llvm-project/llvm/lib/Target/AMDGPU/FLATInstructions.td

622 lines
28 KiB
TableGen

//===-- FLATInstructions.td - FLAT Instruction Defintions -----------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
def FLATAtomic : ComplexPattern<i64, 3, "SelectFlatAtomic", [], [], -10>;
def FLATOffset : ComplexPattern<i64, 3, "SelectFlat", [], [], -10>;
//===----------------------------------------------------------------------===//
// FLAT classes
//===----------------------------------------------------------------------===//
class FLAT_Pseudo<string opName, dag outs, dag ins,
string asmOps, list<dag> pattern=[]> :
InstSI<outs, ins, "", pattern>,
SIMCInstr<opName, SIEncodingFamily.NONE> {
let isPseudo = 1;
let isCodeGenOnly = 1;
let SubtargetPredicate = isCIVI;
let FLAT = 1;
// Internally, FLAT instruction are executed as both an LDS and a
// Buffer instruction; so, they increment both VM_CNT and LGKM_CNT
// and are not considered done until both have been decremented.
let VM_CNT = 1;
let LGKM_CNT = 1;
let UseNamedOperandTable = 1;
let hasSideEffects = 0;
let SchedRW = [WriteVMEM];
string Mnemonic = opName;
string AsmOperands = asmOps;
bits<1> is_flat_global = 0;
bits<1> is_flat_scratch = 0;
bits<1> has_vdst = 1;
bits<1> has_data = 1;
bits<1> has_glc = 1;
bits<1> glcValue = 0;
// TODO: M0 if it could possibly access LDS (before gfx9? only)?
let Uses = !if(is_flat_global, [EXEC], [EXEC, FLAT_SCR]);
}
class FLAT_Real <bits<7> op, FLAT_Pseudo ps> :
InstSI <ps.OutOperandList, ps.InOperandList, ps.Mnemonic # ps.AsmOperands, []>,
Enc64 {
let isPseudo = 0;
let isCodeGenOnly = 0;
// copy relevant pseudo op flags
let SubtargetPredicate = ps.SubtargetPredicate;
let AsmMatchConverter = ps.AsmMatchConverter;
let TSFlags = ps.TSFlags;
let UseNamedOperandTable = ps.UseNamedOperandTable;
// encoding fields
bits<8> vaddr;
bits<8> vdata;
bits<8> vdst;
bits<1> slc;
bits<1> glc;
// Only valid on gfx9
bits<1> lds = 0; // XXX - What does this actually do?
// Segment, 00=flat, 01=scratch, 10=global, 11=reserved
bits<2> seg = !if(ps.is_flat_global, 0b10,
!if(ps.is_flat_scratch, 0b01, 0));
// Signed offset. Highest bit ignored for flat and treated as 12-bit
// unsigned for flat acceses.
bits<13> offset;
bits<1> nv = 0; // XXX - What does this actually do?
// We don't use tfe right now, and it was removed in gfx9.
bits<1> tfe = 0;
// Only valid on GFX9+
let Inst{12-0} = offset;
let Inst{13} = lds;
let Inst{15-14} = seg;
let Inst{16} = !if(ps.has_glc, glc, ps.glcValue);
let Inst{17} = slc;
let Inst{24-18} = op;
let Inst{31-26} = 0x37; // Encoding.
let Inst{39-32} = vaddr;
let Inst{47-40} = !if(ps.has_data, vdata, ?);
// 54-48 is reserved.
let Inst{55} = nv; // nv on GFX9+, TFE before.
let Inst{63-56} = !if(ps.has_vdst, vdst, ?);
}
class FLAT_Load_Pseudo <string opName, RegisterClass regClass,
bit HasSignedOffset = 0> : FLAT_Pseudo<
opName,
(outs regClass:$vdst),
!if(HasSignedOffset,
(ins VReg_64:$vaddr, offset_s13:$offset, GLC:$glc, slc:$slc),
(ins VReg_64:$vaddr, offset_u12:$offset, GLC:$glc, slc:$slc)),
" $vdst, $vaddr$offset$glc$slc"> {
let has_data = 0;
let mayLoad = 1;
}
class FLAT_Global_Load_Pseudo<string opName, RegisterClass regClass> :
FLAT_Load_Pseudo<opName, regClass, 1> {
let is_flat_global = 1;
}
class FLAT_Scratch_Load_Pseudo<string opName, RegisterClass regClass> :
FLAT_Load_Pseudo<opName, regClass, 1> {
