I have written a wrapper in C++11/CLI with Visual Studio to use CUDA’s CuBLAS. I am using CUDA Toolkit 7.0.
Here is the source code of my wrapper:
#pragma once
#include "stdafx.h"
#include "BLAS.h"
#include "cuBLAS.h"
namespace lab
{
namespace Mathematics
{
namespace CUDA
{
void BLAS::DAXPY(int n, double alpha, const array<double> ^x, int incx, array<double> ^y, int incy)
{
pin_ptr<double> xPtr = &(x[0]);
pin_ptr<double> yPtr = &(y[0]);
pin_ptr<double> alphaPtr = α
cuBLAS::DAXPY(n, alphaPtr, xPtr, incx, yPtr, incy);
}
}
}
}
To test this code, I wrote the following test in C#:
using System;
using Microsoft.VisualStudio.TestTools.UnitTesting;
using System.Linq;
using lab.Mathematics.CUDA;
namespace lab.Mathematics.CUDA.Test
{
[TestClass]
public class TestBLAS
{
[TestMethod]
public void TestDAXPY()
{
var count = 10;
var alpha = 1.0;
var a = Enumerable.Range(0, count).Select(x => Convert.ToDouble(x)).ToArray();
var b = Enumerable.Range(0, count).Select(x => Convert.ToDouble(x)).ToArray();
// Call CUDA
BLAS.DAXPY(count, alpha, a, 1, b, 1);
// Validate results
for (int i = 0; i < count; i++)
{
Assert.AreEqual(i + i, b[i]);
}
}
}
}
The program compiles with x64 architecture with no error. But the results I get are different every time I run the test. More precisely, the array b is the result and it has different values every time. And I don’t know why.
I am Also adding my cuda code maybe there, someone can find a problem. note that I don’t get any error, warning whatsoever while compiling. I am also wondering maybe I have to do some changes in the compilation while I did nothing and used the default options.
void cuBLAS::DAXPY(int n, const double *alpha, const double *x, int incx, double *y, int incy)
{
// Allocate GPU memory
double *devX, *devY;
cudaMalloc((void **)&devX, (size_t)n*sizeof(*devX));
cudaMalloc((void **)&devY, (size_t)n*sizeof(*devY));
// Create cuBLAS handle
cublasHandle_t handle;
cublasCreate(&handle);
// Initialize the input matrix and vector
cublasSetVector(n, sizeof(*devX), x, incx, devX, incx);
// Call cuBLAS function
cublasDaxpy(handle, n, alpha, devX, incx, devY, incy);
// Retrieve resulting vector
cublasGetVector(n, sizeof(*devY), devY, incy, y, incy);
// Free GPU resources
cudaFree(devX);
cudaFree(devY);
cublasDestroy(handle);
}