forked from OSchip/llvm-project
2398 lines
116 KiB
C++
2398 lines
116 KiB
C++
//====- X86InstrSSE.td - Describe the X86 Instruction Set -------*- C++ -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file was developed by Evan Cheng and is distributed under the University
|
|
// of Illinois Open Source License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file describes the X86 SSE instruction set, defining the instructions,
|
|
// and properties of the instructions which are needed for code generation,
|
|
// machine code emission, and analysis.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE specific DAG Nodes.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def SDTX86FPShiftOp : SDTypeProfile<1, 2, [ SDTCisSameAs<0, 1>,
|
|
SDTCisFP<0>, SDTCisInt<2> ]>;
|
|
|
|
def X86loadp : SDNode<"X86ISD::LOAD_PACK", SDTLoad, [SDNPHasChain]>;
|
|
def X86loadu : SDNode<"X86ISD::LOAD_UA", SDTLoad, [SDNPHasChain]>;
|
|
def X86fmin : SDNode<"X86ISD::FMIN", SDTFPBinOp>;
|
|
def X86fmax : SDNode<"X86ISD::FMAX", SDTFPBinOp>;
|
|
def X86fand : SDNode<"X86ISD::FAND", SDTFPBinOp,
|
|
[SDNPCommutative, SDNPAssociative]>;
|
|
def X86for : SDNode<"X86ISD::FOR", SDTFPBinOp,
|
|
[SDNPCommutative, SDNPAssociative]>;
|
|
def X86fxor : SDNode<"X86ISD::FXOR", SDTFPBinOp,
|
|
[SDNPCommutative, SDNPAssociative]>;
|
|
def X86fsrl : SDNode<"X86ISD::FSRL", SDTX86FPShiftOp>;
|
|
def X86comi : SDNode<"X86ISD::COMI", SDTX86CmpTest,
|
|
[SDNPHasChain, SDNPOutFlag]>;
|
|
def X86ucomi : SDNode<"X86ISD::UCOMI", SDTX86CmpTest,
|
|
[SDNPHasChain, SDNPOutFlag]>;
|
|
def X86s2vec : SDNode<"X86ISD::S2VEC", SDTypeProfile<1, 1, []>, []>;
|
|
def X86pextrw : SDNode<"X86ISD::PEXTRW", SDTypeProfile<1, 2, []>, []>;
|
|
def X86pinsrw : SDNode<"X86ISD::PINSRW", SDTypeProfile<1, 3, []>, []>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE 'Special' Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def IMPLICIT_DEF_VR128 : I<0, Pseudo, (ops VR128:$dst),
|
|
"#IMPLICIT_DEF $dst",
|
|
[(set VR128:$dst, (v4f32 (undef)))]>,
|
|
Requires<[HasSSE1]>;
|
|
def IMPLICIT_DEF_FR32 : I<0, Pseudo, (ops FR32:$dst),
|
|
"#IMPLICIT_DEF $dst",
|
|
[(set FR32:$dst, (undef))]>, Requires<[HasSSE2]>;
|
|
def IMPLICIT_DEF_FR64 : I<0, Pseudo, (ops FR64:$dst),
|
|
"#IMPLICIT_DEF $dst",
|
|
[(set FR64:$dst, (undef))]>, Requires<[HasSSE2]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE Complex Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// These are 'extloads' from a scalar to the low element of a vector, zeroing
|
|
// the top elements. These are used for the SSE 'ss' and 'sd' instruction
|
|
// forms.
|
|
def sse_load_f32 : ComplexPattern<v4f32, 4, "SelectScalarSSELoad", [],
|
|
[SDNPHasChain]>;
|
|
def sse_load_f64 : ComplexPattern<v2f64, 4, "SelectScalarSSELoad", [],
|
|
[SDNPHasChain]>;
|
|
|
|
def ssmem : Operand<v4f32> {
|
|
let PrintMethod = "printf32mem";
|
|
let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc, i32imm);
|
|
}
|
|
def sdmem : Operand<v2f64> {
|
|
let PrintMethod = "printf64mem";
|
|
let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc, i32imm);
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE pattern fragments
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def X86loadpf32 : PatFrag<(ops node:$ptr), (f32 (X86loadp node:$ptr))>;
|
|
def X86loadpf64 : PatFrag<(ops node:$ptr), (f64 (X86loadp node:$ptr))>;
|
|
|
|
def loadv4f32 : PatFrag<(ops node:$ptr), (v4f32 (load node:$ptr))>;
|
|
def loadv2f64 : PatFrag<(ops node:$ptr), (v2f64 (load node:$ptr))>;
|
|
def loadv2i32 : PatFrag<(ops node:$ptr), (v2i32 (load node:$ptr))>;
|
|
def loadv2i64 : PatFrag<(ops node:$ptr), (v2i64 (load node:$ptr))>;
|
|
|
|
def bc_v4f32 : PatFrag<(ops node:$in), (v4f32 (bitconvert node:$in))>;
|
|
def bc_v2f64 : PatFrag<(ops node:$in), (v2f64 (bitconvert node:$in))>;
|
|
def bc_v16i8 : PatFrag<(ops node:$in), (v16i8 (bitconvert node:$in))>;
|
|
def bc_v8i16 : PatFrag<(ops node:$in), (v8i16 (bitconvert node:$in))>;
|
|
def bc_v4i32 : PatFrag<(ops node:$in), (v4i32 (bitconvert node:$in))>;
|
|
def bc_v2i64 : PatFrag<(ops node:$in), (v2i64 (bitconvert node:$in))>;
|
|
|
|
def fp32imm0 : PatLeaf<(f32 fpimm), [{
|
|
return N->isExactlyValue(+0.0);
|
|
}]>;
|
|
|
|
def PSxLDQ_imm : SDNodeXForm<imm, [{
|
|
// Transformation function: imm >> 3
|
|
return getI32Imm(N->getValue() >> 3);
|
|
}]>;
|
|
|
|
// SHUFFLE_get_shuf_imm xform function: convert vector_shuffle mask to PSHUF*,
|
|
// SHUFP* etc. imm.
|
|
def SHUFFLE_get_shuf_imm : SDNodeXForm<build_vector, [{
|
|
return getI8Imm(X86::getShuffleSHUFImmediate(N));
|
|
}]>;
|
|
|
|
// SHUFFLE_get_pshufhw_imm xform function: convert vector_shuffle mask to
|
|
// PSHUFHW imm.
|
|
def SHUFFLE_get_pshufhw_imm : SDNodeXForm<build_vector, [{
|
|
return getI8Imm(X86::getShufflePSHUFHWImmediate(N));
|
|
}]>;
|
|
|
|
// SHUFFLE_get_pshuflw_imm xform function: convert vector_shuffle mask to
|
|
// PSHUFLW imm.
|
|
def SHUFFLE_get_pshuflw_imm : SDNodeXForm<build_vector, [{
|
|
return getI8Imm(X86::getShufflePSHUFLWImmediate(N));
|
|
}]>;
|
|
|
|
def SSE_splat_mask : PatLeaf<(build_vector), [{
|
|
return X86::isSplatMask(N);
|
|
}], SHUFFLE_get_shuf_imm>;
|
|
|
|
def SSE_splat_lo_mask : PatLeaf<(build_vector), [{
|
|
return X86::isSplatLoMask(N);
|
|
}]>;
|
|
|
|
def MOVHLPS_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isMOVHLPSMask(N);
|
|
}]>;
|
|
|
|
def MOVHLPS_v_undef_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isMOVHLPS_v_undef_Mask(N);
|
|
}]>;
|
|
|
|
def MOVHP_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isMOVHPMask(N);
|
|
}]>;
|
|
|
|
def MOVLP_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isMOVLPMask(N);
|
|
}]>;
|
|
|
|
def MOVL_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isMOVLMask(N);
|
|
}]>;
|
|
|
|
def MOVSHDUP_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isMOVSHDUPMask(N);
|
|
}]>;
|
|
|
|
def MOVSLDUP_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isMOVSLDUPMask(N);
|
|
}]>;
|
|
|
|
def UNPCKL_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isUNPCKLMask(N);
|
|
}]>;
|
|
|
|
def UNPCKH_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isUNPCKHMask(N);
|
|
}]>;
|
|
|
|
def UNPCKL_v_undef_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isUNPCKL_v_undef_Mask(N);
|
|
}]>;
|
|
|
|
def PSHUFD_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isPSHUFDMask(N);
|
|
}], SHUFFLE_get_shuf_imm>;
|
|
|
|
def PSHUFHW_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isPSHUFHWMask(N);
|
|
}], SHUFFLE_get_pshufhw_imm>;
|
|
|
|
def PSHUFLW_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isPSHUFLWMask(N);
|
|
}], SHUFFLE_get_pshuflw_imm>;
|
|
|
|
def SHUFP_unary_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isPSHUFDMask(N);
|
|
}], SHUFFLE_get_shuf_imm>;
|
|
|
|
def SHUFP_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isSHUFPMask(N);
|
|
}], SHUFFLE_get_shuf_imm>;
|
|
|
|
def PSHUFD_binary_shuffle_mask : PatLeaf<(build_vector), [{
|
|
return X86::isSHUFPMask(N);
|
|
}], SHUFFLE_get_shuf_imm>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE scalar FP Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// CMOV* - Used to implement the SSE SELECT DAG operation. Expanded by the
|
|
// scheduler into a branch sequence.
|
|
let usesCustomDAGSchedInserter = 1 in { // Expanded by the scheduler.
|
|
def CMOV_FR32 : I<0, Pseudo,
|
|
(ops FR32:$dst, FR32:$t, FR32:$f, i8imm:$cond),
|
|
"#CMOV_FR32 PSEUDO!",
|
|
[(set FR32:$dst, (X86cmov FR32:$t, FR32:$f, imm:$cond))]>;
|
|
def CMOV_FR64 : I<0, Pseudo,
|
|
(ops FR64:$dst, FR64:$t, FR64:$f, i8imm:$cond),
|
|
"#CMOV_FR64 PSEUDO!",
|
|
[(set FR64:$dst, (X86cmov FR64:$t, FR64:$f, imm:$cond))]>;
|
|
def CMOV_V4F32 : I<0, Pseudo,
|
|
(ops VR128:$dst, VR128:$t, VR128:$f, i8imm:$cond),
|
|
"#CMOV_V4F32 PSEUDO!",
|
|
[(set VR128:$dst,
|
|
(v4f32 (X86cmov VR128:$t, VR128:$f, imm:$cond)))]>;
|
|
def CMOV_V2F64 : I<0, Pseudo,
|
|
(ops VR128:$dst, VR128:$t, VR128:$f, i8imm:$cond),
|
|
"#CMOV_V2F64 PSEUDO!",
|
|
[(set VR128:$dst,
|
|
(v2f64 (X86cmov VR128:$t, VR128:$f, imm:$cond)))]>;
|
|
def CMOV_V2I64 : I<0, Pseudo,
|
|
(ops VR128:$dst, VR128:$t, VR128:$f, i8imm:$cond),
|
|
"#CMOV_V2I64 PSEUDO!",
|
|
[(set VR128:$dst,
|
|
(v2i64 (X86cmov VR128:$t, VR128:$f, imm:$cond)))]>;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE1 Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// SSE1 Instruction Templates:
|
|
//
|
|
// SSI - SSE1 instructions with XS prefix.
|
|
// PSI - SSE1 instructions with TB prefix.
|
|
// PSIi8 - SSE1 instructions with ImmT == Imm8 and TB prefix.
|
|
|
|
class SSI<bits<8> o, Format F, dag ops, string asm, list<dag> pattern>
|
|
: I<o, F, ops, asm, pattern>, XS, Requires<[HasSSE1]>;
|
|
class PSI<bits<8> o, Format F, dag ops, string asm, list<dag> pattern>
|
|
: I<o, F, ops, asm, pattern>, TB, Requires<[HasSSE1]>;
|
|
class PSIi8<bits<8> o, Format F, dag ops, string asm, list<dag> pattern>
|
|
: Ii8<o, F, ops, asm, pattern>, TB, Requires<[HasSSE1]>;
|
|
|
|
// Helpers for defining instructions that directly correspond to intrinsics.
|
|
multiclass SS_IntUnary<bits<8> o, string OpcodeStr, Intrinsic IntId> {
|
|
def r : SSI<o, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
!strconcat(OpcodeStr, " {$src, $dst|$dst, $src}"),
|
|
[(set VR128:$dst, (v4f32 (IntId VR128:$src)))]>;
|
|
def m : SSI<o, MRMSrcMem, (ops VR128:$dst, ssmem:$src),
|
|
!strconcat(OpcodeStr, " {$src, $dst|$dst, $src}"),
|
|
[(set VR128:$dst, (v4f32 (IntId sse_load_f32:$src)))]>;
|
|
}
|
|
|
|
// Move Instructions
|
|
def MOVSSrr : SSI<0x10, MRMSrcReg, (ops FR32:$dst, FR32:$src),
|
|
"movss {$src, $dst|$dst, $src}", []>;
|
|
def MOVSSrm : SSI<0x10, MRMSrcMem, (ops FR32:$dst, f32mem:$src),
|
|
"movss {$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (loadf32 addr:$src))]>;
|
|
def MOVSSmr : SSI<0x11, MRMDestMem, (ops f32mem:$dst, FR32:$src),
|
|
"movss {$src, $dst|$dst, $src}",
|
|
[(store FR32:$src, addr:$dst)]>;
|
|
|
|
def SQRTSSr : SSI<0x51, MRMSrcReg, (ops FR32:$dst, FR32:$src),
|
|
"sqrtss {$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (fsqrt FR32:$src))]>;
|
|
def SQRTSSm : SSI<0x51, MRMSrcMem, (ops FR32:$dst, f32mem:$src),
|
|
"sqrtss {$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (fsqrt (loadf32 addr:$src)))]>;
|
|
|
|
// Aliases to match intrinsics which expect XMM operand(s).
|
|
defm SQRTSS_Int : SS_IntUnary<0x51, "sqrtss" , int_x86_sse_sqrt_ss>;
|
|
defm RSQRTSS_Int : SS_IntUnary<0x52, "rsqrtss", int_x86_sse_rsqrt_ss>;
|
|
defm RCPSS_Int : SS_IntUnary<0x53, "rcpss" , int_x86_sse_rcp_ss>;
|
|
|
|
// Conversion instructions
|
|
def CVTTSS2SIrr : SSI<0x2C, MRMSrcReg, (ops GR32:$dst, FR32:$src),
|
|
"cvttss2si {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (fp_to_sint FR32:$src))]>;
|
|
def CVTTSS2SIrm : SSI<0x2C, MRMSrcMem, (ops GR32:$dst, f32mem:$src),
|
|
"cvttss2si {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (fp_to_sint (loadf32 addr:$src)))]>;
|
|
def CVTSI2SSrr : SSI<0x2A, MRMSrcReg, (ops FR32:$dst, GR32:$src),
|
|
"cvtsi2ss {$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (sint_to_fp GR32:$src))]>;
|
|
def CVTSI2SSrm : SSI<0x2A, MRMSrcMem, (ops FR32:$dst, i32mem:$src),
|
|
"cvtsi2ss {$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (sint_to_fp (loadi32 addr:$src)))]>;
|
|
|
|
// Match intrinsics which expect XMM operand(s).
