70cf58e6c1
Add getShufflevectorNumGroups to vectorize shufflevector. Current getShufflevectorNumGroups can only vectorize limited pattern (e.g., the masks of shufflevector use the elements of the source in order). In addition, ReuseShuffleIndices and ReorderIndices are not supported.
70 lines
3.6 KiB
LLVM
70 lines
3.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -passes=slp-vectorizer,instcombine -S -slp-revec -slp-max-reg-size=1024 -slp-threshold=-100 %s | FileCheck %s
|
|
|
|
define void @test1(ptr %in, ptr %out) {
|
|
; CHECK-LABEL: @test1(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load <8 x i32>, ptr [[IN:%.*]], align 1
|
|
; CHECK-NEXT: [[TMP1:%.*]] = zext <8 x i32> [[TMP0]] to <8 x i64>
|
|
; CHECK-NEXT: store <8 x i64> [[TMP1]], ptr [[OUT:%.*]], align 8
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%0 = load <8 x i32>, ptr %in, align 1
|
|
%1 = shufflevector <8 x i32> %0, <8 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
%2 = shufflevector <8 x i32> %0, <8 x i32> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
|
%3 = zext <4 x i32> %1 to <4 x i64>
|
|
%4 = zext <4 x i32> %2 to <4 x i64>
|
|
%5 = shufflevector <4 x i64> %3, <4 x i64> poison, <2 x i32> <i32 0, i32 1>
|
|
%6 = shufflevector <4 x i64> %3, <4 x i64> poison, <2 x i32> <i32 2, i32 3>
|
|
%7 = shufflevector <4 x i64> %4, <4 x i64> poison, <2 x i32> <i32 0, i32 1>
|
|
%8 = shufflevector <4 x i64> %4, <4 x i64> poison, <2 x i32> <i32 2, i32 3>
|
|
%9 = getelementptr inbounds i64, ptr %out, i64 0
|
|
%10 = getelementptr inbounds i64, ptr %out, i64 2
|
|
%11 = getelementptr inbounds i64, ptr %out, i64 4
|
|
%12 = getelementptr inbounds i64, ptr %out, i64 6
|
|
store <2 x i64> %5, ptr %9, align 8
|
|
store <2 x i64> %6, ptr %10, align 8
|
|
store <2 x i64> %7, ptr %11, align 8
|
|
store <2 x i64> %8, ptr %12, align 8
|
|
ret void
|
|
}
|
|
|
|
define void @test2(ptr %in, ptr %out) {
|
|
; CHECK-LABEL: @test2(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load <8 x i32>, ptr [[IN:%.*]], align 1
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <8 x i32> [[TMP0]], <8 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <8 x i32> [[TMP0]], <8 x i32> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
|
; CHECK-NEXT: [[TMP3:%.*]] = zext <4 x i32> [[TMP1]] to <4 x i64>
|
|
; CHECK-NEXT: [[TMP4:%.*]] = zext <4 x i32> [[TMP2]] to <4 x i64>
|
|
; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i64> [[TMP3]], <4 x i64> poison, <2 x i32> <i32 2, i32 3>
|
|
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i64> [[TMP3]], <4 x i64> poison, <2 x i32> <i32 0, i32 1>
|
|
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[OUT:%.*]], i64 16
|
|
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[OUT]], i64 32
|
|
; CHECK-NEXT: store <2 x i64> [[TMP5]], ptr [[OUT]], align 8
|
|
; CHECK-NEXT: store <2 x i64> [[TMP6]], ptr [[TMP7]], align 8
|
|
; CHECK-NEXT: store <4 x i64> [[TMP4]], ptr [[TMP8]], align 8
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%0 = load <8 x i32>, ptr %in, align 1
|
|
%1 = shufflevector <8 x i32> %0, <8 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
%2 = shufflevector <8 x i32> %0, <8 x i32> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
|
%3 = zext <4 x i32> %1 to <4 x i64>
|
|
%4 = zext <4 x i32> %2 to <4 x i64>
|
|
%5 = shufflevector <4 x i64> %3, <4 x i64> poison, <2 x i32> <i32 2, i32 3>
|
|
%6 = shufflevector <4 x i64> %3, <4 x i64> poison, <2 x i32> <i32 0, i32 1>
|
|
%7 = shufflevector <4 x i64> %4, <4 x i64> poison, <2 x i32> <i32 0, i32 1>
|
|
%8 = shufflevector <4 x i64> %4, <4 x i64> poison, <2 x i32> <i32 2, i32 3>
|
|
%9 = getelementptr inbounds i64, ptr %out, i64 0
|
|
%10 = getelementptr inbounds i64, ptr %out, i64 2
|
|
%11 = getelementptr inbounds i64, ptr %out, i64 4
|
|
%12 = getelementptr inbounds i64, ptr %out, i64 6
|
|
store <2 x i64> %5, ptr %9, align 8
|
|
store <2 x i64> %6, ptr %10, align 8
|
|
store <2 x i64> %7, ptr %11, align 8
|
|
store <2 x i64> %8, ptr %12, align 8
|
|
ret void
|
|
}
|