[X86][SSE] Vectorize v2i32 to v2f64 conversions
This patch enables support for the conversion of v2i32 to v2f64 to use the CVTDQ2PD xmm instruction and stay on the SSE unit instead of scalarizing, sign extending to i64 and using CVTSI2SDQ scalar conversions.
Differential Revision: http://reviews.llvm.org/D10433
llvm-svn: 239855
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 6b76fbc..da3f9c1 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -915,6 +915,8 @@
setOperationAction(ISD::FP_TO_SINT, MVT::v4i32, Legal);
setOperationAction(ISD::SINT_TO_FP, MVT::v4i32, Legal);
+ setOperationAction(ISD::SINT_TO_FP, MVT::v2i32, Custom);
+
setOperationAction(ISD::UINT_TO_FP, MVT::v4i8, Custom);
setOperationAction(ISD::UINT_TO_FP, MVT::v4i16, Custom);
// As there is no 64-bit GPR available, we need build a special custom
@@ -11648,15 +11650,21 @@
SDValue X86TargetLowering::LowerSINT_TO_FP(SDValue Op,
SelectionDAG &DAG) const {
- MVT SrcVT = Op.getOperand(0).getSimpleValueType();
+ SDValue Src = Op.getOperand(0);
+ MVT SrcVT = Src.getSimpleValueType();
+ MVT VT = Op.getSimpleValueType();
SDLoc dl(Op);
if (SrcVT.isVector()) {
+ if (SrcVT == MVT::v2i32 && VT == MVT::v2f64) {
+ return DAG.getNode(X86ISD::CVTDQ2PD, dl, VT,
+ DAG.getNode(ISD::CONCAT_VECTORS, dl, MVT::v4i32, Src,
+ DAG.getUNDEF(SrcVT)));
+ }
if (SrcVT.getVectorElementType() == MVT::i1) {
MVT IntegerVT = MVT::getVectorVT(MVT::i32, SrcVT.getVectorNumElements());
return DAG.getNode(ISD::SINT_TO_FP, dl, Op.getValueType(),
- DAG.getNode(ISD::SIGN_EXTEND, dl, IntegerVT,
- Op.getOperand(0)));
+ DAG.getNode(ISD::SIGN_EXTEND, dl, IntegerVT, Src));
}
return SDValue();
}
@@ -18498,6 +18506,7 @@
case X86ISD::VINSERT: return "X86ISD::VINSERT";
case X86ISD::VFPEXT: return "X86ISD::VFPEXT";
case X86ISD::VFPROUND: return "X86ISD::VFPROUND";
+ case X86ISD::CVTDQ2PD: return "X86ISD::CVTDQ2PD";
case X86ISD::VSHLDQ: return "X86ISD::VSHLDQ";
case X86ISD::VSRLDQ: return "X86ISD::VSRLDQ";
case X86ISD::VSHL: return "X86ISD::VSHL";
diff --git a/llvm/lib/Target/X86/X86ISelLowering.h b/llvm/lib/Target/X86/X86ISelLowering.h
index efda861..7f00c73 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.h
+++ b/llvm/lib/Target/X86/X86ISelLowering.h
@@ -293,6 +293,9 @@
// Vector FP round.
VFPROUND,
+ // Vector signed integer to double.
+ CVTDQ2PD,
+
// 128-bit vector logical left / right shift
VSHLDQ, VSRLDQ,
diff --git a/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td b/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td
index f158d12..889fd39 100644
--- a/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td
+++ b/llvm/lib/Target/X86/X86InstrFragmentsSIMD.td
@@ -72,6 +72,9 @@
def X86ucomi : SDNode<"X86ISD::UCOMI", SDTX86CmpTest>;
def X86cmps : SDNode<"X86ISD::FSETCC", SDTX86Cmps>;
//def X86cmpsd : SDNode<"X86ISD::FSETCCsd", SDTX86Cmpsd>;
+def X86cvtdq2pd: SDNode<"X86ISD::CVTDQ2PD",
+ SDTypeProfile<1, 1, [SDTCisVT<0, v2f64>,
+ SDTCisVT<1, v4i32>]>>;
def X86pshufb : SDNode<"X86ISD::PSHUFB",
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>]>>;
diff --git a/llvm/lib/Target/X86/X86InstrSSE.td b/llvm/lib/Target/X86/X86InstrSSE.td
index 8294e38..9562918 100644
--- a/llvm/lib/Target/X86/X86InstrSSE.td
+++ b/llvm/lib/Target/X86/X86InstrSSE.td
@@ -2234,14 +2234,27 @@
[(set VR128:$dst, (int_x86_sse2_cvtdq2pd VR128:$src))],
IIC_SSE_CVT_PD_RM>, Sched<[WriteCvtI2F]>;
-// AVX 256-bit register conversion intrinsics
+// AVX register conversion intrinsics
let Predicates = [HasAVX] in {
+ def : Pat<(v2f64 (X86cvtdq2pd (v4i32 VR128:$src))),
+ (VCVTDQ2PDrr VR128:$src)>;
+ def : Pat<(v2f64 (X86cvtdq2pd (bc_v4i32 (loadv2i64 addr:$src)))),
+ (VCVTDQ2PDrm addr:$src)>;
+
def : Pat<(v4f64 (sint_to_fp (v4i32 VR128:$src))),
(VCVTDQ2PDYrr VR128:$src)>;
def : Pat<(v4f64 (sint_to_fp (bc_v4i32 (loadv2i64 addr:$src)))),
(VCVTDQ2PDYrm addr:$src)>;
} // Predicates = [HasAVX]
+// SSE2 register conversion intrinsics
+let Predicates = [HasSSE2] in {
+ def : Pat<(v2f64 (X86cvtdq2pd (v4i32 VR128:$src))),
+ (CVTDQ2PDrr VR128:$src)>;
+ def : Pat<(v2f64 (X86cvtdq2pd (bc_v4i32 (loadv2i64 addr:$src)))),
+ (CVTDQ2PDrm addr:$src)>;
+} // Predicates = [HasSSE2]
+
// Convert packed double to packed single
// The assembler can recognize rr 256-bit instructions by seeing a ymm
// register, but the same isn't true when using memory operands instead.