let is_flat_scratch = 1;
}
class FLAT_Store_Pseudo <string opName, RegisterClass vdataClass,
bit HasSignedOffset = 0> : FLAT_Pseudo<
opName,
(outs),
!if(HasSignedOffset,
(ins VReg_64:$vaddr, vdataClass:$vdata, offset_s13:$offset, GLC:$glc, slc:$slc),
(ins VReg_64:$vaddr, vdataClass:$vdata, offset_u12:$offset, GLC:$glc, slc:$slc)),
" $vaddr, $vdata$offset$glc$slc"> {
let mayLoad = 0;
let mayStore = 1;
let has_vdst = 0;
}
class FLAT_Global_Store_Pseudo<string opName, RegisterClass regClass> :
FLAT_Store_Pseudo<opName, regClass, 1> {
let is_flat_global = 1;
}
class FLAT_Scratch_Store_Pseudo<string opName, RegisterClass regClass> :
FLAT_Store_Pseudo<opName, regClass, 1> {
let is_flat_scratch = 1;
}
multiclass FLAT_Atomic_Pseudo<
string opName,
RegisterClass vdst_rc,
ValueType vt,
SDPatternOperator atomic = null_frag,
ValueType data_vt = vt,
RegisterClass data_rc = vdst_rc,
bit HasSignedOffset = 0> {
def "" : FLAT_Pseudo <opName,
(outs),
!if(HasSignedOffset,
(ins VReg_64:$vaddr, data_rc:$vdata, offset_s13:$offset, slc:$slc),
(ins VReg_64:$vaddr, data_rc:$vdata, offset_u12:$offset, slc:$slc)),
" $vaddr, $vdata$offset$slc",
[]>,
AtomicNoRet <NAME, 0> {
let mayLoad = 1;
let mayStore = 1;
let has_glc = 0;
let glcValue = 0;
let has_vdst = 0;
let PseudoInstr = NAME;
}
def _RTN : FLAT_Pseudo <opName,
(outs vdst_rc:$vdst),
!if(HasSignedOffset,
(ins VReg_64:$vaddr, data_rc:$vdata, offset_s13:$offset, slc:$slc),
(ins VReg_64:$vaddr, data_rc:$vdata, offset_u12:$offset, slc:$slc)),
" $vdst, $vaddr, $vdata$offset glc$slc",
[(set vt:$vdst,
(atomic (FLATAtomic i64:$vaddr, i16:$offset, i1:$slc), data_vt:$vdata))]>,
AtomicNoRet <NAME, 1> {
let mayLoad = 1;
let mayStore = 1;
let hasPostISelHook = 1;
let has_glc = 0;
let glcValue = 1;
let PseudoInstr = NAME # "_RTN";
}
}
class flat_binary_atomic_op<SDNode atomic_op> : PatFrag<
(ops node:$ptr, node:$value),
(atomic_op node:$ptr, node:$value),
[{return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUASI.FLAT_ADDRESS;}]
>;
def atomic_cmp_swap_flat : flat_binary_atomic_op<AMDGPUatomic_cmp_swap>;
def atomic_swap_flat : flat_binary_atomic_op<atomic_swap>;
def atomic_add_flat : flat_binary_atomic_op<atomic_load_add>;
def atomic_and_flat : flat_binary_atomic_op<atomic_load_and>;
def atomic_max_flat : flat_binary_atomic_op<atomic_load_max>;
def atomic_min_flat : flat_binary_atomic_op<atomic_load_min>;
def atomic_or_flat : flat_binary_atomic_op<atomic_load_or>;
def atomic_sub_flat : flat_binary_atomic_op<atomic_load_sub>;
def atomic_umax_flat : flat_binary_atomic_op<atomic_load_umax>;
def atomic_umin_flat : flat_binary_atomic_op<atomic_load_umin>;
def atomic_xor_flat : flat_binary_atomic_op<atomic_load_xor>;
def atomic_inc_flat : flat_binary_atomic_op<SIatomic_inc>;
def atomic_dec_flat : flat_binary_atomic_op<SIatomic_dec>;
//===----------------------------------------------------------------------===//
// Flat Instructions
//===----------------------------------------------------------------------===//
def FLAT_LOAD_UBYTE : FLAT_Load_Pseudo <"flat_load_ubyte", VGPR_32>;
def FLAT_LOAD_SBYTE : FLAT_Load_Pseudo <"flat_load_sbyte", VGPR_32>;
def FLAT_LOAD_USHORT : FLAT_Load_Pseudo <"flat_load_ushort", VGPR_32>;
def FLAT_LOAD_SSHORT : FLAT_Load_Pseudo <"flat_load_sshort", VGPR_32>;
def FLAT_LOAD_DWORD : FLAT_Load_Pseudo <"flat_load_dword", VGPR_32>;
