private void Test_addVector(eAddVectorMode addMode)
{
int[] a = new int[N];
int[] b = new int[N];
int[] c = new int[N];
// allocate the memory on the GPU
int[] dev_c = _gpu.Allocate <int>(c);
// fill the arrays 'a' and 'b' on the CPU
for (int i = 0; i < N; i++)
{
a[i] = -i;
b[i] = i * i;
}
// copy the arrays 'a' and 'b' to the GPU
int[] dev_a = _gpu.CopyToDevice(a);
int[] dev_b = _gpu.CopyToDevice(b);
if (addMode == eAddVectorMode.Smart)
{
_gpu.Launch(N, 1, "addVectorSmart", dev_a, dev_b, dev_c);
}
else if (addMode == eAddVectorMode.GlobalVar)
{
_gpu.Launch(N, 1, "addVector", dev_a, dev_b, dev_c);
}
else if (addMode == eAddVectorMode.GlobalVarDevice)
{
_gpu.Launch(N, 1, "addVectorDevice", dev_a, dev_b, dev_c);
}
else
{
throw new NotSupportedException(addMode.ToString());
}
// copy the array 'c' back from the GPU to the CPU
_gpu.CopyFromDevice(dev_c, c);
// test the results
for (int i = 0; i < N; i++)
{
Assert.AreEqual(a[i] + b[i], c[i]);
}
// free the memory allocated on the GPU
_gpu.FreeAll();
}
private void Test_addVector(eAddVectorMode addMode)
{
int[] a = new int[N];
int[] b = new int[N];
int[] c = new int[N];
// allocate the memory on the GPU
int[] dev_c = _gpu.Allocate<int>(c);
// fill the arrays 'a' and 'b' on the CPU
for (int i = 0; i < N; i++)
{
a[i] = -i;
b[i] = i * i;
}
// copy the arrays 'a' and 'b' to the GPU
int[] dev_a = _gpu.CopyToDevice(a);
int[] dev_b = _gpu.CopyToDevice(b);
if (addMode == eAddVectorMode.Smart)
_gpu.Launch(N, 1, "addVectorSmart", dev_a, dev_b, dev_c);
else if (addMode == eAddVectorMode.GlobalVar)
_gpu.Launch(N, 1, "addVector", dev_a, dev_b, dev_c);
else if (addMode == eAddVectorMode.GlobalVarDevice)
_gpu.Launch(N, 1, "addVectorDevice", dev_a, dev_b, dev_c);
else
throw new NotSupportedException(addMode.ToString());
// copy the array 'c' back from the GPU to the CPU
_gpu.CopyFromDevice(dev_c, c);
// test the results
for (int i = 0; i < N; i++)
{
Assert.AreEqual(a[i] + b[i], c[i]);
}
// free the memory allocated on the GPU
_gpu.FreeAll();
}
