7d6e8f2a96
If we vectorize a e.g. store, we leave around a bunch of getelementptrs for the individual scalar stores which we removed. We can go ahead and delete them as well. This is purely for test output quality and readability. It should have no effect in any sane pipeline. Differential Revision: https://reviews.llvm.org/D122493
113 lines
4.2 KiB
LLVM
113 lines
4.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -slp-vectorizer -S -mtriple=x86_64-unknown-linux -mcpu=corei7-avx -slp-threshold=-999 < %s | FileCheck %s
|
|
|
|
|
|
; S[0] = %v1 + %v2
|
|
; S[1] = %v2 + %v1
|
|
; S[2] = %v2 + %v1
|
|
; S[3] = %v1 + %v2
|
|
;
|
|
; We broadcast %v1 and %v2
|
|
;
|
|
|
|
define void @bcast_vals(i64 *%A, i64 *%B, i64 *%S) {
|
|
; CHECK-LABEL: @bcast_vals(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[A0:%.*]] = load i64, i64* [[A:%.*]], align 8
|
|
; CHECK-NEXT: [[B0:%.*]] = load i64, i64* [[B:%.*]], align 8
|
|
; CHECK-NEXT: [[V1:%.*]] = sub i64 [[A0]], 1
|
|
; CHECK-NEXT: [[V2:%.*]] = sub i64 [[B0]], 1
|
|
; CHECK-NEXT: [[IDXS0:%.*]] = getelementptr inbounds i64, i64* [[S:%.*]], i64 0
|
|
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i64> poison, i64 [[V1]], i32 0
|
|
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i64> [[TMP0]], <4 x i64> poison, <4 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i64> poison, i64 [[V2]], i32 0
|
|
; CHECK-NEXT: [[SHUFFLE1:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> poison, <4 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i64> [[SHUFFLE]], [[SHUFFLE1]]
|
|
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i64* [[IDXS0]] to <4 x i64>*
|
|
; CHECK-NEXT: store <4 x i64> [[TMP2]], <4 x i64>* [[TMP3]], align 8
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%A0 = load i64, i64 *%A, align 8
|
|
%B0 = load i64, i64 *%B, align 8
|
|
|
|
%v1 = sub i64 %A0, 1
|
|
%v2 = sub i64 %B0, 1
|
|
|
|
%Add0 = add i64 %v1, %v2
|
|
%Add1 = add i64 %v2, %v1
|
|
%Add2 = add i64 %v2, %v1
|
|
%Add3 = add i64 %v1, %v2
|
|
|
|
%idxS0 = getelementptr inbounds i64, i64* %S, i64 0
|
|
%idxS1 = getelementptr inbounds i64, i64* %S, i64 1
|
|
%idxS2 = getelementptr inbounds i64, i64* %S, i64 2
|
|
%idxS3 = getelementptr inbounds i64, i64* %S, i64 3
|
|
|
|
store i64 %Add0, i64 *%idxS0, align 8
|
|
store i64 %Add1, i64 *%idxS1, align 8
|
|
store i64 %Add2, i64 *%idxS2, align 8
|
|
store i64 %Add3, i64 *%idxS3, align 8
|
|
ret void
|
|
}
|
|
|
|
; S[0] = %v1 + %v2
|
|
; S[1] = %v3 + %v1
|
|
; S[2] = %v5 + %v1
|
|
; S[3] = %v1 + %v4
|
|
;
|
|
; We broadcast %v1.
|
|
|
|
;
|
|
define void @bcast_vals2(i16 *%A, i16 *%B, i16 *%C, i16 *%D, i16 *%E, i32 *%S) {
|
|
; CHECK-LABEL: @bcast_vals2(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[A0:%.*]] = load i16, i16* [[A:%.*]], align 8
|
|
; CHECK-NEXT: [[V1:%.*]] = sext i16 [[A0]] to i32
|
|
; CHECK-NEXT: [[IDXS0:%.*]] = getelementptr inbounds i32, i32* [[S:%.*]], i64 0
|
|
; CHECK-NEXT: [[B0:%.*]] = load i16, i16* [[B:%.*]], align 8
|
|
; CHECK-NEXT: [[C0:%.*]] = load i16, i16* [[C:%.*]], align 8
|
|
; CHECK-NEXT: [[D0:%.*]] = load i16, i16* [[D:%.*]], align 8
|
|
; CHECK-NEXT: [[E0:%.*]] = load i16, i16* [[E:%.*]], align 8
|
|
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i16> poison, i16 [[B0]], i32 0
|
|
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i16> [[TMP0]], i16 [[C0]], i32 1
|
|
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x i16> [[TMP1]], i16 [[E0]], i32 2
|
|
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x i16> [[TMP2]], i16 [[D0]], i32 3
|
|
; CHECK-NEXT: [[TMP4:%.*]] = sext <4 x i16> [[TMP3]] to <4 x i32>
|
|
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x i32> poison, i32 [[V1]], i32 0
|
|
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> poison, <4 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[TMP6:%.*]] = add <4 x i32> [[SHUFFLE]], [[TMP4]]
|
|
; CHECK-NEXT: [[TMP7:%.*]] = bitcast i32* [[IDXS0]] to <4 x i32>*
|
|
; CHECK-NEXT: store <4 x i32> [[TMP6]], <4 x i32>* [[TMP7]], align 8
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%A0 = load i16, i16 *%A, align 8
|
|
%B0 = load i16, i16 *%B, align 8
|
|
%C0 = load i16, i16 *%C, align 8
|
|
%D0 = load i16, i16 *%D, align 8
|
|
%E0 = load i16, i16 *%E, align 8
|
|
|
|
%v1 = sext i16 %A0 to i32
|
|
%v2 = sext i16 %B0 to i32
|
|
%v3 = sext i16 %C0 to i32
|
|
%v4 = sext i16 %D0 to i32
|
|
%v5 = sext i16 %E0 to i32
|
|
|
|
%Add0 = add i32 %v1, %v2
|
|
%Add1 = add i32 %v3, %v1
|
|
%Add2 = add i32 %v5, %v1
|
|
%Add3 = add i32 %v1, %v4
|
|
|
|
%idxS0 = getelementptr inbounds i32, i32* %S, i64 0
|
|
%idxS1 = getelementptr inbounds i32, i32* %S, i64 1
|
|
%idxS2 = getelementptr inbounds i32, i32* %S, i64 2
|
|
%idxS3 = getelementptr inbounds i32, i32* %S, i64 3
|
|
|
|
store i32 %Add0, i32 *%idxS0, align 8
|
|
store i32 %Add1, i32 *%idxS1, align 8
|
|
store i32 %Add2, i32 *%idxS2, align 8
|
|
store i32 %Add3, i32 *%idxS3, align 8
|
|
ret void
|
|
}
|