def FLAT_LOAD_DWORDX2 : FLAT_Load_Pseudo <"flat_load_dwordx2", VReg_64>;
def FLAT_LOAD_DWORDX4 : FLAT_Load_Pseudo <"flat_load_dwordx4", VReg_128>;
def FLAT_LOAD_DWORDX3 : FLAT_Load_Pseudo <"flat_load_dwordx3", VReg_96>;
def FLAT_STORE_BYTE : FLAT_Store_Pseudo <"flat_store_byte", VGPR_32>;
def FLAT_STORE_SHORT : FLAT_Store_Pseudo <"flat_store_short", VGPR_32>;
def FLAT_STORE_DWORD : FLAT_Store_Pseudo <"flat_store_dword", VGPR_32>;
def FLAT_STORE_DWORDX2 : FLAT_Store_Pseudo <"flat_store_dwordx2", VReg_64>;
def FLAT_STORE_DWORDX4 : FLAT_Store_Pseudo <"flat_store_dwordx4", VReg_128>;
def FLAT_STORE_DWORDX3 : FLAT_Store_Pseudo <"flat_store_dwordx3", VReg_96>;
defm FLAT_ATOMIC_CMPSWAP : FLAT_Atomic_Pseudo <"flat_atomic_cmpswap",
VGPR_32, i32, atomic_cmp_swap_flat,
v2i32, VReg_64>;
defm FLAT_ATOMIC_CMPSWAP_X2 : FLAT_Atomic_Pseudo <"flat_atomic_cmpswap_x2",
VReg_64, i64, atomic_cmp_swap_flat,
v2i64, VReg_128>;
defm FLAT_ATOMIC_SWAP : FLAT_Atomic_Pseudo <"flat_atomic_swap",
VGPR_32, i32, atomic_swap_flat>;
defm FLAT_ATOMIC_SWAP_X2 : FLAT_Atomic_Pseudo <"flat_atomic_swap_x2",
VReg_64, i64, atomic_swap_flat>;
defm FLAT_ATOMIC_ADD : FLAT_Atomic_Pseudo <"flat_atomic_add",
VGPR_32, i32, atomic_add_flat>;
defm FLAT_ATOMIC_SUB : FLAT_Atomic_Pseudo <"flat_atomic_sub",
VGPR_32, i32, atomic_sub_flat>;
defm FLAT_ATOMIC_SMIN : FLAT_Atomic_Pseudo <"flat_atomic_smin",
VGPR_32, i32, atomic_min_flat>;
defm FLAT_ATOMIC_UMIN : FLAT_Atomic_Pseudo <"flat_atomic_umin",
VGPR_32, i32, atomic_umin_flat>;
defm FLAT_ATOMIC_SMAX : FLAT_Atomic_Pseudo <"flat_atomic_smax",
VGPR_32, i32, atomic_max_flat>;
defm FLAT_ATOMIC_UMAX : FLAT_Atomic_Pseudo <"flat_atomic_umax",
VGPR_32, i32, atomic_umax_flat>;
defm FLAT_ATOMIC_AND : FLAT_Atomic_Pseudo <"flat_atomic_and",
VGPR_32, i32, atomic_and_flat>;
defm FLAT_ATOMIC_OR : FLAT_Atomic_Pseudo <"flat_atomic_or",
VGPR_32, i32, atomic_or_flat>;
defm FLAT_ATOMIC_XOR : FLAT_Atomic_Pseudo <"flat_atomic_xor",
VGPR_32, i32, atomic_xor_flat>;
defm FLAT_ATOMIC_INC : FLAT_Atomic_Pseudo <"flat_atomic_inc",
VGPR_32, i32, atomic_inc_flat>;
defm FLAT_ATOMIC_DEC : FLAT_Atomic_Pseudo <"flat_atomic_dec",
VGPR_32, i32, atomic_dec_flat>;
defm FLAT_ATOMIC_ADD_X2 : FLAT_Atomic_Pseudo <"flat_atomic_add_x2",
VReg_64, i64, atomic_add_flat>;
defm FLAT_ATOMIC_SUB_X2 : FLAT_Atomic_Pseudo <"flat_atomic_sub_x2",
VReg_64, i64, atomic_sub_flat>;
defm FLAT_ATOMIC_SMIN_X2 : FLAT_Atomic_Pseudo <"flat_atomic_smin_x2",
VReg_64, i64, atomic_min_flat>;
defm FLAT_ATOMIC_UMIN_X2 : FLAT_Atomic_Pseudo <"flat_atomic_umin_x2",
VReg_64, i64, atomic_umin_flat>;
defm FLAT_ATOMIC_SMAX_X2 : FLAT_Atomic_Pseudo <"flat_atomic_smax_x2",
VReg_64, i64, atomic_max_flat>;
defm FLAT_ATOMIC_UMAX_X2 : FLAT_Atomic_Pseudo <"flat_atomic_umax_x2",
VReg_64, i64, atomic_umax_flat>;
defm FLAT_ATOMIC_AND_X2 : FLAT_Atomic_Pseudo <"flat_atomic_and_x2",
VReg_64, i64, atomic_and_flat>;
defm FLAT_ATOMIC_OR_X2 : FLAT_Atomic_Pseudo <"flat_atomic_or_x2",
VReg_64, i64, atomic_or_flat>;
defm FLAT_ATOMIC_XOR_X2 : FLAT_Atomic_Pseudo <"flat_atomic_xor_x2",
VReg_64, i64, atomic_xor_flat>;
defm FLAT_ATOMIC_INC_X2 : FLAT_Atomic_Pseudo <"flat_atomic_inc_x2",
VReg_64, i64, atomic_inc_flat>;
defm FLAT_ATOMIC_DEC_X2 : FLAT_Atomic_Pseudo <"flat_atomic_dec_x2",
VReg_64, i64, atomic_dec_flat>;
let SubtargetPredicate = isCI in { // CI Only flat instructions : FIXME Only?
