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
188 lines
7.0 KiB
LLVM
188 lines
7.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -passes=verify,iroutliner < %s | FileCheck %s
|
|
; RUN: opt -S -passes=verify,iroutliner -ir-outlining-no-cost < %s | FileCheck %s -check-prefix=NOCOST
|
|
|
|
; This test checks that we have different results from when the cost model
|
|
; is on versus when it is off. That is, if the number of instructions needed to
|
|
; handle the arguments is greater than the number of instructions being added,
|
|
; we do not outline.
|
|
|
|
define void @function1() #0 {
|
|
; CHECK-LABEL: @function1(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: call void @outlined_ir_func_0(ptr [[A]], ptr [[B]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
; NOCOST-LABEL: @function1(
|
|
; NOCOST-NEXT: entry:
|
|
; NOCOST-NEXT: [[A:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: [[B:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: call void @outlined_ir_func_0(ptr [[A]], ptr [[B]])
|
|
; NOCOST-NEXT: ret void
|
|
;
|
|
entry:
|
|
%a = alloca i32, align 4
|
|
%b = alloca i32, align 4
|
|
%0 = load i32, ptr %a, align 4
|
|
%1 = load i32, ptr %b, align 4
|
|
%add = add i32 %0, %1
|
|
%mul = mul i32 %0, %1
|
|
%sub = sub i32 %0, %1
|
|
%div = sdiv i32 %0, %1
|
|
%add1 = add i32 %0, %1
|
|
%mul1 = mul i32 %0, %1
|
|
%sub1 = sub i32 %0, %1
|
|
%div1 = sdiv i32 %0, %1
|
|
%add2 = add i32 %0, %1
|
|
%mul2 = mul i32 %0, %1
|
|
%sub2 = sub i32 %0, %1
|
|
%div2 = sdiv i32 %0, %1
|
|
ret void
|
|
}
|
|
|
|
define void @function2() #0 {
|
|
; CHECK-LABEL: @function2(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
|
|
; CHECK-NEXT: call void @outlined_ir_func_0(ptr [[A]], ptr [[B]])
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
; NOCOST-LABEL: @function2(
|
|
; NOCOST-NEXT: entry:
|
|
; NOCOST-NEXT: [[A:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: [[B:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: call void @outlined_ir_func_0(ptr [[A]], ptr [[B]])
|
|
; NOCOST-NEXT: ret void
|
|
;
|
|
entry:
|
|
%a = alloca i32, align 4
|
|
%b = alloca i32, align 4
|
|
%0 = load i32, ptr %a, align 4
|
|
%1 = load i32, ptr %b, align 4
|
|
%add = add i32 %0, %1
|
|
%mul = mul i32 %0, %1
|
|
%sub = sub i32 %0, %1
|
|
%div = sdiv i32 %0, %1
|
|
%add1 = add i32 %0, %1
|
|
%mul1 = mul i32 %0, %1
|
|
%sub1 = sub i32 %0, %1
|
|
%div1 = sdiv i32 %0, %1
|
|
%add2 = add i32 %0, %1
|
|
%mul2 = mul i32 %0, %1
|
|
%sub2 = sub i32 %0, %1
|
|
%div2 = sdiv i32 %0, %1
|
|
ret void
|
|
}
|
|
|
|
define void @function3() #0 {
|
|
; CHECK-LABEL: @function3(
|
|
; CHECK-NEXT: entry:
|
|
; 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: store i32 2, ptr [[A]], align 4
|
|
; CHECK-NEXT: store i32 3, ptr [[B]], align 4
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A]], align 4
|
|
; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B]], align 4
|
|
; CHECK-NEXT: [[ADD:%.*]] = add i32 [[TMP0]], [[TMP1]]
|
|
; CHECK-NEXT: store i32 [[ADD]], ptr [[OUTPUT]], align 4
|
|
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[OUTPUT]], align 4
|
|
; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[OUTPUT]], align 4
|
|
