forked from OSchip/llvm-project
269 lines
9.2 KiB
TableGen
269 lines
9.2 KiB
TableGen
//===-- AMDGPUInstructions.td - Common instruction defs ---*- tablegen -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file contains instruction defs that are common to all hw codegen
|
|
// targets.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class AMDGPUInst <dag outs, dag ins, string asm, list<dag> pattern> : Instruction {
|
|
field bit isRegisterLoad = 0;
|
|
field bit isRegisterStore = 0;
|
|
|
|
let Namespace = "AMDGPU";
|
|
let OutOperandList = outs;
|
|
let InOperandList = ins;
|
|
let AsmString = asm;
|
|
let Pattern = pattern;
|
|
let Itinerary = NullALU;
|
|
|
|
let TSFlags{63} = isRegisterLoad;
|
|
let TSFlags{62} = isRegisterStore;
|
|
}
|
|
|
|
class AMDGPUShaderInst <dag outs, dag ins, string asm, list<dag> pattern>
|
|
: AMDGPUInst<outs, ins, asm, pattern> {
|
|
|
|
field bits<32> Inst = 0xffffffff;
|
|
|
|
}
|
|
|
|
def InstFlag : OperandWithDefaultOps <i32, (ops (i32 0))>;
|
|
|
|
def COND_EQ : PatLeaf <
|
|
(cond),
|
|
[{switch(N->get()){{default: return false;
|
|
case ISD::SETOEQ: case ISD::SETUEQ:
|
|
case ISD::SETEQ: return true;}}}]
|
|
>;
|
|
|
|
def COND_NE : PatLeaf <
|
|
(cond),
|
|
[{switch(N->get()){{default: return false;
|
|
case ISD::SETONE: case ISD::SETUNE:
|
|
case ISD::SETNE: return true;}}}]
|
|
>;
|
|
def COND_GT : PatLeaf <
|
|
(cond),
|
|
[{switch(N->get()){{default: return false;
|
|
case ISD::SETOGT: case ISD::SETUGT:
|
|
case ISD::SETGT: return true;}}}]
|
|
>;
|
|
|
|
def COND_GE : PatLeaf <
|
|
(cond),
|
|
[{switch(N->get()){{default: return false;
|
|
case ISD::SETOGE: case ISD::SETUGE:
|
|
case ISD::SETGE: return true;}}}]
|
|
>;
|
|
|
|
def COND_LT : PatLeaf <
|
|
(cond),
|
|
[{switch(N->get()){{default: return false;
|
|
case ISD::SETOLT: case ISD::SETULT:
|
|
case ISD::SETLT: return true;}}}]
|
|
>;
|
|
|
|
def COND_LE : PatLeaf <
|
|
(cond),
|
|
[{switch(N->get()){{default: return false;
|
|
case ISD::SETOLE: case ISD::SETULE:
|
|
case ISD::SETLE: return true;}}}]
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Load/Store Pattern Fragments
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def zextloadi8_global : PatFrag<(ops node:$ptr), (zextloadi8 node:$ptr), [{
|
|
return isGlobalLoad(dyn_cast<LoadSDNode>(N));
|
|
}]>;
|
|
|
|
class Constants {
|
|
int TWO_PI = 0x40c90fdb;
|
|
int PI = 0x40490fdb;
|
|
int TWO_PI_INV = 0x3e22f983;
|
|
}
|
|
def CONST : Constants;
|
|
|
|
def FP_ZERO : PatLeaf <
|
|
(fpimm),
|
|
[{return N->getValueAPF().isZero();}]
|
|
>;
|
|
|
|
def FP_ONE : PatLeaf <
|
|
(fpimm),
|
|
[{return N->isExactlyValue(1.0);}]
|
|
>;
|
|
|
|
let isCodeGenOnly = 1, isPseudo = 1 in {
|
|
|
|
let usesCustomInserter = 1 in {
|
|
|
|
class CLAMP <RegisterClass rc> : AMDGPUShaderInst <
|
|
(outs rc:$dst),
|
|
(ins rc:$src0),
|
|
"CLAMP $dst, $src0",
|
|
[(set rc:$dst, (int_AMDIL_clamp rc:$src0, (f32 FP_ZERO), (f32 FP_ONE)))]
