forked from OSchip/llvm-project
2871 lines
111 KiB
TableGen
2871 lines
111 KiB
TableGen
//===-- SIInstructions.td - SI Instruction Defintions ---------------------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
// This file was originally auto-generated from a GPU register header file and
|
|
// all the instruction definitions were originally commented out. Instructions
|
|
// that are not yet supported remain commented out.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class InterpSlots {
|
|
int P0 = 2;
|
|
int P10 = 0;
|
|
int P20 = 1;
|
|
}
|
|
def INTERP : InterpSlots;
|
|
|
|
def InterpSlot : Operand<i32> {
|
|
let PrintMethod = "printInterpSlot";
|
|
}
|
|
|
|
def SendMsgImm : Operand<i32> {
|
|
let PrintMethod = "printSendMsg";
|
|
}
|
|
|
|
def isSI : Predicate<"Subtarget.getGeneration() "
|
|
">= AMDGPUSubtarget::SOUTHERN_ISLANDS">;
|
|
|
|
def isCI : Predicate<"Subtarget.getGeneration() "
|
|
">= AMDGPUSubtarget::SEA_ISLANDS">;
|
|
|
|
def isCFDepth0 : Predicate<"isCFDepth0()">;
|
|
|
|
def WAIT_FLAG : InstFlag<"printWaitFlag">;
|
|
|
|
let SubtargetPredicate = isSI in {
|
|
let OtherPredicates = [isCFDepth0] in {
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SMRD Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let mayLoad = 1 in {
|
|
|
|
// We are using the SGPR_32 and not the SReg_32 register class for 32-bit
|
|
// SMRD instructions, because the SGPR_32 register class does not include M0
|
|
// and writing to M0 from an SMRD instruction will hang the GPU.
|
|
defm S_LOAD_DWORD : SMRD_Helper <0x00, "S_LOAD_DWORD", SReg_64, SGPR_32>;
|
|
defm S_LOAD_DWORDX2 : SMRD_Helper <0x01, "S_LOAD_DWORDX2", SReg_64, SReg_64>;
|
|
defm S_LOAD_DWORDX4 : SMRD_Helper <0x02, "S_LOAD_DWORDX4", SReg_64, SReg_128>;
|
|
defm S_LOAD_DWORDX8 : SMRD_Helper <0x03, "S_LOAD_DWORDX8", SReg_64, SReg_256>;
|
|
defm S_LOAD_DWORDX16 : SMRD_Helper <0x04, "S_LOAD_DWORDX16", SReg_64, SReg_512>;
|
|
|
|
defm S_BUFFER_LOAD_DWORD : SMRD_Helper <
|
|
0x08, "S_BUFFER_LOAD_DWORD", SReg_128, SGPR_32
|
|
>;
|
|
|
|
defm S_BUFFER_LOAD_DWORDX2 : SMRD_Helper <
|
|
0x09, "S_BUFFER_LOAD_DWORDX2", SReg_128, SReg_64
|
|
>;
|
|
|
|
defm S_BUFFER_LOAD_DWORDX4 : SMRD_Helper <
|
|
0x0a, "S_BUFFER_LOAD_DWORDX4", SReg_128, SReg_128
|
|
>;
|
|
|
|
defm S_BUFFER_LOAD_DWORDX8 : SMRD_Helper <
|
|
0x0b, "S_BUFFER_LOAD_DWORDX8", SReg_128, SReg_256
|
|
>;
|
|
|
|
defm S_BUFFER_LOAD_DWORDX16 : SMRD_Helper <
|
|
0x0c, "S_BUFFER_LOAD_DWORDX16", SReg_128, SReg_512
|
|
>;
|
|
|
|
} // mayLoad = 1
|
|
|
|
//def S_MEMTIME : SMRD_ <0x0000001e, "S_MEMTIME", []>;
|
|
//def S_DCACHE_INV : SMRD_ <0x0000001f, "S_DCACHE_INV", []>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP1 Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let neverHasSideEffects = 1 in {
|
|
|
|
let isMoveImm = 1 in {
|
|
def S_MOV_B32 : SOP1_32 <0x00000003, "S_MOV_B32", []>;
|
|
def S_MOV_B64 : SOP1_64 <0x00000004, "S_MOV_B64", []>;
|
|
def S_CMOV_B32 : SOP1_32 <0x00000005, "S_CMOV_B32", []>;
|
|
def S_CMOV_B64 : SOP1_64 <0x00000006, "S_CMOV_B64", []>;
|
|
} // End isMoveImm = 1
|
|
|
|
def S_NOT_B32 : SOP1_32 <0x00000007, "S_NOT_B32",
|
|
[(set i32:$dst, (not i32:$src0))]
|
|
>;
|
|
|
|
def S_NOT_B64 : SOP1_64 <0x00000008, "S_NOT_B64",
|
|
[(set i64:$dst, (not i64:$src0))]
|
|
>;
|
|
def S_WQM_B32 : SOP1_32 <0x00000009, "S_WQM_B32", []>;
|
|
def S_WQM_B64 : SOP1_64 <0x0000000a, "S_WQM_B64", []>;
|
|
def S_BREV_B32 : SOP1_32 <0x0000000b, "S_BREV_B32",
|
|
[(set i32:$dst, (AMDGPUbrev i32:$src0))]
|
|
>;
|
|
def S_BREV_B64 : SOP1_64 <0x0000000c, "S_BREV_B64", []>;
|
|
} // End neverHasSideEffects = 1
|
|
|
|
////def S_BCNT0_I32_B32 : SOP1_BCNT0 <0x0000000d, "S_BCNT0_I32_B32", []>;
|
|
////def S_BCNT0_I32_B64 : SOP1_BCNT0 <0x0000000e, "S_BCNT0_I32_B64", []>;
|
|
def S_BCNT1_I32_B32 : SOP1_32 <0x0000000f, "S_BCNT1_I32_B32",
|
|
[(set i32:$dst, (ctpop i32:$src0))]
|
|
>;
|
|
def S_BCNT1_I32_B64 : SOP1_32_64 <0x00000010, "S_BCNT1_I32_B64", []>;
|
|
|
|
////def S_FF0_I32_B32 : SOP1_32 <0x00000011, "S_FF0_I32_B32", []>;
|
|
////def S_FF0_I32_B64 : SOP1_FF0 <0x00000012, "S_FF0_I32_B64", []>;
|
|
def S_FF1_I32_B32 : SOP1_32 <0x00000013, "S_FF1_I32_B32",
|
|
[(set i32:$dst, (cttz_zero_undef i32:$src0))]
|
|
>;
|
|
////def S_FF1_I32_B64 : SOP1_FF1 <0x00000014, "S_FF1_I32_B64", []>;
|
|
|
|
def S_FLBIT_I32_B32 : SOP1_32 <0x00000015, "S_FLBIT_I32_B32",
|
|
[(set i32:$dst, (ctlz_zero_undef i32:$src0))]
|
|
>;
|
|
|
|
//def S_FLBIT_I32_B64 : SOP1_32 <0x00000016, "S_FLBIT_I32_B64", []>;
|
|
def S_FLBIT_I32 : SOP1_32 <0x00000017, "S_FLBIT_I32", []>;
|
|
//def S_FLBIT_I32_I64 : SOP1_32 <0x00000018, "S_FLBIT_I32_I64", []>;
|
|
def S_SEXT_I32_I8 : SOP1_32 <0x00000019, "S_SEXT_I32_I8",
|
|
[(set i32:$dst, (sext_inreg i32:$src0, i8))]
|
|
>;
|
|
def S_SEXT_I32_I16 : SOP1_32 <0x0000001a, "S_SEXT_I32_I16",
|
|
[(set i32:$dst, (sext_inreg i32:$src0, i16))]
|
|
>;
|
|
|
|
////def S_BITSET0_B32 : SOP1_BITSET0 <0x0000001b, "S_BITSET0_B32", []>;
|
|
////def S_BITSET0_B64 : SOP1_BITSET0 <0x0000001c, "S_BITSET0_B64", []>;
|
|
////def S_BITSET1_B32 : SOP1_BITSET1 <0x0000001d, "S_BITSET1_B32", []>;
|
|
////def S_BITSET1_B64 : SOP1_BITSET1 <0x0000001e, "S_BITSET1_B64", []>;
|
|
def S_GETPC_B64 : SOP1_64 <0x0000001f, "S_GETPC_B64", []>;
|
|
def S_SETPC_B64 : SOP1_64 <0x00000020, "S_SETPC_B64", []>;
|
|
def S_SWAPPC_B64 : SOP1_64 <0x00000021, "S_SWAPPC_B64", []>;
|
|
def S_RFE_B64 : SOP1_64 <0x00000022, "S_RFE_B64", []>;
|
|
|
|
let hasSideEffects = 1, Uses = [EXEC], Defs = [EXEC] in {
|
|
|
|
def S_AND_SAVEEXEC_B64 : SOP1_64 <0x00000024, "S_AND_SAVEEXEC_B64", []>;
|
|
def S_OR_SAVEEXEC_B64 : SOP1_64 <0x00000025, "S_OR_SAVEEXEC_B64", []>;
|
|
def S_XOR_SAVEEXEC_B64 : SOP1_64 <0x00000026, "S_XOR_SAVEEXEC_B64", []>;
|
|
def S_ANDN2_SAVEEXEC_B64 : SOP1_64 <0x00000027, "S_ANDN2_SAVEEXEC_B64", []>;
|
|
def S_ORN2_SAVEEXEC_B64 : SOP1_64 <0x00000028, "S_ORN2_SAVEEXEC_B64", []>;
|
|
def S_NAND_SAVEEXEC_B64 : SOP1_64 <0x00000029, "S_NAND_SAVEEXEC_B64", []>;
|
|
def S_NOR_SAVEEXEC_B64 : SOP1_64 <0x0000002a, "S_NOR_SAVEEXEC_B64", []>;
|
|
def S_XNOR_SAVEEXEC_B64 : SOP1_64 <0x0000002b, "S_XNOR_SAVEEXEC_B64", []>;
|
|
|
|
} // End hasSideEffects = 1
|
|
|
|
def S_QUADMASK_B32 : SOP1_32 <0x0000002c, "S_QUADMASK_B32", []>;
|
|
def S_QUADMASK_B64 : SOP1_64 <0x0000002d, "S_QUADMASK_B64", []>;
|
|
def S_MOVRELS_B32 : SOP1_32 <0x0000002e, "S_MOVRELS_B32", []>;
|
|
def S_MOVRELS_B64 : SOP1_64 <0x0000002f, "S_MOVRELS_B64", []>;
|
|
def S_MOVRELD_B32 : SOP1_32 <0x00000030, "S_MOVRELD_B32", []>;
|
|
def S_MOVRELD_B64 : SOP1_64 <0x00000031, "S_MOVRELD_B64", []>;
|
|
//def S_CBRANCH_JOIN : SOP1_ <0x00000032, "S_CBRANCH_JOIN", []>;
|
|
def S_MOV_REGRD_B32 : SOP1_32 <0x00000033, "S_MOV_REGRD_B32", []>;
|
|
def S_ABS_I32 : SOP1_32 <0x00000034, "S_ABS_I32", []>;
|
|
def S_MOV_FED_B32 : SOP1_32 <0x00000035, "S_MOV_FED_B32", []>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP2 Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let Defs = [SCC] in { // Carry out goes to SCC
|
|
let isCommutable = 1 in {
|
|
def S_ADD_U32 : SOP2_32 <0x00000000, "S_ADD_U32", []>;
|
|
def S_ADD_I32 : SOP2_32 <0x00000002, "S_ADD_I32",
|
|
[(set i32:$dst, (add SSrc_32:$src0, SSrc_32:$src1))]
|
|
>;
|
|
} // End isCommutable = 1
|
|
|
|
def S_SUB_U32 : SOP2_32 <0x00000001, "S_SUB_U32", []>;
|
|
def S_SUB_I32 : SOP2_32 <0x00000003, "S_SUB_I32",
|
|
[(set i32:$dst, (sub SSrc_32:$src0, SSrc_32:$src1))]
|
|
>;
|
|
|
|
let Uses = [SCC] in { // Carry in comes from SCC
|
|
let isCommutable = 1 in {
|
|
def S_ADDC_U32 : SOP2_32 <0x00000004, "S_ADDC_U32",
|
|
[(set i32:$dst, (adde (i32 SSrc_32:$src0), (i32 SSrc_32:$src1)))]>;
|
|
} // End isCommutable = 1
|
|
|
|
def S_SUBB_U32 : SOP2_32 <0x00000005, "S_SUBB_U32",
|
|
[(set i32:$dst, (sube (i32 SSrc_32:$src0), (i32 SSrc_32:$src1)))]>;
|
|
} // End Uses = [SCC]
|
|
} // End Defs = [SCC]
|
|
|
|
def S_MIN_I32 : SOP2_32 <0x00000006, "S_MIN_I32",
|
|
[(set i32:$dst, (AMDGPUsmin i32:$src0, i32:$src1))]
|
|
>;
|
|
def S_MIN_U32 : SOP2_32 <0x00000007, "S_MIN_U32",
|
|
[(set i32:$dst, (AMDGPUumin i32:$src0, i32:$src1))]
|
|
>;
|
|
def S_MAX_I32 : SOP2_32 <0x00000008, "S_MAX_I32",
|
|
[(set i32:$dst, (AMDGPUsmax i32:$src0, i32:$src1))]
|
|
>;
|
|
def S_MAX_U32 : SOP2_32 <0x00000009, "S_MAX_U32",
|
|
[(set i32:$dst, (AMDGPUumax i32:$src0, i32:$src1))]
|
|
>;
|
|
|
|
def S_CSELECT_B32 : SOP2 <
|
|
0x0000000a, (outs SReg_32:$dst),
|
|
(ins SReg_32:$src0, SReg_32:$src1, SCCReg:$scc), "S_CSELECT_B32",
|
|
[]
|
|
>;
|
|
|
|
def S_CSELECT_B64 : SOP2_64 <0x0000000b, "S_CSELECT_B64", []>;
|
|
|
|
def S_AND_B32 : SOP2_32 <0x0000000e, "S_AND_B32",
|
|
[(set i32:$dst, (and i32:$src0, i32:$src1))]
|
|
>;
|
|
|
|
def S_AND_B64 : SOP2_64 <0x0000000f, "S_AND_B64",
|
|
[(set i64:$dst, (and i64:$src0, i64:$src1))]
|
|
>;
|
|
|
|
def S_OR_B32 : SOP2_32 <0x00000010, "S_OR_B32",
|
|
[(set i32:$dst, (or i32:$src0, i32:$src1))]
|
|
>;
|
|
|
|
def S_OR_B64 : SOP2_64 <0x00000011, "S_OR_B64",
|
|
[(set i64:$dst, (or i64:$src0, i64:$src1))]
|
|
>;
|
|
|
|
def S_XOR_B32 : SOP2_32 <0x00000012, "S_XOR_B32",
|
|
[(set i32:$dst, (xor i32:$src0, i32:$src1))]
|
|
>;
|
|
|
|
def S_XOR_B64 : SOP2_64 <0x00000013, "S_XOR_B64",
|
|
[(set i64:$dst, (xor i64:$src0, i64:$src1))]
|
|
>;
|
|
def S_ANDN2_B32 : SOP2_32 <0x00000014, "S_ANDN2_B32", []>;
|
|
def S_ANDN2_B64 : SOP2_64 <0x00000015, "S_ANDN2_B64", []>;
|
|
def S_ORN2_B32 : SOP2_32 <0x00000016, "S_ORN2_B32", []>;
|
|
def S_ORN2_B64 : SOP2_64 <0x00000017, "S_ORN2_B64", []>;
|
|
def S_NAND_B32 : SOP2_32 <0x00000018, "S_NAND_B32", []>;
|
|
def S_NAND_B64 : SOP2_64 <0x00000019, "S_NAND_B64", []>;
|
|
def S_NOR_B32 : SOP2_32 <0x0000001a, "S_NOR_B32", []>;
|
|
def S_NOR_B64 : SOP2_64 <0x0000001b, "S_NOR_B64", []>;
|
|
def S_XNOR_B32 : SOP2_32 <0x0000001c, "S_XNOR_B32", []>;
|
|
def S_XNOR_B64 : SOP2_64 <0x0000001d, "S_XNOR_B64", []>;
|
|
|
|
// Use added complexity so these patterns are preferred to the VALU patterns.
|
|
let AddedComplexity = 1 in {
|
|
|
|
def S_LSHL_B32 : SOP2_32 <0x0000001e, "S_LSHL_B32",
|
|
[(set i32:$dst, (shl i32:$src0, i32:$src1))]
|
|
>;
|
|
def S_LSHL_B64 : SOP2_SHIFT_64 <0x0000001f, "S_LSHL_B64",
|
|
[(set i64:$dst, (shl i64:$src0, i32:$src1))]
|
|
>;
|
|
def S_LSHR_B32 : SOP2_32 <0x00000020, "S_LSHR_B32",
|
|
[(set i32:$dst, (srl i32:$src0, i32:$src1))]
|
|
>;
|
|
def S_LSHR_B64 : SOP2_SHIFT_64 <0x00000021, "S_LSHR_B64",
|
|
[(set i64:$dst, (srl i64:$src0, i32:$src1))]
|
|
>;
|
|
def S_ASHR_I32 : SOP2_32 <0x00000022, "S_ASHR_I32",
|
|
[(set i32:$dst, (sra i32:$src0, i32:$src1))]
|
|
>;
|
|
def S_ASHR_I64 : SOP2_SHIFT_64 <0x00000023, "S_ASHR_I64",
|
|
[(set i64:$dst, (sra i64:$src0, i32:$src1))]
|
|
>;
|
|
|
|
} // End AddedComplexity = 1
|
|
|
|
def S_BFM_B32 : SOP2_32 <0x00000024, "S_BFM_B32", []>;
|
|
def S_BFM_B64 : SOP2_64 <0x00000025, "S_BFM_B64", []>;
|
|
def S_MUL_I32 : SOP2_32 <0x00000026, "S_MUL_I32", []>;
|
|
def S_BFE_U32 : SOP2_32 <0x00000027, "S_BFE_U32", []>;
|
|
def S_BFE_I32 : SOP2_32 <0x00000028, "S_BFE_I32", []>;
|
|
def S_BFE_U64 : SOP2_64 <0x00000029, "S_BFE_U64", []>;
|
|
def S_BFE_I64 : SOP2_64 <0x0000002a, "S_BFE_I64", []>;
|
|
//def S_CBRANCH_G_FORK : SOP2_ <0x0000002b, "S_CBRANCH_G_FORK", []>;
|
|
def S_ABSDIFF_I32 : SOP2_32 <0x0000002c, "S_ABSDIFF_I32", []>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOPC Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def S_CMP_EQ_I32 : SOPC_32 <0x00000000, "S_CMP_EQ_I32">;
|
|
def S_CMP_LG_I32 : SOPC_32 <0x00000001, "S_CMP_LG_I32">;
|
|
def S_CMP_GT_I32 : SOPC_32 <0x00000002, "S_CMP_GT_I32">;
|
|
def S_CMP_GE_I32 : SOPC_32 <0x00000003, "S_CMP_GE_I32">;
|
|
def S_CMP_LT_I32 : SOPC_32 <0x00000004, "S_CMP_LT_I32">;
|
|
def S_CMP_LE_I32 : SOPC_32 <0x00000005, "S_CMP_LE_I32">;
|
|
def S_CMP_EQ_U32 : SOPC_32 <0x00000006, "S_CMP_EQ_U32">;
|
|
def S_CMP_LG_U32 : SOPC_32 <0x00000007, "S_CMP_LG_U32">;
|
|
def S_CMP_GT_U32 : SOPC_32 <0x00000008, "S_CMP_GT_U32">;
|
|
def S_CMP_GE_U32 : SOPC_32 <0x00000009, "S_CMP_GE_U32">;
|
|
def S_CMP_LT_U32 : SOPC_32 <0x0000000a, "S_CMP_LT_U32">;
|
|
def S_CMP_LE_U32 : SOPC_32 <0x0000000b, "S_CMP_LE_U32">;
|
|
////def S_BITCMP0_B32 : SOPC_BITCMP0 <0x0000000c, "S_BITCMP0_B32", []>;
|
|
////def S_BITCMP1_B32 : SOPC_BITCMP1 <0x0000000d, "S_BITCMP1_B32", []>;
|
|
////def S_BITCMP0_B64 : SOPC_BITCMP0 <0x0000000e, "S_BITCMP0_B64", []>;
|
|
////def S_BITCMP1_B64 : SOPC_BITCMP1 <0x0000000f, "S_BITCMP1_B64", []>;
|
|
//def S_SETVSKIP : SOPC_ <0x00000010, "S_SETVSKIP", []>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOPK Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def S_MOVK_I32 : SOPK_32 <0x00000000, "S_MOVK_I32", []>;
|
|
def S_CMOVK_I32 : SOPK_32 <0x00000002, "S_CMOVK_I32", []>;
|
|
|
|
/*
|
|
This instruction is disabled for now until we can figure out how to teach
|
|
the instruction selector to correctly use the S_CMP* vs V_CMP*
|
|
instructions.
