llvm-project/llvm/lib/Target/AMDGPU/VOP2Instructions.td

947 lines
37 KiB
TableGen
Raw Normal View History

//===-- VOP2Instructions.td - Vector Instruction Defintions ---------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// VOP2 Classes
//===----------------------------------------------------------------------===//
class VOP2e <bits<6> op, VOPProfile P> : Enc32 {
bits<8> vdst;
bits<9> src0;
bits<8> src1;
let Inst{8-0} = !if(P.HasSrc0, src0, 0);
let Inst{16-9} = !if(P.HasSrc1, src1, 0);
let Inst{24-17} = !if(P.EmitDst, vdst, 0);
let Inst{30-25} = op;
let Inst{31} = 0x0; //encoding
}
class VOP2_MADKe <bits<6> op, VOPProfile P> : Enc64 {
bits<8> vdst;
bits<9> src0;
bits<8> src1;
bits<32> imm;
let Inst{8-0} = !if(P.HasSrc0, src0, 0);
let Inst{16-9} = !if(P.HasSrc1, src1, 0);
let Inst{24-17} = !if(P.EmitDst, vdst, 0);
let Inst{30-25} = op;
let Inst{31} = 0x0; // encoding
let Inst{63-32} = imm;
}
class VOP2_SDWAe <bits<6> op, VOPProfile P> : VOP_SDWAe <P> {
bits<8> vdst;
bits<8> src1;
let Inst{8-0} = 0xf9; // sdwa
let Inst{16-9} = !if(P.HasSrc1, src1{7-0}, 0);
let Inst{24-17} = !if(P.EmitDst, vdst{7-0}, 0);
let Inst{30-25} = op;
let Inst{31} = 0x0; // encoding
}
class VOP2_SDWA9Ae <bits<6> op, VOPProfile P> : VOP_SDWA9Ae <P> {
bits<8> vdst;
bits<9> src1;
let Inst{8-0} = 0xf9; // sdwa
let Inst{16-9} = !if(P.HasSrc1, src1{7-0}, 0);
let Inst{24-17} = !if(P.EmitDst, vdst{7-0}, 0);
let Inst{30-25} = op;
let Inst{31} = 0x0; // encoding
let Inst{63} = !if(P.HasSrc1, src1{8}, 0); // src1_sgpr
}
class VOP2_Pseudo <string opName, VOPProfile P, list<dag> pattern=[], string suffix = "_e32"> :
VOP_Pseudo <opName, suffix, P, P.Outs32, P.Ins32, "", pattern> {
let AsmOperands = P.Asm32;
let Size = 4;
let mayLoad = 0;
let mayStore = 0;
let hasSideEffects = 0;
let SubtargetPredicate = isGCN;
let VOP2 = 1;
let VALU = 1;
let Uses = [EXEC];
let AsmVariantName = AMDGPUAsmVariants.Default;
}
class VOP2_Real <VOP2_Pseudo ps, int EncodingFamily> :
InstSI <ps.OutOperandList, ps.InOperandList, ps.Mnemonic # ps.AsmOperands, []>,
SIMCInstr <ps.PseudoInstr, EncodingFamily> {
let isPseudo = 0;
let isCodeGenOnly = 0;
let Constraints = ps.Constraints;
let DisableEncoding = ps.DisableEncoding;
// copy relevant pseudo op flags
let SubtargetPredicate = ps.SubtargetPredicate;
let AsmMatchConverter = ps.AsmMatchConverter;
let AsmVariantName = ps.AsmVariantName;
let Constraints = ps.Constraints;
let DisableEncoding = ps.DisableEncoding;
let TSFlags = ps.TSFlags;
let UseNamedOperandTable = ps.UseNamedOperandTable;
let Uses = ps.Uses;
let Defs = ps.Defs;
}
class VOP2_SDWA_Pseudo <string OpName, VOPProfile P, list<dag> pattern=[]> :
VOP_SDWA_Pseudo <OpName, P, pattern> {
let AsmMatchConverter = "cvtSdwaVOP2";
}
class getVOP2Pat64 <SDPatternOperator node, VOPProfile P> : LetDummies {
list<dag> ret = !if(P.HasModifiers,
[(set P.DstVT:$vdst,
(node (P.Src0VT
!if(P.HasOMod,
(VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers, i1:$clamp, i32:$omod),
(VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers, i1:$clamp))),
(P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers))))],
[(set P.DstVT:$vdst, (node P.Src0VT:$src0, P.Src1VT:$src1))]);
}
multiclass VOP2Inst <string opName,
VOPProfile P,
SDPatternOperator node = null_frag,
string revOp = opName,
bit GFX9Renamed = 0> {
let renamedInGFX9 = GFX9Renamed in {
def _e32 : VOP2_Pseudo <opName, P>,
Commutable_REV<revOp#"_e32", !eq(revOp, opName)>;
def _e64 : VOP3_Pseudo <opName, P, getVOP2Pat64<node, P>.ret>,
Commutable_REV<revOp#"_e64", !eq(revOp, opName)>;
def _sdwa : VOP2_SDWA_Pseudo <opName, P>;
}
}
multiclass VOP2bInst <string opName,
VOPProfile P,
SDPatternOperator node = null_frag,
string revOp = opName,
bit GFX9Renamed = 0,
bit useSGPRInput = !eq(P.NumSrcArgs, 3)> {
let renamedInGFX9 = GFX9Renamed in {
let SchedRW = [Write32Bit, WriteSALU] in {
let Uses = !if(useSGPRInput, [VCC, EXEC], [EXEC]), Defs = [VCC] in {
def _e32 : VOP2_Pseudo <opName, P>,
Commutable_REV<revOp#"_e32", !eq(revOp, opName)>;
def _sdwa : VOP2_SDWA_Pseudo <opName, P> {
let AsmMatchConverter = "cvtSdwaVOP2b";
}
}
def _e64 : VOP3_Pseudo <opName, P, getVOP2Pat64<node, P>.ret>,
Commutable_REV<revOp#"_e64", !eq(revOp, opName)>;
}
}
}
multiclass VOP2eInst <string opName,
VOPProfile P,
SDPatternOperator node = null_frag,
string revOp = opName,
bit useSGPRInput = !eq(P.NumSrcArgs, 3)> {
let SchedRW = [Write32Bit] in {
let Uses = !if(useSGPRInput, [VCC, EXEC], [EXEC]) in {
def _e32 : VOP2_Pseudo <opName, P>,
Commutable_REV<revOp#"_e32", !eq(revOp, opName)>;
def _sdwa : VOP2_SDWA_Pseudo <opName, P> {
let AsmMatchConverter = "cvtSdwaVOP2b";
}
}
def _e64 : VOP3_Pseudo <opName, P, getVOP2Pat64<node, P>.ret>,
Commutable_REV<revOp#"_e64", !eq(revOp, opName)>;
}
}
class VOP_MADAK <ValueType vt> : VOPProfile <[vt, vt, vt, vt]> {
field Operand ImmOpType = !if(!eq(vt.Size, 32), f32kimm, f16kimm);
field dag Ins32 = (ins VCSrc_f32:$src0, VGPR_32:$src1, ImmOpType:$imm);
field bit HasExt = 0;
// Hack to stop printing _e64
let DstRC = RegisterOperand<VGPR_32>;
field string Asm32 = " $vdst, $src0, $src1, $imm";
}
def VOP_MADAK_F16 : VOP_MADAK <f16>;
def VOP_MADAK_F32 : VOP_MADAK <f32>;
class VOP_MADMK <ValueType vt> : VOPProfile <[vt, vt, vt, vt]> {
field Operand ImmOpType = !if(!eq(vt.Size, 32), f32kimm, f16kimm);
field dag Ins32 = (ins VCSrc_f32:$src0, ImmOpType:$imm, VGPR_32:$src1);
field bit HasExt = 0;
// Hack to stop printing _e64
let DstRC = RegisterOperand<VGPR_32>;
field string Asm32 = " $vdst, $src0, $imm, $src1";
}
def VOP_MADMK_F16 : VOP_MADMK <f16>;
def VOP_MADMK_F32 : VOP_MADMK <f32>;
// FIXME: Remove src2_modifiers. It isn't used, so is wasting memory
// and processing time but it makes it easier to convert to mad.