|
|
def Int_CVTSS2SIrr : SSI<0x2D, MRMSrcReg, (ops GR32:$dst, VR128:$src),
|
|
"cvtss2si {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (int_x86_sse_cvtss2si VR128:$src))]>;
|
|
def Int_CVTSS2SIrm : SSI<0x2D, MRMSrcMem, (ops GR32:$dst, f32mem:$src),
|
|
"cvtss2si {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (int_x86_sse_cvtss2si
|
|
(load addr:$src)))]>;
|
|
|
|
// Aliases for intrinsics
|
|
def Int_CVTTSS2SIrr : SSI<0x2C, MRMSrcReg, (ops GR32:$dst, VR128:$src),
|
|
"cvttss2si {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst,
|
|
(int_x86_sse_cvttss2si VR128:$src))]>;
|
|
def Int_CVTTSS2SIrm : SSI<0x2C, MRMSrcMem, (ops GR32:$dst, f32mem:$src),
|
|
"cvttss2si {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst,
|
|
(int_x86_sse_cvttss2si(load addr:$src)))]>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
def Int_CVTSI2SSrr : SSI<0x2A, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, GR32:$src2),
|
|
"cvtsi2ss {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (int_x86_sse_cvtsi2ss VR128:$src1,
|
|
GR32:$src2))]>;
|
|
def Int_CVTSI2SSrm : SSI<0x2A, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, i32mem:$src2),
|
|
"cvtsi2ss {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (int_x86_sse_cvtsi2ss VR128:$src1,
|
|
(loadi32 addr:$src2)))]>;
|
|
}
|
|
|
|
// Comparison instructions
|
|
let isTwoAddress = 1 in {
|
|
def CMPSSrr : SSI<0xC2, MRMSrcReg,
|
|
(ops FR32:$dst, FR32:$src1, FR32:$src, SSECC:$cc),
|
|
"cmp${cc}ss {$src, $dst|$dst, $src}",
|
|
[]>;
|
|
def CMPSSrm : SSI<0xC2, MRMSrcMem,
|
|
(ops FR32:$dst, FR32:$src1, f32mem:$src, SSECC:$cc),
|
|
"cmp${cc}ss {$src, $dst|$dst, $src}", []>;
|
|
}
|
|
|
|
def UCOMISSrr: PSI<0x2E, MRMSrcReg, (ops FR32:$src1, FR32:$src2),
|
|
"ucomiss {$src2, $src1|$src1, $src2}",
|
|
[(X86cmp FR32:$src1, FR32:$src2)]>;
|
|
def UCOMISSrm: PSI<0x2E, MRMSrcMem, (ops FR32:$src1, f32mem:$src2),
|
|
"ucomiss {$src2, $src1|$src1, $src2}",
|
|
[(X86cmp FR32:$src1, (loadf32 addr:$src2))]>;
|
|
|
|
// Aliases to match intrinsics which expect XMM operand(s).
|
|
let isTwoAddress = 1 in {
|
|
def Int_CMPSSrr : SSI<0xC2, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src, SSECC:$cc),
|
|
"cmp${cc}ss {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse_cmp_ss VR128:$src1,
|
|
VR128:$src, imm:$cc))]>;
|
|
def Int_CMPSSrm : SSI<0xC2, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f32mem:$src, SSECC:$cc),
|
|
"cmp${cc}ss {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse_cmp_ss VR128:$src1,
|
|
(load addr:$src), imm:$cc))]>;
|
|
}
|
|
|
|
def Int_UCOMISSrr: PSI<0x2E, MRMSrcReg, (ops VR128:$src1, VR128:$src2),
|
|
"ucomiss {$src2, $src1|$src1, $src2}",
|
|
[(X86ucomi (v4f32 VR128:$src1), VR128:$src2)]>;
|
|
def Int_UCOMISSrm: PSI<0x2E, MRMSrcMem, (ops VR128:$src1, f128mem:$src2),
|
|
"ucomiss {$src2, $src1|$src1, $src2}",
|
|
[(X86ucomi (v4f32 VR128:$src1), (load addr:$src2))]>;
|
|
|
|
def Int_COMISSrr: PSI<0x2F, MRMSrcReg, (ops VR128:$src1, VR128:$src2),
|
|
"comiss {$src2, $src1|$src1, $src2}",
|
|
[(X86comi (v4f32 VR128:$src1), VR128:$src2)]>;
|
|
def Int_COMISSrm: PSI<0x2F, MRMSrcMem, (ops VR128:$src1, f128mem:$src2),
|
|
"comiss {$src2, $src1|$src1, $src2}",
|
|
[(X86comi (v4f32 VR128:$src1), (load addr:$src2))]>;
|
|
|
|
// Aliases of packed SSE1 instructions for scalar use. These all have names that
|
|
// start with 'Fs'.
|
|
|
|
// Alias instructions that map fld0 to pxor for sse.
|
|
def FsFLD0SS : I<0xEF, MRMInitReg, (ops FR32:$dst),
|
|
"pxor $dst, $dst", [(set FR32:$dst, fp32imm0)]>,
|
|
Requires<[HasSSE1]>, TB, OpSize;
|
|
|
|
// Alias instruction to do FR32 reg-to-reg copy using movaps. Upper bits are
|
|
// disregarded.
|
|
def FsMOVAPSrr : PSI<0x28, MRMSrcReg, (ops FR32:$dst, FR32:$src),
|
|
"movaps {$src, $dst|$dst, $src}", []>;
|
|
|
|
// Alias instruction to load FR32 from f128mem using movaps. Upper bits are
|
|
// disregarded.
|
|
def FsMOVAPSrm : PSI<0x28, MRMSrcMem, (ops FR32:$dst, f128mem:$src),
|
|
"movaps {$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (X86loadpf32 addr:$src))]>;
|
|
|
|
// Alias bitwise logical operations using SSE logical ops on packed FP values.
|
|
let isTwoAddress = 1 in {
|
|
|
|
let isCommutable = 1 in {
|
|
def FsANDPSrr : PSI<0x54, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
|
|
"andps {$src2, $dst|$dst, $src2}",
|
|
[(set FR32:$dst, (X86fand FR32:$src1, FR32:$src2))]>;
|
|
def FsORPSrr : PSI<0x56, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
|
|
"orps {$src2, $dst|$dst, $src2}",
|
|
[(set FR32:$dst, (X86for FR32:$src1, FR32:$src2))]>;
|
|
def FsXORPSrr : PSI<0x57, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
|
|
"xorps {$src2, $dst|$dst, $src2}",
|
|
[(set FR32:$dst, (X86fxor FR32:$src1, FR32:$src2))]>;
|
|
}
|
|
|
|
def FsANDPSrm : PSI<0x54, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f128mem:$src2),
|
|
"andps {$src2, $dst|$dst, $src2}",
|
|
[(set FR32:$dst, (X86fand FR32:$src1,
|
|
(X86loadpf32 addr:$src2)))]>;
|
|
def FsORPSrm : PSI<0x56, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f128mem:$src2),
|
|
"orps {$src2, $dst|$dst, $src2}",
|
|
[(set FR32:$dst, (X86for FR32:$src1,
|
|
(X86loadpf32 addr:$src2)))]>;
|
|
def FsXORPSrm : PSI<0x57, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f128mem:$src2),
|
|
"xorps {$src2, $dst|$dst, $src2}",
|
|
[(set FR32:$dst, (X86fxor FR32:$src1,
|
|
(X86loadpf32 addr:$src2)))]>;
|
|
|
|
def FsANDNPSrr : PSI<0x55, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
|
|
"andnps {$src2, $dst|$dst, $src2}", []>;
|
|
def FsANDNPSrm : PSI<0x55, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f128mem:$src2),
|
|
"andnps {$src2, $dst|$dst, $src2}", []>;
|
|
}
|
|
|
|
/// scalar_sse1_fp_binop_rm - Scalar SSE1 binops come in three basic forms:
|
|
///
|
|
/// 1. f32 - This comes in SSE1 form for floats.
|
|
/// 2. rr vs rm - They include a reg+reg form and a reg+mem form.
|
|
///
|
|
/// In addition, scalar SSE ops have an intrinsic form. This form is unlike the
|
|
/// normal form, in that they take an entire vector (instead of a scalar) and
|
|
/// leave the top elements undefined. This adds another two variants of the
|
|
/// above permutations, giving us 8 forms for 'instruction'.
|
|
///
|
|
let isTwoAddress = 1 in {
|
|
multiclass scalar_sse1_fp_binop_rm<bits<8> opc, string OpcodeStr,
|
|
SDNode OpNode, Intrinsic F32Int,
|
|
bit Commutable = 0> {
|
|
// Scalar operation, reg+reg.
|
|
def SSrr : SSI<opc, MRMSrcReg, (ops FR32:$dst, FR32:$src1, FR32:$src2),
|
|
!strconcat(OpcodeStr, "ss {$src2, $dst|$dst, $src2}"),
|
|
[(set FR32:$dst, (OpNode FR32:$src1, FR32:$src2))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
// Scalar operation, reg+mem.
|
|
def SSrm : SSI<opc, MRMSrcMem, (ops FR32:$dst, FR32:$src1, f32mem:$src2),
|
|
!strconcat(OpcodeStr, "ss {$src2, $dst|$dst, $src2}"),
|
|
[(set FR32:$dst, (OpNode FR32:$src1, (load addr:$src2)))]>;
|
|
|
|
// Vector intrinsic operation, reg+reg.
|
|
def SSrr_Int : SSI<opc, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, "ss {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (F32Int VR128:$src1, VR128:$src2))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
// Vector intrinsic operation, reg+mem.
|
|
def SSrm_Int : SSI<opc, MRMSrcMem, (ops VR128:$dst, VR128:$src1, ssmem:$src2),
|
|
!strconcat(OpcodeStr, "ss {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (F32Int VR128:$src1,
|
|
sse_load_f32:$src2))]>;
|
|
}
|
|
}
|
|
|
|
// Arithmetic instructions
|
|
defm ADD : scalar_sse1_fp_binop_rm<0x58, "add", fadd, int_x86_sse_add_ss, 1>;
|
|
defm MUL : scalar_sse1_fp_binop_rm<0x59, "mul", fmul, int_x86_sse_mul_ss, 1>;
|
|
defm SUB : scalar_sse1_fp_binop_rm<0x5C, "sub", fsub, int_x86_sse_sub_ss>;
|
|
defm DIV : scalar_sse1_fp_binop_rm<0x5E, "div", fdiv, int_x86_sse_div_ss>;
|
|
|
|
defm MAX : scalar_sse1_fp_binop_rm<0x5F, "max", X86fmax, int_x86_sse_max_ss>;
|
|
defm MIN : scalar_sse1_fp_binop_rm<0x5D, "min", X86fmin, int_x86_sse_min_ss>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE packed FP Instructions
|
|
|
|
// Move Instructions
|
|
def MOVAPSrr : PSI<0x28, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"movaps {$src, $dst|$dst, $src}", []>;
|
|
def MOVAPSrm : PSI<0x28, MRMSrcMem, (ops VR128:$dst, f128mem:$src),
|
|
"movaps {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (loadv4f32 addr:$src))]>;
|
|
|
|
def MOVAPSmr : PSI<0x29, MRMDestMem, (ops f128mem:$dst, VR128:$src),
|
|
"movaps {$src, $dst|$dst, $src}",
|
|
[(store (v4f32 VR128:$src), addr:$dst)]>;
|
|
|
|
def MOVUPSrr : PSI<0x10, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"movups {$src, $dst|$dst, $src}", []>;
|
|
def MOVUPSrm : PSI<0x10, MRMSrcMem, (ops VR128:$dst, f128mem:$src),
|
|
"movups {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse_loadu_ps addr:$src))]>;
|
|
def MOVUPSmr : PSI<0x11, MRMDestMem, (ops f128mem:$dst, VR128:$src),
|
|
"movups {$src, $dst|$dst, $src}",
|
|
[(int_x86_sse_storeu_ps addr:$dst, VR128:$src)]>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
let AddedComplexity = 20 in {
|
|
def MOVLPSrm : PSI<0x12, MRMSrcMem, (ops VR128:$dst, VR128:$src1, f64mem:$src2),
|
|
"movlps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (vector_shuffle VR128:$src1,
|
|
(bc_v4f32 (v2f64 (scalar_to_vector (loadf64 addr:$src2)))),
|
|
MOVLP_shuffle_mask)))]>;
|
|
def MOVHPSrm : PSI<0x16, MRMSrcMem, (ops VR128:$dst, VR128:$src1, f64mem:$src2),
|
|
"movhps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (vector_shuffle VR128:$src1,
|
|
(bc_v4f32 (v2f64 (scalar_to_vector (loadf64 addr:$src2)))),
|
|
MOVHP_shuffle_mask)))]>;
|
|
} // AddedComplexity
|
|
} // isTwoAddress
|
|
|
|
def MOVLPSmr : PSI<0x13, MRMDestMem, (ops f64mem:$dst, VR128:$src),
|
|
"movlps {$src, $dst|$dst, $src}",
|
|
[(store (f64 (vector_extract (bc_v2f64 (v4f32 VR128:$src)),
|
|
(iPTR 0))), addr:$dst)]>;
|
|
|
|
// v2f64 extract element 1 is always custom lowered to unpack high to low
|
|
// and extract element 0 so the non-store version isn't too horrible.
|
|
def MOVHPSmr : PSI<0x17, MRMDestMem, (ops f64mem:$dst, VR128:$src),
|
|
"movhps {$src, $dst|$dst, $src}",
|
|
[(store (f64 (vector_extract
|
|
(v2f64 (vector_shuffle
|
|
(bc_v2f64 (v4f32 VR128:$src)), (undef),
|
|
UNPCKH_shuffle_mask)), (iPTR 0))),
|
|
addr:$dst)]>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
let AddedComplexity = 15 in {
|
|
def MOVLHPSrr : PSI<0x16, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"movlhps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
MOVHP_shuffle_mask)))]>;
|
|
|
|
def MOVHLPSrr : PSI<0x12, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"movhlps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
MOVHLPS_shuffle_mask)))]>;
|
|
} // AddedComplexity
|
|
} // isTwoAddress
|
|
|
|
|
|
|
|
/// packed_sse1_fp_binop_rm - Packed SSE binops come in three basic forms:
|
|
/// 1. v4f32 - This comes in SSE1 form for float.
|
|
/// 2. rr vs rm - They include a reg+reg form and a ref+mem form.
|
|
///
|
|
let isTwoAddress = 1 in {
|
|
multiclass packed_sse1_fp_binop_rm<bits<8> opc, string OpcodeStr,
|
|
SDNode OpNode, bit Commutable = 0> {
|
|
// Packed operation, reg+reg.
|
|
def PSrr : PSI<opc, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, "ps {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (v4f32 (OpNode VR128:$src1, VR128:$src2)))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
// Packed operation, reg+mem.
