Google Git
Sign in
llvm / llvm-project / 7e64ade2ef1af72db235f6d76ecd319abc09690e
commit7e64ade2ef1af72db235f6d76ecd319abc09690e[log] [tgz]
authorPhilip Reames <preames@rivosinc.com>Fri May 09 08:09:46 2025 -0700
committerGitHub <noreply@github.com>Fri May 09 08:09:46 2025 -0700
tree2d2678e05d317a1a72b0ed50e6391a24b62bafc8
parent20d6def0ae45b0c7ebcc1627d299689fa34e8cc8 [diff]
[RISCV] Extend zvqdot matching to handle reduction trees (#138965)

Now that we have matching for vqdot in it's basic variants, we can
extend the matcher to handle reduction trees instead of individual
reductions. This is important as we canonicalize reductions by
performing a tree in the vector domain before the root reduction
instruction.

The particular approach taken here has the unfortunate implication that
non-matches visit the entire reduction tree once for each time the
reduction root is visited in DAG. While conceptually problematic for
compile time, this is probably fine in practice as we should only visit
the root once per pass of DAGCombine. I don't really see a better
solution - suggestions welcome.

---------

Co-authored-by: Luke Lau <luke_lau@icloud.com>
2 files changed
tree: 2d2678e05d317a1a72b0ed50e6391a24b62bafc8
  1. .ci/
  2. .github/
  3. bolt/
  4. clang/
  5. clang-tools-extra/
  6. cmake/
  7. compiler-rt/
  8. cross-project-tests/
  9. flang/
  10. flang-rt/
  11. libc/
  12. libclc/
  13. libcxx/
  14. libcxxabi/
  15. libunwind/
  16. lld/
  17. lldb/
  18. llvm/
  19. llvm-libgcc/
  20. mlir/
  21. offload/
  22. openmp/
  23. polly/
  24. pstl/
  25. runtimes/
  26. third-party/
  27. utils/
  28. .clang-format
  29. .clang-format-ignore
  30. .clang-tidy
  31. .git-blame-ignore-revs
  32. .gitattributes
  33. .gitignore
  34. .mailmap
  35. CODE_OF_CONDUCT.md
  36. CONTRIBUTING.md
  37. LICENSE.TXT
  38. pyproject.toml
  39. README.md
  40. SECURITY.md
README.md

The LLVM Compiler Infrastructure

OpenSSF Scorecard OpenSSF Best Practices libc++

Welcome to the LLVM project!

This repository contains the source code for LLVM, a toolkit for the construction of highly optimized compilers, optimizers, and run-time environments.

The LLVM project has multiple components. The core of the project is itself called “LLVM”. This contains all of the tools, libraries, and header files needed to process intermediate representations and convert them into object files. Tools include an assembler, disassembler, bitcode analyzer, and bitcode optimizer.

C-like languages use the Clang frontend. This component compiles C, C++, Objective-C, and Objective-C++ code into LLVM bitcode -- and from there into object files, using LLVM.

Other components include: the libc++ C++ standard library, the LLD linker, and more.

Getting the Source Code and Building LLVM

Consult the Getting Started with LLVM page for information on building and running LLVM.

For information on how to contribute to the LLVM project, please take a look at the Contributing to LLVM guide.

Getting in touch

Join the LLVM Discourse forums, Discord chat, LLVM Office Hours or Regular sync-ups.

The LLVM project has adopted a code of conduct for participants to all modes of communication within the project.