forked from OSchip/llvm-project
225 lines
7.3 KiB
TableGen
225 lines
7.3 KiB
TableGen
//===-- CaymanInstructions.td - CM Instruction defs -------*- tablegen -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// TableGen definitions for instructions which are available only on Cayman
|
|
// family GPUs.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def isCayman : Predicate<"Subtarget.hasCaymanISA()">;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Cayman Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let Predicates = [isCayman] in {
|
|
|
|
def MULADD_INT24_cm : R600_3OP <0x08, "MULADD_INT24",
|
|
[(set i32:$dst, (AMDGPUmad_i24 i32:$src0, i32:$src1, i32:$src2))], VecALU
|
|
>;
|
|
def MUL_INT24_cm : R600_2OP <0x5B, "MUL_INT24",
|
|
[(set i32:$dst, (AMDGPUmul_i24 i32:$src0, i32:$src1))], VecALU
|
|
>;
|
|
|
|
def : IMad24Pat<MULADD_INT24_cm>;
|
|
|
|
let isVector = 1 in {
|
|
|
|
def RECIP_IEEE_cm : RECIP_IEEE_Common<0x86>;
|
|
|
|
def MULLO_INT_cm : MULLO_INT_Common<0x8F>;
|
|
def MULHI_INT_cm : MULHI_INT_Common<0x90>;
|
|
def MULLO_UINT_cm : MULLO_UINT_Common<0x91>;
|
|
def MULHI_UINT_cm : MULHI_UINT_Common<0x92>;
|
|
def RECIPSQRT_CLAMPED_cm : RECIPSQRT_CLAMPED_Common<0x87>;
|
|
def EXP_IEEE_cm : EXP_IEEE_Common<0x81>;
|
|
def LOG_IEEE_cm : LOG_IEEE_Common<0x83>;
|
|
def RECIP_CLAMPED_cm : RECIP_CLAMPED_Common<0x84>;
|
|
def RECIPSQRT_IEEE_cm : RECIPSQRT_IEEE_Common<0x89>;
|
|
def SIN_cm : SIN_Common<0x8D>;
|
|
def COS_cm : COS_Common<0x8E>;
|
|
} // End isVector = 1
|
|
|
|
def : POW_Common <LOG_IEEE_cm, EXP_IEEE_cm, MUL>;
|
|
|
|
defm DIV_cm : DIV_Common<RECIP_IEEE_cm>;
|
|
defm : Expand24UBitOps<MULLO_UINT_cm, ADD_INT>;
|
|
|
|
// RECIP_UINT emulation for Cayman
|
|
// The multiplication scales from [0,1] to the unsigned integer range
|
|
def : Pat <
|
|
(AMDGPUurecip i32:$src0),
|
|
(FLT_TO_UINT_eg (MUL_IEEE (RECIP_IEEE_cm (UINT_TO_FLT_eg $src0)),
|
|
(MOV_IMM_I32 CONST.FP_UINT_MAX_PLUS_1)))
|
|
>;
|
|
|
|
def CF_END_CM : CF_CLAUSE_EG<32, (ins), "CF_END"> {
|
|
let ADDR = 0;
|
|
let POP_COUNT = 0;
|
|
let COUNT = 0;
|
|
}
|
|
|
|
|
|
def : Pat<(fsqrt f32:$src), (MUL R600_Reg32:$src, (RECIPSQRT_CLAMPED_cm $src))>;
|
|
|
|
class RAT_STORE_DWORD <RegisterClass rc, ValueType vt, bits<4> mask> :
|
|
CF_MEM_RAT_CACHELESS <0x14, 0, mask,
|
|
(ins rc:$rw_gpr, R600_TReg32_X:$index_gpr),
|
|
"STORE_DWORD $rw_gpr, $index_gpr",
|
|
[(global_store vt:$rw_gpr, i32:$index_gpr)]> {
|
|
let eop = 0; // This bit is not used on Cayman.
