llvm-project/llvm/test/Transforms/IROutliner/outlining-branches-phi-node...

174 lines
6.1 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --include-generated-funcs
; RUN: opt -S -verify -iroutliner -ir-outlining-no-cost < %s | FileCheck %s
; Here we have multiple exits, but the different sources, same outputs are
; needed, this checks that they are compressed, and moved into the appropriate
; output blocks.
define void @outline_outputs1() #0 {
entry:
%output = alloca i32, align 4
%result = alloca i32, align 4
%output2 = alloca i32, align 4
%result2 = alloca i32, align 4
%a = alloca i32, align 4
%b = alloca i32, align 4
br label %block_2
block_1:
%a2 = alloca i32, align 4
%b2 = alloca i32, align 4
br label %block_2
block_2:
%a2val = load i32, i32* %a
%b2val = load i32, i32* %b
%add2 = add i32 2, %a2val
%mul2 = mul i32 2, %b2val
br label %block_5
block_3:
%aval = load i32, i32* %a
%bval = load i32, i32* %b
%add = add i32 2, %aval
%mul = mul i32 2, %bval
br label %block_4
block_4:
store i32 %add, i32* %output, align 4
store i32 %mul, i32* %result, align 4
br label %block_6
block_5:
store i32 %add2, i32* %output, align 4
store i32 %mul2, i32* %result, align 4
br label %block_6
dummy:
ret void
block_6:
%diff = phi i32 [%aval, %block_4], [%a2val, %block_5]
ret void
}
define void @outline_outputs2() #0 {
entry:
%output = alloca i32, align 4
%result = alloca i32, align 4
%output2 = alloca i32, align 4
%result2 = alloca i32, align 4
%a = alloca i32, align 4
%b = alloca i32, align 4
br label %block_2
block_1:
%a2 = alloca i32, align 4
%b2 = alloca i32, align 4
br label %block_2
block_2:
%a2val = load i32, i32* %a
%b2val = load i32, i32* %b
%add2 = add i32 2, %a2val
%mul2 = mul i32 2, %b2val
br label %block_5
block_3:
%aval = load i32, i32* %a
%bval = load i32, i32* %b
%add = add i32 2, %aval
%mul = mul i32 2, %bval
br label %block_4
block_4:
store i32 %add, i32* %output, align 4
store i32 %mul, i32* %result, align 4
br label %block_6
block_5:
store i32 %add2, i32* %output, align 4
store i32 %mul2, i32* %result, align 4
br label %block_6
dummy:
ret void
block_6:
%diff = phi i32 [%aval, %block_4], [%a2val, %block_5]
ret void
}
; CHECK-LABEL: @outline_outputs1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DIFF_CE_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[OUTPUT:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[RESULT:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[OUTPUT2:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[RESULT2:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
; CHECK-NEXT: br label [[BLOCK_2:%.*]]
; CHECK: block_1:
; CHECK-NEXT: [[A2:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[B2:%.*]] = alloca i32, align 4
; CHECK-NEXT: br label [[BLOCK_2]]
; CHECK: block_2:
; CHECK-NEXT: [[LT_CAST:%.*]] = bitcast i32* [[DIFF_CE_LOC]] to i8*
; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 -1, i8* [[LT_CAST]])
; CHECK-NEXT: call void @outlined_ir_func_0(i32* [[A]], i32* [[B]], i32* [[OUTPUT]], i32* [[RESULT]], i32* [[DIFF_CE_LOC]])
