def X86frcp : SDNode<"X86ISD::FRCP", SDTFPUnaryOp>;
def X86fsrl : SDNode<"X86ISD::FSRL", SDTX86FPShiftOp>;
def X86fgetsign: SDNode<"X86ISD::FGETSIGNx86",SDTFPToIntOp>;
+def X86fhadd : SDNode<"X86ISD::FHADD", SDTFPBinOp>;
+def X86fhsub : SDNode<"X86ISD::FHSUB", SDTFPBinOp>;
+def X86hadd : SDNode<"X86ISD::HADD", SDTIntBinOp>;
+def X86hsub : SDNode<"X86ISD::HSUB", SDTIntBinOp>;
def X86comi : SDNode<"X86ISD::COMI", SDTX86CmpTest>;
def X86ucomi : SDNode<"X86ISD::UCOMI", SDTX86CmpTest>;
+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 X86pandn : SDNode<"X86ISD::PANDN",
- SDTypeProfile<1, 2, [SDTCisVT<0, v2i64>, SDTCisSameAs<0,1>,
+def X86andnp : SDNode<"X86ISD::ANDNP",
+ SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>]>>;
-def X86psignb : SDNode<"X86ISD::PSIGNB",
- SDTypeProfile<1, 2, [SDTCisVT<0, v16i8>, SDTCisSameAs<0,1>,
+def X86psign : SDNode<"X86ISD::PSIGN",
+ SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>]>>;
-def X86psignw : SDNode<"X86ISD::PSIGNW",
- SDTypeProfile<1, 2, [SDTCisVT<0, v8i16>, SDTCisSameAs<0,1>,
- SDTCisSameAs<0,2>]>>;
-def X86psignd : SDNode<"X86ISD::PSIGND",
- SDTypeProfile<1, 2, [SDTCisVT<0, v4i32>, SDTCisSameAs<0,1>,
- SDTCisSameAs<0,2>]>>;
-def X86pblendv : SDNode<"X86ISD::PBLENDVB",
- SDTypeProfile<1, 3, [SDTCisVT<0, v16i8>, SDTCisSameAs<0,1>,
- SDTCisSameAs<0,2>, SDTCisSameAs<0,3>]>>;
def X86pextrb : SDNode<"X86ISD::PEXTRB",
SDTypeProfile<1, 2, [SDTCisVT<0, i32>, SDTCisPtrTy<2>]>>;
def X86pextrw : SDNode<"X86ISD::PEXTRW",
SDTCisVT<2, v4f32>, SDTCisPtrTy<3>]>>;
def X86vzmovl : SDNode<"X86ISD::VZEXT_MOVL",
SDTypeProfile<1, 1, [SDTCisSameAs<0,1>]>>;
+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 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>,
def X86ptest : SDNode<"X86ISD::PTEST", SDTX86CmpPTest>;
def X86testp : SDNode<"X86ISD::TESTP", SDTX86CmpPTest>;
+def X86vpcom : SDNode<"X86ISD::VPCOM",
+ SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
+ SDTCisSameAs<0,2>, SDTCisVT<3, i8>]>>;
+def X86vpcomu : SDNode<"X86ISD::VPCOMU",
+ SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
+ SDTCisSameAs<0,2>, SDTCisVT<3, i8>]>>;
+
+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...
def SDTShuff3OpI : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
SDTCisSameAs<0,2>, SDTCisInt<3>]>;
+def SDTVBroadcast : SDTypeProfile<1, 1, [SDTCisVec<0>]>;
+
def X86PAlign : SDNode<"X86ISD::PALIGN", SDTShuff3OpI>;
def X86PShufd : SDNode<"X86ISD::PSHUFD", SDTShuff2OpI>;
def X86PShufhw : SDNode<"X86ISD::PSHUFHW", SDTShuff2OpI>;
def X86PShuflw : SDNode<"X86ISD::PSHUFLW", SDTShuff2OpI>;
-def X86Shufpd : SDNode<"X86ISD::SHUFPD", SDTShuff3OpI>;
-def X86Shufps : SDNode<"X86ISD::SHUFPS", SDTShuff3OpI>;
+def X86Shufp : SDNode<"X86ISD::SHUFP", SDTShuff3OpI>;
def X86Movddup : SDNode<"X86ISD::MOVDDUP", SDTShuff1Op>;
def X86Movshdup : SDNode<"X86ISD::MOVSHDUP", SDTShuff1Op>;
def X86Movlhps : SDNode<"X86ISD::MOVLHPS", SDTShuff2Op>;
def X86Movlhpd : SDNode<"X86ISD::MOVLHPD", SDTShuff2Op>;
def X86Movhlps : SDNode<"X86ISD::MOVHLPS", SDTShuff2Op>;
-def X86Movhlpd : SDNode<"X86ISD::MOVHLPD", SDTShuff2Op>;
def X86Movlps : SDNode<"X86ISD::MOVLPS", SDTShuff2Op>;
def X86Movlpd : SDNode<"X86ISD::MOVLPD", SDTShuff2Op>;
-def X86Unpcklps : SDNode<"X86ISD::UNPCKLPS", SDTShuff2Op>;
-def X86Unpcklpd : SDNode<"X86ISD::UNPCKLPD", SDTShuff2Op>;
-def X86Unpcklpsy : SDNode<"X86ISD::VUNPCKLPSY", SDTShuff2Op>;
-def X86Unpcklpdy : SDNode<"X86ISD::VUNPCKLPDY", SDTShuff2Op>;
-def X86Unpckhps : SDNode<"X86ISD::UNPCKHPS", SDTShuff2Op>;
-def X86Unpckhpd : SDNode<"X86ISD::UNPCKHPD", SDTShuff2Op>;
+def X86Unpckl : SDNode<"X86ISD::UNPCKL", SDTShuff2Op>;
+def X86Unpckh : SDNode<"X86ISD::UNPCKH", SDTShuff2Op>;
-def X86Punpcklbw : SDNode<"X86ISD::PUNPCKLBW", SDTShuff2Op>;
-def X86Punpcklwd : SDNode<"X86ISD::PUNPCKLWD", SDTShuff2Op>;
-def X86Punpckldq : SDNode<"X86ISD::PUNPCKLDQ", SDTShuff2Op>;
-def X86Punpcklqdq : SDNode<"X86ISD::PUNPCKLQDQ", SDTShuff2Op>;
+def X86VPermilp : SDNode<"X86ISD::VPERMILP", SDTShuff2OpI>;
-def X86Punpckhbw : SDNode<"X86ISD::PUNPCKHBW", SDTShuff2Op>;
-def X86Punpckhwd : SDNode<"X86ISD::PUNPCKHWD", SDTShuff2Op>;
-def X86Punpckhdq : SDNode<"X86ISD::PUNPCKHDQ", SDTShuff2Op>;
-def X86Punpckhqdq : SDNode<"X86ISD::PUNPCKHQDQ", SDTShuff2Op>;
+def X86VPerm2x128 : SDNode<"X86ISD::VPERM2X128", SDTShuff3OpI>;
+
+def X86VBroadcast : SDNode<"X86ISD::VBROADCAST", SDTVBroadcast>;
//===----------------------------------------------------------------------===//
// SSE Complex Patterns
let PrintMethod = "printf32mem";
let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc_nosp, i32imm, i8imm);
let ParserMatchClass = X86MemAsmOperand;
+ let OperandType = "OPERAND_MEMORY";
}
def sdmem : Operand<v2f64> {
let PrintMethod = "printf64mem";
let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc_nosp, i32imm, i8imm);
let ParserMatchClass = X86MemAsmOperand;
+ let OperandType = "OPERAND_MEMORY";
}
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// 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))>;
-// Like 'store', but always requires vector alignment.
+// Like 'store', but always requires 128-bit vector alignment.
def alignedstore : PatFrag<(ops node:$val, node:$ptr),
(store node:$val, node:$ptr), [{
return cast<StoreSDNode>(N)->getAlignment() >= 16;
}]>;
-// Like 'load', but always requires vector alignment.
+// Like 'store', but always requires 256-bit vector alignment.
