[all-commits] [llvm/llvm-project] 1ecffd: [libc] Add Kernel Resource Usage to nvptx-loader (...

[jameshu15869 via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 1ecffdaf27cb456aecc5a1c0272d3994d26bf645
      https://github.com/llvm/llvm-project/commit/1ecffdaf27cb456aecc5a1c0272d3994d26bf645
  Author: jameshu15869 <55058507+jameshu15869 at users.noreply.github.com>
  Date:   2024-07-17 (Wed, 17 Jul 2024)

  Changed paths:
    M libc/benchmarks/gpu/CMakeLists.txt
    M libc/cmake/modules/LLVMLibCTestRules.cmake
    M libc/utils/gpu/loader/Loader.h
    M libc/utils/gpu/loader/Main.cpp
    M libc/utils/gpu/loader/amdgpu/Loader.cpp
    M libc/utils/gpu/loader/nvptx/Loader.cpp

  Log Message:
  -----------
  [libc] Add Kernel Resource Usage to nvptx-loader (#97503)

This PR allows `nvptx-loader` to read the resource usage of `_start`,
`_begin`, and `_end` when executing CUDA binaries.

Example output:
```
$ nvptx-loader --print-resource-usage libc/benchmarks/gpu/src/ctype/libc.benchmarks.gpu.src.ctype.isalnum_benchmark.__build__
[ RUN      ] LlvmLibcIsAlNumGpuBenchmark.IsAlnumWrapper
[       OK ] LlvmLibcIsAlNumGpuBenchmark.IsAlnumWrapper: 93 cycles, 76 min, 470 max, 23 iterations, 78000 ns, 80 stddev
_begin registers: 25
_start registers: 80
_end registers: 62
  ```

---------

Co-authored-by: Joseph Huber <huberjn at outlook.com>



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