RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 03:33:20 +01:00
Code Issues Projects Releases Wiki Activity

[DAGCombiner] Add a DAG combine to turn a splat build_vector where the splat elemnt is a bitcast from a vector type into a concat_vector

Browse Source 
For example, a build_vector of i64 bitcasted from v2i32 can be turned into a concat_vectors of the v2i32 vectors with a bitcast to a vXi64 type

Differential Revision: https://reviews.llvm.org/D42090

llvm-svn: 322811
This commit is contained in:
Craig Topper 2018-01-18 04:17:06 +00:00
parent bfea7bc2f8
commit d4310f3853
2 changed files with 23 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -14947,6 +14947,29 @@ SDValue DAGCombiner::visitBUILD_VECTOR(SDNode *N) {
if (ISD::allOperandsUndef(N))
return DAG.getUNDEF(VT);
// If this is a splat of a bitcast from another vector, change to a
// concat_vector.
// For example:
// (build_vector (i64 (bitcast (v2i32 X))), (i64 (bitcast (v2i32 X)))) ->
// (v2i64 (bitcast (concat_vectors (v2i32 X), (v2i32 X))))
//
// If X is a build_vector itself, the concat can become a larger build_vector.
// TODO: Maybe this is useful for non-splat too?
if (!LegalOperations) {
if (SDValue Splat = cast<BuildVectorSDNode>(N)->getSplatValue()) {
Splat = peekThroughBitcast(Splat);
EVT SrcVT = Splat.getValueType();
if (SrcVT.isVector()) {
unsigned NumElts = N->getNumOperands() * SrcVT.getVectorNumElements();
EVT NewVT = EVT::getVectorVT(*DAG.getContext(),
SrcVT.getVectorElementType(), NumElts);
SmallVector<SDValue, 8> Ops(N->getNumOperands(), Splat);
SDValue Concat = DAG.getNode(ISD::CONCAT_VECTORS, SDLoc(N), NewVT, Ops);
return DAG.getBitcast(VT, Concat);
}
}
}
// Check if we can express BUILD VECTOR via subvector extract.
if (!LegalTypes && (N->getNumOperands() > 1)) {
SDValue Op0 = N->getOperand(0);

8
test/CodeGen/X86/insertelement-shuffle.ll
View File

@ -97,17 +97,9 @@ define <8 x i64> @insert_subvector_512(i32 %x0, i32 %x1, <8 x i64> %v) nounwind
define <8 x i64> @insert_subvector_into_undef(i32 %x0, i32 %x1) nounwind {
; X32_AVX256-LABEL: insert_subvector_into_undef:
; X32_AVX256: # %bb.0:
; X32_AVX256-NEXT: pushl %ebp
; X32_AVX256-NEXT: movl %esp, %ebp
; X32_AVX256-NEXT: andl $-8, %esp
; X32_AVX256-NEXT: subl $8, %esp
; X32_AVX256-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; X32_AVX256-NEXT: vmovlps %xmm0, (%esp)
; X32_AVX256-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; X32_AVX256-NEXT: vbroadcastsd %xmm0, %ymm0
; X32_AVX256-NEXT: vmovaps %ymm0, %ymm1
; X32_AVX256-NEXT: movl %ebp, %esp
; X32_AVX256-NEXT: popl %ebp
; X32_AVX256-NEXT: retl
;
; X64_AVX256-LABEL: insert_subvector_into_undef: