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

X86: Make shuffle -> shift conversion more aggressive about undefs. 

Shuffles that only move an element into position 0 of the vector are common in
the output of the loop vectorizer and often generate suboptimal code when SSSE3
is not available. Lower them to vector shifts if possible.

We still prefer palignr over psrldq because it has higher throughput on
sandybridge.

llvm-svn: 182102
This commit is contained in:
Benjamin Kramer 2013-05-17 14:48:34 +00:00
parent 7ccd1b86bd
commit fc33e1d99b
3 changed files with 54 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -4756,19 +4756,27 @@ static SDValue getShuffleScalarElt(SDNode *N, unsigned Index, SelectionDAG &DAG,
/// getNumOfConsecutiveZeros - Return the number of elements of a vector
/// shuffle operation which come from a consecutively from a zero. The
/// search can start in two different directions, from left or right.
static
unsigned getNumOfConsecutiveZeros(ShuffleVectorSDNode *SVOp, unsigned NumElems,
bool ZerosFromLeft, SelectionDAG &DAG) {
unsigned i;
for (i = 0; i != NumElems; ++i) {
unsigned Index = ZerosFromLeft ? i : NumElems-i-1;
/// We count undefs as zeros until PreferredNum is reached.
static unsigned getNumOfConsecutiveZeros(ShuffleVectorSDNode *SVOp,
unsigned NumElems, bool ZerosFromLeft,
SelectionDAG &DAG,
unsigned PreferredNum = -1U) {
unsigned NumZeros = 0;
for (unsigned i = 0; i != NumElems; ++i) {
unsigned Index = ZerosFromLeft ? i : NumElems - i - 1;
SDValue Elt = getShuffleScalarElt(SVOp, Index, DAG, 0);
if (!(Elt.getNode() &&
(Elt.getOpcode() == ISD::UNDEF || X86::isZeroNode(Elt))))
if (!Elt.getNode())
break;
if (X86::isZeroNode(Elt))
++NumZeros;
else if (Elt.getOpcode() == ISD::UNDEF) // Undef as zero up to PreferredNum.
NumZeros = std::min(NumZeros + 1, PreferredNum);
else
break;
}
return i;
return NumZeros;
}
/// isShuffleMaskConsecutive - Check if the shuffle mask indicies [MaskI, MaskE)
@ -4806,8 +4814,9 @@ bool isShuffleMaskConsecutive(ShuffleVectorSDNode *SVOp,
static bool isVectorShiftRight(ShuffleVectorSDNode *SVOp, SelectionDAG &DAG,
bool &isLeft, SDValue &ShVal, unsigned &ShAmt) {
unsigned NumElems = SVOp->getValueType(0).getVectorNumElements();
unsigned NumZeros = getNumOfConsecutiveZeros(SVOp, NumElems,
false /* check zeros from right */, DAG);
unsigned NumZeros = getNumOfConsecutiveZeros(
SVOp, NumElems, false /* check zeros from right */, DAG,
SVOp->getMaskElt(0));
unsigned OpSrc;
if (!NumZeros)
@ -4839,8 +4848,9 @@ static bool isVectorShiftRight(ShuffleVectorSDNode *SVOp, SelectionDAG &DAG,
static bool isVectorShiftLeft(ShuffleVectorSDNode *SVOp, SelectionDAG &DAG,
bool &isLeft, SDValue &ShVal, unsigned &ShAmt) {
unsigned NumElems = SVOp->getValueType(0).getVectorNumElements();
unsigned NumZeros = getNumOfConsecutiveZeros(SVOp, NumElems,
true /* check zeros from left */, DAG);
unsigned NumZeros = getNumOfConsecutiveZeros(
SVOp, NumElems, true /* check zeros from left */, DAG,
NumElems - SVOp->getMaskElt(NumElems - 1) - 1);
unsigned OpSrc;
if (!NumZeros)
@ -6871,6 +6881,11 @@ X86TargetLowering::LowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG) const {
TargetMask, DAG);
}
if (isPALIGNRMask(M, VT, Subtarget))
return getTargetShuffleNode(X86ISD::PALIGNR, dl, VT, V1, V2,
getShufflePALIGNRImmediate(SVOp),
DAG);
// Check if this can be converted into a logical shift.
bool isLeft = false;
unsigned ShAmt = 0;
@ -6988,11 +7003,6 @@ X86TargetLowering::LowerVECTOR_SHUFFLE(SDValue Op, SelectionDAG &DAG) const {
// inlined here right now to enable us to directly emit target specific
// nodes, and remove one by one until they don't return Op anymore.
if (isPALIGNRMask(M, VT, Subtarget))
return getTargetShuffleNode(X86ISD::PALIGNR, dl, VT, V1, V2,
getShufflePALIGNRImmediate(SVOp),
DAG);
if (ShuffleVectorSDNode::isSplatMask(&M[0], VT) &&
SVOp->getSplatIndex() == 0 && V2IsUndef) {
if (VT == MVT::v2f64 || VT == MVT::v2i64)

2
llvm/test/CodeGen/X86/avx-vpermil.ll
View File

@ -46,7 +46,7 @@ entry:
}
; CHECK: palignr $8
; CHECK: psrldq $8
; CHECK: palignr $8
define <8 x float> @funcF(<8 x float> %a) nounwind uwtable readnone ssp {
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> zeroinitializer, <8 x i32> <i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9>

26
llvm/test/CodeGen/X86/vec_insert-5.ll
View File

@ -1,4 +1,4 @@
; RUN: llc < %s -march=x86 -mattr=+sse2 | FileCheck %s
; RUN: llc < %s -march=x86 -mattr=+sse2,+ssse3 | FileCheck %s
; There are no MMX operations in @t1
define void @t1(i32 %a, x86_mmx* %P) nounwind {
@ -41,3 +41,27 @@ define <4 x float> @t4(<4 x float>* %P) nounwind {
; CHECK: t4:
; CHECK: psrldq $12
}
define <16 x i8> @t5(<16 x i8> %x) nounwind {
%s = shufflevector <16 x i8> %x, <16 x i8> zeroinitializer, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 17>
ret <16 x i8> %s
; CHECK: t5:
; CHECK: psrldq $1
}
define <16 x i8> @t6(<16 x i8> %x) nounwind {
%s = shufflevector <16 x i8> %x, <16 x i8> undef, <16 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
ret <16 x i8> %s
; CHECK: t6:
; CHECK: palignr $1
}
define <16 x i8> @t7(<16 x i8> %x) nounwind {
%s = shufflevector <16 x i8> %x, <16 x i8> undef, <16 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 1, i32 2>
ret <16 x i8> %s
; CHECK: t7:
; CHECK: pslldq $13
}