-//======- X86InstrFragmentsSIMD.td - x86 ISA -------------*- tablegen -*-=====//
+//===-- X86InstrFragmentsSIMD.td - x86 SIMD ISA ------------*- tablegen -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
-//
+//
//===----------------------------------------------------------------------===//
//
// This file provides pattern fragments useful for SIMD instructions.
def SDTX86VFCMP : SDTypeProfile<1, 3, [SDTCisInt<0>, SDTCisSameAs<1, 2>,
SDTCisFP<1>, SDTCisVT<3, i8>]>;
+def X86umin : SDNode<"X86ISD::UMIN", SDTIntBinOp>;
+def X86umax : SDNode<"X86ISD::UMAX", SDTIntBinOp>;
+def X86smin : SDNode<"X86ISD::SMIN", SDTIntBinOp>;
+def X86smax : SDNode<"X86ISD::SMAX", SDTIntBinOp>;
+
def X86fmin : SDNode<"X86ISD::FMIN", SDTFPBinOp>;
def X86fmax : SDNode<"X86ISD::FMAX", SDTFPBinOp>;
+
+// Commutative and Associative FMIN and FMAX.
+def X86fminc : SDNode<"X86ISD::FMINC", SDTFPBinOp,
+ [SDNPCommutative, SDNPAssociative]>;
+def X86fmaxc : SDNode<"X86ISD::FMAXC", SDTFPBinOp,
+ [SDNPCommutative, SDNPAssociative]>;
+
def X86fand : SDNode<"X86ISD::FAND", SDTFPBinOp,
[SDNPCommutative, SDNPAssociative]>;
def X86for : SDNode<"X86ISD::FOR", SDTFPBinOp,
def X86cmpss : SDNode<"X86ISD::FSETCCss", SDTX86Cmpss>;
def X86cmpsd : SDNode<"X86ISD::FSETCCsd", SDTX86Cmpsd>;
def X86pshufb : SDNode<"X86ISD::PSHUFB",
- SDTypeProfile<1, 2, [SDTCisVT<0, v16i8>, SDTCisSameAs<0,1>,
+ SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>]>>;
def X86andnp : SDNode<"X86ISD::ANDNP",
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisVT<2, v4f32>, SDTCisPtrTy<3>]>>;
def X86vzmovl : SDNode<"X86ISD::VZEXT_MOVL",
SDTypeProfile<1, 1, [SDTCisSameAs<0,1>]>>;
+
+def X86vzmovly : SDNode<"X86ISD::VZEXT_MOVL",
+ SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
+ SDTCisOpSmallerThanOp<1, 0> ]>>;
+
+def X86vsmovl : SDNode<"X86ISD::VSEXT_MOVL",
+ SDTypeProfile<1, 1,
+ [SDTCisVec<0>, SDTCisInt<1>, SDTCisInt<0>]>>;
+
def X86vzload : SDNode<"X86ISD::VZEXT_LOAD", SDTLoad,
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
-def X86vshl : SDNode<"X86ISD::VSHL", SDTIntShiftOp>;
-def X86vshr : SDNode<"X86ISD::VSRL", SDTIntShiftOp>;
-def X86cmpps : SDNode<"X86ISD::CMPPS", SDTX86VFCMP>;
-def X86cmppd : SDNode<"X86ISD::CMPPD", SDTX86VFCMP>;
-def X86pcmpeqb : SDNode<"X86ISD::PCMPEQB", SDTIntBinOp, [SDNPCommutative]>;
-def X86pcmpeqw : SDNode<"X86ISD::PCMPEQW", SDTIntBinOp, [SDNPCommutative]>;
-def X86pcmpeqd : SDNode<"X86ISD::PCMPEQD", SDTIntBinOp, [SDNPCommutative]>;
-def X86pcmpeqq : SDNode<"X86ISD::PCMPEQQ", SDTIntBinOp, [SDNPCommutative]>;
-def X86pcmpgtb : SDNode<"X86ISD::PCMPGTB", SDTIntBinOp>;
-def X86pcmpgtw : SDNode<"X86ISD::PCMPGTW", SDTIntBinOp>;
-def X86pcmpgtd : SDNode<"X86ISD::PCMPGTD", SDTIntBinOp>;
-def X86pcmpgtq : SDNode<"X86ISD::PCMPGTQ", SDTIntBinOp>;
+
+def X86vzext : SDNode<"X86ISD::VZEXT",
+ SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
+ SDTCisInt<0>, SDTCisInt<1>]>>;
+
+def X86vsext : SDNode<"X86ISD::VSEXT",
+ SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
+ SDTCisInt<0>, SDTCisInt<1>]>>;
+
+def X86vfpext : SDNode<"X86ISD::VFPEXT",
+ SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
+ SDTCisFP<0>, SDTCisFP<1>]>>;
+def X86vfpround: SDNode<"X86ISD::VFPROUND",
+ SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
+ SDTCisFP<0>, SDTCisFP<1>]>>;
+
+def X86vshldq : SDNode<"X86ISD::VSHLDQ", SDTIntShiftOp>;
