forked from OSchip/llvm-project
610 lines
31 KiB
TableGen
610 lines
31 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_* multiclasses
|
|
// 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).
|
|
|
|
multiclass fma3p_rm_213<bits<8> opc, string OpcodeStr, RegisterClass RC,
|
|
ValueType VT, X86MemOperand x86memop, PatFrag MemFrag,
|
|
SDNode Op, X86FoldableSchedWrite sched> {
|
|
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, (VT (Op RC:$src2, RC:$src1, RC:$src3)))]>,
|
|
Sched<[sched]>;
|
|
|
|
let mayLoad = 1 in
|
|
def m : FMA3<opc, MRMSrcMem, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, x86memop:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set RC:$dst, (VT (Op RC:$src2, RC:$src1,
|
|
(MemFrag addr:$src3))))]>,
|
|
Sched<[sched.Folded, ReadAfterLd, ReadAfterLd]>;
|
|
}
|
|
|
|
multiclass fma3p_rm_231<bits<8> opc, string OpcodeStr, RegisterClass RC,
|
|
ValueType VT, X86MemOperand x86memop, PatFrag MemFrag,
|
|
SDNode Op, X86FoldableSchedWrite sched> {
|
|
let hasSideEffects = 0 in
|
|
def r : FMA3<opc, MRMSrcReg, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, RC:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[]>, Sched<[sched]>;
|
|
|
|
let mayLoad = 1 in
|
|
def m : FMA3<opc, MRMSrcMem, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, x86memop:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set RC:$dst, (VT (Op RC:$src2, (MemFrag addr:$src3),
|
|
RC:$src1)))]>,
|
|
Sched<[sched.Folded, ReadAfterLd, ReadAfterLd]>;
|
|
}
|
|
|
|
multiclass fma3p_rm_132<bits<8> opc, string OpcodeStr, RegisterClass RC,
|
|
ValueType VT, X86MemOperand x86memop, PatFrag MemFrag,
|
|
SDNode Op, X86FoldableSchedWrite sched> {
|
|
let hasSideEffects = 0 in
|
|
def r : FMA3<opc, MRMSrcReg, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, RC:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[]>, Sched<[sched]>;
|
|
|
|
// Pattern is 312 order so that the load is in a different place from the
|
|
// 213 and 231 patterns this helps tablegen's duplicate pattern detection.
|
|
let mayLoad = 1 in
|
|
def m : FMA3<opc, MRMSrcMem, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, x86memop:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set RC:$dst, (VT (Op (MemFrag addr:$src3), RC:$src1,
|
|
RC:$src2)))]>,
|
|
Sched<[sched.Folded, ReadAfterLd, ReadAfterLd]>;
|
|
}
|
|
|
|
let Constraints = "$src1 = $dst", hasSideEffects = 0, isCommutable = 1 in
|
|
multiclass fma3p_forms<bits<8> opc132, bits<8> opc213, bits<8> opc231,
|
|
string OpcodeStr, string PackTy, string Suff,
|
|
PatFrag MemFrag128, PatFrag MemFrag256,
|
|
SDNode Op, ValueType OpTy128, ValueType OpTy256,
|
|
X86SchedWriteWidths sched> {
|
|
defm NAME#213#Suff : fma3p_rm_213<opc213, !strconcat(OpcodeStr, "213", PackTy),
|
|
VR128, OpTy128, f128mem, MemFrag128, Op, sched.XMM>;
|
|