|
|
|
|
When this instruction is enabled the code generator sometimes produces this
|
|
invalid sequence:
|
|
|
|
SCC = S_CMPK_EQ_I32 SGPR0, imm
|
|
VCC = COPY SCC
|
|
VGPR0 = V_CNDMASK VCC, VGPR0, VGPR1
|
|
|
|
def S_CMPK_EQ_I32 : SOPK <
|
|
0x00000003, (outs SCCReg:$dst), (ins SReg_32:$src0, i32imm:$src1),
|
|
"S_CMPK_EQ_I32",
|
|
[(set i1:$dst, (setcc i32:$src0, imm:$src1, SETEQ))]
|
|
>;
|
|
*/
|
|
|
|
let isCompare = 1, Defs = [SCC] in {
|
|
def S_CMPK_LG_I32 : SOPK_32 <0x00000004, "S_CMPK_LG_I32", []>;
|
|
def S_CMPK_GT_I32 : SOPK_32 <0x00000005, "S_CMPK_GT_I32", []>;
|
|
def S_CMPK_GE_I32 : SOPK_32 <0x00000006, "S_CMPK_GE_I32", []>;
|
|
def S_CMPK_LT_I32 : SOPK_32 <0x00000007, "S_CMPK_LT_I32", []>;
|
|
def S_CMPK_LE_I32 : SOPK_32 <0x00000008, "S_CMPK_LE_I32", []>;
|
|
def S_CMPK_EQ_U32 : SOPK_32 <0x00000009, "S_CMPK_EQ_U32", []>;
|
|
def S_CMPK_LG_U32 : SOPK_32 <0x0000000a, "S_CMPK_LG_U32", []>;
|
|
def S_CMPK_GT_U32 : SOPK_32 <0x0000000b, "S_CMPK_GT_U32", []>;
|
|
def S_CMPK_GE_U32 : SOPK_32 <0x0000000c, "S_CMPK_GE_U32", []>;
|
|
def S_CMPK_LT_U32 : SOPK_32 <0x0000000d, "S_CMPK_LT_U32", []>;
|
|
def S_CMPK_LE_U32 : SOPK_32 <0x0000000e, "S_CMPK_LE_U32", []>;
|
|
} // End isCompare = 1, Defs = [SCC]
|
|
|
|
let Defs = [SCC], isCommutable = 1 in {
|
|
def S_ADDK_I32 : SOPK_32 <0x0000000f, "S_ADDK_I32", []>;
|
|
def S_MULK_I32 : SOPK_32 <0x00000010, "S_MULK_I32", []>;
|
|
}
|
|
|
|
//def S_CBRANCH_I_FORK : SOPK_ <0x00000011, "S_CBRANCH_I_FORK", []>;
|
|
def S_GETREG_B32 : SOPK_32 <0x00000012, "S_GETREG_B32", []>;
|
|
def S_SETREG_B32 : SOPK_32 <0x00000013, "S_SETREG_B32", []>;
|
|
def S_GETREG_REGRD_B32 : SOPK_32 <0x00000014, "S_GETREG_REGRD_B32", []>;
|
|
//def S_SETREG_IMM32_B32 : SOPK_32 <0x00000015, "S_SETREG_IMM32_B32", []>;
|
|
//def EXP : EXP_ <0x00000000, "EXP", []>;
|
|
|
|
} // End let OtherPredicates = [isCFDepth0]
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOPP Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def S_NOP : SOPP <0x00000000, (ins i16imm:$SIMM16), "S_NOP $SIMM16", []>;
|
|
|
|
let isTerminator = 1 in {
|
|
|
|
def S_ENDPGM : SOPP <0x00000001, (ins), "S_ENDPGM",
|
|
[(IL_retflag)]> {
|
|
let SIMM16 = 0;
|
|
let isBarrier = 1;
|
|
let hasCtrlDep = 1;
|
|
}
|
|
|
|
let isBranch = 1 in {
|
|
def S_BRANCH : SOPP <
|
|
0x00000002, (ins brtarget:$target), "S_BRANCH $target",
|
|
[(br bb:$target)]> {
|
|
let isBarrier = 1;
|
|
}
|
|
|
|
let DisableEncoding = "$scc" in {
|
|
def S_CBRANCH_SCC0 : SOPP <
|
|
0x00000004, (ins brtarget:$target, SCCReg:$scc),
|
|
"S_CBRANCH_SCC0 $target", []
|
|
>;
|
|
def S_CBRANCH_SCC1 : SOPP <
|
|
0x00000005, (ins brtarget:$target, SCCReg:$scc),
|
|
"S_CBRANCH_SCC1 $target",
|
|
[]
|
|
>;
|
|
} // End DisableEncoding = "$scc"
|
|
|
|
def S_CBRANCH_VCCZ : SOPP <
|
|
0x00000006, (ins brtarget:$target, VCCReg:$vcc),
|
|
"S_CBRANCH_VCCZ $target",
|
|
[]
|
|
>;
|
|
def S_CBRANCH_VCCNZ : SOPP <
|
|
0x00000007, (ins brtarget:$target, VCCReg:$vcc),
|
|
"S_CBRANCH_VCCNZ $target",
|
|
[]
|
|
>;
|
|
|
|
let DisableEncoding = "$exec" in {
|
|
def S_CBRANCH_EXECZ : SOPP <
|
|
0x00000008, (ins brtarget:$target, EXECReg:$exec),
|
|
"S_CBRANCH_EXECZ $target",
|
|
[]
|
|
>;
|
|
def S_CBRANCH_EXECNZ : SOPP <
|
|
0x00000009, (ins brtarget:$target, EXECReg:$exec),
|
|
"S_CBRANCH_EXECNZ $target",
|
|
[]
|
|
>;
|
|
} // End DisableEncoding = "$exec"
|
|
|
|
|
|
} // End isBranch = 1
|
|
} // End isTerminator = 1
|
|
|
|
let hasSideEffects = 1 in {
|
|
def S_BARRIER : SOPP <0x0000000a, (ins), "S_BARRIER",
|
|
[(int_AMDGPU_barrier_local)]
|
|
> {
|
|
let SIMM16 = 0;
|
|
let isBarrier = 1;
|
|
let hasCtrlDep = 1;
|
|
let mayLoad = 1;
|
|
let mayStore = 1;
|
|
}
|
|
|
|
def S_WAITCNT : SOPP <0x0000000c, (ins WAIT_FLAG:$simm16), "S_WAITCNT $simm16",
|
|
[]
|
|
>;
|
|
//def S_SETHALT : SOPP_ <0x0000000d, "S_SETHALT", []>;
|
|
//def S_SLEEP : SOPP_ <0x0000000e, "S_SLEEP", []>;
|
|
//def S_SETPRIO : SOPP_ <0x0000000f, "S_SETPRIO", []>;
|
|
|
|
let Uses = [EXEC] in {
|
|
def S_SENDMSG : SOPP <0x00000010, (ins SendMsgImm:$simm16, M0Reg:$m0), "S_SENDMSG $simm16",
|
|
[(int_SI_sendmsg imm:$simm16, M0Reg:$m0)]
|
|
> {
|
|
let DisableEncoding = "$m0";
|
|
}
|
|
} // End Uses = [EXEC]
|
|
|
|
//def S_SENDMSGHALT : SOPP_ <0x00000011, "S_SENDMSGHALT", []>;
|
|
//def S_TRAP : SOPP_ <0x00000012, "S_TRAP", []>;
|
|
//def S_ICACHE_INV : SOPP_ <0x00000013, "S_ICACHE_INV", []>;
|
|
//def S_INCPERFLEVEL : SOPP_ <0x00000014, "S_INCPERFLEVEL", []>;
|
|
//def S_DECPERFLEVEL : SOPP_ <0x00000015, "S_DECPERFLEVEL", []>;
|
|
//def S_TTRACEDATA : SOPP_ <0x00000016, "S_TTRACEDATA", []>;
|
|
} // End hasSideEffects
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VOPC Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let isCompare = 1 in {
|
|
|
|
defm V_CMP_F_F32 : VOPC_32 <0x00000000, "V_CMP_F_F32">;
|
|
defm V_CMP_LT_F32 : VOPC_32 <0x00000001, "V_CMP_LT_F32", f32, COND_OLT>;
|
|
defm V_CMP_EQ_F32 : VOPC_32 <0x00000002, "V_CMP_EQ_F32", f32, COND_OEQ>;
|
|
defm V_CMP_LE_F32 : VOPC_32 <0x00000003, "V_CMP_LE_F32", f32, COND_OLE>;
|
|
defm V_CMP_GT_F32 : VOPC_32 <0x00000004, "V_CMP_GT_F32", f32, COND_OGT>;
|
|
defm V_CMP_LG_F32 : VOPC_32 <0x00000005, "V_CMP_LG_F32">;
|
|
defm V_CMP_GE_F32 : VOPC_32 <0x00000006, "V_CMP_GE_F32", f32, COND_OGE>;
|
|
defm V_CMP_O_F32 : VOPC_32 <0x00000007, "V_CMP_O_F32", f32, COND_O>;
|
|
defm V_CMP_U_F32 : VOPC_32 <0x00000008, "V_CMP_U_F32", f32, COND_UO>;
|
|
defm V_CMP_NGE_F32 : VOPC_32 <0x00000009, "V_CMP_NGE_F32">;
|
|
defm V_CMP_NLG_F32 : VOPC_32 <0x0000000a, "V_CMP_NLG_F32">;
|
|
defm V_CMP_NGT_F32 : VOPC_32 <0x0000000b, "V_CMP_NGT_F32">;
|
|
defm V_CMP_NLE_F32 : VOPC_32 <0x0000000c, "V_CMP_NLE_F32">;
|
|
defm V_CMP_NEQ_F32 : VOPC_32 <0x0000000d, "V_CMP_NEQ_F32", f32, COND_UNE>;
|
|
defm V_CMP_NLT_F32 : VOPC_32 <0x0000000e, "V_CMP_NLT_F32">;
|
|
defm V_CMP_TRU_F32 : VOPC_32 <0x0000000f, "V_CMP_TRU_F32">;
|
|
|
|
let hasSideEffects = 1 in {
|
|
|
|
defm V_CMPX_F_F32 : VOPCX_32 <0x00000010, "V_CMPX_F_F32">;
|
|
defm V_CMPX_LT_F32 : VOPCX_32 <0x00000011, "V_CMPX_LT_F32">;
|
|
defm V_CMPX_EQ_F32 : VOPCX_32 <0x00000012, "V_CMPX_EQ_F32">;
|
|
defm V_CMPX_LE_F32 : VOPCX_32 <0x00000013, "V_CMPX_LE_F32">;
|
|
defm V_CMPX_GT_F32 : VOPCX_32 <0x00000014, "V_CMPX_GT_F32">;
|
|
defm V_CMPX_LG_F32 : VOPCX_32 <0x00000015, "V_CMPX_LG_F32">;
|
|
defm V_CMPX_GE_F32 : VOPCX_32 <0x00000016, "V_CMPX_GE_F32">;
|
|
defm V_CMPX_O_F32 : VOPCX_32 <0x00000017, "V_CMPX_O_F32">;
|
|
defm V_CMPX_U_F32 : VOPCX_32 <0x00000018, "V_CMPX_U_F32">;
|
|
defm V_CMPX_NGE_F32 : VOPCX_32 <0x00000019, "V_CMPX_NGE_F32">;
|
|
defm V_CMPX_NLG_F32 : VOPCX_32 <0x0000001a, "V_CMPX_NLG_F32">;
|
|
defm V_CMPX_NGT_F32 : VOPCX_32 <0x0000001b, "V_CMPX_NGT_F32">;
|
|
defm V_CMPX_NLE_F32 : VOPCX_32 <0x0000001c, "V_CMPX_NLE_F32">;
|
|
defm V_CMPX_NEQ_F32 : VOPCX_32 <0x0000001d, "V_CMPX_NEQ_F32">;
|
|
defm V_CMPX_NLT_F32 : VOPCX_32 <0x0000001e, "V_CMPX_NLT_F32">;
|
|
defm V_CMPX_TRU_F32 : VOPCX_32 <0x0000001f, "V_CMPX_TRU_F32">;
|
|
|
|
} // End hasSideEffects = 1
|
|
|
|
defm V_CMP_F_F64 : VOPC_64 <0x00000020, "V_CMP_F_F64">;
|
|
defm V_CMP_LT_F64 : VOPC_64 <0x00000021, "V_CMP_LT_F64", f64, COND_OLT>;
|
|
defm V_CMP_EQ_F64 : VOPC_64 <0x00000022, "V_CMP_EQ_F64", f64, COND_OEQ>;
|
|
defm V_CMP_LE_F64 : VOPC_64 <0x00000023, "V_CMP_LE_F64", f64, COND_OLE>;
|
|
defm V_CMP_GT_F64 : VOPC_64 <0x00000024, "V_CMP_GT_F64", f64, COND_OGT>;
|
|
defm V_CMP_LG_F64 : VOPC_64 <0x00000025, "V_CMP_LG_F64">;
|
|
defm V_CMP_GE_F64 : VOPC_64 <0x00000026, "V_CMP_GE_F64", f64, COND_OGE>;
|
|
defm V_CMP_O_F64 : VOPC_64 <0x00000027, "V_CMP_O_F64", f64, COND_O>;
|
|
defm V_CMP_U_F64 : VOPC_64 <0x00000028, "V_CMP_U_F64", f64, COND_UO>;
|
|
defm V_CMP_NGE_F64 : VOPC_64 <0x00000029, "V_CMP_NGE_F64">;
|
|
defm V_CMP_NLG_F64 : VOPC_64 <0x0000002a, "V_CMP_NLG_F64">;
|
|
defm V_CMP_NGT_F64 : VOPC_64 <0x0000002b, "V_CMP_NGT_F64">;
|
|
defm V_CMP_NLE_F64 : VOPC_64 <0x0000002c, "V_CMP_NLE_F64">;
|
|
defm V_CMP_NEQ_F64 : VOPC_64 <0x0000002d, "V_CMP_NEQ_F64", f64, COND_UNE>;
|
|
defm V_CMP_NLT_F64 : VOPC_64 <0x0000002e, "V_CMP_NLT_F64">;
|
|
defm V_CMP_TRU_F64 : VOPC_64 <0x0000002f, "V_CMP_TRU_F64">;
|
|
|
|
let hasSideEffects = 1 in {
|
|
|
|
defm V_CMPX_F_F64 : VOPCX_64 <0x00000030, "V_CMPX_F_F64">;
|
|
defm V_CMPX_LT_F64 : VOPCX_64 <0x00000031, "V_CMPX_LT_F64">;
|
|
defm V_CMPX_EQ_F64 : VOPCX_64 <0x00000032, "V_CMPX_EQ_F64">;
|
|
defm V_CMPX_LE_F64 : VOPCX_64 <0x00000033, "V_CMPX_LE_F64">;
|
|
defm V_CMPX_GT_F64 : VOPCX_64 <0x00000034, "V_CMPX_GT_F64">;
|
|
defm V_CMPX_LG_F64 : VOPCX_64 <0x00000035, "V_CMPX_LG_F64">;
|
|
defm V_CMPX_GE_F64 : VOPCX_64 <0x00000036, "V_CMPX_GE_F64">;
|
|
defm V_CMPX_O_F64 : VOPCX_64 <0x00000037, "V_CMPX_O_F64">;
|
|
defm V_CMPX_U_F64 : VOPCX_64 <0x00000038, "V_CMPX_U_F64">;
|
|
defm V_CMPX_NGE_F64 : VOPCX_64 <0x00000039, "V_CMPX_NGE_F64">;
|
|
defm V_CMPX_NLG_F64 : VOPCX_64 <0x0000003a, "V_CMPX_NLG_F64">;
|
|
defm V_CMPX_NGT_F64 : VOPCX_64 <0x0000003b, "V_CMPX_NGT_F64">;
|
|
defm V_CMPX_NLE_F64 : VOPCX_64 <0x0000003c, "V_CMPX_NLE_F64">;
|
|
defm V_CMPX_NEQ_F64 : VOPCX_64 <0x0000003d, "V_CMPX_NEQ_F64">;
|
|
defm V_CMPX_NLT_F64 : VOPCX_64 <0x0000003e, "V_CMPX_NLT_F64">;
|
|
defm V_CMPX_TRU_F64 : VOPCX_64 <0x0000003f, "V_CMPX_TRU_F64">;
|
|
|
|
} // End hasSideEffects = 1
|
|
|
|
defm V_CMPS_F_F32 : VOPC_32 <0x00000040, "V_CMPS_F_F32">;
|
|
defm V_CMPS_LT_F32 : VOPC_32 <0x00000041, "V_CMPS_LT_F32">;
|
|
defm V_CMPS_EQ_F32 : VOPC_32 <0x00000042, "V_CMPS_EQ_F32">;
|
|
defm V_CMPS_LE_F32 : VOPC_32 <0x00000043, "V_CMPS_LE_F32">;
|
|
defm V_CMPS_GT_F32 : VOPC_32 <0x00000044, "V_CMPS_GT_F32">;
|
|
defm V_CMPS_LG_F32 : VOPC_32 <0x00000045, "V_CMPS_LG_F32">;
|
|
defm V_CMPS_GE_F32 : VOPC_32 <0x00000046, "V_CMPS_GE_F32">;
|
|
defm V_CMPS_O_F32 : VOPC_32 <0x00000047, "V_CMPS_O_F32">;
|
|
defm V_CMPS_U_F32 : VOPC_32 <0x00000048, "V_CMPS_U_F32">;
|
|
defm V_CMPS_NGE_F32 : VOPC_32 <0x00000049, "V_CMPS_NGE_F32">;
|
|
defm V_CMPS_NLG_F32 : VOPC_32 <0x0000004a, "V_CMPS_NLG_F32">;
|
|
defm V_CMPS_NGT_F32 : VOPC_32 <0x0000004b, "V_CMPS_NGT_F32">;
|
|
defm V_CMPS_NLE_F32 : VOPC_32 <0x0000004c, "V_CMPS_NLE_F32">;
|
|
defm V_CMPS_NEQ_F32 : VOPC_32 <0x0000004d, "V_CMPS_NEQ_F32">;
|
|
defm V_CMPS_NLT_F32 : VOPC_32 <0x0000004e, "V_CMPS_NLT_F32">;
|
|
defm V_CMPS_TRU_F32 : VOPC_32 <0x0000004f, "V_CMPS_TRU_F32">;
|
|
|
|
let hasSideEffects = 1 in {
|
|
|
|
defm V_CMPSX_F_F32 : VOPCX_32 <0x00000050, "V_CMPSX_F_F32">;
|
|
defm V_CMPSX_LT_F32 : VOPCX_32 <0x00000051, "V_CMPSX_LT_F32">;
|
|
defm V_CMPSX_EQ_F32 : VOPCX_32 <0x00000052, "V_CMPSX_EQ_F32">;
|
|
defm V_CMPSX_LE_F32 : VOPCX_32 <0x00000053, "V_CMPSX_LE_F32">;
|
|
defm V_CMPSX_GT_F32 : VOPCX_32 <0x00000054, "V_CMPSX_GT_F32">;
|
|
defm V_CMPSX_LG_F32 : VOPCX_32 <0x00000055, "V_CMPSX_LG_F32">;
|
|
defm V_CMPSX_GE_F32 : VOPCX_32 <0x00000056, "V_CMPSX_GE_F32">;
|
|
defm V_CMPSX_O_F32 : VOPCX_32 <0x00000057, "V_CMPSX_O_F32">;
|
|
defm V_CMPSX_U_F32 : VOPCX_32 <0x00000058, "V_CMPSX_U_F32">;
|
|
defm V_CMPSX_NGE_F32 : VOPCX_32 <0x00000059, "V_CMPSX_NGE_F32">;
|
|
defm V_CMPSX_NLG_F32 : VOPCX_32 <0x0000005a, "V_CMPSX_NLG_F32">;
|
|
defm V_CMPSX_NGT_F32 : VOPCX_32 <0x0000005b, "V_CMPSX_NGT_F32">;
|
|
defm V_CMPSX_NLE_F32 : VOPCX_32 <0x0000005c, "V_CMPSX_NLE_F32">;
|
|
defm V_CMPSX_NEQ_F32 : VOPCX_32 <0x0000005d, "V_CMPSX_NEQ_F32">;
|
|
defm V_CMPSX_NLT_F32 : VOPCX_32 <0x0000005e, "V_CMPSX_NLT_F32">;
|
|
defm V_CMPSX_TRU_F32 : VOPCX_32 <0x0000005f, "V_CMPSX_TRU_F32">;
|
|
|
|
} // End hasSideEffects = 1
|
|
|
|
defm V_CMPS_F_F64 : VOPC_64 <0x00000060, "V_CMPS_F_F64">;
|
|
defm V_CMPS_LT_F64 : VOPC_64 <0x00000061, "V_CMPS_LT_F64">;
|
|
defm V_CMPS_EQ_F64 : VOPC_64 <0x00000062, "V_CMPS_EQ_F64">;
|
|
defm V_CMPS_LE_F64 : VOPC_64 <0x00000063, "V_CMPS_LE_F64">;
|
|
defm V_CMPS_GT_F64 : VOPC_64 <0x00000064, "V_CMPS_GT_F64">;
|
|
defm V_CMPS_LG_F64 : VOPC_64 <0x00000065, "V_CMPS_LG_F64">;
|
|
defm V_CMPS_GE_F64 : VOPC_64 <0x00000066, "V_CMPS_GE_F64">;
|
|
defm V_CMPS_O_F64 : VOPC_64 <0x00000067, "V_CMPS_O_F64">;
|
|
defm V_CMPS_U_F64 : VOPC_64 <0x00000068, "V_CMPS_U_F64">;
|
|
defm V_CMPS_NGE_F64 : VOPC_64 <0x00000069, "V_CMPS_NGE_F64">;
|
|
defm V_CMPS_NLG_F64 : VOPC_64 <0x0000006a, "V_CMPS_NLG_F64">;
|
|
defm V_CMPS_NGT_F64 : VOPC_64 <0x0000006b, "V_CMPS_NGT_F64">;
|
|
defm V_CMPS_NLE_F64 : VOPC_64 <0x0000006c, "V_CMPS_NLE_F64">;
|
|
defm V_CMPS_NEQ_F64 : VOPC_64 <0x0000006d, "V_CMPS_NEQ_F64">;
|
|
defm V_CMPS_NLT_F64 : VOPC_64 <0x0000006e, "V_CMPS_NLT_F64">;
|
|
defm V_CMPS_TRU_F64 : VOPC_64 <0x0000006f, "V_CMPS_TRU_F64">;
|
|
|
|
let hasSideEffects = 1, Defs = [EXEC] in {
|
|
|
|
defm V_CMPSX_F_F64 : VOPC_64 <0x00000070, "V_CMPSX_F_F64">;
|
|