+def X86vshrdq : SDNode<"X86ISD::VSRLDQ", SDTIntShiftOp>;
+def X86cmpp : SDNode<"X86ISD::CMPP", SDTX86VFCMP>;
+def X86pcmpeq : SDNode<"X86ISD::PCMPEQ", SDTIntBinOp, [SDNPCommutative]>;
+def X86pcmpgt : SDNode<"X86ISD::PCMPGT", SDTIntBinOp>;
+
+def X86vshl : SDNode<"X86ISD::VSHL",
+ SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
+ SDTCisVec<2>]>>;
+def X86vsrl : SDNode<"X86ISD::VSRL",
+ SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
+ SDTCisVec<2>]>>;
+def X86vsra : SDNode<"X86ISD::VSRA",
+ SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
+ SDTCisVec<2>]>>;
+
+def X86vshli : SDNode<"X86ISD::VSHLI", SDTIntShiftOp>;
+def X86vsrli : SDNode<"X86ISD::VSRLI", SDTIntShiftOp>;
+def X86vsrai : SDNode<"X86ISD::VSRAI", SDTIntShiftOp>;
def SDTX86CmpPTest : SDTypeProfile<1, 2, [SDTCisVT<0, i32>,
SDTCisVec<1>,
SDTCisSameAs<2, 1>]>;
+def X86subus : SDNode<"X86ISD::SUBUS", SDTIntBinOp>;
def X86ptest : SDNode<"X86ISD::PTEST", SDTX86CmpPTest>;
def X86testp : SDNode<"X86ISD::TESTP", SDTX86CmpPTest>;
+def X86pmuludq : SDNode<"X86ISD::PMULUDQ",
+ SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisVec<1>,
+ SDTCisSameAs<1,2>]>>;
+
// Specific shuffle nodes - At some point ISD::VECTOR_SHUFFLE will always get
// translated into one of the target nodes below during lowering.
// Note: this is a work in progress...
SDTCisSameAs<0,2>, SDTCisInt<3>]>;
def SDTVBroadcast : SDTypeProfile<1, 1, [SDTCisVec<0>]>;
+def SDTBlend : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
+ SDTCisSameAs<1,2>, SDTCisVT<3, i32>]>;
+
+def SDTFma : SDTypeProfile<1, 3, [SDTCisSameAs<0,1>,
+ SDTCisSameAs<1,2>, SDTCisSameAs<1,3>]>;
def X86PAlign : SDNode<"X86ISD::PALIGN", SDTShuff3OpI>;
def X86Unpckh : SDNode<"X86ISD::UNPCKH", SDTShuff2Op>;
def X86VPermilp : SDNode<"X86ISD::VPERMILP", SDTShuff2OpI>;
+def X86VPermv : SDNode<"X86ISD::VPERMV", SDTShuff2Op>;
+def X86VPermi : SDNode<"X86ISD::VPERMI", SDTShuff2OpI>;
def X86VPerm2x128 : SDNode<"X86ISD::VPERM2X128", SDTShuff3OpI>;
def X86VBroadcast : SDNode<"X86ISD::VBROADCAST", SDTVBroadcast>;
+def X86Blendi : SDNode<"X86ISD::BLENDI", SDTBlend>;
+def X86Fmadd : SDNode<"X86ISD::FMADD", SDTFma>;
+def X86Fnmadd : SDNode<"X86ISD::FNMADD", SDTFma>;
+def X86Fmsub : SDNode<"X86ISD::FMSUB", SDTFma>;
+def X86Fnmsub : SDNode<"X86ISD::FNMSUB", SDTFma>;
+def X86Fmaddsub : SDNode<"X86ISD::FMADDSUB", SDTFma>;
+def X86Fmsubadd : SDNode<"X86ISD::FMSUBADD", SDTFma>;
+
+def SDT_PCMPISTRI : SDTypeProfile<2, 3, [SDTCisVT<0, i32>, SDTCisVT<1, i32>,
+ SDTCisVT<2, v16i8>, SDTCisVT<3, v16i8>,
+ SDTCisVT<4, i8>]>;
+def SDT_PCMPESTRI : SDTypeProfile<2, 5, [SDTCisVT<0, i32>, SDTCisVT<1, i32>,
+ SDTCisVT<2, v16i8>, SDTCisVT<3, i32>,
+ SDTCisVT<4, v16i8>, SDTCisVT<5, i32>,
+ SDTCisVT<6, i8>]>;
+
+def X86pcmpistri : SDNode<"X86ISD::PCMPISTRI", SDT_PCMPISTRI>;
+def X86pcmpestri : SDNode<"X86ISD::PCMPESTRI", SDT_PCMPESTRI>;
+
//===----------------------------------------------------------------------===//
// SSE Complex Patterns
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// 128-bit load pattern fragments
+// NOTE: all 128-bit integer vector loads are promoted to v2i64
def loadv4f32 : PatFrag<(ops node:$ptr), (v4f32 (load node:$ptr))>;
def loadv2f64 : PatFrag<(ops node:$ptr), (v2f64 (load node:$ptr))>;
-def loadv4i32 : PatFrag<(ops node:$ptr), (v4i32 (load node:$ptr))>;
