mirror of
https://github.com/boostorg/math.git
synced 2025-05-11 21:33:52 +00:00
e9cd6c96fd
Add SYCL testing of normal dist Add CUDA testing of normal dist Add NVRTC testing of normal dist NVRTC fixes Move headers for NVRTC support Add GPU support to inverse gaussian dist Add NVRTC testing of inverse Gaussian dist Add CUDA testing of inverse gaussian dist Add SYCL testing of inverse gaussian dist Add GPU support to lognormal dist Add SYCL testing of lognormal dist Add CUDA testing of lognormal dist Add nvrtc testing of lognormal dist Add GPU support to negative binomial dist Avoid float_prior on GPU platform Add NVRTC testing of negative binomial dist Fix ambiguous use of nextafter Add CUDA testing of negative binomial dist Fix float_prior workaround Add SYCL testing of negative binomial dist Add GPU support to non_central_beta dist Add SYCL testing of nc beta dist Add CUDA testing of nc beta dist Enable generic dist handling on GPU Add GPU support to brent_find_minima Add NVRTC testing of nc beta dist Add utility header Replace non-functional macro with new function Add GPU support to non central chi squared dist Add SYCL testing of non central chi squared dist Add missing macro definition Markup generic quantile finder Add CUDA testing of non central chi squared dist Add NVRTC testing of non central chi squared dist Add GPU support to the non-central f dist Add SYCL testing of ncf Add CUDA testing of ncf dist Add NVRTC testing of ncf dist Add GPU support to students_t dist Add SYCL testing of students_t dist Add CUDA testing of students_t Add NVRTC testing of students_t dist Workaround for header cycle Add GPU support to pareto dist Add SYCL testing of pareto dist Add CUDA testing of pareto dist Add NVRTC testing of pareto dist Add missing header Add GPU support to poisson dist Add SYCL testing of poisson dist Add CUDA testing of poisson dist Add NVRTC testing of poisson dist Add forward decl for NVRTC platform Add GPU support to rayleigh dist Add CUDA testing of rayleigh dist Add SYCL testing of rayleigh dist Add NVRTC testing of rayleigh dist Add GPU support to triangular dist Add SYCL testing of triangular dist Add NVRTC testing of triangular dist Add CUDA testing of triangular dist Add GPU support to the uniform dist Add CUDA testing of uniform dist Add SYCL testing of uniform dist Add NVRTC testing of uniform dist Fix missing header Add markers to docs
114 lines
3.5 KiB
Plaintext
114 lines
3.5 KiB
Plaintext
// Copyright John Maddock 2016.
|
|
// Copyright Matt Borland 2024.
|
|
// Use, modification and distribution are subject to the
|
|
// Boost Software License, Version 1.0. (See accompanying file
|
|
// LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt)
|
|
|
|
#define BOOST_MATH_OVERFLOW_ERROR_POLICY ignore_error
|
|
|
|
#include <iostream>
|
|
#include <iomanip>
|
|
#include <vector>
|
|
#include <boost/math/distributions/triangular.hpp>
|
|
#include <boost/math/special_functions/relative_difference.hpp>
|
|
#include <boost/random/mersenne_twister.hpp>
|
|
#include <boost/random/uniform_real_distribution.hpp>
|
|
#include "cuda_managed_ptr.hpp"
|
|
#include "stopwatch.hpp"
|
|
|
|
// For the CUDA runtime routines (prefixed with "cuda_")
|
|
#include <cuda_runtime.h>
|
|
|
|
typedef float float_type;
|
|
|
|
/**
|
|
* CUDA Kernel Device code
|
|
*
|
|
*/
|
|
__global__ void cuda_test(const float_type *in1, float_type *out, int numElements)
|
|
{
|
|
using std::cos;
|
|
int i = blockDim.x * blockIdx.x + threadIdx.x;
|
|
|
|
if (i < numElements)
|
|
{
|
|
out[i] = cdf(boost::math::triangular_distribution<float_type>(1), in1[i]);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Host main routine
|
|
*/
|
|
int main(void)
|
|
{
|
|
try{
|
|
|
|
// Error code to check return values for CUDA calls
|
|
cudaError_t err = cudaSuccess;
|
|
|
|
// Print the vector length to be used, and compute its size
|
|
int numElements = 50000;
|
|
std::cout << "[Vector operation on " << numElements << " elements]" << std::endl;
|
|
|
|
// Allocate the managed input vector A
|
|
cuda_managed_ptr<float_type> input_vector1(numElements);
|
|
|
|
// Allocate the managed output vector C
|
|
cuda_managed_ptr<float_type> output_vector(numElements);
|
|
|
|
boost::random::mt19937 gen;
|
|
boost::random::uniform_real_distribution<float_type> dist;
|
|
// Initialize the input vectors
|
|
for (int i = 0; i < numElements; ++i)
|
|
{
|
|
input_vector1[i] = dist(gen);
|
|
}
|
|
|
|
// Launch the Vector Add CUDA Kernel
|
|
int threadsPerBlock = 256;
|
|
int blocksPerGrid =(numElements + threadsPerBlock - 1) / threadsPerBlock;
|
|
std::cout << "CUDA kernel launch with " << blocksPerGrid << " blocks of " << threadsPerBlock << " threads" << std::endl;
|
|
|
|
watch w;
|
|
cuda_test<<<blocksPerGrid, threadsPerBlock>>>(input_vector1.get(), output_vector.get(), numElements);
|
|
cudaDeviceSynchronize();
|
|
std::cout << "CUDA kernal done in " << w.elapsed() << "s" << std::endl;
|
|
|
|
err = cudaGetLastError();
|
|
if (err != cudaSuccess)
|
|
{
|
|
std::cerr << "Failed to launch vectorAdd kernel (error code " << cudaGetErrorString(err) << ")!" << std::endl;
|
|
return EXIT_FAILURE;
|
|
}
|
|
|
|
// Verify that the result vector is correct
|
|
std::vector<float_type> results;
|
|
results.reserve(numElements);
|
|
w.reset();
|
|
for(int i = 0; i < numElements; ++i)
|
|
results.push_back(cdf(boost::math::triangular_distribution<float_type>(1), input_vector1[i]));
|
|
double t = w.elapsed();
|
|
// check the results
|
|
for(int i = 0; i < numElements; ++i)
|
|
{
|
|
if (std::isfinite(results[i]))
|
|
{
|
|
if (boost::math::epsilon_difference(output_vector[i], results[i]) > 100.0)
|
|
{
|
|
std::cerr << "Result verification failed at element " << i << "!" << std::endl;
|
|
std::cerr << "Error rate was: " << boost::math::epsilon_difference(output_vector[i], results[i]) << "eps" << std::endl;
|
|
return EXIT_FAILURE;
|
|
}
|
|
}
|
|
}
|
|
|
|
std::cout << "Test PASSED with calculation time: " << t << "s" << std::endl;
|
|
std::cout << "Done\n";
|
|
}
|
|
catch(const std::exception& e)
|
|
{
|
|
std::cerr << "Stopped with exception: " << e.what() << std::endl;
|
|
}
|
|
return 0;
|
|
}
|