class VOP_MAC <ValueType vt> : VOPProfile <[vt, vt, vt, vt]> {
let Ins32 = (ins Src0RC32:$src0, Src1RC32:$src1, VGPR_32:$src2);
let Ins64 = getIns64<Src0RC64, Src1RC64, RegisterOperand<VGPR_32>, 3,
0, HasModifiers, HasOMod, Src0Mod, Src1Mod, Src2Mod>.ret;
[AMDGPU] Add pseudo "old" source to all DPP instructions Summary: All instructions with the DPP modifier may not write to certain lanes of the output if bound_ctrl=1 is set or any bits in bank_mask or row_mask aren't set, so the destination register may be both defined and modified. The right way to handle this is to add a constraint that the destination register is the same as one of the inputs. We could tie the destination to the first source, but that would be too restrictive for some use-cases where we want the destination to be some other value before the instruction executes. Instead, add a fake "old" source and tie it to the destination. Effectively, the "old" source defines what value unwritten lanes will get. We'll expose this functionality to users with a new intrinsic later. Also, we want to use DPP instructions for computing derivatives, which means we need to set WQM for them. We also need to enable the entire wavefront when using DPP intrinsics to implement nonuniform subgroup reductions, since otherwise we'll get incorrect results in some cases. To accomodate this, add a new operand to all DPP instructions which will be interpreted by the SI WQM pass. This will be exposed with a new intrinsic later. We'll also add support for Whole Wavefront Mode later. I also fixed llvm.amdgcn.mov.dpp to overwrite the source and fixed up the test. However, I could also keep the old behavior (where lanes that aren't written are undefined) if people want it. Reviewers: tstellar, arsenm Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye Differential Revision: https://reviews.llvm.org/D34716 llvm-svn: 310283
2017-08-08 03:10:56 +08:00
let InsDPP = (ins DstRCDPP:$old,
Src0ModDPP:$src0_modifiers, Src0DPP:$src0,
Src1ModDPP:$src1_modifiers, Src1DPP:$src1,
dpp_ctrl:$dpp_ctrl, row_mask:$row_mask,
bank_mask:$bank_mask, bound_ctrl:$bound_ctrl);
let InsSDWA = (ins Src0ModSDWA:$src0_modifiers, Src0SDWA:$src0,
Src1ModSDWA:$src1_modifiers, Src1SDWA:$src1,
VGPR_32:$src2, // stub argument
clampmod:$clamp, omod:$omod,
dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel, src1_sel:$src1_sel);
let Asm32 = getAsm32<1, 2, vt>.ret;
let Asm64 = getAsm64<1, 2, 0, HasModifiers, HasOMod, vt>.ret;
let AsmDPP = getAsmDPP<1, 2, HasModifiers, vt>.ret;
let AsmSDWA = getAsmSDWA<1, 2, vt>.ret;
let AsmSDWA9 = getAsmSDWA9<1, 1, 2, vt>.ret;
let HasSrc2 = 0;
let HasSrc2Mods = 0;
let HasExt = 1;
let HasSDWA9 = 0;
}
def VOP_MAC_F16 : VOP_MAC <f16> {
// FIXME: Move 'Asm64' definition to VOP_MAC, and use 'vt'. Currently it gives
// 'not a string initializer' error.
let Asm64 = getAsm64<1, 2, 0, HasModifiers, HasOMod, f16>.ret;
}
def VOP_MAC_F32 : VOP_MAC <f32> {
// FIXME: Move 'Asm64' definition to VOP_MAC, and use 'vt'. Currently it gives
// 'not a string initializer' error.
let Asm64 = getAsm64<1, 2, 0, HasModifiers, HasOMod, f32>.ret;
}
// Write out to vcc or arbitrary SGPR.
def VOP2b_I32_I1_I32_I32 : VOPProfile<[i32, i32, i32, untyped]> {
let Asm32 = "$vdst, vcc, $src0, $src1";
let Asm64 = "$vdst, $sdst, $src0, $src1";
let AsmSDWA = "$vdst, vcc, $src0_modifiers, $src1_modifiers$clamp $dst_sel $dst_unused $src0_sel $src1_sel";
let AsmSDWA9 = "$vdst, vcc, $src0_modifiers, $src1_modifiers$clamp $dst_sel $dst_unused $src0_sel $src1_sel";
let AsmDPP = "$vdst, vcc, $src0, $src1 $dpp_ctrl$row_mask$bank_mask$bound_ctrl";
let Outs32 = (outs DstRC:$vdst);
let Outs64 = (outs DstRC:$vdst, SReg_64:$sdst);
}
// Write out to vcc or arbitrary SGPR and read in from vcc or
// arbitrary SGPR.
def VOP2b_I32_I1_I32_I32_I1 : VOPProfile<[i32, i32, i32, i1]> {
// We use VCSrc_b32 to exclude literal constants, even though the
// encoding normally allows them since the implicit VCC use means
// using one would always violate the constant bus
// restriction. SGPRs are still allowed because it should
// technically be possible to use VCC again as src0.
let Src0RC32 = VCSrc_b32;
let Asm32 = "$vdst, vcc, $src0, $src1, vcc";
let Asm64 = "$vdst, $sdst, $src0, $src1, $src2";
let AsmSDWA = "$vdst, vcc, $src0_modifiers, $src1_modifiers, vcc $clamp $dst_sel $dst_unused $src0_sel $src1_sel";
let AsmSDWA9 = "$vdst, vcc, $src0_modifiers, $src1_modifiers, vcc $clamp $dst_sel $dst_unused $src0_sel $src1_sel";
let AsmDPP = "$vdst, vcc, $src0, $src1, vcc $dpp_ctrl$row_mask$bank_mask$bound_ctrl";
let Outs32 = (outs DstRC:$vdst);
let Outs64 = (outs DstRC:$vdst, SReg_64:$sdst);
// Suppress src2 implied by type since the 32-bit encoding uses an
// implicit VCC use.
