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
255 lines
8.2 KiB
LLVM
255 lines
8.2 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 checks that commutative instructions where the operands are
|
|
; swapped are outlined as the same function.
|
|
|
|
; It also checks that non-commutative instructions outlined as different
|
|
; functions when the operands are swapped;
|
|
|
|
; These are identical functions, except that in the flipped functions,
|
|
; the operands in the adds are commuted. However, since add instructions
|
|
; are commutative, we should still outline from all four as the same
|
|
; instruction.
|
|
|
|
define void @outline_from_add1() {
|
|
; CHECK-LABEL: @outline_from_add1(
|
|
; 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_0(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
|
|
%0 = add i32 %al, %bl
|
|
%1 = add i32 %al, %cl
|
|
%2 = add i32 %bl, %cl
|
|
ret void
|
|
}
|
|
|
|
define void @outline_from_add2() {
|
|
; CHECK-LABEL: @outline_from_add2(
|
|
; 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_0(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
|
|
%0 = add i32 %al, %bl
|
|
%1 = add i32 %al, %cl
|
|
%2 = add i32 %bl, %cl
|
|
ret void
|
|
}
|
|
|
|
define void @outline_from_flipped_add3() {
|
|
; CHECK-LABEL: @outline_from_flipped_add3(
|
|
; 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_0(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
|
|
%0 = add i32 %bl, %al
|
|
%1 = add i32 %cl, %al
|
|
%2 = add i32 %cl, %bl
|
|
ret void
|
|
}
|
|
|
|
define void @outline_from_flipped_add4() {
|
|
; CHECK-LABEL: @outline_from_flipped_add4(
|
|
; 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_0(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
|
|
%0 = add i32 %bl, %al
|
|
%1 = add i32 %cl, %al
|
|
%2 = add i32 %cl, %bl
|
|
ret void
|
|
}
|
|
|
|
; These are identical functions, except that in the flipped functions,
|
|
; the operands in the subtractions are commuted. Since subtraction
|
|
; instructions are not commutative, we should outline the first two functions
|
|
; differently than the second two functions.
|
|
|
|
define void @outline_from_sub1() {
|
|
; CHECK-LABEL: @outline_from_sub1(
|
|
; 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_2(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
|
|
%0 = sub i32 %al, %bl
|
|
%1 = sub i32 %al, %cl
|
|
%2 = sub i32 %bl, %cl
|
|
ret void
|
|
}
|
|
|
|
define void @outline_from_sub2() {
|
|
; CHECK-LABEL: @outline_from_sub2(
|
|
; 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_2(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
|
|
%0 = sub i32 %al, %bl
|
|
%1 = sub i32 %al, %cl
|
|
%2 = sub i32 %bl, %cl
|
|
ret void
|
|
}
|
|
|
|
define void @dontoutline_from_flipped_sub3() {
|
|
; CHECK-LABEL: @dontoutline_from_flipped_sub3(
|
|
; 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
|
|
%0 = sub i32 %bl, %al
|
|
%1 = sub i32 %cl, %al
|
|
%2 = sub i32 %cl, %bl
|
|
ret void
|
|
}
|
|
|
|
define void @dontoutline_from_flipped_sub4() {
|
|
; CHECK-LABEL: @dontoutline_from_flipped_sub4(
|
|
; 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
|
|
%0 = sub i32 %bl, %al
|
|
%1 = sub i32 %cl, %al
|
|
%2 = sub i32 %cl, %bl
|
|
ret void
|
|
}
|
|
|
|
; CHECK: define internal void @outlined_ir_func_0(ptr [[ARG0:%.*]], ptr [[ARG1:%.*]], ptr [[ARG2:%.*]]) #0 {
|
|
; CHECK: entry_to_outline:
|
|
; CHECK-NEXT: store i32 2, ptr [[ARG0]], align 4
|
|
; CHECK-NEXT: store i32 3, ptr [[ARG1]], align 4
|
|
; CHECK-NEXT: store i32 4, ptr [[ARG2]], align 4
|
|
; CHECK-NEXT: [[AL:%.*]] = load i32, ptr [[ARG0]], align 4
|
|
; CHECK-NEXT: [[BL:%.*]] = load i32, ptr [[ARG1]], align 4
|
|
; CHECK-NEXT: [[CL:%.*]] = load i32, ptr [[ARG2]], align 4
|
|
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[AL]], [[BL]]
|
|
; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[AL]], [[CL]]
|
|
; CHECK-NEXT: [[TMP2:%.*]] = add i32 [[BL]], [[CL]]
|
|
|
|
; CHECK: define internal void @outlined_ir_func_1(ptr [[ARG0:%.*]], ptr [[ARG1:%.*]], ptr [[ARG2:%.*]]) #0 {
|
|
; CHECK: entry_to_outline:
|
|
; CHECK-NEXT: store i32 2, ptr [[ARG0]], align 4
|
|
; CHECK-NEXT: store i32 3, ptr [[ARG1]], align 4
|
|
; CHECK-NEXT: store i32 4, ptr [[ARG2]], align 4
|
|
; CHECK-NEXT: [[AL:%.*]] = load i32, ptr [[ARG0]], align 4
|
|
; CHECK-NEXT: [[BL:%.*]] = load i32, ptr [[ARG1]], align 4
|
|
; CHECK-NEXT: [[CL:%.*]] = load i32, ptr [[ARG2]], align 4
|
|
; CHECK-NEXT: [[TMP0:%.*]] = sub i32 [[BL]], [[AL]]
|
|
; CHECK-NEXT: [[TMP1:%.*]] = sub i32 [[CL]], [[AL]]
|
|
; CHECK-NEXT: [[TMP2:%.*]] = sub i32 [[CL]], [[BL]]
|
|
|
|
; CHECK: define internal void @outlined_ir_func_2(ptr [[ARG0:%.*]], ptr [[ARG1:%.*]], ptr [[ARG2:%.*]]) #0 {
|
|
; CHECK: entry_to_outline:
|
|
; CHECK-NEXT: store i32 2, ptr [[ARG0]], align 4
|
|
; CHECK-NEXT: store i32 3, ptr [[ARG1]], align 4
|
|
; CHECK-NEXT: store i32 4, ptr [[ARG2]], align 4
|
|
; CHECK-NEXT: [[AL:%.*]] = load i32, ptr [[ARG0]], align 4
|
|
; CHECK-NEXT: [[BL:%.*]] = load i32, ptr [[ARG1]], align 4
|
|
; CHECK-NEXT: [[CL:%.*]] = load i32, ptr [[ARG2]], align 4
|
|
; CHECK-NEXT: [[TMP0:%.*]] = sub i32 [[AL]], [[BL]]
|
|
; CHECK-NEXT: [[TMP1:%.*]] = sub i32 [[AL]], [[CL]]
|
|
; CHECK-NEXT: [[TMP2:%.*]] = sub i32 [[BL]], [[CL]]
|