def loadv2i64 : PatFrag<(ops node:$ptr), (v2i64 (load node:$ptr))>;
// 256-bit load pattern fragments
+// NOTE: all 256-bit integer vector loads are promoted to v4i64
def loadv8f32 : PatFrag<(ops node:$ptr), (v8f32 (load node:$ptr))>;
def loadv4f64 : PatFrag<(ops node:$ptr), (v4f64 (load node:$ptr))>;
-def loadv8i32 : PatFrag<(ops node:$ptr), (v8i32 (load node:$ptr))>;
def loadv4i64 : PatFrag<(ops node:$ptr), (v4i64 (load node:$ptr))>;
+// 128-/256-bit extload pattern fragments
+def extloadv2f32 : PatFrag<(ops node:$ptr), (v2f64 (extloadvf32 node:$ptr))>;
+def extloadv4f32 : PatFrag<(ops node:$ptr), (v4f64 (extloadvf32 node:$ptr))>;
+
// Like 'store', but always requires 128-bit vector alignment.
def alignedstore : PatFrag<(ops node:$val, node:$ptr),
(store node:$val, node:$ptr), [{
return cast<LoadSDNode>(N)->getAlignment() >= 16;
}]>;
+// Like 'X86vzload', but always requires 128-bit vector alignment.
+def alignedX86vzload : PatFrag<(ops node:$ptr), (X86vzload node:$ptr), [{
+ return cast<MemSDNode>(N)->getAlignment() >= 16;
+}]>;
+
// Like 'load', but always requires 256-bit vector alignment.
def alignedload256 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
return cast<LoadSDNode>(N)->getAlignment() >= 32;
(f64 (alignedload node:$ptr))>;
// 128-bit aligned load pattern fragments
+// NOTE: all 128-bit integer vector loads are promoted to v2i64
def alignedloadv4f32 : PatFrag<(ops node:$ptr),
(v4f32 (alignedload node:$ptr))>;
def alignedloadv2f64 : PatFrag<(ops node:$ptr),
(v2f64 (alignedload node:$ptr))>;
-def alignedloadv4i32 : PatFrag<(ops node:$ptr),
- (v4i32 (alignedload node:$ptr))>;
def alignedloadv2i64 : PatFrag<(ops node:$ptr),
(v2i64 (alignedload node:$ptr))>;
// 256-bit aligned load pattern fragments
+// NOTE: all 256-bit integer vector loads are promoted to v4i64
def alignedloadv8f32 : PatFrag<(ops node:$ptr),
(v8f32 (alignedload256 node:$ptr))>;
def alignedloadv4f64 : PatFrag<(ops node:$ptr),
(v4f64 (alignedload256 node:$ptr))>;
-def alignedloadv8i32 : PatFrag<(ops node:$ptr),
- (v8i32 (alignedload256 node:$ptr))>;
def alignedloadv4i64 : PatFrag<(ops node:$ptr),
(v4i64 (alignedload256 node:$ptr))>;
def memopfsf64 : PatFrag<(ops node:$ptr), (f64 (memop node:$ptr))>;
// 128-bit memop pattern fragments
+// NOTE: all 128-bit integer vector loads are promoted to v2i64
def memopv4f32 : PatFrag<(ops node:$ptr), (v4f32 (memop node:$ptr))>;
def memopv2f64 : PatFrag<(ops node:$ptr), (v2f64 (memop node:$ptr))>;
-def memopv4i32 : PatFrag<(ops node:$ptr), (v4i32 (memop node:$ptr))>;
def memopv2i64 : PatFrag<(ops node:$ptr), (v2i64 (memop node:$ptr))>;
-def memopv8i16 : PatFrag<(ops node:$ptr), (v8i16 (memop node:$ptr))>;
-def memopv16i8 : PatFrag<(ops node:$ptr), (v16i8 (memop node:$ptr))>;
// 256-bit memop pattern fragments
+// NOTE: all 256-bit integer vector loads are promoted to v4i64
def memopv8f32 : PatFrag<(ops node:$ptr), (v8f32 (memop node:$ptr))>;
def memopv4f64 : PatFrag<(ops node:$ptr), (v4f64 (memop node:$ptr))>;
def memopv4i64 : PatFrag<(ops node:$ptr), (v4i64 (memop node:$ptr))>;
-def memopv8i32 : PatFrag<(ops node:$ptr), (v8i32 (memop node:$ptr))>;
-def memopv16i16 : PatFrag<(ops node:$ptr), (v16i16 (memop node:$ptr))>;
-def memopv32i8 : PatFrag<(ops node:$ptr), (v32i8 (memop node:$ptr))>;
// SSSE3 uses MMX registers for some instructions. They aren't aligned on a
// 16-byte boundary.
