[all-commits] [llvm/llvm-project] 3eacda: [AArch64] Add all SME2.1 instructions Assembly/Dis...

Mon Nov 14 06:57:00 PST 2022

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 3eacda4547c59c3daa2daf275321c8013eb485cd
      https://github.com/llvm/llvm-project/commit/3eacda4547c59c3daa2daf275321c8013eb485cd
  Author: Caroline Concatto <caroline.concatto at arm.com>
  Date:   2022-11-14 (Mon, 14 Nov 2022)

  Changed paths:
    M llvm/include/llvm/Support/AArch64TargetParser.def
    M llvm/include/llvm/Support/AArch64TargetParser.h
    M llvm/lib/Target/AArch64/AArch64.td
    M llvm/lib/Target/AArch64/AArch64InstrInfo.td
    M llvm/lib/Target/AArch64/AArch64RegisterInfo.td
    M llvm/lib/Target/AArch64/AArch64SMEInstrInfo.td
    M llvm/lib/Target/AArch64/AArch64SchedA64FX.td
    M llvm/lib/Target/AArch64/AsmParser/AArch64AsmParser.cpp
    M llvm/lib/Target/AArch64/SMEInstrFormats.td
    M llvm/test/MC/AArch64/SME2/fmla-diagnostics.s
    M llvm/test/MC/AArch64/SME2/fmls-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/bfadd-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/bfadd.s
    A llvm/test/MC/AArch64/SME2p1/bfclamp-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/bfclamp.s
    A llvm/test/MC/AArch64/SME2p1/bfmax-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/bfmax.s
    A llvm/test/MC/AArch64/SME2p1/bfmaxnm-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/bfmaxnm.s
    A llvm/test/MC/AArch64/SME2p1/bfmin-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/bfmin.s
    A llvm/test/MC/AArch64/SME2p1/bfminnm-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/bfminnm.s
    A llvm/test/MC/AArch64/SME2p1/bfmla-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/bfmla.s
    A llvm/test/MC/AArch64/SME2p1/bfmls-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/bfmls.s
    A llvm/test/MC/AArch64/SME2p1/bfmopa-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/bfmopa.s
    A llvm/test/MC/AArch64/SME2p1/bfmops-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/bfmops.s
    A llvm/test/MC/AArch64/SME2p1/bfsub-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/bfsub.s
    A llvm/test/MC/AArch64/SME2p1/fadd-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/fadd.s
    A llvm/test/MC/AArch64/SME2p1/fcvt-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/fcvt.s
    A llvm/test/MC/AArch64/SME2p1/fcvtl-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/fcvtl.s
    A llvm/test/MC/AArch64/SME2p1/fmla-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/fmla.s
    A llvm/test/MC/AArch64/SME2p1/fmls-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/fmls.s
    A llvm/test/MC/AArch64/SME2p1/fmopa-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/fmopa.s
    A llvm/test/MC/AArch64/SME2p1/fmops-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/fmops.s
    A llvm/test/MC/AArch64/SME2p1/fsub-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/fsub.s
    A llvm/test/MC/AArch64/SME2p1/luti2-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/luti2.s
    A llvm/test/MC/AArch64/SME2p1/luti4-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/luti4.s
    A llvm/test/MC/AArch64/SME2p1/movaz-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/movaz.s
    A llvm/test/MC/AArch64/SME2p1/zero-diagnostics.s
    A llvm/test/MC/AArch64/SME2p1/zero.s
    M llvm/unittests/Support/TargetParserTest.cpp

  Log Message:
  -----------
  [AArch64] Add all SME2.1 instructions Assembly/Disassembly

This patch adds a new feature flag:
sme-f16f16 to represent FEAT_SME-F16F16

This patch add the following instructions:
SME2.1 stand alone instructions:
   MOVAZ (array to vector, four registers): Move and zero four ZA single-vector groups to vector registers.
         (array to vector, two registers): Move and zero two ZA single-vector groups to vector registers.
         (tile to vector, four registers): Move and zero four ZA tile slices to vector registers.
         (tile to vector, single): Move and zero ZA tile slice to vector register.
         (tile to vector, two registers): Move and zero two ZA tile slices to vector registers.

   LUTI2 (Strided four registers): Lookup table read with 2-bit indexes.
         (Strided two registers): Lookup table read with 2-bit indexes.

   LUTI4 (Strided four registers): Lookup table read with 4-bit indexes.
         (Strided two registers): Lookup table read with 4-bit indexes.

   ZERO (double-vector): Zero ZA double-vector groups.
        (quad-vector): Zero ZA quad-vector groups.
        (single-vector): Zero ZA single-vector groups.

SME2p1 and SME-F16F16:
 All instructions are half precision elements:
   FADD: Floating-point add multi-vector to ZA array vector accumulators.

   FSUB: Floating-point subtract multi-vector from ZA array vector accumulators.

   FMLA (multiple and indexed vector): Multi-vector floating-point fused multiply-add by indexed element.
        (multiple and single vector): Multi-vector floating-point fused multiply-add by vector.
        (multiple vectors): Multi-vector floating-point fused multiply-add.

   FMLS (multiple and indexed vector): Multi-vector floating-point fused multiply-subtract by indexed element.
        (multiple and single vector): Multi-vector floating-point fused multiply-subtract by vector.
        (multiple vectors): Multi-vector floating-point fused multiply-subtract.

   FCVT (widening): Multi-vector floating-point convert from half-precision to single-precision (in-order).

   FCVTL: Multi-vector floating-point convert from half-precision to deinterleaved single-precision.

   FMOPA (non-widening): Floating-point outer product and accumulate.

   FMOPS (non-widening): Floating-point outer product and subtract.

SME2p1 and B16B16:
   BFADD: BFloat16 floating-point add multi-vector to ZA array vector accumulators.

   BFSUB: BFloat16 floating-point subtract multi-vector from ZA array vector accumulators.

   BFCLAMP: Multi-vector BFloat16 floating-point clamp to minimum/maximum number.

   BFMLA (multiple and indexed vector): Multi-vector BFloat16 floating-point fused multiply-add by indexed element.
         (multiple and single vector): Multi-vector BFloat16 floating-point fused multiply-add by vector.
         (multiple vectors): Multi-vector BFloat16 floating-point fused multiply-add.

   BFMLS (multiple and indexed vector): Multi-vector BFloat16 floating-point fused multiply-subtract by indexed element.
         (multiple and single vector): Multi-vector BFloat16 floating-point fused multiply-subtract by vector.
         (multiple vectors): Multi-vector BFloat16 floating-point fused multiply-subtract.

   BFMAX (multiple and single vector): Multi-vector BFloat16 floating-point maximum by vector.
         (multiple vectors): Multi-vector BFloat16 floating-point maximum.

   BFMAXNM (multiple and single vector): Multi-vector BFloat16 floating-point maximum number by vector.
           (multiple vectors): Multi-vector BFloat16 floating-point maximum number.

   BFMIN (multiple and single vector): Multi-vector BFloat16 floating-point minimum by vector.
         (multiple vectors): Multi-vector BFloat16 floating-point minimum.

   BFMINNM (multiple and single vector): Multi-vector BFloat16 floating-point minimum number by vector.
           (multiple vectors): Multi-vector BFloat16 floating-point minimum number.

   BFMOPA (non-widening): BFloat16 floating-point outer product and accumulate.

   BFMOPS (non-widening): BFloat16 floating-point outer product and subtract.

The reference can be found here:

https://developer.arm.com/documentation/ddi0602/2022-09

Differential Revision: https://reviews.llvm.org/D137571