[all-commits] [llvm/llvm-project] 812e02: [NVPTX] Use fast-math flags when lowering sin, cos...

[Alex MacLean via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 812e02a74c0afb8bce8bf7ac7cc606ace188e30d
      https://github.com/llvm/llvm-project/commit/812e02a74c0afb8bce8bf7ac7cc606ace188e30d
  Author: Alex MacLean <amaclean at nvidia.com>
  Date:   2025-03-28 (Fri, 28 Mar 2025)

  Changed paths:
    M llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
    M llvm/lib/Target/NVPTX/NVPTXInstrInfo.td
    M llvm/test/CodeGen/NVPTX/f16-instructions.ll
    M llvm/test/CodeGen/NVPTX/f16x2-instructions.ll
    M llvm/test/CodeGen/NVPTX/fast-math.ll
    A llvm/test/CodeGen/NVPTX/frem.ll

  Log Message:
  -----------
  [NVPTX] Use fast-math flags when lowering sin, cos, frem (#133121)

Update the lowering rules for sin, cos, and frem to respect the
instruction-level flags in addition to the global and function-level
options. For sin and cos, the TableGen lowering has been updated to
check the `afn` flag on the node. The lowering for frem has been pulled
to custom instruction legalization in order to allow for DAG Combiner
optimizations to operate over the expanded instructions.



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