defm NAME#231#Suff : fma3p_rm_231<opc231, !strconcat(OpcodeStr, "231", PackTy),
|
|
VR128, OpTy128, f128mem, MemFrag128, Op, sched.XMM>;
|
|
defm NAME#132#Suff : fma3p_rm_132<opc132, !strconcat(OpcodeStr, "132", PackTy),
|
|
VR128, OpTy128, f128mem, MemFrag128, Op, sched.XMM>;
|
|
|
|
defm NAME#213#Suff#Y : fma3p_rm_213<opc213, !strconcat(OpcodeStr, "213", PackTy),
|
|
VR256, OpTy256, f256mem, MemFrag256, Op, sched.YMM>,
|
|
VEX_L;
|
|
defm NAME#231#Suff#Y : fma3p_rm_231<opc231, !strconcat(OpcodeStr, "231", PackTy),
|
|
VR256, OpTy256, f256mem, MemFrag256, Op, sched.YMM>,
|
|
VEX_L;
|
|
defm NAME#132#Suff#Y : fma3p_rm_132<opc132, !strconcat(OpcodeStr, "132", PackTy),
|
|
VR256, OpTy256, f256mem, MemFrag256, Op, sched.YMM>,
|
|
VEX_L;
|
|
}
|
|
|
|
// Fused Multiply-Add
|
|
let ExeDomain = SSEPackedSingle in {
|
|
defm VFMADD : fma3p_forms<0x98, 0xA8, 0xB8, "vfmadd", "ps", "PS",
|
|
loadv4f32, loadv8f32, X86Fmadd, v4f32, v8f32,
|
|
SchedWriteFMA>;
|
|
defm VFMSUB : fma3p_forms<0x9A, 0xAA, 0xBA, "vfmsub", "ps", "PS",
|
|
loadv4f32, loadv8f32, X86Fmsub, v4f32, v8f32,
|
|
SchedWriteFMA>;
|
|
defm VFMADDSUB : fma3p_forms<0x96, 0xA6, 0xB6, "vfmaddsub", "ps", "PS",
|
|
loadv4f32, loadv8f32, X86Fmaddsub, v4f32, v8f32,
|
|
SchedWriteFMA>;
|
|
defm VFMSUBADD : fma3p_forms<0x97, 0xA7, 0xB7, "vfmsubadd", "ps", "PS",
|
|
loadv4f32, loadv8f32, X86Fmsubadd, v4f32, v8f32,
|
|
SchedWriteFMA>;
|
|
}
|
|
|
|
let ExeDomain = SSEPackedDouble in {
|
|
defm VFMADD : fma3p_forms<0x98, 0xA8, 0xB8, "vfmadd", "pd", "PD",
|
|
loadv2f64, loadv4f64, X86Fmadd, v2f64,
|
|
v4f64, SchedWriteFMA>, VEX_W;
|
|
defm VFMSUB : fma3p_forms<0x9A, 0xAA, 0xBA, "vfmsub", "pd", "PD",
|
|
loadv2f64, loadv4f64, X86Fmsub, v2f64,
|
|
v4f64, SchedWriteFMA>, VEX_W;
|
|
defm VFMADDSUB : fma3p_forms<0x96, 0xA6, 0xB6, "vfmaddsub", "pd", "PD",
|
|
loadv2f64, loadv4f64, X86Fmaddsub,
|
|
v2f64, v4f64, SchedWriteFMA>, VEX_W;
|
|
defm VFMSUBADD : fma3p_forms<0x97, 0xA7, 0xB7, "vfmsubadd", "pd", "PD",
|
|
loadv2f64, loadv4f64, X86Fmsubadd,
|
|
v2f64, v4f64, SchedWriteFMA>, VEX_W;
|
|
}
|
|
|
|
// Fused Negative Multiply-Add
|
|
let ExeDomain = SSEPackedSingle in {
|
|
defm VFNMADD : fma3p_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "ps", "PS", loadv4f32,
|
|
loadv8f32, X86Fnmadd, v4f32, v8f32, SchedWriteFMA>;
|
|
defm VFNMSUB : fma3p_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "ps", "PS", loadv4f32,
|
|
loadv8f32, X86Fnmsub, v4f32, v8f32, SchedWriteFMA>;
|
|
}
|
|
let ExeDomain = SSEPackedDouble in {
|
|
defm VFNMADD : fma3p_forms<0x9C, 0xAC, 0xBC, "vfnmadd", "pd", "PD", loadv2f64,
|
|
loadv4f64, X86Fnmadd, v2f64, v4f64, SchedWriteFMA>, VEX_W;
|
|
defm VFNMSUB : fma3p_forms<0x9E, 0xAE, 0xBE, "vfnmsub", "pd", "PD", loadv2f64,
|
|
loadv4f64, X86Fnmsub, v2f64, v4f64, SchedWriteFMA>, 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.
