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
92 lines
3.1 KiB
LLVM
92 lines
3.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
|
|
; RUN: opt -aa-pipeline=basic-aa -passes='require<aa>,require<target-ir>,require<scalar-evolution>,require<opt-remark-emit>,loop-mssa(licm)' < %s -S | FileCheck %s
|
|
|
|
; We should be able to hoist loads in presence of read only calls and stores
|
|
; that do not alias.
|
|
|
|
; Since LICM uses the AST mechanism for alias analysis, we will clump
|
|
; together all loads and stores in one set along with the read-only call.
|
|
; This prevents hoisting load that doesn't alias with any other memory
|
|
; operations.
|
|
|
|
declare void @foo(i64, ptr) readonly
|
|
|
|
; hoist the load out with the n2-threshold
|
|
; since it doesn't alias with the store.
|
|
; default AST mechanism clumps all memory locations in one set because of the
|
|
; readonly call
|
|
define void @test1(ptr %ptr) {
|
|
; CHECK-LABEL: define void @test1(
|
|
; CHECK-SAME: ptr [[PTR:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*]]:
|
|
; CHECK-NEXT: [[VAL:%.*]] = load i32, ptr [[PTR]], align 4
|
|
; CHECK-NEXT: [[P2:%.*]] = getelementptr i32, ptr [[PTR]], i32 1
|
|
; CHECK-NEXT: br label %[[LOOP:.*]]
|
|
; CHECK: [[LOOP]]:
|
|
; CHECK-NEXT: [[X:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[X_INC:%.*]], %[[LOOP]] ]
|
|
; CHECK-NEXT: call void @foo(i64 4, ptr [[PTR]])
|
|
; CHECK-NEXT: store volatile i32 0, ptr [[P2]], align 4
|
|
; CHECK-NEXT: [[X_INC]] = add i32 [[X]], [[VAL]]
|
|
; CHECK-NEXT: br label %[[LOOP]]
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%x = phi i32 [ 0, %entry ], [ %x.inc, %loop ]
|
|
%val = load i32, ptr %ptr
|
|
call void @foo(i64 4, ptr %ptr)
|
|
%p2 = getelementptr i32, ptr %ptr, i32 1
|
|
store volatile i32 0, ptr %p2
|
|
%x.inc = add i32 %x, %val
|
|
br label %loop
|
|
}
|
|
|
|
; can hoist out load with the default AST and the alias analysis mechanism.
|
|
define void @test2(ptr %ptr) {
|
|
; CHECK-LABEL: define void @test2(
|
|
; CHECK-SAME: ptr [[PTR:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*]]:
|
|
; CHECK-NEXT: [[VAL:%.*]] = load i32, ptr [[PTR]], align 4
|
|
; CHECK-NEXT: br label %[[LOOP:.*]]
|
|
; CHECK: [[LOOP]]:
|
|
; CHECK-NEXT: [[X:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[X_INC:%.*]], %[[LOOP]] ]
|
|
; CHECK-NEXT: call void @foo(i64 4, ptr [[PTR]])
|
|
; CHECK-NEXT: [[X_INC]] = add i32 [[X]], [[VAL]]
|
|
; CHECK-NEXT: br label %[[LOOP]]
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%x = phi i32 [ 0, %entry ], [ %x.inc, %loop ]
|
|
%val = load i32, ptr %ptr
|
|
call void @foo(i64 4, ptr %ptr)
|
|
%x.inc = add i32 %x, %val
|
|
br label %loop
|
|
}
|
|
|
|
; cannot hoist load since not guaranteed to execute
|
|
define void @test3(ptr %ptr) {
|
|
; CHECK-LABEL: define void @test3(
|
|
; CHECK-SAME: ptr [[PTR:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*]]:
|
|
; CHECK-NEXT: br label %[[LOOP:.*]]
|
|
; CHECK: [[LOOP]]:
|
|
; CHECK-NEXT: [[X:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[X_INC:%.*]], %[[LOOP]] ]
|
|
; CHECK-NEXT: call void @foo(i64 4, ptr [[PTR]])
|
|
; CHECK-NEXT: [[VAL:%.*]] = load i32, ptr [[PTR]], align 4
|
|
; CHECK-NEXT: [[X_INC]] = add i32 [[X]], [[VAL]]
|
|
; CHECK-NEXT: br label %[[LOOP]]
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%x = phi i32 [ 0, %entry ], [ %x.inc, %loop ]
|
|
call void @foo(i64 4, ptr %ptr)
|
|
%val = load i32, ptr %ptr
|
|
%x.inc = add i32 %x, %val
|
|
br label %loop
|
|
}
|