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
128 lines
4.7 KiB
LLVM
128 lines
4.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -passes=verify,iroutliner -ir-outlining-no-cost < %s | FileCheck %s
|
|
|
|
; This test makes sure we are extracting the found similarity sections
|
|
; correctly at the call site.
|
|
|
|
define void @extract1() {
|
|
; CHECK-LABEL: @extract1(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[C:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: call void @outlined_ir_func_1(ptr [[A]], ptr [[B]], ptr [[C]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%a = alloca i32, align 4
|
|
%b = alloca i32, align 4
|
|
%c = alloca i32, align 4
|
|
store i32 2, ptr %a, align 4
|
|
store i32 3, ptr %b, align 4
|
|
store i32 4, ptr %c, align 4
|
|
%al = load i32, ptr %a
|
|
%bl = load i32, ptr %b
|
|
%cl = load i32, ptr %c
|
|
ret void
|
|
}
|
|
|
|
define void @extract2() {
|
|
; CHECK-LABEL: @extract2(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[C:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: call void @outlined_ir_func_1(ptr [[A]], ptr [[B]], ptr [[C]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%a = alloca i32, align 4
|
|
%b = alloca i32, align 4
|
|
%c = alloca i32, align 4
|
|
store i32 2, ptr %a, align 4
|
|
store i32 3, ptr %b, align 4
|
|
store i32 4, ptr %c, align 4
|
|
%al = load i32, ptr %a
|
|
%bl = load i32, ptr %b
|
|
%cl = load i32, ptr %c
|
|
ret void
|
|
}
|
|
|
|
; There are potential ouptuts in this sections, but we do not extract sections
|
|
; with outputs right now, since they cannot be consolidated.
|
|
define void @extract_outs1() #0 {
|
|
; CHECK-LABEL: @extract_outs1(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[DOTLOC:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[ADD_LOC:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[OUTPUT:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[RESULT:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: call void @llvm.lifetime.start.p0(ptr [[ADD_LOC]])
|
|
; CHECK-NEXT: call void @llvm.lifetime.start.p0(ptr [[DOTLOC]])
|
|
; CHECK-NEXT: call void @outlined_ir_func_0(ptr [[A]], ptr [[B]], ptr [[OUTPUT]], ptr [[ADD_LOC]], ptr [[DOTLOC]])
|
|
; CHECK-NEXT: [[ADD_RELOAD:%.*]] = load i32, ptr [[ADD_LOC]], align 4
|
|
; CHECK-NEXT: [[DOTRELOAD:%.*]] = load i32, ptr [[DOTLOC]], align 4
|
|
; CHECK-NEXT: call void @llvm.lifetime.end.p0(ptr [[ADD_LOC]])
|
|
; CHECK-NEXT: call void @llvm.lifetime.end.p0(ptr [[DOTLOC]])
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[OUTPUT]], align 4
|
|
; CHECK-NEXT: call void @outlined_ir_func_2(i32 [[DOTRELOAD]], i32 [[ADD_RELOAD]], ptr [[RESULT]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%a = alloca i32, align 4
|
|
%b = alloca i32, align 4
|
|
%output = alloca i32, align 4
|
|
%result = alloca i32, align 4
|
|
store i32 2, ptr %a, align 4
|
|
store i32 3, ptr %b, align 4
|
|
%0 = load i32, ptr %a, align 4
|
|
%1 = load i32, ptr %b, align 4
|
|
%add = add i32 %0, %1
|
|
store i32 %add, ptr %output, align 4
|
|
%2 = load i32, ptr %output, align 4
|
|
%3 = load i32, ptr %output, align 4
|
|
%mul = mul i32 %2, %add
|
|
store i32 %mul, ptr %result, align 4
|
|
ret void
|
|
}
|
|
|
|
; There are potential ouptuts in this sections, but we do not extract sections
|
|
; with outputs right now, since they cannot be consolidated.
|
|
define void @extract_outs2() #0 {
|
|
; CHECK-LABEL: @extract_outs2(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[DOTLOC:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[ADD_LOC:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[OUTPUT:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[RESULT:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: call void @llvm.lifetime.start.p0(ptr [[ADD_LOC]])
|
|
; CHECK-NEXT: call void @llvm.lifetime.start.p0(ptr [[DOTLOC]])
|
|
; CHECK-NEXT: call void @outlined_ir_func_0(ptr [[A]], ptr [[B]], ptr [[OUTPUT]], ptr [[ADD_LOC]], ptr [[DOTLOC]])
|
|
; CHECK-NEXT: [[ADD_RELOAD:%.*]] = load i32, ptr [[ADD_LOC]], align 4
|
|
; CHECK-NEXT: [[DOTRELOAD:%.*]] = load i32, ptr [[DOTLOC]], align 4
|
|
; CHECK-NEXT: call void @llvm.lifetime.end.p0(ptr [[ADD_LOC]])
|
|
; CHECK-NEXT: call void @llvm.lifetime.end.p0(ptr [[DOTLOC]])
|
|
; CHECK-NEXT: call void @outlined_ir_func_2(i32 [[DOTRELOAD]], i32 [[ADD_RELOAD]], ptr [[RESULT]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%a = alloca i32, align 4
|
|
%b = alloca i32, align 4
|
|
%output = alloca i32, align 4
|
|
%result = alloca i32, align 4
|
|
store i32 2, ptr %a, align 4
|
|
store i32 3, ptr %b, align 4
|
|
%0 = load i32, ptr %a, align 4
|
|
%1 = load i32, ptr %b, align 4
|
|
%add = add i32 %0, %1
|
|
store i32 %add, ptr %output, align 4
|
|
%2 = load i32, ptr %output, align 4
|
|
%mul = mul i32 %2, %add
|
|
store i32 %mul, ptr %result, align 4
|
|
ret void
|
|
}
|