|
|
multiclass fma3s_rm_213<bits<8> opc, string OpcodeStr,
|
|
X86MemOperand x86memop, RegisterClass RC,
|
|
SDPatternOperator OpNode,
|
|
X86FoldableSchedWrite sched> {
|
|
def r : FMA3S<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:$src3))]>,
|
|
Sched<[sched]>;
|
|
|
|
let mayLoad = 1 in
|
|
def m : FMA3S<opc, MRMSrcMem, (outs RC:$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:$src3)))]>,
|
|
Sched<[sched.Folded, ReadAfterLd, ReadAfterLd]>;
|
|
}
|
|
|
|
multiclass fma3s_rm_231<bits<8> opc, string OpcodeStr,
|
|
X86MemOperand x86memop, RegisterClass RC,
|
|
SDPatternOperator OpNode, X86FoldableSchedWrite sched> {
|
|
let hasSideEffects = 0 in
|
|
def r : FMA3S<opc, MRMSrcReg, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, RC:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[]>, Sched<[sched]>;
|
|
|
|
let mayLoad = 1 in
|
|
def m : FMA3S<opc, MRMSrcMem, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, x86memop:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set RC:$dst,
|
|
(OpNode RC:$src2, (load addr:$src3), RC:$src1))]>,
|
|
Sched<[sched.Folded, ReadAfterLd, ReadAfterLd]>;
|
|
}
|
|
|
|
multiclass fma3s_rm_132<bits<8> opc, string OpcodeStr,
|
|
X86MemOperand x86memop, RegisterClass RC,
|
|
SDPatternOperator OpNode, X86FoldableSchedWrite sched> {
|
|
let hasSideEffects = 0 in
|
|
def r : FMA3S<opc, MRMSrcReg, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, RC:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[]>, Sched<[sched]>;
|
|
|
|
// Pattern is 312 order so that the load is in a different place from the
|
|
// 213 and 231 patterns this helps tablegen's duplicate pattern detection.
|
|
let mayLoad = 1 in
|
|
def m : FMA3S<opc, MRMSrcMem, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, x86memop:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[(set RC:$dst,
|
|
(OpNode (load addr:$src3), RC:$src1, RC:$src2))]>,
|
|
Sched<[sched.Folded, ReadAfterLd, ReadAfterLd]>;
|
|
}
|
|
|
|
let Constraints = "$src1 = $dst", isCommutable = 1, hasSideEffects = 0 in
|
|
multiclass fma3s_forms<bits<8> opc132, bits<8> opc213, bits<8> opc231,
|
|
string OpStr, string PackTy, string Suff,
|
|
SDNode OpNode, RegisterClass RC,
|
|
X86MemOperand x86memop, X86FoldableSchedWrite sched> {
|
|
defm NAME#213#Suff : fma3s_rm_213<opc213, !strconcat(OpStr, "213", PackTy),
|
|
x86memop, RC, OpNode, sched>;
|
|
defm NAME#231#Suff : fma3s_rm_231<opc231, !strconcat(OpStr, "231", PackTy),
|
|
x86memop, RC, OpNode, sched>;
|
|
defm NAME#132#Suff : fma3s_rm_132<opc132, !strconcat(OpStr, "132", PackTy),
|
|
x86memop, RC, OpNode, sched>;
|
|
}
|
|
|
|
// These FMA*_Int instructions are defined specially for being used when
|
|
// the scalar FMA intrinsics are lowered to machine instructions, and in that
|
|
// sense, they are similar to existing ADD*_Int, SUB*_Int, MUL*_Int, etc.
|
|
// instructions.
|
|
//
|
|
// All of the FMA*_Int opcodes are defined as commutable here.
|
|
// Commuting the 2nd and 3rd source register operands of FMAs is quite trivial
|
|
// and the corresponding optimizations have been developed.