|
|
def PSrm : PSI<opc, MRMSrcMem, (ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
!strconcat(OpcodeStr, "ps {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (OpNode VR128:$src1, (loadv4f32 addr:$src2)))]>;
|
|
}
|
|
}
|
|
|
|
defm ADD : packed_sse1_fp_binop_rm<0x58, "add", fadd, 1>;
|
|
defm MUL : packed_sse1_fp_binop_rm<0x59, "mul", fmul, 1>;
|
|
defm DIV : packed_sse1_fp_binop_rm<0x5E, "div", fdiv>;
|
|
defm SUB : packed_sse1_fp_binop_rm<0x5C, "sub", fsub>;
|
|
|
|
// Arithmetic
|
|
|
|
class PS_Intr<bits<8> o, string OpcodeStr, Intrinsic IntId>
|
|
: PSI<o, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
!strconcat(OpcodeStr, " {$src, $dst|$dst, $src}"),
|
|
[(set VR128:$dst, (IntId VR128:$src))]>;
|
|
class PS_Intm<bits<8> o, string OpcodeStr, Intrinsic IntId>
|
|
: PSI<o, MRMSrcMem, (ops VR128:$dst, f32mem:$src),
|
|
!strconcat(OpcodeStr, " {$src, $dst|$dst, $src}"),
|
|
[(set VR128:$dst, (IntId (load addr:$src)))]>;
|
|
|
|
class PS_Intrr<bits<8> o, string OpcodeStr, Intrinsic IntId>
|
|
: PSI<o, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (IntId VR128:$src1, VR128:$src2))]>;
|
|
class PS_Intrm<bits<8> o, string OpcodeStr, Intrinsic IntId>
|
|
: PSI<o, MRMSrcMem, (ops VR128:$dst, VR128:$src1, f32mem:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (IntId VR128:$src1, (load addr:$src2)))]>;
|
|
|
|
def SQRTPSr : PS_Intr<0x51, "sqrtps", int_x86_sse_sqrt_ps>;
|
|
def SQRTPSm : PS_Intm<0x51, "sqrtps", int_x86_sse_sqrt_ps>;
|
|
|
|
def RSQRTPSr : PS_Intr<0x52, "rsqrtps", int_x86_sse_rsqrt_ps>;
|
|
def RSQRTPSm : PS_Intm<0x52, "rsqrtps", int_x86_sse_rsqrt_ps>;
|
|
def RCPPSr : PS_Intr<0x53, "rcpps", int_x86_sse_rcp_ps>;
|
|
def RCPPSm : PS_Intm<0x53, "rcpps", int_x86_sse_rcp_ps>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
let isCommutable = 1 in {
|
|
def MAXPSrr : PS_Intrr<0x5F, "maxps", int_x86_sse_max_ps>;
|
|
def MINPSrr : PS_Intrr<0x5D, "minps", int_x86_sse_min_ps>;
|
|
}
|
|
|
|
def MAXPSrm : PS_Intrm<0x5F, "maxps", int_x86_sse_max_ps>;
|
|
def MINPSrm : PS_Intrm<0x5D, "minps", int_x86_sse_min_ps>;
|
|
}
|
|
|
|
// Logical
|
|
let isTwoAddress = 1 in {
|
|
let isCommutable = 1 in {
|
|
def ANDPSrr : PSI<0x54, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"andps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (v2i64
|
|
(and VR128:$src1, VR128:$src2)))]>;
|
|
def ORPSrr : PSI<0x56, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"orps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (v2i64
|
|
(or VR128:$src1, VR128:$src2)))]>;
|
|
def XORPSrr : PSI<0x57, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"xorps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (v2i64
|
|
(xor VR128:$src1, VR128:$src2)))]>;
|
|
}
|
|
|
|
def ANDPSrm : PSI<0x54, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
"andps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (and VR128:$src1,
|
|
(bc_v2i64 (loadv4f32 addr:$src2))))]>;
|
|
def ORPSrm : PSI<0x56, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
"orps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (or VR128:$src1,
|
|
(bc_v2i64 (loadv4f32 addr:$src2))))]>;
|
|
def XORPSrm : PSI<0x57, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
"xorps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (xor VR128:$src1,
|
|
(bc_v2i64 (loadv4f32 addr:$src2))))]>;
|
|
def ANDNPSrr : PSI<0x55, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"andnps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2i64 (and (xor VR128:$src1,
|
|
(bc_v2i64 (v4i32 immAllOnesV))),
|
|
VR128:$src2)))]>;
|
|
def ANDNPSrm : PSI<0x55, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1,f128mem:$src2),
|
|
"andnps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2i64 (and (xor VR128:$src1,
|
|
(bc_v2i64 (v4i32 immAllOnesV))),
|
|
(bc_v2i64 (loadv4f32 addr:$src2)))))]>;
|
|
}
|
|
|
|
let isTwoAddress = 1 in {
|
|
def CMPPSrri : PSIi8<0xC2, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src, SSECC:$cc),
|
|
"cmp${cc}ps {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse_cmp_ps VR128:$src1,
|
|
VR128:$src, imm:$cc))]>;
|
|
def CMPPSrmi : PSIi8<0xC2, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src, SSECC:$cc),
|
|
"cmp${cc}ps {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse_cmp_ps VR128:$src1,
|
|
(load addr:$src), imm:$cc))]>;
|
|
}
|
|
|
|
// Shuffle and unpack instructions
|
|
let isTwoAddress = 1 in {
|
|
let isConvertibleToThreeAddress = 1 in // Convert to pshufd
|
|
def SHUFPSrri : PSIi8<0xC6, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1,
|
|
VR128:$src2, i32i8imm:$src3),
|
|
"shufps {$src3, $src2, $dst|$dst, $src2, $src3}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (vector_shuffle
|
|
VR128:$src1, VR128:$src2,
|
|
SHUFP_shuffle_mask:$src3)))]>;
|
|
def SHUFPSrmi : PSIi8<0xC6, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1,
|
|
f128mem:$src2, i32i8imm:$src3),
|
|
"shufps {$src3, $src2, $dst|$dst, $src2, $src3}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (vector_shuffle
|
|
VR128:$src1, (load addr:$src2),
|
|
SHUFP_shuffle_mask:$src3)))]>;
|
|
|
|
let AddedComplexity = 10 in {
|
|
def UNPCKHPSrr : PSI<0x15, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"unpckhps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (vector_shuffle
|
|
VR128:$src1, VR128:$src2,
|
|
UNPCKH_shuffle_mask)))]>;
|
|
def UNPCKHPSrm : PSI<0x15, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
"unpckhps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (vector_shuffle
|
|
VR128:$src1, (load addr:$src2),
|
|
UNPCKH_shuffle_mask)))]>;
|
|
|
|
def UNPCKLPSrr : PSI<0x14, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"unpcklps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (vector_shuffle
|
|
VR128:$src1, VR128:$src2,
|
|
UNPCKL_shuffle_mask)))]>;
|
|
def UNPCKLPSrm : PSI<0x14, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
"unpcklps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (vector_shuffle
|
|
VR128:$src1, (load addr:$src2),
|
|
UNPCKL_shuffle_mask)))]>;
|
|
} // AddedComplexity
|
|
} // isTwoAddress
|
|
|
|
// Mask creation
|
|
def MOVMSKPSrr : PSI<0x50, MRMSrcReg, (ops GR32:$dst, VR128:$src),
|
|
"movmskps {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (int_x86_sse_movmsk_ps VR128:$src))]>;
|
|
def MOVMSKPDrr : PSI<0x50, MRMSrcReg, (ops GR32:$dst, VR128:$src),
|
|
"movmskpd {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (int_x86_sse2_movmsk_pd VR128:$src))]>;
|
|
|
|
// Prefetching loads.
|
|
// TODO: no intrinsics for these?
|
|
def PREFETCHT0 : PSI<0x18, MRM1m, (ops i8mem:$src), "prefetcht0 $src", []>;
|
|
def PREFETCHT1 : PSI<0x18, MRM2m, (ops i8mem:$src), "prefetcht1 $src", []>;
|
|
def PREFETCHT2 : PSI<0x18, MRM3m, (ops i8mem:$src), "prefetcht2 $src", []>;
|
|
def PREFETCHNTA : PSI<0x18, MRM0m, (ops i8mem:$src), "prefetchnta $src", []>;
|
|
|
|
// Non-temporal stores
|
|
def MOVNTPSmr : PSI<0x2B, MRMDestMem, (ops i128mem:$dst, VR128:$src),
|
|
"movntps {$src, $dst|$dst, $src}",
|
|
[(int_x86_sse_movnt_ps addr:$dst, VR128:$src)]>;
|
|
|
|
// Load, store, and memory fence
|
|
def SFENCE : PSI<0xAE, MRM7m, (ops), "sfence", [(int_x86_sse_sfence)]>;
|
|
|
|
// MXCSR register
|
|
def LDMXCSR : PSI<0xAE, MRM2m, (ops i32mem:$src),
|
|
"ldmxcsr $src", [(int_x86_sse_ldmxcsr addr:$src)]>;
|
|
def STMXCSR : PSI<0xAE, MRM3m, (ops i32mem:$dst),
|
|
"stmxcsr $dst", [(int_x86_sse_stmxcsr addr:$dst)]>;
|
|
|
|
// Alias instructions that map zero vector to pxor / xorp* for sse.
|
|
// FIXME: remove when we can teach regalloc that xor reg, reg is ok.
|
|
let isReMaterializable = 1 in
|
|
def V_SET0 : PSI<0x57, MRMInitReg, (ops VR128:$dst),
|
|
"xorps $dst, $dst",
|
|
[(set VR128:$dst, (v4f32 immAllZerosV))]>;
|
|
|
|
// FR32 to 128-bit vector conversion.
|
|
def MOVSS2PSrr : SSI<0x10, MRMSrcReg, (ops VR128:$dst, FR32:$src),
|
|
"movss {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (scalar_to_vector FR32:$src)))]>;
|
|
def MOVSS2PSrm : SSI<0x10, MRMSrcMem, (ops VR128:$dst, f32mem:$src),
|
|
"movss {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (scalar_to_vector (loadf32 addr:$src))))]>;
|
|
|
|
// FIXME: may not be able to eliminate this movss with coalescing the src and
|
|
// dest register classes are different. We really want to write this pattern
|
|
// like this:
|
|
// def : Pat<(f32 (vector_extract (v4f32 VR128:$src), (iPTR 0))),
|
|
// (f32 FR32:$src)>;
|
|
def MOVPS2SSrr : SSI<0x10, MRMSrcReg, (ops FR32:$dst, VR128:$src),
|
|
"movss {$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (vector_extract (v4f32 VR128:$src),
|
|
(iPTR 0)))]>;
|
|
def MOVPS2SSmr : SSI<0x11, MRMDestMem, (ops f32mem:$dst, VR128:$src),
|
|
"movss {$src, $dst|$dst, $src}",
|
|
[(store (f32 (vector_extract (v4f32 VR128:$src),
|
|
(iPTR 0))), addr:$dst)]>;
|
|
|
|
|
|
// Move to lower bits of a VR128, leaving upper bits alone.
|
|
// Three operand (but two address) aliases.
|
|
let isTwoAddress = 1 in {
|
|
def MOVLSS2PSrr : SSI<0x10, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, FR32:$src2),
|
|
"movss {$src2, $dst|$dst, $src2}", []>;
|
|
|
|
let AddedComplexity = 15 in
|
|
def MOVLPSrr : SSI<0x10, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"movss {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4f32 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
MOVL_shuffle_mask)))]>;
|
|
}
|
|
|
|
// Move to lower bits of a VR128 and zeroing upper bits.
|
|
// Loading from memory automatically zeroing upper bits.
|
|
let AddedComplexity = 20 in
|
|
def MOVZSS2PSrm : SSI<0x10, MRMSrcMem, (ops VR128:$dst, f32mem:$src),
|
|
"movss {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (v4f32 (vector_shuffle immAllZerosV,
|
|
(v4f32 (scalar_to_vector (loadf32 addr:$src))),
|
|
MOVL_shuffle_mask)))]>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE2 Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// SSE2 Instruction Templates:
|
|
//
|
|
// SDI - SSE2 instructions with XD prefix.
|
|
// PDI - SSE2 instructions with TB and OpSize prefixes.
|
|
// PDIi8 - SSE2 instructions with ImmT == Imm8 and TB and OpSize prefixes.
|
|
|
|
class SDI<bits<8> o, Format F, dag ops, string asm, list<dag> pattern>
|
|
: I<o, F, ops, asm, pattern>, XD, Requires<[HasSSE2]>;
|
|
class PDI<bits<8> o, Format F, dag ops, string asm, list<dag> pattern>
|
|
: I<o, F, ops, asm, pattern>, TB, OpSize, Requires<[HasSSE2]>;
|
|
class PDIi8<bits<8> o, Format F, dag ops, string asm, list<dag> pattern>
|
|
: Ii8<o, F, ops, asm, pattern>, TB, OpSize, Requires<[HasSSE2]>;
|
|
|
|
// Helpers for defining instructions that directly correspond to intrinsics.
|
|
multiclass SD_IntUnary<bits<8> o, string OpcodeStr, Intrinsic IntId> {
|
|
def r : SDI<o, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
!strconcat(OpcodeStr, " {$src, $dst|$dst, $src}"),
|
|
[(set VR128:$dst, (v2f64 (IntId VR128:$src)))]>;
|
|
def m : SDI<o, MRMSrcMem, (ops VR128:$dst, sdmem:$src),
|
|
!strconcat(OpcodeStr, " {$src, $dst|$dst, $src}"),
|
|
[(set VR128:$dst, (v2f64 (IntId sse_load_f64:$src)))]>;
|
|
}
|
|
|
|
// Move Instructions
|
|
def MOVSDrr : SDI<0x10, MRMSrcReg, (ops FR64:$dst, FR64:$src),
|
|
"movsd {$src, $dst|$dst, $src}", []>;
|
|
def MOVSDrm : SDI<0x10, MRMSrcMem, (ops FR64:$dst, f64mem:$src),
|
|
"movsd {$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (loadf64 addr:$src))]>;
|
|
def MOVSDmr : SDI<0x11, MRMDestMem, (ops f64mem:$dst, FR64:$src),
|
|
"movsd {$src, $dst|$dst, $src}",
|
|
[(store FR64:$src, addr:$dst)]>;
|
|
|
|
def SQRTSDr : SDI<0x51, MRMSrcReg, (ops FR64:$dst, FR64:$src),
|
|
"sqrtsd {$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (fsqrt FR64:$src))]>;
|
|
def SQRTSDm : SDI<0x51, MRMSrcMem, (ops FR64:$dst, f64mem:$src),
|
|
"sqrtsd {$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (fsqrt (loadf64 addr:$src)))]>;
|
|
|
|
// Aliases to match intrinsics which expect XMM operand(s).
|
|
defm SQRTSD_Int : SD_IntUnary<0x51, "sqrtsd" , int_x86_sse2_sqrt_sd>;
|
|
|
|
// Conversion instructions
|
|
def CVTTSD2SIrr : SDI<0x2C, MRMSrcReg, (ops GR32:$dst, FR64:$src),
|
|
"cvttsd2si {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (fp_to_sint FR64:$src))]>;
|
|
def CVTTSD2SIrm : SDI<0x2C, MRMSrcMem, (ops GR32:$dst, f64mem:$src),
|
|
"cvttsd2si {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (fp_to_sint (loadf64 addr:$src)))]>;
|
|
def CVTSD2SSrr : SDI<0x5A, MRMSrcReg, (ops FR32:$dst, FR64:$src),
|
|
"cvtsd2ss {$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (fround FR64:$src))]>;
|
|
def CVTSD2SSrm : SDI<0x5A, MRMSrcMem, (ops FR32:$dst, f64mem:$src),
|
|
"cvtsd2ss {$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (fround (loadf64 addr:$src)))]>;
|
|
def CVTSI2SDrr : SDI<0x2A, MRMSrcReg, (ops FR64:$dst, GR32:$src),
|
|
"cvtsi2sd {$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (sint_to_fp GR32:$src))]>;
|
|
def CVTSI2SDrm : SDI<0x2A, MRMSrcMem, (ops FR64:$dst, i32mem:$src),
|
|
"cvtsi2sd {$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (sint_to_fp (loadi32 addr:$src)))]>;
|
|
|
|
// SSE2 instructions with XS prefix
|
|
def CVTSS2SDrr : I<0x5A, MRMSrcReg, (ops FR64:$dst, FR32:$src),
|
|
"cvtss2sd {$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (fextend FR32:$src))]>, XS,
|
|
Requires<[HasSSE2]>;
|
|
def CVTSS2SDrm : I<0x5A, MRMSrcMem, (ops FR64:$dst, f32mem:$src),
|
|
"cvtss2sd {$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (extloadf32 addr:$src))]>, XS,
|
|
Requires<[HasSSE2]>;
|
|
|
|
// Match intrinsics which expect XMM operand(s).
|
|
def Int_CVTSD2SIrr : SDI<0x2D, MRMSrcReg, (ops GR32:$dst, VR128:$src),
|
|
"cvtsd2si {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (int_x86_sse2_cvtsd2si VR128:$src))]>;
|
|
def Int_CVTSD2SIrm : SDI<0x2D, MRMSrcMem, (ops GR32:$dst, f128mem:$src),
|
|
"cvtsd2si {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (int_x86_sse2_cvtsd2si
|
|
(load addr:$src)))]>;
|
|
|
|
// Aliases for intrinsics
|
|
def Int_CVTTSD2SIrr : SDI<0x2C, MRMSrcReg, (ops GR32:$dst, VR128:$src),
|
|
"cvttsd2si {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst,
|
|
(int_x86_sse2_cvttsd2si VR128:$src))]>;
|
|
def Int_CVTTSD2SIrm : SDI<0x2C, MRMSrcMem, (ops GR32:$dst, f128mem:$src),
|
|
"cvttsd2si {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (int_x86_sse2_cvttsd2si
|
|
(load addr:$src)))]>;
|
|
|
|
// Comparison instructions
|
|
let isTwoAddress = 1 in {
|
|
def CMPSDrr : SDI<0xC2, MRMSrcReg,
|
|
(ops FR64:$dst, FR64:$src1, FR64:$src, SSECC:$cc),
|
|
"cmp${cc}sd {$src, $dst|$dst, $src}", []>;
|
|
def CMPSDrm : SDI<0xC2, MRMSrcMem,
|
|
(ops FR64:$dst, FR64:$src1, f64mem:$src, SSECC:$cc),
|
|
"cmp${cc}sd {$src, $dst|$dst, $src}", []>;
|
|
}
|
|
|
|
def UCOMISDrr: PDI<0x2E, MRMSrcReg, (ops FR64:$src1, FR64:$src2),
|
|
"ucomisd {$src2, $src1|$src1, $src2}",
|
|
[(X86cmp FR64:$src1, FR64:$src2)]>;
|
|
def UCOMISDrm: PDI<0x2E, MRMSrcMem, (ops FR64:$src1, f64mem:$src2),
|
|
"ucomisd {$src2, $src1|$src1, $src2}",
|
|
[(X86cmp FR64:$src1, (loadf64 addr:$src2))]>;
|
|
|
|
// Aliases to match intrinsics which expect XMM operand(s).
