[all-commits] [llvm/llvm-project] 482a77: [DAG] visitCLMUL - fold (clmul x, c_pow2) -> (shl ...

[fbrv via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 482a7718a8d8376b56e9dad7432624c1491ee1e6
      https://github.com/llvm/llvm-project/commit/482a7718a8d8376b56e9dad7432624c1491ee1e6
  Author: fbrv <Fabio.Baravalle at gmail.com>
  Date:   2026-03-02 (Mon, 02 Mar 2026)

  Changed paths:
    M llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
    M llvm/test/CodeGen/RISCV/combine-clmul.ll
    M llvm/test/CodeGen/X86/combine-clmul.ll

  Log Message:
  -----------
  [DAG] visitCLMUL - fold (clmul x, c_pow2) -> (shl x, log2(c_pow2)) (#184049)

Implements the missing basic folds for `ISD::CLMUL` in `visitCLMUL`:
 - `(clmul x, 1)` → `x` 
 - `(clmul x, c_pow2)` → `(shl x, log2(c_pow2))`

These were previously only folded during scalar expansion
(`expandCLMUL`), so targets with native CLMUL support (e.g. X86 pclmul,
RISCV Zbc) never had the opportunity to simplify these cases.

Fixes #181831



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