defm V_CMPSX_LT_F64 : VOPC_64 <0x00000071, "V_CMPSX_LT_F64">;
|
|
defm V_CMPSX_EQ_F64 : VOPC_64 <0x00000072, "V_CMPSX_EQ_F64">;
|
|
defm V_CMPSX_LE_F64 : VOPC_64 <0x00000073, "V_CMPSX_LE_F64">;
|
|
defm V_CMPSX_GT_F64 : VOPC_64 <0x00000074, "V_CMPSX_GT_F64">;
|
|
defm V_CMPSX_LG_F64 : VOPC_64 <0x00000075, "V_CMPSX_LG_F64">;
|
|
defm V_CMPSX_GE_F64 : VOPC_64 <0x00000076, "V_CMPSX_GE_F64">;
|
|
defm V_CMPSX_O_F64 : VOPC_64 <0x00000077, "V_CMPSX_O_F64">;
|
|
defm V_CMPSX_U_F64 : VOPC_64 <0x00000078, "V_CMPSX_U_F64">;
|
|
defm V_CMPSX_NGE_F64 : VOPC_64 <0x00000079, "V_CMPSX_NGE_F64">;
|
|
defm V_CMPSX_NLG_F64 : VOPC_64 <0x0000007a, "V_CMPSX_NLG_F64">;
|
|
defm V_CMPSX_NGT_F64 : VOPC_64 <0x0000007b, "V_CMPSX_NGT_F64">;
|
|
defm V_CMPSX_NLE_F64 : VOPC_64 <0x0000007c, "V_CMPSX_NLE_F64">;
|
|
defm V_CMPSX_NEQ_F64 : VOPC_64 <0x0000007d, "V_CMPSX_NEQ_F64">;
|
|
defm V_CMPSX_NLT_F64 : VOPC_64 <0x0000007e, "V_CMPSX_NLT_F64">;
|
|
defm V_CMPSX_TRU_F64 : VOPC_64 <0x0000007f, "V_CMPSX_TRU_F64">;
|
|
|
|
} // End hasSideEffects = 1, Defs = [EXEC]
|
|
|
|
defm V_CMP_F_I32 : VOPC_32 <0x00000080, "V_CMP_F_I32">;
|
|
defm V_CMP_LT_I32 : VOPC_32 <0x00000081, "V_CMP_LT_I32", i32, COND_SLT>;
|
|
defm V_CMP_EQ_I32 : VOPC_32 <0x00000082, "V_CMP_EQ_I32", i32, COND_EQ>;
|
|
defm V_CMP_LE_I32 : VOPC_32 <0x00000083, "V_CMP_LE_I32", i32, COND_SLE>;
|
|
defm V_CMP_GT_I32 : VOPC_32 <0x00000084, "V_CMP_GT_I32", i32, COND_SGT>;
|
|
defm V_CMP_NE_I32 : VOPC_32 <0x00000085, "V_CMP_NE_I32", i32, COND_NE>;
|
|
defm V_CMP_GE_I32 : VOPC_32 <0x00000086, "V_CMP_GE_I32", i32, COND_SGE>;
|
|
defm V_CMP_T_I32 : VOPC_32 <0x00000087, "V_CMP_T_I32">;
|
|
|
|
let hasSideEffects = 1 in {
|
|
|
|
defm V_CMPX_F_I32 : VOPCX_32 <0x00000090, "V_CMPX_F_I32">;
|
|
defm V_CMPX_LT_I32 : VOPCX_32 <0x00000091, "V_CMPX_LT_I32">;
|
|
defm V_CMPX_EQ_I32 : VOPCX_32 <0x00000092, "V_CMPX_EQ_I32">;
|
|
defm V_CMPX_LE_I32 : VOPCX_32 <0x00000093, "V_CMPX_LE_I32">;
|
|
defm V_CMPX_GT_I32 : VOPCX_32 <0x00000094, "V_CMPX_GT_I32">;
|
|
defm V_CMPX_NE_I32 : VOPCX_32 <0x00000095, "V_CMPX_NE_I32">;
|
|
defm V_CMPX_GE_I32 : VOPCX_32 <0x00000096, "V_CMPX_GE_I32">;
|
|
defm V_CMPX_T_I32 : VOPCX_32 <0x00000097, "V_CMPX_T_I32">;
|
|
|
|
} // End hasSideEffects = 1
|
|
|
|
defm V_CMP_F_I64 : VOPC_64 <0x000000a0, "V_CMP_F_I64">;
|
|
defm V_CMP_LT_I64 : VOPC_64 <0x000000a1, "V_CMP_LT_I64", i64, COND_SLT>;
|
|
defm V_CMP_EQ_I64 : VOPC_64 <0x000000a2, "V_CMP_EQ_I64", i64, COND_EQ>;
|
|
defm V_CMP_LE_I64 : VOPC_64 <0x000000a3, "V_CMP_LE_I64", i64, COND_SLE>;
|
|
defm V_CMP_GT_I64 : VOPC_64 <0x000000a4, "V_CMP_GT_I64", i64, COND_SGT>;
|
|
defm V_CMP_NE_I64 : VOPC_64 <0x000000a5, "V_CMP_NE_I64", i64, COND_NE>;
|
|
defm V_CMP_GE_I64 : VOPC_64 <0x000000a6, "V_CMP_GE_I64", i64, COND_SGE>;
|
|
defm V_CMP_T_I64 : VOPC_64 <0x000000a7, "V_CMP_T_I64">;
|
|
|
|
let hasSideEffects = 1 in {
|
|
|
|
defm V_CMPX_F_I64 : VOPCX_64 <0x000000b0, "V_CMPX_F_I64">;
|
|
defm V_CMPX_LT_I64 : VOPCX_64 <0x000000b1, "V_CMPX_LT_I64">;
|
|
defm V_CMPX_EQ_I64 : VOPCX_64 <0x000000b2, "V_CMPX_EQ_I64">;
|
|
defm V_CMPX_LE_I64 : VOPCX_64 <0x000000b3, "V_CMPX_LE_I64">;
|
|
defm V_CMPX_GT_I64 : VOPCX_64 <0x000000b4, "V_CMPX_GT_I64">;
|
|
defm V_CMPX_NE_I64 : VOPCX_64 <0x000000b5, "V_CMPX_NE_I64">;
|
|
defm V_CMPX_GE_I64 : VOPCX_64 <0x000000b6, "V_CMPX_GE_I64">;
|
|
defm V_CMPX_T_I64 : VOPCX_64 <0x000000b7, "V_CMPX_T_I64">;
|
|
|
|
} // End hasSideEffects = 1
|
|
|
|
defm V_CMP_F_U32 : VOPC_32 <0x000000c0, "V_CMP_F_U32">;
|
|
defm V_CMP_LT_U32 : VOPC_32 <0x000000c1, "V_CMP_LT_U32", i32, COND_ULT>;
|
|
defm V_CMP_EQ_U32 : VOPC_32 <0x000000c2, "V_CMP_EQ_U32", i32, COND_EQ>;
|
|
defm V_CMP_LE_U32 : VOPC_32 <0x000000c3, "V_CMP_LE_U32", i32, COND_ULE>;
|
|
defm V_CMP_GT_U32 : VOPC_32 <0x000000c4, "V_CMP_GT_U32", i32, COND_UGT>;
|
|
defm V_CMP_NE_U32 : VOPC_32 <0x000000c5, "V_CMP_NE_U32", i32, COND_NE>;
|
|
defm V_CMP_GE_U32 : VOPC_32 <0x000000c6, "V_CMP_GE_U32", i32, COND_UGE>;
|
|
defm V_CMP_T_U32 : VOPC_32 <0x000000c7, "V_CMP_T_U32">;
|
|
|
|
let hasSideEffects = 1 in {
|
|
|
|
defm V_CMPX_F_U32 : VOPCX_32 <0x000000d0, "V_CMPX_F_U32">;
|
|
defm V_CMPX_LT_U32 : VOPCX_32 <0x000000d1, "V_CMPX_LT_U32">;
|
|
defm V_CMPX_EQ_U32 : VOPCX_32 <0x000000d2, "V_CMPX_EQ_U32">;
|
|
defm V_CMPX_LE_U32 : VOPCX_32 <0x000000d3, "V_CMPX_LE_U32">;
|
|
defm V_CMPX_GT_U32 : VOPCX_32 <0x000000d4, "V_CMPX_GT_U32">;
|
|
defm V_CMPX_NE_U32 : VOPCX_32 <0x000000d5, "V_CMPX_NE_U32">;
|
|
defm V_CMPX_GE_U32 : VOPCX_32 <0x000000d6, "V_CMPX_GE_U32">;
|
|
defm V_CMPX_T_U32 : VOPCX_32 <0x000000d7, "V_CMPX_T_U32">;
|
|
|
|
} // End hasSideEffects = 1
|
|
|
|
defm V_CMP_F_U64 : VOPC_64 <0x000000e0, "V_CMP_F_U64">;
|
|
defm V_CMP_LT_U64 : VOPC_64 <0x000000e1, "V_CMP_LT_U64", i64, COND_ULT>;
|
|
defm V_CMP_EQ_U64 : VOPC_64 <0x000000e2, "V_CMP_EQ_U64", i64, COND_EQ>;
|
|
defm V_CMP_LE_U64 : VOPC_64 <0x000000e3, "V_CMP_LE_U64", i64, COND_ULE>;
|
|
defm V_CMP_GT_U64 : VOPC_64 <0x000000e4, "V_CMP_GT_U64", i64, COND_UGT>;
|
|
defm V_CMP_NE_U64 : VOPC_64 <0x000000e5, "V_CMP_NE_U64", i64, COND_NE>;
|
|
defm V_CMP_GE_U64 : VOPC_64 <0x000000e6, "V_CMP_GE_U64", i64, COND_UGE>;
|
|
defm V_CMP_T_U64 : VOPC_64 <0x000000e7, "V_CMP_T_U64">;
|
|
|
|
let hasSideEffects = 1 in {
|
|
|
|
defm V_CMPX_F_U64 : VOPCX_64 <0x000000f0, "V_CMPX_F_U64">;
|
|
defm V_CMPX_LT_U64 : VOPCX_64 <0x000000f1, "V_CMPX_LT_U64">;
|
|
defm V_CMPX_EQ_U64 : VOPCX_64 <0x000000f2, "V_CMPX_EQ_U64">;
|
|
defm V_CMPX_LE_U64 : VOPCX_64 <0x000000f3, "V_CMPX_LE_U64">;
|
|
defm V_CMPX_GT_U64 : VOPCX_64 <0x000000f4, "V_CMPX_GT_U64">;
|
|
defm V_CMPX_NE_U64 : VOPCX_64 <0x000000f5, "V_CMPX_NE_U64">;
|
|
defm V_CMPX_GE_U64 : VOPCX_64 <0x000000f6, "V_CMPX_GE_U64">;
|
|
defm V_CMPX_T_U64 : VOPCX_64 <0x000000f7, "V_CMPX_T_U64">;
|
|
|
|
} // End hasSideEffects = 1
|
|
|
|
defm V_CMP_CLASS_F32 : VOPC_32 <0x00000088, "V_CMP_CLASS_F32">;
|
|
|
|
let hasSideEffects = 1 in {
|
|
defm V_CMPX_CLASS_F32 : VOPCX_32 <0x00000098, "V_CMPX_CLASS_F32">;
|
|
} // End hasSideEffects = 1
|
|
|
|
defm V_CMP_CLASS_F64 : VOPC_64 <0x000000a8, "V_CMP_CLASS_F64">;
|
|
|
|
let hasSideEffects = 1 in {
|
|
defm V_CMPX_CLASS_F64 : VOPCX_64 <0x000000b8, "V_CMPX_CLASS_F64">;
|
|
} // End hasSideEffects = 1
|
|
|
|
} // End isCompare = 1
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// DS Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
def DS_ADD_U32 : DS_1A1D_NORET <0x0, "DS_ADD_U32", VReg_32>;
|
|
def DS_SUB_U32 : DS_1A1D_NORET <0x1, "DS_SUB_U32", VReg_32>;
|
|
def DS_RSUB_U32 : DS_1A1D_NORET <0x2, "DS_RSUB_U32", VReg_32>;
|
|
def DS_INC_U32 : DS_1A1D_NORET <0x3, "DS_INC_U32", VReg_32>;
|
|
def DS_DEC_U32 : DS_1A1D_NORET <0x4, "DS_DEC_U32", VReg_32>;
|
|
def DS_MIN_I32 : DS_1A1D_NORET <0x5, "DS_MIN_I32", VReg_32>;
|
|
def DS_MAX_I32 : DS_1A1D_NORET <0x6, "DS_MAX_I32", VReg_32>;
|
|
def DS_MIN_U32 : DS_1A1D_NORET <0x7, "DS_MIN_U32", VReg_32>;
|
|
def DS_MAX_U32 : DS_1A1D_NORET <0x8, "DS_MAX_U32", VReg_32>;
|
|
def DS_AND_B32 : DS_1A1D_NORET <0x9, "DS_AND_B32", VReg_32>;
|
|
def DS_OR_B32 : DS_1A1D_NORET <0xa, "DS_OR_B32", VReg_32>;
|
|
def DS_XOR_B32 : DS_1A1D_NORET <0xb, "DS_XOR_B32", VReg_32>;
|
|
def DS_MSKOR_B32 : DS_1A1D_NORET <0xc, "DS_MSKOR_B32", VReg_32>;
|
|
def DS_CMPST_B32 : DS_1A2D_NORET <0x10, "DS_CMPST_B32", VReg_32>;
|
|
def DS_CMPST_F32 : DS_1A2D_NORET <0x11, "DS_CMPST_F32", VReg_32>;
|
|
def DS_MIN_F32 : DS_1A1D_NORET <0x12, "DS_MIN_F32", VReg_32>;
|
|
def DS_MAX_F32 : DS_1A1D_NORET <0x13, "DS_MAX_F32", VReg_32>;
|
|
|
|
def DS_ADD_RTN_U32 : DS_1A1D_RET <0x20, "DS_ADD_RTN_U32", VReg_32>;
|
|
def DS_SUB_RTN_U32 : DS_1A1D_RET <0x21, "DS_SUB_RTN_U32", VReg_32>;
|
|
def DS_RSUB_RTN_U32 : DS_1A1D_RET <0x22, "DS_RSUB_RTN_U32", VReg_32>;
|
|
def DS_INC_RTN_U32 : DS_1A1D_RET <0x23, "DS_INC_RTN_U32", VReg_32>;
|
|
def DS_DEC_RTN_U32 : DS_1A1D_RET <0x24, "DS_DEC_RTN_U32", VReg_32>;
|
|
def DS_MIN_RTN_I32 : DS_1A1D_RET <0x25, "DS_MIN_RTN_I32", VReg_32>;
|
|
def DS_MAX_RTN_I32 : DS_1A1D_RET <0x26, "DS_MAX_RTN_I32", VReg_32>;
|
|
def DS_MIN_RTN_U32 : DS_1A1D_RET <0x27, "DS_MIN_RTN_U32", VReg_32>;
|
|
def DS_MAX_RTN_U32 : DS_1A1D_RET <0x28, "DS_MAX_RTN_U32", VReg_32>;
|
|
def DS_AND_RTN_B32 : DS_1A1D_RET <0x29, "DS_AND_RTN_B32", VReg_32>;
|
|
def DS_OR_RTN_B32 : DS_1A1D_RET <0x2a, "DS_OR_RTN_B32", VReg_32>;
|
|
def DS_XOR_RTN_B32 : DS_1A1D_RET <0x2b, "DS_XOR_RTN_B32", VReg_32>;
|
|
def DS_MSKOR_RTN_B32 : DS_1A1D_RET <0x2c, "DS_MSKOR_RTN_B32", VReg_32>;
|
|
def DS_WRXCHG_RTN_B32 : DS_1A1D_RET <0x2d, "DS_WRXCHG_RTN_B32", VReg_32>;
|
|
//def DS_WRXCHG2_RTN_B32 : DS_2A0D_RET <0x2e, "DS_WRXCHG2_RTN_B32", VReg_32>;
|
|
//def DS_WRXCHG2ST64_RTN_B32 : DS_2A0D_RET <0x2f, "DS_WRXCHG2_RTN_B32", VReg_32>;
|
|
def DS_CMPST_RTN_B32 : DS_1A2D_RET <0x30, "DS_CMPST_RTN_B32", VReg_32>;
|
|
def DS_CMPST_RTN_F32 : DS_1A2D_RET <0x31, "DS_CMPST_RTN_F32", VReg_32>;
|
|
def DS_MIN_RTN_F32 : DS_1A1D_RET <0x32, "DS_MIN_RTN_F32", VReg_32>;
|
|
def DS_MAX_RTN_F32 : DS_1A1D_RET <0x33, "DS_MAX_RTN_F32", VReg_32>;
|
|
|
|
let SubtargetPredicate = isCI in {
|
|
def DS_WRAP_RTN_F32 : DS_1A1D_RET <0x34, "DS_WRAP_RTN_F32", VReg_32>;
|
|
} // End isCI
|
|
|
|
|
|
def DS_ADD_U64 : DS_1A1D_NORET <0x40, "DS_ADD_U64", VReg_32>;
|
|
def DS_SUB_U64 : DS_1A1D_NORET <0x41, "DS_SUB_U64", VReg_32>;
|
|
def DS_RSUB_U64 : DS_1A1D_NORET <0x42, "DS_RSUB_U64", VReg_32>;
|
|
def DS_INC_U64 : DS_1A1D_NORET <0x43, "DS_INC_U64", VReg_32>;
|
|
def DS_DEC_U64 : DS_1A1D_NORET <0x44, "DS_DEC_U64", VReg_32>;
|
|
def DS_MIN_I64 : DS_1A1D_NORET <0x45, "DS_MIN_I64", VReg_64>;
|
|
def DS_MAX_I64 : DS_1A1D_NORET <0x46, "DS_MAX_I64", VReg_64>;
|
|
def DS_MIN_U64 : DS_1A1D_NORET <0x47, "DS_MIN_U64", VReg_64>;
|
|
def DS_MAX_U64 : DS_1A1D_NORET <0x48, "DS_MAX_U64", VReg_64>;
|
|
def DS_AND_B64 : DS_1A1D_NORET <0x49, "DS_AND_B64", VReg_64>;
|
|
def DS_OR_B64 : DS_1A1D_NORET <0x4a, "DS_OR_B64", VReg_64>;
|
|
def DS_XOR_B64 : DS_1A1D_NORET <0x4b, "DS_XOR_B64", VReg_64>;
|
|
def DS_MSKOR_B64 : DS_1A1D_NORET <0x4c, "DS_MSKOR_B64", VReg_64>;
|
|
def DS_CMPST_B64 : DS_1A2D_NORET <0x50, "DS_CMPST_B64", VReg_64>;
|
|
def DS_CMPST_F64 : DS_1A2D_NORET <0x51, "DS_CMPST_F64", VReg_64>;
|
|
def DS_MIN_F64 : DS_1A1D_NORET <0x52, "DS_MIN_F64", VReg_64>;
|
|
def DS_MAX_F64 : DS_1A1D_NORET <0x53, "DS_MAX_F64", VReg_64>;
|
|
|
|
def DS_ADD_RTN_U64 : DS_1A1D_RET <0x60, "DS_ADD_RTN_U64", VReg_64>;
|
|
def DS_SUB_RTN_U64 : DS_1A1D_RET <0x61, "DS_SUB_RTN_U64", VReg_64>;
|
|
def DS_RSUB_RTN_U64 : DS_1A1D_RET <0x62, "DS_RSUB_RTN_U64", VReg_64>;
|
|
def DS_INC_RTN_U64 : DS_1A1D_RET <0x63, "DS_INC_RTN_U64", VReg_64>;
|
|
def DS_DEC_RTN_U64 : DS_1A1D_RET <0x64, "DS_DEC_RTN_U64", VReg_64>;
|
|
def DS_MIN_RTN_I64 : DS_1A1D_RET <0x65, "DS_MIN_RTN_I64", VReg_64>;
|
|
def DS_MAX_RTN_I64 : DS_1A1D_RET <0x66, "DS_MAX_RTN_I64", VReg_64>;
|
|
def DS_MIN_RTN_U64 : DS_1A1D_RET <0x67, "DS_MIN_RTN_U64", VReg_64>;
|
|
def DS_MAX_RTN_U64 : DS_1A1D_RET <0x68, "DS_MAX_RTN_U64", VReg_64>;
|
|
def DS_AND_RTN_B64 : DS_1A1D_RET <0x69, "DS_AND_RTN_B64", VReg_64>;
|
|
def DS_OR_RTN_B64 : DS_1A1D_RET <0x6a, "DS_OR_RTN_B64", VReg_64>;
|
|
def DS_XOR_RTN_B64 : DS_1A1D_RET <0x6b, "DS_XOR_RTN_B64", VReg_64>;
|
|
def DS_MSKOR_RTN_B64 : DS_1A1D_RET <0x6c, "DS_MSKOR_RTN_B64", VReg_64>;
|
|
def DS_WRXCHG_RTN_B64 : DS_1A1D_RET <0x6d, "DS_WRXCHG_RTN_B64", VReg_64>;
|
|
//def DS_WRXCHG2_RTN_B64 : DS_2A0D_RET <0x6e, "DS_WRXCHG2_RTN_B64", VReg_64>;
|
|
//def DS_WRXCHG2ST64_RTN_B64 : DS_2A0D_RET <0x6f, "DS_WRXCHG2_RTN_B64", VReg_64>;
|
|
def DS_CMPST_RTN_B64 : DS_1A2D_RET <0x70, "DS_CMPST_RTN_B64", VReg_64>;
|
|
def DS_CMPST_RTN_F64 : DS_1A2D_RET <0x71, "DS_CMPST_RTN_F64", VReg_64>;
|
|
def DS_MIN_RTN_F64 : DS_1A1D_RET <0x72, "DS_MIN_F64", VReg_64>;
|
|
def DS_MAX_RTN_F64 : DS_1A1D_RET <0x73, "DS_MAX_F64", VReg_64>;
|
|
|
|
//let SubtargetPredicate = isCI in {
|
|
// DS_CONDXCHG32_RTN_B64
|
|
// DS_CONDXCHG32_RTN_B128
|
|
//} // End isCI
|
|
|
|
// TODO: _SRC2_* forms
|
|
|
|
def DS_WRITE_B32 : DS_Store_Helper <0x0000000d, "DS_WRITE_B32", VReg_32>;
|
|
def DS_WRITE_B8 : DS_Store_Helper <0x00000001e, "DS_WRITE_B8", VReg_32>;
|
|
def DS_WRITE_B16 : DS_Store_Helper <0x00000001f, "DS_WRITE_B16", VReg_32>;
|
|
def DS_WRITE_B64 : DS_Store_Helper <0x00000004d, "DS_WRITE_B64", VReg_64>;
|
|
|
|
def DS_READ_B32 : DS_Load_Helper <0x00000036, "DS_READ_B32", VReg_32>;
|
|
def DS_READ_I8 : DS_Load_Helper <0x00000039, "DS_READ_I8", VReg_32>;
|
|
def DS_READ_U8 : DS_Load_Helper <0x0000003a, "DS_READ_U8", VReg_32>;
|
|
def DS_READ_I16 : DS_Load_Helper <0x0000003b, "DS_READ_I16", VReg_32>;
|
|
def DS_READ_U16 : DS_Load_Helper <0x0000003c, "DS_READ_U16", VReg_32>;
|
|
def DS_READ_B64 : DS_Load_Helper <0x00000076, "DS_READ_B64", VReg_64>;
|
|
|
|
// 2 forms.