|
|
let isTwoAddress = 1 in {
|
|
def Int_CMPSDrr : SDI<0xC2, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src, SSECC:$cc),
|
|
"cmp${cc}sd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cmp_sd VR128:$src1,
|
|
VR128:$src, imm:$cc))]>;
|
|
def Int_CMPSDrm : SDI<0xC2, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f64mem:$src, SSECC:$cc),
|
|
"cmp${cc}sd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cmp_sd VR128:$src1,
|
|
(load addr:$src), imm:$cc))]>;
|
|
}
|
|
|
|
def Int_UCOMISDrr: PDI<0x2E, MRMSrcReg, (ops VR128:$src1, VR128:$src2),
|
|
"ucomisd {$src2, $src1|$src1, $src2}",
|
|
[(X86ucomi (v2f64 VR128:$src1), (v2f64 VR128:$src2))]>;
|
|
def Int_UCOMISDrm: PDI<0x2E, MRMSrcMem, (ops VR128:$src1, f128mem:$src2),
|
|
"ucomisd {$src2, $src1|$src1, $src2}",
|
|
[(X86ucomi (v2f64 VR128:$src1), (load addr:$src2))]>;
|
|
|
|
def Int_COMISDrr: PDI<0x2F, MRMSrcReg, (ops VR128:$src1, VR128:$src2),
|
|
"comisd {$src2, $src1|$src1, $src2}",
|
|
[(X86comi (v2f64 VR128:$src1), (v2f64 VR128:$src2))]>;
|
|
def Int_COMISDrm: PDI<0x2F, MRMSrcMem, (ops VR128:$src1, f128mem:$src2),
|
|
"comisd {$src2, $src1|$src1, $src2}",
|
|
[(X86comi (v2f64 VR128:$src1), (load addr:$src2))]>;
|
|
|
|
// Aliases of packed instructions for scalar use. These all have names that
|
|
// start with 'Fs'.
|
|
|
|
// Alias instructions that map fld0 to pxor for sse.
|
|
def FsFLD0SD : I<0xEF, MRMInitReg, (ops FR64:$dst),
|
|
"pxor $dst, $dst", [(set FR64:$dst, fp64imm0)]>,
|
|
Requires<[HasSSE2]>, TB, OpSize;
|
|
|
|
// Alias instructions to do FR64 reg-to-reg copy using movapd. Upper bits are
|
|
// disregarded.
|
|
def FsMOVAPDrr : PDI<0x28, MRMSrcReg, (ops FR64:$dst, FR64:$src),
|
|
"movapd {$src, $dst|$dst, $src}", []>;
|
|
|
|
// Alias instructions to load FR64 from f128mem using movapd. Upper bits are
|
|
// disregarded.
|
|
def FsMOVAPDrm : PDI<0x28, MRMSrcMem, (ops FR64:$dst, f128mem:$src),
|
|
"movapd {$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (X86loadpf64 addr:$src))]>;
|
|
|
|
// Alias bitwise logical operations using SSE logical ops on packed FP values.
|
|
let isTwoAddress = 1 in {
|
|
let isCommutable = 1 in {
|
|
def FsANDPDrr : PDI<0x54, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
|
|
"andpd {$src2, $dst|$dst, $src2}",
|
|
[(set FR64:$dst, (X86fand FR64:$src1, FR64:$src2))]>;
|
|
def FsORPDrr : PDI<0x56, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
|
|
"orpd {$src2, $dst|$dst, $src2}",
|
|
[(set FR64:$dst, (X86for FR64:$src1, FR64:$src2))]>;
|
|
def FsXORPDrr : PDI<0x57, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
|
|
"xorpd {$src2, $dst|$dst, $src2}",
|
|
[(set FR64:$dst, (X86fxor FR64:$src1, FR64:$src2))]>;
|
|
}
|
|
|
|
def FsANDPDrm : PDI<0x54, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f128mem:$src2),
|
|
"andpd {$src2, $dst|$dst, $src2}",
|
|
[(set FR64:$dst, (X86fand FR64:$src1,
|
|
(X86loadpf64 addr:$src2)))]>;
|
|
def FsORPDrm : PDI<0x56, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f128mem:$src2),
|
|
"orpd {$src2, $dst|$dst, $src2}",
|
|
[(set FR64:$dst, (X86for FR64:$src1,
|
|
(X86loadpf64 addr:$src2)))]>;
|
|
def FsXORPDrm : PDI<0x57, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f128mem:$src2),
|
|
"xorpd {$src2, $dst|$dst, $src2}",
|
|
[(set FR64:$dst, (X86fxor FR64:$src1,
|
|
(X86loadpf64 addr:$src2)))]>;
|
|
|
|
def FsANDNPDrr : PDI<0x55, MRMSrcReg,
|
|
(ops FR64:$dst, FR64:$src1, FR64:$src2),
|
|
"andnpd {$src2, $dst|$dst, $src2}", []>;
|
|
def FsANDNPDrm : PDI<0x55, MRMSrcMem,
|
|
(ops FR64:$dst, FR64:$src1, f128mem:$src2),
|
|
"andnpd {$src2, $dst|$dst, $src2}", []>;
|
|
}
|
|
|
|
/// scalar_sse2_fp_binop_rm - Scalar SSE2 binops come in three basic forms:
|
|
///
|
|
/// 1. f64 - This comes in SSE2 form for doubles.
|
|
/// 2. rr vs rm - They include a reg+reg form and a reg+mem form.
|
|
///
|
|
/// In addition, scalar SSE ops have an intrinsic form. This form is unlike the
|
|
/// normal form, in that they take an entire vector (instead of a scalar) and
|
|
/// leave the top elements undefined. This adds another two variants of the
|
|
/// above permutations, giving us 8 forms for 'instruction'.
|
|
///
|
|
let isTwoAddress = 1 in {
|
|
multiclass scalar_sse2_fp_binop_rm<bits<8> opc, string OpcodeStr,
|
|
SDNode OpNode, Intrinsic F64Int,
|
|
bit Commutable = 0> {
|
|
// Scalar operation, reg+reg.
|
|
def SDrr : SDI<opc, MRMSrcReg, (ops FR64:$dst, FR64:$src1, FR64:$src2),
|
|
!strconcat(OpcodeStr, "sd {$src2, $dst|$dst, $src2}"),
|
|
[(set FR64:$dst, (OpNode FR64:$src1, FR64:$src2))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
// Scalar operation, reg+mem.
|
|
def SDrm : SDI<opc, MRMSrcMem, (ops FR64:$dst, FR64:$src1, f64mem:$src2),
|
|
!strconcat(OpcodeStr, "sd {$src2, $dst|$dst, $src2}"),
|
|
[(set FR64:$dst, (OpNode FR64:$src1, (load addr:$src2)))]>;
|
|
|
|
// Vector intrinsic operation, reg+reg.
|
|
def SDrr_Int : SDI<opc, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, "sd {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (F64Int VR128:$src1, VR128:$src2))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
// Vector intrinsic operation, reg+mem.
|
|
def SDrm_Int : SDI<opc, MRMSrcMem, (ops VR128:$dst, VR128:$src1, sdmem:$src2),
|
|
!strconcat(OpcodeStr, "sd {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (F64Int VR128:$src1,
|
|
sse_load_f64:$src2))]>;
|
|
}
|
|
}
|
|
|
|
// Arithmetic instructions
|
|
defm ADD : scalar_sse2_fp_binop_rm<0x58, "add", fadd, int_x86_sse2_add_sd, 1>;
|
|
defm MUL : scalar_sse2_fp_binop_rm<0x59, "mul", fmul, int_x86_sse2_mul_sd, 1>;
|
|
defm SUB : scalar_sse2_fp_binop_rm<0x5C, "sub", fsub, int_x86_sse2_sub_sd>;
|
|
defm DIV : scalar_sse2_fp_binop_rm<0x5E, "div", fdiv, int_x86_sse2_div_sd>;
|
|
|
|
defm MAX : scalar_sse2_fp_binop_rm<0x5F, "max", X86fmax, int_x86_sse2_max_sd>;
|
|
defm MIN : scalar_sse2_fp_binop_rm<0x5D, "min", X86fmin, int_x86_sse2_min_sd>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE packed FP Instructions
|
|
|
|
// Move Instructions
|
|
def MOVAPDrr : PDI<0x28, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"movapd {$src, $dst|$dst, $src}", []>;
|
|
def MOVAPDrm : PDI<0x28, MRMSrcMem, (ops VR128:$dst, f128mem:$src),
|
|
"movapd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (loadv2f64 addr:$src))]>;
|
|
|
|
def MOVAPDmr : PDI<0x29, MRMDestMem, (ops f128mem:$dst, VR128:$src),
|
|
"movapd {$src, $dst|$dst, $src}",
|
|
[(store (v2f64 VR128:$src), addr:$dst)]>;
|
|
|
|
def MOVUPDrr : PDI<0x10, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"movupd {$src, $dst|$dst, $src}", []>;
|
|
def MOVUPDrm : PDI<0x10, MRMSrcMem, (ops VR128:$dst, f128mem:$src),
|
|
"movupd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_loadu_pd addr:$src))]>;
|
|
def MOVUPDmr : PDI<0x11, MRMDestMem, (ops f128mem:$dst, VR128:$src),
|
|
"movupd {$src, $dst|$dst, $src}",
|
|
[(int_x86_sse2_storeu_pd addr:$dst, VR128:$src)]>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
let AddedComplexity = 20 in {
|
|
def MOVLPDrm : PDI<0x12, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f64mem:$src2),
|
|
"movlpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2f64 (vector_shuffle VR128:$src1,
|
|
(scalar_to_vector (loadf64 addr:$src2)),
|
|
MOVLP_shuffle_mask)))]>;
|
|
def MOVHPDrm : PDI<0x16, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f64mem:$src2),
|
|
"movhpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2f64 (vector_shuffle VR128:$src1,
|
|
(scalar_to_vector (loadf64 addr:$src2)),
|
|
MOVHP_shuffle_mask)))]>;
|
|
} // AddedComplexity
|
|
} // isTwoAddress
|
|
|
|
def MOVLPDmr : PDI<0x13, MRMDestMem, (ops f64mem:$dst, VR128:$src),
|
|
"movlpd {$src, $dst|$dst, $src}",
|
|
[(store (f64 (vector_extract (v2f64 VR128:$src),
|
|
(iPTR 0))), addr:$dst)]>;
|
|
|
|
// v2f64 extract element 1 is always custom lowered to unpack high to low
|
|
// and extract element 0 so the non-store version isn't too horrible.
|
|
def MOVHPDmr : PDI<0x17, MRMDestMem, (ops f64mem:$dst, VR128:$src),
|
|
"movhpd {$src, $dst|$dst, $src}",
|
|
[(store (f64 (vector_extract
|
|
(v2f64 (vector_shuffle VR128:$src, (undef),
|
|
UNPCKH_shuffle_mask)), (iPTR 0))),
|
|
addr:$dst)]>;
|
|
|
|
// SSE2 instructions without OpSize prefix
|
|
def Int_CVTDQ2PSrr : I<0x5B, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"cvtdq2ps {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtdq2ps VR128:$src))]>,
|
|
TB, Requires<[HasSSE2]>;
|
|
def Int_CVTDQ2PSrm : I<0x5B, MRMSrcMem, (ops VR128:$dst, i128mem:$src),
|
|
"cvtdq2ps {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtdq2ps
|
|
(bitconvert (loadv2i64 addr:$src))))]>,
|
|
TB, Requires<[HasSSE2]>;
|
|
|
|
// SSE2 instructions with XS prefix
|
|
def Int_CVTDQ2PDrr : I<0xE6, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"cvtdq2pd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtdq2pd VR128:$src))]>,
|
|
XS, Requires<[HasSSE2]>;
|
|
def Int_CVTDQ2PDrm : I<0xE6, MRMSrcMem, (ops VR128:$dst, i64mem:$src),
|
|
"cvtdq2pd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtdq2pd
|
|
(bitconvert (loadv2i64 addr:$src))))]>,
|
|
XS, Requires<[HasSSE2]>;
|
|
|
|
def Int_CVTPS2DQrr : PDI<0x5B, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"cvtps2dq {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtps2dq VR128:$src))]>;
|
|
def Int_CVTPS2DQrm : PDI<0x5B, MRMSrcMem, (ops VR128:$dst, f128mem:$src),
|
|
"cvtps2dq {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtps2dq
|
|
(load addr:$src)))]>;
|
|
// SSE2 packed instructions with XS prefix
|
|
def Int_CVTTPS2DQrr : I<0x5B, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"cvttps2dq {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvttps2dq VR128:$src))]>,
|
|
XS, Requires<[HasSSE2]>;
|
|
def Int_CVTTPS2DQrm : I<0x5B, MRMSrcMem, (ops VR128:$dst, f128mem:$src),
|
|
"cvttps2dq {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvttps2dq
|
|
(load addr:$src)))]>,
|
|
XS, Requires<[HasSSE2]>;
|
|
|
|
// SSE2 packed instructions with XD prefix
|
|
def Int_CVTPD2DQrr : I<0xE6, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"cvtpd2dq {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtpd2dq VR128:$src))]>,
|
|
XD, Requires<[HasSSE2]>;
|
|
def Int_CVTPD2DQrm : I<0xE6, MRMSrcMem, (ops VR128:$dst, f128mem:$src),
|
|
"cvtpd2dq {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtpd2dq
|
|
(load addr:$src)))]>,
|
|
XD, Requires<[HasSSE2]>;
|
|
|
|
def Int_CVTTPD2DQrr : PDI<0xE6, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"cvttpd2dq {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvttpd2dq VR128:$src))]>;
|
|
def Int_CVTTPD2DQrm : PDI<0xE6, MRMSrcMem, (ops VR128:$dst, f128mem:$src),
|
|
"cvttpd2dq {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvttpd2dq
|
|
(load addr:$src)))]>;
|
|
|
|
// SSE2 instructions without OpSize prefix
|
|
def Int_CVTPS2PDrr : I<0x5A, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"cvtps2pd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtps2pd VR128:$src))]>,
|
|
TB, Requires<[HasSSE2]>;
|
|
def Int_CVTPS2PDrm : I<0x5A, MRMSrcReg, (ops VR128:$dst, f64mem:$src),
|
|
"cvtps2pd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtps2pd
|
|
(load addr:$src)))]>,
|
|
TB, Requires<[HasSSE2]>;
|
|
|
|
def Int_CVTPD2PSrr : PDI<0x5A, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"cvtpd2ps {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtpd2ps VR128:$src))]>;
|
|
def Int_CVTPD2PSrm : PDI<0x5A, MRMSrcReg, (ops VR128:$dst, f128mem:$src),
|
|
"cvtpd2ps {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtpd2ps
|
|
(load addr:$src)))]>;
|
|
|
|
// Match intrinsics which expect XMM operand(s).
|
|
// Aliases for intrinsics
|
|
let isTwoAddress = 1 in {
|
|
def Int_CVTSI2SDrr: SDI<0x2A, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, GR32:$src2),
|
|
"cvtsi2sd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtsi2sd VR128:$src1,
|
|
GR32:$src2))]>;
|
|
def Int_CVTSI2SDrm: SDI<0x2A, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, i32mem:$src2),
|
|
"cvtsi2sd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtsi2sd VR128:$src1,
|
|
(loadi32 addr:$src2)))]>;
|
|
def Int_CVTSD2SSrr: SDI<0x5A, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"cvtsd2ss {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtsd2ss VR128:$src1,
|
|
VR128:$src2))]>;
|
|
def Int_CVTSD2SSrm: SDI<0x5A, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f64mem:$src2),
|
|
"cvtsd2ss {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtsd2ss VR128:$src1,
|
|
(load addr:$src2)))]>;
|
|
def Int_CVTSS2SDrr: I<0x5A, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"cvtss2sd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtss2sd VR128:$src1,
|
|
VR128:$src2))]>, XS,
|
|
Requires<[HasSSE2]>;
|
|
def Int_CVTSS2SDrm: I<0x5A, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f32mem:$src2),
|
|
"cvtss2sd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (int_x86_sse2_cvtss2sd VR128:$src1,
|
|
(load addr:$src2)))]>, XS,
|
|
Requires<[HasSSE2]>;
|
|
}
|
|
|
|
/// packed_sse2_fp_binop_rm - Packed SSE binops come in three basic forms:
|
|
/// 1. v2f64 - This comes in SSE2 form for doubles.
|
|
/// 2. rr vs rm - They include a reg+reg form and a ref+mem form.
|
|
///
|
|
let isTwoAddress = 1 in {
|
|
multiclass packed_sse2_fp_binop_rm<bits<8> opc, string OpcodeStr,
|
|
SDNode OpNode, bit Commutable = 0> {
|
|
// Packed operation, reg+reg.
