[PATCH] D129308: [mlir] Remove VectorToROCDL

[Krzysztof Drewniak via Phabricator via cfe-commits]

krzysz00 created this revision.
Herald added subscribers: bzcheeseman, kosarev, sdasgup3, wenzhicui, wrengr, dcaballe, cota, teijeong, rdzhabarov, tatianashp, msifontes, jurahul, Kayjukh, grosul1, Joonsoo, liufengdb, aartbik, mgester, arpith-jacob, csigg, antiagainst, shauheen, rriddle, mehdi_amini, tpr, mgorny.
Herald added a reviewer: aartbik.
Herald added a reviewer: ThomasRaoux.
Herald added a project: All.
krzysz00 requested review of this revision.
Herald added subscribers: cfe-commits, stephenneuendorffer, nicolasvasilache.
Herald added a reviewer: herhut.
Herald added projects: clang, MLIR.

Between issues such as
https://github.com/llvm/llvm-project/issues/56323, the fact that this
lowering (unlike the code in amdgpu-to-rocdl) does not correctly set
up bounds checks (and thus will cause page faults on reads that might
need to be padded instead), and that fixing these problems would,
essentially, involve replicating amdgpu-to-rocdl, remove
--vector-to-rocdl for being broken. In addition, the lowering does not
support many aspects of transfer_{read,write}, like supervectors, and
may not work correctly in their presence.

We (the MLIR-based convolution generator at AMD) do not use this
conversion pass, nor are we aware of any other clients.

Migration strategies:

- Use VectorToLLVM
- If buffer ops are particularly needed in your application, use

amdgpu.raw_buffer_{load,store}

A VectorToAMDGPU pass may be introduced in the future.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D129308

Files:
  clang/docs/ClangFormattedStatus.rst
  clang/docs/tools/clang-formatted-files.txt
  mlir/include/mlir/Conversion/Passes.h
  mlir/include/mlir/Conversion/Passes.td
  mlir/include/mlir/Conversion/VectorToROCDL/VectorToROCDL.h
  mlir/lib/Conversion/CMakeLists.txt
  mlir/lib/Conversion/GPUToROCDL/CMakeLists.txt
  mlir/lib/Conversion/GPUToROCDL/LowerGpuOpsToROCDLOps.cpp
  mlir/lib/Conversion/VectorToROCDL/CMakeLists.txt
  mlir/lib/Conversion/VectorToROCDL/VectorToROCDL.cpp
  mlir/test/Conversion/VectorToROCDL/vector-to-rocdl.mlir
  mlir/test/Integration/GPU/ROCM/vector-transferops.mlir
  utils/bazel/llvm-project-overlay/mlir/BUILD.bazel

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D129308.442984.patch
Type: text/x-patch
Size: 22307 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20220707/2cc875bb/attachment-0001.bin>