|
|
// Commuting the 1st operand of FMA*_Int requires some additional analysis,
|
|
// the commute optimization is legal only if all users of FMA*_Int use only
|
|
// the lowest element of the FMA*_Int instruction. Even though such analysis
|
|
// may be not implemented yet we allow the routines doing the actual commute
|
|
// transformation to decide if one or another instruction is commutable or not.
|
|
let Constraints = "$src1 = $dst", isCommutable = 1, isCodeGenOnly = 1,
|
|
hasSideEffects = 0 in
|
|
multiclass fma3s_rm_int<bits<8> opc, string OpcodeStr,
|
|
Operand memopr, RegisterClass RC,
|
|
X86FoldableSchedWrite sched> {
|
|
def r_Int : FMA3S_Int<opc, MRMSrcReg, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, RC:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[]>, Sched<[sched]>;
|
|
|
|
let mayLoad = 1 in
|
|
def m_Int : FMA3S_Int<opc, MRMSrcMem, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, memopr:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
|
|
[]>, Sched<[sched.Folded, ReadAfterLd, ReadAfterLd]>;
|
|
}
|
|
|
|
// 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, string Suff,
|
|
RegisterClass RC, Operand memop,
|
|
X86FoldableSchedWrite sched> {
|
|
defm NAME#132#Suff : fma3s_rm_int<opc132, !strconcat(OpStr, "132", PackTy),
|
|
memop, RC, sched>;
|
|
defm NAME#213#Suff : fma3s_rm_int<opc213, !strconcat(OpStr, "213", PackTy),
|
|
memop, RC, sched>;
|
|
defm NAME#231#Suff : fma3s_rm_int<opc231, !strconcat(OpStr, "231", PackTy),
|
|
memop, RC, sched>;
|
|
}
|
|
|
|
multiclass fma3s<bits<8> opc132, bits<8> opc213, bits<8> opc231,
|
|
string OpStr, SDNode OpNodeIntrin, SDNode OpNode,
|
|
X86FoldableSchedWrite sched> {
|
|
let ExeDomain = SSEPackedSingle in
|
|
defm NAME : fma3s_forms<opc132, opc213, opc231, OpStr, "ss", "SS", OpNode,
|
|
FR32, f32mem, sched>,
|
|
fma3s_int_forms<opc132, opc213, opc231, OpStr, "ss", "SS",
|
|
VR128, ssmem, sched>;
|
|
|
|
let ExeDomain = SSEPackedDouble in
|
|
defm NAME : fma3s_forms<opc132, opc213, opc231, OpStr, "sd", "SD", OpNode,
|
|
FR64, f64mem, sched>,
|
|
fma3s_int_forms<opc132, opc213, opc231, OpStr, "sd", "SD",
|
|
VR128, sdmem, sched>, 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.
