[RISCV][Codegen] Account for LMUL in Vector Mask instructions
authorMichael Maitland <michaeltmaitland@gmail.com>
Thu, 3 Nov 2022 17:44:10 +0000 (10:44 -0700)
committerMichael Maitland <michaeltmaitland@gmail.com>
Tue, 6 Dec 2022 14:48:42 +0000 (06:48 -0800)
commite2b44258482a56e8c3f7dbd961c2ab05a07ed143
tree131ba1814c7e2a1275577b7fc2402f58d1b87504
parentfef73b81e9a742c4db61ded747c801e3717dae78
[RISCV][Codegen] Account for LMUL in Vector Mask instructions

It is likley that subtargets act differently for vector fixed-point arithmetic instructions based on the LMUL.
This patch creates seperate SchedRead, SchedWrite, WriteRes, ReadAdvance for each relevant LMUL.

Differential Revision: https://reviews.llvm.org/D137427
llvm/lib/Target/RISCV/RISCVInstrInfoV.td
llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
llvm/lib/Target/RISCV/RISCVScheduleV.td