2a7ca101d7
Sparse-checkout from NVIDIA/cccl main branch to complete cccl_upstream: Added: - python/cuda_cccl/ (226 files) — Python bindings for device-level algorithms Critical for muh toolchain: cuda.compute.reduce_into, scan, radix_sort, etc. Includes 204 .py files with full test coverage for all 27 algorithms - ci/ (163 files) — Build/test infrastructure build_cub.sh, test_cub.sh, build_and_test_targets.sh, matrix.yaml Directly maps to our [INFRA-CI] and [INFRA-BUILD] items - .agent/skills/ (7 files) — NVIDIA's own agent skills for CCCL cccl-style/SKILL.md, cccl-test/SKILL.md, sass-diff/SKILL.md - docs/ (491 files) — Official CCCL documentation CI references, CMake guides, Python compute docs, libcudacxx PTX docs - test/ (12 files) — Top-level integration tests (cuda_smoke, stdpar) - Root configs: .clang-format, .clang-tidy, CONTRIBUTING.md, pyproject.toml - CLAUDE.md symlink → AGENTS.md (NVIDIA's standard) cccl_upstream now mirrors full NVIDIA/cccl structure: Before: 42M (cub + thrust + libcudacxx + cudax + c + examples + benchmarks) After: 53M (+python +ci +docs +.agent +test +configs) This completes the CCCL base needed for: - [muh-bench] items: ci/util/build_and_test_targets.sh for targeted builds - [CCCL-verify] items: python/cuda_cccl/tests/ as reference implementations - [CCCL-test] items: ci/test_cub.sh, ci/test_thrust.sh - Agent workflow: .agent/skills/ for consistent style and test patterns
81 lines
2.0 KiB
C++
81 lines
2.0 KiB
C++
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of CUDA C++ Core Libraries, under the Apache License v2.0 with
|
|
// LLVM Exceptions. See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
// SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include <cuda/version>
|
|
|
|
#include <algorithm>
|
|
#include <cstddef>
|
|
#include <execution>
|
|
#include <numeric>
|
|
#include <vector>
|
|
|
|
// Ensure that we are indeed using the correct CCCL version
|
|
static_assert(CCCL_MAJOR_VERSION == CMAKE_CCCL_VERSION_MAJOR);
|
|
static_assert(CCCL_MINOR_VERSION == CMAKE_CCCL_VERSION_MINOR);
|
|
static_assert(CCCL_PATCH_VERSION == CMAKE_CCCL_VERSION_PATCH);
|
|
|
|
int main()
|
|
{
|
|
constexpr std::size_t num_items = 1 << 16;
|
|
std::vector<int> values(num_items);
|
|
const std::vector<int> offsets(num_items, 5);
|
|
std::vector<int> output(num_items, 0);
|
|
std::iota(values.begin(), values.end(), 0);
|
|
|
|
constexpr auto double_value = [](const int value) {
|
|
return value * 2;
|
|
};
|
|
|
|
constexpr auto add_values = [](const int lhs, const int rhs) {
|
|
return lhs + rhs;
|
|
};
|
|
|
|
const auto unary_end =
|
|
std::transform(std::execution::par, values.begin(), values.end(), output.begin(), double_value);
|
|
|
|
if (unary_end != output.end())
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
for (std::size_t i = 0; i < num_items; ++i)
|
|
{
|
|
if (output[i] != values[i] * 2)
|
|
{
|
|
return 1;
|
|
}
|
|
}
|
|
|
|
const auto binary_end =
|
|
std::transform(std::execution::par, values.begin(), values.end(), offsets.begin(), output.begin(), add_values);
|
|
|
|
if (binary_end != output.end())
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
for (std::size_t i = 0; i < num_items; ++i)
|
|
{
|
|
if (output[i] != values[i] + offsets[i])
|
|
{
|
|
return 1;
|
|
}
|
|
}
|
|
|
|
const auto empty_end =
|
|
std::transform(std::execution::par, values.begin(), values.begin(), output.begin(), double_value);
|
|
|
|
if (empty_end != output.begin())
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|