[all-commits] [llvm/llvm-project] 3264a5: [clang][NVPTX] Add builtins and intrinsics for con...

[Srinivasa Ravi via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 3264a50fe2b61e79572d1623d0cceb2fe88da533
      https://github.com/llvm/llvm-project/commit/3264a50fe2b61e79572d1623d0cceb2fe88da533
  Author: Srinivasa Ravi <srinivasar at nvidia.com>
  Date:   2025-04-16 (Wed, 16 Apr 2025)

  Changed paths:
    M clang/include/clang/Basic/BuiltinsNVPTX.td
    M clang/test/CodeGen/builtins-nvptx.c
    M llvm/include/llvm/IR/IntrinsicsNVVM.td
    M llvm/lib/Target/NVPTX/NVPTXInstrInfo.td
    M llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
    A llvm/test/CodeGen/NVPTX/convert-sm100a.ll

  Log Message:
  -----------
  [clang][NVPTX] Add builtins and intrinsics for conversions of new FP types (#134345)

This change:
- Adds NVVM intrinsics and clang builtins for the cvt instruction
variants of types (FP6) `.e2m3x2`, `.e3m2x2`, and (FP8) `.ue8m0x2`
introduced in PTX 8.6 for `sm_100a`, `sm_101a`, and `sm_120a`.
- Adds clang builtins for cvt instruction variant of type tf32.

Tests are added in `NVPTX/convert-sm100a.ll` and
`clang/test/CodeGen/builtins-nvptx.c` and verified through ptxas 12.8.0.

PTX Spec Reference:
https://docs.nvidia.com/cuda/parallel-thread-execution/#data-movement-and-conversion-instructions-cvt



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