|
|
def PDrr : PDI<opc, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, "pd {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (v2f64 (OpNode VR128:$src1, VR128:$src2)))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
// Packed operation, reg+mem.
|
|
def PDrm : PDI<opc, MRMSrcMem, (ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
!strconcat(OpcodeStr, "pd {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (OpNode VR128:$src1, (loadv2f64 addr:$src2)))]>;
|
|
}
|
|
}
|
|
|
|
defm ADD : packed_sse2_fp_binop_rm<0x58, "add", fadd, 1>;
|
|
defm MUL : packed_sse2_fp_binop_rm<0x59, "mul", fmul, 1>;
|
|
defm DIV : packed_sse2_fp_binop_rm<0x5E, "div", fdiv>;
|
|
defm SUB : packed_sse2_fp_binop_rm<0x5C, "sub", fsub>;
|
|
|
|
// Arithmetic
|
|
|
|
class PD_Intr<bits<8> o, string OpcodeStr, Intrinsic IntId>
|
|
: PDI<o, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
!strconcat(OpcodeStr, " {$src, $dst|$dst, $src}"),
|
|
[(set VR128:$dst, (IntId VR128:$src))]>;
|
|
class PD_Intm<bits<8> o, string OpcodeStr, Intrinsic IntId>
|
|
: PDI<o, MRMSrcMem, (ops VR128:$dst, f64mem:$src),
|
|
!strconcat(OpcodeStr, " {$src, $dst|$dst, $src}"),
|
|
[(set VR128:$dst, (IntId (load addr:$src)))]>;
|
|
|
|
class PD_Intrr<bits<8> o, string OpcodeStr, Intrinsic IntId>
|
|
: PDI<o, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (IntId VR128:$src1, VR128:$src2))]>;
|
|
class PD_Intrm<bits<8> o, string OpcodeStr, Intrinsic IntId>
|
|
: PDI<o, MRMSrcMem, (ops VR128:$dst, VR128:$src1, f64mem:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (IntId VR128:$src1, (load addr:$src2)))]>;
|
|
|
|
def SQRTPDr : PD_Intr<0x51, "sqrtpd", int_x86_sse2_sqrt_pd>;
|
|
def SQRTPDm : PD_Intm<0x51, "sqrtpd", int_x86_sse2_sqrt_pd>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
let isCommutable = 1 in {
|
|
def MAXPDrr : PD_Intrr<0x5F, "maxpd", int_x86_sse2_max_pd>;
|
|
def MINPDrr : PD_Intrr<0x5D, "minpd", int_x86_sse2_min_pd>;
|
|
}
|
|
|
|
def MAXPDrm : PD_Intrm<0x5F, "maxpd", int_x86_sse2_max_pd>;
|
|
def MINPDrm : PD_Intrm<0x5D, "minpd", int_x86_sse2_min_pd>;
|
|
}
|
|
|
|
// Logical
|
|
let isTwoAddress = 1 in {
|
|
let isCommutable = 1 in {
|
|
def ANDPDrr : PDI<0x54, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"andpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(and (bc_v2i64 (v2f64 VR128:$src1)),
|
|
(bc_v2i64 (v2f64 VR128:$src2))))]>;
|
|
def ORPDrr : PDI<0x56, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"orpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(or (bc_v2i64 (v2f64 VR128:$src1)),
|
|
(bc_v2i64 (v2f64 VR128:$src2))))]>;
|
|
def XORPDrr : PDI<0x57, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"xorpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(xor (bc_v2i64 (v2f64 VR128:$src1)),
|
|
(bc_v2i64 (v2f64 VR128:$src2))))]>;
|
|
}
|
|
|
|
def ANDPDrm : PDI<0x54, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
"andpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(and (bc_v2i64 (v2f64 VR128:$src1)),
|
|
(bc_v2i64 (loadv2f64 addr:$src2))))]>;
|
|
def ORPDrm : PDI<0x56, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
"orpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(or (bc_v2i64 (v2f64 VR128:$src1)),
|
|
(bc_v2i64 (loadv2f64 addr:$src2))))]>;
|
|
def XORPDrm : PDI<0x57, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
"xorpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(xor (bc_v2i64 (v2f64 VR128:$src1)),
|
|
(bc_v2i64 (loadv2f64 addr:$src2))))]>;
|
|
def ANDNPDrr : PDI<0x55, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"andnpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(and (vnot (bc_v2i64 (v2f64 VR128:$src1))),
|
|
(bc_v2i64 (v2f64 VR128:$src2))))]>;
|
|
def ANDNPDrm : PDI<0x55, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1,f128mem:$src2),
|
|
"andnpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(and (vnot (bc_v2i64 (v2f64 VR128:$src1))),
|
|
(bc_v2i64 (loadv2f64 addr:$src2))))]>;
|
|
}
|
|
|
|
let isTwoAddress = 1 in {
|
|
def CMPPDrri : PDIi8<0xC2, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src, SSECC:$cc),
|
|
"cmp${cc}pd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cmp_pd VR128:$src1,
|
|
VR128:$src, imm:$cc))]>;
|
|
def CMPPDrmi : PDIi8<0xC2, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src, SSECC:$cc),
|
|
"cmp${cc}pd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_cmp_pd VR128:$src1,
|
|
(load addr:$src), imm:$cc))]>;
|
|
}
|
|
|
|
// Shuffle and unpack instructions
|
|
let isTwoAddress = 1 in {
|
|
def SHUFPDrri : PDIi8<0xC6, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2, i8imm:$src3),
|
|
"shufpd {$src3, $src2, $dst|$dst, $src2, $src3}",
|
|
[(set VR128:$dst, (v2f64 (vector_shuffle
|
|
VR128:$src1, VR128:$src2,
|
|
SHUFP_shuffle_mask:$src3)))]>;
|
|
def SHUFPDrmi : PDIi8<0xC6, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1,
|
|
f128mem:$src2, i8imm:$src3),
|
|
"shufpd {$src3, $src2, $dst|$dst, $src2, $src3}",
|
|
[(set VR128:$dst,
|
|
(v2f64 (vector_shuffle
|
|
VR128:$src1, (load addr:$src2),
|
|
SHUFP_shuffle_mask:$src3)))]>;
|
|
|
|
let AddedComplexity = 10 in {
|
|
def UNPCKHPDrr : PDI<0x15, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"unpckhpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2f64 (vector_shuffle
|
|
VR128:$src1, VR128:$src2,
|
|
UNPCKH_shuffle_mask)))]>;
|
|
def UNPCKHPDrm : PDI<0x15, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
"unpckhpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2f64 (vector_shuffle
|
|
VR128:$src1, (load addr:$src2),
|
|
UNPCKH_shuffle_mask)))]>;
|
|
|
|
def UNPCKLPDrr : PDI<0x14, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"unpcklpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2f64 (vector_shuffle
|
|
VR128:$src1, VR128:$src2,
|
|
UNPCKL_shuffle_mask)))]>;
|
|
def UNPCKLPDrm : PDI<0x14, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
"unpcklpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2f64 (vector_shuffle
|
|
VR128:$src1, (load addr:$src2),
|
|
UNPCKL_shuffle_mask)))]>;
|
|
} // AddedComplexity
|
|
} // isTwoAddress
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE integer instructions
|
|
|
|
// Move Instructions
|
|
def MOVDQArr : PDI<0x6F, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"movdqa {$src, $dst|$dst, $src}", []>;
|
|
def MOVDQArm : PDI<0x6F, MRMSrcMem, (ops VR128:$dst, i128mem:$src),
|
|
"movdqa {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (loadv2i64 addr:$src))]>;
|
|
def MOVDQAmr : PDI<0x7F, MRMDestMem, (ops i128mem:$dst, VR128:$src),
|
|
"movdqa {$src, $dst|$dst, $src}",
|
|
[(store (v2i64 VR128:$src), addr:$dst)]>;
|
|
def MOVDQUrm : I<0x6F, MRMSrcMem, (ops VR128:$dst, i128mem:$src),
|
|
"movdqu {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_loadu_dq addr:$src))]>,
|
|
XS, Requires<[HasSSE2]>;
|
|
def MOVDQUmr : I<0x7F, MRMDestMem, (ops i128mem:$dst, VR128:$src),
|
|
"movdqu {$src, $dst|$dst, $src}",
|
|
[(int_x86_sse2_storeu_dq addr:$dst, VR128:$src)]>,
|
|
XS, Requires<[HasSSE2]>;
|
|
|
|
|
|
let isTwoAddress = 1 in {
|
|
|
|
multiclass PDI_binop_rm_int<bits<8> opc, string OpcodeStr, Intrinsic IntId,
|
|
bit Commutable = 0> {
|
|
def rr : PDI<opc, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (IntId VR128:$src1, VR128:$src2))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
def rm : PDI<opc, MRMSrcMem, (ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (IntId VR128:$src1,
|
|
(bitconvert (loadv2i64 addr:$src2))))]>;
|
|
}
|
|
|
|
multiclass PDI_binop_rmi_int<bits<8> opc, bits<8> opc2, Format ImmForm,
|
|
string OpcodeStr, Intrinsic IntId> {
|
|
def rr : PDI<opc, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (IntId VR128:$src1, VR128:$src2))]>;
|
|
def rm : PDI<opc, MRMSrcMem, (ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (IntId VR128:$src1,
|
|
(bitconvert (loadv2i64 addr:$src2))))]>;
|
|
def ri : PDIi8<opc2, ImmForm, (ops VR128:$dst, VR128:$src1, i32i8imm:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (IntId VR128:$src1,
|
|
(scalar_to_vector (i32 imm:$src2))))]>;
|
|
}
|
|
|
|
|
|
/// PDI_binop_rm - Simple SSE2 binary operator.
|
|
multiclass PDI_binop_rm<bits<8> opc, string OpcodeStr, SDNode OpNode,
|
|
ValueType OpVT, bit Commutable = 0> {
|
|
def rr : PDI<opc, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (OpVT (OpNode VR128:$src1, VR128:$src2)))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
def rm : PDI<opc, MRMSrcMem, (ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (OpVT (OpNode VR128:$src1,
|
|
(bitconvert (loadv2i64 addr:$src2)))))]>;
|
|
}
|
|
|
|
/// PDI_binop_rm_v2i64 - Simple SSE2 binary operator whose type is v2i64.
|
|
///
|
|
/// FIXME: we could eliminate this and use PDI_binop_rm instead if tblgen knew
|
|
/// to collapse (bitconvert VT to VT) into its operand.
|
|
///
|
|
multiclass PDI_binop_rm_v2i64<bits<8> opc, string OpcodeStr, SDNode OpNode,
|
|
bit Commutable = 0> {
|
|
def rr : PDI<opc, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (v2i64 (OpNode VR128:$src1, VR128:$src2)))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
def rm : PDI<opc, MRMSrcMem, (ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (OpNode VR128:$src1,(loadv2i64 addr:$src2)))]>;
|
|
}
|
|
|
|
} // isTwoAddress
|
|
|
|
// 128-bit Integer Arithmetic
|
|
|
|
defm PADDB : PDI_binop_rm<0xFC, "paddb", add, v16i8, 1>;
|
|
defm PADDW : PDI_binop_rm<0xFD, "paddw", add, v8i16, 1>;
|
|
defm PADDD : PDI_binop_rm<0xFE, "paddd", add, v4i32, 1>;
|
|
defm PADDQ : PDI_binop_rm_v2i64<0xD4, "paddq", add, 1>;
|
|
|
|
defm PADDSB : PDI_binop_rm_int<0xEC, "paddsb" , int_x86_sse2_padds_b, 1>;
|
|
defm PADDSW : PDI_binop_rm_int<0xED, "paddsw" , int_x86_sse2_padds_w, 1>;
|
|
defm PADDUSB : PDI_binop_rm_int<0xDC, "paddusb", int_x86_sse2_paddus_b, 1>;
|
|
defm PADDUSW : PDI_binop_rm_int<0xDD, "paddusw", int_x86_sse2_paddus_w, 1>;
|
|
|
|
defm PSUBB : PDI_binop_rm<0xF8, "psubb", sub, v16i8>;
|
|
defm PSUBW : PDI_binop_rm<0xF9, "psubw", sub, v8i16>;
|
|
defm PSUBD : PDI_binop_rm<0xFA, "psubd", sub, v4i32>;
|
|
defm PSUBQ : PDI_binop_rm_v2i64<0xFB, "psubq", sub>;
|
|
|
|
defm PSUBSB : PDI_binop_rm_int<0xE8, "psubsb" , int_x86_sse2_psubs_b>;
|
|
defm PSUBSW : PDI_binop_rm_int<0xE9, "psubsw" , int_x86_sse2_psubs_w>;
|
|
defm PSUBUSB : PDI_binop_rm_int<0xD8, "psubusb", int_x86_sse2_psubus_b>;
|
|
defm PSUBUSW : PDI_binop_rm_int<0xD9, "psubusw", int_x86_sse2_psubus_w>;
|
|
|
|
defm PMULLW : PDI_binop_rm<0xD5, "pmullw", mul, v8i16, 1>;
|
|
|
|
defm PMULHUW : PDI_binop_rm_int<0xE4, "pmulhuw", int_x86_sse2_pmulhu_w, 1>;
|
|
defm PMULHW : PDI_binop_rm_int<0xE5, "pmulhw" , int_x86_sse2_pmulh_w , 1>;
|
|
defm PMULUDQ : PDI_binop_rm_int<0xF4, "pmuludq", int_x86_sse2_pmulu_dq, 1>;
|
|
|
|
defm PMADDWD : PDI_binop_rm_int<0xF5, "pmaddwd", int_x86_sse2_pmadd_wd, 1>;
|
|
|
|
defm PAVGB : PDI_binop_rm_int<0xE0, "pavgb", int_x86_sse2_pavg_b, 1>;
|
|
defm PAVGW : PDI_binop_rm_int<0xE3, "pavgw", int_x86_sse2_pavg_w, 1>;
|
|
|
|
|
|
defm PMINUB : PDI_binop_rm_int<0xDA, "pminub", int_x86_sse2_pminu_b, 1>;
|
|
defm PMINSW : PDI_binop_rm_int<0xEA, "pminsw", int_x86_sse2_pmins_w, 1>;
|
|
defm PMAXUB : PDI_binop_rm_int<0xDE, "pmaxub", int_x86_sse2_pmaxu_b, 1>;
|
|
defm PMAXSW : PDI_binop_rm_int<0xEE, "pmaxsw", int_x86_sse2_pmaxs_w, 1>;
|
|
defm PSADBW : PDI_binop_rm_int<0xE0, "psadbw", int_x86_sse2_psad_bw, 1>;
|
|
|
|
|
|
defm PSLLW : PDI_binop_rmi_int<0xF1, 0x71, MRM6r, "psllw", int_x86_sse2_psll_w>;
|
|
defm PSLLD : PDI_binop_rmi_int<0xF2, 0x72, MRM6r, "pslld", int_x86_sse2_psll_d>;
|
|
defm PSLLQ : PDI_binop_rmi_int<0xF3, 0x73, MRM6r, "psllq", int_x86_sse2_psll_q>;
|
|
|
|
defm PSRLW : PDI_binop_rmi_int<0xD1, 0x71, MRM2r, "psrlw", int_x86_sse2_psrl_w>;
|
|
defm PSRLD : PDI_binop_rmi_int<0xD2, 0x72, MRM2r, "psrld", int_x86_sse2_psrl_d>;
|
|
defm PSRLQ : PDI_binop_rmi_int<0xD3, 0x73, MRM2r, "psrlq", int_x86_sse2_psrl_q>;
|
|
|
|
defm PSRAW : PDI_binop_rmi_int<0xE1, 0x71, MRM4r, "psraw", int_x86_sse2_psra_w>;
|
|
defm PSRAD : PDI_binop_rmi_int<0xE2, 0x72, MRM4r, "psrad", int_x86_sse2_psra_d>;
|
|
// PSRAQ doesn't exist in SSE[1-3].
|
|
|
|
// 128-bit logical shifts.
|
|
let isTwoAddress = 1 in {
|
|
def PSLLDQri : PDIi8<0x73, MRM7r,
|
|
(ops VR128:$dst, VR128:$src1, i32i8imm:$src2),
|
|
"pslldq {$src2, $dst|$dst, $src2}", []>;
|
|
def PSRLDQri : PDIi8<0x73, MRM3r,
|
|
(ops VR128:$dst, VR128:$src1, i32i8imm:$src2),
|
|
"psrldq {$src2, $dst|$dst, $src2}", []>;
|
|
// PSRADQri doesn't exist in SSE[1-3].
