forked from OSchip/llvm-project
442 lines
22 KiB
TableGen
442 lines
22 KiB
TableGen
//===-- X86InstrFMA.td - FMA 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
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// For all FMA opcodes declared in fma3p_rm and fma3s_rm milticlasses defined
|
|
// below, both the register and memory variants are commutable.
|
|
// For the register form the commutable operands are 1, 2 and 3.
|
|
// For the memory variant the folded operand must be in 3. Thus,
|
|
// in that case, only the operands 1 and 2 can be swapped.
|
|
// Commuting some of operands may require the opcode change.
|
|
// FMA*213*:
|
|
// operands 1 and 2 (memory & register forms): *213* --> *213*(no changes);
|
|
// operands 1 and 3 (register forms only): *213* --> *231*;
|
|
// operands 2 and 3 (register forms only): *213* --> *132*.
|
|
// FMA*132*:
|
|
// operands 1 and 2 (memory & register forms): *132* --> *231*;
|
|
// operands 1 and 3 (register forms only): *132* --> *132*(no changes);
|
|
// operands 2 and 3 (register forms only): *132* --> *213*.
|
|
// FMA*231*:
|
|
// operands 1 and 2 (memory & register forms): *231* --> *132*;
|
|
// operands 1 and 3 (register forms only): *231* --> *213*;
|
|
// operands 2 and 3 (register forms only): *231* --> *231*(no changes).
|
|
|
|
let Constraints = "$src1 = $dst", hasSideEffects = 0, isCommutable = 1 in
|
|
multiclass fma3p_rm<bits<8> opc, string OpcodeStr,
|
|
PatFrag MemFrag128, PatFrag MemFrag256,
|
|
ValueType OpVT128, ValueType OpVT256,
|
|
SDPatternOperator Op = null_frag> {
|
|
let usesCustomInserter = 1 in
|
|
def r : FMA3<opc, MRMSrcReg, (outs VR128:$dst),
|
|
(ins VR128:$src1, VR128:$src2, VR128:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set VR128:$dst, (OpVT128 (Op VR128:$src2,
|
|
VR128:$src1, VR128:$src3)))]>;
|
|
|
|
let mayLoad = 1 in
|
|
def m : FMA3<opc, MRMSrcMem, (outs VR128:$dst),
|
|
(ins VR128:$src1, VR128:$src2, f128mem:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set VR128:$dst, (OpVT128 (Op VR128:$src2, VR128:$src1,
|
|
(MemFrag128 addr:$src3))))]>;
|
|
|
|
let usesCustomInserter = 1 in
|
|
def rY : FMA3<opc, MRMSrcReg, (outs VR256:$dst),
|
|
(ins VR256:$src1, VR256:$src2, VR256:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set VR256:$dst, (OpVT256 (Op VR256:$src2, VR256:$src1,
|
|
VR256:$src3)))]>, VEX_L;
|
|
|
|
let mayLoad = 1 in
|
|
def mY : FMA3<opc, MRMSrcMem, (outs VR256:$dst),
|
|
(ins VR256:$src1, VR256:$src2, f256mem:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set VR256:$dst,
|
|
(OpVT256 (Op VR256:$src2, VR256:$src1,
|
|
(MemFrag256 addr:$src3))))]>, VEX_L;
|
|
}
|
|
|
|
multiclass fma3p_forms<bits<8> opc132, bits<8> opc213, bits<8> opc231,
|
|
string OpcodeStr, string PackTy,
|
|
PatFrag MemFrag128, PatFrag MemFrag256,
|
|
SDNode Op, ValueType OpTy128, ValueType OpTy256> {
|
|
defm r213 : fma3p_rm<opc213,
|
|
!strconcat(OpcodeStr, "213", PackTy),
|
|
MemFrag128, MemFrag256, OpTy128, OpTy256, Op>;
|
|
defm r132 : fma3p_rm<opc132,
|
|
!strconcat(OpcodeStr, "132", PackTy),
|
|
MemFrag128, MemFrag256, OpTy128, OpTy256>;
|
|
defm r231 : fma3p_rm<opc231,
|
|
!strconcat(OpcodeStr, "231", PackTy),
|
|
MemFrag128, MemFrag256, OpTy128, OpTy256>;
|
|
}
|
|
|
|
// Fused Multiply-Add
|
|
let ExeDomain = SSEPackedSingle in {
|
|
defm VFMADDPS : fma3p_forms<0x98, 0xA8, 0xB8, "vfmadd", "ps", loadv4f32,
|
|
loadv8f32, X86Fmadd, v4f32, v8f32>;
|
|
defm VFMSUBPS : fma3p_forms<0x9A, 0xAA, 0xBA, "vfmsub", "ps", loadv4f32,
|
|
loadv8f32, X86Fmsub, v4f32, v8f32>;
|
|
defm VFMADDSUBPS : fma3p_forms<0x96, 0xA6, 0xB6, "vfmaddsub", "ps",
|
|
loadv4f32, loadv8f32, X86Fmaddsub,
|
|
v4f32, v8f32>;
|
|
defm VFMSUBADDPS : fma3p_forms<0x97, 0xA7, 0xB7, "vfmsubadd", "ps",
|
|
loadv4f32, loadv8f32, X86Fmsubadd,
|
|
v4f32, v8f32>;
|
|
}
|
|
|
|
let ExeDomain = SSEPackedDouble in {
|
|
defm VFMADDPD : fma3p_forms<0x98, 0xA8, 0xB8, "vfmadd", "pd", loadv2f64,
|
|
loadv4f64, X86Fmadd, v2f64, v4f64>, VEX_W;
|
|
defm VFMSUBPD : fma3p_forms<0x9A, 0xAA, 0xBA, "vfmsub", "pd", loadv2f64,
|
|
loadv4f64, X86Fmsub, v2f64, v4f64>, VEX_W;
|
|
defm VFMADDSUBPD : fma3p_forms<0x96, 0xA6, 0xB6, "vfmaddsub", "pd",
|
|
loadv2f64, loadv4f64, X86Fmaddsub,
|
|
v2f64, v4f64>, VEX_W;
|
|
defm VFMSUBADDPD : fma3p_forms<0x97, 0xA7, 0xB7, "vfmsubadd", "pd",
|
|
loadv2f64, loadv4f64, X86Fmsubadd,
|
|
v2f64, v4f64>, VEX_W;
|
|
}
|
|
|
|
// Fused Negative Multiply-Add
|
|
let ExeDomain = SSEPackedSingle in {
|
|
defm VFNMADDPS : fma3p_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "ps", loadv4f32,
|
|
loadv8f32, X86Fnmadd, v4f32, v8f32>;
|
|
defm VFNMSUBPS : fma3p_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "ps", loadv4f32,
|
|
loadv8f32, X86Fnmsub, v4f32, v8f32>;
|
|
}
|
|
let ExeDomain = SSEPackedDouble in {
|
|
defm VFNMADDPD : fma3p_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "pd", loadv2f64,
|
|
loadv4f64, X86Fnmadd, v2f64, v4f64>, VEX_W;
|
|
defm VFNMSUBPD : fma3p_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "pd",
|
|
loadv2f64, loadv4f64, X86Fnmsub, v2f64,
|
|
v4f64>, VEX_W;
|
|
}
|
|
|
|
// All source register operands of FMA opcodes defined in fma3s_rm multiclass
|
|
// can be commuted. In many cases such commute transformation requres an opcode
|
|
// adjustment, for example, commuting the operands 1 and 2 in FMA*132 form
|
|
// would require an opcode change to FMA*231:
|
|
// FMA*132* reg1, reg2, reg3; // reg1 * reg3 + reg2;
|
|
// -->
|
|
// FMA*231* reg2, reg1, reg3; // reg1 * reg3 + reg2;
|
|
// Please see more detailed comment at the very beginning of the section
|
|
// defining FMA3 opcodes above.
|
|
let Constraints = "$src1 = $dst", isCommutable = 1, hasSideEffects = 0 in
|
|
multiclass fma3s_rm<bits<8> opc, string OpcodeStr,
|
|
X86MemOperand x86memop, RegisterClass RC,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
let usesCustomInserter = 1 in
|
|
def r : FMA3<opc, MRMSrcReg, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, RC:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set RC:$dst, (OpNode RC:$src2, RC:$src1, RC:$src3))]>;
|
|
|
|
let mayLoad = 1 in
|
|
def m : FMA3<opc, MRMSrcMem, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, x86memop:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set RC:$dst,
|
|
(OpNode RC:$src2, RC:$src1, (load addr:$src3)))]>;
|
|
}
|
|
|
|
// These FMA*_Int instructions are defined specially for being used when
|
|
// the scalar FMA intrinsics are lowered to machine instructions, and in that
|
|
// sense, they are similar to existing ADD*_Int, SUB*_Int, MUL*_Int, etc.