|
|
let Predicates = [HasFMA, NoAVX512] in {
|
|
def : Pat<(v4f32 (OpNodeIntrin VR128:$src1, VR128:$src2, VR128:$src3)),
|
|
(!cast<Instruction>(NAME#"213SSr_Int")
|
|
VR128:$src1, VR128:$src2, VR128:$src3)>;
|
|
|
|
def : Pat<(v2f64 (OpNodeIntrin VR128:$src1, VR128:$src2, VR128:$src3)),
|
|
(!cast<Instruction>(NAME#"213SDr_Int")
|
|
VR128:$src1, VR128:$src2, VR128:$src3)>;
|
|
|
|
def : Pat<(v4f32 (OpNodeIntrin VR128:$src1, VR128:$src2,
|
|
sse_load_f32:$src3)),
|
|
(!cast<Instruction>(NAME#"213SSm_Int")
|
|
VR128:$src1, VR128:$src2, sse_load_f32:$src3)>;
|
|
|
|
def : Pat<(v2f64 (OpNodeIntrin VR128:$src1, VR128:$src2,
|
|
sse_load_f64:$src3)),
|
|
(!cast<Instruction>(NAME#"213SDm_Int")
|
|
VR128:$src1, VR128:$src2, sse_load_f64:$src3)>;
|
|
|
|
def : Pat<(v4f32 (OpNodeIntrin VR128:$src1, sse_load_f32:$src3,
|
|
VR128:$src2)),
|
|
(!cast<Instruction>(NAME#"132SSm_Int")
|
|
VR128:$src1, VR128:$src2, sse_load_f32:$src3)>;
|
|
|
|
def : Pat<(v2f64 (OpNodeIntrin VR128:$src1, sse_load_f64:$src3,
|
|
VR128:$src2)),
|
|
(!cast<Instruction>(NAME#"132SDm_Int")
|
|
VR128:$src1, VR128:$src2, sse_load_f64:$src3)>;
|
|
}
|
|
}
|
|
|
|
defm VFMADD : fma3s<0x99, 0xA9, 0xB9, "vfmadd", X86Fmadds1, X86Fmadd,
|
|
SchedWriteFMA.Scl>, VEX_LIG;
|
|
defm VFMSUB : fma3s<0x9B, 0xAB, 0xBB, "vfmsub", X86Fmsubs1, X86Fmsub,
|
|
SchedWriteFMA.Scl>, VEX_LIG;
|
|
|
|
defm VFNMADD : fma3s<0x9D, 0xAD, 0xBD, "vfnmadd", X86Fnmadds1, X86Fnmadd,
|
|
SchedWriteFMA.Scl>, VEX_LIG;
|
|
defm VFNMSUB : fma3s<0x9F, 0xAF, 0xBF, "vfnmsub", X86Fnmsubs1, X86Fnmsub,
|
|
SchedWriteFMA.Scl>, VEX_LIG;
|
|
|
|
multiclass scalar_fma_patterns<SDNode Op, string Prefix, string Suffix, SDNode Move,
|
|
ValueType VT, ValueType EltVT> {
|
|
let Predicates = [HasFMA, NoAVX512] in {
|
|
def : Pat<(VT (Move (VT VR128:$src2), (VT (scalar_to_vector
|
|
(Op (EltVT (extractelt (VT VR128:$src1), (iPTR 0))),
|
|
(EltVT (extractelt (VT VR128:$src2), (iPTR 0))),
|
|
(EltVT (extractelt (VT VR128:$src3), (iPTR 0)))))))),
|
|
(!cast<I>(Prefix#"213"#Suffix#"r_Int")
|
|
VR128:$src2, VR128:$src1, VR128:$src3)>;
|
|
}
|
|
}
|
|
|
|
defm : scalar_fma_patterns<X86Fmadd, "VFMADD", "SS", X86Movss, v4f32, f32>;
|
|
defm : scalar_fma_patterns<X86Fmsub, "VFMSUB", "SS", X86Movss, v4f32, f32>;
|
|
defm : scalar_fma_patterns<X86Fnmadd, "VFNMADD", "SS", X86Movss, v4f32, f32>;
|
|
defm : scalar_fma_patterns<X86Fnmsub, "VFNMSUB", "SS", X86Movss, v4f32, f32>;
|
|
|
|
defm : scalar_fma_patterns<X86Fmadd, "VFMADD", "SD", X86Movsd, v2f64, f64>;
|
|
defm : scalar_fma_patterns<X86Fmsub, "VFMSUB", "SD", X86Movsd, v2f64, f64>;
|
|
defm : scalar_fma_patterns<X86Fnmadd, "VFNMADD", "SD", X86Movsd, v2f64, f64>;
