[PATCH] D97842: [RISCV] Preserve fixed-length VL on insert_vector_elt in more cases

[Fraser Cormack via Phabricator via llvm-commits]

frasercrmck created this revision.
frasercrmck added reviewers: craig.topper, evandro, rogfer01, HsiangKai, khchen, arcbbb.
Herald added subscribers: vkmr, luismarques, apazos, sameer.abuasal, s.egerton, Jim, benna, psnobl, jocewei, PkmX, the_o, brucehoult, MartinMosbeck, edward-jones, zzheng, jrtc27, shiva0217, kito-cheng, niosHD, sabuasal, simoncook, johnrusso, rbar, asb, hiraditya.
frasercrmck requested review of this revision.
Herald added subscribers: llvm-commits, MaskRay.
Herald added a project: LLVM.

This patch fixes up one case where the fixed-length-vector VL was
dropped (falling back to VLMAX) when inserting vector elements, as the
code would lower via ISD::INSERT_VECTOR_ELT (at index 0) which loses the
fixed-length vector information.

To this end, a custom node, VMV_S_XF_VL, was introduced to carry the VL
operand through to the final instruction. This node wraps the RVV
vmv.s.x and vmv.s.f instructions, which were being selected by
insert_vector_elt anyway.

There should be no observable difference in scalable-vector codegen.

There is still one outstanding drop from fixed-length VL to VLMAX, when
an i64 element is inserted into a vector on RV32; the splat (which is
custom legalized) has no notion of the original fixed-length vector
type.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D97842

Files:
  llvm/lib/Target/RISCV/RISCVISelLowering.cpp
  llvm/lib/Target/RISCV/RISCVISelLowering.h
  llvm/lib/Target/RISCV/RISCVInstrInfoVSDPatterns.td
  llvm/lib/Target/RISCV/RISCVInstrInfoVVLPatterns.td
  llvm/test/CodeGen/RISCV/rvv/fixed-vectors-insert.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D97842.327719.patch
Type: text/x-patch
Size: 9733 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210303/3965bd8f/attachment.bin>