|
|
def DS_WRITE2_B32 : DS_Load2_Helper <0x0000000E, "DS_WRITE2_B32", VReg_64>;
|
|
def DS_WRITE2_B64 : DS_Load2_Helper <0x0000004E, "DS_WRITE2_B64", VReg_128>;
|
|
|
|
def DS_READ2_B32 : DS_Load2_Helper <0x00000037, "DS_READ2_B32", VReg_64>;
|
|
def DS_READ2_B64 : DS_Load2_Helper <0x00000075, "DS_READ2_B64", VReg_128>;
|
|
|
|
// TODO: DS_READ2ST64_B32, DS_READ2ST64_B64,
|
|
// DS_WRITE2ST64_B32, DS_WRITE2ST64_B64
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// MUBUF Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//def BUFFER_LOAD_FORMAT_X : MUBUF_ <0x00000000, "BUFFER_LOAD_FORMAT_X", []>;
|
|
//def BUFFER_LOAD_FORMAT_XY : MUBUF_ <0x00000001, "BUFFER_LOAD_FORMAT_XY", []>;
|
|
//def BUFFER_LOAD_FORMAT_XYZ : MUBUF_ <0x00000002, "BUFFER_LOAD_FORMAT_XYZ", []>;
|
|
defm BUFFER_LOAD_FORMAT_XYZW : MUBUF_Load_Helper <0x00000003, "BUFFER_LOAD_FORMAT_XYZW", VReg_128>;
|
|
//def BUFFER_STORE_FORMAT_X : MUBUF_ <0x00000004, "BUFFER_STORE_FORMAT_X", []>;
|
|
//def BUFFER_STORE_FORMAT_XY : MUBUF_ <0x00000005, "BUFFER_STORE_FORMAT_XY", []>;
|
|
//def BUFFER_STORE_FORMAT_XYZ : MUBUF_ <0x00000006, "BUFFER_STORE_FORMAT_XYZ", []>;
|
|
//def BUFFER_STORE_FORMAT_XYZW : MUBUF_ <0x00000007, "BUFFER_STORE_FORMAT_XYZW", []>;
|
|
defm BUFFER_LOAD_UBYTE : MUBUF_Load_Helper <
|
|
0x00000008, "BUFFER_LOAD_UBYTE", VReg_32, i32, az_extloadi8_global
|
|
>;
|
|
defm BUFFER_LOAD_SBYTE : MUBUF_Load_Helper <
|
|
0x00000009, "BUFFER_LOAD_SBYTE", VReg_32, i32, sextloadi8_global
|
|
>;
|
|
defm BUFFER_LOAD_USHORT : MUBUF_Load_Helper <
|
|
0x0000000a, "BUFFER_LOAD_USHORT", VReg_32, i32, az_extloadi16_global
|
|
>;
|
|
defm BUFFER_LOAD_SSHORT : MUBUF_Load_Helper <
|
|
0x0000000b, "BUFFER_LOAD_SSHORT", VReg_32, i32, sextloadi16_global
|
|
>;
|
|
defm BUFFER_LOAD_DWORD : MUBUF_Load_Helper <
|
|
0x0000000c, "BUFFER_LOAD_DWORD", VReg_32, i32, global_load
|
|
>;
|
|
defm BUFFER_LOAD_DWORDX2 : MUBUF_Load_Helper <
|
|
0x0000000d, "BUFFER_LOAD_DWORDX2", VReg_64, v2i32, global_load
|
|
>;
|
|
defm BUFFER_LOAD_DWORDX4 : MUBUF_Load_Helper <
|
|
0x0000000e, "BUFFER_LOAD_DWORDX4", VReg_128, v4i32, global_load
|
|
>;
|
|
|
|
def BUFFER_STORE_BYTE : MUBUF_Store_Helper <
|
|
0x00000018, "BUFFER_STORE_BYTE", VReg_32, i32, truncstorei8_global
|
|
>;
|
|
|
|
def BUFFER_STORE_SHORT : MUBUF_Store_Helper <
|
|
0x0000001a, "BUFFER_STORE_SHORT", VReg_32, i32, truncstorei16_global
|
|
>;
|
|
|
|
def BUFFER_STORE_DWORD : MUBUF_Store_Helper <
|
|
0x0000001c, "BUFFER_STORE_DWORD", VReg_32, i32, global_store
|
|
>;
|
|
|
|
def BUFFER_STORE_DWORDX2 : MUBUF_Store_Helper <
|
|
0x0000001d, "BUFFER_STORE_DWORDX2", VReg_64, v2i32, global_store
|
|
>;
|
|
|
|
def BUFFER_STORE_DWORDX4 : MUBUF_Store_Helper <
|
|
0x0000001e, "BUFFER_STORE_DWORDX4", VReg_128, v4i32, global_store
|
|
>;
|
|
//def BUFFER_ATOMIC_SWAP : MUBUF_ <0x00000030, "BUFFER_ATOMIC_SWAP", []>;
|
|
//def BUFFER_ATOMIC_CMPSWAP : MUBUF_ <0x00000031, "BUFFER_ATOMIC_CMPSWAP", []>;
|
|
//def BUFFER_ATOMIC_ADD : MUBUF_ <0x00000032, "BUFFER_ATOMIC_ADD", []>;
|
|
//def BUFFER_ATOMIC_SUB : MUBUF_ <0x00000033, "BUFFER_ATOMIC_SUB", []>;
|
|
//def BUFFER_ATOMIC_RSUB : MUBUF_ <0x00000034, "BUFFER_ATOMIC_RSUB", []>;
|
|
//def BUFFER_ATOMIC_SMIN : MUBUF_ <0x00000035, "BUFFER_ATOMIC_SMIN", []>;
|
|
//def BUFFER_ATOMIC_UMIN : MUBUF_ <0x00000036, "BUFFER_ATOMIC_UMIN", []>;
|
|
//def BUFFER_ATOMIC_SMAX : MUBUF_ <0x00000037, "BUFFER_ATOMIC_SMAX", []>;
|
|
//def BUFFER_ATOMIC_UMAX : MUBUF_ <0x00000038, "BUFFER_ATOMIC_UMAX", []>;
|
|
//def BUFFER_ATOMIC_AND : MUBUF_ <0x00000039, "BUFFER_ATOMIC_AND", []>;
|
|
//def BUFFER_ATOMIC_OR : MUBUF_ <0x0000003a, "BUFFER_ATOMIC_OR", []>;
|
|
//def BUFFER_ATOMIC_XOR : MUBUF_ <0x0000003b, "BUFFER_ATOMIC_XOR", []>;
|
|
//def BUFFER_ATOMIC_INC : MUBUF_ <0x0000003c, "BUFFER_ATOMIC_INC", []>;
|
|
//def BUFFER_ATOMIC_DEC : MUBUF_ <0x0000003d, "BUFFER_ATOMIC_DEC", []>;
|
|
//def BUFFER_ATOMIC_FCMPSWAP : MUBUF_ <0x0000003e, "BUFFER_ATOMIC_FCMPSWAP", []>;
|
|
//def BUFFER_ATOMIC_FMIN : MUBUF_ <0x0000003f, "BUFFER_ATOMIC_FMIN", []>;
|
|
//def BUFFER_ATOMIC_FMAX : MUBUF_ <0x00000040, "BUFFER_ATOMIC_FMAX", []>;
|
|
//def BUFFER_ATOMIC_SWAP_X2 : MUBUF_X2 <0x00000050, "BUFFER_ATOMIC_SWAP_X2", []>;
|
|
//def BUFFER_ATOMIC_CMPSWAP_X2 : MUBUF_X2 <0x00000051, "BUFFER_ATOMIC_CMPSWAP_X2", []>;
|
|
//def BUFFER_ATOMIC_ADD_X2 : MUBUF_X2 <0x00000052, "BUFFER_ATOMIC_ADD_X2", []>;
|
|
//def BUFFER_ATOMIC_SUB_X2 : MUBUF_X2 <0x00000053, "BUFFER_ATOMIC_SUB_X2", []>;
|
|
//def BUFFER_ATOMIC_RSUB_X2 : MUBUF_X2 <0x00000054, "BUFFER_ATOMIC_RSUB_X2", []>;
|
|
//def BUFFER_ATOMIC_SMIN_X2 : MUBUF_X2 <0x00000055, "BUFFER_ATOMIC_SMIN_X2", []>;
|
|
//def BUFFER_ATOMIC_UMIN_X2 : MUBUF_X2 <0x00000056, "BUFFER_ATOMIC_UMIN_X2", []>;
|
|
//def BUFFER_ATOMIC_SMAX_X2 : MUBUF_X2 <0x00000057, "BUFFER_ATOMIC_SMAX_X2", []>;
|
|
//def BUFFER_ATOMIC_UMAX_X2 : MUBUF_X2 <0x00000058, "BUFFER_ATOMIC_UMAX_X2", []>;
|
|
//def BUFFER_ATOMIC_AND_X2 : MUBUF_X2 <0x00000059, "BUFFER_ATOMIC_AND_X2", []>;
|
|
//def BUFFER_ATOMIC_OR_X2 : MUBUF_X2 <0x0000005a, "BUFFER_ATOMIC_OR_X2", []>;
|
|
//def BUFFER_ATOMIC_XOR_X2 : MUBUF_X2 <0x0000005b, "BUFFER_ATOMIC_XOR_X2", []>;
|
|
//def BUFFER_ATOMIC_INC_X2 : MUBUF_X2 <0x0000005c, "BUFFER_ATOMIC_INC_X2", []>;
|
|
//def BUFFER_ATOMIC_DEC_X2 : MUBUF_X2 <0x0000005d, "BUFFER_ATOMIC_DEC_X2", []>;
|
|
//def BUFFER_ATOMIC_FCMPSWAP_X2 : MUBUF_X2 <0x0000005e, "BUFFER_ATOMIC_FCMPSWAP_X2", []>;
|
|
//def BUFFER_ATOMIC_FMIN_X2 : MUBUF_X2 <0x0000005f, "BUFFER_ATOMIC_FMIN_X2", []>;
|
|
//def BUFFER_ATOMIC_FMAX_X2 : MUBUF_X2 <0x00000060, "BUFFER_ATOMIC_FMAX_X2", []>;
|
|
//def BUFFER_WBINVL1_SC : MUBUF_WBINVL1 <0x00000070, "BUFFER_WBINVL1_SC", []>;
|
|
//def BUFFER_WBINVL1 : MUBUF_WBINVL1 <0x00000071, "BUFFER_WBINVL1", []>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// MTBUF Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//def TBUFFER_LOAD_FORMAT_X : MTBUF_ <0x00000000, "TBUFFER_LOAD_FORMAT_X", []>;
|
|
//def TBUFFER_LOAD_FORMAT_XY : MTBUF_ <0x00000001, "TBUFFER_LOAD_FORMAT_XY", []>;
|
|
//def TBUFFER_LOAD_FORMAT_XYZ : MTBUF_ <0x00000002, "TBUFFER_LOAD_FORMAT_XYZ", []>;
|
|
def TBUFFER_LOAD_FORMAT_XYZW : MTBUF_Load_Helper <0x00000003, "TBUFFER_LOAD_FORMAT_XYZW", VReg_128>;
|
|
def TBUFFER_STORE_FORMAT_X : MTBUF_Store_Helper <0x00000004, "TBUFFER_STORE_FORMAT_X", VReg_32>;
|
|
def TBUFFER_STORE_FORMAT_XY : MTBUF_Store_Helper <0x00000005, "TBUFFER_STORE_FORMAT_XY", VReg_64>;
|
|
def TBUFFER_STORE_FORMAT_XYZ : MTBUF_Store_Helper <0x00000006, "TBUFFER_STORE_FORMAT_XYZ", VReg_128>;
|
|
def TBUFFER_STORE_FORMAT_XYZW : MTBUF_Store_Helper <0x00000007, "TBUFFER_STORE_FORMAT_XYZW", VReg_128>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// MIMG Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
defm IMAGE_LOAD : MIMG_NoSampler <0x00000000, "IMAGE_LOAD">;
|
|
defm IMAGE_LOAD_MIP : MIMG_NoSampler <0x00000001, "IMAGE_LOAD_MIP">;
|
|
//def IMAGE_LOAD_PCK : MIMG_NoPattern_ <"IMAGE_LOAD_PCK", 0x00000002>;
|
|
//def IMAGE_LOAD_PCK_SGN : MIMG_NoPattern_ <"IMAGE_LOAD_PCK_SGN", 0x00000003>;
|
|
//def IMAGE_LOAD_MIP_PCK : MIMG_NoPattern_ <"IMAGE_LOAD_MIP_PCK", 0x00000004>;
|
|
//def IMAGE_LOAD_MIP_PCK_SGN : MIMG_NoPattern_ <"IMAGE_LOAD_MIP_PCK_SGN", 0x00000005>;
|
|
//def IMAGE_STORE : MIMG_NoPattern_ <"IMAGE_STORE", 0x00000008>;
|
|
//def IMAGE_STORE_MIP : MIMG_NoPattern_ <"IMAGE_STORE_MIP", 0x00000009>;
|
|
//def IMAGE_STORE_PCK : MIMG_NoPattern_ <"IMAGE_STORE_PCK", 0x0000000a>;
|
|
//def IMAGE_STORE_MIP_PCK : MIMG_NoPattern_ <"IMAGE_STORE_MIP_PCK", 0x0000000b>;
|
|
defm IMAGE_GET_RESINFO : MIMG_NoSampler <0x0000000e, "IMAGE_GET_RESINFO">;
|
|
//def IMAGE_ATOMIC_SWAP : MIMG_NoPattern_ <"IMAGE_ATOMIC_SWAP", 0x0000000f>;
|
|
//def IMAGE_ATOMIC_CMPSWAP : MIMG_NoPattern_ <"IMAGE_ATOMIC_CMPSWAP", 0x00000010>;
|
|
//def IMAGE_ATOMIC_ADD : MIMG_NoPattern_ <"IMAGE_ATOMIC_ADD", 0x00000011>;
|
|
//def IMAGE_ATOMIC_SUB : MIMG_NoPattern_ <"IMAGE_ATOMIC_SUB", 0x00000012>;
|
|
//def IMAGE_ATOMIC_RSUB : MIMG_NoPattern_ <"IMAGE_ATOMIC_RSUB", 0x00000013>;
|
|
//def IMAGE_ATOMIC_SMIN : MIMG_NoPattern_ <"IMAGE_ATOMIC_SMIN", 0x00000014>;
|
|
//def IMAGE_ATOMIC_UMIN : MIMG_NoPattern_ <"IMAGE_ATOMIC_UMIN", 0x00000015>;
|
|
//def IMAGE_ATOMIC_SMAX : MIMG_NoPattern_ <"IMAGE_ATOMIC_SMAX", 0x00000016>;
|
|
//def IMAGE_ATOMIC_UMAX : MIMG_NoPattern_ <"IMAGE_ATOMIC_UMAX", 0x00000017>;
|
|
//def IMAGE_ATOMIC_AND : MIMG_NoPattern_ <"IMAGE_ATOMIC_AND", 0x00000018>;
|
|
//def IMAGE_ATOMIC_OR : MIMG_NoPattern_ <"IMAGE_ATOMIC_OR", 0x00000019>;
|
|
//def IMAGE_ATOMIC_XOR : MIMG_NoPattern_ <"IMAGE_ATOMIC_XOR", 0x0000001a>;
|
|
//def IMAGE_ATOMIC_INC : MIMG_NoPattern_ <"IMAGE_ATOMIC_INC", 0x0000001b>;
|
|
//def IMAGE_ATOMIC_DEC : MIMG_NoPattern_ <"IMAGE_ATOMIC_DEC", 0x0000001c>;
|
|
//def IMAGE_ATOMIC_FCMPSWAP : MIMG_NoPattern_ <"IMAGE_ATOMIC_FCMPSWAP", 0x0000001d>;
|
|
//def IMAGE_ATOMIC_FMIN : MIMG_NoPattern_ <"IMAGE_ATOMIC_FMIN", 0x0000001e>;
|
|
//def IMAGE_ATOMIC_FMAX : MIMG_NoPattern_ <"IMAGE_ATOMIC_FMAX", 0x0000001f>;
|
|
defm IMAGE_SAMPLE : MIMG_Sampler <0x00000020, "IMAGE_SAMPLE">;
|
|
defm IMAGE_SAMPLE_CL : MIMG_Sampler <0x00000021, "IMAGE_SAMPLE_CL">;
|
|
defm IMAGE_SAMPLE_D : MIMG_Sampler <0x00000022, "IMAGE_SAMPLE_D">;
|
|
defm IMAGE_SAMPLE_D_CL : MIMG_Sampler <0x00000023, "IMAGE_SAMPLE_D_CL">;
|
|
defm IMAGE_SAMPLE_L : MIMG_Sampler <0x00000024, "IMAGE_SAMPLE_L">;
|
|
defm IMAGE_SAMPLE_B : MIMG_Sampler <0x00000025, "IMAGE_SAMPLE_B">;
|
|
defm IMAGE_SAMPLE_B_CL : MIMG_Sampler <0x00000026, "IMAGE_SAMPLE_B_CL">;
|
|
defm IMAGE_SAMPLE_LZ : MIMG_Sampler <0x00000027, "IMAGE_SAMPLE_LZ">;
|
|
defm IMAGE_SAMPLE_C : MIMG_Sampler <0x00000028, "IMAGE_SAMPLE_C">;
|
|
defm IMAGE_SAMPLE_C_CL : MIMG_Sampler <0x00000029, "IMAGE_SAMPLE_C_CL">;
|
|
defm IMAGE_SAMPLE_C_D : MIMG_Sampler <0x0000002a, "IMAGE_SAMPLE_C_D">;
|
|
defm IMAGE_SAMPLE_C_D_CL : MIMG_Sampler <0x0000002b, "IMAGE_SAMPLE_C_D_CL">;
|
|
defm IMAGE_SAMPLE_C_L : MIMG_Sampler <0x0000002c, "IMAGE_SAMPLE_C_L">;
|
|
defm IMAGE_SAMPLE_C_B : MIMG_Sampler <0x0000002d, "IMAGE_SAMPLE_C_B">;
|
|
defm IMAGE_SAMPLE_C_B_CL : MIMG_Sampler <0x0000002e, "IMAGE_SAMPLE_C_B_CL">;
|
|
defm IMAGE_SAMPLE_C_LZ : MIMG_Sampler <0x0000002f, "IMAGE_SAMPLE_C_LZ">;
|
|
defm IMAGE_SAMPLE_O : MIMG_Sampler <0x00000030, "IMAGE_SAMPLE_O">;
|
|
defm IMAGE_SAMPLE_CL_O : MIMG_Sampler <0x00000031, "IMAGE_SAMPLE_CL_O">;
|
|
defm IMAGE_SAMPLE_D_O : MIMG_Sampler <0x00000032, "IMAGE_SAMPLE_D_O">;
|
|
defm IMAGE_SAMPLE_D_CL_O : MIMG_Sampler <0x00000033, "IMAGE_SAMPLE_D_CL_O">;
|
|
defm IMAGE_SAMPLE_L_O : MIMG_Sampler <0x00000034, "IMAGE_SAMPLE_L_O">;
|
|
defm IMAGE_SAMPLE_B_O : MIMG_Sampler <0x00000035, "IMAGE_SAMPLE_B_O">;
|
|
defm IMAGE_SAMPLE_B_CL_O : MIMG_Sampler <0x00000036, "IMAGE_SAMPLE_B_CL_O">;
|
|
defm IMAGE_SAMPLE_LZ_O : MIMG_Sampler <0x00000037, "IMAGE_SAMPLE_LZ_O">;
|
|
defm IMAGE_SAMPLE_C_O : MIMG_Sampler <0x00000038, "IMAGE_SAMPLE_C_O">;
|
|
defm IMAGE_SAMPLE_C_CL_O : MIMG_Sampler <0x00000039, "IMAGE_SAMPLE_C_CL_O">;
|
|
defm IMAGE_SAMPLE_C_D_O : MIMG_Sampler <0x0000003a, "IMAGE_SAMPLE_C_D_O">;
|
|
defm IMAGE_SAMPLE_C_D_CL_O : MIMG_Sampler <0x0000003b, "IMAGE_SAMPLE_C_D_CL_O">;
|
|
defm IMAGE_SAMPLE_C_L_O : MIMG_Sampler <0x0000003c, "IMAGE_SAMPLE_C_L_O">;
|
|
defm IMAGE_SAMPLE_C_B_O : MIMG_Sampler <0x0000003d, "IMAGE_SAMPLE_C_B_O">;
|
|
defm IMAGE_SAMPLE_C_B_CL_O : MIMG_Sampler <0x0000003e, "IMAGE_SAMPLE_C_B_CL_O">;
|
|
defm IMAGE_SAMPLE_C_LZ_O : MIMG_Sampler <0x0000003f, "IMAGE_SAMPLE_C_LZ_O">;
|
|
defm IMAGE_GATHER4 : MIMG_Gather <0x00000040, "IMAGE_GATHER4">;
|
|
defm IMAGE_GATHER4_CL : MIMG_Gather <0x00000041, "IMAGE_GATHER4_CL">;
|
|
defm IMAGE_GATHER4_L : MIMG_Gather <0x00000044, "IMAGE_GATHER4_L">;
|
|
defm IMAGE_GATHER4_B : MIMG_Gather <0x00000045, "IMAGE_GATHER4_B">;
|
|
defm IMAGE_GATHER4_B_CL : MIMG_Gather <0x00000046, "IMAGE_GATHER4_B_CL">;
|
|
defm IMAGE_GATHER4_LZ : MIMG_Gather <0x00000047, "IMAGE_GATHER4_LZ">;
|
|
defm IMAGE_GATHER4_C : MIMG_Gather <0x00000048, "IMAGE_GATHER4_C">;
|
|
defm IMAGE_GATHER4_C_CL : MIMG_Gather <0x00000049, "IMAGE_GATHER4_C_CL">;
|
|
defm IMAGE_GATHER4_C_L : MIMG_Gather <0x0000004c, "IMAGE_GATHER4_C_L">;
|
|
defm IMAGE_GATHER4_C_B : MIMG_Gather <0x0000004d, "IMAGE_GATHER4_C_B">;
|
|
defm IMAGE_GATHER4_C_B_CL : MIMG_Gather <0x0000004e, "IMAGE_GATHER4_C_B_CL">;
|
|
defm IMAGE_GATHER4_C_LZ : MIMG_Gather <0x0000004f, "IMAGE_GATHER4_C_LZ">;
|
|
defm IMAGE_GATHER4_O : MIMG_Gather <0x00000050, "IMAGE_GATHER4_O">;
|
|
defm IMAGE_GATHER4_CL_O : MIMG_Gather <0x00000051, "IMAGE_GATHER4_CL_O">;
|
|
defm IMAGE_GATHER4_L_O : MIMG_Gather <0x00000054, "IMAGE_GATHER4_L_O">;
|
|
defm IMAGE_GATHER4_B_O : MIMG_Gather <0x00000055, "IMAGE_GATHER4_B_O">;
|
|
defm IMAGE_GATHER4_B_CL_O : MIMG_Gather <0x00000056, "IMAGE_GATHER4_B_CL_O">;
|
|
defm IMAGE_GATHER4_LZ_O : MIMG_Gather <0x00000057, "IMAGE_GATHER4_LZ_O">;
|
|
defm IMAGE_GATHER4_C_O : MIMG_Gather <0x00000058, "IMAGE_GATHER4_C_O">;
|
|
defm IMAGE_GATHER4_C_CL_O : MIMG_Gather <0x00000059, "IMAGE_GATHER4_C_CL_O">;
|
|
defm IMAGE_GATHER4_C_L_O : MIMG_Gather <0x0000005c, "IMAGE_GATHER4_C_L_O">;
|
|
defm IMAGE_GATHER4_C_B_O : MIMG_Gather <0x0000005d, "IMAGE_GATHER4_C_B_O">;
|
|
defm IMAGE_GATHER4_C_B_CL_O : MIMG_Gather <0x0000005e, "IMAGE_GATHER4_C_B_CL_O">;
|
|
defm IMAGE_GATHER4_C_LZ_O : MIMG_Gather <0x0000005f, "IMAGE_GATHER4_C_LZ_O">;
|
|
defm IMAGE_GET_LOD : MIMG_Sampler <0x00000060, "IMAGE_GET_LOD">;
|
|
defm IMAGE_SAMPLE_CD : MIMG_Sampler <0x00000068, "IMAGE_SAMPLE_CD">;
|
|
defm IMAGE_SAMPLE_CD_CL : MIMG_Sampler <0x00000069, "IMAGE_SAMPLE_CD_CL">;
|
|
defm IMAGE_SAMPLE_C_CD : MIMG_Sampler <0x0000006a, "IMAGE_SAMPLE_C_CD">;
|
|
defm IMAGE_SAMPLE_C_CD_CL : MIMG_Sampler <0x0000006b, "IMAGE_SAMPLE_C_CD_CL">;
|
|
defm IMAGE_SAMPLE_CD_O : MIMG_Sampler <0x0000006c, "IMAGE_SAMPLE_CD_O">;
|
|
defm IMAGE_SAMPLE_CD_CL_O : MIMG_Sampler <0x0000006d, "IMAGE_SAMPLE_CD_CL_O">;
|
|
defm IMAGE_SAMPLE_C_CD_O : MIMG_Sampler <0x0000006e, "IMAGE_SAMPLE_C_CD_O">;
|
|
defm IMAGE_SAMPLE_C_CD_CL_O : MIMG_Sampler <0x0000006f, "IMAGE_SAMPLE_C_CD_CL_O">;
|
|
//def IMAGE_RSRC256 : MIMG_NoPattern_RSRC256 <"IMAGE_RSRC256", 0x0000007e>;
|
|
//def IMAGE_SAMPLER : MIMG_NoPattern_ <"IMAGE_SAMPLER", 0x0000007f>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VOP1 Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//def V_NOP : VOP1_ <0x00000000, "V_NOP", []>;
|
|
|
|
let neverHasSideEffects = 1, isMoveImm = 1 in {
|
|
defm V_MOV_B32 : VOP1_32 <0x00000001, "V_MOV_B32", []>;
|
|
} // End neverHasSideEffects = 1, isMoveImm = 1
|
|
|
|
let Uses = [EXEC] in {
|
|
|
|
def V_READFIRSTLANE_B32 : VOP1 <
|
|
0x00000002,
|
|
(outs SReg_32:$vdst),
|
|
(ins VReg_32:$src0),
|
|
"V_READFIRSTLANE_B32 $vdst, $src0",
|
|
[]
|
|
>;
|
|
|
|
}
|
|
|
|
defm V_CVT_I32_F64 : VOP1_32_64 <0x00000003, "V_CVT_I32_F64",
|
|
[(set i32:$dst, (fp_to_sint f64:$src0))]
|
|
>;
|
|
defm V_CVT_F64_I32 : VOP1_64_32 <0x00000004, "V_CVT_F64_I32",
|
|
[(set f64:$dst, (sint_to_fp i32:$src0))]
|
|
>;
|
|
defm V_CVT_F32_I32 : VOP1_32 <0x00000005, "V_CVT_F32_I32",
|
|
[(set f32:$dst, (sint_to_fp i32:$src0))]
|
|
>;
|
|
defm V_CVT_F32_U32 : VOP1_32 <0x00000006, "V_CVT_F32_U32",
|
|
[(set f32:$dst, (uint_to_fp i32:$src0))]
|
|
>;
|
|
defm V_CVT_U32_F32 : VOP1_32 <0x00000007, "V_CVT_U32_F32",
|
|
[(set i32:$dst, (fp_to_uint f32:$src0))]
|
|
>;
|
|
defm V_CVT_I32_F32 : VOP1_32 <0x00000008, "V_CVT_I32_F32",
|
|
[(set i32:$dst, (fp_to_sint f32:$src0))]
|
|
>;
|
|
defm V_MOV_FED_B32 : VOP1_32 <0x00000009, "V_MOV_FED_B32", []>;
|
|
defm V_CVT_F16_F32 : VOP1_32 <0x0000000a, "V_CVT_F16_F32",
|
|
[(set i32:$dst, (f32_to_f16 f32:$src0))]
|
|
>;
|
|
defm V_CVT_F32_F16 : VOP1_32 <0x0000000b, "V_CVT_F32_F16",
|
|
[(set f32:$dst, (f16_to_f32 i32:$src0))]
|
|
>;
|
|
//defm V_CVT_RPI_I32_F32 : VOP1_32 <0x0000000c, "V_CVT_RPI_I32_F32", []>;
|
|
//defm V_CVT_FLR_I32_F32 : VOP1_32 <0x0000000d, "V_CVT_FLR_I32_F32", []>;
|
|