|
|
defm : scalar_fma_patterns<X86Fnmsub, "VFNMSUB", "SD", X86Movsd, v2f64, f64>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// 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, X86FoldableSchedWrite sched> {
|
|
let isCommutable = 1 in
|
|
def rr : FMA4S<opc, MRMSrcRegOp4, (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:$src3)))]>, VEX_W, VEX_LIG,
|
|
Sched<[sched]>;
|
|
def rm : FMA4S<opc, MRMSrcMemOp4, (outs RC:$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:$src3)))]>, VEX_W, VEX_LIG,
|
|
Sched<[sched.Folded, ReadAfterLd, ReadAfterLd]>;
|
|
def mr : FMA4S<opc, MRMSrcMem, (outs RC:$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:$src3))]>, VEX_LIG,
|
|
Sched<[sched.Folded, ReadAfterLd,
|
|
// x86memop:$src2
|
|
ReadDefault, ReadDefault, ReadDefault, ReadDefault,
|
|
ReadDefault,
|
|
// RC:$src3
|
|
ReadAfterLd]>;
|
|
// For disassembler
|
|
let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in
|
|
def rr_REV : FMA4S<opc, MRMSrcReg, (outs RC:$dst),
|
|
(ins RC:$src1, RC:$src2, RC:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"), []>,
|
|
VEX_LIG, FoldGenData<NAME#rr>, Sched<[sched]>;
|
|
}
|
|
|
|
multiclass fma4s_int<bits<8> opc, string OpcodeStr, Operand memop,
|
|
ValueType VT, ComplexPattern mem_cpat, SDNode OpNode,
|
|
X86FoldableSchedWrite sched> {
|
|
let isCodeGenOnly = 1 in {
|
|
def rr_Int : FMA4S_Int<opc, MRMSrcRegOp4, (outs VR128:$dst),
|
|
(ins VR128:$src1, VR128:$src2, VR128:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set VR128:$dst,
|
|
(VT (OpNode VR128:$src1, VR128:$src2, VR128:$src3)))]>, VEX_W,
|
|
VEX_LIG, Sched<[sched]>;
|
|
def rm_Int : FMA4S_Int<opc, MRMSrcMemOp4, (outs VR128:$dst),
|
|
(ins VR128:$src1, VR128:$src2, memop:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set VR128:$dst, (VT (OpNode VR128:$src1, VR128:$src2,
|
|
mem_cpat:$src3)))]>, VEX_W, VEX_LIG,
|
|
Sched<[sched.Folded, ReadAfterLd, ReadAfterLd]>;
|
|
def mr_Int : FMA4S_Int<opc, MRMSrcMem, (outs VR128:$dst),
|
|
(ins VR128:$src1, memop:$src2, VR128:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[(set VR128:$dst,
|
|
(VT (OpNode VR128:$src1, mem_cpat:$src2, VR128:$src3)))]>,
|
|
VEX_LIG, Sched<[sched.Folded, ReadAfterLd,
|
|
// memop:$src2
|
|
ReadDefault, ReadDefault, ReadDefault,
|
|
ReadDefault, ReadDefault,
|
|
// VR128::$src3
|
|
ReadAfterLd]>;
|
|
let hasSideEffects = 0 in
|
|
def rr_Int_REV : FMA4S_Int<opc, MRMSrcReg, (outs VR128:$dst),
|
|
(ins VR128:$src1, VR128:$src2, VR128:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
|
|
[]>, VEX_LIG, FoldGenData<NAME#rr_Int>, Sched<[sched]>;
|
|
} // isCodeGenOnly = 1
|
|
}
|
|
|
|