|
|
}
|
|
|
|
let Predicates = [HasSSE2] in {
|
|
def : Pat<(int_x86_sse2_psll_dq VR128:$src1, imm:$src2),
|
|
(v2i64 (PSLLDQri VR128:$src1, (PSxLDQ_imm imm:$src2)))>;
|
|
def : Pat<(int_x86_sse2_psrl_dq VR128:$src1, imm:$src2),
|
|
(v2i64 (PSRLDQri VR128:$src1, (PSxLDQ_imm imm:$src2)))>;
|
|
def : Pat<(v2f64 (X86fsrl VR128:$src1, i32immSExt8:$src2)),
|
|
(v2f64 (PSRLDQri VR128:$src1, (PSxLDQ_imm imm:$src2)))>;
|
|
}
|
|
|
|
// Logical
|
|
defm PAND : PDI_binop_rm_v2i64<0xDB, "pand", and, 1>;
|
|
defm POR : PDI_binop_rm_v2i64<0xEB, "por" , or , 1>;
|
|
defm PXOR : PDI_binop_rm_v2i64<0xEF, "pxor", xor, 1>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
def PANDNrr : PDI<0xDF, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"pandn {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (v2i64 (and (vnot VR128:$src1),
|
|
VR128:$src2)))]>;
|
|
|
|
def PANDNrm : PDI<0xDF, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
"pandn {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (v2i64 (and (vnot VR128:$src1),
|
|
(load addr:$src2))))]>;
|
|
}
|
|
|
|
// SSE2 Integer comparison
|
|
defm PCMPEQB : PDI_binop_rm_int<0x74, "pcmpeqb", int_x86_sse2_pcmpeq_b>;
|
|
defm PCMPEQW : PDI_binop_rm_int<0x75, "pcmpeqw", int_x86_sse2_pcmpeq_w>;
|
|
defm PCMPEQD : PDI_binop_rm_int<0x76, "pcmpeqd", int_x86_sse2_pcmpeq_d>;
|
|
defm PCMPGTB : PDI_binop_rm_int<0x64, "pcmpgtb", int_x86_sse2_pcmpgt_b>;
|
|
defm PCMPGTW : PDI_binop_rm_int<0x65, "pcmpgtw", int_x86_sse2_pcmpgt_w>;
|
|
defm PCMPGTD : PDI_binop_rm_int<0x66, "pcmpgtd", int_x86_sse2_pcmpgt_d>;
|
|
|
|
// Pack instructions
|
|
defm PACKSSWB : PDI_binop_rm_int<0x63, "packsswb", int_x86_sse2_packsswb_128>;
|
|
defm PACKSSDW : PDI_binop_rm_int<0x6B, "packssdw", int_x86_sse2_packssdw_128>;
|
|
defm PACKUSWB : PDI_binop_rm_int<0x67, "packuswb", int_x86_sse2_packuswb_128>;
|
|
|
|
// Shuffle and unpack instructions
|
|
def PSHUFDri : PDIi8<0x70, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, i8imm:$src2),
|
|
"pshufd {$src2, $src1, $dst|$dst, $src1, $src2}",
|
|
[(set VR128:$dst, (v4i32 (vector_shuffle
|
|
VR128:$src1, (undef),
|
|
PSHUFD_shuffle_mask:$src2)))]>;
|
|
def PSHUFDmi : PDIi8<0x70, MRMSrcMem,
|
|
(ops VR128:$dst, i128mem:$src1, i8imm:$src2),
|
|
"pshufd {$src2, $src1, $dst|$dst, $src1, $src2}",
|
|
[(set VR128:$dst, (v4i32 (vector_shuffle
|
|
(bc_v4i32(loadv2i64 addr:$src1)),
|
|
(undef),
|
|
PSHUFD_shuffle_mask:$src2)))]>;
|
|
|
|
// SSE2 with ImmT == Imm8 and XS prefix.
|
|
def PSHUFHWri : Ii8<0x70, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, i8imm:$src2),
|
|
"pshufhw {$src2, $src1, $dst|$dst, $src1, $src2}",
|
|
[(set VR128:$dst, (v8i16 (vector_shuffle
|
|
VR128:$src1, (undef),
|
|
PSHUFHW_shuffle_mask:$src2)))]>,
|
|
XS, Requires<[HasSSE2]>;
|
|
def PSHUFHWmi : Ii8<0x70, MRMSrcMem,
|
|
(ops VR128:$dst, i128mem:$src1, i8imm:$src2),
|
|
"pshufhw {$src2, $src1, $dst|$dst, $src1, $src2}",
|
|
[(set VR128:$dst, (v8i16 (vector_shuffle
|
|
(bc_v8i16 (loadv2i64 addr:$src1)),
|
|
(undef),
|
|
PSHUFHW_shuffle_mask:$src2)))]>,
|
|
XS, Requires<[HasSSE2]>;
|
|
|
|
// SSE2 with ImmT == Imm8 and XD prefix.
|
|
def PSHUFLWri : Ii8<0x70, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, i32i8imm:$src2),
|
|
"pshuflw {$src2, $src1, $dst|$dst, $src1, $src2}",
|
|
[(set VR128:$dst, (v8i16 (vector_shuffle
|
|
VR128:$src1, (undef),
|
|
PSHUFLW_shuffle_mask:$src2)))]>,
|
|
XD, Requires<[HasSSE2]>;
|
|
def PSHUFLWmi : Ii8<0x70, MRMSrcMem,
|
|
(ops VR128:$dst, i128mem:$src1, i32i8imm:$src2),
|
|
"pshuflw {$src2, $src1, $dst|$dst, $src1, $src2}",
|
|
[(set VR128:$dst, (v8i16 (vector_shuffle
|
|
(bc_v8i16 (loadv2i64 addr:$src1)),
|
|
(undef),
|
|
PSHUFLW_shuffle_mask:$src2)))]>,
|
|
XD, Requires<[HasSSE2]>;
|
|
|
|
|
|
let isTwoAddress = 1 in {
|
|
def PUNPCKLBWrr : PDI<0x60, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"punpcklbw {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v16i8 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
UNPCKL_shuffle_mask)))]>;
|
|
def PUNPCKLBWrm : PDI<0x60, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
"punpcklbw {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v16i8 (vector_shuffle VR128:$src1,
|
|
(bc_v16i8 (loadv2i64 addr:$src2)),
|
|
UNPCKL_shuffle_mask)))]>;
|
|
def PUNPCKLWDrr : PDI<0x61, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"punpcklwd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v8i16 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
UNPCKL_shuffle_mask)))]>;
|
|
def PUNPCKLWDrm : PDI<0x61, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
"punpcklwd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v8i16 (vector_shuffle VR128:$src1,
|
|
(bc_v8i16 (loadv2i64 addr:$src2)),
|
|
UNPCKL_shuffle_mask)))]>;
|
|
def PUNPCKLDQrr : PDI<0x62, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"punpckldq {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4i32 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
UNPCKL_shuffle_mask)))]>;
|
|
def PUNPCKLDQrm : PDI<0x62, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
"punpckldq {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4i32 (vector_shuffle VR128:$src1,
|
|
(bc_v4i32 (loadv2i64 addr:$src2)),
|
|
UNPCKL_shuffle_mask)))]>;
|
|
def PUNPCKLQDQrr : PDI<0x6C, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"punpcklqdq {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2i64 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
UNPCKL_shuffle_mask)))]>;
|
|
def PUNPCKLQDQrm : PDI<0x6C, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
"punpcklqdq {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2i64 (vector_shuffle VR128:$src1,
|
|
(loadv2i64 addr:$src2),
|
|
UNPCKL_shuffle_mask)))]>;
|
|
|
|
def PUNPCKHBWrr : PDI<0x68, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"punpckhbw {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v16i8 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
UNPCKH_shuffle_mask)))]>;
|
|
def PUNPCKHBWrm : PDI<0x68, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
"punpckhbw {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v16i8 (vector_shuffle VR128:$src1,
|
|
(bc_v16i8 (loadv2i64 addr:$src2)),
|
|
UNPCKH_shuffle_mask)))]>;
|
|
def PUNPCKHWDrr : PDI<0x69, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"punpckhwd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v8i16 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
UNPCKH_shuffle_mask)))]>;
|
|
def PUNPCKHWDrm : PDI<0x69, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
"punpckhwd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v8i16 (vector_shuffle VR128:$src1,
|
|
(bc_v8i16 (loadv2i64 addr:$src2)),
|
|
UNPCKH_shuffle_mask)))]>;
|
|
def PUNPCKHDQrr : PDI<0x6A, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"punpckhdq {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4i32 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
UNPCKH_shuffle_mask)))]>;
|
|
def PUNPCKHDQrm : PDI<0x6A, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
"punpckhdq {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v4i32 (vector_shuffle VR128:$src1,
|
|
(bc_v4i32 (loadv2i64 addr:$src2)),
|
|
UNPCKH_shuffle_mask)))]>;
|
|
def PUNPCKHQDQrr : PDI<0x6D, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"punpckhqdq {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2i64 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
UNPCKH_shuffle_mask)))]>;
|
|
def PUNPCKHQDQrm : PDI<0x6D, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
"punpckhqdq {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2i64 (vector_shuffle VR128:$src1,
|
|
(loadv2i64 addr:$src2),
|
|
UNPCKH_shuffle_mask)))]>;
|
|
}
|
|
|
|
// Extract / Insert
|
|
def PEXTRWri : PDIi8<0xC5, MRMSrcReg,
|
|
(ops GR32:$dst, VR128:$src1, i32i8imm:$src2),
|
|
"pextrw {$src2, $src1, $dst|$dst, $src1, $src2}",
|
|
[(set GR32:$dst, (X86pextrw (v8i16 VR128:$src1),
|
|
(iPTR imm:$src2)))]>;
|
|
let isTwoAddress = 1 in {
|
|
def PINSRWrri : PDIi8<0xC4, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1,
|
|
GR32:$src2, i32i8imm:$src3),
|
|
"pinsrw {$src3, $src2, $dst|$dst, $src2, $src3}",
|
|
[(set VR128:$dst,
|
|
(v8i16 (X86pinsrw (v8i16 VR128:$src1),
|
|
GR32:$src2, (iPTR imm:$src3))))]>;
|
|
def PINSRWrmi : PDIi8<0xC4, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1,
|
|
i16mem:$src2, i32i8imm:$src3),
|
|
"pinsrw {$src3, $src2, $dst|$dst, $src2, $src3}",
|
|
[(set VR128:$dst,
|
|
(v8i16 (X86pinsrw (v8i16 VR128:$src1),
|
|
(i32 (anyext (loadi16 addr:$src2))),
|
|
(iPTR imm:$src3))))]>;
|
|
}
|
|
|
|
// Mask creation
|
|
def PMOVMSKBrr : PDI<0xD7, MRMSrcReg, (ops GR32:$dst, VR128:$src),
|
|
"pmovmskb {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (int_x86_sse2_pmovmskb_128 VR128:$src))]>;
|
|
|
|
// Conditional store
|
|
def MASKMOVDQU : PDI<0xF7, MRMSrcReg, (ops VR128:$src, VR128:$mask),
|
|
"maskmovdqu {$mask, $src|$src, $mask}",
|
|
[(int_x86_sse2_maskmov_dqu VR128:$src, VR128:$mask, EDI)]>,
|
|
Imp<[EDI],[]>;
|
|
|
|
// Non-temporal stores
|
|
def MOVNTPDmr : PDI<0x2B, MRMDestMem, (ops i128mem:$dst, VR128:$src),
|
|
"movntpd {$src, $dst|$dst, $src}",
|
|
[(int_x86_sse2_movnt_pd addr:$dst, VR128:$src)]>;
|
|
def MOVNTDQmr : PDI<0xE7, MRMDestMem, (ops f128mem:$dst, VR128:$src),
|
|
"movntdq {$src, $dst|$dst, $src}",
|
|
[(int_x86_sse2_movnt_dq addr:$dst, VR128:$src)]>;
|
|
def MOVNTImr : I<0xC3, MRMDestMem, (ops i32mem:$dst, GR32:$src),
|
|
"movnti {$src, $dst|$dst, $src}",
|
|
[(int_x86_sse2_movnt_i addr:$dst, GR32:$src)]>,
|
|
TB, Requires<[HasSSE2]>;
|
|
|
|
// Flush cache
|
|
def CLFLUSH : I<0xAE, MRM7m, (ops i8mem:$src),
|
|
"clflush $src", [(int_x86_sse2_clflush addr:$src)]>,
|
|
TB, Requires<[HasSSE2]>;
|
|
|
|
// Load, store, and memory fence
|
|
def LFENCE : I<0xAE, MRM5m, (ops),
|
|
"lfence", [(int_x86_sse2_lfence)]>, TB, Requires<[HasSSE2]>;
|
|
def MFENCE : I<0xAE, MRM6m, (ops),
|
|
"mfence", [(int_x86_sse2_mfence)]>, TB, Requires<[HasSSE2]>;
|
|
|
|
|
|
// Alias instructions that map zero vector to pxor / xorp* for sse.
|
|
// FIXME: remove when we can teach regalloc that xor reg, reg is ok.
|
|
let isReMaterializable = 1 in
|
|
def V_SETALLONES : PDI<0x76, MRMInitReg, (ops VR128:$dst),
|
|
"pcmpeqd $dst, $dst",
|
|
[(set VR128:$dst, (v2f64 immAllOnesV))]>;
|
|
|
|
// FR64 to 128-bit vector conversion.
|
|
def MOVSD2PDrr : SDI<0x10, MRMSrcReg, (ops VR128:$dst, FR64:$src),
|
|
"movsd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst,
|
|
(v2f64 (scalar_to_vector FR64:$src)))]>;
|
|
def MOVSD2PDrm : SDI<0x10, MRMSrcMem, (ops VR128:$dst, f64mem:$src),
|
|
"movsd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst,
|
|
(v2f64 (scalar_to_vector (loadf64 addr:$src))))]>;
|
|
|
|
def MOVDI2PDIrr : PDI<0x6E, MRMSrcReg, (ops VR128:$dst, GR32:$src),
|
|
"movd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst,
|
|
(v4i32 (scalar_to_vector GR32:$src)))]>;
|
|
def MOVDI2PDIrm : PDI<0x6E, MRMSrcMem, (ops VR128:$dst, i32mem:$src),
|
|
"movd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst,
|
|
(v4i32 (scalar_to_vector (loadi32 addr:$src))))]>;
|
|
|
|
def MOVDI2SSrr : PDI<0x6E, MRMSrcReg, (ops FR32:$dst, GR32:$src),
|
|
"movd {$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (bitconvert GR32:$src))]>;
|
|
|
|
def MOVDI2SSrm : PDI<0x6E, MRMSrcMem, (ops FR32:$dst, i32mem:$src),
|
|
"movd {$src, $dst|$dst, $src}",
|
|
[(set FR32:$dst, (bitconvert (loadi32 addr:$src)))]>;
|
|
|
|
// SSE2 instructions with XS prefix
|
|
def MOVQI2PQIrm : I<0x7E, MRMSrcMem, (ops VR128:$dst, i64mem:$src),
|
|
"movq {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst,
|
|
(v2i64 (scalar_to_vector (loadi64 addr:$src))))]>, XS,
|
|
Requires<[HasSSE2]>;
|
|
def MOVPQI2QImr : PDI<0xD6, MRMDestMem, (ops i64mem:$dst, VR128:$src),
|
|
"movq {$src, $dst|$dst, $src}",
|
|
[(store (i64 (vector_extract (v2i64 VR128:$src),
|
|
(iPTR 0))), addr:$dst)]>;
|
|
|
|
// FIXME: may not be able to eliminate this movss with coalescing the src and
|
|
// dest register classes are different. We really want to write this pattern
|
|
// like this:
|
|
// def : Pat<(f32 (vector_extract (v4f32 VR128:$src), (iPTR 0))),
|
|
// (f32 FR32:$src)>;
|
|
def MOVPD2SDrr : SDI<0x10, MRMSrcReg, (ops FR64:$dst, VR128:$src),
|
|
"movsd {$src, $dst|$dst, $src}",
|
|
[(set FR64:$dst, (vector_extract (v2f64 VR128:$src),
|
|
(iPTR 0)))]>;
|
|
def MOVPD2SDmr : SDI<0x11, MRMDestMem, (ops f64mem:$dst, VR128:$src),
|
|
"movsd {$src, $dst|$dst, $src}",
|
|
[(store (f64 (vector_extract (v2f64 VR128:$src),
|
|
(iPTR 0))), addr:$dst)]>;
|
|
def MOVPDI2DIrr : PDI<0x7E, MRMDestReg, (ops GR32:$dst, VR128:$src),
|
|
"movd {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (vector_extract (v4i32 VR128:$src),
|
|
(iPTR 0)))]>;
|
|
def MOVPDI2DImr : PDI<0x7E, MRMDestMem, (ops i32mem:$dst, VR128:$src),
|
|
"movd {$src, $dst|$dst, $src}",
|
|
[(store (i32 (vector_extract (v4i32 VR128:$src),
|
|
(iPTR 0))), addr:$dst)]>;
|
|
|
|
def MOVSS2DIrr : PDI<0x7E, MRMDestReg, (ops GR32:$dst, FR32:$src),
|
|
"movd {$src, $dst|$dst, $src}",
|
|
[(set GR32:$dst, (bitconvert FR32:$src))]>;
|
|
def MOVSS2DImr : PDI<0x7E, MRMDestMem, (ops i32mem:$dst, FR32:$src),
|
|
"movd {$src, $dst|$dst, $src}",
|
|
[(store (i32 (bitconvert FR32:$src)), addr:$dst)]>;
|
|
|
|
|
|
// Move to lower bits of a VR128, leaving upper bits alone.
|
|
// Three operand (but two address) aliases.
|
|
let isTwoAddress = 1 in {
|
|
def MOVLSD2PDrr : SDI<0x10, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, FR64:$src2),
|
|
"movsd {$src2, $dst|$dst, $src2}", []>;
|
|
|
|
let AddedComplexity = 15 in
|
|
def MOVLPDrr : SDI<0x10, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"movsd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst,
|
|
(v2f64 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
MOVL_shuffle_mask)))]>;
|
|
}
|
|
|
|
// Store / copy lower 64-bits of a XMM register.
|
|
def MOVLQ128mr : PDI<0xD6, MRMDestMem, (ops i64mem:$dst, VR128:$src),
|
|
"movq {$src, $dst|$dst, $src}",
|
|
[(int_x86_sse2_storel_dq addr:$dst, VR128:$src)]>;
|
|
|
|
// Move to lower bits of a VR128 and zeroing upper bits.
|
|
// Loading from memory automatically zeroing upper bits.
|
|
let AddedComplexity = 20 in
|
|
def MOVZSD2PDrm : SDI<0x10, MRMSrcMem, (ops VR128:$dst, f64mem:$src),
|
|
"movsd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst,
|
|
(v2f64 (vector_shuffle immAllZerosV,
|
|
(v2f64 (scalar_to_vector
|
|
(loadf64 addr:$src))),
|
|
MOVL_shuffle_mask)))]>;
|
|
|
|
let AddedComplexity = 15 in
|
|
// movd / movq to XMM register zero-extends
|
|
def MOVZDI2PDIrr : PDI<0x6E, MRMSrcReg, (ops VR128:$dst, GR32:$src),
|
|
"movd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst,
|
|
(v4i32 (vector_shuffle immAllZerosV,
|
|
(v4i32 (scalar_to_vector GR32:$src)),
|
|
MOVL_shuffle_mask)))]>;
|
|
let AddedComplexity = 20 in
|
|
def MOVZDI2PDIrm : PDI<0x6E, MRMSrcMem, (ops VR128:$dst, i32mem:$src),
|
|
"movd {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst,
|
|
(v4i32 (vector_shuffle immAllZerosV,
|
|
(v4i32 (scalar_to_vector (loadi32 addr:$src))),
|
|
MOVL_shuffle_mask)))]>;
|
|
|
|
// Moving from XMM to XMM but still clear upper 64 bits.
|
|
let AddedComplexity = 15 in
|
|
def MOVZQI2PQIrr : I<0x7E, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"movq {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_movl_dq VR128:$src))]>,
|
|
XS, Requires<[HasSSE2]>;
|
|
let AddedComplexity = 20 in
|
|
def MOVZQI2PQIrm : I<0x7E, MRMSrcMem, (ops VR128:$dst, i64mem:$src),
|
|
"movq {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse2_movl_dq
|
|
(bitconvert (loadv2i64 addr:$src))))]>,
|
|
XS, Requires<[HasSSE2]>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE3 Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// SSE3 Instruction Templates:
|
|
//
|
|
// S3I - SSE3 instructions with TB and OpSize prefixes.
|
|
// S3SI - SSE3 instructions with XS prefix.
|
|
// S3DI - SSE3 instructions with XD prefix.
|
|
|
|
class S3SI<bits<8> o, Format F, dag ops, string asm, list<dag> pattern>
|
|
: I<o, F, ops, asm, pattern>, XS, Requires<[HasSSE3]>;
|
|
class S3DI<bits<8> o, Format F, dag ops, string asm, list<dag> pattern>
|
|
: I<o, F, ops, asm, pattern>, XD, Requires<[HasSSE3]>;
|
|
class S3I<bits<8> o, Format F, dag ops, string asm, list<dag> pattern>
|
|
: I<o, F, ops, asm, pattern>, TB, OpSize, Requires<[HasSSE3]>;
|
|
|
|
// Move Instructions
|
|
def MOVSHDUPrr : S3SI<0x16, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"movshdup {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (v4f32 (vector_shuffle
|
|
VR128:$src, (undef),
|
|
MOVSHDUP_shuffle_mask)))]>;
|
|
def MOVSHDUPrm : S3SI<0x16, MRMSrcMem, (ops VR128:$dst, f128mem:$src),
|
|
"movshdup {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (v4f32 (vector_shuffle
|
|
(loadv4f32 addr:$src), (undef),
|
|
MOVSHDUP_shuffle_mask)))]>;
|
|
|
|
def MOVSLDUPrr : S3SI<0x12, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"movsldup {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (v4f32 (vector_shuffle
|
|
VR128:$src, (undef),
|
|
MOVSLDUP_shuffle_mask)))]>;
|
|
def MOVSLDUPrm : S3SI<0x12, MRMSrcMem, (ops VR128:$dst, f128mem:$src),
|
|
"movsldup {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (v4f32 (vector_shuffle
|
|
(loadv4f32 addr:$src), (undef),
|
|
MOVSLDUP_shuffle_mask)))]>;
|
|
|
|
def MOVDDUPrr : S3DI<0x12, MRMSrcReg, (ops VR128:$dst, VR128:$src),
|
|
"movddup {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (v2f64 (vector_shuffle
|
|
VR128:$src, (undef),
|
|
SSE_splat_lo_mask)))]>;
|
|
def MOVDDUPrm : S3DI<0x12, MRMSrcMem, (ops VR128:$dst, f64mem:$src),
|
|
"movddup {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst,
|
|
(v2f64 (vector_shuffle
|
|
(scalar_to_vector (loadf64 addr:$src)),
|
|
(undef),
|
|
SSE_splat_lo_mask)))]>;
|
|
|
|
// Arithmetic
|
|
let isTwoAddress = 1 in {
|
|
def ADDSUBPSrr : S3DI<0xD0, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"addsubps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (int_x86_sse3_addsub_ps VR128:$src1,
|
|
VR128:$src2))]>;
|
|
def ADDSUBPSrm : S3DI<0xD0, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
"addsubps {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (int_x86_sse3_addsub_ps VR128:$src1,
|
|
(load addr:$src2)))]>;
|
|
def ADDSUBPDrr : S3I<0xD0, MRMSrcReg,
|
|
(ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
"addsubpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (int_x86_sse3_addsub_pd VR128:$src1,
|
|
VR128:$src2))]>;
|
|
def ADDSUBPDrm : S3I<0xD0, MRMSrcMem,
|
|
(ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
"addsubpd {$src2, $dst|$dst, $src2}",
|
|
[(set VR128:$dst, (int_x86_sse3_addsub_pd VR128:$src1,
|
|
(load addr:$src2)))]>;
|
|
}
|
|
|
|
def LDDQUrm : S3DI<0xF0, MRMSrcMem, (ops VR128:$dst, i128mem:$src),
|
|
"lddqu {$src, $dst|$dst, $src}",
|
|
[(set VR128:$dst, (int_x86_sse3_ldu_dq addr:$src))]>;
|
|
|
|
// Horizontal ops
|
|
class S3D_Intrr<bits<8> o, string OpcodeStr, Intrinsic IntId>
|
|
: S3DI<o, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (v4f32 (IntId VR128:$src1, VR128:$src2)))]>;
|
|
class S3D_Intrm<bits<8> o, string OpcodeStr, Intrinsic IntId>
|
|
: S3DI<o, MRMSrcMem, (ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (v4f32 (IntId VR128:$src1, (load addr:$src2))))]>;
|
|
class S3_Intrr<bits<8> o, string OpcodeStr, Intrinsic IntId>
|
|
: S3I<o, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (v2f64 (IntId VR128:$src1, VR128:$src2)))]>;
|
|
class S3_Intrm<bits<8> o, string OpcodeStr, Intrinsic IntId>
|
|
: S3I<o, MRMSrcMem, (ops VR128:$dst, VR128:$src1, f128mem:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (v2f64 (IntId VR128:$src1, (load addr:$src2))))]>;
|
|
|
|
let isTwoAddress = 1 in {
|
|
def HADDPSrr : S3D_Intrr<0x7C, "haddps", int_x86_sse3_hadd_ps>;
|
|
def HADDPSrm : S3D_Intrm<0x7C, "haddps", int_x86_sse3_hadd_ps>;
|
|
def HADDPDrr : S3_Intrr <0x7C, "haddpd", int_x86_sse3_hadd_pd>;
|
|
def HADDPDrm : S3_Intrm <0x7C, "haddpd", int_x86_sse3_hadd_pd>;
|
|
def HSUBPSrr : S3D_Intrr<0x7D, "hsubps", int_x86_sse3_hsub_ps>;
|
|
def HSUBPSrm : S3D_Intrm<0x7D, "hsubps", int_x86_sse3_hsub_ps>;
|
|
def HSUBPDrr : S3_Intrr <0x7D, "hsubpd", int_x86_sse3_hsub_pd>;
|
|
def HSUBPDrm : S3_Intrm <0x7D, "hsubpd", int_x86_sse3_hsub_pd>;
|
|
}
|
|
|
|
// Thread synchronization
|
|
def MONITOR : I<0xC8, RawFrm, (ops), "monitor",
|
|
[(int_x86_sse3_monitor EAX, ECX, EDX)]>,TB, Requires<[HasSSE3]>;
|
|
def MWAIT : I<0xC9, RawFrm, (ops), "mwait",
|
|
[(int_x86_sse3_mwait ECX, EAX)]>, TB, Requires<[HasSSE3]>;
|
|
|
|
// vector_shuffle v1, <undef> <1, 1, 3, 3>
|
|
let AddedComplexity = 15 in
|
|
def : Pat<(v4i32 (vector_shuffle VR128:$src, (undef),
|
|
MOVSHDUP_shuffle_mask)),
|
|
(MOVSHDUPrr VR128:$src)>, Requires<[HasSSE3]>;
|
|
let AddedComplexity = 20 in
|
|
def : Pat<(v4i32 (vector_shuffle (bc_v4i32 (loadv2i64 addr:$src)), (undef),
|
|
MOVSHDUP_shuffle_mask)),
|
|
(MOVSHDUPrm addr:$src)>, Requires<[HasSSE3]>;
|
|
|
|
// vector_shuffle v1, <undef> <0, 0, 2, 2>
|
|
let AddedComplexity = 15 in
|
|
def : Pat<(v4i32 (vector_shuffle VR128:$src, (undef),
|
|
MOVSLDUP_shuffle_mask)),
|
|
(MOVSLDUPrr VR128:$src)>, Requires<[HasSSE3]>;
|
|
let AddedComplexity = 20 in
|
|
def : Pat<(v4i32 (vector_shuffle (bc_v4i32 (loadv2i64 addr:$src)), (undef),
|
|
MOVSLDUP_shuffle_mask)),
|
|
(MOVSLDUPrm addr:$src)>, Requires<[HasSSE3]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSSE3 Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// SSE3 Instruction Templates:
|
|
//
|
|
// SS38I - SSSE3 instructions with T8 and OpSize prefixes.
|
|
// SS3AI - SSSE3 instructions with TA and OpSize prefixes.
|
|
|
|
class SS38I<bits<8> o, Format F, dag ops, string asm, list<dag> pattern>
|
|
: I<o, F, ops, asm, pattern>, T8, OpSize, Requires<[HasSSSE3]>;
|
|
class SS3AI<bits<8> o, Format F, dag ops, string asm, list<dag> pattern>
|
|
: I<o, F, ops, asm, pattern>, TA, OpSize, Requires<[HasSSSE3]>;
|
|
|
|
/// SS3I_binop_rm_int - Simple SSSE3 binary operatr whose type is v2i64.
|
|
let isTwoAddress = 1 in {
|
|
multiclass SS3I_binop_rm_int<bits<8> opc, string OpcodeStr, Intrinsic IntId,
|
|
bit Commutable = 0> {
|
|
def rr : SS38I<opc, MRMSrcReg, (ops VR128:$dst, VR128:$src1, VR128:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst, (IntId VR128:$src1, VR128:$src2))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
def rm : SS38I<opc, MRMSrcMem, (ops VR128:$dst, VR128:$src1, i128mem:$src2),
|
|
!strconcat(OpcodeStr, " {$src2, $dst|$dst, $src2}"),
|
|
[(set VR128:$dst,
|
|
(IntId VR128:$src1,
|
|
(bitconvert (loadv2i64 addr:$src2))))]>;
|
|
}
|
|
}
|
|
|
|
defm PMULHRSW128 : SS3I_binop_rm_int<0x0B, "pmulhrsw",
|
|
int_x86_ssse3_pmulhrsw_128, 1>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Non-Instruction Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// 128-bit vector undef's.
|
|
def : Pat<(v2f64 (undef)), (IMPLICIT_DEF_VR128)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v16i8 (undef)), (IMPLICIT_DEF_VR128)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v8i16 (undef)), (IMPLICIT_DEF_VR128)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v4i32 (undef)), (IMPLICIT_DEF_VR128)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v2i64 (undef)), (IMPLICIT_DEF_VR128)>, Requires<[HasSSE2]>;
|
|
|
|
// 128-bit vector all zero's.
|
|
def : Pat<(v16i8 immAllZerosV), (V_SET0)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v8i16 immAllZerosV), (V_SET0)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v4i32 immAllZerosV), (V_SET0)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v2i64 immAllZerosV), (V_SET0)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v2f64 immAllZerosV), (V_SET0)>, Requires<[HasSSE2]>;
|
|
|
|
// 128-bit vector all one's.
|
|
def : Pat<(v16i8 immAllOnesV), (V_SETALLONES)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v8i16 immAllOnesV), (V_SETALLONES)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v4i32 immAllOnesV), (V_SETALLONES)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v2i64 immAllOnesV), (V_SETALLONES)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v4f32 immAllOnesV), (V_SETALLONES)>, Requires<[HasSSE1]>;
|
|
|
|
// Store 128-bit integer vector values.
|
|
def : Pat<(store (v16i8 VR128:$src), addr:$dst),
|
|
(MOVDQAmr addr:$dst, VR128:$src)>, Requires<[HasSSE2]>;
|
|
def : Pat<(store (v8i16 VR128:$src), addr:$dst),
|
|
(MOVDQAmr addr:$dst, VR128:$src)>, Requires<[HasSSE2]>;
|
|
def : Pat<(store (v4i32 VR128:$src), addr:$dst),
|
|
(MOVDQAmr addr:$dst, VR128:$src)>, Requires<[HasSSE2]>;
|
|
|
|
// Scalar to v8i16 / v16i8. The source may be a GR32, but only the lower 8 or
|
|
// 16-bits matter.
