Skip to content
Snippets Groups Projects
Commit f31e965b authored by gkusoglu's avatar gkusoglu
Browse files

trying optimize 3mm

parent 127b4534
No related merge requests found
......@@ -91,19 +91,23 @@ void kernel_3mm(int ni, int nj, int nk, int nl, int nm,
for (j = 0; j < _PB_NL; j++)
F[i][j] += C[i][k] * D[k][j];
/* E := A*B */
/* G := E*F */
for (i = 0; i < _PB_NI; i++){
/* E := A*B */
for (i = 0; i < _PB_NI; i++)
for (j = 0; j < _PB_NJ; j++)
E[i][j] = SCALAR_VAL(0.0);
for (i = 0; i < _PB_NI; i++)
for (k = 0; k < _PB_NK; ++k)
for (j = 0; j < _PB_NJ; j++)
E[i][j] += A[i][k] * B[k][j];
/* G := E*F */
for (i = 0; i < _PB_NI; i++){
for (j = 0; j < _PB_NL; j++)
G[i][j] = SCALAR_VAL(0.0);
}
for (i = 0; i < _PB_NI; i++){
for (k = 0; k < _PB_NK; ++k)
for (j = 0; j < _PB_NJ; j++)
E[i][j] += A[i][k] * B[k][j];
for (k = 0; k < _PB_NJ; ++k)
for (j = 0; j < _PB_NL; j++)
G[i][j] += E[i][k] * F[k][j];
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment