Add CUDA testing of pFq

test/cuda_jamfile

@@ -9,8 +9,7 @@ project : requirements
     [ requires cxx14_decltype_auto cxx14_generic_lambdas cxx14_return_type_deduction cxx14_variable_templates cxx14_constexpr ]
     ;
 
-run test_2F0_double.cu ;
-run test_2F0_float.cu ;
+run test_pFq_double.cu ;
 
 # Quad
 run test_exp_sinh_quad_float.cu ;
@@ -367,6 +366,8 @@ run test_0F1_double.cu ;
 run test_0F1_float.cu ;
 run test_1F0_double.cu ;
 run test_1F0_float.cu ;
+run test_2F0_double.cu ;
+run test_2F0_float.cu ;
 
 run test_lgamma_double.cu ;
 run test_lgamma_float.cu ;

test/test_pFq_double.cu

@@ -0,0 +1,104 @@
+
+//  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)
+
+#include <iostream>
+#include <iomanip>
+#include <vector>
+#include <boost/math/special_functions.hpp>
+#include "cuda_managed_ptr.hpp"
+#include "stopwatch.hpp"
+
+// For the CUDA runtime routines (prefixed with "cuda_")
+#include <cuda_runtime.h>
+
+typedef double float_type;
+
+/**
+ * CUDA Kernel Device code
+ *
+ */
+__global__ void cuda_test(const float_type *in1, const float_type *in2, float_type *out, int numElements)
+{
+    using std::cos;
+    int i = blockDim.x * blockIdx.x + threadIdx.x;
+
+    if (i < numElements)
+    {
+        out[i] = boost::math::hypergeometric_pFq(std::initializer_list<float_type>({in1[i]}), std::initializer_list<float_type>({in2[i]}), static_cast<float_type>(1));
+    }
+}
+
+/**
+ * Host main routine
+ */
+int main(void)
+{
+    // 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 input vector B
+    cuda_managed_ptr<float_type> input_vector2(numElements);
+
+    // Allocate the managed output vector C
+    cuda_managed_ptr<float_type> output_vector(numElements);
+
+    // Initialize the input vectors
+    for (int i = 0; i < numElements; ++i)
+    {
+        input_vector1[i] = rand()/(float_type)RAND_MAX;
+        input_vector2[i] = rand()/(float_type)RAND_MAX;
+    }
+
+    // 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(), input_vector2.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 CUDA 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(boost::math::hypergeometric_pFq(std::initializer_list<float_type>({input_vector1[i]}), std::initializer_list<float_type>({input_vector2[i]}), static_cast<float_type>(1)));
+    double t = w.elapsed();
+    // check the results
+    for(int i = 0; i < numElements; ++i)
+    {
+        if (boost::math::epsilon_difference(output_vector[i], results[i]) > 10)
+        {
+            std::cerr << "Result verification failed at element " << i << "!" << std::endl;
+            return EXIT_FAILURE;
+        }
+    }
+
+    std::cout << "Test PASSED, normal calculation time: " << t << "s" << std::endl;
+    std::cout << "Done\n";
+
+    return 0;
+}

test/test_pFq_float.cu

@@ -0,0 +1,104 @@
+
+//  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)
+
+#include <iostream>
+#include <iomanip>
+#include <vector>
+#include <boost/math/special_functions.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, const float_type *in2, float_type *out, int numElements)
+{
+    using std::cos;
+    int i = blockDim.x * blockIdx.x + threadIdx.x;
+
+    if (i < numElements)
+    {
+        out[i] = boost::math::hypergeometric_pFq(std::initializer_list<float_type>({in1[i]}), std::initializer_list<float_type>({in2[i]}), static_cast<float_type>(1));
+    }
+}
+
+/**
+ * Host main routine
+ */
+int main(void)
+{
+    // 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 input vector B
+    cuda_managed_ptr<float_type> input_vector2(numElements);
+
+    // Allocate the managed output vector C
+    cuda_managed_ptr<float_type> output_vector(numElements);
+
+    // Initialize the input vectors
+    for (int i = 0; i < numElements; ++i)
+    {
+        input_vector1[i] = rand()/(float_type)RAND_MAX;
+        input_vector2[i] = rand()/(float_type)RAND_MAX;
+    }
+
+    // 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(), input_vector2.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 CUDA 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(boost::math::hypergeometric_pFq(std::initializer_list<float_type>({input_vector1[i]}), std::initializer_list<float_type>({input_vector2[i]}), static_cast<float_type>(1)));
+    double t = w.elapsed();
+    // check the results
+    for(int i = 0; i < numElements; ++i)
+    {
+        if (boost::math::epsilon_difference(output_vector[i], results[i]) > 10)
+        {
+            std::cerr << "Result verification failed at element " << i << "!" << std::endl;
+            return EXIT_FAILURE;
+        }
+    }
+
+    std::cout << "Test PASSED, normal calculation time: " << t << "s" << std::endl;
+    std::cout << "Done\n";
+
+    return 0;
+}