}]>;
def alignednontemporalstore : PatFrag<(ops node:$val, node:$ptr),
- (st node:$val, node:$ptr), [{
+ (st node:$val, node:$ptr), [{
if (StoreSDNode *ST = dyn_cast<StoreSDNode>(N))
return ST->isNonTemporal() && !ST->isTruncatingStore() &&
ST->getAddressingMode() == ISD::UNINDEXED &&
}]>;
def unalignednontemporalstore : PatFrag<(ops node:$val, node:$ptr),
- (st node:$val, node:$ptr), [{
+ (st node:$val, node:$ptr), [{
if (StoreSDNode *ST = dyn_cast<StoreSDNode>(N))
return ST->isNonTemporal() &&
ST->getAlignment() < 16;
return getI32Imm(N->getZExtValue() >> 3);
}]>;
-// SHUFFLE_get_shuf_imm xform function: convert vector_shuffle mask to PSHUF*,
-// SHUFP* etc. imm.
-def SHUFFLE_get_shuf_imm : SDNodeXForm<vector_shuffle, [{
- return getI8Imm(X86::getShuffleSHUFImmediate(cast<ShuffleVectorSDNode>(N)));
-}]>;
-
-// SHUFFLE_get_pshufhw_imm xform function: convert vector_shuffle mask to
-// PSHUFHW imm.
-def SHUFFLE_get_pshufhw_imm : SDNodeXForm<vector_shuffle, [{
- return getI8Imm(X86::getShufflePSHUFHWImmediate(N));
-}]>;
-
-// SHUFFLE_get_pshuflw_imm xform function: convert vector_shuffle mask to
-// PSHUFLW imm.
-def SHUFFLE_get_pshuflw_imm : SDNodeXForm<vector_shuffle, [{
- return getI8Imm(X86::getShufflePSHUFLWImmediate(N));
-}]>;
-
// EXTRACT_get_vextractf128_imm xform function: convert extract_subvector index
// to VEXTRACTF128 imm.
def EXTRACT_get_vextractf128_imm : SDNodeXForm<extract_subvector, [{
return getI8Imm(X86::getInsertVINSERTF128Immediate(N));
}]>;
-def splat_lo : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- ShuffleVectorSDNode *SVOp = cast<ShuffleVectorSDNode>(N);
- return SVOp->isSplat() && SVOp->getSplatIndex() == 0;
-}]>;
-
-def movddup : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isMOVDDUPMask(cast<ShuffleVectorSDNode>(N));
-}]>;
-
-def movhlps : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isMOVHLPSMask(cast<ShuffleVectorSDNode>(N));
-}]>;
-
-def movhlps_undef : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isMOVHLPS_v_undef_Mask(cast<ShuffleVectorSDNode>(N));
-}]>;
-
-def movlhps : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isMOVLHPSMask(cast<ShuffleVectorSDNode>(N));
-}]>;
-
-def movlp : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isMOVLPMask(cast<ShuffleVectorSDNode>(N));
-}]>;
-
-def movl : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isMOVLMask(cast<ShuffleVectorSDNode>(N));
-}]>;
-
-def unpckl : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isUNPCKLMask(cast<ShuffleVectorSDNode>(N), Subtarget->hasAVX2());
-}]>;
-
-def unpckh : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isUNPCKHMask(cast<ShuffleVectorSDNode>(N), Subtarget->hasAVX2());
-}]>;
-
-def pshufd : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isPSHUFDMask(cast<ShuffleVectorSDNode>(N));
-}], SHUFFLE_get_shuf_imm>;
-
-def shufp : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isSHUFPMask(cast<ShuffleVectorSDNode>(N), Subtarget->hasAVX());
-}], SHUFFLE_get_shuf_imm>;
-
-def pshufhw : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isPSHUFHWMask(cast<ShuffleVectorSDNode>(N));
-}], SHUFFLE_get_pshufhw_imm>;
-
-def pshuflw : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isPSHUFLWMask(cast<ShuffleVectorSDNode>(N));
-}], SHUFFLE_get_pshuflw_imm>;
-
def vextractf128_extract : PatFrag<(ops node:$bigvec, node:$index),
(extract_subvector node:$bigvec,
node:$index), [{