let Ins32 = (ins Src0RC32:$src0, Src1RC32:$src1);
let InsSDWA = (ins Src0ModSDWA:$src0_modifiers, Src0SDWA:$src0,
Src1ModSDWA:$src1_modifiers, Src1SDWA:$src1,
clampmod:$clamp,
dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel, src1_sel:$src1_sel);
[AMDGPU] Add pseudo "old" source to all DPP instructions Summary: All instructions with the DPP modifier may not write to certain lanes of the output if bound_ctrl=1 is set or any bits in bank_mask or row_mask aren't set, so the destination register may be both defined and modified. The right way to handle this is to add a constraint that the destination register is the same as one of the inputs. We could tie the destination to the first source, but that would be too restrictive for some use-cases where we want the destination to be some other value before the instruction executes. Instead, add a fake "old" source and tie it to the destination. Effectively, the "old" source defines what value unwritten lanes will get. We'll expose this functionality to users with a new intrinsic later. Also, we want to use DPP instructions for computing derivatives, which means we need to set WQM for them. We also need to enable the entire wavefront when using DPP intrinsics to implement nonuniform subgroup reductions, since otherwise we'll get incorrect results in some cases. To accomodate this, add a new operand to all DPP instructions which will be interpreted by the SI WQM pass. This will be exposed with a new intrinsic later. We'll also add support for Whole Wavefront Mode later. I also fixed llvm.amdgcn.mov.dpp to overwrite the source and fixed up the test. However, I could also keep the old behavior (where lanes that aren't written are undefined) if people want it. Reviewers: tstellar, arsenm Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye Differential Revision: https://reviews.llvm.org/D34716 llvm-svn: 310283
2017-08-08 03:10:56 +08:00
let InsDPP = (ins DstRCDPP:$old,
Src0DPP:$src0,
Src1DPP:$src1,
dpp_ctrl:$dpp_ctrl, row_mask:$row_mask,
bank_mask:$bank_mask, bound_ctrl:$bound_ctrl);
let HasExt = 1;
let HasSDWA9 = 1;
}
// Read in from vcc or arbitrary SGPR
def VOP2e_I32_I32_I32_I1 : VOPProfile<[i32, i32, i32, i1]> {
let Src0RC32 = VCSrc_b32; // See comment in def VOP2b_I32_I1_I32_I32_I1 above.
let Asm32 = "$vdst, $src0, $src1, vcc";
let Asm64 = "$vdst, $src0, $src1, $src2";
let AsmSDWA = "$vdst, $src0_modifiers, $src1_modifiers, vcc $clamp $dst_sel $dst_unused $src0_sel $src1_sel";
let AsmSDWA9 = "$vdst, $src0_modifiers, $src1_modifiers, vcc $clamp $dst_sel $dst_unused $src0_sel $src1_sel";
let AsmDPP = "$vdst, $src0, $src1, vcc $dpp_ctrl$row_mask$bank_mask$bound_ctrl";
let Outs32 = (outs DstRC:$vdst);
let Outs64 = (outs DstRC:$vdst);
// Suppress src2 implied by type since the 32-bit encoding uses an
// implicit VCC use.
let Ins32 = (ins Src0RC32:$src0, Src1RC32:$src1);
let InsSDWA = (ins Src0ModSDWA:$src0_modifiers, Src0SDWA:$src0,
Src1ModSDWA:$src1_modifiers, Src1SDWA:$src1,
clampmod:$clamp,
dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel, src1_sel:$src1_sel);
let InsDPP = (ins DstRCDPP:$old,
Src0DPP:$src0,
Src1DPP:$src1,
dpp_ctrl:$dpp_ctrl, row_mask:$row_mask,
bank_mask:$bank_mask, bound_ctrl:$bound_ctrl);
let HasExt = 1;
let HasSDWA9 = 1;
}
def VOP_READLANE : VOPProfile<[i32, i32, i32]> {
let Outs32 = (outs SReg_32:$vdst);
let Outs64 = Outs32;
let Ins32 = (ins VGPR_32:$src0, SCSrc_b32:$src1);
let Ins64 = Ins32;
let Asm32 = " $vdst, $src0, $src1";
let Asm64 = Asm32;
let HasExt = 0;
let HasSDWA9 = 0;
}
def VOP_WRITELANE : VOPProfile<[i32, i32, i32, i32]> {
let Outs32 = (outs VGPR_32:$vdst);
let Outs64 = Outs32;
let Ins32 = (ins SCSrc_b32:$src0, SCSrc_b32:$src1, VGPR_32:$vdst_in);
let Ins64 = Ins32;
let Asm32 = " $vdst, $src0, $src1";
let Asm64 = Asm32;
let HasExt = 0;
let HasSDWA9 = 0;
let HasSrc2 = 0;
let HasSrc2Mods = 0;
}
//===----------------------------------------------------------------------===//
// VOP2 Instructions
//===----------------------------------------------------------------------===//
let SubtargetPredicate = isGCN in {
defm V_CNDMASK_B32 : VOP2eInst <"v_cndmask_b32", VOP2e_I32_I32_I32_I1>;
def V_MADMK_F32 : VOP2_Pseudo <"v_madmk_f32", VOP_MADMK_F32, [], "">;
let isCommutable = 1 in {
defm V_ADD_F32 : VOP2Inst <"v_add_f32", VOP_F32_F32_F32, fadd>;
defm V_SUB_F32 : VOP2Inst <"v_sub_f32", VOP_F32_F32_F32, fsub>;
defm V_SUBREV_F32 : VOP2Inst <"v_subrev_f32", VOP_F32_F32_F32, null_frag, "v_sub_f32">;
defm V_MUL_LEGACY_F32 : VOP2Inst <"v_mul_legacy_f32", VOP_F32_F32_F32, AMDGPUfmul_legacy>;
defm V_MUL_F32 : VOP2Inst <"v_mul_f32", VOP_F32_F32_F32, fmul>;
defm V_MUL_I32_I24 : VOP2Inst <"v_mul_i32_i24", VOP_I32_I32_I32, AMDGPUmul_i24>;
defm V_MUL_HI_I32_I24 : VOP2Inst <"v_mul_hi_i32_i24", VOP_I32_I32_I32, AMDGPUmulhi_i24>;
defm V_MUL_U32_U24 : VOP2Inst <"v_mul_u32_u24", VOP_I32_I32_I32, AMDGPUmul_u24>;
defm V_MUL_HI_U32_U24 : VOP2Inst <"v_mul_hi_u32_u24", VOP_I32_I32_I32, AMDGPUmulhi_u24>;
defm V_MIN_F32 : VOP2Inst <"v_min_f32", VOP_F32_F32_F32, fminnum>;
defm V_MAX_F32 : VOP2Inst <"v_max_f32", VOP_F32_F32_F32, fmaxnum>;
defm V_MIN_I32 : VOP2Inst <"v_min_i32", VOP_I32_I32_I32>;
defm V_MAX_I32 : VOP2Inst <"v_max_i32", VOP_I32_I32_I32>;
defm V_MIN_U32 : VOP2Inst <"v_min_u32", VOP_I32_I32_I32>;
defm V_MAX_U32 : VOP2Inst <"v_max_u32", VOP_I32_I32_I32>;
defm V_LSHRREV_B32 : VOP2Inst <"v_lshrrev_b32", VOP_I32_I32_I32, null_frag, "v_lshr_b32">;
defm V_ASHRREV_I32 : VOP2Inst <"v_ashrrev_i32", VOP_I32_I32_I32, null_frag, "v_ashr_i32">;
defm V_LSHLREV_B32 : VOP2Inst <"v_lshlrev_b32", VOP_I32_I32_I32, null_frag, "v_lshl_b32">;
defm V_AND_B32 : VOP2Inst <"v_and_b32", VOP_I32_I32_I32>;
defm V_OR_B32 : VOP2Inst <"v_or_b32", VOP_I32_I32_I32>;
defm V_XOR_B32 : VOP2Inst <"v_xor_b32", VOP_I32_I32_I32>;
let Constraints = "$vdst = $src2", DisableEncoding="$src2",
isConvertibleToThreeAddress = 1 in {
defm V_MAC_F32 : VOP2Inst <"v_mac_f32", VOP_MAC_F32>;
}
def V_MADAK_F32 : VOP2_Pseudo <"v_madak_f32", VOP_MADAK_F32, [], "">;
// No patterns so that the scalar instructions are always selected.
// The scalar versions will be replaced with vector when needed later.
// V_ADD_I32, V_SUB_I32, and V_SUBREV_I32 where renamed to *_U32 in VI,
// but the VI instructions behave the same as the SI versions.
defm V_ADD_I32 : VOP2bInst <"v_add_i32", VOP2b_I32_I1_I32_I32, null_frag, "v_add_i32", 1>;
defm V_SUB_I32 : VOP2bInst <"v_sub_i32", VOP2b_I32_I1_I32_I32, null_frag, "v_sub_i32", 1>;
defm V_SUBREV_I32 : VOP2bInst <"v_subrev_i32", VOP2b_I32_I1_I32_I32, null_frag, "v_sub_i32", 1>;
defm V_ADDC_U32 : VOP2bInst <"v_addc_u32", VOP2b_I32_I1_I32_I32_I1, null_frag, "v_addc_u32", 1>;
defm V_SUBB_U32 : VOP2bInst <"v_subb_u32", VOP2b_I32_I1_I32_I32_I1, null_frag, "v_subb_u32", 1>;
defm V_SUBBREV_U32 : VOP2bInst <"v_subbrev_u32", VOP2b_I32_I1_I32_I32_I1, null_frag, "v_subb_u32", 1>;
let SubtargetPredicate = HasAddNoCarryInsts in {
defm V_ADD_U32 : VOP2Inst <"v_add_u32", VOP_I32_I32_I32, null_frag, "v_add_u32", 1>;
defm V_SUB_U32 : VOP2Inst <"v_sub_u32", VOP_I32_I32_I32, null_frag, "v_sub_u32", 1>;
defm V_SUBREV_U32 : VOP2Inst <"v_subrev_u32", VOP_I32_I32_I32, null_frag, "v_sub_u32", 1>;
}
} // End isCommutable = 1
// These are special and do not read the exec mask.
let isConvergent = 1, Uses = []<Register> in {
def V_READLANE_B32 : VOP2_Pseudo<"v_readlane_b32", VOP_READLANE,
[(set i32:$vdst, (int_amdgcn_readlane i32:$src0, i32:$src1))], "">;
let Constraints = "$vdst = $vdst_in", DisableEncoding="$vdst_in" in {
def V_WRITELANE_B32 : VOP2_Pseudo<"v_writelane_b32", VOP_WRITELANE,
[(set i32:$vdst, (int_amdgcn_writelane i32:$src0, i32:$src1, i32:$vdst_in))], "">;
} // End $vdst = $vdst_in, DisableEncoding $vdst_in
} // End isConvergent = 1
defm V_BFM_B32 : VOP2Inst <"v_bfm_b32", VOP_NO_EXT<VOP_I32_I32_I32>>;
defm V_BCNT_U32_B32 : VOP2Inst <"v_bcnt_u32_b32", VOP_NO_EXT<VOP_I32_I32_I32>>;
defm V_MBCNT_LO_U32_B32 : VOP2Inst <"v_mbcnt_lo_u32_b32", VOP_NO_EXT<VOP_I32_I32_I32>, int_amdgcn_mbcnt_lo>;
defm V_MBCNT_HI_U32_B32 : VOP2Inst <"v_mbcnt_hi_u32_b32", VOP_NO_EXT<VOP_I32_I32_I32>, int_amdgcn_mbcnt_hi>;
defm V_LDEXP_F32 : VOP2Inst <"v_ldexp_f32", VOP_NO_EXT<VOP_F32_F32_I32>, AMDGPUldexp>;
defm V_CVT_PKACCUM_U8_F32 : VOP2Inst <"v_cvt_pkaccum_u8_f32", VOP_NO_EXT<VOP_I32_F32_I32>>; // TODO: set "Uses = dst"
defm V_CVT_PKNORM_I16_F32 : VOP2Inst <"v_cvt_pknorm_i16_f32", VOP_NO_EXT<VOP_I32_F32_F32>, AMDGPUpknorm_i16_f32>;
defm V_CVT_PKNORM_U16_F32 : VOP2Inst <"v_cvt_pknorm_u16_f32", VOP_NO_EXT<VOP_I32_F32_F32>, AMDGPUpknorm_u16_f32>;
defm V_CVT_PKRTZ_F16_F32 : VOP2Inst <"v_cvt_pkrtz_f16_f32", VOP_NO_EXT<VOP_I32_F32_F32>, AMDGPUpkrtz_f16_f32>;
defm V_CVT_PK_U16_U32 : VOP2Inst <"v_cvt_pk_u16_u32", VOP_NO_EXT<VOP_I32_I32_I32>, AMDGPUpk_u16_u32>;
defm V_CVT_PK_I16_I32 : VOP2Inst <"v_cvt_pk_i16_i32", VOP_NO_EXT<VOP_I32_I32_I32>, AMDGPUpk_i16_i32>;
} // End SubtargetPredicate = isGCN
def : GCNPat<
(AMDGPUadde i32:$src0, i32:$src1, i1:$src2),
(V_ADDC_U32_e64 $src0, $src1, $src2)
>;
def : GCNPat<
(AMDGPUsube i32:$src0, i32:$src1, i1:$src2),
(V_SUBB_U32_e64 $src0, $src1, $src2)
>;
// These instructions only exist on SI and CI
let SubtargetPredicate = isSICI in {
defm V_MIN_LEGACY_F32 : VOP2Inst <"v_min_legacy_f32", VOP_F32_F32_F32, AMDGPUfmin_legacy>;
defm V_MAX_LEGACY_F32 : VOP2Inst <"v_max_legacy_f32", VOP_F32_F32_F32, AMDGPUfmax_legacy>;
let isCommutable = 1 in {
defm V_MAC_LEGACY_F32 : VOP2Inst <"v_mac_legacy_f32", VOP_F32_F32_F32>;
defm V_LSHR_B32 : VOP2Inst <"v_lshr_b32", VOP_I32_I32_I32>;
defm V_ASHR_I32 : VOP2Inst <"v_ashr_i32", VOP_I32_I32_I32>;
defm V_LSHL_B32 : VOP2Inst <"v_lshl_b32", VOP_I32_I32_I32>;
} // End isCommutable = 1
} // End let SubtargetPredicate = SICI
let SubtargetPredicate = Has16BitInsts in {
def V_MADMK_F16 : VOP2_Pseudo <"v_madmk_f16", VOP_MADMK_F16, [], "">;
defm V_LSHLREV_B16 : VOP2Inst <"v_lshlrev_b16", VOP_I16_I16_I16>;
defm V_LSHRREV_B16 : VOP2Inst <"v_lshrrev_b16", VOP_I16_I16_I16>;
defm V_ASHRREV_I16 : VOP2Inst <"v_ashrrev_i16", VOP_I16_I16_I16>;
defm V_LDEXP_F16 : VOP2Inst <"v_ldexp_f16", VOP_F16_F16_I32, AMDGPUldexp>;
let isCommutable = 1 in {
defm V_ADD_F16 : VOP2Inst <"v_add_f16", VOP_F16_F16_F16, fadd>;
defm V_SUB_F16 : VOP2Inst <"v_sub_f16", VOP_F16_F16_F16, fsub>;
defm V_SUBREV_F16 : VOP2Inst <"v_subrev_f16", VOP_F16_F16_F16, null_frag, "v_sub_f16">;
defm V_MUL_F16 : VOP2Inst <"v_mul_f16", VOP_F16_F16_F16, fmul>;
def V_MADAK_F16 : VOP2_Pseudo <"v_madak_f16", VOP_MADAK_F16, [], "">;
defm V_ADD_U16 : VOP2Inst <"v_add_u16", VOP_I16_I16_I16>;
defm V_SUB_U16 : VOP2Inst <"v_sub_u16" , VOP_I16_I16_I16>;
defm V_SUBREV_U16 : VOP2Inst <"v_subrev_u16", VOP_I16_I16_I16, null_frag, "v_sub_u16">;
defm V_MUL_LO_U16 : VOP2Inst <"v_mul_lo_u16", VOP_I16_I16_I16>;
defm V_MAX_F16 : VOP2Inst <"v_max_f16", VOP_F16_F16_F16, fmaxnum>;
defm V_MIN_F16 : VOP2Inst <"v_min_f16", VOP_F16_F16_F16, fminnum>;
defm V_MAX_U16 : VOP2Inst <"v_max_u16", VOP_I16_I16_I16>;
defm V_MAX_I16 : VOP2Inst <"v_max_i16", VOP_I16_I16_I16>;
defm V_MIN_U16 : VOP2Inst <"v_min_u16", VOP_I16_I16_I16>;
defm V_MIN_I16 : VOP2Inst <"v_min_i16", VOP_I16_I16_I16>;
let Constraints = "$vdst = $src2", DisableEncoding="$src2",
isConvertibleToThreeAddress = 1 in {
defm V_MAC_F16 : VOP2Inst <"v_mac_f16", VOP_MAC_F16>;
}
} // End isCommutable = 1
} // End SubtargetPredicate = Has16BitInsts
// Note: 16-bit instructions produce a 0 result in the high 16-bits.
multiclass Arithmetic_i16_Pats <SDPatternOperator op, Instruction inst> {
def : GCNPat<
(op i16:$src0, i16:$src1),
(inst $src0, $src1)
>;
def : GCNPat<
(i32 (zext (op i16:$src0, i16:$src1))),
(inst $src0, $src1)
>;
def : GCNPat<
(i64 (zext (op i16:$src0, i16:$src1))),
(REG_SEQUENCE VReg_64,
(inst $src0, $src1), sub0,
(V_MOV_B32_e32 (i32 0)), sub1)
>;
}
multiclass Bits_OpsRev_i16_Pats <SDPatternOperator op, Instruction inst> {
def : GCNPat<
(op i16:$src0, i16:$src1),
(inst $src1, $src0)
>;
def : GCNPat<
(i32 (zext (op i16:$src0, i16:$src1))),
(inst $src1, $src0)
>;
def : GCNPat<
(i64 (zext (op i16:$src0, i16:$src1))),
(REG_SEQUENCE VReg_64,
(inst $src1, $src0), sub0,
(V_MOV_B32_e32 (i32 0)), sub1)
>;
}
class ZExt_i16_i1_Pat <SDNode ext> : GCNPat <
(i16 (ext i1:$src)),
(V_CNDMASK_B32_e64 (i32 0), (i32 1), $src)
>;
let Predicates = [Has16BitInsts] in {
defm : Arithmetic_i16_Pats<add, V_ADD_U16_e64>;
defm : Arithmetic_i16_Pats<mul, V_MUL_LO_U16_e64>;
defm : Arithmetic_i16_Pats<sub, V_SUB_U16_e64>;
defm : Arithmetic_i16_Pats<smin, V_MIN_I16_e64>;
defm : Arithmetic_i16_Pats<smax, V_MAX_I16_e64>;
defm : Arithmetic_i16_Pats<umin, V_MIN_U16_e64>;
defm : Arithmetic_i16_Pats<umax, V_MAX_U16_e64>;
def : GCNPat <
(and i16:$src0, i16:$src1),
(V_AND_B32_e64 $src0, $src1)
>;
def : GCNPat <
(or i16:$src0, i16:$src1),
(V_OR_B32_e64 $src0, $src1)
>;
def : GCNPat <
(xor i16:$src0, i16:$src1),
(V_XOR_B32_e64 $src0, $src1)
>;
defm : Bits_OpsRev_i16_Pats<shl, V_LSHLREV_B16_e64>;
defm : Bits_OpsRev_i16_Pats<srl, V_LSHRREV_B16_e64>;
defm : Bits_OpsRev_i16_Pats<sra, V_ASHRREV_I16_e64>;
def : ZExt_i16_i1_Pat<zext>;
def : ZExt_i16_i1_Pat<anyext>;
def : GCNPat <
(i16 (sext i1:$src)),
(V_CNDMASK_B32_e64 (i32 0), (i32 -1), $src)
>;
// Undo sub x, c -> add x, -c canonicalization since c is more likely
// an inline immediate than -c.
// TODO: Also do for 64-bit.
def : GCNPat<
(add i16:$src0, (i16 NegSubInlineConst16:$src1)),
(V_SUB_U16_e64 $src0, NegSubInlineConst16:$src1)
>;
} // End Predicates = [Has16BitInsts]
//===----------------------------------------------------------------------===//
// SI
//===----------------------------------------------------------------------===//
let AssemblerPredicates = [isSICI], DecoderNamespace = "SICI" in {
multiclass VOP2_Real_si <bits<6> op> {
def _si :
VOP2_Real<!cast<VOP2_Pseudo>(NAME), SIEncodingFamily.SI>,
VOP2e<op{5-0}, !cast<VOP2_Pseudo>(NAME).Pfl>;
}
multiclass VOP2_Real_MADK_si <bits<6> op> {
def _si : VOP2_Real<!cast<VOP2_Pseudo>(NAME), SIEncodingFamily.SI>,
VOP2_MADKe<op{5-0}, !cast<VOP2_Pseudo>(NAME).Pfl>;
}
multiclass VOP2_Real_e32_si <bits<6> op> {
def _e32_si :
VOP2_Real<!cast<VOP2_Pseudo>(NAME#"_e32"), SIEncodingFamily.SI>,
VOP2e<op{5-0}, !cast<VOP2_Pseudo>(NAME#"_e32").Pfl>;
}
multiclass VOP2_Real_e32e64_si <bits<6> op> : VOP2_Real_e32_si<op> {
def _e64_si :
VOP3_Real<!cast<VOP3_Pseudo>(NAME#"_e64"), SIEncodingFamily.SI>,
VOP3e_si <{1, 0, 0, op{5-0}}, !cast<VOP3_Pseudo>(NAME#"_e64").Pfl>;
}
multiclass VOP2be_Real_e32e64_si <bits<6> op> : VOP2_Real_e32_si<op> {
def _e64_si :
VOP3_Real<!cast<VOP3_Pseudo>(NAME#"_e64"), SIEncodingFamily.SI>,
VOP3be_si <{1, 0, 0, op{5-0}}, !cast<VOP3_Pseudo>(NAME#"_e64").Pfl>;
}
} // End AssemblerPredicates = [isSICI], DecoderNamespace = "SICI"
defm V_CNDMASK_B32 : VOP2_Real_e32e64_si <0x0>;
defm V_ADD_F32 : VOP2_Real_e32e64_si <0x3>;
defm V_SUB_F32 : VOP2_Real_e32e64_si <0x4>;
defm V_SUBREV_F32 : VOP2_Real_e32e64_si <0x5>;
defm V_MUL_LEGACY_F32 : VOP2_Real_e32e64_si <0x7>;
defm V_MUL_F32 : VOP2_Real_e32e64_si <0x8>;
defm V_MUL_I32_I24 : VOP2_Real_e32e64_si <0x9>;
defm V_MUL_HI_I32_I24 : VOP2_Real_e32e64_si <0xa>;
defm V_MUL_U32_U24 : VOP2_Real_e32e64_si <0xb>;
defm V_MUL_HI_U32_U24 : VOP2_Real_e32e64_si <0xc>;
defm V_MIN_F32 : VOP2_Real_e32e64_si <0xf>;
defm V_MAX_F32 : VOP2_Real_e32e64_si <0x10>;
defm V_MIN_I32 : VOP2_Real_e32e64_si <0x11>;
defm V_MAX_I32 : VOP2_Real_e32e64_si <0x12>;
defm V_MIN_U32 : VOP2_Real_e32e64_si <0x13>;
defm V_MAX_U32 : VOP2_Real_e32e64_si <0x14>;
defm V_LSHRREV_B32 : VOP2_Real_e32e64_si <0x16>;
defm V_ASHRREV_I32 : VOP2_Real_e32e64_si <0x18>;
defm V_LSHLREV_B32 : VOP2_Real_e32e64_si <0x1a>;
defm V_AND_B32 : VOP2_Real_e32e64_si <0x1b>;
defm V_OR_B32 : VOP2_Real_e32e64_si <0x1c>;
defm V_XOR_B32 : VOP2_Real_e32e64_si <0x1d>;
defm V_MAC_F32 : VOP2_Real_e32e64_si <0x1f>;
defm V_MADMK_F32 : VOP2_Real_MADK_si <0x20>;
defm V_MADAK_F32 : VOP2_Real_MADK_si <0x21>;
defm V_ADD_I32 : VOP2be_Real_e32e64_si <0x25>;
defm V_SUB_I32 : VOP2be_Real_e32e64_si <0x26>;
defm V_SUBREV_I32 : VOP2be_Real_e32e64_si <0x27>;
defm V_ADDC_U32 : VOP2be_Real_e32e64_si <0x28>;
defm V_SUBB_U32 : VOP2be_Real_e32e64_si <0x29>;
defm V_SUBBREV_U32 : VOP2be_Real_e32e64_si <0x2a>;
defm V_READLANE_B32 : VOP2_Real_si <0x01>;
let InOperandList = (ins SSrc_b32:$src0, SCSrc_b32:$src1, VSrc_b32:$vdst_in) in {
defm V_WRITELANE_B32 : VOP2_Real_si <0x02>;
}
defm V_MAC_LEGACY_F32 : VOP2_Real_e32e64_si <0x6>;
defm V_MIN_LEGACY_F32 : VOP2_Real_e32e64_si <0xd>;
defm V_MAX_LEGACY_F32 : VOP2_Real_e32e64_si <0xe>;
defm V_LSHR_B32 : VOP2_Real_e32e64_si <0x15>;
defm V_ASHR_I32 : VOP2_Real_e32e64_si <0x17>;
defm V_LSHL_B32 : VOP2_Real_e32e64_si <0x19>;
defm V_BFM_B32 : VOP2_Real_e32e64_si <0x1e>;
defm V_BCNT_U32_B32 : VOP2_Real_e32e64_si <0x22>;
defm V_MBCNT_LO_U32_B32 : VOP2_Real_e32e64_si <0x23>;
defm V_MBCNT_HI_U32_B32 : VOP2_Real_e32e64_si <0x24>;
defm V_LDEXP_F32 : VOP2_Real_e32e64_si <0x2b>;
defm V_CVT_PKACCUM_U8_F32 : VOP2_Real_e32e64_si <0x2c>;
defm V_CVT_PKNORM_I16_F32 : VOP2_Real_e32e64_si <0x2d>;
defm V_CVT_PKNORM_U16_F32 : VOP2_Real_e32e64_si <0x2e>;
defm V_CVT_PKRTZ_F16_F32 : VOP2_Real_e32e64_si <0x2f>;
defm V_CVT_PK_U16_U32 : VOP2_Real_e32e64_si <0x30>;
defm V_CVT_PK_I16_I32 : VOP2_Real_e32e64_si <0x31>;
//===----------------------------------------------------------------------===//
// VI
//===----------------------------------------------------------------------===//
class VOP2_DPP <bits<6> op, VOP2_Pseudo ps, string OpName = ps.OpName, VOPProfile P = ps.Pfl> :
VOP_DPP <OpName, P> {
let Defs = ps.Defs;
let Uses = ps.Uses;
let SchedRW = ps.SchedRW;
let hasSideEffects = ps.hasSideEffects;
bits<8> vdst;
bits<8> src1;
let Inst{8-0} = 0xfa; //dpp
let Inst{16-9} = !if(P.HasSrc1, src1{7-0}, 0);
let Inst{24-17} = !if(P.EmitDst, vdst{7-0}, 0);
let Inst{30-25} = op;
let Inst{31} = 0x0; //encoding
}
let AssemblerPredicates = [isVI], DecoderNamespace = "VI" in {
multiclass VOP32_Real_vi <bits<10> op> {
def _vi :
VOP2_Real<!cast<VOP2_Pseudo>(NAME), SIEncodingFamily.VI>,
VOP3e_vi<op, !cast<VOP2_Pseudo>(NAME).Pfl>;
}
multiclass VOP2_Real_MADK_vi <bits<6> op> {
def _vi : VOP2_Real<!cast<VOP2_Pseudo>(NAME), SIEncodingFamily.VI>,
VOP2_MADKe<op{5-0}, !cast<VOP2_Pseudo>(NAME).Pfl>;
}
multiclass VOP2_Real_e32_vi <bits<6> op> {
def _e32_vi :
VOP2_Real<!cast<VOP2_Pseudo>(NAME#"_e32"), SIEncodingFamily.VI>,
VOP2e<op{5-0}, !cast<VOP2_Pseudo>(NAME#"_e32").Pfl>;
}
multiclass VOP2_Real_e64_vi <bits<10> op> {
def _e64_vi :
VOP3_Real<!cast<VOP3_Pseudo>(NAME#"_e64"), SIEncodingFamily.VI>,
VOP3e_vi <op, !cast<VOP3_Pseudo>(NAME#"_e64").Pfl>;
}
multiclass VOP2_Real_e64only_vi <bits<10> op> {
def _e64_vi :
VOP3_Real<!cast<VOP3_Pseudo>(NAME#"_e64"), SIEncodingFamily.VI>,
VOP3e_vi <op, !cast<VOP3_Pseudo>(NAME#"_e64").Pfl> {
// Hack to stop printing _e64
VOP3_Pseudo ps = !cast<VOP3_Pseudo>(NAME#"_e64");
let OutOperandList = (outs VGPR_32:$vdst);
let AsmString = ps.Mnemonic # " " # ps.AsmOperands;
}
}
multiclass Base_VOP2_Real_e32e64_vi <bits<6> op> :
VOP2_Real_e32_vi<op>,
VOP2_Real_e64_vi<{0, 1, 0, 0, op{5-0}}>;
} // End AssemblerPredicates = [isVI], DecoderNamespace = "VI"
multiclass VOP2_SDWA_Real <bits<6> op> {
def _sdwa_vi :
VOP_SDWA_Real <!cast<VOP2_SDWA_Pseudo>(NAME#"_sdwa")>,
VOP2_SDWAe <op{5-0}, !cast<VOP2_SDWA_Pseudo>(NAME#"_sdwa").Pfl>;
}
multiclass VOP2_SDWA9_Real <bits<6> op> {
def _sdwa_gfx9 :
VOP_SDWA9_Real <!cast<VOP2_SDWA_Pseudo>(NAME#"_sdwa")>,
VOP2_SDWA9Ae <op{5-0}, !cast<VOP2_SDWA_Pseudo>(NAME#"_sdwa").Pfl>;
}
let AssemblerPredicates = [isVIOnly] in {
multiclass VOP2be_Real_e32e64_vi_only <bits<6> op, string OpName, string AsmName> {
def _e32_vi :
VOP2_Real<!cast<VOP2_Pseudo>(OpName#"_e32"), SIEncodingFamily.VI>,
VOP2e<op{5-0}, !cast<VOP2_Pseudo>(OpName#"_e32").Pfl> {
VOP2_Pseudo ps = !cast<VOP2_Pseudo>(OpName#"_e32");
let AsmString = AsmName # ps.AsmOperands;
let DecoderNamespace = "VI";
}
def _e64_vi :
VOP3_Real<!cast<VOP3_Pseudo>(OpName#"_e64"), SIEncodingFamily.VI>,
VOP3be_vi <{0, 1, 0, 0, op{5-0}}, !cast<VOP3_Pseudo>(OpName#"_e64").Pfl> {
VOP3_Pseudo ps = !cast<VOP3_Pseudo>(OpName#"_e64");
let AsmString = AsmName # ps.AsmOperands;
let DecoderNamespace = "VI";
}
def _sdwa_vi :
VOP_SDWA_Real <!cast<VOP2_SDWA_Pseudo>(OpName#"_sdwa")>,
VOP2_SDWAe <op{5-0}, !cast<VOP2_SDWA_Pseudo>(OpName#"_sdwa").Pfl> {
VOP2_SDWA_Pseudo ps = !cast<VOP2_SDWA_Pseudo>(OpName#"_sdwa");
let AsmString = AsmName # ps.AsmOperands;
}
def _dpp :
VOP2_DPP<op, !cast<VOP2_Pseudo>(OpName#"_e32"), AsmName>;
}
}
let AssemblerPredicates = [isGFX9] in {
multiclass VOP2be_Real_e32e64_gfx9 <bits<6> op, string OpName, string AsmName> {
def _e32_gfx9 :
VOP2_Real<!cast<VOP2_Pseudo>(OpName#"_e32"), SIEncodingFamily.GFX9>,
VOP2e<op{5-0}, !cast<VOP2_Pseudo>(OpName#"_e32").Pfl> {
VOP2_Pseudo ps = !cast<VOP2_Pseudo>(OpName#"_e32");
let AsmString = AsmName # ps.AsmOperands;
let DecoderNamespace = "GFX9";
}
def _e64_gfx9 :
VOP3_Real<!cast<VOP3_Pseudo>(OpName#"_e64"), SIEncodingFamily.GFX9>,
VOP3be_vi <{0, 1, 0, 0, op{5-0}}, !cast<VOP3_Pseudo>(OpName#"_e64").Pfl> {
VOP3_Pseudo ps = !cast<VOP3_Pseudo>(OpName#"_e64");
let AsmString = AsmName # ps.AsmOperands;
let DecoderNamespace = "GFX9";
}
def _sdwa_gfx9 :
VOP_SDWA9_Real <!cast<VOP2_SDWA_Pseudo>(OpName#"_sdwa")>,
VOP2_SDWA9Ae <op{5-0}, !cast<VOP2_SDWA_Pseudo>(OpName#"_sdwa").Pfl> {
VOP2_SDWA_Pseudo ps = !cast<VOP2_SDWA_Pseudo>(OpName#"_sdwa");
let AsmString = AsmName # ps.AsmOperands;
}
def _dpp_gfx9 :
VOP2_DPP<op, !cast<VOP2_Pseudo>(OpName#"_e32"), AsmName> {
let DecoderNamespace = "SDWA9";
}
}
multiclass VOP2_Real_e32e64_gfx9 <bits<6> op> {
def _e32_gfx9 :
VOP2_Real<!cast<VOP2_Pseudo>(NAME#"_e32"), SIEncodingFamily.GFX9>,
VOP2e<op{5-0}, !cast<VOP2_Pseudo>(NAME#"_e32").Pfl>{
let DecoderNamespace = "GFX9";
}
def _e64_gfx9 :
VOP3_Real<!cast<VOP3_Pseudo>(NAME#"_e64"), SIEncodingFamily.GFX9>,
VOP3e_vi <{0, 1, 0, 0, op{5-0}}, !cast<VOP3_Pseudo>(NAME#"_e64").Pfl> {
let DecoderNamespace = "GFX9";
}
def _sdwa_gfx9 :
VOP_SDWA9_Real <!cast<VOP2_SDWA_Pseudo>(NAME#"_sdwa")>,
VOP2_SDWA9Ae <op{5-0}, !cast<VOP2_SDWA_Pseudo>(NAME#"_sdwa").Pfl> {
}
def _dpp_gfx9 :
VOP2_DPP<op, !cast<VOP2_Pseudo>(NAME#"_e32")> {
let DecoderNamespace = "SDWA9";
}
}
} // AssemblerPredicates = [isGFX9]
multiclass VOP2_Real_e32e64_vi <bits<6> op> :
Base_VOP2_Real_e32e64_vi<op>, VOP2_SDWA_Real<op>, VOP2_SDWA9_Real<op> {
// For now left dpp only for asm/dasm
// TODO: add corresponding pseudo
def _dpp : VOP2_DPP<op, !cast<VOP2_Pseudo>(NAME#"_e32")>;
}
defm V_CNDMASK_B32 : VOP2_Real_e32e64_vi <0x0>;
defm V_ADD_F32 : VOP2_Real_e32e64_vi <0x1>;
defm V_SUB_F32 : VOP2_Real_e32e64_vi <0x2>;
defm V_SUBREV_F32 : VOP2_Real_e32e64_vi <0x3>;
defm V_MUL_LEGACY_F32 : VOP2_Real_e32e64_vi <0x4>;
defm V_MUL_F32 : VOP2_Real_e32e64_vi <0x5>;
defm V_MUL_I32_I24 : VOP2_Real_e32e64_vi <0x6>;
defm V_MUL_HI_I32_I24 : VOP2_Real_e32e64_vi <0x7>;
defm V_MUL_U32_U24 : VOP2_Real_e32e64_vi <0x8>;
defm V_MUL_HI_U32_U24 : VOP2_Real_e32e64_vi <0x9>;
defm V_MIN_F32 : VOP2_Real_e32e64_vi <0xa>;
defm V_MAX_F32 : VOP2_Real_e32e64_vi <0xb>;
defm V_MIN_I32 : VOP2_Real_e32e64_vi <0xc>;
defm V_MAX_I32 : VOP2_Real_e32e64_vi <0xd>;
defm V_MIN_U32 : VOP2_Real_e32e64_vi <0xe>;
defm V_MAX_U32 : VOP2_Real_e32e64_vi <0xf>;
defm V_LSHRREV_B32 : VOP2_Real_e32e64_vi <0x10>;
defm V_ASHRREV_I32 : VOP2_Real_e32e64_vi <0x11>;
defm V_LSHLREV_B32 : VOP2_Real_e32e64_vi <0x12>;
defm V_AND_B32 : VOP2_Real_e32e64_vi <0x13>;
defm V_OR_B32 : VOP2_Real_e32e64_vi <0x14>;
defm V_XOR_B32 : VOP2_Real_e32e64_vi <0x15>;
defm V_MAC_F32 : VOP2_Real_e32e64_vi <0x16>;
defm V_MADMK_F32 : VOP2_Real_MADK_vi <0x17>;
defm V_MADAK_F32 : VOP2_Real_MADK_vi <0x18>;
defm V_ADD_U32 : VOP2be_Real_e32e64_vi_only <0x19, "V_ADD_I32", "v_add_u32">;
defm V_SUB_U32 : VOP2be_Real_e32e64_vi_only <0x1a, "V_SUB_I32", "v_sub_u32">;
defm V_SUBREV_U32 : VOP2be_Real_e32e64_vi_only <0x1b, "V_SUBREV_I32", "v_subrev_u32">;
defm V_ADDC_U32 : VOP2be_Real_e32e64_vi_only <0x1c, "V_ADDC_U32", "v_addc_u32">;
defm V_SUBB_U32 : VOP2be_Real_e32e64_vi_only <0x1d, "V_SUBB_U32", "v_subb_u32">;
defm V_SUBBREV_U32 : VOP2be_Real_e32e64_vi_only <0x1e, "V_SUBBREV_U32", "v_subbrev_u32">;
defm V_ADD_CO_U32 : VOP2be_Real_e32e64_gfx9 <0x19, "V_ADD_I32", "v_add_co_u32">;
defm V_SUB_CO_U32 : VOP2be_Real_e32e64_gfx9 <0x1a, "V_SUB_I32", "v_sub_co_u32">;
defm V_SUBREV_CO_U32 : VOP2be_Real_e32e64_gfx9 <0x1b, "V_SUBREV_I32", "v_subrev_co_u32">;
defm V_ADDC_CO_U32 : VOP2be_Real_e32e64_gfx9 <0x1c, "V_ADDC_U32", "v_addc_co_u32">;
defm V_SUBB_CO_U32 : VOP2be_Real_e32e64_gfx9 <0x1d, "V_SUBB_U32", "v_subb_co_u32">;
defm V_SUBBREV_CO_U32 : VOP2be_Real_e32e64_gfx9 <0x1e, "V_SUBBREV_U32", "v_subbrev_co_u32">;
defm V_ADD_U32 : VOP2_Real_e32e64_gfx9 <0x34>;
defm V_SUB_U32 : VOP2_Real_e32e64_gfx9 <0x35>;
defm V_SUBREV_U32 : VOP2_Real_e32e64_gfx9 <0x36>;
defm V_READLANE_B32 : VOP32_Real_vi <0x289>;
defm V_WRITELANE_B32 : VOP32_Real_vi <0x28a>;
defm V_BFM_B32 : VOP2_Real_e64only_vi <0x293>;
defm V_BCNT_U32_B32 : VOP2_Real_e64only_vi <0x28b>;
defm V_MBCNT_LO_U32_B32 : VOP2_Real_e64only_vi <0x28c>;
defm V_MBCNT_HI_U32_B32 : VOP2_Real_e64only_vi <0x28d>;
defm V_LDEXP_F32 : VOP2_Real_e64only_vi <0x288>;
defm V_CVT_PKACCUM_U8_F32 : VOP2_Real_e64only_vi <0x1f0>;
defm V_CVT_PKNORM_I16_F32 : VOP2_Real_e64only_vi <0x294>;
defm V_CVT_PKNORM_U16_F32 : VOP2_Real_e64only_vi <0x295>;
defm V_CVT_PKRTZ_F16_F32 : VOP2_Real_e64only_vi <0x296>;
defm V_CVT_PK_U16_U32 : VOP2_Real_e64only_vi <0x297>;
defm V_CVT_PK_I16_I32 : VOP2_Real_e64only_vi <0x298>;
defm V_ADD_F16 : VOP2_Real_e32e64_vi <0x1f>;
defm V_SUB_F16 : VOP2_Real_e32e64_vi <0x20>;
defm V_SUBREV_F16 : VOP2_Real_e32e64_vi <0x21>;
defm V_MUL_F16 : VOP2_Real_e32e64_vi <0x22>;
defm V_MAC_F16 : VOP2_Real_e32e64_vi <0x23>;
defm V_MADMK_F16 : VOP2_Real_MADK_vi <0x24>;
defm V_MADAK_F16 : VOP2_Real_MADK_vi <0x25>;
defm V_ADD_U16 : VOP2_Real_e32e64_vi <0x26>;
defm V_SUB_U16 : VOP2_Real_e32e64_vi <0x27>;
defm V_SUBREV_U16 : VOP2_Real_e32e64_vi <0x28>;
defm V_MUL_LO_U16 : VOP2_Real_e32e64_vi <0x29>;
defm V_LSHLREV_B16 : VOP2_Real_e32e64_vi <0x2a>;
defm V_LSHRREV_B16 : VOP2_Real_e32e64_vi <0x2b>;
defm V_ASHRREV_I16 : VOP2_Real_e32e64_vi <0x2c>;
defm V_MAX_F16 : VOP2_Real_e32e64_vi <0x2d>;
defm V_MIN_F16 : VOP2_Real_e32e64_vi <0x2e>;
defm V_MAX_U16 : VOP2_Real_e32e64_vi <0x2f>;
defm V_MAX_I16 : VOP2_Real_e32e64_vi <0x30>;
defm V_MIN_U16 : VOP2_Real_e32e64_vi <0x31>;
defm V_MIN_I16 : VOP2_Real_e32e64_vi <0x32>;
defm V_LDEXP_F16 : VOP2_Real_e32e64_vi <0x33>;
let SubtargetPredicate = isVI in {
// Aliases to simplify matching of floating-point instructions that
// are VOP2 on SI and VOP3 on VI.
class SI2_VI3Alias <string name, VOP3_Real inst> : InstAlias <
name#" $dst, $src0, $src1",
!if(inst.Pfl.HasOMod,
(inst VGPR_32:$dst, 0, VCSrc_f32:$src0, 0, VCSrc_f32:$src1, 0, 0),
(inst VGPR_32:$dst, 0, VCSrc_f32:$src0, 0, VCSrc_f32:$src1, 0))
>, PredicateControl {
let UseInstAsmMatchConverter = 0;
let AsmVariantName = AMDGPUAsmVariants.VOP3;
}
def : SI2_VI3Alias <"v_ldexp_f32", V_LDEXP_F32_e64_vi>;
def : SI2_VI3Alias <"v_cvt_pkaccum_u8_f32", V_CVT_PKACCUM_U8_F32_e64_vi>;
def : SI2_VI3Alias <"v_cvt_pknorm_i16_f32", V_CVT_PKNORM_I16_F32_e64_vi>;
def : SI2_VI3Alias <"v_cvt_pknorm_u16_f32", V_CVT_PKNORM_U16_F32_e64_vi>;
def : SI2_VI3Alias <"v_cvt_pkrtz_f16_f32", V_CVT_PKRTZ_F16_F32_e64_vi>;
} // End SubtargetPredicate = isVI