llvm-project/llvm/lib/Target/X86/X86InstrFMA.td

449 lines
23 KiB
TableGen

//====- X86InstrFMA.td - Describe the X86 Instruction Set --*- tablegen -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file describes FMA (Fused Multiply-Add) instructions.
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// FMA3 - Intel 3 operand Fused Multiply-Add instructions
//===----------------------------------------------------------------------===//
multiclass fma_rm<bits<8> opc, string OpcodeStr> {
def r : FMA3<opc, MRMSrcReg, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
[]>;
def m : FMA3<opc, MRMSrcMem, (outs VR128:$dst),
(ins VR128:$src1, f128mem:$src2),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
[]>;
def rY : FMA3<opc, MRMSrcReg, (outs VR256:$dst),
(ins VR256:$src1, VR256:$src2),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
[]>;
def mY : FMA3<opc, MRMSrcMem, (outs VR256:$dst),
(ins VR256:$src1, f256mem:$src2),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
[]>;
}
multiclass fma_forms<bits<8> opc132, bits<8> opc213, bits<8> opc231,
string OpcodeStr, string PackTy> {
defm r132 : fma_rm<opc132, !strconcat(OpcodeStr, !strconcat("132", PackTy))>;
defm r213 : fma_rm<opc213, !strconcat(OpcodeStr, !strconcat("213", PackTy))>;
defm r231 : fma_rm<opc231, !strconcat(OpcodeStr, !strconcat("231", PackTy))>;
}
let isAsmParserOnly = 1 in {
// Fused Multiply-Add
defm VFMADDPS : fma_forms<0x98, 0xA8, 0xB8, "vfmadd", "ps">;
defm VFMADDPD : fma_forms<0x98, 0xA8, 0xB8, "vfmadd", "pd">, VEX_W;
defm VFMADDSUBPS : fma_forms<0x96, 0xA6, 0xB6, "vfmaddsub", "ps">;
defm VFMADDSUBPD : fma_forms<0x96, 0xA6, 0xB6, "vfmaddsub", "pd">, VEX_W;
defm VFMSUBADDPS : fma_forms<0x97, 0xA7, 0xB7, "vfmsubadd", "ps">;
defm VFMSUBADDPD : fma_forms<0x97, 0xA7, 0xB7, "vfmsubadd", "pd">, VEX_W;
defm VFMSUBPS : fma_forms<0x9A, 0xAA, 0xBA, "vfmsub", "ps">;
defm VFMSUBPD : fma_forms<0x9A, 0xAA, 0xBA, "vfmsub", "pd">, VEX_W;
// Fused Negative Multiply-Add
defm VFNMADDPS : fma_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "ps">;
defm VFNMADDPD : fma_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "pd">, VEX_W;
defm VFNMSUBPS : fma_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "ps">;
defm VFNMSUBPD : fma_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "pd">, VEX_W;
}
//===----------------------------------------------------------------------===//
// FMA4 - AMD 4 operand Fused Multiply-Add instructions
//===----------------------------------------------------------------------===//
multiclass fma4s<bits<8> opc, string OpcodeStr> {
def rr : FMA4<opc, MRMSrcReg, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2, VR128:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>, XOP_W;
def rm : FMA4<opc, MRMSrcMem, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2, f128mem:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>, XOP_W;
def mr : FMA4<opc, MRMSrcMem, (outs VR128:$dst),
(ins VR128:$src1, f128mem:$src2, VR128:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>;
}
multiclass fma4p<bits<8> opc, string OpcodeStr> {
def rr : FMA4<opc, MRMSrcReg, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2, VR128:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>, XOP_W;
def rm : FMA4<opc, MRMSrcMem, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2, f128mem:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>, XOP_W;
def mr : FMA4<opc, MRMSrcMem, (outs VR128:$dst),
(ins VR128:$src1, f128mem:$src2, VR128:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>;
