[PATCH] D143277: [SME2][AArch64] Add multi-multi multiply-add long long intrinsics

[Kerry McLaughlin via Phabricator via llvm-commits]

kmclaughlin added inline comments.


================
Comment at: llvm/lib/Target/AArch64/SMEInstrFormats.td:2816
 
 multiclass sme2_mla_ll_array_vg2_multi<string mnemonic, bits<4> op,
                                        MatrixOperand matrix_ty,
----------------
david-arm wrote:
> Again, same suggestion as here https://reviews.llvm.org/D143276#inline-1386660, but feel free to ignore this if it doesn't make it any better!
I think in this case it will not reduce much because the VG2 & VG4 instructions have to use separate classes (`sme2_mla_ll_array_vg2_multi` and `sme2_mla_ll_array_vg4_multi`)?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D143277/new/

https://reviews.llvm.org/D143277