public static void ConjugateGradient(FloatResidentArray X, SparseMatrix A, FloatResidentArray B, int maxiter, float eps)
{
int N = (int)B.Count;
FloatResidentArray R = new FloatResidentArray(N);
FloatResidentArray P = new FloatResidentArray(N);
FloatResidentArray AP = new FloatResidentArray(N);
A.RefreshDevice();
X.RefreshDevice();
B.RefreshDevice();
wrapper.Fmsub(R, B, A, X, N); // R = B - A*X
wrapper.Copy(P, R, N);
int k = 0;
while (k < maxiter)
{
wrapper.Multiply(AP, A, P, N); // AP = A*P
float r = ScalarProd(R, R, N); // save <R|R>
float alpha = r / ScalarProd(P, AP, N); // alpha = <R|R> / <P|AP>
wrapper.Saxpy(X, X, alpha, P, N); // X = X - alpha*P
wrapper.Saxpy(R, R, -alpha, AP, N); // RR = R-alpha*AP
float rr = ScalarProd(R, R, N);
if (rr < eps * eps)
{
break;
}
float beta = rr / r;
wrapper.Saxpy(P, R, beta, P, N); // P = R + beta*P
++k;
}
X.RefreshHost();
}
static void Main(string[] args)
{
const int N = 1024 * 1024 * 32;
FloatResidentArray arr = new FloatResidentArray(N);
float[] res = new float[1];
for (int i = 0; i < N; ++i)
{
arr[i] = 1.0F;
}
arr.RefreshDevice();
var runner = HybRunner.Cuda();
cudaDeviceProp prop;
cuda.GetDeviceProperties(out prop, 0);
runner.SetDistrib(16 * prop.multiProcessorCount, 1, 128, 1, 1, 128 * sizeof(float));
var wrapped = runner.Wrap(new Program());
runner.saveAssembly();
cuda.ERROR_CHECK((cudaError_t)(int)wrapped.Total(arr, N, res));
cuda.ERROR_CHECK(cuda.DeviceSynchronize());
Console.WriteLine(res[0]);
}
public void RefreshDevice()
{
indices.RefreshDevice();
data.RefreshDevice();
rows.RefreshDevice();
}