defm FLAT_ATOMIC_FCMPSWAP : FLAT_Atomic_Pseudo <"flat_atomic_fcmpswap",
VGPR_32, f32, null_frag, v2f32, VReg_64>;
defm FLAT_ATOMIC_FCMPSWAP_X2 : FLAT_Atomic_Pseudo <"flat_atomic_fcmpswap_x2",
VReg_64, f64, null_frag, v2f64, VReg_128>;
defm FLAT_ATOMIC_FMIN : FLAT_Atomic_Pseudo <"flat_atomic_fmin",
VGPR_32, f32>;
defm FLAT_ATOMIC_FMAX : FLAT_Atomic_Pseudo <"flat_atomic_fmax",
VGPR_32, f32>;
defm FLAT_ATOMIC_FMIN_X2 : FLAT_Atomic_Pseudo <"flat_atomic_fmin_x2",
VReg_64, f64>;
defm FLAT_ATOMIC_FMAX_X2 : FLAT_Atomic_Pseudo <"flat_atomic_fmax_x2",
VReg_64, f64>;
} // End SubtargetPredicate = isCI
let SubtargetPredicate = HasFlatGlobalInsts in {
def GLOBAL_LOAD_UBYTE : FLAT_Global_Load_Pseudo <"global_load_ubyte", VGPR_32>;
def GLOBAL_LOAD_SBYTE : FLAT_Global_Load_Pseudo <"global_load_sbyte", VGPR_32>;
def GLOBAL_LOAD_USHORT : FLAT_Global_Load_Pseudo <"global_load_ushort", VGPR_32>;
def GLOBAL_LOAD_SSHORT : FLAT_Global_Load_Pseudo <"global_load_sshort", VGPR_32>;
def GLOBAL_LOAD_DWORD : FLAT_Global_Load_Pseudo <"global_load_dword", VGPR_32>;
def GLOBAL_LOAD_DWORDX2 : FLAT_Global_Load_Pseudo <"global_load_dwordx2", VReg_64>;
def GLOBAL_LOAD_DWORDX3 : FLAT_Global_Load_Pseudo <"global_load_dwordx3", VReg_96>;
def GLOBAL_LOAD_DWORDX4 : FLAT_Global_Load_Pseudo <"global_load_dwordx4", VReg_128>;
def GLOBAL_STORE_BYTE : FLAT_Global_Store_Pseudo <"global_store_byte", VGPR_32>;
def GLOBAL_STORE_SHORT : FLAT_Global_Store_Pseudo <"global_store_short", VGPR_32>;
def GLOBAL_STORE_DWORD : FLAT_Global_Store_Pseudo <"global_store_dword", VGPR_32>;
def GLOBAL_STORE_DWORDX2 : FLAT_Global_Store_Pseudo <"global_store_dwordx2", VReg_64>;
def GLOBAL_STORE_DWORDX3 : FLAT_Global_Store_Pseudo <"global_store_dwordx3", VReg_96>;
def GLOBAL_STORE_DWORDX4 : FLAT_Global_Store_Pseudo <"global_store_dwordx4", VReg_128>;
} // End SubtargetPredicate = HasFlatGlobalInsts
//===----------------------------------------------------------------------===//
// Flat Patterns
//===----------------------------------------------------------------------===//
class flat_ld <SDPatternOperator ld> : PatFrag<(ops node:$ptr),
(ld node:$ptr), [{
auto const AS = cast<MemSDNode>(N)->getAddressSpace();
return AS == AMDGPUASI.FLAT_ADDRESS ||
AS == AMDGPUASI.GLOBAL_ADDRESS ||
AS == AMDGPUASI.CONSTANT_ADDRESS;
}]>;
class flat_st <SDPatternOperator st> : PatFrag<(ops node:$val, node:$ptr),
(st node:$val, node:$ptr), [{
auto const AS = cast<MemSDNode>(N)->getAddressSpace();
return AS == AMDGPUASI.FLAT_ADDRESS ||
AS == AMDGPUASI.GLOBAL_ADDRESS;
}]>;
def atomic_flat_load : flat_ld <atomic_load>;
def flat_load : flat_ld <load>;
def flat_az_extloadi8 : flat_ld <az_extloadi8>;
def flat_sextloadi8 : flat_ld <sextloadi8>;
def flat_az_extloadi16 : flat_ld <az_extloadi16>;
def flat_sextloadi16 : flat_ld <sextloadi16>;
def atomic_flat_store : flat_st <atomic_store>;
def flat_store : flat_st <store>;
def flat_truncstorei8 : flat_st <truncstorei8>;
def flat_truncstorei16 : flat_st <truncstorei16>;
// Patterns for global loads with no offset.
class FlatLoadPat <FLAT_Pseudo inst, SDPatternOperator node, ValueType vt> : Pat <
(vt (node (FLATAtomic i64:$vaddr, i16:$offset, i1:$slc))),
(inst $vaddr, $offset, 0, $slc)
>;
class FlatLoadAtomicPat <FLAT_Pseudo inst, SDPatternOperator node, ValueType vt> : Pat <
(vt (node (FLATAtomic i64:$vaddr, i16:$offset, i1:$slc))),
(inst $vaddr, $offset, 1, $slc)
>;
class FlatStorePat <FLAT_Pseudo inst, SDPatternOperator node, ValueType vt> : Pat <
(node vt:$data, (FLATAtomic i64:$vaddr, i16:$offset, i1:$slc)),
(inst $vaddr, $data, $offset, 0, $slc)
>;
class FlatStoreAtomicPat <FLAT_Pseudo inst, SDPatternOperator node, ValueType vt> : Pat <
// atomic store follows atomic binop convention so the address comes
// first.
(node (FLATAtomic i64:$vaddr, i16:$offset, i1:$slc), vt:$data),
(inst $vaddr, $data, $offset, 1, $slc)
>;
class FlatAtomicPat <FLAT_Pseudo inst, SDPatternOperator node, ValueType vt,
ValueType data_vt = vt> : Pat <
(vt (node (FLATAtomic i64:$vaddr, i16:$offset, i1:$slc), data_vt:$data)),
(inst $vaddr, $data, $offset, $slc)
>;
let Predicates = [isCIVI] in {
def : FlatLoadPat <FLAT_LOAD_UBYTE, flat_az_extloadi8, i32>;
def : FlatLoadPat <FLAT_LOAD_SBYTE, flat_sextloadi8, i32>;
def : FlatLoadPat <FLAT_LOAD_UBYTE, flat_az_extloadi8, i16>;
def : FlatLoadPat <FLAT_LOAD_SBYTE, flat_sextloadi8, i16>;
def : FlatLoadPat <FLAT_LOAD_USHORT, flat_az_extloadi16, i32>;
def : FlatLoadPat <FLAT_LOAD_SSHORT, flat_sextloadi16, i32>;
def : FlatLoadPat <FLAT_LOAD_DWORD, flat_load, i32>;
def : FlatLoadPat <FLAT_LOAD_DWORDX2, flat_load, v2i32>;
def : FlatLoadPat <FLAT_LOAD_DWORDX4, flat_load, v4i32>;
def : FlatLoadAtomicPat <FLAT_LOAD_DWORD, atomic_flat_load, i32>;
def : FlatLoadAtomicPat <FLAT_LOAD_DWORDX2, atomic_flat_load, i64>;
def : FlatStorePat <FLAT_STORE_BYTE, flat_truncstorei8, i32>;
def : FlatStorePat <FLAT_STORE_SHORT, flat_truncstorei16, i32>;
def : FlatStorePat <FLAT_STORE_DWORD, flat_store, i32>;
def : FlatStorePat <FLAT_STORE_DWORDX2, flat_store, v2i32>;
def : FlatStorePat <FLAT_STORE_DWORDX4, flat_store, v4i32>;
def : FlatStoreAtomicPat <FLAT_STORE_DWORD, atomic_flat_store, i32>;
def : FlatStoreAtomicPat <FLAT_STORE_DWORDX2, atomic_flat_store, i64>;
def : FlatAtomicPat <FLAT_ATOMIC_ADD_RTN, atomic_add_global, i32>;
def : FlatAtomicPat <FLAT_ATOMIC_SUB_RTN, atomic_sub_global, i32>;
def : FlatAtomicPat <FLAT_ATOMIC_INC_RTN, atomic_inc_global, i32>;
def : FlatAtomicPat <FLAT_ATOMIC_DEC_RTN, atomic_dec_global, i32>;
def : FlatAtomicPat <FLAT_ATOMIC_AND_RTN, atomic_and_global, i32>;
def : FlatAtomicPat <FLAT_ATOMIC_SMAX_RTN, atomic_max_global, i32>;
def : FlatAtomicPat <FLAT_ATOMIC_UMAX_RTN, atomic_umax_global, i32>;
def : FlatAtomicPat <FLAT_ATOMIC_SMIN_RTN, atomic_min_global, i32>;
def : FlatAtomicPat <FLAT_ATOMIC_UMIN_RTN, atomic_umin_global, i32>;
def : FlatAtomicPat <FLAT_ATOMIC_OR_RTN, atomic_or_global, i32>;
def : FlatAtomicPat <FLAT_ATOMIC_SWAP_RTN, atomic_swap_global, i32>;
def : FlatAtomicPat <FLAT_ATOMIC_CMPSWAP_RTN, AMDGPUatomic_cmp_swap_global, i32, v2i32>;
def : FlatAtomicPat <FLAT_ATOMIC_XOR_RTN, atomic_xor_global, i32>;
def : FlatAtomicPat <FLAT_ATOMIC_ADD_X2_RTN, atomic_add_global, i64>;
def : FlatAtomicPat <FLAT_ATOMIC_SUB_X2_RTN, atomic_sub_global, i64>;
def : FlatAtomicPat <FLAT_ATOMIC_INC_X2_RTN, atomic_inc_global, i64>;
def : FlatAtomicPat <FLAT_ATOMIC_DEC_X2_RTN, atomic_dec_global, i64>;
def : FlatAtomicPat <FLAT_ATOMIC_AND_X2_RTN, atomic_and_global, i64>;
def : FlatAtomicPat <FLAT_ATOMIC_SMAX_X2_RTN, atomic_max_global, i64>;
def : FlatAtomicPat <FLAT_ATOMIC_UMAX_X2_RTN, atomic_umax_global, i64>;
def : FlatAtomicPat <FLAT_ATOMIC_SMIN_X2_RTN, atomic_min_global, i64>;
def : FlatAtomicPat <FLAT_ATOMIC_UMIN_X2_RTN, atomic_umin_global, i64>;
def : FlatAtomicPat <FLAT_ATOMIC_OR_X2_RTN, atomic_or_global, i64>;
def : FlatAtomicPat <FLAT_ATOMIC_SWAP_X2_RTN, atomic_swap_global, i64>;
def : FlatAtomicPat <FLAT_ATOMIC_CMPSWAP_X2_RTN, AMDGPUatomic_cmp_swap_global, i64, v2i64>;
def : FlatAtomicPat <FLAT_ATOMIC_XOR_X2_RTN, atomic_xor_global, i64>;
} // End Predicates = [isCIVI]
let Predicates = [isVI] in {
def : FlatStorePat <FLAT_STORE_BYTE, flat_truncstorei8, i16>;
def : FlatStorePat <FLAT_STORE_SHORT, flat_store, i16>;
}
//===----------------------------------------------------------------------===//
// Target
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// CI
//===----------------------------------------------------------------------===//
class FLAT_Real_ci <bits<7> op, FLAT_Pseudo ps> :
FLAT_Real <op, ps>,
SIMCInstr <ps.PseudoInstr, SIEncodingFamily.SI> {
let AssemblerPredicate = isCIOnly;
let DecoderNamespace="CI";
}
def FLAT_LOAD_UBYTE_ci : FLAT_Real_ci <0x8, FLAT_LOAD_UBYTE>;
def FLAT_LOAD_SBYTE_ci : FLAT_Real_ci <0x9, FLAT_LOAD_SBYTE>;
def FLAT_LOAD_USHORT_ci : FLAT_Real_ci <0xa, FLAT_LOAD_USHORT>;
def FLAT_LOAD_SSHORT_ci : FLAT_Real_ci <0xb, FLAT_LOAD_SSHORT>;
def FLAT_LOAD_DWORD_ci : FLAT_Real_ci <0xc, FLAT_LOAD_DWORD>;
def FLAT_LOAD_DWORDX2_ci : FLAT_Real_ci <0xd, FLAT_LOAD_DWORDX2>;
def FLAT_LOAD_DWORDX4_ci : FLAT_Real_ci <0xe, FLAT_LOAD_DWORDX4>;
def FLAT_LOAD_DWORDX3_ci : FLAT_Real_ci <0xf, FLAT_LOAD_DWORDX3>;
def FLAT_STORE_BYTE_ci : FLAT_Real_ci <0x18, FLAT_STORE_BYTE>;
def FLAT_STORE_SHORT_ci : FLAT_Real_ci <0x1a, FLAT_STORE_SHORT>;
def FLAT_STORE_DWORD_ci : FLAT_Real_ci <0x1c, FLAT_STORE_DWORD>;
def FLAT_STORE_DWORDX2_ci : FLAT_Real_ci <0x1d, FLAT_STORE_DWORDX2>;
def FLAT_STORE_DWORDX4_ci : FLAT_Real_ci <0x1e, FLAT_STORE_DWORDX4>;
def FLAT_STORE_DWORDX3_ci : FLAT_Real_ci <0x1f, FLAT_STORE_DWORDX3>;
multiclass FLAT_Real_Atomics_ci <bits<7> op, FLAT_Pseudo ps> {
def _ci : FLAT_Real_ci<op, !cast<FLAT_Pseudo>(ps.PseudoInstr)>;
def _RTN_ci : FLAT_Real_ci<op, !cast<FLAT_Pseudo>(ps.PseudoInstr # "_RTN")>;
}
defm FLAT_ATOMIC_SWAP : FLAT_Real_Atomics_ci <0x30, FLAT_ATOMIC_SWAP>;
defm FLAT_ATOMIC_CMPSWAP : FLAT_Real_Atomics_ci <0x31, FLAT_ATOMIC_CMPSWAP>;
defm FLAT_ATOMIC_ADD : FLAT_Real_Atomics_ci <0x32, FLAT_ATOMIC_ADD>;
defm FLAT_ATOMIC_SUB : FLAT_Real_Atomics_ci <0x33, FLAT_ATOMIC_SUB>;
defm FLAT_ATOMIC_SMIN : FLAT_Real_Atomics_ci <0x35, FLAT_ATOMIC_SMIN>;
defm FLAT_ATOMIC_UMIN : FLAT_Real_Atomics_ci <0x36, FLAT_ATOMIC_UMIN>;
defm FLAT_ATOMIC_SMAX : FLAT_Real_Atomics_ci <0x37, FLAT_ATOMIC_SMAX>;
defm FLAT_ATOMIC_UMAX : FLAT_Real_Atomics_ci <0x38, FLAT_ATOMIC_UMAX>;
defm FLAT_ATOMIC_AND : FLAT_Real_Atomics_ci <0x39, FLAT_ATOMIC_AND>;
defm FLAT_ATOMIC_OR : FLAT_Real_Atomics_ci <0x3a, FLAT_ATOMIC_OR>;
defm FLAT_ATOMIC_XOR : FLAT_Real_Atomics_ci <0x3b, FLAT_ATOMIC_XOR>;
defm FLAT_ATOMIC_INC : FLAT_Real_Atomics_ci <0x3c, FLAT_ATOMIC_INC>;
defm FLAT_ATOMIC_DEC : FLAT_Real_Atomics_ci <0x3d, FLAT_ATOMIC_DEC>;
defm FLAT_ATOMIC_SWAP_X2 : FLAT_Real_Atomics_ci <0x50, FLAT_ATOMIC_SWAP_X2>;
defm FLAT_ATOMIC_CMPSWAP_X2 : FLAT_Real_Atomics_ci <0x51, FLAT_ATOMIC_CMPSWAP_X2>;
defm FLAT_ATOMIC_ADD_X2 : FLAT_Real_Atomics_ci <0x52, FLAT_ATOMIC_ADD_X2>;
defm FLAT_ATOMIC_SUB_X2 : FLAT_Real_Atomics_ci <0x53, FLAT_ATOMIC_SUB_X2>;
defm FLAT_ATOMIC_SMIN_X2 : FLAT_Real_Atomics_ci <0x55, FLAT_ATOMIC_SMIN_X2>;
defm FLAT_ATOMIC_UMIN_X2 : FLAT_Real_Atomics_ci <0x56, FLAT_ATOMIC_UMIN_X2>;
defm FLAT_ATOMIC_SMAX_X2 : FLAT_Real_Atomics_ci <0x57, FLAT_ATOMIC_SMAX_X2>;
defm FLAT_ATOMIC_UMAX_X2 : FLAT_Real_Atomics_ci <0x58, FLAT_ATOMIC_UMAX_X2>;
defm FLAT_ATOMIC_AND_X2 : FLAT_Real_Atomics_ci <0x59, FLAT_ATOMIC_AND_X2>;
defm FLAT_ATOMIC_OR_X2 : FLAT_Real_Atomics_ci <0x5a, FLAT_ATOMIC_OR_X2>;
defm FLAT_ATOMIC_XOR_X2 : FLAT_Real_Atomics_ci <0x5b, FLAT_ATOMIC_XOR_X2>;
defm FLAT_ATOMIC_INC_X2 : FLAT_Real_Atomics_ci <0x5c, FLAT_ATOMIC_INC_X2>;
defm FLAT_ATOMIC_DEC_X2 : FLAT_Real_Atomics_ci <0x5d, FLAT_ATOMIC_DEC_X2>;
// CI Only flat instructions
defm FLAT_ATOMIC_FCMPSWAP : FLAT_Real_Atomics_ci <0x3e, FLAT_ATOMIC_FCMPSWAP>;
defm FLAT_ATOMIC_FMIN : FLAT_Real_Atomics_ci <0x3f, FLAT_ATOMIC_FMIN>;
defm FLAT_ATOMIC_FMAX : FLAT_Real_Atomics_ci <0x40, FLAT_ATOMIC_FMAX>;
defm FLAT_ATOMIC_FCMPSWAP_X2 : FLAT_Real_Atomics_ci <0x5e, FLAT_ATOMIC_FCMPSWAP_X2>;
defm FLAT_ATOMIC_FMIN_X2 : FLAT_Real_Atomics_ci <0x5f, FLAT_ATOMIC_FMIN_X2>;
defm FLAT_ATOMIC_FMAX_X2 : FLAT_Real_Atomics_ci <0x60, FLAT_ATOMIC_FMAX_X2>;
//===----------------------------------------------------------------------===//
// VI
//===----------------------------------------------------------------------===//
class FLAT_Real_vi <bits<7> op, FLAT_Pseudo ps> :
FLAT_Real <op, ps>,
SIMCInstr <ps.PseudoInstr, SIEncodingFamily.VI> {
let AssemblerPredicate = isVI;
let DecoderNamespace="VI";
}
def FLAT_LOAD_UBYTE_vi : FLAT_Real_vi <0x10, FLAT_LOAD_UBYTE>;
def FLAT_LOAD_SBYTE_vi : FLAT_Real_vi <0x11, FLAT_LOAD_SBYTE>;
def FLAT_LOAD_USHORT_vi : FLAT_Real_vi <0x12, FLAT_LOAD_USHORT>;
def FLAT_LOAD_SSHORT_vi : FLAT_Real_vi <0x13, FLAT_LOAD_SSHORT>;
def FLAT_LOAD_DWORD_vi : FLAT_Real_vi <0x14, FLAT_LOAD_DWORD>;
def FLAT_LOAD_DWORDX2_vi : FLAT_Real_vi <0x15, FLAT_LOAD_DWORDX2>;
def FLAT_LOAD_DWORDX4_vi : FLAT_Real_vi <0x17, FLAT_LOAD_DWORDX4>;
def FLAT_LOAD_DWORDX3_vi : FLAT_Real_vi <0x16, FLAT_LOAD_DWORDX3>;
def FLAT_STORE_BYTE_vi : FLAT_Real_vi <0x18, FLAT_STORE_BYTE>;
def FLAT_STORE_SHORT_vi : FLAT_Real_vi <0x1a, FLAT_STORE_SHORT>;
def FLAT_STORE_DWORD_vi : FLAT_Real_vi <0x1c, FLAT_STORE_DWORD>;
def FLAT_STORE_DWORDX2_vi : FLAT_Real_vi <0x1d, FLAT_STORE_DWORDX2>;
def FLAT_STORE_DWORDX4_vi : FLAT_Real_vi <0x1f, FLAT_STORE_DWORDX4>;
def FLAT_STORE_DWORDX3_vi : FLAT_Real_vi <0x1e, FLAT_STORE_DWORDX3>;
multiclass FLAT_Real_Atomics_vi <bits<7> op, FLAT_Pseudo ps> {
def _vi : FLAT_Real_vi<op, !cast<FLAT_Pseudo>(ps.PseudoInstr)>;
def _RTN_vi : FLAT_Real_vi<op, !cast<FLAT_Pseudo>(ps.PseudoInstr # "_RTN")>;
}
defm FLAT_ATOMIC_SWAP : FLAT_Real_Atomics_vi <0x40, FLAT_ATOMIC_SWAP>;
defm FLAT_ATOMIC_CMPSWAP : FLAT_Real_Atomics_vi <0x41, FLAT_ATOMIC_CMPSWAP>;
defm FLAT_ATOMIC_ADD : FLAT_Real_Atomics_vi <0x42, FLAT_ATOMIC_ADD>;
defm FLAT_ATOMIC_SUB : FLAT_Real_Atomics_vi <0x43, FLAT_ATOMIC_SUB>;
defm FLAT_ATOMIC_SMIN : FLAT_Real_Atomics_vi <0x44, FLAT_ATOMIC_SMIN>;
defm FLAT_ATOMIC_UMIN : FLAT_Real_Atomics_vi <0x45, FLAT_ATOMIC_UMIN>;
defm FLAT_ATOMIC_SMAX : FLAT_Real_Atomics_vi <0x46, FLAT_ATOMIC_SMAX>;
defm FLAT_ATOMIC_UMAX : FLAT_Real_Atomics_vi <0x47, FLAT_ATOMIC_UMAX>;
defm FLAT_ATOMIC_AND : FLAT_Real_Atomics_vi <0x48, FLAT_ATOMIC_AND>;
defm FLAT_ATOMIC_OR : FLAT_Real_Atomics_vi <0x49, FLAT_ATOMIC_OR>;
defm FLAT_ATOMIC_XOR : FLAT_Real_Atomics_vi <0x4a, FLAT_ATOMIC_XOR>;
defm FLAT_ATOMIC_INC : FLAT_Real_Atomics_vi <0x4b, FLAT_ATOMIC_INC>;
defm FLAT_ATOMIC_DEC : FLAT_Real_Atomics_vi <0x4c, FLAT_ATOMIC_DEC>;
defm FLAT_ATOMIC_SWAP_X2 : FLAT_Real_Atomics_vi <0x60, FLAT_ATOMIC_SWAP_X2>;
defm FLAT_ATOMIC_CMPSWAP_X2 : FLAT_Real_Atomics_vi <0x61, FLAT_ATOMIC_CMPSWAP_X2>;
defm FLAT_ATOMIC_ADD_X2 : FLAT_Real_Atomics_vi <0x62, FLAT_ATOMIC_ADD_X2>;
defm FLAT_ATOMIC_SUB_X2 : FLAT_Real_Atomics_vi <0x63, FLAT_ATOMIC_SUB_X2>;
defm FLAT_ATOMIC_SMIN_X2 : FLAT_Real_Atomics_vi <0x64, FLAT_ATOMIC_SMIN_X2>;
defm FLAT_ATOMIC_UMIN_X2 : FLAT_Real_Atomics_vi <0x65, FLAT_ATOMIC_UMIN_X2>;
defm FLAT_ATOMIC_SMAX_X2 : FLAT_Real_Atomics_vi <0x66, FLAT_ATOMIC_SMAX_X2>;
defm FLAT_ATOMIC_UMAX_X2 : FLAT_Real_Atomics_vi <0x67, FLAT_ATOMIC_UMAX_X2>;
defm FLAT_ATOMIC_AND_X2 : FLAT_Real_Atomics_vi <0x68, FLAT_ATOMIC_AND_X2>;
defm FLAT_ATOMIC_OR_X2 : FLAT_Real_Atomics_vi <0x69, FLAT_ATOMIC_OR_X2>;
defm FLAT_ATOMIC_XOR_X2 : FLAT_Real_Atomics_vi <0x6a, FLAT_ATOMIC_XOR_X2>;
defm FLAT_ATOMIC_INC_X2 : FLAT_Real_Atomics_vi <0x6b, FLAT_ATOMIC_INC_X2>;
defm FLAT_ATOMIC_DEC_X2 : FLAT_Real_Atomics_vi <0x6c, FLAT_ATOMIC_DEC_X2>;
def GLOBAL_LOAD_UBYTE_vi : FLAT_Real_vi <0x10, GLOBAL_LOAD_UBYTE>;
def GLOBAL_LOAD_SBYTE_vi : FLAT_Real_vi <0x11, GLOBAL_LOAD_SBYTE>;
def GLOBAL_LOAD_USHORT_vi : FLAT_Real_vi <0x12, GLOBAL_LOAD_USHORT>;
def GLOBAL_LOAD_SSHORT_vi : FLAT_Real_vi <0x13, GLOBAL_LOAD_SSHORT>;
def GLOBAL_LOAD_DWORD_vi : FLAT_Real_vi <0x14, GLOBAL_LOAD_DWORD>;
def GLOBAL_LOAD_DWORDX2_vi : FLAT_Real_vi <0x15, GLOBAL_LOAD_DWORDX2>;
def GLOBAL_LOAD_DWORDX4_vi : FLAT_Real_vi <0x17, GLOBAL_LOAD_DWORDX4>;
def GLOBAL_LOAD_DWORDX3_vi : FLAT_Real_vi <0x16, GLOBAL_LOAD_DWORDX3>;
def GLOBAL_STORE_BYTE_vi : FLAT_Real_vi <0x18, GLOBAL_STORE_BYTE>;
def GLOBAL_STORE_SHORT_vi : FLAT_Real_vi <0x1a, GLOBAL_STORE_SHORT>;
def GLOBAL_STORE_DWORD_vi : FLAT_Real_vi <0x1c, GLOBAL_STORE_DWORD>;
def GLOBAL_STORE_DWORDX2_vi : FLAT_Real_vi <0x1d, GLOBAL_STORE_DWORDX2>;
def GLOBAL_STORE_DWORDX4_vi : FLAT_Real_vi <0x1f, GLOBAL_STORE_DWORDX4>;
def GLOBAL_STORE_DWORDX3_vi : FLAT_Real_vi <0x1e, GLOBAL_STORE_DWORDX3>;