//defm V_CVT_OFF_F32_I4 : VOP1_32 <0x0000000e, "V_CVT_OFF_F32_I4", []>;
|
|
defm V_CVT_F32_F64 : VOP1_32_64 <0x0000000f, "V_CVT_F32_F64",
|
|
[(set f32:$dst, (fround f64:$src0))]
|
|
>;
|
|
defm V_CVT_F64_F32 : VOP1_64_32 <0x00000010, "V_CVT_F64_F32",
|
|
[(set f64:$dst, (fextend f32:$src0))]
|
|
>;
|
|
defm V_CVT_F32_UBYTE0 : VOP1_32 <0x00000011, "V_CVT_F32_UBYTE0",
|
|
[(set f32:$dst, (AMDGPUcvt_f32_ubyte0 i32:$src0))]
|
|
>;
|
|
defm V_CVT_F32_UBYTE1 : VOP1_32 <0x00000012, "V_CVT_F32_UBYTE1",
|
|
[(set f32:$dst, (AMDGPUcvt_f32_ubyte1 i32:$src0))]
|
|
>;
|
|
defm V_CVT_F32_UBYTE2 : VOP1_32 <0x00000013, "V_CVT_F32_UBYTE2",
|
|
[(set f32:$dst, (AMDGPUcvt_f32_ubyte2 i32:$src0))]
|
|
>;
|
|
defm V_CVT_F32_UBYTE3 : VOP1_32 <0x00000014, "V_CVT_F32_UBYTE3",
|
|
[(set f32:$dst, (AMDGPUcvt_f32_ubyte3 i32:$src0))]
|
|
>;
|
|
defm V_CVT_U32_F64 : VOP1_32_64 <0x00000015, "V_CVT_U32_F64",
|
|
[(set i32:$dst, (fp_to_uint f64:$src0))]
|
|
>;
|
|
defm V_CVT_F64_U32 : VOP1_64_32 <0x00000016, "V_CVT_F64_U32",
|
|
[(set f64:$dst, (uint_to_fp i32:$src0))]
|
|
>;
|
|
|
|
defm V_FRACT_F32 : VOP1_32 <0x00000020, "V_FRACT_F32",
|
|
[(set f32:$dst, (AMDGPUfract f32:$src0))]
|
|
>;
|
|
defm V_TRUNC_F32 : VOP1_32 <0x00000021, "V_TRUNC_F32",
|
|
[(set f32:$dst, (ftrunc f32:$src0))]
|
|
>;
|
|
defm V_CEIL_F32 : VOP1_32 <0x00000022, "V_CEIL_F32",
|
|
[(set f32:$dst, (fceil f32:$src0))]
|
|
>;
|
|
defm V_RNDNE_F32 : VOP1_32 <0x00000023, "V_RNDNE_F32",
|
|
[(set f32:$dst, (frint f32:$src0))]
|
|
>;
|
|
defm V_FLOOR_F32 : VOP1_32 <0x00000024, "V_FLOOR_F32",
|
|
[(set f32:$dst, (ffloor f32:$src0))]
|
|
>;
|
|
defm V_EXP_F32 : VOP1_32 <0x00000025, "V_EXP_F32",
|
|
[(set f32:$dst, (fexp2 f32:$src0))]
|
|
>;
|
|
defm V_LOG_CLAMP_F32 : VOP1_32 <0x00000026, "V_LOG_CLAMP_F32", []>;
|
|
defm V_LOG_F32 : VOP1_32 <0x00000027, "V_LOG_F32",
|
|
[(set f32:$dst, (flog2 f32:$src0))]
|
|
>;
|
|
|
|
defm V_RCP_CLAMP_F32 : VOP1_32 <0x00000028, "V_RCP_CLAMP_F32", []>;
|
|
defm V_RCP_LEGACY_F32 : VOP1_32 <0x00000029, "V_RCP_LEGACY_F32", []>;
|
|
defm V_RCP_F32 : VOP1_32 <0x0000002a, "V_RCP_F32",
|
|
[(set f32:$dst, (AMDGPUrcp f32:$src0))]
|
|
>;
|
|
defm V_RCP_IFLAG_F32 : VOP1_32 <0x0000002b, "V_RCP_IFLAG_F32", []>;
|
|
defm V_RSQ_CLAMP_F32 : VOP1_32 <0x0000002c, "V_RSQ_CLAMP_F32",
|
|
[(set f32:$dst, (AMDGPUrsq_clamped f32:$src0))]
|
|
>;
|
|
defm V_RSQ_LEGACY_F32 : VOP1_32 <
|
|
0x0000002d, "V_RSQ_LEGACY_F32",
|
|
[(set f32:$dst, (AMDGPUrsq_legacy f32:$src0))]
|
|
>;
|
|
defm V_RSQ_F32 : VOP1_32 <0x0000002e, "V_RSQ_F32",
|
|
[(set f32:$dst, (AMDGPUrsq f32:$src0))]
|
|
>;
|
|
defm V_RCP_F64 : VOP1_64 <0x0000002f, "V_RCP_F64",
|
|
[(set f64:$dst, (AMDGPUrcp f64:$src0))]
|
|
>;
|
|
defm V_RCP_CLAMP_F64 : VOP1_64 <0x00000030, "V_RCP_CLAMP_F64", []>;
|
|
defm V_RSQ_F64 : VOP1_64 <0x00000031, "V_RSQ_F64",
|
|
[(set f64:$dst, (AMDGPUrsq f64:$src0))]
|
|
>;
|
|
defm V_RSQ_CLAMP_F64 : VOP1_64 <0x00000032, "V_RSQ_CLAMP_F64",
|
|
[(set f64:$dst, (AMDGPUrsq_clamped f64:$src0))]
|
|
>;
|
|
defm V_SQRT_F32 : VOP1_32 <0x00000033, "V_SQRT_F32",
|
|
[(set f32:$dst, (fsqrt f32:$src0))]
|
|
>;
|
|
defm V_SQRT_F64 : VOP1_64 <0x00000034, "V_SQRT_F64",
|
|
[(set f64:$dst, (fsqrt f64:$src0))]
|
|
>;
|
|
defm V_SIN_F32 : VOP1_32 <0x00000035, "V_SIN_F32", []>;
|
|
defm V_COS_F32 : VOP1_32 <0x00000036, "V_COS_F32", []>;
|
|
defm V_NOT_B32 : VOP1_32 <0x00000037, "V_NOT_B32", []>;
|
|
defm V_BFREV_B32 : VOP1_32 <0x00000038, "V_BFREV_B32", []>;
|
|
defm V_FFBH_U32 : VOP1_32 <0x00000039, "V_FFBH_U32", []>;
|
|
defm V_FFBL_B32 : VOP1_32 <0x0000003a, "V_FFBL_B32", []>;
|
|
defm V_FFBH_I32 : VOP1_32 <0x0000003b, "V_FFBH_I32", []>;
|
|
//defm V_FREXP_EXP_I32_F64 : VOP1_32 <0x0000003c, "V_FREXP_EXP_I32_F64", []>;
|
|
defm V_FREXP_MANT_F64 : VOP1_64 <0x0000003d, "V_FREXP_MANT_F64", []>;
|
|
defm V_FRACT_F64 : VOP1_64 <0x0000003e, "V_FRACT_F64", []>;
|
|
//defm V_FREXP_EXP_I32_F32 : VOP1_32 <0x0000003f, "V_FREXP_EXP_I32_F32", []>;
|
|
defm V_FREXP_MANT_F32 : VOP1_32 <0x00000040, "V_FREXP_MANT_F32", []>;
|
|
//def V_CLREXCP : VOP1_ <0x00000041, "V_CLREXCP", []>;
|
|
defm V_MOVRELD_B32 : VOP1_32 <0x00000042, "V_MOVRELD_B32", []>;
|
|
defm V_MOVRELS_B32 : VOP1_32 <0x00000043, "V_MOVRELS_B32", []>;
|
|
defm V_MOVRELSD_B32 : VOP1_32 <0x00000044, "V_MOVRELSD_B32", []>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VINTRP Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def V_INTERP_P1_F32 : VINTRP <
|
|
0x00000000,
|
|
(outs VReg_32:$dst),
|
|
(ins VReg_32:$i, i32imm:$attr_chan, i32imm:$attr, M0Reg:$m0),
|
|
"V_INTERP_P1_F32 $dst, $i, $attr_chan, $attr, [$m0]",
|
|
[]> {
|
|
let DisableEncoding = "$m0";
|
|
}
|
|
|
|
def V_INTERP_P2_F32 : VINTRP <
|
|
0x00000001,
|
|
(outs VReg_32:$dst),
|
|
(ins VReg_32:$src0, VReg_32:$j, i32imm:$attr_chan, i32imm:$attr, M0Reg:$m0),
|
|
"V_INTERP_P2_F32 $dst, [$src0], $j, $attr_chan, $attr, [$m0]",
|
|
[]> {
|
|
|
|
let Constraints = "$src0 = $dst";
|
|
let DisableEncoding = "$src0,$m0";
|
|
|
|
}
|
|
|
|
def V_INTERP_MOV_F32 : VINTRP <
|
|
0x00000002,
|
|
(outs VReg_32:$dst),
|
|
(ins InterpSlot:$src0, i32imm:$attr_chan, i32imm:$attr, M0Reg:$m0),
|
|
"V_INTERP_MOV_F32 $dst, $src0, $attr_chan, $attr, [$m0]",
|
|
[]> {
|
|
let DisableEncoding = "$m0";
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VOP2 Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def V_CNDMASK_B32_e32 : VOP2 <0x00000000, (outs VReg_32:$dst),
|
|
(ins VSrc_32:$src0, VReg_32:$src1, VCCReg:$vcc),
|
|
"V_CNDMASK_B32_e32 $dst, $src0, $src1, [$vcc]",
|
|
[]
|
|
>{
|
|
let DisableEncoding = "$vcc";
|
|
}
|
|
|
|
def V_CNDMASK_B32_e64 : VOP3 <0x00000100, (outs VReg_32:$dst),
|
|
(ins VSrc_32:$src0, VSrc_32:$src1, SSrc_64:$src2,
|
|
InstFlag:$abs, InstFlag:$clamp, InstFlag:$omod, InstFlag:$neg),
|
|
"V_CNDMASK_B32_e64 $dst, $src0, $src1, $src2, $abs, $clamp, $omod, $neg",
|
|
[(set i32:$dst, (select i1:$src2, i32:$src1, i32:$src0))]
|
|
> {
|
|
let src0_modifiers = 0;
|
|
let src1_modifiers = 0;
|
|
let src2_modifiers = 0;
|
|
}
|
|
|
|
def V_READLANE_B32 : VOP2 <
|
|
0x00000001,
|
|
(outs SReg_32:$vdst),
|
|
(ins VReg_32:$src0, SSrc_32:$vsrc1),
|
|
"V_READLANE_B32 $vdst, $src0, $vsrc1",
|
|
[]
|
|
>;
|
|
|
|
def V_WRITELANE_B32 : VOP2 <
|
|
0x00000002,
|
|
(outs VReg_32:$vdst),
|
|
(ins SReg_32:$src0, SSrc_32:$vsrc1),
|
|
"V_WRITELANE_B32 $vdst, $src0, $vsrc1",
|
|
[]
|
|
>;
|
|
|
|
let isCommutable = 1 in {
|
|
defm V_ADD_F32 : VOP2_32 <0x00000003, "V_ADD_F32",
|
|
[(set f32:$dst, (fadd f32:$src0, f32:$src1))]
|
|
>;
|
|
|
|
defm V_SUB_F32 : VOP2_32 <0x00000004, "V_SUB_F32",
|
|
[(set f32:$dst, (fsub f32:$src0, f32:$src1))]
|
|
>;
|
|
defm V_SUBREV_F32 : VOP2_32 <0x00000005, "V_SUBREV_F32", [], "V_SUB_F32">;
|
|
} // End isCommutable = 1
|
|
|
|
defm V_MAC_LEGACY_F32 : VOP2_32 <0x00000006, "V_MAC_LEGACY_F32", []>;
|
|
|
|
let isCommutable = 1 in {
|
|
|
|
defm V_MUL_LEGACY_F32 : VOP2_32 <
|
|
0x00000007, "V_MUL_LEGACY_F32",
|
|
[(set f32:$dst, (int_AMDGPU_mul f32:$src0, f32:$src1))]
|
|
>;
|
|
|
|
defm V_MUL_F32 : VOP2_32 <0x00000008, "V_MUL_F32",
|
|
[(set f32:$dst, (fmul f32:$src0, f32:$src1))]
|
|
>;
|
|
|
|
|
|
defm V_MUL_I32_I24 : VOP2_32 <0x00000009, "V_MUL_I32_I24",
|
|
[(set i32:$dst, (AMDGPUmul_i24 i32:$src0, i32:$src1))]
|
|
>;
|
|
//defm V_MUL_HI_I32_I24 : VOP2_32 <0x0000000a, "V_MUL_HI_I32_I24", []>;
|
|
defm V_MUL_U32_U24 : VOP2_32 <0x0000000b, "V_MUL_U32_U24",
|
|
[(set i32:$dst, (AMDGPUmul_u24 i32:$src0, i32:$src1))]
|
|
>;
|
|
//defm V_MUL_HI_U32_U24 : VOP2_32 <0x0000000c, "V_MUL_HI_U32_U24", []>;
|
|
|
|
|
|
defm V_MIN_LEGACY_F32 : VOP2_32 <0x0000000d, "V_MIN_LEGACY_F32",
|
|
[(set f32:$dst, (AMDGPUfmin f32:$src0, f32:$src1))]
|
|
>;
|
|
|
|
defm V_MAX_LEGACY_F32 : VOP2_32 <0x0000000e, "V_MAX_LEGACY_F32",
|
|
[(set f32:$dst, (AMDGPUfmax f32:$src0, f32:$src1))]
|
|
>;
|
|
|
|
defm V_MIN_F32 : VOP2_32 <0x0000000f, "V_MIN_F32", []>;
|
|
defm V_MAX_F32 : VOP2_32 <0x00000010, "V_MAX_F32", []>;
|
|
defm V_MIN_I32 : VOP2_32 <0x00000011, "V_MIN_I32",
|
|
[(set i32:$dst, (AMDGPUsmin i32:$src0, i32:$src1))]>;
|
|
defm V_MAX_I32 : VOP2_32 <0x00000012, "V_MAX_I32",
|
|
[(set i32:$dst, (AMDGPUsmax i32:$src0, i32:$src1))]>;
|
|
defm V_MIN_U32 : VOP2_32 <0x00000013, "V_MIN_U32",
|
|
[(set i32:$dst, (AMDGPUumin i32:$src0, i32:$src1))]>;
|
|
defm V_MAX_U32 : VOP2_32 <0x00000014, "V_MAX_U32",
|
|
[(set i32:$dst, (AMDGPUumax i32:$src0, i32:$src1))]>;
|
|
|
|
defm V_LSHR_B32 : VOP2_32 <0x00000015, "V_LSHR_B32",
|
|
[(set i32:$dst, (srl i32:$src0, i32:$src1))]
|
|
>;
|
|
|
|
defm V_LSHRREV_B32 : VOP2_32 <0x00000016, "V_LSHRREV_B32", [], "V_LSHR_B32">;
|
|
|
|
defm V_ASHR_I32 : VOP2_32 <0x00000017, "V_ASHR_I32",
|
|
[(set i32:$dst, (sra i32:$src0, i32:$src1))]
|
|
>;
|
|
defm V_ASHRREV_I32 : VOP2_32 <0x00000018, "V_ASHRREV_I32", [], "V_ASHR_I32">;
|
|
|
|
let hasPostISelHook = 1 in {
|
|
|
|
defm V_LSHL_B32 : VOP2_32 <0x00000019, "V_LSHL_B32",
|
|
[(set i32:$dst, (shl i32:$src0, i32:$src1))]
|
|
>;
|
|
|
|
}
|
|
defm V_LSHLREV_B32 : VOP2_32 <0x0000001a, "V_LSHLREV_B32", [], "V_LSHL_B32">;
|
|
|
|
defm V_AND_B32 : VOP2_32 <0x0000001b, "V_AND_B32",
|
|
[(set i32:$dst, (and i32:$src0, i32:$src1))]>;
|
|
defm V_OR_B32 : VOP2_32 <0x0000001c, "V_OR_B32",
|
|
[(set i32:$dst, (or i32:$src0, i32:$src1))]
|
|
>;
|
|
defm V_XOR_B32 : VOP2_32 <0x0000001d, "V_XOR_B32",
|
|
[(set i32:$dst, (xor i32:$src0, i32:$src1))]
|
|
>;
|
|
|
|
} // End isCommutable = 1
|
|
|
|
defm V_BFM_B32 : VOP2_32 <0x0000001e, "V_BFM_B32",
|
|
[(set i32:$dst, (AMDGPUbfm i32:$src0, i32:$src1))]>;
|
|
defm V_MAC_F32 : VOP2_32 <0x0000001f, "V_MAC_F32", []>;
|
|
defm V_MADMK_F32 : VOP2_32 <0x00000020, "V_MADMK_F32", []>;
|
|
defm V_MADAK_F32 : VOP2_32 <0x00000021, "V_MADAK_F32", []>;
|
|
defm V_BCNT_U32_B32 : VOP2_32 <0x00000022, "V_BCNT_U32_B32", []>;
|
|
defm V_MBCNT_LO_U32_B32 : VOP2_32 <0x00000023, "V_MBCNT_LO_U32_B32", []>;
|
|
defm V_MBCNT_HI_U32_B32 : VOP2_32 <0x00000024, "V_MBCNT_HI_U32_B32", []>;
|
|
|
|
let isCommutable = 1, Defs = [VCC] in { // Carry-out goes to VCC
|
|
// No patterns so that the scalar instructions are always selected.
|
|
// The scalar versions will be replaced with vector when needed later.
|
|
defm V_ADD_I32 : VOP2b_32 <0x00000025, "V_ADD_I32",
|
|
[(set i32:$dst, (add i32:$src0, i32:$src1))], VSrc_32>;
|
|
defm V_SUB_I32 : VOP2b_32 <0x00000026, "V_SUB_I32",
|
|
[(set i32:$dst, (sub i32:$src0, i32:$src1))], VSrc_32>;
|
|
defm V_SUBREV_I32 : VOP2b_32 <0x00000027, "V_SUBREV_I32", [], VSrc_32,
|
|
"V_SUB_I32">;
|
|
|
|
let Uses = [VCC] in { // Carry-in comes from VCC
|
|
defm V_ADDC_U32 : VOP2b_32 <0x00000028, "V_ADDC_U32",
|
|
[(set i32:$dst, (adde i32:$src0, i32:$src1))], VReg_32>;
|
|
defm V_SUBB_U32 : VOP2b_32 <0x00000029, "V_SUBB_U32",
|
|
[(set i32:$dst, (sube i32:$src0, i32:$src1))], VReg_32>;
|
|
defm V_SUBBREV_U32 : VOP2b_32 <0x0000002a, "V_SUBBREV_U32", [], VReg_32,
|
|
"V_SUBB_U32">;
|
|
} // End Uses = [VCC]
|
|
} // End isCommutable = 1, Defs = [VCC]
|
|
|
|
defm V_LDEXP_F32 : VOP2_32 <0x0000002b, "V_LDEXP_F32", []>;
|
|
////def V_CVT_PKACCUM_U8_F32 : VOP2_U8 <0x0000002c, "V_CVT_PKACCUM_U8_F32", []>;
|
|
////def V_CVT_PKNORM_I16_F32 : VOP2_I16 <0x0000002d, "V_CVT_PKNORM_I16_F32", []>;
|
|
////def V_CVT_PKNORM_U16_F32 : VOP2_U16 <0x0000002e, "V_CVT_PKNORM_U16_F32", []>;
|
|
defm V_CVT_PKRTZ_F16_F32 : VOP2_32 <0x0000002f, "V_CVT_PKRTZ_F16_F32",
|
|
[(set i32:$dst, (int_SI_packf16 f32:$src0, f32:$src1))]
|
|
>;
|
|
////def V_CVT_PK_U16_U32 : VOP2_U16 <0x00000030, "V_CVT_PK_U16_U32", []>;
|
|
////def V_CVT_PK_I16_I32 : VOP2_I16 <0x00000031, "V_CVT_PK_I16_I32", []>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VOP3 Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let neverHasSideEffects = 1 in {
|
|
|
|
defm V_MAD_LEGACY_F32 : VOP3_32 <0x00000140, "V_MAD_LEGACY_F32", []>;
|
|
defm V_MAD_F32 : VOP3_32 <0x00000141, "V_MAD_F32",
|
|
[(set f32:$dst, (fadd (fmul f32:$src0, f32:$src1), f32:$src2))]
|
|
>;
|
|
defm V_MAD_I32_I24 : VOP3_32 <0x00000142, "V_MAD_I32_I24",
|
|
[(set i32:$dst, (AMDGPUmad_i24 i32:$src0, i32:$src1, i32:$src2))]
|
|
>;
|
|
defm V_MAD_U32_U24 : VOP3_32 <0x00000143, "V_MAD_U32_U24",
|
|
[(set i32:$dst, (AMDGPUmad_u24 i32:$src0, i32:$src1, i32:$src2))]
|
|
>;
|
|
|
|
} // End neverHasSideEffects
|
|
|
|
defm V_CUBEID_F32 : VOP3_32 <0x00000144, "V_CUBEID_F32", []>;
|
|
defm V_CUBESC_F32 : VOP3_32 <0x00000145, "V_CUBESC_F32", []>;
|
|
defm V_CUBETC_F32 : VOP3_32 <0x00000146, "V_CUBETC_F32", []>;
|
|
defm V_CUBEMA_F32 : VOP3_32 <0x00000147, "V_CUBEMA_F32", []>;
|
|
|
|
let neverHasSideEffects = 1, mayLoad = 0, mayStore = 0 in {
|
|
defm V_BFE_U32 : VOP3_32 <0x00000148, "V_BFE_U32",
|
|
[(set i32:$dst, (AMDGPUbfe_u32 i32:$src0, i32:$src1, i32:$src2))]>;
|
|
defm V_BFE_I32 : VOP3_32 <0x00000149, "V_BFE_I32",
|
|
[(set i32:$dst, (AMDGPUbfe_i32 i32:$src0, i32:$src1, i32:$src2))]>;
|
|
}
|
|
|
|
defm V_BFI_B32 : VOP3_32 <0x0000014a, "V_BFI_B32",
|
|
[(set i32:$dst, (AMDGPUbfi i32:$src0, i32:$src1, i32:$src2))]>;
|
|
defm V_FMA_F32 : VOP3_32 <0x0000014b, "V_FMA_F32",
|
|
[(set f32:$dst, (fma f32:$src0, f32:$src1, f32:$src2))]
|
|
>;
|
|
def V_FMA_F64 : VOP3_64 <0x0000014c, "V_FMA_F64",
|
|
[(set f64:$dst, (fma f64:$src0, f64:$src1, f64:$src2))]
|
|
>;
|
|
//def V_LERP_U8 : VOP3_U8 <0x0000014d, "V_LERP_U8", []>;
|
|
defm V_ALIGNBIT_B32 : VOP3_32 <0x0000014e, "V_ALIGNBIT_B32", []>;
|
|
|
|
defm V_ALIGNBYTE_B32 : VOP3_32 <0x0000014f, "V_ALIGNBYTE_B32", []>;
|
|
defm V_MULLIT_F32 : VOP3_32 <0x00000150, "V_MULLIT_F32", []>;
|
|
////def V_MIN3_F32 : VOP3_MIN3 <0x00000151, "V_MIN3_F32", []>;
|
|
////def V_MIN3_I32 : VOP3_MIN3 <0x00000152, "V_MIN3_I32", []>;
|
|
////def V_MIN3_U32 : VOP3_MIN3 <0x00000153, "V_MIN3_U32", []>;
|
|
////def V_MAX3_F32 : VOP3_MAX3 <0x00000154, "V_MAX3_F32", []>;
|
|
////def V_MAX3_I32 : VOP3_MAX3 <0x00000155, "V_MAX3_I32", []>;
|
|
////def V_MAX3_U32 : VOP3_MAX3 <0x00000156, "V_MAX3_U32", []>;
|
|
////def V_MED3_F32 : VOP3_MED3 <0x00000157, "V_MED3_F32", []>;
|
|
////def V_MED3_I32 : VOP3_MED3 <0x00000158, "V_MED3_I32", []>;
|
|
////def V_MED3_U32 : VOP3_MED3 <0x00000159, "V_MED3_U32", []>;
|
|
//def V_SAD_U8 : VOP3_U8 <0x0000015a, "V_SAD_U8", []>;
|
|
//def V_SAD_HI_U8 : VOP3_U8 <0x0000015b, "V_SAD_HI_U8", []>;
|
|
//def V_SAD_U16 : VOP3_U16 <0x0000015c, "V_SAD_U16", []>;
|
|
defm V_SAD_U32 : VOP3_32 <0x0000015d, "V_SAD_U32", []>;
|
|
////def V_CVT_PK_U8_F32 : VOP3_U8 <0x0000015e, "V_CVT_PK_U8_F32", []>;
|
|
defm V_DIV_FIXUP_F32 : VOP3_32 <0x0000015f, "V_DIV_FIXUP_F32",
|
|
[(set f32:$dst, (AMDGPUdiv_fixup f32:$src0, f32:$src1, f32:$src2))]
|
|
>;
|
|
def V_DIV_FIXUP_F64 : VOP3_64 <0x00000160, "V_DIV_FIXUP_F64",
|
|
[(set f64:$dst, (AMDGPUdiv_fixup f64:$src0, f64:$src1, f64:$src2))]
|
|
>;
|
|
|
|
def V_LSHL_B64 : VOP3_64_32 <0x00000161, "V_LSHL_B64",
|
|
[(set i64:$dst, (shl i64:$src0, i32:$src1))]
|
|
>;
|
|
def V_LSHR_B64 : VOP3_64_32 <0x00000162, "V_LSHR_B64",
|
|
[(set i64:$dst, (srl i64:$src0, i32:$src1))]
|
|
>;
|
|
def V_ASHR_I64 : VOP3_64_32 <0x00000163, "V_ASHR_I64",
|
|
[(set i64:$dst, (sra i64:$src0, i32:$src1))]
|
|
>;
|
|
|
|
let isCommutable = 1 in {
|
|
|
|
def V_ADD_F64 : VOP3_64 <0x00000164, "V_ADD_F64", []>;
|
|
def V_MUL_F64 : VOP3_64 <0x00000165, "V_MUL_F64", []>;
|
|
def V_MIN_F64 : VOP3_64 <0x00000166, "V_MIN_F64", []>;
|
|
def V_MAX_F64 : VOP3_64 <0x00000167, "V_MAX_F64", []>;
|
|
|
|
} // isCommutable = 1
|
|
|
|
def V_LDEXP_F64 : VOP3_64 <0x00000168, "V_LDEXP_F64", []>;
|
|
|
|
let isCommutable = 1 in {
|
|
|
|
defm V_MUL_LO_U32 : VOP3_32 <0x00000169, "V_MUL_LO_U32", []>;
|
|
defm V_MUL_HI_U32 : VOP3_32 <0x0000016a, "V_MUL_HI_U32", []>;
|
|
defm V_MUL_LO_I32 : VOP3_32 <0x0000016b, "V_MUL_LO_I32", []>;
|
|
defm V_MUL_HI_I32 : VOP3_32 <0x0000016c, "V_MUL_HI_I32", []>;
|
|
|
|
} // isCommutable = 1
|
|
|
|
def V_DIV_SCALE_F32 : VOP3b_32 <0x0000016d, "V_DIV_SCALE_F32", []>;
|
|
|
|
// Double precision division pre-scale.
