1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 10:42:39 +01:00

[PowerPC] Do not emit XXSPLTI32DX for sub 64-bit constants

If the APInt returned by BuildVectorSDNode::isConstantSplat() is narrower than
64 bits, the result produced by XXSPLTI32DX is incorrect. The result returned
by the function appears to be incorrect and we'll investigate/fix it in a
follow-up commit. However, since this causes miscompiles, we must
temporarily disable emitting this instruction for such values.
This commit is contained in:
Nemanja Ivanovic 2021-01-27 23:08:39 -06:00
parent 100d58ed00
commit a8e6b38859
2 changed files with 24 additions and 1 deletions

View File

@ -8613,7 +8613,8 @@ SDValue PPCTargetLowering::LowerBUILD_VECTOR(SDValue Op,
PPCISD::XXSPLTI_SP_TO_DP, dl, MVT::v2f64,
DAG.getTargetConstant(APSplatBits.getZExtValue(), dl, MVT::i32));
return DAG.getBitcast(Op.getValueType(), SplatNode);
} else { // We may lose precision, so we have to use XXSPLTI32DX.
} else if (APSplatBits.getBitWidth() == 64) {
// We may lose precision, so we have to use XXSPLTI32DX.
uint32_t Hi =
(uint32_t)((APSplatBits.getZExtValue() & 0xFFFFFFFF00000000LL) >> 32);

View File

@ -100,3 +100,25 @@ define dso_local <8 x i16> @test_xxsplti32dx_9() {
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: 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>
}