CCCL (CUDA C++ Core Libraries) provides: - CUB: device/block/warp-level GPU primitives (reduce, scan, sort, topk) - Thrust: high-level parallel algorithms (transform_reduce, sort, scan) - libcudacxx: CUDA C++ standard library (atomics, barriers, memory) - cudax: experimental features (memory resources, allocators) - Tuning policies: per-SM hardware-specific algorithm parameters Competition optimization vectors mapped to CCCL: - Output TPS (83% weight): warp_reduce, block_reduce, device_topk - Input TPS (14% weight): device_scan, block_load, prefetch - Cache TPS (3% weight): prefix caching strategy patterns - Memory (0.9 util): pooled/cached/buddy allocators Source: https://github.com/NVIDIA/cccl (shallow clone, HEAD only) License: Apache-2.0
30 lines
1.3 KiB
Plaintext
30 lines
1.3 KiB
Plaintext
//===---------------------------------------------------------------------===//
|
|
// Notes relating to various libc++ tasks
|
|
//===---------------------------------------------------------------------===//
|
|
|
|
This file contains notes about various libc++ tasks and processes.
|
|
|
|
//===---------------------------------------------------------------------===//
|
|
// Post-Release TODO
|
|
//===---------------------------------------------------------------------===//
|
|
|
|
These notes contain a list of things that must be done after branching for
|
|
an LLVM release.
|
|
|
|
1. Update _LIBCUDACXX_VERSION in `__config`
|
|
2. Update the __cccl_version file.
|
|
3. Update the version number in `docs/conf.py`
|
|
4. Create ABI lists for the previous release under `lib/abi`
|
|
|
|
//===---------------------------------------------------------------------===//
|
|
// Adding a new header TODO
|
|
//===---------------------------------------------------------------------===//
|
|
|
|
These notes contain a list of things that must be done upon adding a new header
|
|
to libc++.
|
|
|
|
1. Add a test under `test/libcxx` that the header defines `_LIBCUDACXX_VERSION`.
|
|
2. Update `test/libcxx/double_include.sh.cpp` to include the new header.
|
|
3. Create a submodule in `include/module.modulemap` for the new header.
|
|
4. Update the include/CMakeLists.txt file to include the new header.
|