multiclass fma4p<bits<8> opc, string OpcodeStr, SDNode OpNode,
|
|
ValueType OpVT128, ValueType OpVT256,
|
|
PatFrag ld_frag128, PatFrag ld_frag256,
|
|
X86SchedWriteWidths sched> {
|
|
let isCommutable = 1 in
|
|
def rr : FMA4<opc, MRMSrcRegOp4, (outs VR128:$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:$src3)))]>,
|
|
VEX_W, Sched<[sched.XMM]>;
|
|
def rm : FMA4<opc, MRMSrcMemOp4, (outs VR128:$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:$src3)))]>, VEX_W,
|
|
Sched<[sched.XMM.Folded, ReadAfterLd, ReadAfterLd]>;
|
|
def mr : FMA4<opc, MRMSrcMem, (outs VR128:$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:$src3))]>,
|
|
Sched<[sched.XMM.Folded, ReadAfterLd,
|
|
// f128mem:$src2
|
|
ReadDefault, ReadDefault, ReadDefault, ReadDefault,
|
|
ReadDefault,
|
|
// VR128::$src3
|
|
ReadAfterLd]>;
|
|
let isCommutable = 1 in
|
|
def Yrr : FMA4<opc, MRMSrcRegOp4, (outs VR256:$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:$src3)))]>,
|
|
VEX_W, VEX_L, Sched<[sched.YMM]>;
|
|
def Yrm : FMA4<opc, MRMSrcMemOp4, (outs VR256:$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:$src3)))]>, VEX_W, VEX_L,
|
|
Sched<[sched.YMM.Folded, ReadAfterLd, ReadAfterLd]>;
|
|
def Ymr : FMA4<opc, MRMSrcMem, (outs VR256:$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:$src3))]>, VEX_L,
|
|
Sched<[sched.YMM.Folded, ReadAfterLd,
|
|
// f256mem:$src2
|
|
ReadDefault, ReadDefault, ReadDefault, ReadDefault,
|
|
ReadDefault,
|
|
// VR256::$src3
|
|
ReadAfterLd]>;
|
|
// For disassembler
|
|
let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in {
|
|
def rr_REV : FMA4<opc, MRMSrcReg, (outs VR128:$dst),
|
|
(ins VR128:$src1, VR128:$src2, VR128:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"), []>,
|
|
Sched<[sched.XMM]>, FoldGenData<NAME#rr>;
|
|
def Yrr_REV : FMA4<opc, MRMSrcReg, (outs VR256:$dst),
|
|
(ins VR256:$src1, VR256:$src2, VR256:$src3),
|
|
!strconcat(OpcodeStr,
|
|
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"), []>,
|
|
VEX_L, Sched<[sched.YMM]>, FoldGenData<NAME#Yrr>;
|
|
} // isCodeGenOnly = 1
|
|
}
|
|
|
|
let ExeDomain = SSEPackedSingle in {
|
|
// Scalar Instructions
|
|
defm VFMADDSS4 : fma4s<0x6A, "vfmaddss", FR32, f32mem, f32, X86Fmadd, loadf32,
|
|
SchedWriteFMA.Scl>,
|
|
fma4s_int<0x6A, "vfmaddss", ssmem, v4f32, sse_load_f32,
|
|
X86Fmadd4s, SchedWriteFMA.Scl>;
|
|
defm VFMSUBSS4 : fma4s<0x6E, "vfmsubss", FR32, f32mem, f32, X86Fmsub, loadf32,
|
|
SchedWriteFMA.Scl>,
|
|
fma4s_int<0x6E, "vfmsubss", ssmem, v4f32, sse_load_f32,
|
|
X86Fmsub4s, SchedWriteFMA.Scl>;
|
|
defm VFNMADDSS4 : fma4s<0x7A, "vfnmaddss", FR32, f32mem, f32,
|
|
X86Fnmadd, loadf32, SchedWriteFMA.Scl>,