|
|
def V_DIV_SCALE_F64 : VOP3b_64 <0x0000016e, "V_DIV_SCALE_F64", []>;
|
|
|
|
defm V_DIV_FMAS_F32 : VOP3_32 <0x0000016f, "V_DIV_FMAS_F32",
|
|
[(set f32:$dst, (AMDGPUdiv_fmas f32:$src0, f32:$src1, f32:$src2))]
|
|
>;
|
|
def V_DIV_FMAS_F64 : VOP3_64 <0x00000170, "V_DIV_FMAS_F64",
|
|
[(set f64:$dst, (AMDGPUdiv_fmas f64:$src0, f64:$src1, f64:$src2))]
|
|
>;
|
|
//def V_MSAD_U8 : VOP3_U8 <0x00000171, "V_MSAD_U8", []>;
|
|
//def V_QSAD_U8 : VOP3_U8 <0x00000172, "V_QSAD_U8", []>;
|
|
//def V_MQSAD_U8 : VOP3_U8 <0x00000173, "V_MQSAD_U8", []>;
|
|
def V_TRIG_PREOP_F64 : VOP3_64_32 <0x00000174, "V_TRIG_PREOP_F64",
|
|
[(set f64:$dst, (AMDGPUtrig_preop f64:$src0, i32:$src1))]
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Pseudo Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let isCodeGenOnly = 1, isPseudo = 1 in {
|
|
|
|
def V_MOV_I1 : InstSI <
|
|
(outs VReg_1:$dst),
|
|
(ins i1imm:$src),
|
|
"", [(set i1:$dst, (imm:$src))]
|
|
>;
|
|
|
|
def V_AND_I1 : InstSI <
|
|
(outs VReg_1:$dst), (ins VReg_1:$src0, VReg_1:$src1), "",
|
|
[(set i1:$dst, (and i1:$src0, i1:$src1))]
|
|
>;
|
|
|
|
def V_OR_I1 : InstSI <
|
|
(outs VReg_1:$dst), (ins VReg_1:$src0, VReg_1:$src1), "",
|
|
[(set i1:$dst, (or i1:$src0, i1:$src1))]
|
|
>;
|
|
|
|
// SI pseudo instructions. These are used by the CFG structurizer pass
|
|
// and should be lowered to ISA instructions prior to codegen.
|
|
|
|
let mayLoad = 1, mayStore = 1, hasSideEffects = 1,
|
|
Uses = [EXEC], Defs = [EXEC] in {
|
|
|
|
let isBranch = 1, isTerminator = 1 in {
|
|
|
|
def SI_IF: InstSI <
|
|
(outs SReg_64:$dst),
|
|
(ins SReg_64:$vcc, brtarget:$target),
|
|
"",
|
|
[(set i64:$dst, (int_SI_if i1:$vcc, bb:$target))]
|
|
>;
|
|
|
|
def SI_ELSE : InstSI <
|
|
(outs SReg_64:$dst),
|
|
(ins SReg_64:$src, brtarget:$target),
|
|
"",
|
|
[(set i64:$dst, (int_SI_else i64:$src, bb:$target))]
|
|
> {
|
|
let Constraints = "$src = $dst";
|
|
}
|
|
|
|
def SI_LOOP : InstSI <
|
|
(outs),
|
|
(ins SReg_64:$saved, brtarget:$target),
|
|
"SI_LOOP $saved, $target",
|
|
[(int_SI_loop i64:$saved, bb:$target)]
|
|
>;
|
|
|
|
} // end isBranch = 1, isTerminator = 1
|
|
|
|
def SI_BREAK : InstSI <
|
|
(outs SReg_64:$dst),
|
|
(ins SReg_64:$src),
|
|
"SI_ELSE $dst, $src",
|
|
[(set i64:$dst, (int_SI_break i64:$src))]
|
|
>;
|
|
|
|
def SI_IF_BREAK : InstSI <
|
|
(outs SReg_64:$dst),
|
|
(ins SReg_64:$vcc, SReg_64:$src),
|
|
"SI_IF_BREAK $dst, $vcc, $src",
|
|
[(set i64:$dst, (int_SI_if_break i1:$vcc, i64:$src))]
|
|
>;
|
|
|
|
def SI_ELSE_BREAK : InstSI <
|
|
(outs SReg_64:$dst),
|
|
(ins SReg_64:$src0, SReg_64:$src1),
|
|
"SI_ELSE_BREAK $dst, $src0, $src1",
|
|
[(set i64:$dst, (int_SI_else_break i64:$src0, i64:$src1))]
|
|
>;
|
|
|
|
def SI_END_CF : InstSI <
|
|
(outs),
|
|
(ins SReg_64:$saved),
|
|
"SI_END_CF $saved",
|
|
[(int_SI_end_cf i64:$saved)]
|
|
>;
|
|
|
|
def SI_KILL : InstSI <
|
|
(outs),
|
|
(ins VSrc_32:$src),
|
|
"SI_KILL $src",
|
|
[(int_AMDGPU_kill f32:$src)]
|
|
>;
|
|
|
|
} // end mayLoad = 1, mayStore = 1, hasSideEffects = 1
|
|
// Uses = [EXEC], Defs = [EXEC]
|
|
|
|
let Uses = [EXEC], Defs = [EXEC,VCC,M0] in {
|
|
|
|
//defm SI_ : RegisterLoadStore <VReg_32, FRAMEri, ADDRIndirect>;
|
|
|
|
let UseNamedOperandTable = 1 in {
|
|
|
|
def SI_RegisterLoad : InstSI <
|
|
(outs VReg_32:$dst, SReg_64:$temp),
|
|
(ins FRAMEri32:$addr, i32imm:$chan),
|
|
"", []
|
|
> {
|
|
let isRegisterLoad = 1;
|
|
let mayLoad = 1;
|
|
}
|
|
|
|
class SIRegStore<dag outs> : InstSI <
|
|
outs,
|
|
(ins VReg_32:$val, FRAMEri32:$addr, i32imm:$chan),
|
|
"", []
|
|
> {
|
|
let isRegisterStore = 1;
|
|
let mayStore = 1;
|
|
}
|
|
|
|
let usesCustomInserter = 1 in {
|
|
def SI_RegisterStorePseudo : SIRegStore<(outs)>;
|
|
} // End usesCustomInserter = 1
|
|
def SI_RegisterStore : SIRegStore<(outs SReg_64:$temp)>;
|
|
|
|
|
|
} // End UseNamedOperandTable = 1
|
|
|
|
def SI_INDIRECT_SRC : InstSI <
|
|
(outs VReg_32:$dst, SReg_64:$temp),
|
|
(ins unknown:$src, VSrc_32:$idx, i32imm:$off),
|
|
"SI_INDIRECT_SRC $dst, $temp, $src, $idx, $off",
|
|
[]
|
|
>;
|
|
|
|
class SI_INDIRECT_DST<RegisterClass rc> : InstSI <
|
|
(outs rc:$dst, SReg_64:$temp),
|
|
(ins unknown:$src, VSrc_32:$idx, i32imm:$off, VReg_32:$val),
|
|
"SI_INDIRECT_DST $dst, $temp, $src, $idx, $off, $val",
|
|
[]
|
|
> {
|
|
let Constraints = "$src = $dst";
|
|
}
|
|
|
|
def SI_INDIRECT_DST_V1 : SI_INDIRECT_DST<VReg_32>;
|
|
def SI_INDIRECT_DST_V2 : SI_INDIRECT_DST<VReg_64>;
|
|
def SI_INDIRECT_DST_V4 : SI_INDIRECT_DST<VReg_128>;
|
|
def SI_INDIRECT_DST_V8 : SI_INDIRECT_DST<VReg_256>;
|
|
def SI_INDIRECT_DST_V16 : SI_INDIRECT_DST<VReg_512>;
|
|
|
|
} // Uses = [EXEC,VCC,M0], Defs = [EXEC,VCC,M0]
|
|
|
|
let usesCustomInserter = 1 in {
|
|
|
|
// This pseudo instruction takes a pointer as input and outputs a resource
|
|
// constant that can be used with the ADDR64 MUBUF instructions.
|
|
def SI_ADDR64_RSRC : InstSI <
|
|
(outs SReg_128:$srsrc),
|
|
(ins SSrc_64:$ptr),
|
|
"", []
|
|
>;
|
|
|
|
def V_SUB_F64 : InstSI <
|
|
(outs VReg_64:$dst),
|
|
(ins VReg_64:$src0, VReg_64:$src1),
|
|
"V_SUB_F64 $dst, $src0, $src1",
|
|
[(set f64:$dst, (fsub f64:$src0, f64:$src1))]
|
|
>;
|
|
|
|
} // end usesCustomInserter
|
|
|
|
multiclass SI_SPILL_SGPR <RegisterClass sgpr_class> {
|
|
|
|
def _SAVE : InstSI <
|
|
(outs VReg_32:$dst),
|
|
(ins sgpr_class:$src, i32imm:$frame_idx),
|
|
"", []
|
|
>;
|
|
|
|
def _RESTORE : InstSI <
|
|
(outs sgpr_class:$dst),
|
|
(ins VReg_32:$src, i32imm:$frame_idx),
|
|
"", []
|
|
>;
|
|
|
|
}
|
|
|
|
defm SI_SPILL_S32 : SI_SPILL_SGPR <SReg_32>;
|
|
defm SI_SPILL_S64 : SI_SPILL_SGPR <SReg_64>;
|
|
defm SI_SPILL_S128 : SI_SPILL_SGPR <SReg_128>;
|
|
defm SI_SPILL_S256 : SI_SPILL_SGPR <SReg_256>;
|
|
defm SI_SPILL_S512 : SI_SPILL_SGPR <SReg_512>;
|
|
|
|
} // end IsCodeGenOnly, isPseudo
|
|
|
|
} // end SubtargetPredicate = SI
|
|
|
|
let Predicates = [isSI] in {
|
|
|
|
def : Pat<
|
|
(int_AMDGPU_cndlt f32:$src0, f32:$src1, f32:$src2),
|
|
(V_CNDMASK_B32_e64 $src2, $src1, (V_CMP_GT_F32_e64 0, $src0))
|
|
>;
|
|
|
|
def : Pat <
|
|
(int_AMDGPU_kilp),
|
|
(SI_KILL 0xbf800000)
|
|
>;
|
|
|
|
/* int_SI_vs_load_input */
|
|
def : Pat<
|
|
(SIload_input v4i32:$tlst, imm:$attr_offset, i32:$buf_idx_vgpr),
|
|
(BUFFER_LOAD_FORMAT_XYZW_IDXEN $tlst, $buf_idx_vgpr, imm:$attr_offset, 0, 0, 0, 0)
|
|
>;
|
|
|
|
/* int_SI_export */
|
|
def : Pat <
|
|
(int_SI_export imm:$en, imm:$vm, imm:$done, imm:$tgt, imm:$compr,
|
|
f32:$src0, f32:$src1, f32:$src2, f32:$src3),
|
|
(EXP imm:$en, imm:$tgt, imm:$compr, imm:$done, imm:$vm,
|
|
$src0, $src1, $src2, $src3)
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SMRD Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
multiclass SMRD_Pattern <SMRD Instr_IMM, SMRD Instr_SGPR, ValueType vt> {
|
|
|
|
// 1. Offset as 8bit DWORD immediate
|
|
def : Pat <
|
|
(constant_load (add i64:$sbase, (i64 IMM8bitDWORD:$offset))),
|
|
(vt (Instr_IMM $sbase, (as_dword_i32imm $offset)))
|
|
>;
|
|
|
|
// 2. Offset loaded in an 32bit SGPR
|
|
def : Pat <
|
|
(constant_load (add i64:$sbase, (i64 IMM32bit:$offset))),
|
|
(vt (Instr_SGPR $sbase, (S_MOV_B32 (i32 (as_i32imm $offset)))))
|
|
>;
|
|
|
|
// 3. No offset at all
|
|
def : Pat <
|
|
(constant_load i64:$sbase),
|
|
(vt (Instr_IMM $sbase, 0))
|
|
>;
|
|
}
|
|
|
|
defm : SMRD_Pattern <S_LOAD_DWORD_IMM, S_LOAD_DWORD_SGPR, f32>;
|
|
defm : SMRD_Pattern <S_LOAD_DWORD_IMM, S_LOAD_DWORD_SGPR, i32>;
|
|
defm : SMRD_Pattern <S_LOAD_DWORDX2_IMM, S_LOAD_DWORDX2_SGPR, v2i32>;
|
|
defm : SMRD_Pattern <S_LOAD_DWORDX4_IMM, S_LOAD_DWORDX4_SGPR, v4i32>;
|
|
defm : SMRD_Pattern <S_LOAD_DWORDX8_IMM, S_LOAD_DWORDX8_SGPR, v32i8>;
|
|
defm : SMRD_Pattern <S_LOAD_DWORDX8_IMM, S_LOAD_DWORDX8_SGPR, v8i32>;
|
|
defm : SMRD_Pattern <S_LOAD_DWORDX16_IMM, S_LOAD_DWORDX16_SGPR, v16i32>;
|
|
|
|
// 1. Offset as 8bit DWORD immediate
|
|
def : Pat <
|
|
(SIload_constant v4i32:$sbase, IMM8bitDWORD:$offset),
|
|
(S_BUFFER_LOAD_DWORD_IMM $sbase, (as_dword_i32imm $offset))
|
|
>;
|
|
|
|
// 2. Offset loaded in an 32bit SGPR
|
|
def : Pat <
|
|
(SIload_constant v4i32:$sbase, imm:$offset),
|
|
(S_BUFFER_LOAD_DWORD_SGPR $sbase, (S_MOV_B32 imm:$offset))
|
|
>;
|
|
|
|
} // Predicates = [isSI] in {
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP1 Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let Predicates = [isSI, isCFDepth0] in {
|
|
|
|
def : Pat <
|
|
(i64 (ctpop i64:$src)),
|
|
(INSERT_SUBREG (INSERT_SUBREG (i64 (IMPLICIT_DEF)),
|
|
(S_BCNT1_I32_B64 $src), sub0),
|
|
(S_MOV_B32 0), sub1)
|
|
>;
|
|
|
|
} // Predicates = [isSI, isCFDepth0]
|
|
|
|
let Predicates = [isSI] in {
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP2 Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def : Pat <
|
|
(i1 (xor i1:$src0, i1:$src1)),
|
|
(S_XOR_B64 $src0, $src1)
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOPP Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def : Pat <
|
|
(int_AMDGPU_barrier_global),
|
|
(S_BARRIER)
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VOP1 Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let Predicates = [UnsafeFPMath] in {
|
|
def : RcpPat<V_RCP_F64_e32, f64>;
|
|
defm : RsqPat<V_RSQ_F64_e32, f64>;
|
|
defm : RsqPat<V_RSQ_F32_e32, f32>;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VOP2 Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class BinOp64Pat <SDNode node, Instruction inst> : Pat <
|
|
(node i64:$src0, i64:$src1),
|
|
(INSERT_SUBREG (INSERT_SUBREG (i64 (IMPLICIT_DEF)),
|
|
(inst (EXTRACT_SUBREG i64:$src0, sub0),
|
|
(EXTRACT_SUBREG i64:$src1, sub0)), sub0),
|
|
(inst (EXTRACT_SUBREG i64:$src0, sub1),
|
|
(EXTRACT_SUBREG i64:$src1, sub1)), sub1)
|
|
>;
|
|
|
|
def : BinOp64Pat <or, V_OR_B32_e32>;
|
|
def : BinOp64Pat <xor, V_XOR_B32_e32>;
|
|
|
|
class SextInReg <ValueType vt, int ShiftAmt> : Pat <
|
|
(sext_inreg i32:$src0, vt),
|
|
(V_ASHRREV_I32_e32 ShiftAmt, (V_LSHLREV_B32_e32 ShiftAmt, $src0))
|
|
>;
|
|
|
|
def : SextInReg <i8, 24>;
|
|
def : SextInReg <i16, 16>;
|
|
|
|
def : Pat <
|
|
(i32 (add (i32 (ctpop i32:$popcnt)), i32:$val)),
|
|
(V_BCNT_U32_B32_e32 $popcnt, $val)
|
|
>;
|
|
|
|
def : Pat <
|
|
(i32 (ctpop i32:$popcnt)),
|
|
(V_BCNT_U32_B32_e64 $popcnt, 0, 0, 0)
|
|
>;
|
|
|
|
def : Pat <
|
|
(i64 (ctpop i64:$src)),
|
|
(INSERT_SUBREG
|
|
(INSERT_SUBREG (i64 (IMPLICIT_DEF)),
|
|
(V_BCNT_U32_B32_e32 (EXTRACT_SUBREG $src, sub1),
|
|
(V_BCNT_U32_B32_e64 (EXTRACT_SUBREG $src, sub0), 0, 0, 0)),
|
|
sub0),
|
|
(V_MOV_B32_e32 0), sub1)
|
|
>;
|
|
|
|
/********** ======================= **********/
|
|
/********** Image sampling patterns **********/
|
|
/********** ======================= **********/
|
|
|
|
// Image + sampler
|
|
class SampleRawPattern<SDPatternOperator name, MIMG opcode, ValueType vt> : Pat <
|
|
(name vt:$addr, v8i32:$rsrc, v4i32:$sampler, i32:$dmask, i32:$unorm,
|
|
i32:$r128, i32:$da, i32:$glc, i32:$slc, i32:$tfe, i32:$lwe),
|
|
(opcode (as_i32imm $dmask), (as_i1imm $unorm), (as_i1imm $glc), (as_i1imm $da),
|
|
(as_i1imm $r128), (as_i1imm $tfe), (as_i1imm $lwe), (as_i1imm $slc),
|
|
$addr, $rsrc, $sampler)
|
|
>;
|
|
|
|
multiclass SampleRawPatterns<SDPatternOperator name, string opcode> {
|
|
def : SampleRawPattern<name, !cast<MIMG>(opcode # _V4_V1), i32>;
|
|
def : SampleRawPattern<name, !cast<MIMG>(opcode # _V4_V2), v2i32>;
|
|
def : SampleRawPattern<name, !cast<MIMG>(opcode # _V4_V4), v4i32>;
|
|
def : SampleRawPattern<name, !cast<MIMG>(opcode # _V4_V8), v8i32>;
|
|
def : SampleRawPattern<name, !cast<MIMG>(opcode # _V4_V16), v16i32>;
|
|
}
|
|
|
|
// Image only
|
|
class ImagePattern<SDPatternOperator name, MIMG opcode, ValueType vt> : Pat <
|
|
(name vt:$addr, v8i32:$rsrc, i32:$dmask, i32:$unorm,
|
|
i32:$r128, i32:$da, i32:$glc, i32:$slc, i32:$tfe, i32:$lwe),
|
|
(opcode (as_i32imm $dmask), (as_i1imm $unorm), (as_i1imm $glc), (as_i1imm $da),
|
|
(as_i1imm $r128), (as_i1imm $tfe), (as_i1imm $lwe), (as_i1imm $slc),
|
|
$addr, $rsrc)
|
|
>;
|
|
|
|
multiclass ImagePatterns<SDPatternOperator name, string opcode> {
|
|
def : ImagePattern<name, !cast<MIMG>(opcode # _V4_V1), i32>;
|
|
def : ImagePattern<name, !cast<MIMG>(opcode # _V4_V2), v2i32>;
|
|
def : ImagePattern<name, !cast<MIMG>(opcode # _V4_V4), v4i32>;
|
|
}
|
|
|
|
// Basic sample
|
|
defm : SampleRawPatterns<int_SI_image_sample, "IMAGE_SAMPLE">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_cl, "IMAGE_SAMPLE_CL">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_d, "IMAGE_SAMPLE_D">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_d_cl, "IMAGE_SAMPLE_D_CL">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_l, "IMAGE_SAMPLE_L">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_b, "IMAGE_SAMPLE_B">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_b_cl, "IMAGE_SAMPLE_B_CL">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_lz, "IMAGE_SAMPLE_LZ">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_cd, "IMAGE_SAMPLE_CD">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_cd_cl, "IMAGE_SAMPLE_CD_CL">;
|
|
|
|
// Sample with comparison
|
|
defm : SampleRawPatterns<int_SI_image_sample_c, "IMAGE_SAMPLE_C">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_cl, "IMAGE_SAMPLE_C_CL">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_d, "IMAGE_SAMPLE_C_D">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_d_cl, "IMAGE_SAMPLE_C_D_CL">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_l, "IMAGE_SAMPLE_C_L">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_b, "IMAGE_SAMPLE_C_B">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_b_cl, "IMAGE_SAMPLE_C_B_CL">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_lz, "IMAGE_SAMPLE_C_LZ">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_cd, "IMAGE_SAMPLE_C_CD">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_cd_cl, "IMAGE_SAMPLE_C_CD_CL">;
|
|
|
|
// Sample with offsets
|
|
defm : SampleRawPatterns<int_SI_image_sample_o, "IMAGE_SAMPLE_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_cl_o, "IMAGE_SAMPLE_CL_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_d_o, "IMAGE_SAMPLE_D_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_d_cl_o, "IMAGE_SAMPLE_D_CL_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_l_o, "IMAGE_SAMPLE_L_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_b_o, "IMAGE_SAMPLE_B_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_b_cl_o, "IMAGE_SAMPLE_B_CL_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_lz_o, "IMAGE_SAMPLE_LZ_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_cd_o, "IMAGE_SAMPLE_CD_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_cd_cl_o, "IMAGE_SAMPLE_CD_CL_O">;
|
|
|
|
// Sample with comparison and offsets
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_o, "IMAGE_SAMPLE_C_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_cl_o, "IMAGE_SAMPLE_C_CL_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_d_o, "IMAGE_SAMPLE_C_D_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_d_cl_o, "IMAGE_SAMPLE_C_D_CL_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_l_o, "IMAGE_SAMPLE_C_L_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_b_o, "IMAGE_SAMPLE_C_B_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_b_cl_o, "IMAGE_SAMPLE_C_B_CL_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_lz_o, "IMAGE_SAMPLE_C_LZ_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_cd_o, "IMAGE_SAMPLE_C_CD_O">;
|
|
defm : SampleRawPatterns<int_SI_image_sample_c_cd_cl_o, "IMAGE_SAMPLE_C_CD_CL_O">;
|
|
|
|
// Gather opcodes
|
|
// Only the variants which make sense are defined.