|
|
// instructions.
|
|
//
|
|
// All of the FMA*_Int opcodes are defined as commutable here.
|
|
// Commuting the 2nd and 3rd source register operands of FMAs is quite trivial
|
|
// and the corresponding optimizations have been developed.
|
|
// Commuting the 1st operand of FMA*_Int requires some additional analysis,
|
|
// the commute optimization is legal only if all users of FMA*_Int use only
|
|
// the lowest element of the FMA*_Int instruction. Even though such analysis
|
|
// may be not implemented yet we allow the routines doing the actual commute
|
|
// transformation to decide if one or another instruction is commutable or not.
|
|
let Constraints = "$src1 = $dst", isCommutable = 1, isCodeGenOnly = 1,
|
|
hasSideEffects = 0 in
|
|
multiclass fma3s_rm_int<bits<8> opc, string OpcodeStr,
|
|
Operand memopr, RegisterClass RC> {
|
|
def r_Int : FMA3<opc, MRMSrcReg, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, RC:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[]>;
|
|
|
|
let mayLoad = 1 in
|
|
def m_Int : FMA3<opc, MRMSrcMem, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, memopr:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[]>;
|
|
}
|
|
|
|
multiclass fma3s_forms<bits<8> opc132, bits<8> opc213, bits<8> opc231,
|
|
string OpStr, string PackTy,
|
|
SDNode OpNode, RegisterClass RC,
|
|
X86MemOperand x86memop> {
|
|
defm r132 : fma3s_rm<opc132, !strconcat(OpStr, "132", PackTy), x86memop, RC>;
|
|
defm r213 : fma3s_rm<opc213, !strconcat(OpStr, "213", PackTy), x86memop, RC,
|
|
OpNode>;
|
|
defm r231 : fma3s_rm<opc231, !strconcat(OpStr, "231", PackTy), x86memop, RC>;
|
|
}
|
|
|
|
// The FMA 213 form is created for lowering of scalar FMA intrinscis
|
|
// to machine instructions.
|
|
// The FMA 132 form can trivially be get by commuting the 2nd and 3rd operands
|
|
// of FMA 213 form.
|
|
// The FMA 231 form can be get only by commuting the 1st operand of 213 or 132
|
|
// forms and is possible only after special analysis of all uses of the initial
|
|
// instruction. Such analysis do not exist yet and thus introducing the 231
|
|
// form of FMA*_Int instructions is done using an optimistic assumption that
|
|
// such analysis will be implemented eventually.
|
|
multiclass fma3s_int_forms<bits<8> opc132, bits<8> opc213, bits<8> opc231,
|
|
string OpStr, string PackTy,
|
|
RegisterClass RC, Operand memop> {
|
|
defm r132 : fma3s_rm_int<opc132, !strconcat(OpStr, "132", PackTy),
|
|
memop, RC>;
|
|
defm r213 : fma3s_rm_int<opc213, !strconcat(OpStr, "213", PackTy),
|
|
memop, RC>;
|
|
defm r231 : fma3s_rm_int<opc231, !strconcat(OpStr, "231", PackTy),
|
|
memop, RC>;
|
|
}
|
|
|
|
multiclass fma3s<bits<8> opc132, bits<8> opc213, bits<8> opc231,
|
|
string OpStr, Intrinsic IntF32, Intrinsic IntF64,
|
|
SDNode OpNode> {
|
|
let ExeDomain = SSEPackedSingle in
|
|
defm SS : fma3s_forms<opc132, opc213, opc231, OpStr, "ss", OpNode,
|
|
FR32, f32mem>,
|
|
fma3s_int_forms<opc132, opc213, opc231, OpStr, "ss", VR128, ssmem>;
|
|
|
|
let ExeDomain = SSEPackedDouble in
|
|
defm SD : fma3s_forms<opc132, opc213, opc231, OpStr, "sd", OpNode,
|
|
FR64, f64mem>,
|
|
fma3s_int_forms<opc132, opc213, opc231, OpStr, "sd", VR128, sdmem>,
|
|
VEX_W;
|
|
|
|
// These patterns use the 123 ordering, instead of 213, even though
|
|
// they match the intrinsic to the 213 version of the instruction.
