RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 10:42:39 +01:00
Code Issues Projects Releases Wiki Activity

[PowerPC][Power10] Fix XXSPLI32DX not correctly exploiting specific cases

Browse Source 
Some cases may be transformed into 32 bit splats before hitting the boolean statement, which may cause incorrect behaviour and provide XXSPLTI32DX with the incorrect values of splat. The condition was reversed so that the shortcut prevents this problem.

Differential Revision: https://reviews.llvm.org/D95634
This commit is contained in:
Albion Fung 2021-01-28 15:17:18 -05:00
parent 85f9252ff2
commit d6b6754937
2 changed files with 9 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
lib/Target/PowerPC/PPCISelLowering.cpp
View File

@ -8604,16 +8604,19 @@ SDValue PPCTargetLowering::LowerBUILD_VECTOR(SDValue Op,
// If it is a splat of a double, check if we can shrink it to a 32 bit
// non-denormal float which when converted back to double gives us the same
// double. This is to exploit the XXSPLTIDP instruction.+ // If we lose precision, we use XXSPLTI32DX.
// double. This is to exploit the XXSPLTIDP instruction.
// If we lose precision, we use XXSPLTI32DX.
if (BVNIsConstantSplat && (SplatBitSize == 64) &&
Subtarget.hasPrefixInstrs()) {
if (convertToNonDenormSingle(APSplatBits) &&
(Op->getValueType(0) == MVT::v2f64)) {
// Check the type first to short-circuit so we don't modify APSplatBits if
// this block isn't executed.
if ((Op->getValueType(0) == MVT::v2f64) &&
convertToNonDenormSingle(APSplatBits)) {
SDValue SplatNode = DAG.getNode(
PPCISD::XXSPLTI_SP_TO_DP, dl, MVT::v2f64,
DAG.getTargetConstant(APSplatBits.getZExtValue(), dl, MVT::i32));
return DAG.getBitcast(Op.getValueType(), SplatNode);
} else if (APSplatBits.getBitWidth() == 64) {
} else {
// We may lose precision, so we have to use XXSPLTI32DX.
uint32_t Hi =

16
test/CodeGen/PowerPC/p10-splatImm32.ll
View File

@ -101,23 +101,11 @@ entry:
ret <8 x i16> <i16 291, i16 undef, i16 undef, i16 364, i16 undef, i16 1, i16 173, i16 undef>
}
define dso_local <16 x i8> @test_xxsplti32dx_10() {
; CHECK-LABEL: test_xxsplti32dx_10:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor vs34, vs34, vs34
; CHECK-NEXT: xxsplti32dx vs34, 0, 1207959552
; CHECK-NEXT: blr
entry:
ret <16 x i8> <i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 72, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 72>
}
; FIXME: It appears that there is something wrong with the computation
; of the 64-bit constant to splat so we cannot emit xxsplti32dx for
; this test case for now.
define dso_local <16 x i8> @constSplatBug() {
; CHECK-LABEL: constSplatBug:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: plxv vs34, .LCPI10_0@PCREL(0), 1
; CHECK-NEXT: xxlxor vs34, vs34, vs34
; CHECK-NEXT: xxsplti32dx vs34, 0, 1191182336
; CHECK-NEXT: blr
entry:
ret <16 x i8> <i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 71, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 71>