maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Fix the bug when handling shufflevector for aarch64. 

Summary: This Fixes https://bugs.llvm.org/show_bug.cgi?id=33600

Reviewers: mssimpso, davidxl, Carrot

Reviewed By: mssimpso

Subscribers: aemerson, rengolin, sanjoy, javed.absar, llvm-commits, kristof.beyls

Differential Revision: https://reviews.llvm.org/D34641

llvm-svn: 306334
This commit is contained in:
Dehao Chen 2017-06-26 21:33:51 +00:00
parent 53fae0772a
commit 38f1bc7834
2 changed files with 28 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
View File

@ -7561,8 +7561,9 @@ bool AArch64TargetLowering::lowerInterleavedLoad(
// Convert the integer vector to pointer vector if the element is pointer.
if (EltTy->isPointerTy())
SubVec = Builder.CreateIntToPtr(SubVec, SVI->getType());
SubVec = Builder.CreateIntToPtr(
SubVec, VectorType::get(SVI->getType()->getVectorElementType(),
VecTy->getVectorNumElements()));
SubVecs[SVI].push_back(SubVec);
}
}

25
llvm/test/Transforms/InterleavedAccess/AArch64/interleaved-accesses.ll
View File

@ -774,3 +774,28 @@ define void @load_factor2_fp128(<4 x fp128>* %ptr) {
%v1 = shufflevector <4 x fp128> %interleaved.vec, <4 x fp128> undef, <2 x i32> <i32 1, i32 3>
ret void
}
define <4 x i1> @load_large_vector(<12 x i64 *>* %p) {
; NEON-LABEL: @load_large_vector(
; NEON: [[LDN:%.*]] = call { <2 x i64>, <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld3.v2i64.p0v2i64(<2 x i64>*
; NEON-NEXT: [[TMP1:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64> } [[LDN]], 1
; NEON-NEXT: [[TMP2:%.*]] = inttoptr <2 x i64> [[TMP1]] to <2 x i64*>
; NEON-NEXT: [[TMP3:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64> } [[LDN]], 0
; NEON-NEXT: [[TMP4:%.*]] = inttoptr <2 x i64> [[TMP3]] to <2 x i64*>
; NEON: [[LDN1:%.*]] = call { <2 x i64>, <2 x i64>, <2 x i64> } @llvm.aarch64.neon.ld3.v2i64.p0v2i64(<2 x i64>*
; NEON-NEXT: [[TMP5:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64> } [[LDN1]], 1
; NEON-NEXT: [[TMP6:%.*]] = inttoptr <2 x i64> [[TMP5]] to <2 x i64*>
; NEON-NEXT: [[TMP7:%.*]] = extractvalue { <2 x i64>, <2 x i64>, <2 x i64> } [[LDN1]], 0
; NEON-NEXT: [[TMP8:%.*]] = inttoptr <2 x i64> [[TMP7]] to <2 x i64*>
; NEON-NEXT: shufflevector <2 x i64*> [[TMP2]], <2 x i64*> [[TMP6]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; NEON-NEXT: shufflevector <2 x i64*> [[TMP4]], <2 x i64*> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; NO_NEON-LABEL: @load_large_vector(
; NO_NEON-NOT: @llvm.aarch64.neon
; NO_NEON: ret
;
%l = load <12 x i64 *>, <12 x i64 *>* %p
%s1 = shufflevector <12 x i64 *> %l, <12 x i64 *> undef, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
%s2 = shufflevector <12 x i64 *> %l, <12 x i64 *> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
%ret = icmp ne <4 x i64 *> %s1, %s2
ret <4 x i1> %ret
}