56fd68e7dd
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
90 lines
2.3 KiB
TOML
90 lines
2.3 KiB
TOML
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
#
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
[workspace]
|
|
channels = ["conda-forge"]
|
|
platforms = ["linux-64"]
|
|
channel-priority = "disabled"
|
|
|
|
# CUDA 13.1 system requirement
|
|
[feature.cu13.system-requirements]
|
|
cuda = "13"
|
|
|
|
[feature.cu13.dependencies]
|
|
cuda-version = "13.1.*"
|
|
|
|
# Python benchmark dependencies
|
|
[feature.bench.dependencies]
|
|
python = "3.13.*"
|
|
numpy = "*"
|
|
cupy = "*"
|
|
pytest-benchmark = "*"
|
|
pyyaml = "*"
|
|
pre-commit = "*"
|
|
|
|
[feature.bench.pypi-dependencies]
|
|
cuda-bench = ">=0.2.0"
|
|
|
|
# C++ benchmark build dependencies
|
|
[feature.cpp-bench.dependencies]
|
|
cmake = "*"
|
|
ninja = "*"
|
|
cxx-compiler = "*"
|
|
fmt = "*"
|
|
cuda-cudart-dev = "*"
|
|
|
|
[feature.cpp-bench.target.linux-64.dependencies]
|
|
cuda-crt-dev_linux-64 = "*"
|
|
cuda-driver-dev_linux-64 = "*"
|
|
|
|
[feature.cpp-bench.target.linux-64.activation.env]
|
|
CUDA_HOME = "$CONDA_PREFIX/targets/x86_64-linux"
|
|
|
|
# Important: cuda-cccl installation variants
|
|
|
|
# Released version from PyPI
|
|
[feature.cccl-wheel.pypi-dependencies]
|
|
cuda-cccl = { version = ">=0.1.0", extras = ["cu13"] }
|
|
|
|
# Local source build (editable install from repo)
|
|
# Needs nvcc, compilers, and CUDA dev libraries for scikit-build-core to build cuda-cccl
|
|
[feature.cccl-source.dependencies]
|
|
cuda-nvcc = "*"
|
|
cuda-nvrtc-dev = "*"
|
|
libnvjitlink-dev = "*"
|
|
cuda-cudart-dev = "*"
|
|
cuda-driver-dev = "*"
|
|
c-compiler = "*"
|
|
cxx-compiler = "*"
|
|
|
|
[feature.cccl-source.pypi-dependencies]
|
|
cuda-cccl = { path = "../..", editable = true, extras = ["cu13"] }
|
|
|
|
# Environments
|
|
[environments]
|
|
wheel = { features = ["cu13", "bench", "cpp-bench", "cccl-wheel"] }
|
|
source = { features = ["cu13", "bench", "cpp-bench", "cccl-source"] }
|
|
|
|
# Tasks
|
|
[tasks.bench]
|
|
cmd = ["python", "run_benchmarks.py", "--py"]
|
|
description = "Run Python cuda.compute benchmarks"
|
|
|
|
[tasks.bench-quick]
|
|
cmd = ["python", "run_benchmarks.py", "--py", "--quick"]
|
|
description = "Run Python benchmarks with reduced parameter set"
|
|
|
|
[tasks.bench-cpp]
|
|
cmd = ["python", "run_benchmarks.py", "--cpp"]
|
|
description = "Run C++ CUB benchmarks"
|
|
|
|
[tasks.bench-all]
|
|
cmd = ["python", "run_benchmarks.py"]
|
|
description = "Run both Python and C++ benchmarks"
|
|
|
|
[tasks.pre-commit]
|
|
cmd = ["pre-commit", "run", "--all-files"]
|
|
cwd = "../../../.."
|
|
description = "Run pre-commit checks on the entire repo"
|