|
|
fma4s_int<0x7A, "vfnmaddss", ssmem, v4f32, sse_load_f32,
|
|
X86Fnmadd4s, SchedWriteFMA.Scl>;
|
|
defm VFNMSUBSS4 : fma4s<0x7E, "vfnmsubss", FR32, f32mem, f32,
|
|
X86Fnmsub, loadf32, SchedWriteFMA.Scl>,
|
|
fma4s_int<0x7E, "vfnmsubss", ssmem, v4f32, sse_load_f32,
|
|
X86Fnmsub4s, SchedWriteFMA.Scl>;
|
|
// Packed Instructions
|
|
defm VFMADDPS4 : fma4p<0x68, "vfmaddps", X86Fmadd, v4f32, v8f32,
|
|
loadv4f32, loadv8f32, SchedWriteFMA>;
|
|
defm VFMSUBPS4 : fma4p<0x6C, "vfmsubps", X86Fmsub, v4f32, v8f32,
|
|
loadv4f32, loadv8f32, SchedWriteFMA>;
|
|
defm VFNMADDPS4 : fma4p<0x78, "vfnmaddps", X86Fnmadd, v4f32, v8f32,
|
|
loadv4f32, loadv8f32, SchedWriteFMA>;
|
|
defm VFNMSUBPS4 : fma4p<0x7C, "vfnmsubps", X86Fnmsub, v4f32, v8f32,
|
|
loadv4f32, loadv8f32, SchedWriteFMA>;
|
|
defm VFMADDSUBPS4 : fma4p<0x5C, "vfmaddsubps", X86Fmaddsub, v4f32, v8f32,
|
|
loadv4f32, loadv8f32, SchedWriteFMA>;
|
|
defm VFMSUBADDPS4 : fma4p<0x5E, "vfmsubaddps", X86Fmsubadd, v4f32, v8f32,
|
|
loadv4f32, loadv8f32, SchedWriteFMA>;
|
|
}
|
|
|
|
let ExeDomain = SSEPackedDouble in {
|
|
// Scalar Instructions
|
|
defm VFMADDSD4 : fma4s<0x6B, "vfmaddsd", FR64, f64mem, f64, X86Fmadd, loadf64,
|
|
SchedWriteFMA.Scl>,
|
|
fma4s_int<0x6B, "vfmaddsd", sdmem, v2f64, sse_load_f64,
|
|
X86Fmadd4s, SchedWriteFMA.Scl>;
|
|
defm VFMSUBSD4 : fma4s<0x6F, "vfmsubsd", FR64, f64mem, f64, X86Fmsub, loadf64,
|
|
SchedWriteFMA.Scl>,
|
|
fma4s_int<0x6F, "vfmsubsd", sdmem, v2f64, sse_load_f64,
|
|
X86Fmsub4s, SchedWriteFMA.Scl>;
|
|
defm VFNMADDSD4 : fma4s<0x7B, "vfnmaddsd", FR64, f64mem, f64,
|
|
X86Fnmadd, loadf64, SchedWriteFMA.Scl>,
|
|
fma4s_int<0x7B, "vfnmaddsd", sdmem, v2f64, sse_load_f64,
|
|
X86Fnmadd4s, SchedWriteFMA.Scl>;
|
|
defm VFNMSUBSD4 : fma4s<0x7F, "vfnmsubsd", FR64, f64mem, f64,
|
|
X86Fnmsub, loadf64, SchedWriteFMA.Scl>,
|
|
fma4s_int<0x7F, "vfnmsubsd", sdmem, v2f64, sse_load_f64,
|
|
X86Fnmsub4s, SchedWriteFMA.Scl>;
|
|
// Packed Instructions
|
|
defm VFMADDPD4 : fma4p<0x69, "vfmaddpd", X86Fmadd, v2f64, v4f64,
|
|
loadv2f64, loadv4f64, SchedWriteFMA>;
|
|
defm VFMSUBPD4 : fma4p<0x6D, "vfmsubpd", X86Fmsub, v2f64, v4f64,
|
|
loadv2f64, loadv4f64, SchedWriteFMA>;
|
|
defm VFNMADDPD4 : fma4p<0x79, "vfnmaddpd", X86Fnmadd, v2f64, v4f64,
|
|
loadv2f64, loadv4f64, SchedWriteFMA>;
|
|
defm VFNMSUBPD4 : fma4p<0x7D, "vfnmsubpd", X86Fnmsub, v2f64, v4f64,
|
|
loadv2f64, loadv4f64, SchedWriteFMA>;
|
|
defm VFMADDSUBPD4 : fma4p<0x5D, "vfmaddsubpd", X86Fmaddsub, v2f64, v4f64,
|
|
loadv2f64, loadv4f64, SchedWriteFMA>;
|
|
defm VFMSUBADDPD4 : fma4p<0x5F, "vfmsubaddpd", X86Fmsubadd, v2f64, v4f64,
|
|
loadv2f64, loadv4f64, SchedWriteFMA>;
|
|
}
|
|
|