-info -verify-loop-info -verify-scev -verify-loop-lcssa -loop-interchange-threshold=0 -S 2>&1 | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
|
|
|
|
; Checks the order of the inner phi nodes does not cause havoc.
|
|
; The inner loop has a reduction into C. The IV is not the first phi.
|
|
;
|
|
; for (i = 0; i < 90; i++)
|
|
; for (j = 0; j < 90; j++) {
|
|
; red = C[i][j];
|
|
; for (k = 1; k < 90; k++) {
|
|
; red += A[i][k];
|
|
; }
|
|
; C[i][j] = red;
|
|
; }
|
|
|
|
; Function Attrs: norecurse nounwind
|
|
define void @test(i32 %T, ptr noalias nocapture %C, ptr noalias nocapture readonly %A, ptr noalias nocapture readonly %B) local_unnamed_addr #0 {
|
|
; CHECK-LABEL: define void @test(
|
|
; CHECK-SAME: i32 [[T:%.*]], ptr noalias captures(none) [[C:%.*]], ptr noalias readonly captures(none) [[A:%.*]], ptr noalias readonly captures(none) [[B:%.*]]) local_unnamed_addr {
|
|
; CHECK-NEXT: [[ENTRY:.*]]:
|
|
; CHECK-NEXT: br label %[[FOR1_HEADER:.*]]
|
|
; CHECK: [[FOR1_HEADER]]:
|
|
; CHECK-NEXT: [[I:%.*]] = phi i32 [ [[INC20:%.*]], %[[FOR1_INC19:.*]] ], [ 0, %[[ENTRY]] ]
|
|
; CHECK-NEXT: br label %[[FOR2_HEADER:.*]]
|
|
; CHECK: [[FOR2_HEADER]]:
|
|
; CHECK-NEXT: [[J:%.*]] = phi i32 [ 0, %[[FOR1_HEADER]] ], [ [[INC17:%.*]], %[[FOR2_INC16:.*]] ]
|
|
; CHECK-NEXT: [[GEP_C:%.*]] = getelementptr inbounds [90 x i32], ptr [[C]], i32 [[I]], i32 [[J]]
|
|
; CHECK-NEXT: [[RED_INIT:%.*]] = load i32, ptr [[GEP_C]], align 4
|
|
; CHECK-NEXT: br label %[[FOR3:.*]]
|
|
; CHECK: [[FOR3]]:
|
|
; CHECK-NEXT: [[RED:%.*]] = phi i32 [ [[RED_INIT]], %[[FOR2_HEADER]] ], [ [[ADD15:%.*]], %[[FOR3]] ]
|
|
; CHECK-NEXT: [[K:%.*]] = phi i32 [ 1, %[[FOR2_HEADER]] ], [ [[INC:%.*]], %[[FOR3]] ]
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [90 x i16], ptr [[A]], i32 [[I]], i32 [[K]]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load i16, ptr [[ARRAYIDX]], align 2
|
|
; CHECK-NEXT: [[CONV:%.*]] = sext i16 [[TMP0]] to i32
|
|
; CHECK-NEXT: [[ADD15]] = add nsw i32 [[CONV]], [[RED]]
|
|
; CHECK-NEXT: [[INC]] = add nuw nsw i32 [[K]], 1
|
|
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[INC]], 90
|
|
; CHECK-NEXT: br i1 [[EXITCOND]], label %[[FOR2_INC16]], label %[[FOR3]]
|
|
; CHECK: [[FOR2_INC16]]:
|
|
; CHECK-NEXT: [[RED_LCSSA:%.*]] = phi i32 [ [[RED]], %[[FOR3]] ]
|
|
; CHECK-NEXT: store i32 [[RED_LCSSA]], ptr [[GEP_C]], align 4
|
|
; CHECK-NEXT: [[INC17]] = add nuw nsw i32 [[J]], 1
|
|
; CHECK-NEXT: [[EXITCOND47:%.*]] = icmp eq i32 [[INC17]], 90
|
|
; CHECK-NEXT: br i1 [[EXITCOND47]], label %[[FOR1_INC19]], label %[[FOR2_HEADER]]
|
|
; CHECK: [[FOR1_INC19]]:
|
|
; CHECK-NEXT: [[INC20]] = add nuw nsw i32 [[I]], 1
|
|
; CHECK-NEXT: [[EXITCOND48:%.*]] = icmp eq i32 [[INC20]], 90
|
|
; CHECK-NEXT: br i1 [[EXITCOND48]], label %[[FOR1_LOOPEXIT:.*]], label %[[FOR1_HEADER]]
|
|
; CHECK: [[FOR1_LOOPEXIT]]:
|
|
; CHECK-NEXT: br label %[[EXIT:.*]]
|
|
; CHECK: [[EXIT]]:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %for1.header
|
|
|
|
for1.header: ; preds = %entry
|
|
%i = phi i32 [ %inc20, %for1.inc19 ], [ 0, %entry ]
|
|
br label %for2.header
|
|
|
|
for2.header: ; preds = %for2.inc16, %for1.header
|
|
%j = phi i32 [ 0, %for1.header ], [ %inc17, %for2.inc16 ]
|
|
%gep.c = getelementptr inbounds [90 x i32], ptr %C, i32 %i, i32 %j
|
|
%red.init = load i32, ptr %gep.c
|
|
br label %for3
|
|
|
|
for3: ; preds = %for3, %for2.header
|
|
%red = phi i32 [ %red.init, %for2.header ], [ %add15, %for3 ]
|
|
%k = phi i32 [ 1, %for2.header ], [ %inc, %for3 ]
|
|
%arrayidx = getelementptr inbounds [90 x i16], ptr %A, i32 %i, i32 %k
|
|
%0 = load i16, ptr %arrayidx, align 2
|
|
%conv = sext i16 %0 to i32
|
|
%add15 = add nsw i32 %conv, %red
|
|
%inc = add nuw nsw i32 %k, 1
|
|
%exitcond = icmp eq i32 %inc, 90
|
|
br i1 %exitcond, label %for2.inc16, label %for3
|
|
|
|
for2.inc16: ; preds = %for.body6
|
|
%red.lcssa = phi i32 [ %red, %for3 ]
|
|
store i32 %red.lcssa, ptr %gep.c
|
|
%inc17 = add nuw nsw i32 %j, 1
|
|
%exitcond47 = icmp eq i32 %inc17, 90
|
|
br i1 %exitcond47, label %for1.inc19, label %for2.header
|
|
|
|
for1.inc19: ; preds = %for2.inc16
|
|
%inc20 = add nuw nsw i32 %i, 1
|
|
%exitcond48 = icmp eq i32 %inc20, 90
|
|
br i1 %exitcond48, label %for1.loopexit, label %for1.header
|
|
|
|
for1.loopexit: ; preds = %for1.inc19
|
|
br label %exit
|
|
|
|
exit: ; preds = %for1.loopexit
|
|
ret void
|
|
}
|