[all-commits] [llvm/llvm-project] 3140a6: [IR] Allow vector atomicrmw xchg (#208510)

[Yonah Goldberg via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 3140a6478c782dcf9e26dbaedb7dd684be571bdf
      https://github.com/llvm/llvm-project/commit/3140a6478c782dcf9e26dbaedb7dd684be571bdf
  Author: Yonah Goldberg <ygoldberg at nvidia.com>
  Date:   2026-07-22 (Wed, 22 Jul 2026)

  Changed paths:
    M llvm/docs/LangRef.md
    M llvm/include/llvm/CodeGen/TargetLowering.h
    M llvm/lib/AsmParser/LLParser.cpp
    M llvm/lib/CodeGen/AtomicExpandPass.cpp
    M llvm/lib/IR/Verifier.cpp
    M llvm/test/Assembler/atomic.ll
    R llvm/test/Assembler/invalid-atomicrmw-xchg-fp-vector.ll
    A llvm/test/Assembler/invalid-atomicrmw-xchg.ll
    M llvm/test/Bitcode/compatibility.ll
    M llvm/test/Transforms/AtomicExpand/Mips/atomicrmw-vector.ll
    M llvm/unittests/IR/VerifierTest.cpp

  Log Message:
  -----------
  [IR] Allow vector atomicrmw xchg (#208510)

Previously, we only allowed vector `atomicrmw xchg` for `elementwise`
`atomicrmw`. Relax this restriction. By default, expand these by casting
to integer.

This is a follow-up on: https://github.com/llvm/llvm-project/pull/190716

Assisted by AI.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications