1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 04:32:44 +01:00
llvm-mirror/lib/Target/AArch64/AArch64SMEInstrInfo.td
Cullen Rhodes 1ae2c0fb16 [AArch64][SME] Add zero instruction
This patch adds the zero instruction for zeroing a list of 64-bit
element ZA tiles. The instruction takes a list of up to eight tiles
ZA0.D-ZA7.D, which must be in order, e.g.

  zero {za0.d,za1.d,za2.d,za3.d,za4.d,za5.d,za6.d,za7.d}
  zero {za1.d,za3.d,za5.d,za7.d}

The assembler also accepts 32-bit, 16-bit and 8-bit element tiles which
are mapped to corresponding 64-bit element tiles in accordance with the
architecturally defined mapping between different element size tiles,
e.g.

  * Zeroing ZA0.B, or the entire array name ZA, is equivalent to zeroing
    all eight 64-bit element tiles ZA0.D to ZA7.D.
  * Zeroing ZA0.S is equivalent to zeroing ZA0.D and ZA4.D.

The preferred disassembly of this instruction uses the shortest list of
tile names that represent the encoded immediate mask, e.g.

  * An immediate which encodes 64-bit element tiles ZA0.D, ZA1.D, ZA4.D and
    ZA5.D is disassembled as {ZA0.S, ZA1.S}.
  * An immediate which encodes 64-bit element tiles ZA0.D, ZA2.D, ZA4.D and
    ZA6.D is disassembled as {ZA0.H}.
  * An all-ones immediate is disassembled as {ZA}.
  * An all-zeros immediate is disassembled as an empty list {}.

This patch adds the MatrixTileList asm operand and related parsing to support
this.

Depends on D105570.

The reference can be found here:
https://developer.arm.com/documentation/ddi0602/2021-06

Reviewed By: david-arm

Differential Revision: https://reviews.llvm.org/D105575
2021-07-27 08:35:45 +00:00

144 lines
5.5 KiB
TableGen

//=- AArch64SMEInstrInfo.td - AArch64 SME Instructions -*- tablegen -*-----=//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// AArch64 Scalable Matrix Extension (SME) Instruction definitions.
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// Add vector elements horizontally or vertically to ZA tile.
//===----------------------------------------------------------------------===//
let Predicates = [HasSME] in {
def ADDHA_MPPZ_S : sme_add_vector_to_tile_u32<0b0, "addha">;
def ADDVA_MPPZ_S : sme_add_vector_to_tile_u32<0b1, "addva">;
}
let Predicates = [HasSMEI64] in {
def ADDHA_MPPZ_D : sme_add_vector_to_tile_u64<0b0, "addha">;
def ADDVA_MPPZ_D : sme_add_vector_to_tile_u64<0b1, "addva">;
}
let Predicates = [HasSME] in {
//===----------------------------------------------------------------------===//
// Outer products
//===----------------------------------------------------------------------===//
defm BFMOPA_MPPZZ : sme_bf16_outer_product<0b0, "bfmopa">;
defm BFMOPS_MPPZZ : sme_bf16_outer_product<0b1, "bfmops">;
def FMOPA_MPPZZ_S : sme_outer_product_fp32<0b0, "fmopa">;
def FMOPS_MPPZZ_S : sme_outer_product_fp32<0b1, "fmops">;
}
let Predicates = [HasSMEF64] in {
def FMOPA_MPPZZ_D : sme_outer_product_fp64<0b0, "fmopa">;
def FMOPS_MPPZZ_D : sme_outer_product_fp64<0b1, "fmops">;
}
let Predicates = [HasSME] in {
defm FMOPAL_MPPZZ : sme_f16_outer_product<0b0, "fmopa">;
defm FMOPSL_MPPZZ : sme_f16_outer_product<0b1, "fmops">;
def SMOPA_MPPZZ_S : sme_int_outer_product_i32<0b000, "smopa">;
def SMOPS_MPPZZ_S : sme_int_outer_product_i32<0b001, "smops">;
def UMOPA_MPPZZ_S : sme_int_outer_product_i32<0b110, "umopa">;
def UMOPS_MPPZZ_S : sme_int_outer_product_i32<0b111, "umops">;
def SUMOPA_MPPZZ_S : sme_int_outer_product_i32<0b010, "sumopa">;
def SUMOPS_MPPZZ_S : sme_int_outer_product_i32<0b011, "sumops">;
def USMOPA_MPPZZ_S : sme_int_outer_product_i32<0b100, "usmopa">;
def USMOPS_MPPZZ_S : sme_int_outer_product_i32<0b101, "usmops">;
}
let Predicates = [HasSMEI64] in {
def SMOPA_MPPZZ_D : sme_int_outer_product_i64<0b000, "smopa">;
def SMOPS_MPPZZ_D : sme_int_outer_product_i64<0b001, "smops">;
def UMOPA_MPPZZ_D : sme_int_outer_product_i64<0b110, "umopa">;
def UMOPS_MPPZZ_D : sme_int_outer_product_i64<0b111, "umops">;
def SUMOPA_MPPZZ_D : sme_int_outer_product_i64<0b010, "sumopa">;
def SUMOPS_MPPZZ_D : sme_int_outer_product_i64<0b011, "sumops">;
def USMOPA_MPPZZ_D : sme_int_outer_product_i64<0b100, "usmopa">;
def USMOPS_MPPZZ_D : sme_int_outer_product_i64<0b101, "usmops">;
}
let Predicates = [HasSME] in {
//===----------------------------------------------------------------------===//
// Loads and stores
//===----------------------------------------------------------------------===//
defm LD1_MXIPXX : sme_mem_ld_ss<"ld1">;
defm ST1_MXIPXX : sme_mem_st_ss<"st1">;
//===----------------------------------------------------------------------===//
// Spill + fill
//===----------------------------------------------------------------------===//
defm LDR_ZA : sme_fill<"ldr">;
defm STR_ZA : sme_spill<"str">;
//===----------------------------------------------------------------------===//
// Move instructions
//===----------------------------------------------------------------------===//
defm INSERT_MXIPZ : sme_vector_to_tile<"mova">;
defm EXTRACT_ZPMXI : sme_tile_to_vector<"mova">;
//===----------------------------------------------------------------------===//
// Zero instruction
//===----------------------------------------------------------------------===//
defm ZERO_M : sme_zero<"zero">;
//===----------------------------------------------------------------------===//
// Mode selection and state access instructions
//===----------------------------------------------------------------------===//
// SME defines three pstate fields to set or clear PSTATE.SM, PSTATE.ZA, or
// both fields:
//
// MSR SVCRSM, #<imm1>
// MSR SVCRZA, #<imm1>
// MSR SVCRSMZA, #<imm1>
//
// It's tricky to using the existing pstate operand defined in
// AArch64SystemOperands.td since it only encodes 5 bits including op1;op2,
// when these fields are also encoded in CRm[3:1].
class MSRpstatesvcrImm0_1
: PstateWriteSimple<(ins svcr_op:$pstatefield, imm0_1:$imm), "msr",
"\t$pstatefield, $imm">,
Sched<[WriteSys]> {
bits<3> pstatefield;
bit imm;
let Inst{18-16} = 0b011; // op1
let Inst{11-9} = pstatefield;
let Inst{8} = imm;
let Inst{7-5} = 0b011; // op2
}
def MSRpstatesvcrImm1 : MSRpstatesvcrImm0_1;
def : InstAlias<"smstart", (MSRpstatesvcrImm1 0b011, 0b1)>;
def : InstAlias<"smstart sm", (MSRpstatesvcrImm1 0b001, 0b1)>;
def : InstAlias<"smstart za", (MSRpstatesvcrImm1 0b010, 0b1)>;
def : InstAlias<"smstop", (MSRpstatesvcrImm1 0b011, 0b0)>;
def : InstAlias<"smstop sm", (MSRpstatesvcrImm1 0b001, 0b0)>;
def : InstAlias<"smstop za", (MSRpstatesvcrImm1 0b010, 0b0)>;
//===----------------------------------------------------------------------===//
// SVE2 instructions
//===----------------------------------------------------------------------===//
def REVD_ZPmZ : sve2_int_perm_revd<"revd">;
defm SCLAMP_ZZZ : sve2_clamp<"sclamp", 0b0>;
defm UCLAMP_ZZZ : sve2_clamp<"uclamp", 0b1>;
defm DUP_PPzPRI : sve2_int_perm_dup_p<"dup">;
} // End let Predicates = [HasSME]