+def alignedstore256 : PatFrag<(ops node:$val, node:$ptr),
+ (store node:$val, node:$ptr), [{
+ return cast<StoreSDNode>(N)->getAlignment() >= 32;
+}]>;
+
+// Like 'load', but always requires 128-bit vector alignment.
def alignedload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
return cast<LoadSDNode>(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;
+}]>;
+
def alignedloadfsf32 : PatFrag<(ops node:$ptr),
(f32 (alignedload node:$ptr))>;
def alignedloadfsf64 : PatFrag<(ops node:$ptr),
(f64 (alignedload node:$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:$ptr),
- (v8f32 (alignedload node:$ptr))>;
+ (v8f32 (alignedload256 node:$ptr))>;
def alignedloadv4f64 : PatFrag<(ops node:$ptr),
- (v4f64 (alignedload node:$ptr))>;
-def alignedloadv8i32 : PatFrag<(ops node:$ptr),
- (v8i32 (alignedload node:$ptr))>;
+ (v4f64 (alignedload256 node:$ptr))>;
def alignedloadv4i64 : PatFrag<(ops node:$ptr),
- (v4i64 (alignedload node:$ptr))>;
+ (v4i64 (alignedload256 node:$ptr))>;
// Like 'load', but uses special alignment checks suitable for use in
// memory operands in most SSE instructions, which are required to
def memopfsf64 : PatFrag<(ops node:$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:$ptr))>;
// 256-bit memop pattern fragments
-def memopv32i8 : PatFrag<(ops node:$ptr), (v32i8 (memop node:$ptr))>;
+// NOTE: all 256-bit integer vector loads are promoted to v4i64
def memopv8f32 : PatFrag<(ops node:$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:$ptr))>;
// SSSE3 uses MMX registers for some instructions. They aren't aligned on a
// 16-byte boundary.
def bc_v2i64 : PatFrag<(ops node:$in), (v2i64 (bitconvert node:$in))>;
// 256-bit bitconvert pattern fragments
+def bc_v32i8 : PatFrag<(ops node:$in), (v32i8 (bitconvert node:$in))>;
+def bc_v16i16 : PatFrag<(ops node:$in), (v16i16 (bitconvert node:$in))>;
def bc_v8i32 : PatFrag<(ops node:$in), (v8i32 (bitconvert node:$in))>;
+def bc_v4i64 : PatFrag<(ops node:$in), (v4i64 (bitconvert node:$in))>;
def vzmovl_v2i64 : PatFrag<(ops node:$src),
(bitconvert (v2i64 (X86vzmovl
// 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(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));
-}]>;
-
-// SHUFFLE_get_palign_imm xform function: convert vector_shuffle mask to
-// a PALIGNR imm.
-def SHUFFLE_get_palign_imm : SDNodeXForm<vector_shuffle, [{
- return getI8Imm(X86::getShufflePALIGNRImmediate(N));
+ return getI8Imm(X86::getShuffleSHUFImmediate(cast<ShuffleVectorSDNode>(N)));
}]>;
// EXTRACT_get_vextractf128_imm xform function: convert extract_subvector index
return getI8Imm(X86::getExtractVEXTRACTF128Immediate(N));
}]>;
-// INSERT_get_vinsertf128_imm xform function: convert insert_subvector index to
+// INSERT_get_vinsertf128_imm xform function: convert insert_subvector index to
// VINSERTF128 imm.
def INSERT_get_vinsertf128_imm : SDNodeXForm<insert_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));
return X86::isMOVLMask(cast<ShuffleVectorSDNode>(N));
}]>;
-def movshdup : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isMOVSHDUPMask(cast<ShuffleVectorSDNode>(N));
-}]>;
-
-def movsldup : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isMOVSLDUPMask(cast<ShuffleVectorSDNode>(N));
-}]>;
-
def unpckl : PatFrag<(ops node:$lhs, node:$rhs),
(vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isUNPCKLMask(cast<ShuffleVectorSDNode>(N));
+ 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));
+ return X86::isUNPCKHMask(cast<ShuffleVectorSDNode>(N), Subtarget->hasAVX2());
}]>;
-def unpckl_undef : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isUNPCKL_v_undef_Mask(cast<ShuffleVectorSDNode>(N));
-}]>;
-
-def unpckh_undef : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isUNPCKH_v_undef_Mask(cast<ShuffleVectorSDNode>(N));
-}]>;
-
-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));
-}], 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 palign : PatFrag<(ops node:$lhs, node:$rhs),
- (vector_shuffle node:$lhs, node:$rhs), [{
- return X86::isPALIGNRMask(cast<ShuffleVectorSDNode>(N));
-}], SHUFFLE_get_palign_imm>;
-
def vextractf128_extract : PatFrag<(ops node:$bigvec, node:$index),
(extract_subvector node:$bigvec,
node:$index), [{
node:$index), [{
return X86::isVINSERTF128Index(N);
}], INSERT_get_vinsertf128_imm>;
+