Google Git
Sign in
llvm/llvm-project/6e17b2ef33b84c41bfaa86711472ab4cc5a9829a
commit
6e17b2ef33b84c41bfaa86711472ab4cc5a9829a
[log]
author
albertbolt1 <45144020+albertbolt1@users.noreply.github.com>
Tue Mar 17 19:13:14 2026 +0530
committer
GitHub <noreply@github.com>
Tue Mar 17 13:43:14 2026 +0000
tree
4996639b667465eec9712209e5b1eb9841086bdb
parent
240bc0a7ad74698c293c133f981be09bf6b47d86 [diff]
[CIR][AArch64] Upstream NEON shift left builtins (#186406)

This PR adds CIR generation for the following AArch64 NEON builtins:

__builtin_neon_vshld_n_s64 and __builtin_neon_vshld_n_u64 (constant
shifts)

extracted the constant value and use it directly for shift left

__builtin_neon_vshld_s64  and __builtin_neon_vshld_u64 (variable shifts)
there is an existing function to handles SISD (SIngle Instruction Single
Data), reusing this to create the right CIR instructions


__builtin_neon_vshld_s64 -- call i64 @llvm.aarch64.neon.sshl.i64(i64
[[A]], i64 [[B]])
__builtin_neon_vshld_u64 -- call i64 @llvm.aarch64.neon.ushl.i64(i64
[[A]], i64 [[B]])

added test cases in intrinsics.c by looking at the test cases present in

https://github.com/llvm/llvm-project/blob/main/clang/test/CodeGen/AArch64/neon-shifts.c

before adding the code it gave a not implemented error and after adding
the code changes the error is not present the code succeeds.


ran the test cases using 
```
bin/llvm-lit -v  \
  /Users/albertbolt/projects/llvm-project/clang/test/CodeGen/AArch64/neon/intrinsics.c
```

#185382

---------

Co-authored-by: Andrzej Warzyński <andrzej.warzynski@gmail.com>
3 files changed
tree: 4996639b667465eec9712209e5b1eb9841086bdb
  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. libsycl/
  16. libunwind/
  17. lld/
  18. lldb/
  19. llvm/
  20. llvm-libgcc/
  21. mlir/
  22. offload/
  23. openmp/
  24. orc-rt/
  25. polly/
  26. runtimes/
  27. third-party/
  28. utils/
  29. .clang-format
  30. .clang-format-ignore
  31. .clang-tidy
  32. .git-blame-ignore-revs
  33. .gitattributes
  34. .gitignore
  35. .mailmap
  36. CODE_OF_CONDUCT.md
  37. CONTRIBUTING.md
  38. LICENSE.TXT
  39. pyproject.toml
  40. README.md
  41. 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.