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

//====- 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 fma3p_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 fma3p_forms<bits<8> opc132, bits<8> opc213, bits<8> opc231,
                       string OpcodeStr, string PackTy> {
  defm r132 : fma3p_rm<opc132, !strconcat(OpcodeStr, !strconcat("132", PackTy))>;
  defm r213 : fma3p_rm<opc213, !strconcat(OpcodeStr, !strconcat("213", PackTy))>;
  defm r231 : fma3p_rm<opc231, !strconcat(OpcodeStr, !strconcat("231", PackTy))>;
}

// Fused Multiply-Add
let ExeDomain = SSEPackedSingle in {
  defm VFMADDPS    : fma3p_forms<0x98, 0xA8, 0xB8, "vfmadd", "ps">;
  defm VFMSUBPS    : fma3p_forms<0x9A, 0xAA, 0xBA, "vfmsub", "ps">;
  defm VFMADDSUBPS : fma3p_forms<0x96, 0xA6, 0xB6, "vfmaddsub", "ps">;
  defm VFMSUBADDPS : fma3p_forms<0x97, 0xA7, 0xB7, "vfmsubadd", "ps">;
}

let ExeDomain = SSEPackedDouble in {
  defm VFMADDPD    : fma3p_forms<0x98, 0xA8, 0xB8, "vfmadd", "pd">, VEX_W;
  defm VFMSUBPD    : fma3p_forms<0x9A, 0xAA, 0xBA, "vfmsub", "pd">, VEX_W;
  defm VFMADDSUBPD : fma3p_forms<0x96, 0xA6, 0xB6, "vfmaddsub", "pd">, VEX_W;
  defm VFMSUBADDPD : fma3p_forms<0x97, 0xA7, 0xB7, "vfmsubadd", "pd">, VEX_W;
}

// Fused Negative Multiply-Add
let ExeDomain = SSEPackedSingle in {
  defm VFNMADDPS : fma3p_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "ps">;
  defm VFNMSUBPS : fma3p_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "ps">;
}
let ExeDomain = SSEPackedDouble in {
  defm VFNMADDPD : fma3p_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "pd">, VEX_W;
  defm VFNMSUBPD : fma3p_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "pd">, VEX_W;
}

multiclass fma3s_rm<bits<8> opc, string OpcodeStr, X86MemOperand x86memop> {
  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:$src1, x86memop:$src2),
           !strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
           []>;
}

multiclass fma3s_forms<bits<8> opc132, bits<8> opc213, bits<8> opc231,
                       string OpcodeStr> {
  defm SSr132 : fma3s_rm<opc132, !strconcat(OpcodeStr, "132ss"), f32mem>;
  defm SSr213 : fma3s_rm<opc213, !strconcat(OpcodeStr, "213ss"), f32mem>;
  defm SSr231 : fma3s_rm<opc231, !strconcat(OpcodeStr, "231ss"), f32mem>;
  defm SDr132 : fma3s_rm<opc132, !strconcat(OpcodeStr, "132sd"), f64mem>, VEX_W;
  defm SDr213 : fma3s_rm<opc213, !strconcat(OpcodeStr, "213sd"), f64mem>, VEX_W;
  defm SDr231 : fma3s_rm<opc231, !strconcat(OpcodeStr, "231sd"), f64mem>, VEX_W;
}

defm VFMADD : fma3s_forms<0x99, 0xA9, 0xB9, "vfmadd">;
defm VFMSUB : fma3s_forms<0x9B, 0xAB, 0xBB, "vfmsub">;

defm VFNMADD : fma3s_forms<0x9D, 0xAD, 0xBD, "vfnmadd">;
defm VFNMSUB : fma3s_forms<0x9F, 0xAF, 0xBF, "vfnmsub">;

//===----------------------------------------------------------------------===//
// FMA4 - AMD 4 operand Fused Multiply-Add instructions
//===----------------------------------------------------------------------===//


multiclass fma4s<bits<8> opc, string OpcodeStr, Operand memop> {
  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, memop:$src3),
           !strconcat(OpcodeStr,
           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
           []>, XOP_W;
  def mr : FMA4<opc, MRMSrcMem, (outs VR128:$dst),
           (ins VR128:$src1, memop:$src2, VR128:$src3),
           !strconcat(OpcodeStr,
           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
           []>;
}

multiclass fma4p<bits<8> opc, string OpcodeStr,
                 Intrinsic Int128, Intrinsic Int256,
                 PatFrag ld_frag128, PatFrag ld_frag256> {
  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, $src3}"),
           [(set VR128:$dst,
             (Int128 VR128:$src1, VR128:$src2, VR128:$src3))]>, XOP_W;
  def rm : FMA4<opc, MRMSrcMem, (outs VR128:$dst),
           (ins VR128:$src1, VR128:$src2, f128mem:$src3),
           !strconcat(OpcodeStr,
           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
           [(set VR128:$dst, (Int128 VR128:$src1, VR128:$src2,
                              (ld_frag128 addr:$src3)))]>, XOP_W;
  def mr : FMA4<opc, MRMSrcMem, (outs VR128:$dst),
           (ins VR128:$src1, f128mem:$src2, VR128:$src3),
           !strconcat(OpcodeStr,
           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
           [(set VR128:$dst,
             (Int128 VR128:$src1, (ld_frag128 addr:$src2), VR128:$src3))]>;
  def rrY : FMA4<opc, MRMSrcReg, (outs VR256:$dst),
           (ins VR256:$src1, VR256:$src2, VR256:$src3),
           !strconcat(OpcodeStr,
           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
           [(set VR256:$dst,
             (Int256 VR256:$src1, VR256:$src2, VR256:$src3))]>, XOP_W;
  def rmY : FMA4<opc, MRMSrcMem, (outs VR256:$dst),
           (ins VR256:$src1, VR256:$src2, f256mem:$src3),
           !strconcat(OpcodeStr,
           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
           [(set VR256:$dst, (Int256 VR256:$src1, VR256:$src2,
                              (ld_frag256 addr:$src3)))]>, XOP_W;
  def mrY : FMA4<opc, MRMSrcMem, (outs VR256:$dst),
           (ins VR256:$src1, f256mem:$src2, VR256:$src3),
           !strconcat(OpcodeStr,
           "\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
           [(set VR256:$dst,
             (Int256 VR256:$src1, (ld_frag256 addr:$src2), VR256:$src3))]>;
}

let isAsmParserOnly = 1 in {
  defm VFMADDSS4    : fma4s<0x6A, "vfmaddss", ssmem>;
  defm VFMADDSD4    : fma4s<0x6B, "vfmaddsd", sdmem>;
  defm VFMADDPS4    : fma4p<0x68, "vfmaddps", int_x86_fma4_vfmadd_ps,
                            int_x86_fma4_vfmadd_ps_256, memopv4f32, memopv8f32>;
  defm VFMADDPD4    : fma4p<0x69, "vfmaddpd", int_x86_fma4_vfmadd_pd,
                            int_x86_fma4_vfmadd_pd_256, memopv2f64, memopv4f64>;
  defm VFMSUBSS4    : fma4s<0x6E, "vfmsubss", ssmem>;
  defm VFMSUBSD4    : fma4s<0x6F, "vfmsubsd", sdmem>;
  defm VFMSUBPS4    : fma4p<0x6C, "vfmsubps", int_x86_fma4_vfmsub_ps,
                            int_x86_fma4_vfmsub_ps_256, memopv4f32, memopv8f32>;
  defm VFMSUBPD4    : fma4p<0x6D, "vfmsubpd", int_x86_fma4_vfmsub_pd,
                            int_x86_fma4_vfmsub_pd_256, memopv2f64, memopv4f64>;
  defm VFNMADDSS4   : fma4s<0x7A, "vfnmaddss", ssmem>;
  defm VFNMADDSD4   : fma4s<0x7B, "vfnmaddsd", sdmem>;
  defm VFNMADDPS4   : fma4p<0x78, "vfnmaddps", int_x86_fma4_vfnmadd_ps,
                           int_x86_fma4_vfnmadd_ps_256, memopv4f32, memopv8f32>;
  defm VFNMADDPD4   : fma4p<0x79, "vfnmaddpd", int_x86_fma4_vfnmadd_pd,
                           int_x86_fma4_vfnmadd_pd_256, memopv2f64, memopv4f64>;
  defm VFNMSUBSS4   : fma4s<0x7E, "vfnmsubss", ssmem>;
  defm VFNMSUBSD4   : fma4s<0x7F, "vfnmsubsd", sdmem>;
  defm VFNMSUBPS4   : fma4p<0x7C, "vfnmsubps", int_x86_fma4_vfnmsub_ps,
                           int_x86_fma4_vfnmsub_ps_256, memopv4f32, memopv8f32>;
  defm VFNMSUBPD4   : fma4p<0x7D, "vfnmsubpd", int_x86_fma4_vfnmsub_pd,
                           int_x86_fma4_vfnmsub_pd_256, memopv2f64, memopv4f64>;
  defm VFMADDSUBPS4 : fma4p<0x5C, "vfmaddsubps", int_x86_fma4_vfmaddsub_ps,
                         int_x86_fma4_vfmaddsub_ps_256, memopv4f32, memopv8f32>;
  defm VFMADDSUBPD4 : fma4p<0x5D, "vfmaddsubpd", int_x86_fma4_vfmaddsub_pd,
                         int_x86_fma4_vfmaddsub_pd_256, memopv2f64, memopv4f64>;
  defm VFMSUBADDPS4 : fma4p<0x5E, "vfmsubaddps", int_x86_fma4_vfmsubadd_ps,
                         int_x86_fma4_vfmsubadd_ps_256, memopv4f32, memopv8f32>;
  defm VFMSUBADDPD4 : fma4p<0x5F, "vfmsubaddpd", int_x86_fma4_vfmsubadd_pd,
                         int_x86_fma4_vfmsubadd_pd_256, memopv2f64, memopv4f64>;
}

// FMA4 Intrinsics patterns

let Predicates = [HasFMA4] in {

// 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, sse_load_f32:$src3),
          (VFMADDSS4rm VR128:$src1, VR128:$src2, sse_load_f32:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_ss VR128:$src1, sse_load_f32:$src2, VR128:$src3),
          (VFMADDSS4mr VR128:$src1, sse_load_f32:$src2, VR128:$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, sse_load_f64:$src3),
          (VFMADDSD4rm VR128:$src1, VR128:$src2, sse_load_f64:$src3)>;
def : Pat<(int_x86_fma4_vfmadd_sd VR128:$src1, sse_load_f64:$src2, VR128:$src3),
          (VFMADDSD4mr VR128:$src1, sse_load_f64:$src2, VR128:$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, sse_load_f32:$src3),
          (VFMSUBSS4rm VR128:$src1, VR128:$src2, sse_load_f32:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_ss VR128:$src1, sse_load_f32:$src2, VR128:$src3),
          (VFMSUBSS4mr VR128:$src1, sse_load_f32:$src2, VR128:$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, sse_load_f64:$src3),
          (VFMSUBSD4rm VR128:$src1, VR128:$src2, sse_load_f64:$src3)>;
def : Pat<(int_x86_fma4_vfmsub_sd VR128:$src1, sse_load_f64:$src2, VR128:$src3),
          (VFMSUBSD4mr VR128:$src1, sse_load_f64:$src2, VR128:$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, sse_load_f32:$src3),
          (VFNMADDSS4rm VR128:$src1, VR128:$src2, sse_load_f32:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_ss VR128:$src1, sse_load_f32:$src2, VR128:$src3),
          (VFNMADDSS4mr VR128:$src1, sse_load_f32:$src2, VR128:$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, sse_load_f64:$src3),
          (VFNMADDSD4rm VR128:$src1, VR128:$src2, sse_load_f64:$src3)>;
def : Pat<(int_x86_fma4_vfnmadd_sd VR128:$src1, sse_load_f64:$src2, VR128:$src3),
          (VFNMADDSD4mr VR128:$src1, sse_load_f64:$src2, VR128:$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, sse_load_f32:$src3),
          (VFNMSUBSS4rm VR128:$src1, VR128:$src2, sse_load_f32:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_ss VR128:$src1, sse_load_f32:$src2, VR128:$src3),
          (VFNMSUBSS4mr VR128:$src1, sse_load_f32:$src2, VR128:$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, sse_load_f64:$src3),
          (VFNMSUBSD4rm VR128:$src1, VR128:$src2, sse_load_f64:$src3)>;
def : Pat<(int_x86_fma4_vfnmsub_sd VR128:$src1, sse_load_f64:$src2, VR128:$src3),
          (VFNMSUBSD4mr VR128:$src1, sse_load_f64:$src2, VR128:$src3)>;

// VFMADDSUB
def : Pat<(int_x86_fma4_vfmaddsub_ps VR128:$src1, (memopv4f32 addr:$src2),
                                  VR128:$src3),
          (VFMADDSUBPS4mr VR128:$src1, addr:$src2, VR128:$src3)>;

def : Pat<(int_x86_fma4_vfmaddsub_pd VR128:$src1, (memopv2f64 addr:$src2),
                                  VR128:$src3),
          (VFMADDSUBPD4mr VR128:$src1, addr:$src2, VR128:$src3)>;


// VFMSUBADD
def : Pat<(int_x86_fma4_vfmsubadd_ps VR128:$src1, (memopv4f32 addr:$src2),
                                  VR128:$src3),
          (VFMSUBADDPS4mr VR128:$src1, addr:$src2, VR128:$src3)>;

def : Pat<(int_x86_fma4_vfmsubadd_pd VR128:$src1, (memopv2f64 addr:$src2),
                                  VR128:$src3),
          (VFMSUBADDPD4mr VR128:$src1, addr:$src2, VR128:$src3)>;

} // Predicates = [HasFMA4]