I need to write matrix-vector and matrix-matrix multiplication functions but I cannot wrap my head around SSE commands.
The dimensions of matrices and vectors are always multiples of 4.
I managed to write the vector-vector multiplication function that looks like this:
void vector_multiplication_SSE(float* m, float* n, float* result, unsigned const int size)
{
int i;
__declspec(align(16))__m128 *p_m = (__m128*)m;
__declspec(align(16))__m128 *p_n = (__m128*)n;
__declspec(align(16))__m128 *p_result = (__m128*)result;
for (i = 0; i < size / 4; ++i)
p_result[i] = _mm_mul_ps(p_m[i], p_n[i]);
// print the result
for (int i = 0; i < size; ++i)
{
if (i % 4 == 0) cout << endl;
cout << result[i] << '\t';
}
}
and now I'm trying to implement matrix-vector multiplication.
Here's what I have so far:
void multiply_matrix_by_vector_SSE(float* m, float* v, float* result, unsigned const int vector_dims)
{
int i, j;
__declspec(align(16))__m128 *p_m = (__m128*)m;
__declspec(align(16))__m128 *p_v = (__m128*)v;
__declspec(align(16))__m128 *p_result = (__m128*)result;
for (i = 0; i < vector_dims; i += 4)
{
__m128 tmp = _mm_load_ps(&result[i]);
__m128 p_m_tmp = _mm_load_ps(&m[i]);
tmp = _mm_add_ps(tmp, _mm_mul_ps(tmp, p_m_tmp));
_mm_store_ps(&result[i], tmp);
// another for loop here?
}
// print the result
for (int i = 0; i < vector_dims; ++i)
{
if (i % 4 == 0) cout << endl;
cout << result[i] << '\t';
}
}
This function looks completely wrong. I mean not only it doesn't work correctly, but it also seems that I'm moving in the wrong direction.
Could anyone help me with implementing vector-matrix and matrix-matrix multiplication? I'd really appreciate some piece of example code and a very detailed explanation
Update
Here's my attempt number 2:
it fails with Access reading violation
exception but still feels closer
void multiply_matrix_by_vector_SSE(float* m, float* v, float* result, unsigned const int vector_dims)
{
int i, j;
__declspec(align(16))__m128 *p_m = (__m128*)m;
__declspec(align(16))__m128 *p_v = (__m128*)v;
__declspec(align(16))__m128 *p_result = (__m128*)result;
for (i = 0; i < vector_dims; ++i)
{
p_result[i] = _mm_mul_ps(_mm_load_ps(&m[i]), _mm_load_ps1(&v[i]));
}
// print the result
for (int i = 0; i < vector_dims; ++i)
{
if (i % 4 == 0) cout << endl;
cout << result[i] << '\t';
}
}
Update 2
void multiply_matrix_by_vector_SSE(float* m, float* v, float* result, unsigned const int vector_dims)
{
int i, j;
__declspec(align(16))__m128 *p_m = (__m128*)m;
__declspec(align(16))__m128 *p_v = (__m128*)v;
__declspec(align(16))__m128 *p_result = (__m128*)result;
for (i = 0; i < vector_dims; ++i)
{
for (j = 0; j < vector_dims * vector_dims / 4; ++j)
{
p_result[i] = _mm_mul_ps(p_v[i], p_m[j]);
}
}
for (int i = 0; i < vector_dims; ++i)
{
if (i % 4 == 0) cout << endl;
cout << result[i] << '\t';
}
cout << endl;
}