; CHECK-NEXT: [[MUL:%.*]] = mul i32 [[TMP2]], [[ADD]]
|
|
; CHECK-NEXT: store i32 [[MUL]], ptr [[RESULT]], align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
; NOCOST-LABEL: @function3(
|
|
; NOCOST-NEXT: entry:
|
|
; NOCOST-NEXT: [[DOTLOC:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: [[ADD_LOC:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: [[A:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: [[B:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: [[OUTPUT:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: [[RESULT:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: call void @llvm.lifetime.start.p0(ptr [[ADD_LOC]])
|
|
; NOCOST-NEXT: call void @llvm.lifetime.start.p0(ptr [[DOTLOC]])
|
|
; NOCOST-NEXT: call void @outlined_ir_func_1(ptr [[A]], ptr [[B]], ptr [[OUTPUT]], ptr [[ADD_LOC]], ptr [[DOTLOC]])
|
|
; NOCOST-NEXT: [[ADD_RELOAD:%.*]] = load i32, ptr [[ADD_LOC]], align 4
|
|
; NOCOST-NEXT: [[DOTRELOAD:%.*]] = load i32, ptr [[DOTLOC]], align 4
|
|
; NOCOST-NEXT: call void @llvm.lifetime.end.p0(ptr [[ADD_LOC]])
|
|
; NOCOST-NEXT: call void @llvm.lifetime.end.p0(ptr [[DOTLOC]])
|
|
; NOCOST-NEXT: [[TMP0:%.*]] = load i32, ptr [[OUTPUT]], align 4
|
|
; NOCOST-NEXT: call void @outlined_ir_func_2(i32 [[DOTRELOAD]], i32 [[ADD_RELOAD]], ptr [[RESULT]])
|
|
; NOCOST-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
|
|
}
|
|
|
|
define void @function4() #0 {
|
|
; CHECK-LABEL: @function4(
|
|
; CHECK-NEXT: entry:
|
|
; 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: store i32 2, ptr [[A]], align 4
|
|
; CHECK-NEXT: store i32 3, ptr [[B]], align 4
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A]], align 4
|
|
; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B]], align 4
|
|
; CHECK-NEXT: [[ADD:%.*]] = add i32 [[TMP0]], [[TMP1]]
|
|
; CHECK-NEXT: store i32 [[ADD]], ptr [[OUTPUT]], align 4
|
|
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[OUTPUT]], align 4
|
|
; CHECK-NEXT: [[MUL:%.*]] = mul i32 [[TMP2]], [[ADD]]
|
|
; CHECK-NEXT: store i32 [[MUL]], ptr [[RESULT]], align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
; NOCOST-LABEL: @function4(
|
|
; NOCOST-NEXT: entry:
|
|
; NOCOST-NEXT: [[DOTLOC:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: [[ADD_LOC:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: [[A:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: [[B:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: [[OUTPUT:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: [[RESULT:%.*]] = alloca i32, align 4
|
|
; NOCOST-NEXT: call void @llvm.lifetime.start.p0(ptr [[ADD_LOC]])
|
|
; NOCOST-NEXT: call void @llvm.lifetime.start.p0(ptr [[DOTLOC]])
|
|
; NOCOST-NEXT: call void @outlined_ir_func_1(ptr [[A]], ptr [[B]], ptr [[OUTPUT]], ptr [[ADD_LOC]], ptr [[DOTLOC]])
|
|
; NOCOST-NEXT: [[ADD_RELOAD:%.*]] = load i32, ptr [[ADD_LOC]], align 4
|
|
; NOCOST-NEXT: [[DOTRELOAD:%.*]] = load i32, ptr [[DOTLOC]], align 4
|
|
; NOCOST-NEXT: call void @llvm.lifetime.end.p0(ptr [[ADD_LOC]])
|
|
; NOCOST-NEXT: call void @llvm.lifetime.end.p0(ptr [[DOTLOC]])
|
|
; NOCOST-NEXT: call void @outlined_ir_func_2(i32 [[DOTRELOAD]], i32 [[ADD_RELOAD]], ptr [[RESULT]])
|
|
; NOCOST-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
|
|
}
|