|
|
}
|
|
|
|
def RAT_STORE_DWORD32 : RAT_STORE_DWORD <R600_TReg32_X, i32, 0x1>;
|
|
def RAT_STORE_DWORD64 : RAT_STORE_DWORD <R600_Reg64, v2i32, 0x3>;
|
|
def RAT_STORE_DWORD128 : RAT_STORE_DWORD <R600_Reg128, v4i32, 0xf>;
|
|
|
|
class VTX_READ_cm <string name, bits<8> buffer_id, dag outs, list<dag> pattern>
|
|
: VTX_WORD0_cm, VTX_READ<name, buffer_id, outs, pattern> {
|
|
|
|
// Static fields
|
|
let VC_INST = 0;
|
|
let FETCH_TYPE = 2;
|
|
let FETCH_WHOLE_QUAD = 0;
|
|
let BUFFER_ID = buffer_id;
|
|
let SRC_REL = 0;
|
|
// XXX: We can infer this field based on the SRC_GPR. This would allow us
|
|
// to store vertex addresses in any channel, not just X.
|
|
let SRC_SEL_X = 0;
|
|
let SRC_SEL_Y = 0;
|
|
let STRUCTURED_READ = 0;
|
|
let LDS_REQ = 0;
|
|
let COALESCED_READ = 0;
|
|
|
|
let Inst{31-0} = Word0;
|
|
}
|
|
|
|
class VTX_READ_8_cm <bits<8> buffer_id, list<dag> pattern>
|
|
: VTX_READ_cm <"VTX_READ_8 $dst_gpr, $src_gpr", buffer_id,
|
|
(outs R600_TReg32_X:$dst_gpr), pattern> {
|
|
|
|
let DST_SEL_X = 0;
|
|
let DST_SEL_Y = 7; // Masked
|
|
let DST_SEL_Z = 7; // Masked
|
|
let DST_SEL_W = 7; // Masked
|
|
let DATA_FORMAT = 1; // FMT_8
|
|
}
|
|
|
|
class VTX_READ_16_cm <bits<8> buffer_id, list<dag> pattern>
|
|
: VTX_READ_cm <"VTX_READ_16 $dst_gpr, $src_gpr", buffer_id,
|
|
(outs R600_TReg32_X:$dst_gpr), pattern> {
|
|
let DST_SEL_X = 0;
|
|
let DST_SEL_Y = 7; // Masked
|
|
let DST_SEL_Z = 7; // Masked
|
|
let DST_SEL_W = 7; // Masked
|
|
let DATA_FORMAT = 5; // FMT_16
|
|
|
|
}
|
|
|
|
class VTX_READ_32_cm <bits<8> buffer_id, list<dag> pattern>
|
|
: VTX_READ_cm <"VTX_READ_32 $dst_gpr, $src_gpr", buffer_id,
|
|
(outs R600_TReg32_X:$dst_gpr), pattern> {
|
|
|
|
let DST_SEL_X = 0;
|
|
let DST_SEL_Y = 7; // Masked
|
|
let DST_SEL_Z = 7; // Masked
|
|
let DST_SEL_W = 7; // Masked
|
|
let DATA_FORMAT = 0xD; // COLOR_32
|
|
|
|
// This is not really necessary, but there were some GPU hangs that appeared
|
|
// to be caused by ALU instructions in the next instruction group that wrote
|
|
// to the $src_gpr registers of the VTX_READ.
|
|
// e.g.
|
|
// %T3_X<def> = VTX_READ_PARAM_32_eg %T2_X<kill>, 24
|
|
// %T2_X<def> = MOV %ZERO
|
|
//Adding this constraint prevents this from happening.
