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

[x86] Fix a bug in the VZEXT DAG combine that I just made more powerful.

Browse Source 
It turns out this combine was always somewhat flawed -- there are cases
where nested VZEXT nodes *can't* be combined: if their types have
a mismatch that can be observed in the result. While none of these show
up in currently, once I switch to the new vector shuffle lowering a few
test cases actually form such nested VZEXT nodes. I've not come up with
any IR pattern that I can sensible write to exercise this, but it will
be covered by tests once I flip the switch.

llvm-svn: 219044
This commit is contained in:
Chandler Carruth 2014-10-04 02:51:03 +00:00
parent b73b4f12a1
commit 7001fb9ace
1 changed files with 23 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
lib/Target/X86/X86ISelLowering.cpp
View File

@ -24596,19 +24596,39 @@ static SDValue performVZEXTCombine(SDNode *N, SelectionDAG &DAG,
SDValue Op = N->getOperand(0);
MVT OpVT = Op.getSimpleValueType();
MVT OpEltVT = OpVT.getVectorElementType();
unsigned InputBits = OpEltVT.getSizeInBits() * VT.getVectorNumElements();
// (vzext (bitcast (vzext (x)) -> (vzext x)
SDValue V = Op;
while (V.getOpcode() == ISD::BITCAST)
V = V.getOperand(0);
if (V != Op && V.getOpcode() == X86ISD::VZEXT)
return DAG.getNode(X86ISD::VZEXT, DL, VT, V.getOperand(0));
if (V != Op && V.getOpcode() == X86ISD::VZEXT) {
MVT InnerVT = V.getSimpleValueType();
MVT InnerEltVT = InnerVT.getVectorElementType();
// If the element sizes match exactly, we can just do one larger vzext. This
// is always an exact type match as vzext operates on integer types.
if (OpEltVT == InnerEltVT) {
assert(OpVT == InnerVT && "Types must match for vzext!");
return DAG.getNode(X86ISD::VZEXT, DL, VT, V.getOperand(0));
}
// The only other way we can combine them is if only a single element of the
// inner vzext is used in the input to the outer vzext.
if (InnerEltVT.getSizeInBits() < InputBits)
return SDValue();
// In this case, the inner vzext is completely dead because we're going to
// only look at bits inside of the low element. Just do the outer vzext on
// a bitcast of the input to the inner.
return DAG.getNode(X86ISD::VZEXT, DL, VT,
DAG.getNode(ISD::BITCAST, DL, OpVT, V));
}
// Check if we can bypass extracting and re-inserting an element of an input
// vector. Essentialy:
// (bitcast (sclr2vec (ext_vec_elt x))) -> (bitcast x)
unsigned InputBits = OpEltVT.getSizeInBits() * VT.getVectorNumElements();
if (V.getOpcode() == ISD::SCALAR_TO_VECTOR &&
V.getOperand(0).getOpcode() == ISD::EXTRACT_VECTOR_ELT &&
V.getOperand(0).getSimpleValueType().getSizeInBits() == InputBits) {