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
59 lines
1.6 KiB
C++
59 lines
1.6 KiB
C++
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of the LLVM Project, 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
#ifndef SUPPORT_FP_COMPARE_H
|
|
#define SUPPORT_FP_COMPARE_H
|
|
|
|
#include <cuda/std/algorithm> // for cuda::std::max
|
|
#include <cuda/std/cassert>
|
|
#include <cuda/std/cmath> // for cuda::std::abs
|
|
|
|
#include "test_macros.h"
|
|
// See
|
|
// https://www.boost.org/doc/libs/1_70_0/libs/test/doc/html/boost_test/testing_tools/extended_comparison/floating_point/floating_points_comparison_theory.html
|
|
|
|
template <typename T>
|
|
TEST_FUNC bool fptest_close(T val, T expected, T eps)
|
|
{
|
|
constexpr T zero = T(0);
|
|
assert(eps >= zero);
|
|
|
|
// Handle the zero cases
|
|
if (eps == zero)
|
|
{
|
|
return val == expected;
|
|
}
|
|
if (val == zero)
|
|
{
|
|
return cuda::std::abs(expected) <= eps;
|
|
}
|
|
if (expected == zero)
|
|
{
|
|
return cuda::std::abs(val) <= eps;
|
|
}
|
|
|
|
return cuda::std::abs(val - expected) < eps && cuda::std::abs(val - expected) / cuda::std::abs(val) < eps;
|
|
}
|
|
|
|
template <typename T>
|
|
TEST_FUNC bool fptest_close_pct(T val, T expected, T percent)
|
|
{
|
|
constexpr T zero = T(0);
|
|
assert(percent >= zero);
|
|
|
|
// Handle the zero cases
|
|
if (percent == zero)
|
|
{
|
|
return val == expected;
|
|
}
|
|
T eps = (percent / T(100)) * cuda::std::max(cuda::std::abs(val), cuda::std::abs(expected));
|
|
|
|
return fptest_close(val, expected, eps);
|
|
}
|
|
|
|
#endif // SUPPORT_FP_COMPARE_H
|