def rrY : FMA4<opc, MRMSrcReg, (outs VR256:$dst),
(ins VR256:$src1, VR256:$src2, VR256:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>, XOP_W;
def rmY : FMA4<opc, MRMSrcMem, (outs VR256:$dst),
(ins VR256:$src1, VR256:$src2, f256mem:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>, XOP_W;
def mrY : FMA4<opc, MRMSrcMem, (outs VR256:$dst),
(ins VR256:$src1, f256mem:$src2, VR256:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>;
}
let isAsmParserOnly = 1 in {
defm VFMADDSS4 : fma4s<0x6A, "vfmaddss">;
defm VFMADDSD4 : fma4s<0x6B, "vfmaddsd">;
defm VFMADDPS4 : fma4p<0x68, "vfmaddps">;
defm VFMADDPD4 : fma4p<0x69, "vfmaddpd">;
defm VFMSUBSS4 : fma4s<0x6E, "vfmsubss">;
defm VFMSUBSD4 : fma4s<0x6F, "vfmsubsd">;
defm VFMSUBPS4 : fma4p<0x6C, "vfmsubps">;
defm VFMSUBPD4 : fma4p<0x6D, "vfmsubpd">;
defm VFNMADDSS4 : fma4s<0x7A, "vfnmaddss">;
defm VFNMADDSD4 : fma4s<0x7B, "vfnmaddsd">;
defm VFNMADDPS4 : fma4p<0x78, "vfnmaddps">;
defm VFNMADDPD4 : fma4p<0x79, "vfnmaddpd">;
defm VFNMSUBSS4 : fma4s<0x7E, "vfnmsubss">;
defm VFNMSUBSD4 : fma4s<0x7F, "vfnmsubsd">;
defm VFNMSUBPS4 : fma4p<0x7C, "vfnmsubps">;
defm VFNMSUBPD4 : fma4p<0x7D, "vfnmsubpd">;
defm VFMADDSUBPS4 : fma4p<0x5C, "vfmaddsubps">;
defm VFMADDSUBPD4 : fma4p<0x5D, "vfmaddsubpd">;
defm VFMSUBADDPS4 : fma4p<0x5E, "vfmsubaddps">;
defm VFMSUBADDPD4 : fma4p<0x5F, "vfmsubaddpd">;
}
// FMA4 Intrinsics patterns
// VFMADD
def : Pat<(int_x86_fma4_vfmadd_ss VR128:$src1, VR128:$src2, VR128:$src3),
(VFMADDSS4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_ss VR128:$src1, VR128:$src2,
(alignedloadv4f32 addr:$src3)),
(VFMADDSS4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_ss VR128:$src1, (alignedloadv4f32 addr:$src2),
VR128:$src3),
(VFMADDSS4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_sd VR128:$src1, VR128:$src2, VR128:$src3),
(VFMADDSD4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_sd VR128:$src1, VR128:$src2,
(alignedloadv2f64 addr:$src3)),
(VFMADDSD4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_sd VR128:$src1, (alignedloadv2f64 addr:$src2),
VR128:$src3),
(VFMADDSD4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_ps VR128:$src1, VR128:$src2, VR128:$src3),
(VFMADDPS4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_ps VR128:$src1, VR128:$src2,
(alignedloadv4f32 addr:$src3)),
(VFMADDPS4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_ps VR128:$src1, (alignedloadv4f32 addr:$src2),
VR128:$src3),
(VFMADDPS4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_pd VR128:$src1, VR128:$src2, VR128:$src3),
(VFMADDPD4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_pd VR128:$src1, VR128:$src2,
(alignedloadv2f64 addr:$src3)),
(VFMADDPD4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_pd VR128:$src1, (alignedloadv2f64 addr:$src2),
VR128:$src3),
(VFMADDPD4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_ps_256 VR256:$src1, VR256:$src2, VR256:$src3),
(VFMADDPS4rrY VR256:$src1, VR256:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_ps_256 VR256:$src1, VR256:$src2,
(alignedloadv8f32 addr:$src3)),
(VFMADDPS4rmY VR256:$src1, VR256:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_ps_256 VR256:$src1,
(alignedloadv8f32 addr:$src2),
VR256:$src3),
(VFMADDPS4mrY VR256:$src1, addr:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_pd_256 VR256:$src1, VR256:$src2, VR256:$src3),
(VFMADDPD4rrY VR256:$src1, VR256:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_pd_256 VR256:$src1, VR256:$src2,
(alignedloadv4f64 addr:$src3)),