|
|
// This is because src1 is tied to dest, and the scalar intrinsics
|
|
// require the pass-through values to come from the first source
|
|
// operand, not the second.
|
|
def : Pat<(IntF32 VR128:$src1, VR128:$src2, VR128:$src3),
|
|
(COPY_TO_REGCLASS(!cast<Instruction>(NAME#"SSr213r_Int")
|
|
$src1, $src2, $src3), VR128)>;
|
|
|
|
def : Pat<(IntF64 VR128:$src1, VR128:$src2, VR128:$src3),
|
|
(COPY_TO_REGCLASS(!cast<Instruction>(NAME#"SDr213r_Int")
|
|
$src1, $src2, $src3), VR128)>;
|
|
}
|
|
|
|
defm VFMADD : fma3s<0x99, 0xA9, 0xB9, "vfmadd", int_x86_fma_vfmadd_ss,
|
|
int_x86_fma_vfmadd_sd, X86Fmadd>, VEX_LIG;
|
|
defm VFMSUB : fma3s<0x9B, 0xAB, 0xBB, "vfmsub", int_x86_fma_vfmsub_ss,
|
|
int_x86_fma_vfmsub_sd, X86Fmsub>, VEX_LIG;
|
|
|
|
defm VFNMADD : fma3s<0x9D, 0xAD, 0xBD, "vfnmadd", int_x86_fma_vfnmadd_ss,
|
|
int_x86_fma_vfnmadd_sd, X86Fnmadd>, VEX_LIG;
|
|
defm VFNMSUB : fma3s<0x9F, 0xAF, 0xBF, "vfnmsub", int_x86_fma_vfnmsub_ss,
|
|
int_x86_fma_vfnmsub_sd, X86Fnmsub>, VEX_LIG;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// FMA4 - AMD 4 operand Fused Multiply-Add instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
multiclass fma4s<bits<8> opc, string OpcodeStr, RegisterClass RC,
|
|
X86MemOperand x86memop, ValueType OpVT, SDNode OpNode,
|
|
PatFrag mem_frag> {
|
|
let isCommutable = 1 in
|
|
def rr : FMA4<opc, MRMSrcReg, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, RC:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set RC:$dst,
|
|
(OpVT (OpNode RC:$src1, RC:$src2, RC:$src3)))]>, VEX_W, VEX_LIG, MemOp4;
|
|
def rm : FMA4<opc, MRMSrcMem, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, x86memop:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set RC:$dst, (OpNode RC:$src1, RC:$src2,
|
|
(mem_frag addr:$src3)))]>, VEX_W, VEX_LIG, MemOp4;
|
|
def mr : FMA4<opc, MRMSrcMem, (outs RC:$dst),
|
|
(ins RC:$src1, x86memop:$src2, RC:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set RC:$dst,
|
|
(OpNode RC:$src1, (mem_frag addr:$src2), RC:$src3))]>, VEX_LIG;
|
|
// For disassembler
|
|
let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in
|
|
def rr_REV : FMA4<opc, MRMSrcReg, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, RC:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"), []>,
|
|
VEX_LIG;
|
|
}
|
|
|
|
multiclass fma4s_int<bits<8> opc, string OpcodeStr, Operand memop,
|
|
ComplexPattern mem_cpat, Intrinsic Int> {
|
|
let isCodeGenOnly = 1 in {
|
|
let isCommutable = 1 in
|
|
def rr_Int : FMA4<opc, MRMSrcReg, (outs VR128:$dst),
|
|
(ins VR128:$src1, VR128:$src2, VR128:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set VR128:$dst,
|
|
(Int VR128:$src1, VR128:$src2, VR128:$src3))]>, VEX_W, VEX_LIG, MemOp4;
