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
4.3 KiB
LLVM
102 lines
4.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt < %s -passes='loop(loop-interchange),simplifycfg' -simplifycfg-require-and-preserve-domtree=1 \
|
|
; RUN: -pass-remarks=loop-interchange -pass-remarks-missed=loop-interchange -stats -S 2>&1 \
|
|
; RUN: | FileCheck -check-prefix=STATS %s
|
|
|
|
; no_deps_interchange just accesses a single nested array and can be interchange.
|
|
;
|
|
define i32 @no_deps_interchange(ptr nocapture %Arr) {
|
|
; STATS-LABEL: define i32 @no_deps_interchange(
|
|
; STATS-SAME: ptr captures(none) [[ARR:%.*]]) {
|
|
; STATS-NEXT: [[ENTRY:.*]]:
|
|
; STATS-NEXT: br label %[[FOR2:.*]]
|
|
; STATS: [[FOR1_HEADER:.*]]:
|
|
; STATS-NEXT: [[INDVARS_IV19:%.*]] = phi i64 [ [[INDVARS_IV_NEXT20:%.*]], %[[FOR1_HEADER]] ], [ 0, %[[FOR2]] ]
|
|
; STATS-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [1024 x i32], ptr [[ARR]], i64 [[INDVARS_IV:%.*]], i64 [[INDVARS_IV19]]
|
|
; STATS-NEXT: store i32 0, ptr [[ARRAYIDX6]], align 4
|
|
; STATS-NEXT: [[INDVARS_IV_NEXT:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 1
|
|
; STATS-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], 1024
|
|
; STATS-NEXT: [[INDVARS_IV_NEXT20]] = add nuw nsw i64 [[INDVARS_IV19]], 1
|
|
; STATS-NEXT: [[EXITCOND21:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT20]], 1024
|
|
; STATS-NEXT: br i1 [[EXITCOND21]], label %[[FOR1_HEADER]], label %[[FOR2_SPLIT:.*]]
|
|
; STATS: [[FOR2]]:
|
|
; STATS-NEXT: [[INDVARS_IV]] = phi i64 [ [[TMP0:%.*]], %[[FOR2_SPLIT]] ], [ 0, %[[ENTRY]] ]
|
|
; STATS-NEXT: br label %[[FOR1_HEADER]]
|
|
; STATS: [[FOR2_SPLIT]]:
|
|
; STATS-NEXT: [[TMP0]] = add nuw nsw i64 [[INDVARS_IV]], 1
|
|
; STATS-NEXT: [[TMP1:%.*]] = icmp ne i64 [[TMP0]], 1024
|
|
; STATS-NEXT: br i1 [[TMP1]], label %[[FOR2]], label %[[EXIT:.*]]
|
|
; STATS: [[EXIT]]:
|
|
; STATS-NEXT: ret i32 0
|
|
;
|
|
entry:
|
|
br label %for1.header
|
|
|
|
for1.header:
|
|
%indvars.iv19 = phi i64 [ 0, %entry ], [ %indvars.iv.next20, %for1.inc ]
|
|
br label %for2
|
|
|
|
for2:
|
|
%indvars.iv = phi i64 [ 0, %for1.header ], [ %indvars.iv.next, %for2 ]
|
|
%arrayidx6 = getelementptr inbounds [1024 x i32], ptr %Arr, i64 %indvars.iv, i64 %indvars.iv19
|
|
store i32 0, ptr %arrayidx6, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp ne i64 %indvars.iv.next, 1024
|
|
br i1 %exitcond, label %for2, label %for1.inc
|
|
|
|
for1.inc:
|
|
%indvars.iv.next20 = add nuw nsw i64 %indvars.iv19, 1
|
|
%exitcond21 = icmp ne i64 %indvars.iv.next20, 1024
|
|
br i1 %exitcond21, label %for1.header, label %exit
|
|
|
|
exit:
|
|
ret i32 0
|
|
|
|
}
|
|
|
|
; No memory access using any induction variables, interchanging not beneficial.
|
|
;
|
|
define i32 @no_mem_instrs(ptr %ptr) {
|
|
; STATS-LABEL: define i32 @no_mem_instrs(
|
|
; STATS-SAME: ptr [[PTR:%.*]]) {
|
|
; STATS-NEXT: [[ENTRY:.*]]:
|
|
; STATS-NEXT: br label %[[FOR1_HEADER:.*]]
|
|
; STATS: [[FOR1_HEADER]]:
|
|
; STATS-NEXT: [[INDVARS_IV19:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[INDVARS_IV_NEXT20:%.*]], %[[FOR1_INC:.*]] ]
|
|
; STATS-NEXT: br label %[[FOR2:.*]]
|
|
; STATS: [[FOR2]]:
|
|
; STATS-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, %[[FOR1_HEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[FOR2]] ]
|
|
; STATS-NEXT: store i64 [[INDVARS_IV]], ptr [[PTR]], align 4
|
|
; STATS-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
|
|
; STATS-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], 1024
|
|
; STATS-NEXT: br i1 [[EXITCOND]], label %[[FOR2]], label %[[FOR1_INC]]
|
|
; STATS: [[FOR1_INC]]:
|
|
; STATS-NEXT: [[INDVARS_IV_NEXT20]] = add nuw nsw i64 [[INDVARS_IV19]], 1
|
|
; STATS-NEXT: [[EXITCOND21:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT20]], 1024
|
|
; STATS-NEXT: br i1 [[EXITCOND21]], label %[[FOR1_HEADER]], label %[[EXIT:.*]]
|
|
; STATS: [[EXIT]]:
|
|
; STATS-NEXT: ret i32 0
|
|
;
|
|
entry:
|
|
br label %for1.header
|
|
|
|
for1.header:
|
|
%indvars.iv19 = phi i64 [ 0, %entry ], [ %indvars.iv.next20, %for1.inc ]
|
|
br label %for2
|
|
|
|
for2:
|
|
%indvars.iv = phi i64 [ 0, %for1.header ], [ %indvars.iv.next, %for2 ]
|
|
store i64 %indvars.iv, ptr %ptr, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp ne i64 %indvars.iv.next, 1024
|
|
br i1 %exitcond, label %for2, label %for1.inc
|
|
|
|
for1.inc:
|
|
%indvars.iv.next20 = add nuw nsw i64 %indvars.iv19, 1
|
|
%exitcond21 = icmp ne i64 %indvars.iv.next20, 1024
|
|
br i1 %exitcond21, label %for1.header, label %exit
|
|
|
|
exit: ; preds = %for1.inc
|
|
ret i32 0
|
|
}
|