(VFMADDPD4rmY VR256:$src1, VR256:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_pd_256 VR256:$src1,
(alignedloadv4f64 addr:$src2),
VR256:$src3),
(VFMADDPD4mrY VR256:$src1, addr:$src2, VR256:$src3)>;
// VFMSUB
def : Pat<(int_x86_fma4_vfmsub_ss VR128:$src1, VR128:$src2, VR128:$src3),
(VFMSUBSS4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_ss VR128:$src1, VR128:$src2,
(alignedloadv4f32 addr:$src3)),
(VFMSUBSS4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_ss VR128:$src1, (alignedloadv4f32 addr:$src2),
VR128:$src3),
(VFMSUBSS4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_sd VR128:$src1, VR128:$src2, VR128:$src3),
(VFMSUBSD4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_sd VR128:$src1, VR128:$src2,
(alignedloadv2f64 addr:$src3)),
(VFMSUBSD4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_sd VR128:$src1, (alignedloadv2f64 addr:$src2),
VR128:$src3),
(VFMSUBSD4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_ps VR128:$src1, VR128:$src2, VR128:$src3),
(VFMSUBPS4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_ps VR128:$src1, VR128:$src2,
(alignedloadv4f32 addr:$src3)),
(VFMSUBPS4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_ps VR128:$src1, (alignedloadv4f32 addr:$src2),
VR128:$src3),
(VFMSUBPS4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_pd VR128:$src1, VR128:$src2, VR128:$src3),
(VFMSUBPD4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_pd VR128:$src1, VR128:$src2,
(alignedloadv2f64 addr:$src3)),
(VFMSUBPD4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_pd VR128:$src1, (alignedloadv2f64 addr:$src2),
VR128:$src3),
(VFMSUBPD4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_ps_256 VR256:$src1, VR256:$src2, VR256:$src3),
(VFMSUBPS4rrY VR256:$src1, VR256:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_ps_256 VR256:$src1, VR256:$src2,
(alignedloadv8f32 addr:$src3)),
(VFMSUBPS4rmY VR256:$src1, VR256:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_ps_256 VR256:$src1,
(alignedloadv8f32 addr:$src2),
VR256:$src3),
(VFMSUBPS4mrY VR256:$src1, addr:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_pd_256 VR256:$src1, VR256:$src2, VR256:$src3),
(VFMSUBPD4rrY VR256:$src1, VR256:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_pd_256 VR256:$src1, VR256:$src2,
(alignedloadv4f64 addr:$src3)),
(VFMSUBPD4rmY VR256:$src1, VR256:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_pd_256 VR256:$src1,
(alignedloadv4f64 addr:$src2),
VR256:$src3),
(VFMSUBPD4mrY VR256:$src1, addr:$src2, VR256:$src3)>;
// VFNMADD
def : Pat<(int_x86_fma4_vfnmadd_ss VR128:$src1, VR128:$src2, VR128:$src3),
(VFNMADDSS4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_ss VR128:$src1, VR128:$src2,
(alignedloadv4f32 addr:$src3)),
(VFNMADDSS4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_ss VR128:$src1, (alignedloadv4f32 addr:$src2),
VR128:$src3),
(VFNMADDSS4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_sd VR128:$src1, VR128:$src2, VR128:$src3),
(VFNMADDSD4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_sd VR128:$src1, VR128:$src2,
(alignedloadv2f64 addr:$src3)),
(VFNMADDSD4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_sd VR128:$src1, (alignedloadv2f64 addr:$src2),
VR128:$src3),
(VFNMADDSD4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_ps VR128:$src1, VR128:$src2, VR128:$src3),
(VFNMADDPS4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_ps VR128:$src1, VR128:$src2,
(alignedloadv4f32 addr:$src3)),
(VFNMADDPS4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_ps VR128:$src1, (alignedloadv4f32 addr:$src2),
VR128:$src3),
(VFNMADDPS4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_pd VR128:$src1, VR128:$src2, VR128:$src3),
(VFNMADDPD4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_pd VR128:$src1, VR128:$src2,
(alignedloadv2f64 addr:$src3)),
(VFNMADDPD4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_pd VR128:$src1, (alignedloadv2f64 addr:$src2),
VR128:$src3),
(VFNMADDPD4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_ps_256 VR256:$src1, VR256:$src2, VR256:$src3),
(VFNMADDPS4rrY VR256:$src1, VR256:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_ps_256 VR256:$src1, VR256:$src2,
(alignedloadv8f32 addr:$src3)),
(VFNMADDPS4rmY VR256:$src1, VR256:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_ps_256 VR256:$src1,
(alignedloadv8f32 addr:$src2),
VR256:$src3),
(VFNMADDPS4mrY VR256:$src1, addr:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_pd_256 VR256:$src1, VR256:$src2, VR256:$src3),
(VFNMADDPD4rrY VR256:$src1, VR256:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_pd_256 VR256:$src1, VR256:$src2,
(alignedloadv4f64 addr:$src3)),
(VFNMADDPD4rmY VR256:$src1, VR256:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_pd_256 VR256:$src1,
(alignedloadv4f64 addr:$src2),
VR256:$src3),
(VFNMADDPD4mrY VR256:$src1, addr:$src2, VR256:$src3)>;
// VFNMSUB
def : Pat<(int_x86_fma4_vfnmsub_ss VR128:$src1, VR128:$src2, VR128:$src3),
(VFNMSUBSS4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_ss VR128:$src1, VR128:$src2,
(alignedloadv4f32 addr:$src3)),
(VFNMSUBSS4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_ss VR128:$src1, (alignedloadv4f32 addr:$src2),
VR128:$src3),
(VFNMSUBSS4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_sd VR128:$src1, VR128:$src2, VR128:$src3),
(VFNMSUBSD4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_sd VR128:$src1, VR128:$src2,
(alignedloadv2f64 addr:$src3)),
(VFNMSUBSD4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_sd VR128:$src1, (alignedloadv2f64 addr:$src2),
VR128:$src3),
(VFNMSUBSD4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_ps VR128:$src1, VR128:$src2, VR128:$src3),
(VFNMSUBPS4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_ps VR128:$src1, VR128:$src2,
(alignedloadv4f32 addr:$src3)),
(VFNMSUBPS4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_ps VR128:$src1, (alignedloadv4f32 addr:$src2),
VR128:$src3),
(VFNMSUBPS4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_pd VR128:$src1, VR128:$src2, VR128:$src3),
(VFNMSUBPD4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_pd VR128:$src1, VR128:$src2,
(alignedloadv2f64 addr:$src3)),
(VFNMSUBPD4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_pd VR128:$src1, (alignedloadv2f64 addr:$src2),
VR128:$src3),
(VFNMSUBPD4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_ps_256 VR256:$src1, VR256:$src2, VR256:$src3),
(VFNMSUBPS4rrY VR256:$src1, VR256:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_ps_256 VR256:$src1, VR256:$src2,
(alignedloadv8f32 addr:$src3)),
(VFNMSUBPS4rmY VR256:$src1, VR256:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_ps_256 VR256:$src1,
(alignedloadv8f32 addr:$src2),
VR256:$src3),
(VFNMSUBPS4mrY VR256:$src1, addr:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_pd_256 VR256:$src1, VR256:$src2, VR256:$src3),
(VFNMSUBPD4rrY VR256:$src1, VR256:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_pd_256 VR256:$src1, VR256:$src2,
(alignedloadv4f64 addr:$src3)),
(VFNMSUBPD4rmY VR256:$src1, VR256:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_pd_256 VR256:$src1,
(alignedloadv4f64 addr:$src2),
VR256:$src3),
(VFNMSUBPD4mrY VR256:$src1, addr:$src2, VR256:$src3)>;
// VFMADDSUB
def : Pat<(int_x86_fma4_vfmaddsub_ps VR128:$src1, VR128:$src2, VR128:$src3),
(VFMADDSUBPS4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmaddsub_ps VR128:$src1, VR128:$src2,
(alignedloadv4f32 addr:$src3)),
(VFMADDSUBPS4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmaddsub_ps VR128:$src1, (alignedloadv4f32 addr:$src2),
VR128:$src3),
(VFMADDSUBPS4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmaddsub_pd VR128:$src1, VR128:$src2, VR128:$src3),
(VFMADDSUBPD4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmaddsub_pd VR128:$src1, VR128:$src2,
(alignedloadv2f64 addr:$src3)),
(VFMADDSUBPD4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmaddsub_pd VR128:$src1, (alignedloadv2f64 addr:$src2),
VR128:$src3),
(VFMADDSUBPD4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmaddsub_ps_256 VR256:$src1, VR256:$src2, VR256:$src3),
(VFMADDSUBPS4rrY VR256:$src1, VR256:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfmaddsub_ps_256 VR256:$src1, VR256:$src2,
(alignedloadv8f32 addr:$src3)),
(VFMADDSUBPS4rmY VR256:$src1, VR256:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmaddsub_ps_256 VR256:$src1,
(alignedloadv8f32 addr:$src2),
VR256:$src3),
(VFMADDSUBPS4mrY VR256:$src1, addr:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfmaddsub_pd_256 VR256:$src1, VR256:$src2, VR256:$src3),
(VFMADDSUBPD4rrY VR256:$src1, VR256:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfmaddsub_pd_256 VR256:$src1, VR256:$src2,
(alignedloadv4f64 addr:$src3)),
(VFMADDSUBPD4rmY VR256:$src1, VR256:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmaddsub_pd_256 VR256:$src1,
(alignedloadv4f64 addr:$src2),
VR256:$src3),
(VFMADDSUBPD4mrY VR256:$src1, addr:$src2, VR256:$src3)>;
// VFMSUBADD
def : Pat<(int_x86_fma4_vfmsubadd_ps VR128:$src1, VR128:$src2, VR128:$src3),
(VFMSUBADDPS4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmsubadd_ps VR128:$src1, VR128:$src2,
(alignedloadv4f32 addr:$src3)),
(VFMSUBADDPS4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmsubadd_ps VR128:$src1, (alignedloadv4f32 addr:$src2),
VR128:$src3),
(VFMSUBADDPS4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmsubadd_pd VR128:$src1, VR128:$src2, VR128:$src3),
(VFMSUBADDPD4rr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmsubadd_pd VR128:$src1, VR128:$src2,
(alignedloadv2f64 addr:$src3)),
(VFMSUBADDPD4rm VR128:$src1, VR128:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmsubadd_pd VR128:$src1, (alignedloadv2f64 addr:$src2),
VR128:$src3),
(VFMSUBADDPD4mr VR128:$src1, addr:$src2, VR128:$src3)>;
def : Pat<(int_x86_fma4_vfmsubadd_ps_256 VR256:$src1, VR256:$src2, VR256:$src3),
(VFMSUBADDPS4rrY VR256:$src1, VR256:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfmsubadd_ps_256 VR256:$src1, VR256:$src2,
(alignedloadv8f32 addr:$src3)),
(VFMSUBADDPS4rmY VR256:$src1, VR256:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmsubadd_ps_256 VR256:$src1,
(alignedloadv8f32 addr:$src2),
VR256:$src3),
(VFMSUBADDPS4mrY VR256:$src1, addr:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfmsubadd_pd_256 VR256:$src1, VR256:$src2, VR256:$src3),
(VFMSUBADDPD4rrY VR256:$src1, VR256:$src2, VR256:$src3)>;
def : Pat<(int_x86_fma4_vfmsubadd_pd_256 VR256:$src1, VR256:$src2,
(alignedloadv4f64 addr:$src3)),
(VFMSUBADDPD4rmY VR256:$src1, VR256:$src2, addr:$src3)>;
def : Pat<(int_x86_fma4_vfmsubadd_pd_256 VR256:$src1,
(alignedloadv4f64 addr:$src2),
VR256:$src3),
(VFMSUBADDPD4mrY VR256:$src1, addr:$src2, VR256:$src3)>;