floraachy
/
OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Expanding the scop of 2D thread distribution

This commit is contained in:
yamazaki-mitsufumi 2024-04-18 18:20:25 +09:00
parent bece730218
commit 51ab1903e7
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
driver/level3/level3_thread.c
View File

@ -826,6 +826,16 @@ int CNAME(blas_arg_t *args, BLASLONG *range_m, BLASLONG *range_n, IFLOAT *sa, IF
if (nthreads_m * nthreads_n > args -> nthreads) {
nthreads_n = blas_quickdivide(args -> nthreads, nthreads_m);
}
/* The nthreads_m and nthreads_n are adjusted so that the submatrix */
/* to be handled by each thread preferably becomes a square matrix */
/* by minimizing an objective function 'n * nthreads_m + m * nthreads_n'. */
/* Objective function come from sum of partitions in m and n. */
/* (n / nthreads_n) + (m / nthreads_m) */
/* = (n * nthreads_m + m * nthreads_n) / (nthreads_n * nthreads_m) */
while (nthreads_m % 2 == 0 && n * nthreads_m + m * nthreads_n > n * (nthreads_m / 2) + m * (nthreads_n * 2)) {
nthreads_m /= 2;
nthreads_n *= 2;
}
}
/* Execute serial or parallel computation */