|
|
def rm_Int : FMA4<opc, MRMSrcMem, (outs VR128:$dst),
|
|
(ins VR128:$src1, VR128:$src2, memop:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set VR128:$dst, (Int VR128:$src1, VR128:$src2,
|
|
mem_cpat:$src3))]>, VEX_W, VEX_LIG, MemOp4;
|
|
def mr_Int : FMA4<opc, MRMSrcMem, (outs VR128:$dst),
|
|
(ins VR128:$src1, memop:$src2, VR128:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set VR128:$dst,
|
|
(Int VR128:$src1, mem_cpat:$src2, VR128:$src3))]>, VEX_LIG;
|
|
} // isCodeGenOnly = 1
|
|
}
|
|
|
|
multiclass fma4p<bits<8> opc, string OpcodeStr, SDNode OpNode,
|
|
ValueType OpVT128, ValueType OpVT256,
|
|
PatFrag ld_frag128, PatFrag ld_frag256> {
|
|
let isCommutable = 1 in
|
|
def rr : FMA4<opc, MRMSrcReg, (outs VR128:$dst),
|
|
(ins VR128:$src1, VR128:$src2, VR128:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set VR128:$dst,
|
|
(OpVT128 (OpNode VR128:$src1, VR128:$src2, VR128:$src3)))]>,
|
|
VEX_W, MemOp4;
|
|
def rm : FMA4<opc, MRMSrcMem, (outs VR128:$dst),
|
|
(ins VR128:$src1, VR128:$src2, f128mem:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set VR128:$dst, (OpNode VR128:$src1, VR128:$src2,
|
|
(ld_frag128 addr:$src3)))]>, VEX_W, MemOp4;
|
|
def mr : FMA4<opc, MRMSrcMem, (outs VR128:$dst),
|
|
(ins VR128:$src1, f128mem:$src2, VR128:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set VR128:$dst,
|
|
(OpNode VR128:$src1, (ld_frag128 addr:$src2), VR128:$src3))]>;
|
|
let isCommutable = 1 in
|
|
def rrY : FMA4<opc, MRMSrcReg, (outs VR256:$dst),
|
|
(ins VR256:$src1, VR256:$src2, VR256:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set VR256:$dst,
|
|
(OpVT256 (OpNode VR256:$src1, VR256:$src2, VR256:$src3)))]>,
|
|
VEX_W, MemOp4, VEX_L;
|
|
def rmY : FMA4<opc, MRMSrcMem, (outs VR256:$dst),
|
|
(ins VR256:$src1, VR256:$src2, f256mem:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set VR256:$dst, (OpNode VR256:$src1, VR256:$src2,
|
|
(ld_frag256 addr:$src3)))]>, VEX_W, MemOp4, VEX_L;
|
|
def mrY : FMA4<opc, MRMSrcMem, (outs VR256:$dst),
|
|
(ins VR256:$src1, f256mem:$src2, VR256:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set VR256:$dst, (OpNode VR256:$src1,
|
|
(ld_frag256 addr:$src2), VR256:$src3))]>, VEX_L;
|
|
// For disassembler
|
|
let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in {
|
|
def rr_REV : FMA4<opc, MRMSrcReg, (outs VR128:$dst),
|
|
(ins VR128:$src1, VR128:$src2, VR128:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"), []>;
|
|
def rrY_REV : FMA4<opc, MRMSrcReg, (outs VR256:$dst),
|
|
(ins VR256:$src1, VR256:$src2, VR256:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"), []>,
|
|
VEX_L;
|
|
} // isCodeGenOnly = 1
|
|
}
|
|
|
|
let ExeDomain = SSEPackedSingle in {
|
|
// Scalar Instructions
|
|
defm VFMADDSS4 : fma4s<0x6A, "vfmaddss", FR32, f32mem, f32, X86Fmadd, loadf32>,
|
|
fma4s_int<0x6A, "vfmaddss", ssmem, sse_load_f32,
|
|
int_x86_fma_vfmadd_ss>;
|
|
defm VFMSUBSS4 : fma4s<0x6E, "vfmsubss", FR32, f32mem, f32, X86Fmsub, loadf32>,
|
|
fma4s_int<0x6E, "vfmsubss", ssmem, sse_load_f32,
|
|
int_x86_fma_vfmsub_ss>;
|
|
defm VFNMADDSS4 : fma4s<0x7A, "vfnmaddss", FR32, f32mem, f32,
|
|
X86Fnmadd, loadf32>,
|
|
fma4s_int<0x7A, "vfnmaddss", ssmem, sse_load_f32,
|
|
int_x86_fma_vfnmadd_ss>;
|
|
defm VFNMSUBSS4 : fma4s<0x7E, "vfnmsubss", FR32, f32mem, f32,
|
|
X86Fnmsub, loadf32>,
|
|
fma4s_int<0x7E, "vfnmsubss", ssmem, sse_load_f32,
|
|
int_x86_fma_vfnmsub_ss>;
|
|
// Packed Instructions
|
|
defm VFMADDPS4 : fma4p<0x68, "vfmaddps", X86Fmadd, v4f32, v8f32,
|
|
loadv4f32, loadv8f32>;
|
|
defm VFMSUBPS4 : fma4p<0x6C, "vfmsubps", X86Fmsub, v4f32, v8f32,
|
|
loadv4f32, loadv8f32>;
|
|
defm VFNMADDPS4 : fma4p<0x78, "vfnmaddps", X86Fnmadd, v4f32, v8f32,
|
|
loadv4f32, loadv8f32>;
|
|
defm VFNMSUBPS4 : fma4p<0x7C, "vfnmsubps", X86Fnmsub, v4f32, v8f32,
|
|
loadv4f32, loadv8f32>;
|
|
defm VFMADDSUBPS4 : fma4p<0x5C, "vfmaddsubps", X86Fmaddsub, v4f32, v8f32,
|
|
loadv4f32, loadv8f32>;
|
|
defm VFMSUBADDPS4 : fma4p<0x5E, "vfmsubaddps", X86Fmsubadd, v4f32, v8f32,
|
|
loadv4f32, loadv8f32>;
|
|
}
|
|
|
|
let ExeDomain = SSEPackedDouble in {
|
|
// Scalar Instructions
|
|
defm VFMADDSD4 : fma4s<0x6B, "vfmaddsd", FR64, f64mem, f64, X86Fmadd, loadf64>,
|
|
fma4s_int<0x6B, "vfmaddsd", sdmem, sse_load_f64,
|
|
int_x86_fma_vfmadd_sd>;
|
|
defm VFMSUBSD4 : fma4s<0x6F, "vfmsubsd", FR64, f64mem, f64, X86Fmsub, loadf64>,
|
|
fma4s_int<0x6F, "vfmsubsd", sdmem, sse_load_f64,
|
|
int_x86_fma_vfmsub_sd>;
|
|
defm VFNMADDSD4 : fma4s<0x7B, "vfnmaddsd", FR64, f64mem, f64,
|
|
X86Fnmadd, loadf64>,
|
|
fma4s_int<0x7B, "vfnmaddsd", sdmem, sse_load_f64,
|
|
int_x86_fma_vfnmadd_sd>;
|
|
defm VFNMSUBSD4 : fma4s<0x7F, "vfnmsubsd", FR64, f64mem, f64,
|
|
X86Fnmsub, loadf64>,
|
|
fma4s_int<0x7F, "vfnmsubsd", sdmem, sse_load_f64,
|
|
int_x86_fma_vfnmsub_sd>;
|
|
// Packed Instructions
|
|
defm VFMADDPD4 : fma4p<0x69, "vfmaddpd", X86Fmadd, v2f64, v4f64,
|
|
loadv2f64, loadv4f64>;
|
|
defm VFMSUBPD4 : fma4p<0x6D, "vfmsubpd", X86Fmsub, v2f64, v4f64,
|
|
loadv2f64, loadv4f64>;
|
|
defm VFNMADDPD4 : fma4p<0x79, "vfnmaddpd", X86Fnmadd, v2f64, v4f64,
|
|
loadv2f64, loadv4f64>;
|
|
defm VFNMSUBPD4 : fma4p<0x7D, "vfnmsubpd", X86Fnmsub, v2f64, v4f64,
|
|
loadv2f64, loadv4f64>;
|
|
defm VFMADDSUBPD4 : fma4p<0x5D, "vfmaddsubpd", X86Fmaddsub, v2f64, v4f64,
|
|
loadv2f64, loadv4f64>;
|
|
defm VFMSUBADDPD4 : fma4p<0x5F, "vfmsubaddpd", X86Fmsubadd, v2f64, v4f64,
|
|
loadv2f64, loadv4f64>;
|
|
}
|
|
|