|
|
def : SampleRawPattern<int_SI_gather4, IMAGE_GATHER4_V4_V2, v2i32>;
|
|
def : SampleRawPattern<int_SI_gather4, IMAGE_GATHER4_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_cl, IMAGE_GATHER4_CL_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_l, IMAGE_GATHER4_L_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_b, IMAGE_GATHER4_B_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_b_cl, IMAGE_GATHER4_B_CL_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_b_cl, IMAGE_GATHER4_B_CL_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_lz, IMAGE_GATHER4_LZ_V4_V2, v2i32>;
|
|
def : SampleRawPattern<int_SI_gather4_lz, IMAGE_GATHER4_LZ_V4_V4, v4i32>;
|
|
|
|
def : SampleRawPattern<int_SI_gather4_c, IMAGE_GATHER4_C_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_cl, IMAGE_GATHER4_C_CL_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_cl, IMAGE_GATHER4_C_CL_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_l, IMAGE_GATHER4_C_L_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_l, IMAGE_GATHER4_C_L_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_b, IMAGE_GATHER4_C_B_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_b, IMAGE_GATHER4_C_B_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_b_cl, IMAGE_GATHER4_C_B_CL_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_lz, IMAGE_GATHER4_C_LZ_V4_V4, v4i32>;
|
|
|
|
def : SampleRawPattern<int_SI_gather4_o, IMAGE_GATHER4_O_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_cl_o, IMAGE_GATHER4_CL_O_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_cl_o, IMAGE_GATHER4_CL_O_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_l_o, IMAGE_GATHER4_L_O_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_l_o, IMAGE_GATHER4_L_O_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_b_o, IMAGE_GATHER4_B_O_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_b_o, IMAGE_GATHER4_B_O_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_b_cl_o, IMAGE_GATHER4_B_CL_O_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_lz_o, IMAGE_GATHER4_LZ_O_V4_V4, v4i32>;
|
|
|
|
def : SampleRawPattern<int_SI_gather4_c_o, IMAGE_GATHER4_C_O_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_o, IMAGE_GATHER4_C_O_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_cl_o, IMAGE_GATHER4_C_CL_O_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_l_o, IMAGE_GATHER4_C_L_O_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_b_o, IMAGE_GATHER4_C_B_O_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_b_cl_o, IMAGE_GATHER4_C_B_CL_O_V4_V8, v8i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_lz_o, IMAGE_GATHER4_C_LZ_O_V4_V4, v4i32>;
|
|
def : SampleRawPattern<int_SI_gather4_c_lz_o, IMAGE_GATHER4_C_LZ_O_V4_V8, v8i32>;
|
|
|
|
def : SampleRawPattern<int_SI_getlod, IMAGE_GET_LOD_V4_V1, i32>;
|
|
def : SampleRawPattern<int_SI_getlod, IMAGE_GET_LOD_V4_V2, v2i32>;
|
|
def : SampleRawPattern<int_SI_getlod, IMAGE_GET_LOD_V4_V4, v4i32>;
|
|
|
|
def : ImagePattern<int_SI_getresinfo, IMAGE_GET_RESINFO_V4_V1, i32>;
|
|
defm : ImagePatterns<int_SI_image_load, "IMAGE_LOAD">;
|
|
defm : ImagePatterns<int_SI_image_load_mip, "IMAGE_LOAD_MIP">;
|
|
|
|
/* SIsample for simple 1D texture lookup */
|
|
def : Pat <
|
|
(SIsample i32:$addr, v32i8:$rsrc, v4i32:$sampler, imm),
|
|
(IMAGE_SAMPLE_V4_V1 0xf, 0, 0, 0, 0, 0, 0, 0, $addr, $rsrc, $sampler)
|
|
>;
|
|
|
|
class SamplePattern<SDNode name, MIMG opcode, ValueType vt> : Pat <
|
|
(name vt:$addr, v32i8:$rsrc, v4i32:$sampler, imm),
|
|
(opcode 0xf, 0, 0, 0, 0, 0, 0, 0, $addr, $rsrc, $sampler)
|
|
>;
|
|
|
|
class SampleRectPattern<SDNode name, MIMG opcode, ValueType vt> : Pat <
|
|
(name vt:$addr, v32i8:$rsrc, v4i32:$sampler, TEX_RECT),
|
|
(opcode 0xf, 1, 0, 0, 0, 0, 0, 0, $addr, $rsrc, $sampler)
|
|
>;
|
|
|
|
class SampleArrayPattern<SDNode name, MIMG opcode, ValueType vt> : Pat <
|
|
(name vt:$addr, v32i8:$rsrc, v4i32:$sampler, TEX_ARRAY),
|
|
(opcode 0xf, 0, 0, 1, 0, 0, 0, 0, $addr, $rsrc, $sampler)
|
|
>;
|
|
|
|
class SampleShadowPattern<SDNode name, MIMG opcode,
|
|
ValueType vt> : Pat <
|
|
(name vt:$addr, v32i8:$rsrc, v4i32:$sampler, TEX_SHADOW),
|
|
(opcode 0xf, 0, 0, 0, 0, 0, 0, 0, $addr, $rsrc, $sampler)
|
|
>;
|
|
|
|
class SampleShadowArrayPattern<SDNode name, MIMG opcode,
|
|
ValueType vt> : Pat <
|
|
(name vt:$addr, v32i8:$rsrc, v4i32:$sampler, TEX_SHADOW_ARRAY),
|
|
(opcode 0xf, 0, 0, 1, 0, 0, 0, 0, $addr, $rsrc, $sampler)
|
|
>;
|
|
|
|
/* SIsample* for texture lookups consuming more address parameters */
|
|
multiclass SamplePatterns<MIMG sample, MIMG sample_c, MIMG sample_l,
|
|
MIMG sample_c_l, MIMG sample_b, MIMG sample_c_b,
|
|
MIMG sample_d, MIMG sample_c_d, ValueType addr_type> {
|
|
def : SamplePattern <SIsample, sample, addr_type>;
|
|
def : SampleRectPattern <SIsample, sample, addr_type>;
|
|
def : SampleArrayPattern <SIsample, sample, addr_type>;
|
|
def : SampleShadowPattern <SIsample, sample_c, addr_type>;
|
|
def : SampleShadowArrayPattern <SIsample, sample_c, addr_type>;
|
|
|
|
def : SamplePattern <SIsamplel, sample_l, addr_type>;
|
|
def : SampleArrayPattern <SIsamplel, sample_l, addr_type>;
|
|
def : SampleShadowPattern <SIsamplel, sample_c_l, addr_type>;
|
|
def : SampleShadowArrayPattern <SIsamplel, sample_c_l, addr_type>;
|
|
|
|
def : SamplePattern <SIsampleb, sample_b, addr_type>;
|
|
def : SampleArrayPattern <SIsampleb, sample_b, addr_type>;
|
|
def : SampleShadowPattern <SIsampleb, sample_c_b, addr_type>;
|
|
def : SampleShadowArrayPattern <SIsampleb, sample_c_b, addr_type>;
|
|
|
|
def : SamplePattern <SIsampled, sample_d, addr_type>;
|
|
def : SampleArrayPattern <SIsampled, sample_d, addr_type>;
|
|
def : SampleShadowPattern <SIsampled, sample_c_d, addr_type>;
|
|
def : SampleShadowArrayPattern <SIsampled, sample_c_d, addr_type>;
|
|
}
|
|
|
|
defm : SamplePatterns<IMAGE_SAMPLE_V4_V2, IMAGE_SAMPLE_C_V4_V2,
|
|
IMAGE_SAMPLE_L_V4_V2, IMAGE_SAMPLE_C_L_V4_V2,
|
|
IMAGE_SAMPLE_B_V4_V2, IMAGE_SAMPLE_C_B_V4_V2,
|
|
IMAGE_SAMPLE_D_V4_V2, IMAGE_SAMPLE_C_D_V4_V2,
|
|
v2i32>;
|
|
defm : SamplePatterns<IMAGE_SAMPLE_V4_V4, IMAGE_SAMPLE_C_V4_V4,
|
|
IMAGE_SAMPLE_L_V4_V4, IMAGE_SAMPLE_C_L_V4_V4,
|
|
IMAGE_SAMPLE_B_V4_V4, IMAGE_SAMPLE_C_B_V4_V4,
|
|
IMAGE_SAMPLE_D_V4_V4, IMAGE_SAMPLE_C_D_V4_V4,
|
|
v4i32>;
|
|
defm : SamplePatterns<IMAGE_SAMPLE_V4_V8, IMAGE_SAMPLE_C_V4_V8,
|
|
IMAGE_SAMPLE_L_V4_V8, IMAGE_SAMPLE_C_L_V4_V8,
|
|
IMAGE_SAMPLE_B_V4_V8, IMAGE_SAMPLE_C_B_V4_V8,
|
|
IMAGE_SAMPLE_D_V4_V8, IMAGE_SAMPLE_C_D_V4_V8,
|
|
v8i32>;
|
|
defm : SamplePatterns<IMAGE_SAMPLE_V4_V16, IMAGE_SAMPLE_C_V4_V16,
|
|
IMAGE_SAMPLE_L_V4_V16, IMAGE_SAMPLE_C_L_V4_V16,
|
|
IMAGE_SAMPLE_B_V4_V16, IMAGE_SAMPLE_C_B_V4_V16,
|
|
IMAGE_SAMPLE_D_V4_V16, IMAGE_SAMPLE_C_D_V4_V16,
|
|
v16i32>;
|
|
|
|
/* int_SI_imageload for texture fetches consuming varying address parameters */
|
|
class ImageLoadPattern<Intrinsic name, MIMG opcode, ValueType addr_type> : Pat <
|
|
(name addr_type:$addr, v32i8:$rsrc, imm),
|
|
(opcode 0xf, 0, 0, 0, 0, 0, 0, 0, $addr, $rsrc)
|
|
>;
|
|
|
|
class ImageLoadArrayPattern<Intrinsic name, MIMG opcode, ValueType addr_type> : Pat <
|
|
(name addr_type:$addr, v32i8:$rsrc, TEX_ARRAY),
|
|
(opcode 0xf, 0, 0, 1, 0, 0, 0, 0, $addr, $rsrc)
|
|
>;
|
|
|
|
class ImageLoadMSAAPattern<Intrinsic name, MIMG opcode, ValueType addr_type> : Pat <
|
|
(name addr_type:$addr, v32i8:$rsrc, TEX_MSAA),
|
|
(opcode 0xf, 0, 0, 0, 0, 0, 0, 0, $addr, $rsrc)
|
|
>;
|
|
|
|
class ImageLoadArrayMSAAPattern<Intrinsic name, MIMG opcode, ValueType addr_type> : Pat <
|
|
(name addr_type:$addr, v32i8:$rsrc, TEX_ARRAY_MSAA),
|
|
(opcode 0xf, 0, 0, 1, 0, 0, 0, 0, $addr, $rsrc)
|
|
>;
|
|
|
|
multiclass ImageLoadPatterns<MIMG opcode, ValueType addr_type> {
|
|
def : ImageLoadPattern <int_SI_imageload, opcode, addr_type>;
|
|
def : ImageLoadArrayPattern <int_SI_imageload, opcode, addr_type>;
|
|
}
|
|
|
|
multiclass ImageLoadMSAAPatterns<MIMG opcode, ValueType addr_type> {
|
|
def : ImageLoadMSAAPattern <int_SI_imageload, opcode, addr_type>;
|
|
def : ImageLoadArrayMSAAPattern <int_SI_imageload, opcode, addr_type>;
|
|
}
|
|
|
|
defm : ImageLoadPatterns<IMAGE_LOAD_MIP_V4_V2, v2i32>;
|
|
defm : ImageLoadPatterns<IMAGE_LOAD_MIP_V4_V4, v4i32>;
|
|
|
|
defm : ImageLoadMSAAPatterns<IMAGE_LOAD_V4_V2, v2i32>;
|
|
defm : ImageLoadMSAAPatterns<IMAGE_LOAD_V4_V4, v4i32>;
|
|
|
|
/* Image resource information */
|
|
def : Pat <
|
|
(int_SI_resinfo i32:$mipid, v32i8:$rsrc, imm),
|
|
(IMAGE_GET_RESINFO_V4_V1 0xf, 0, 0, 0, 0, 0, 0, 0, (V_MOV_B32_e32 $mipid), $rsrc)
|
|
>;
|
|
|
|
def : Pat <
|
|
(int_SI_resinfo i32:$mipid, v32i8:$rsrc, TEX_ARRAY),
|
|
(IMAGE_GET_RESINFO_V4_V1 0xf, 0, 0, 1, 0, 0, 0, 0, (V_MOV_B32_e32 $mipid), $rsrc)
|
|
>;
|
|
|
|
def : Pat <
|
|
(int_SI_resinfo i32:$mipid, v32i8:$rsrc, TEX_ARRAY_MSAA),
|
|
(IMAGE_GET_RESINFO_V4_V1 0xf, 0, 0, 1, 0, 0, 0, 0, (V_MOV_B32_e32 $mipid), $rsrc)
|
|
>;
|
|
|
|
/********** ============================================ **********/
|
|
/********** Extraction, Insertion, Building and Casting **********/
|
|
/********** ============================================ **********/
|
|
|
|
foreach Index = 0-2 in {
|
|
def Extract_Element_v2i32_#Index : Extract_Element <
|
|
i32, v2i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v2i32_#Index : Insert_Element <
|
|
i32, v2i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Extract_Element_v2f32_#Index : Extract_Element <
|
|
f32, v2f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v2f32_#Index : Insert_Element <
|
|
f32, v2f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
}
|
|
|
|
foreach Index = 0-3 in {
|
|
def Extract_Element_v4i32_#Index : Extract_Element <
|
|
i32, v4i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v4i32_#Index : Insert_Element <
|
|
i32, v4i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Extract_Element_v4f32_#Index : Extract_Element <
|
|
f32, v4f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v4f32_#Index : Insert_Element <
|
|
f32, v4f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
}
|
|
|
|
foreach Index = 0-7 in {
|
|
def Extract_Element_v8i32_#Index : Extract_Element <
|
|
i32, v8i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v8i32_#Index : Insert_Element <
|
|
i32, v8i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Extract_Element_v8f32_#Index : Extract_Element <
|
|
f32, v8f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v8f32_#Index : Insert_Element <
|
|
f32, v8f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
}
|
|
|
|
foreach Index = 0-15 in {
|
|
def Extract_Element_v16i32_#Index : Extract_Element <
|
|
i32, v16i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v16i32_#Index : Insert_Element <
|
|
i32, v16i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Extract_Element_v16f32_#Index : Extract_Element <
|
|
f32, v16f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v16f32_#Index : Insert_Element <
|
|
f32, v16f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
}
|
|
|
|
def : BitConvert <i32, f32, SReg_32>;
|
|
def : BitConvert <i32, f32, VReg_32>;
|
|
|
|
def : BitConvert <f32, i32, SReg_32>;
|
|
def : BitConvert <f32, i32, VReg_32>;
|
|
|
|
def : BitConvert <i64, f64, VReg_64>;
|
|
|
|
def : BitConvert <f64, i64, VReg_64>;
|
|
|
|
def : BitConvert <v2f32, v2i32, VReg_64>;
|
|
def : BitConvert <v2i32, v2f32, VReg_64>;
|
|
def : BitConvert <v2i32, i64, VReg_64>;
|
|
def : BitConvert <i64, v2i32, VReg_64>;
|
|
def : BitConvert <v2f32, i64, VReg_64>;
|
|
def : BitConvert <i64, v2f32, VReg_64>;
|
|
def : BitConvert <v2i32, f64, VReg_64>;
|
|
def : BitConvert <f64, v2i32, VReg_64>;
|
|
def : BitConvert <v4f32, v4i32, VReg_128>;
|
|
def : BitConvert <v4i32, v4f32, VReg_128>;
|
|
|
|
def : BitConvert <v8f32, v8i32, SReg_256>;
|
|
def : BitConvert <v8i32, v8f32, SReg_256>;
|
|
def : BitConvert <v8i32, v32i8, SReg_256>;
|
|
def : BitConvert <v32i8, v8i32, SReg_256>;
|
|
def : BitConvert <v8i32, v32i8, VReg_256>;
|
|
def : BitConvert <v8i32, v8f32, VReg_256>;
|
|
def : BitConvert <v8f32, v8i32, VReg_256>;
|
|
def : BitConvert <v32i8, v8i32, VReg_256>;
|
|
|
|
def : BitConvert <v16i32, v16f32, VReg_512>;
|
|
def : BitConvert <v16f32, v16i32, VReg_512>;
|
|
|
|
/********** =================== **********/
|
|
/********** Src & Dst modifiers **********/
|
|
/********** =================== **********/
|
|
|
|
def FCLAMP_SI : AMDGPUShaderInst <
|
|
(outs VReg_32:$dst),
|
|
(ins VSrc_32:$src0),
|
|
"FCLAMP_SI $dst, $src0",
|
|
[]
|
|
> {
|
|
let usesCustomInserter = 1;
|
|
}
|
|
|
|
def : Pat <
|
|
(AMDGPUclamp f32:$src, (f32 FP_ZERO), (f32 FP_ONE)),
|
|
(FCLAMP_SI f32:$src)
|
|
>;
|
|
|
|
/********** ================================ **********/
|
|
/********** Floating point absolute/negative **********/
|
|
/********** ================================ **********/
|
|
|
|
// Manipulate the sign bit directly, as e.g. using the source negation modifier
|
|
// in V_ADD_F32_e64 $src, 0, [...] does not result in -0.0 for $src == +0.0,
|
|
// breaking the piglit *s-floatBitsToInt-neg* tests
|
|
|
|
// TODO: Look into not implementing isFNegFree/isFAbsFree for SI, and possibly
|
|
// removing these patterns
|
|
|
|
def : Pat <
|
|
(fneg (fabs f32:$src)),
|
|
(V_OR_B32_e32 $src, (V_MOV_B32_e32 0x80000000)) /* Set sign bit */
|
|
>;
|
|
|
|
def FABS_SI : AMDGPUShaderInst <
|
|
(outs VReg_32:$dst),
|
|
(ins VSrc_32:$src0),
|
|
"FABS_SI $dst, $src0",
|
|
[]
|
|
> {
|
|
let usesCustomInserter = 1;
|
|
}
|
|
|
|
def : Pat <
|
|
(fabs f32:$src),
|
|
(FABS_SI f32:$src)
|
|
>;
|
|
|
|
def FNEG_SI : AMDGPUShaderInst <
|
|
(outs VReg_32:$dst),
|
|
(ins VSrc_32:$src0),
|
|
"FNEG_SI $dst, $src0",
|
|
[]
|
|
> {
|
|
let usesCustomInserter = 1;
|
|
}
|
|
|
|
def : Pat <
|
|
(fneg f32:$src),
|
|
(FNEG_SI f32:$src)
|
|
>;
|
|
|
|
/********** ================== **********/
|
|
/********** Immediate Patterns **********/
|
|
/********** ================== **********/
|
|
|
|
def : Pat <
|
|
(SGPRImm<(i32 imm)>:$imm),
|
|
(S_MOV_B32 imm:$imm)
|
|
>;
|
|
|
|
def : Pat <
|
|
(SGPRImm<(f32 fpimm)>:$imm),
|
|
(S_MOV_B32 fpimm:$imm)
|
|
>;
|
|
|
|
def : Pat <
|
|
(i32 imm:$imm),
|
|
(V_MOV_B32_e32 imm:$imm)
|
|
>;
|
|
|
|
def : Pat <
|
|
(f32 fpimm:$imm),
|
|
(V_MOV_B32_e32 fpimm:$imm)
|
|
>;
|
|
|
|
def : Pat <
|
|
(i64 InlineImm<i64>:$imm),
|
|
(S_MOV_B64 InlineImm<i64>:$imm)
|
|
>;
|
|
|
|
/********** ===================== **********/
|
|
/********** Interpolation Paterns **********/
|
|
/********** ===================== **********/
|
|
|
|
def : Pat <
|
|
(int_SI_fs_constant imm:$attr_chan, imm:$attr, i32:$params),
|
|
(V_INTERP_MOV_F32 INTERP.P0, imm:$attr_chan, imm:$attr, $params)
|
|
>;
|
|
|
|
def : Pat <
|
|
(int_SI_fs_interp imm:$attr_chan, imm:$attr, M0Reg:$params, v2i32:$ij),
|
|
(V_INTERP_P2_F32 (V_INTERP_P1_F32 (EXTRACT_SUBREG v2i32:$ij, sub0),
|
|
imm:$attr_chan, imm:$attr, i32:$params),
|
|
(EXTRACT_SUBREG $ij, sub1),
|
|
imm:$attr_chan, imm:$attr, $params)
|
|
>;
|
|
|
|
/********** ================== **********/
|
|
/********** Intrinsic Patterns **********/
|
|
/********** ================== **********/
|
|
|
|
/* llvm.AMDGPU.pow */
|
|
def : POW_Common <V_LOG_F32_e32, V_EXP_F32_e32, V_MUL_LEGACY_F32_e32>;
|
|
|
|
def : Pat <
|
|
(int_AMDGPU_div f32:$src0, f32:$src1),
|
|
(V_MUL_LEGACY_F32_e32 $src0, (V_RCP_LEGACY_F32_e32 $src1))
|
|
>;
|
|
|
|
def : Pat<
|
|
(fdiv f64:$src0, f64:$src1),
|
|
(V_MUL_F64 $src0, (V_RCP_F64_e32 $src1), (i64 0))
|
|
>;
|
|
|
|
def : Pat <
|
|
(fcos f32:$src0),
|
|
(V_COS_F32_e32 (V_MUL_F32_e32 $src0, (V_MOV_B32_e32 CONST.TWO_PI_INV)))
|
|
>;
|
|
|
|
def : Pat <
|
|
(fsin f32:$src0),
|
|
(V_SIN_F32_e32 (V_MUL_F32_e32 $src0, (V_MOV_B32_e32 CONST.TWO_PI_INV)))
|
|
>;
|
|
|
|
def : Pat <
|
|
(int_AMDGPU_cube v4f32:$src),
|
|
(INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG (INSERT_SUBREG (v4f32 (IMPLICIT_DEF)),
|
|
(V_CUBETC_F32 (EXTRACT_SUBREG $src, sub0),
|
|
(EXTRACT_SUBREG $src, sub1),
|
|
(EXTRACT_SUBREG $src, sub2)),
|
|
sub0),
|
|
(V_CUBESC_F32 (EXTRACT_SUBREG $src, sub0),
|
|
(EXTRACT_SUBREG $src, sub1),
|
|
(EXTRACT_SUBREG $src, sub2)),
|
|
sub1),
|
|
(V_CUBEMA_F32 (EXTRACT_SUBREG $src, sub0),
|
|
(EXTRACT_SUBREG $src, sub1),
|
|
(EXTRACT_SUBREG $src, sub2)),
|
|
sub2),
|
|
(V_CUBEID_F32 (EXTRACT_SUBREG $src, sub0),
|
|
(EXTRACT_SUBREG $src, sub1),
|
|
(EXTRACT_SUBREG $src, sub2)),
|
|
sub3)
|
|
>;
|
|
|
|
def : Pat <
|
|
(i32 (sext i1:$src0)),
|
|
(V_CNDMASK_B32_e64 (i32 0), (i32 -1), $src0)
|
|
>;
|
|
|
|
class Ext32Pat <SDNode ext> : Pat <
|
|
(i32 (ext i1:$src0)),
|
|
(V_CNDMASK_B32_e64 (i32 0), (i32 1), $src0)
|
|
>;
|
|
|
|
def : Ext32Pat <zext>;
|
|
def : Ext32Pat <anyext>;
|
|
|
|
// Offset in an 32Bit VGPR
|
|
def : Pat <
|
|
(SIload_constant v4i32:$sbase, i32:$voff),
|
|
(BUFFER_LOAD_DWORD_OFFEN $sbase, $voff, 0, 0, 0, 0)
|
|
>;
|
|
|
|
// The multiplication scales from [0,1] to the unsigned integer range
|
|
def : Pat <
|
|
(AMDGPUurecip i32:$src0),
|
|
(V_CVT_U32_F32_e32
|
|
(V_MUL_F32_e32 CONST.FP_UINT_MAX_PLUS_1,
|
|
(V_RCP_IFLAG_F32_e32 (V_CVT_F32_U32_e32 $src0))))
|
|
>;
|
|
|
|
def : Pat <
|
|
(int_SI_tid),
|
|
(V_MBCNT_HI_U32_B32_e32 0xffffffff,
|
|
(V_MBCNT_LO_U32_B32_e64 0xffffffff, 0, 0, 0))
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VOP3 Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def : IMad24Pat<V_MAD_I32_I24>;
|
|
def : UMad24Pat<V_MAD_U32_U24>;
|
|
|
|
def : Pat <
|
|
(fadd f64:$src0, f64:$src1),
|
|
(V_ADD_F64 $src0, $src1, (i64 0))
|
|
>;
|
|
|
|
def : Pat <
|
|
(fmul f64:$src0, f64:$src1),
|
|
(V_MUL_F64 $src0, $src1, (i64 0))
|
|
>;
|
|
|
|
def : Pat <
|
|
(mul i32:$src0, i32:$src1),
|
|
(V_MUL_LO_I32 $src0, $src1, (i32 0))
|
|
>;
|
|
|
|
def : Pat <
|
|
(mulhu i32:$src0, i32:$src1),
|
|
(V_MUL_HI_U32 $src0, $src1, (i32 0))
|
|
>;
|
|
|
|
def : Pat <
|
|
(mulhs i32:$src0, i32:$src1),
|
|
(V_MUL_HI_I32 $src0, $src1, (i32 0))
|
|
>;
|
|
|
|
defm : BFIPatterns <V_BFI_B32, S_MOV_B32>;
|
|
def : ROTRPattern <V_ALIGNBIT_B32>;
|
|
|
|
/********** ======================= **********/
|
|
/********** Load/Store Patterns **********/
|
|
/********** ======================= **********/
|
|
|
|
multiclass DSReadPat <DS inst, ValueType vt, PatFrag frag> {
|
|
def : Pat <
|
|
(vt (frag (add i32:$ptr, (i32 IMM16bit:$offset)))),
|
|
(inst (i1 0), $ptr, (as_i16imm $offset))
|
|
>;
|
|
|
|
def : Pat <
|
|
(frag i32:$src0),
|
|
(vt (inst 0, $src0, 0))
|
|
>;
|
|
}
|
|
|
|
defm : DSReadPat <DS_READ_I8, i32, sextloadi8_local>;
|
|
defm : DSReadPat <DS_READ_U8, i32, az_extloadi8_local>;
|
|
defm : DSReadPat <DS_READ_I16, i32, sextloadi16_local>;
|
|
defm : DSReadPat <DS_READ_U16, i32, az_extloadi16_local>;
|
|
defm : DSReadPat <DS_READ_B32, i32, local_load>;
|
|
defm : DSReadPat <DS_READ_B64, v2i32, local_load>;
|
|
|
|
multiclass DSWritePat <DS inst, ValueType vt, PatFrag frag> {
|
|
def : Pat <
|
|
(frag vt:$value, (add i32:$ptr, (i32 IMM16bit:$offset))),
|
|
(inst (i1 0), $ptr, $value, (as_i16imm $offset))
|
|
>;
|
|
|
|
def : Pat <
|
|
(frag vt:$val, i32:$ptr),
|
|
(inst 0, $ptr, $val, 0)
|
|
>;
|
|
}
|
|
|
|
defm : DSWritePat <DS_WRITE_B8, i32, truncstorei8_local>;
|
|
defm : DSWritePat <DS_WRITE_B16, i32, truncstorei16_local>;
|
|
defm : DSWritePat <DS_WRITE_B32, i32, local_store>;
|
|
defm : DSWritePat <DS_WRITE_B64, v2i32, local_store>;
|
|
|
|
multiclass DSAtomicRetPat<DS inst, ValueType vt, PatFrag frag> {
|
|
def : Pat <
|
|
(frag (add i32:$ptr, (i32 IMM16bit:$offset)), vt:$value),
|
|
(inst (i1 0), $ptr, $value, (as_i16imm $offset))
|
|
>;
|
|
|
|
def : Pat <
|
|
(frag i32:$ptr, vt:$val),
|
|
(inst 0, $ptr, $val, 0)
|
|
>;
|
|
}
|
|
|
|
// Special case of DSAtomicRetPat for add / sub 1 -> inc / dec
|
|
//
|
|
// We need to use something for the data0, so we set a register to
|
|
// -1. For the non-rtn variants, the manual says it does
|
|
// DS[A] = (DS[A] >= D0) ? 0 : DS[A] + 1, and setting D0 to uint_max
|
|
// will always do the increment so I'm assuming it's the same.