|
|
>;
|
|
|
|
class FABS <RegisterClass rc> : AMDGPUShaderInst <
|
|
(outs rc:$dst),
|
|
(ins rc:$src0),
|
|
"FABS $dst, $src0",
|
|
[(set rc:$dst, (fabs rc:$src0))]
|
|
>;
|
|
|
|
class FNEG <RegisterClass rc> : AMDGPUShaderInst <
|
|
(outs rc:$dst),
|
|
(ins rc:$src0),
|
|
"FNEG $dst, $src0",
|
|
[(set rc:$dst, (fneg rc:$src0))]
|
|
>;
|
|
|
|
def SHADER_TYPE : AMDGPUShaderInst <
|
|
(outs),
|
|
(ins i32imm:$type),
|
|
"SHADER_TYPE $type",
|
|
[(int_AMDGPU_shader_type imm:$type)]
|
|
>;
|
|
|
|
} // usesCustomInserter = 1
|
|
|
|
multiclass RegisterLoadStore <RegisterClass dstClass, Operand addrClass,
|
|
ComplexPattern addrPat> {
|
|
def RegisterLoad : AMDGPUShaderInst <
|
|
(outs dstClass:$dst),
|
|
(ins addrClass:$addr, i32imm:$chan),
|
|
"RegisterLoad $dst, $addr",
|
|
[(set (i32 dstClass:$dst), (AMDGPUregister_load addrPat:$addr,
|
|
(i32 timm:$chan)))]
|
|
> {
|
|
let isRegisterLoad = 1;
|
|
}
|
|
|
|
def RegisterStore : AMDGPUShaderInst <
|
|
(outs),
|
|
(ins dstClass:$val, addrClass:$addr, i32imm:$chan),
|
|
"RegisterStore $val, $addr",
|
|
[(AMDGPUregister_store (i32 dstClass:$val), addrPat:$addr, (i32 timm:$chan))]
|
|
> {
|
|
let isRegisterStore = 1;
|
|
}
|
|
}
|
|
|
|
} // End isCodeGenOnly = 1, isPseudo = 1
|
|
|
|
/* Generic helper patterns for intrinsics */
|
|
/* -------------------------------------- */
|
|
|
|
class POW_Common <AMDGPUInst log_ieee, AMDGPUInst exp_ieee, AMDGPUInst mul,
|
|
RegisterClass rc> : Pat <
|
|
(fpow rc:$src0, rc:$src1),
|
|
(exp_ieee (mul rc:$src1, (log_ieee rc:$src0)))
|
|
>;
|
|
|
|
/* Other helper patterns */
|
|
/* --------------------- */
|
|
|
|
/* Extract element pattern */
|
|
class Extract_Element <ValueType sub_type, ValueType vec_type,
|
|
RegisterClass vec_class, int sub_idx,
|
|
SubRegIndex sub_reg>: Pat<
|
|
(sub_type (vector_extract (vec_type vec_class:$src), sub_idx)),
|
|
(EXTRACT_SUBREG vec_class:$src, sub_reg)
|
|
>;
|
|
|
|
/* Insert element pattern */
|
|
class Insert_Element <ValueType elem_type, ValueType vec_type,
|
|
RegisterClass elem_class, RegisterClass vec_class,
|
|
int sub_idx, SubRegIndex sub_reg> : Pat <
|
|
|
|
(vec_type (vector_insert (vec_type vec_class:$vec),
|
|
(elem_type elem_class:$elem), sub_idx)),
|
|
(INSERT_SUBREG vec_class:$vec, elem_class:$elem, sub_reg)
|
|
>;
|
|
|
|
// Vector Build pattern
|
|
class Vector1_Build <ValueType vecType, RegisterClass vectorClass,
|
|
ValueType elemType, RegisterClass elemClass> : Pat <
|
|
(vecType (build_vector (elemType elemClass:$src))),
|
|
(vecType elemClass:$src)
|
|
>;
|
|
|
|
class Vector2_Build <ValueType vecType, RegisterClass vectorClass,
|
|
ValueType elemType, RegisterClass elemClass> : Pat <
|
|
(vecType (build_vector (elemType elemClass:$sub0), (elemType elemClass:$sub1))),
|
|
(INSERT_SUBREG (INSERT_SUBREG
|
|
(vecType (IMPLICIT_DEF)), elemClass:$sub0, sub0), elemClass:$sub1, sub1)
|
|
>;
|
|
|
|
