This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [patch,libgfortran] PR51119 - MATMUL slow for large matrices
Hi Jerry,
With these changes, OK for trunk?
Just going over this with a fine comb...
One thing just struck me: The loop variables should be index_type, so
const index_type m = xcount, n = ycount, k = count;
[...]
index_type a_dim1, a_offset, b_dim1, b_offset, c_dim1, c_offset, i1, i2,
i3, i4, i5, i6;
/* Local variables */
GFC_REAL_4 t1[65536], /* was [256][256] */
f11, f12, f21, f22, f31, f32, f41, f42,
f13, f14, f23, f24, f33, f34, f43, f44;
index_type i, j, l, ii, jj, ll;
index_type isec, jsec, lsec, uisec, ujsec, ulsec;
I agree that we should do the tuning of the inline limit
separately.
When we do that, we should think about -Os. With the buffering, we have
much more memory usage in the library function. If -Os is in force,
we should also consider raising the limit for inlining.
Since I was involved in the development, I would like to give others a
few days to raise more comments. If there are none, OK to commit with
the above change within a few days. Of course, somebody else might also
OK this patch :-)
Regards
Thomas