|
|
//
|
|
// We also load this -1 with s_mov_b32 / s_mov_b64 even though this
|
|
// needs to be a VGPR. The SGPR copy pass will fix this, and it's
|
|
// easier since there is no v_mov_b64.
|
|
multiclass DSAtomicIncRetPat<DS inst, ValueType vt,
|
|
Instruction LoadImm, PatFrag frag> {
|
|
def : Pat <
|
|
(frag (add i32:$ptr, (i32 IMM16bit:$offset)), (vt 1)),
|
|
(inst (i1 0), $ptr, (LoadImm (vt -1)), (as_i16imm $offset))
|
|
>;
|
|
|
|
def : Pat <
|
|
(frag i32:$ptr, (vt 1)),
|
|
(inst 0, $ptr, (LoadImm (vt -1)), 0)
|
|
>;
|
|
}
|
|
|
|
multiclass DSAtomicCmpXChg <DS inst, ValueType vt, PatFrag frag> {
|
|
def : Pat <
|
|
(frag (add i32:$ptr, (i32 IMM16bit:$offset)), vt:$cmp, vt:$swap),
|
|
(inst (i1 0), $ptr, $cmp, $swap, (as_i16imm $offset))
|
|
>;
|
|
|
|
def : Pat <
|
|
(frag i32:$ptr, vt:$cmp, vt:$swap),
|
|
(inst 0, $ptr, $cmp, $swap, 0)
|
|
>;
|
|
}
|
|
|
|
|
|
// 32-bit atomics.
|
|
defm : DSAtomicIncRetPat<DS_INC_RTN_U32, i32,
|
|
S_MOV_B32, atomic_load_add_local>;
|
|
defm : DSAtomicIncRetPat<DS_DEC_RTN_U32, i32,
|
|
S_MOV_B32, atomic_load_sub_local>;
|
|
|
|
defm : DSAtomicRetPat<DS_WRXCHG_RTN_B32, i32, atomic_swap_local>;
|
|
defm : DSAtomicRetPat<DS_ADD_RTN_U32, i32, atomic_load_add_local>;
|
|
defm : DSAtomicRetPat<DS_SUB_RTN_U32, i32, atomic_load_sub_local>;
|
|
defm : DSAtomicRetPat<DS_AND_RTN_B32, i32, atomic_load_and_local>;
|
|
defm : DSAtomicRetPat<DS_OR_RTN_B32, i32, atomic_load_or_local>;
|
|
defm : DSAtomicRetPat<DS_XOR_RTN_B32, i32, atomic_load_xor_local>;
|
|
defm : DSAtomicRetPat<DS_MIN_RTN_I32, i32, atomic_load_min_local>;
|
|
defm : DSAtomicRetPat<DS_MAX_RTN_I32, i32, atomic_load_max_local>;
|
|
defm : DSAtomicRetPat<DS_MIN_RTN_U32, i32, atomic_load_umin_local>;
|
|
defm : DSAtomicRetPat<DS_MAX_RTN_U32, i32, atomic_load_umax_local>;
|
|
|
|
defm : DSAtomicCmpXChg<DS_CMPST_RTN_B32, i32, atomic_cmp_swap_32_local>;
|
|
|
|
// 64-bit atomics.
|
|
defm : DSAtomicIncRetPat<DS_INC_RTN_U64, i64,
|
|
S_MOV_B64, atomic_load_add_local>;
|
|
defm : DSAtomicIncRetPat<DS_DEC_RTN_U64, i64,
|
|
S_MOV_B64, atomic_load_sub_local>;
|
|
|
|
defm : DSAtomicRetPat<DS_WRXCHG_RTN_B64, i64, atomic_swap_local>;
|
|
defm : DSAtomicRetPat<DS_ADD_RTN_U64, i64, atomic_load_add_local>;
|
|
defm : DSAtomicRetPat<DS_SUB_RTN_U64, i64, atomic_load_sub_local>;
|
|
defm : DSAtomicRetPat<DS_AND_RTN_B64, i64, atomic_load_and_local>;
|
|
defm : DSAtomicRetPat<DS_OR_RTN_B64, i64, atomic_load_or_local>;
|
|
defm : DSAtomicRetPat<DS_XOR_RTN_B64, i64, atomic_load_xor_local>;
|
|
defm : DSAtomicRetPat<DS_MIN_RTN_I64, i64, atomic_load_min_local>;
|
|
defm : DSAtomicRetPat<DS_MAX_RTN_I64, i64, atomic_load_max_local>;
|
|
defm : DSAtomicRetPat<DS_MIN_RTN_U64, i64, atomic_load_umin_local>;
|
|
defm : DSAtomicRetPat<DS_MAX_RTN_U64, i64, atomic_load_umax_local>;
|
|
|
|
defm : DSAtomicCmpXChg<DS_CMPST_RTN_B64, i64, atomic_cmp_swap_64_local>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// MUBUF Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
multiclass MUBUFLoad_Pattern <MUBUF Instr_ADDR64, ValueType vt,
|
|
PatFrag constant_ld> {
|
|
def : Pat <
|
|
(vt (constant_ld (add i64:$ptr, i64:$offset))),
|
|
(Instr_ADDR64 (SI_ADDR64_RSRC $ptr), $offset, 0)
|
|
>;
|
|
}
|
|
|
|
defm : MUBUFLoad_Pattern <BUFFER_LOAD_SBYTE_ADDR64, i32,
|
|
sextloadi8_constant>;
|
|
defm : MUBUFLoad_Pattern <BUFFER_LOAD_UBYTE_ADDR64, i32,
|
|
az_extloadi8_constant>;
|
|
defm : MUBUFLoad_Pattern <BUFFER_LOAD_SSHORT_ADDR64, i32,
|
|
sextloadi16_constant>;
|
|
defm : MUBUFLoad_Pattern <BUFFER_LOAD_USHORT_ADDR64, i32,
|
|
az_extloadi16_constant>;
|
|
defm : MUBUFLoad_Pattern <BUFFER_LOAD_DWORD_ADDR64, i32,
|
|
constant_load>;
|
|
defm : MUBUFLoad_Pattern <BUFFER_LOAD_DWORDX2_ADDR64, v2i32,
|
|
constant_load>;
|
|
defm : MUBUFLoad_Pattern <BUFFER_LOAD_DWORDX4_ADDR64, v4i32,
|
|
constant_load>;
|
|
|
|
// BUFFER_LOAD_DWORD*, addr64=0
|
|
multiclass MUBUF_Load_Dword <ValueType vt, MUBUF offset, MUBUF offen, MUBUF idxen,
|
|
MUBUF bothen> {
|
|
|
|
def : Pat <
|
|
(vt (int_SI_buffer_load_dword v4i32:$rsrc, i32:$vaddr, i32:$soffset,
|
|
imm:$offset, 0, 0, imm:$glc, imm:$slc,
|
|
imm:$tfe)),
|
|
(offset $rsrc, $vaddr, (as_i16imm $offset), $soffset, (as_i1imm $glc),
|
|
(as_i1imm $slc), (as_i1imm $tfe))
|
|
>;
|
|
|
|
def : Pat <
|
|
(vt (int_SI_buffer_load_dword v4i32:$rsrc, i32:$vaddr, i32:$soffset,
|
|
imm, 1, 0, imm:$glc, imm:$slc,
|
|
imm:$tfe)),
|
|
(offen $rsrc, $vaddr, $soffset, (as_i1imm $glc), (as_i1imm $slc),
|
|
(as_i1imm $tfe))
|
|
>;
|
|
|
|
def : Pat <
|
|
(vt (int_SI_buffer_load_dword v4i32:$rsrc, i32:$vaddr, i32:$soffset,
|
|
imm:$offset, 0, 1, imm:$glc, imm:$slc,
|
|
imm:$tfe)),
|
|
(idxen $rsrc, $vaddr, (as_i16imm $offset), $soffset, (as_i1imm $glc),
|
|
(as_i1imm $slc), (as_i1imm $tfe))
|
|
>;
|
|
|
|
def : Pat <
|
|
(vt (int_SI_buffer_load_dword v4i32:$rsrc, v2i32:$vaddr, i32:$soffset,
|
|
imm, 1, 1, imm:$glc, imm:$slc,
|
|
imm:$tfe)),
|
|
(bothen $rsrc, $vaddr, $soffset, (as_i1imm $glc), (as_i1imm $slc),
|
|
(as_i1imm $tfe))
|
|
>;
|
|
}
|
|
|
|
defm : MUBUF_Load_Dword <i32, BUFFER_LOAD_DWORD_OFFSET, BUFFER_LOAD_DWORD_OFFEN,
|
|
BUFFER_LOAD_DWORD_IDXEN, BUFFER_LOAD_DWORD_BOTHEN>;
|
|
defm : MUBUF_Load_Dword <v2i32, BUFFER_LOAD_DWORDX2_OFFSET, BUFFER_LOAD_DWORDX2_OFFEN,
|
|
BUFFER_LOAD_DWORDX2_IDXEN, BUFFER_LOAD_DWORDX2_BOTHEN>;
|
|
defm : MUBUF_Load_Dword <v4i32, BUFFER_LOAD_DWORDX4_OFFSET, BUFFER_LOAD_DWORDX4_OFFEN,
|
|
BUFFER_LOAD_DWORDX4_IDXEN, BUFFER_LOAD_DWORDX4_BOTHEN>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// MTBUF Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// TBUFFER_STORE_FORMAT_*, addr64=0
|
|
class MTBUF_StoreResource <ValueType vt, int num_channels, MTBUF opcode> : Pat<
|
|
(SItbuffer_store v4i32:$rsrc, vt:$vdata, num_channels, i32:$vaddr,
|
|
i32:$soffset, imm:$inst_offset, imm:$dfmt,
|
|
imm:$nfmt, imm:$offen, imm:$idxen,
|
|
imm:$glc, imm:$slc, imm:$tfe),
|
|
(opcode
|
|
$vdata, (as_i16imm $inst_offset), (as_i1imm $offen), (as_i1imm $idxen),
|
|
(as_i1imm $glc), 0, (as_i8imm $dfmt), (as_i8imm $nfmt), $vaddr, $rsrc,
|
|
(as_i1imm $slc), (as_i1imm $tfe), $soffset)
|
|
>;
|
|
|
|
def : MTBUF_StoreResource <i32, 1, TBUFFER_STORE_FORMAT_X>;
|
|
def : MTBUF_StoreResource <v2i32, 2, TBUFFER_STORE_FORMAT_XY>;
|
|
def : MTBUF_StoreResource <v4i32, 3, TBUFFER_STORE_FORMAT_XYZ>;
|
|
def : MTBUF_StoreResource <v4i32, 4, TBUFFER_STORE_FORMAT_XYZW>;
|
|
|
|
let SubtargetPredicate = isCI in {
|
|
|
|
// Sea island new arithmetic instructinos
|
|
let neverHasSideEffects = 1 in {
|
|
defm V_TRUNC_F64 : VOP1_64 <0x00000017, "V_TRUNC_F64",
|
|
[(set f64:$dst, (ftrunc f64:$src0))]
|
|
>;
|
|
defm V_CEIL_F64 : VOP1_64 <0x00000018, "V_CEIL_F64",
|
|
[(set f64:$dst, (fceil f64:$src0))]
|
|
>;
|
|
defm V_FLOOR_F64 : VOP1_64 <0x0000001A, "V_FLOOR_F64",
|
|
[(set f64:$dst, (ffloor f64:$src0))]
|
|
>;
|
|
defm V_RNDNE_F64 : VOP1_64 <0x00000019, "V_RNDNE_F64",
|
|
[(set f64:$dst, (frint f64:$src0))]
|
|
>;
|
|
|
|
defm V_QSAD_PK_U16_U8 : VOP3_32 <0x00000173, "V_QSAD_PK_U16_U8", []>;
|
|
defm V_MQSAD_U16_U8 : VOP3_32 <0x000000172, "V_MQSAD_U16_U8", []>;
|
|
defm V_MQSAD_U32_U8 : VOP3_32 <0x00000175, "V_MQSAD_U32_U8", []>;
|
|
def V_MAD_U64_U32 : VOP3_64 <0x00000176, "V_MAD_U64_U32", []>;
|
|
|
|
// XXX - Does this set VCC?
|
|
def V_MAD_I64_I32 : VOP3_64 <0x00000177, "V_MAD_I64_I32", []>;
|
|
} // End neverHasSideEffects = 1
|
|
|
|
// Remaining instructions:
|
|
// FLAT_*
|
|
// S_CBRANCH_CDBGUSER
|
|
// S_CBRANCH_CDBGSYS
|
|
// S_CBRANCH_CDBGSYS_OR_USER
|
|
// S_CBRANCH_CDBGSYS_AND_USER
|
|
// S_DCACHE_INV_VOL
|
|
// V_EXP_LEGACY_F32
|
|
// V_LOG_LEGACY_F32
|
|
// DS_NOP
|
|
// DS_GWS_SEMA_RELEASE_ALL
|
|
// DS_WRAP_RTN_B32
|
|
// DS_CNDXCHG32_RTN_B64
|
|
// DS_WRITE_B96
|
|
// DS_WRITE_B128
|
|
// DS_CONDXCHG32_RTN_B128
|
|
// DS_READ_B96
|
|
// DS_READ_B128
|
|
// BUFFER_LOAD_DWORDX3
|
|
// BUFFER_STORE_DWORDX3
|
|
|
|
} // End iSCI
|
|
|
|
|
|
/********** ====================== **********/
|
|
/********** Indirect adressing **********/
|
|
/********** ====================== **********/
|
|
|
|
multiclass SI_INDIRECT_Pattern <ValueType vt, ValueType eltvt, SI_INDIRECT_DST IndDst> {
|
|
|
|
// 1. Extract with offset
|
|
def : Pat<
|
|
(vector_extract vt:$vec, (add i32:$idx, imm:$off)),
|
|
(eltvt (SI_INDIRECT_SRC (IMPLICIT_DEF), $vec, $idx, imm:$off))
|
|
>;
|
|
|
|
// 2. Extract without offset
|
|
def : Pat<
|
|
(vector_extract vt:$vec, i32:$idx),
|
|
(eltvt (SI_INDIRECT_SRC (IMPLICIT_DEF), $vec, $idx, 0))
|
|
>;
|
|
|
|
// 3. Insert with offset
|
|
def : Pat<
|
|
(vector_insert vt:$vec, eltvt:$val, (add i32:$idx, imm:$off)),
|
|
(IndDst (IMPLICIT_DEF), $vec, $idx, imm:$off, $val)
|
|
>;
|
|
|
|
// 4. Insert without offset
|
|
def : Pat<
|
|
(vector_insert vt:$vec, eltvt:$val, i32:$idx),
|
|
(IndDst (IMPLICIT_DEF), $vec, $idx, 0, $val)
|
|
>;
|
|
}
|
|
|
|
defm : SI_INDIRECT_Pattern <v2f32, f32, SI_INDIRECT_DST_V2>;
|
|
defm : SI_INDIRECT_Pattern <v4f32, f32, SI_INDIRECT_DST_V4>;
|
|
defm : SI_INDIRECT_Pattern <v8f32, f32, SI_INDIRECT_DST_V8>;
|
|
defm : SI_INDIRECT_Pattern <v16f32, f32, SI_INDIRECT_DST_V16>;
|
|
|
|
defm : SI_INDIRECT_Pattern <v2i32, i32, SI_INDIRECT_DST_V2>;
|
|
defm : SI_INDIRECT_Pattern <v4i32, i32, SI_INDIRECT_DST_V4>;
|
|
defm : SI_INDIRECT_Pattern <v8i32, i32, SI_INDIRECT_DST_V8>;
|
|
defm : SI_INDIRECT_Pattern <v16i32, i32, SI_INDIRECT_DST_V16>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Conversion Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def : Pat<(i32 (sext_inreg i32:$src, i1)),
|
|
(S_BFE_I32 i32:$src, 65536)>; // 0 | 1 << 16
|
|
|
|
// TODO: Match 64-bit BFE. SI has a 64-bit BFE, but it's scalar only so it
|
|
// might not be worth the effort, and will need to expand to shifts when
|
|
// fixing SGPR copies.
|
|
|
|
// Handle sext_inreg in i64
|
|
def : Pat <
|
|
(i64 (sext_inreg i64:$src, i1)),
|
|
(INSERT_SUBREG (INSERT_SUBREG (i64 (IMPLICIT_DEF)),
|
|
(S_BFE_I32 (EXTRACT_SUBREG i64:$src, sub0), 65536), sub0), // 0 | 1 << 16
|
|
(S_MOV_B32 -1), sub1)
|
|
>;
|
|
|
|
def : Pat <
|
|
(i64 (sext_inreg i64:$src, i8)),
|
|
(INSERT_SUBREG (INSERT_SUBREG (i64 (IMPLICIT_DEF)),
|
|
(S_SEXT_I32_I8 (EXTRACT_SUBREG i64:$src, sub0)), sub0),
|
|
(S_MOV_B32 -1), sub1)
|
|
>;
|
|
|
|
def : Pat <
|
|
(i64 (sext_inreg i64:$src, i16)),
|
|
(INSERT_SUBREG (INSERT_SUBREG (i64 (IMPLICIT_DEF)),
|
|
(S_SEXT_I32_I16 (EXTRACT_SUBREG i64:$src, sub0)), sub0),
|
|
(S_MOV_B32 -1), sub1)
|
|
>;
|
|
|
|
class ZExt_i64_i32_Pat <SDNode ext> : Pat <
|
|
(i64 (ext i32:$src)),
|
|
(INSERT_SUBREG (INSERT_SUBREG (i64 (IMPLICIT_DEF)), $src, sub0),
|
|
(S_MOV_B32 0), sub1)
|
|
>;
|
|
|
|
class ZExt_i64_i1_Pat <SDNode ext> : Pat <
|
|
(i64 (ext i1:$src)),
|
|
(INSERT_SUBREG
|
|
(INSERT_SUBREG (i64 (IMPLICIT_DEF)),
|
|
(V_CNDMASK_B32_e64 (i32 0), (i32 1), $src), sub0),
|
|
(S_MOV_B32 0), sub1)
|
|
>;
|
|
|
|
|
|
def : ZExt_i64_i32_Pat<zext>;
|
|
def : ZExt_i64_i32_Pat<anyext>;
|
|
def : ZExt_i64_i1_Pat<zext>;
|
|
def : ZExt_i64_i1_Pat<anyext>;
|
|
|
|
def : Pat <
|
|
(i64 (sext i32:$src)),
|
|
(INSERT_SUBREG
|
|
(INSERT_SUBREG (i64 (IMPLICIT_DEF)), $src, sub0),
|
|
(S_ASHR_I32 $src, 31), sub1)
|
|
>;
|
|
|
|
def : Pat <
|
|
(i64 (sext i1:$src)),
|
|
(INSERT_SUBREG
|
|
(INSERT_SUBREG
|
|
(i64 (IMPLICIT_DEF)),
|
|
(V_CNDMASK_B32_e64 0, -1, $src), sub0),
|
|
(V_CNDMASK_B32_e64 0, -1, $src), sub1)
|
|
>;
|
|
|
|
def : Pat <
|
|
(f32 (sint_to_fp i1:$src)),
|
|
(V_CNDMASK_B32_e64 (i32 0), CONST.FP32_NEG_ONE, $src)
|
|
>;
|
|
|
|
def : Pat <
|
|
(f32 (uint_to_fp i1:$src)),
|
|
(V_CNDMASK_B32_e64 (i32 0), CONST.FP32_ONE, $src)
|
|
>;
|
|
|
|
def : Pat <
|
|
(f64 (sint_to_fp i1:$src)),
|
|
(V_CVT_F64_I32_e32 (V_CNDMASK_B32_e64 (i32 0), (i32 -1), $src))
|
|
>;
|
|
|
|
def : Pat <
|
|
(f64 (uint_to_fp i1:$src)),
|
|
(V_CVT_F64_U32_e32 (V_CNDMASK_B32_e64 (i32 0), (i32 1), $src))
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Miscellaneous Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def : Pat <
|
|
(i32 (trunc i64:$a)),
|
|
(EXTRACT_SUBREG $a, sub0)
|
|
>;
|
|
|
|
def : Pat <
|
|
(i1 (trunc i32:$a)),
|
|
(V_CMP_EQ_I32_e64 (V_AND_B32_e32 (i32 1), $a), 1)
|
|
>;
|
|
|
|
// V_ADD_I32_e32/S_ADD_I32 produces carry in VCC/SCC. For the vector
|
|
// case, the sgpr-copies pass will fix this to use the vector version.
|
|
def : Pat <
|
|
(i32 (addc i32:$src0, i32:$src1)),
|
|
(S_ADD_I32 $src0, $src1)
|
|
>;
|
|
|
|
//============================================================================//
|
|
// Miscellaneous Optimization Patterns
|
|
//============================================================================//
|
|
|
|
def : SHA256MaPattern <V_BFI_B32, V_XOR_B32_e32>;
|
|
|
|
} // End isSI predicate
|