; CHECK-NEXT: [[DIFF_CE_RELOAD:%.*]] = load i32, i32* [[DIFF_CE_LOC]], align 4
; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 -1, i8* [[LT_CAST]])
; CHECK-NEXT: br label [[BLOCK_6:%.*]]
; CHECK: dummy:
; CHECK-NEXT: ret void
; CHECK: block_6:
; CHECK-NEXT: [[DIFF:%.*]] = phi i32 [ [[DIFF_CE_RELOAD]], [[BLOCK_2]] ]
; CHECK-NEXT: ret void
;
;
; CHECK-LABEL: @outline_outputs2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DIFF_CE_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[OUTPUT:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[RESULT:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[OUTPUT2:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[RESULT2:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
; CHECK-NEXT: br label [[BLOCK_2:%.*]]
; CHECK: block_1:
; CHECK-NEXT: [[A2:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[B2:%.*]] = alloca i32, align 4
; CHECK-NEXT: br label [[BLOCK_2]]
; CHECK: block_2:
; CHECK-NEXT: [[LT_CAST:%.*]] = bitcast i32* [[DIFF_CE_LOC]] to i8*
; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 -1, i8* [[LT_CAST]])
; CHECK-NEXT: call void @outlined_ir_func_0(i32* [[A]], i32* [[B]], i32* [[OUTPUT]], i32* [[RESULT]], i32* [[DIFF_CE_LOC]])
; CHECK-NEXT: [[DIFF_CE_RELOAD:%.*]] = load i32, i32* [[DIFF_CE_LOC]], align 4
; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 -1, i8* [[LT_CAST]])
; CHECK-NEXT: br label [[BLOCK_6:%.*]]
; CHECK: dummy:
; CHECK-NEXT: ret void
; CHECK: block_6:
; CHECK-NEXT: [[DIFF:%.*]] = phi i32 [ [[DIFF_CE_RELOAD]], [[BLOCK_2]] ]
; CHECK-NEXT: ret void
;
;
; CHECK: define internal void @outlined_ir_func_0(
; CHECK-NEXT: newFuncRoot:
; CHECK-NEXT: br label [[BLOCK_2_TO_OUTLINE:%.*]]
; CHECK: block_2_to_outline:
; CHECK-NEXT: [[A2VAL:%.*]] = load i32, i32* [[TMP0:%.*]], align 4
; CHECK-NEXT: [[B2VAL:%.*]] = load i32, i32* [[TMP1:%.*]], align 4
; CHECK-NEXT: [[ADD2:%.*]] = add i32 2, [[A2VAL]]
; CHECK-NEXT: [[MUL2:%.*]] = mul i32 2, [[B2VAL]]
; CHECK-NEXT: br label [[BLOCK_5:%.*]]
; CHECK: block_3:
; CHECK-NEXT: [[AVAL:%.*]] = load i32, i32* [[TMP0]], align 4
; CHECK-NEXT: [[BVAL:%.*]] = load i32, i32* [[TMP1]], align 4
; CHECK-NEXT: [[ADD:%.*]] = add i32 2, [[AVAL]]
; CHECK-NEXT: [[MUL:%.*]] = mul i32 2, [[BVAL]]
; CHECK-NEXT: br label [[BLOCK_4:%.*]]
; CHECK: block_4:
; CHECK-NEXT: store i32 [[ADD]], i32* [[TMP2:%.*]], align 4
; CHECK-NEXT: store i32 [[MUL]], i32* [[TMP3:%.*]], align 4
; CHECK-NEXT: br label [[BLOCK_6_SPLIT:%.*]]
; CHECK: block_5:
; CHECK-NEXT: store i32 [[ADD2]], i32* [[TMP2]], align 4
; CHECK-NEXT: store i32 [[MUL2]], i32* [[TMP3]], align 4
; CHECK-NEXT: br label [[BLOCK_6_SPLIT]]
; CHECK: block_6.split:
; CHECK-NEXT: [[DIFF_CE:%.*]] = phi i32 [ [[AVAL]], [[BLOCK_4]] ], [ [[A2VAL]], [[BLOCK_5]] ]
; CHECK-NEXT: br label [[BLOCK_6_EXITSTUB:%.*]]
; CHECK: block_6.exitStub:
; CHECK-NEXT: store i32 [[DIFF_CE]], i32* [[TMP4:%.*]], align 4
; CHECK-NEXT: ret void
;