class Vector_Build <ValueType vecType, RegisterClass vectorClass,
|
|
ValueType elemType, RegisterClass elemClass> : Pat <
|
|
(vecType (build_vector (elemType elemClass:$x), (elemType elemClass:$y),
|
|
(elemType elemClass:$z), (elemType elemClass:$w))),
|
|
(INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG
|
|
(vecType (IMPLICIT_DEF)), elemClass:$x, sub0), elemClass:$y, sub1),
|
|
elemClass:$z, sub2), elemClass:$w, sub3)
|
|
>;
|
|
|
|
class Vector8_Build <ValueType vecType, RegisterClass vectorClass,
|
|
ValueType elemType, RegisterClass elemClass> : Pat <
|
|
(vecType (build_vector (elemType elemClass:$sub0), (elemType elemClass:$sub1),
|
|
(elemType elemClass:$sub2), (elemType elemClass:$sub3),
|
|
(elemType elemClass:$sub4), (elemType elemClass:$sub5),
|
|
(elemType elemClass:$sub6), (elemType elemClass:$sub7))),
|
|
(INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG
|
|
(INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG
|
|
(vecType (IMPLICIT_DEF)), elemClass:$sub0, sub0), elemClass:$sub1, sub1),
|
|
elemClass:$sub2, sub2), elemClass:$sub3, sub3),
|
|
elemClass:$sub4, sub4), elemClass:$sub5, sub5),
|
|
elemClass:$sub6, sub6), elemClass:$sub7, sub7)
|
|
>;
|
|
|
|
class Vector16_Build <ValueType vecType, RegisterClass vectorClass,
|
|
ValueType elemType, RegisterClass elemClass> : Pat <
|
|
(vecType (build_vector (elemType elemClass:$sub0), (elemType elemClass:$sub1),
|
|
(elemType elemClass:$sub2), (elemType elemClass:$sub3),
|
|
(elemType elemClass:$sub4), (elemType elemClass:$sub5),
|
|
(elemType elemClass:$sub6), (elemType elemClass:$sub7),
|
|
(elemType elemClass:$sub8), (elemType elemClass:$sub9),
|
|
(elemType elemClass:$sub10), (elemType elemClass:$sub11),
|
|
(elemType elemClass:$sub12), (elemType elemClass:$sub13),
|
|
(elemType elemClass:$sub14), (elemType elemClass:$sub15))),
|
|
(INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG
|
|
(INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG
|
|
(INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG
|
|
(INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG
|
|
(vecType (IMPLICIT_DEF)), elemClass:$sub0, sub0), elemClass:$sub1, sub1),
|
|
elemClass:$sub2, sub2), elemClass:$sub3, sub3),
|
|
elemClass:$sub4, sub4), elemClass:$sub5, sub5),
|
|
elemClass:$sub6, sub6), elemClass:$sub7, sub7),
|
|
elemClass:$sub8, sub8), elemClass:$sub9, sub9),
|
|
elemClass:$sub10, sub10), elemClass:$sub11, sub11),
|
|
elemClass:$sub12, sub12), elemClass:$sub13, sub13),
|
|
elemClass:$sub14, sub14), elemClass:$sub15, sub15)
|
|
>;
|
|
|
|
// bitconvert pattern
|
|
class BitConvert <ValueType dt, ValueType st, RegisterClass rc> : Pat <
|
|
(dt (bitconvert (st rc:$src0))),
|
|
(dt rc:$src0)
|
|
>;
|
|
|
|
class DwordAddrPat<ValueType vt, RegisterClass rc> : Pat <
|
|
(vt (AMDGPUdwordaddr (vt rc:$addr))),
|
|
(vt rc:$addr)
|
|
>;
|
|
|
|
include "R600Instructions.td"
|
|
|
|
include "SIInstrInfo.td"
|
|
|