|
|
def : Pat<(v8i16 (X86s2vec GR32:$src)), (MOVDI2PDIrr GR32:$src)>,
|
|
Requires<[HasSSE2]>;
|
|
def : Pat<(v16i8 (X86s2vec GR32:$src)), (MOVDI2PDIrr GR32:$src)>,
|
|
Requires<[HasSSE2]>;
|
|
|
|
// bit_convert
|
|
let Predicates = [HasSSE2] in {
|
|
def : Pat<(v2i64 (bitconvert (v4i32 VR128:$src))), (v2i64 VR128:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v8i16 VR128:$src))), (v2i64 VR128:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v16i8 VR128:$src))), (v2i64 VR128:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v2f64 VR128:$src))), (v2i64 VR128:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v4f32 VR128:$src))), (v2i64 VR128:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v2i64 VR128:$src))), (v4i32 VR128:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v8i16 VR128:$src))), (v4i32 VR128:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v16i8 VR128:$src))), (v4i32 VR128:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v2f64 VR128:$src))), (v4i32 VR128:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v4f32 VR128:$src))), (v4i32 VR128:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v2i64 VR128:$src))), (v8i16 VR128:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v4i32 VR128:$src))), (v8i16 VR128:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v16i8 VR128:$src))), (v8i16 VR128:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v2f64 VR128:$src))), (v8i16 VR128:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v4f32 VR128:$src))), (v8i16 VR128:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v2i64 VR128:$src))), (v16i8 VR128:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v4i32 VR128:$src))), (v16i8 VR128:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v8i16 VR128:$src))), (v16i8 VR128:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v2f64 VR128:$src))), (v16i8 VR128:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v4f32 VR128:$src))), (v16i8 VR128:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v2i64 VR128:$src))), (v4f32 VR128:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v4i32 VR128:$src))), (v4f32 VR128:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v8i16 VR128:$src))), (v4f32 VR128:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v16i8 VR128:$src))), (v4f32 VR128:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v2f64 VR128:$src))), (v4f32 VR128:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v2i64 VR128:$src))), (v2f64 VR128:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v4i32 VR128:$src))), (v2f64 VR128:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v8i16 VR128:$src))), (v2f64 VR128:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v16i8 VR128:$src))), (v2f64 VR128:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v4f32 VR128:$src))), (v2f64 VR128:$src)>;
|
|
}
|
|
|
|
// Move scalar to XMM zero-extended
|
|
// movd to XMM register zero-extends
|
|
let AddedComplexity = 15 in {
|
|
def : Pat<(v8i16 (vector_shuffle immAllZerosV,
|
|
(v8i16 (X86s2vec GR32:$src)), MOVL_shuffle_mask)),
|
|
(MOVZDI2PDIrr GR32:$src)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v16i8 (vector_shuffle immAllZerosV,
|
|
(v16i8 (X86s2vec GR32:$src)), MOVL_shuffle_mask)),
|
|
(MOVZDI2PDIrr GR32:$src)>, Requires<[HasSSE2]>;
|
|
// Zeroing a VR128 then do a MOVS{S|D} to the lower bits.
|
|
def : Pat<(v2f64 (vector_shuffle immAllZerosV,
|
|
(v2f64 (scalar_to_vector FR64:$src)), MOVL_shuffle_mask)),
|
|
(MOVLSD2PDrr (V_SET0), FR64:$src)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v4f32 (vector_shuffle immAllZerosV,
|
|
(v4f32 (scalar_to_vector FR32:$src)), MOVL_shuffle_mask)),
|
|
(MOVLSS2PSrr (V_SET0), FR32:$src)>, Requires<[HasSSE2]>;
|
|
}
|
|
|
|
// Splat v2f64 / v2i64
|
|
let AddedComplexity = 10 in {
|
|
def : Pat<(vector_shuffle (v2f64 VR128:$src), (undef), SSE_splat_lo_mask:$sm),
|
|
(UNPCKLPDrr VR128:$src, VR128:$src)>, Requires<[HasSSE2]>;
|
|
def : Pat<(vector_shuffle (v2f64 VR128:$src), (undef), UNPCKH_shuffle_mask:$sm),
|
|
(UNPCKHPDrr VR128:$src, VR128:$src)>, Requires<[HasSSE2]>;
|
|
def : Pat<(vector_shuffle (v2i64 VR128:$src), (undef), SSE_splat_lo_mask:$sm),
|
|
(PUNPCKLQDQrr VR128:$src, VR128:$src)>, Requires<[HasSSE2]>;
|
|
def : Pat<(vector_shuffle (v2i64 VR128:$src), (undef), UNPCKH_shuffle_mask:$sm),
|
|
(PUNPCKHQDQrr VR128:$src, VR128:$src)>, Requires<[HasSSE2]>;
|
|
}
|
|
|
|
// Splat v4f32
|
|
def : Pat<(vector_shuffle (v4f32 VR128:$src), (undef), SSE_splat_mask:$sm),
|
|
(SHUFPSrri VR128:$src, VR128:$src, SSE_splat_mask:$sm)>,
|
|
Requires<[HasSSE1]>;
|
|
|
|
// Special unary SHUFPSrri case.
|
|
// FIXME: when we want non two-address code, then we should use PSHUFD?
|
|
def : Pat<(vector_shuffle (v4f32 VR128:$src1), (undef),
|
|
SHUFP_unary_shuffle_mask:$sm),
|
|
(SHUFPSrri VR128:$src1, VR128:$src1, SHUFP_unary_shuffle_mask:$sm)>,
|
|
Requires<[HasSSE1]>;
|
|
// Unary v4f32 shuffle with PSHUF* in order to fold a load.
|
|
def : Pat<(vector_shuffle (loadv4f32 addr:$src1), (undef),
|
|
SHUFP_unary_shuffle_mask:$sm),
|
|
(PSHUFDmi addr:$src1, SHUFP_unary_shuffle_mask:$sm)>,
|
|
Requires<[HasSSE2]>;
|
|
// Special binary v4i32 shuffle cases with SHUFPS.
|
|
def : Pat<(vector_shuffle (v4i32 VR128:$src1), (v4i32 VR128:$src2),
|
|
PSHUFD_binary_shuffle_mask:$sm),
|
|
(SHUFPSrri VR128:$src1, VR128:$src2, PSHUFD_binary_shuffle_mask:$sm)>,
|
|
Requires<[HasSSE2]>;
|
|
def : Pat<(vector_shuffle (v4i32 VR128:$src1),
|
|
(bc_v4i32 (loadv2i64 addr:$src2)), PSHUFD_binary_shuffle_mask:$sm),
|
|
(SHUFPSrmi VR128:$src1, addr:$src2, PSHUFD_binary_shuffle_mask:$sm)>,
|
|
Requires<[HasSSE2]>;
|
|
|
|
// vector_shuffle v1, <undef>, <0, 0, 1, 1, ...>
|
|
let AddedComplexity = 10 in {
|
|
def : Pat<(v4f32 (vector_shuffle VR128:$src, (undef),
|
|
UNPCKL_v_undef_shuffle_mask)),
|
|
(UNPCKLPSrr VR128:$src, VR128:$src)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v16i8 (vector_shuffle VR128:$src, (undef),
|
|
UNPCKL_v_undef_shuffle_mask)),
|
|
(PUNPCKLBWrr VR128:$src, VR128:$src)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v8i16 (vector_shuffle VR128:$src, (undef),
|
|
UNPCKL_v_undef_shuffle_mask)),
|
|
(PUNPCKLWDrr VR128:$src, VR128:$src)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v4i32 (vector_shuffle VR128:$src, (undef),
|
|
UNPCKL_v_undef_shuffle_mask)),
|
|
(PUNPCKLDQrr VR128:$src, VR128:$src)>, Requires<[HasSSE1]>;
|
|
}
|
|
|
|
let AddedComplexity = 15 in {
|
|
// vector_shuffle v1, v2 <0, 1, 4, 5> using MOVLHPS
|
|
def : Pat<(v4i32 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
MOVHP_shuffle_mask)),
|
|
(MOVLHPSrr VR128:$src1, VR128:$src2)>;
|
|
|
|
// vector_shuffle v1, v2 <6, 7, 2, 3> using MOVHLPS
|
|
def : Pat<(v4i32 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
MOVHLPS_shuffle_mask)),
|
|
(MOVHLPSrr VR128:$src1, VR128:$src2)>;
|
|
|
|
// vector_shuffle v1, undef <2, ?, ?, ?> using MOVHLPS
|
|
def : Pat<(v4f32 (vector_shuffle VR128:$src1, (undef),
|
|
MOVHLPS_v_undef_shuffle_mask)),
|
|
(MOVHLPSrr VR128:$src1, VR128:$src1)>;
|
|
def : Pat<(v4i32 (vector_shuffle VR128:$src1, (undef),
|
|
MOVHLPS_v_undef_shuffle_mask)),
|
|
(MOVHLPSrr VR128:$src1, VR128:$src1)>;
|
|
}
|
|
|
|
let AddedComplexity = 20 in {
|
|
// vector_shuffle v1, (load v2) <4, 5, 2, 3> using MOVLPS
|
|
// vector_shuffle v1, (load v2) <0, 1, 4, 5> using MOVHPS
|
|
def : Pat<(v4f32 (vector_shuffle VR128:$src1, (loadv4f32 addr:$src2),
|
|
MOVLP_shuffle_mask)),
|
|
(MOVLPSrm VR128:$src1, addr:$src2)>, Requires<[HasSSE1]>;
|
|
def : Pat<(v2f64 (vector_shuffle VR128:$src1, (loadv2f64 addr:$src2),
|
|
MOVLP_shuffle_mask)),
|
|
(MOVLPDrm VR128:$src1, addr:$src2)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v4f32 (vector_shuffle VR128:$src1, (loadv4f32 addr:$src2),
|
|
MOVHP_shuffle_mask)),
|
|
(MOVHPSrm VR128:$src1, addr:$src2)>, Requires<[HasSSE1]>;
|
|
def : Pat<(v2f64 (vector_shuffle VR128:$src1, (loadv2f64 addr:$src2),
|
|
MOVHP_shuffle_mask)),
|
|
(MOVHPDrm VR128:$src1, addr:$src2)>, Requires<[HasSSE2]>;
|
|
|
|
def : Pat<(v4i32 (vector_shuffle VR128:$src1, (bc_v4i32 (loadv2i64 addr:$src2)),
|
|
MOVLP_shuffle_mask)),
|
|
(MOVLPSrm VR128:$src1, addr:$src2)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v2i64 (vector_shuffle VR128:$src1, (loadv2i64 addr:$src2),
|
|
MOVLP_shuffle_mask)),
|
|
(MOVLPDrm VR128:$src1, addr:$src2)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v4i32 (vector_shuffle VR128:$src1, (bc_v4i32 (loadv2i64 addr:$src2)),
|
|
MOVHP_shuffle_mask)),
|
|
(MOVHPSrm VR128:$src1, addr:$src2)>, Requires<[HasSSE1]>;
|
|
def : Pat<(v2i64 (vector_shuffle VR128:$src1, (loadv2i64 addr:$src2),
|
|
MOVLP_shuffle_mask)),
|
|
(MOVLPDrm VR128:$src1, addr:$src2)>, Requires<[HasSSE2]>;
|
|
}
|
|
|
|
let AddedComplexity = 15 in {
|
|
// Setting the lowest element in the vector.
|
|
def : Pat<(v4i32 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
MOVL_shuffle_mask)),
|
|
(MOVLPSrr VR128:$src1, VR128:$src2)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v2i64 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
MOVL_shuffle_mask)),
|
|
(MOVLPDrr VR128:$src1, VR128:$src2)>, Requires<[HasSSE2]>;
|
|
|
|
// vector_shuffle v1, v2 <4, 5, 2, 3> using MOVLPDrr (movsd)
|
|
def : Pat<(v4f32 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
MOVLP_shuffle_mask)),
|
|
(MOVLPDrr VR128:$src1, VR128:$src2)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v4i32 (vector_shuffle VR128:$src1, VR128:$src2,
|
|
MOVLP_shuffle_mask)),
|
|
(MOVLPDrr VR128:$src1, VR128:$src2)>, Requires<[HasSSE2]>;
|
|
}
|
|
|
|
// Set lowest element and zero upper elements.
|
|
let AddedComplexity = 20 in
|
|
def : Pat<(bc_v2i64 (vector_shuffle immAllZerosV,
|
|
(v2f64 (scalar_to_vector (loadf64 addr:$src))),
|
|
MOVL_shuffle_mask)),
|
|
(MOVZQI2PQIrm addr:$src)>, Requires<[HasSSE2]>;
|
|
|
|
// FIXME: Temporary workaround since 2-wide shuffle is broken.
|
|
def : Pat<(int_x86_sse2_movs_d VR128:$src1, VR128:$src2),
|
|
(v2f64 (MOVLPDrr VR128:$src1, VR128:$src2))>, Requires<[HasSSE2]>;
|
|
def : Pat<(int_x86_sse2_loadh_pd VR128:$src1, addr:$src2),
|
|
(v2f64 (MOVHPDrm VR128:$src1, addr:$src2))>, Requires<[HasSSE2]>;
|
|
def : Pat<(int_x86_sse2_loadl_pd VR128:$src1, addr:$src2),
|
|
(v2f64 (MOVLPDrm VR128:$src1, addr:$src2))>, Requires<[HasSSE2]>;
|
|
def : Pat<(int_x86_sse2_shuf_pd VR128:$src1, VR128:$src2, imm:$src3),
|
|
(v2f64 (SHUFPDrri VR128:$src1, VR128:$src2, imm:$src3))>,
|
|
Requires<[HasSSE2]>;
|
|
def : Pat<(int_x86_sse2_shuf_pd VR128:$src1, (load addr:$src2), imm:$src3),
|
|
(v2f64 (SHUFPDrmi VR128:$src1, addr:$src2, imm:$src3))>,
|
|
Requires<[HasSSE2]>;
|
|
def : Pat<(int_x86_sse2_unpckh_pd VR128:$src1, VR128:$src2),
|
|
(v2f64 (UNPCKHPDrr VR128:$src1, VR128:$src2))>, Requires<[HasSSE2]>;
|
|
def : Pat<(int_x86_sse2_unpckh_pd VR128:$src1, (load addr:$src2)),
|
|
(v2f64 (UNPCKHPDrm VR128:$src1, addr:$src2))>, Requires<[HasSSE2]>;
|
|
def : Pat<(int_x86_sse2_unpckl_pd VR128:$src1, VR128:$src2),
|
|
(v2f64 (UNPCKLPDrr VR128:$src1, VR128:$src2))>, Requires<[HasSSE2]>;
|
|
def : Pat<(int_x86_sse2_unpckl_pd VR128:$src1, (load addr:$src2)),
|
|
(v2f64 (UNPCKLPDrm VR128:$src1, addr:$src2))>, Requires<[HasSSE2]>;
|
|
def : Pat<(int_x86_sse2_punpckh_qdq VR128:$src1, VR128:$src2),
|
|
(v2i64 (PUNPCKHQDQrr VR128:$src1, VR128:$src2))>, Requires<[HasSSE2]>;
|
|
def : Pat<(int_x86_sse2_punpckh_qdq VR128:$src1, (load addr:$src2)),
|
|
(v2i64 (PUNPCKHQDQrm VR128:$src1, addr:$src2))>, Requires<[HasSSE2]>;
|
|
def : Pat<(int_x86_sse2_punpckl_qdq VR128:$src1, VR128:$src2),
|
|
(v2i64 (PUNPCKLQDQrr VR128:$src1, VR128:$src2))>, Requires<[HasSSE2]>;
|
|
def : Pat<(int_x86_sse2_punpckl_qdq VR128:$src1, (load addr:$src2)),
|
|
(PUNPCKLQDQrm VR128:$src1, addr:$src2)>, Requires<[HasSSE2]>;
|
|
|
|
// Some special case pandn patterns.
|
|
def : Pat<(v2i64 (and (xor VR128:$src1, (bc_v2i64 (v4i32 immAllOnesV))),
|
|
VR128:$src2)),
|
|
(PANDNrr VR128:$src1, VR128:$src2)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v2i64 (and (xor VR128:$src1, (bc_v2i64 (v8i16 immAllOnesV))),
|
|
VR128:$src2)),
|
|
(PANDNrr VR128:$src1, VR128:$src2)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v2i64 (and (xor VR128:$src1, (bc_v2i64 (v16i8 immAllOnesV))),
|
|
VR128:$src2)),
|
|
(PANDNrr VR128:$src1, VR128:$src2)>, Requires<[HasSSE2]>;
|
|
|
|
def : Pat<(v2i64 (and (xor VR128:$src1, (bc_v2i64 (v4i32 immAllOnesV))),
|
|
(load addr:$src2))),
|
|
(PANDNrm VR128:$src1, addr:$src2)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v2i64 (and (xor VR128:$src1, (bc_v2i64 (v8i16 immAllOnesV))),
|
|
(load addr:$src2))),
|
|
(PANDNrm VR128:$src1, addr:$src2)>, Requires<[HasSSE2]>;
|
|
def : Pat<(v2i64 (and (xor VR128:$src1, (bc_v2i64 (v16i8 immAllOnesV))),
|
|
(load addr:$src2))),
|
|
(PANDNrm VR128:$src1, addr:$src2)>, Requires<[HasSSE2]>;
|
|
|
|
// Unaligned load
|
|
def : Pat<(v4f32 (X86loadu addr:$src)), (MOVUPSrm addr:$src)>,
|
|
Requires<[HasSSE1]>;
|