|
|
let Constraints = "$src_gpr.ptr = $dst_gpr";
|
|
}
|
|
|
|
class VTX_READ_64_cm <bits<8> buffer_id, list<dag> pattern>
|
|
: VTX_READ_cm <"VTX_READ_64 $dst_gpr, $src_gpr", buffer_id,
|
|
(outs R600_Reg64:$dst_gpr), pattern> {
|
|
|
|
let DST_SEL_X = 0;
|
|
let DST_SEL_Y = 1;
|
|
let DST_SEL_Z = 7;
|
|
let DST_SEL_W = 7;
|
|
let DATA_FORMAT = 0x1D; // COLOR_32_32
|
|
}
|
|
|
|
class VTX_READ_128_cm <bits<8> buffer_id, list<dag> pattern>
|
|
: VTX_READ_cm <"VTX_READ_128 $dst_gpr.XYZW, $src_gpr", buffer_id,
|
|
(outs R600_Reg128:$dst_gpr), pattern> {
|
|
|
|
let DST_SEL_X = 0;
|
|
let DST_SEL_Y = 1;
|
|
let DST_SEL_Z = 2;
|
|
let DST_SEL_W = 3;
|
|
let DATA_FORMAT = 0x22; // COLOR_32_32_32_32
|
|
|
|
// XXX: Need to force VTX_READ_128 instructions to write to the same register
|
|
// that holds its buffer address to avoid potential hangs. We can't use
|
|
// the same constraint as VTX_READ_32_eg, because the $src_gpr.ptr and $dst
|
|
// registers are different sizes.
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VTX Read from parameter memory space
|
|
//===----------------------------------------------------------------------===//
|
|
def VTX_READ_PARAM_8_cm : VTX_READ_8_cm <0,
|
|
[(set i32:$dst_gpr, (load_param_exti8 ADDRVTX_READ:$src_gpr))]
|
|
>;
|
|
|
|
def VTX_READ_PARAM_16_cm : VTX_READ_16_cm <0,
|
|
[(set i32:$dst_gpr, (load_param_exti16 ADDRVTX_READ:$src_gpr))]
|
|
>;
|
|
|
|
def VTX_READ_PARAM_32_cm : VTX_READ_32_cm <0,
|
|
[(set i32:$dst_gpr, (load_param ADDRVTX_READ:$src_gpr))]
|
|
>;
|
|
|
|
def VTX_READ_PARAM_64_cm : VTX_READ_64_cm <0,
|
|
[(set v2i32:$dst_gpr, (load_param ADDRVTX_READ:$src_gpr))]
|
|
>;
|
|
|
|
def VTX_READ_PARAM_128_cm : VTX_READ_128_cm <0,
|
|
[(set v4i32:$dst_gpr, (load_param ADDRVTX_READ:$src_gpr))]
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VTX Read from global memory space
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// 8-bit reads
|
|
def VTX_READ_GLOBAL_8_cm : VTX_READ_8_cm <1,
|
|
[(set i32:$dst_gpr, (az_extloadi8_global ADDRVTX_READ:$src_gpr))]
|
|
>;
|
|
|
|
def VTX_READ_GLOBAL_16_cm : VTX_READ_16_cm <1,
|
|
[(set i32:$dst_gpr, (az_extloadi16_global ADDRVTX_READ:$src_gpr))]
|
|
>;
|
|
|
|
// 32-bit reads
|
|
def VTX_READ_GLOBAL_32_cm : VTX_READ_32_cm <1,
|
|
[(set i32:$dst_gpr, (global_load ADDRVTX_READ:$src_gpr))]
|
|
>;
|
|
|
|
// 64-bit reads
|
|
def VTX_READ_GLOBAL_64_cm : VTX_READ_64_cm <1,
|
|
[(set v2i32:$dst_gpr, (global_load ADDRVTX_READ:$src_gpr))]
|
|
>;
|
|
|
|
// 128-bit reads
|
|
def VTX_READ_GLOBAL_128_cm : VTX_READ_128_cm <1,
|
|
[(set v4i32:$dst_gpr, (global_load ADDRVTX_READ:$src_gpr))]
|
|
>;
|
|
|
|
} // End isCayman
|
|
|