blob: 8f8a0eaabe796787ca122bf5892b3c88c7e44186 [file] [log] [blame]
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -iroutliner -ir-outlining-no-cost < %s | FileCheck %s
; These functions are constructed slightly differently so that they require
; the same output blocks for the values used outside of the region. We are
; checking that two output blocks are created with the same store instructions.
define void @outline_outputs1() #0 {
; CHECK-LABEL: @outline_outputs1(
; 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: [[LT_CAST:%.*]] = bitcast i32* [[ADD_LOC]] to i8*
; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 -1, i8* [[LT_CAST]])
; CHECK-NEXT: [[LT_CAST1:%.*]] = bitcast i32* [[DOTLOC]] to i8*
; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 -1, i8* [[LT_CAST1]])
; CHECK-NEXT: call void @outlined_ir_func_0(i32* [[A]], i32* [[B]], i32* [[OUTPUT]], i32* [[ADD_LOC]], i32* [[DOTLOC]])
; CHECK-NEXT: [[ADD_RELOAD:%.*]] = load i32, i32* [[ADD_LOC]], align 4
; CHECK-NEXT: [[DOTRELOAD:%.*]] = load i32, i32* [[DOTLOC]], align 4
; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 -1, i8* [[LT_CAST]])
; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 -1, i8* [[LT_CAST1]])
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[OUTPUT]], align 4
; CHECK-NEXT: call void @outlined_ir_func_1(i32 [[DOTRELOAD]], i32 [[ADD_RELOAD]], i32* [[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, i32* %a, align 4
store i32 3, i32* %b, align 4
%0 = load i32, i32* %a, align 4
%1 = load i32, i32* %b, align 4
%add = add i32 %0, %1
store i32 %add, i32* %output, align 4
%2 = load i32, i32* %output, align 4
%3 = load i32, i32* %output, align 4
%mul = mul i32 %2, %add
store i32 %mul, i32* %result, align 4
ret void
}
define void @outline_outputs2() #0 {
; CHECK-LABEL: @outline_outputs2(
; 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: [[LT_CAST:%.*]] = bitcast i32* [[ADD_LOC]] to i8*
; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 -1, i8* [[LT_CAST]])
; CHECK-NEXT: [[LT_CAST1:%.*]] = bitcast i32* [[DOTLOC]] to i8*
; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 -1, i8* [[LT_CAST1]])
; CHECK-NEXT: call void @outlined_ir_func_0(i32* [[A]], i32* [[B]], i32* [[OUTPUT]], i32* [[ADD_LOC]], i32* [[DOTLOC]])
; CHECK-NEXT: [[ADD_RELOAD:%.*]] = load i32, i32* [[ADD_LOC]], align 4
; CHECK-NEXT: [[DOTRELOAD:%.*]] = load i32, i32* [[DOTLOC]], align 4
; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 -1, i8* [[LT_CAST]])
; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 -1, i8* [[LT_CAST1]])
; CHECK-NEXT: call void @outlined_ir_func_1(i32 [[DOTRELOAD]], i32 [[ADD_RELOAD]], i32* [[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, i32* %a, align 4
store i32 3, i32* %b, align 4
%0 = load i32, i32* %a, align 4
%1 = load i32, i32* %b, align 4
%add = add i32 %0, %1
store i32 %add, i32* %output, align 4
%2 = load i32, i32* %output, align 4
%mul = mul i32 %2, %add
store i32 %mul, i32* %result, align 4
ret void
}
; CHECK: define internal void @outlined_ir_func_0(i32* [[ARG0:%.*]], i32* [[ARG1:%.*]], i32* [[ARG2:%.*]], i32* [[ARG3:%.*]], i32* [[ARG4:%.*]]) #1 {
; CHECK: entry_after_outline.exitStub:
; CHECK-NEXT: store i32 [[ADD:%.*]], i32* [[ARG3]], align 4
; CHECK-NEXT: store i32 [[TMP2:%.*]], i32* [[ARG4]], align 4
; CHECK: entry_to_outline:
; CHECK-NEXT: store i32 2, i32* [[ARG0]], align 4
; CHECK-NEXT: store i32 3, i32* [[ARG1]], align 4
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARG0]], align 4
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARG1]], align 4
; CHECK-NEXT: [[ADD]] = add i32 [[TMP0]], [[TMP1]]
; CHECK-NEXT: store i32 [[ADD]], i32* [[ARG2]], align 4
; CHECK-NEXT: [[TMP2]] = load i32, i32* [[ARG2]], align 4