d/freebsd-dev
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Further unobfuscate the method of drawing the mouse cursor in vga planar

Browse Source 
mode.

Don't manually unroll the 2 inner loops.  On Haswell, doing so gave a
speedup of about 0.5% (about 4 cycles per iteration out of 1400), but
hard-coded a limit of width 9 and made better better optimizations
harder to see.  gcc-4.2.1 -O does the unrolling anyway, unless tricked
with a volatile hack.  gcc's unrolling is not very good and gives a
a speedup of about half as much (about 2 cycles per iteration).  (All
timing on i386.)

Manual unrolling was only feasible because the inner loop only iterates
once or twice.  Usually twice, but a dynamic check is needed to decide,
and was not moved from the second-innermost loop manually or by gcc.
This commit basically adds another dynamic check in the inner loop.

Cursor widths of 10-17 require 3 iterations in the inner loop and this
is not so easy to unroll -- even gcc stops at 2.
This commit is contained in:
Bruce Evans 2017-04-14 12:03:34 +00:00
parent da62ffd9cd
commit ddac85e5a0
Notes: svn2git 2020-12-20 02:59:44 +00:00 
svn path=/head/; revision=316827
1 changed files with 17 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
sys/dev/syscons/scvgarndr.c
View File

@ -1031,7 +1031,7 @@ draw_pxlmouse_planar(scr_stat *scp, int x, int y)
int xoff, yoff;
int ymax;
u_short m;
int i, j;
int i, j, k;
line_width = scp->sc->adp->va_line_width;
xoff = (x - scp->xoff*8)%8;
@ -1043,42 +1043,27 @@ draw_pxlmouse_planar(scr_stat *scp, int x, int y)
outw(GDCIDX, 0xff08); /* bit mask */
outw(GDCIDX, 0x0803); /* data rotate/function select (and) */
p = scp->sc->adp->va_window + line_width*y + x/8;
if (x < scp->xpixel - 8) {
for (i = y, j = 0; i < ymax; ++i, ++j) {
m = ~((mouse_and_mask[j] & ~mouse_or_mask[j]) >> xoff);
readb(p);
writeb(p, m >> 8);
readb(p + 1);
writeb(p + 1, m);
p += line_width;
}
} else {
xoff += 8;
for (i = y, j = 0; i < ymax; ++i, ++j) {
m = ~((mouse_and_mask[j] & ~mouse_or_mask[j]) >> xoff);
readb(p);
writeb(p, m);
p += line_width;
for (i = y, j = 0; i < ymax; ++i, ++j) {
m = ~((mouse_and_mask[j] & ~mouse_or_mask[j]) >> xoff);
for (k = 0; k < 2; ++k) {
if (x + 8 * k < scp->xpixel) {
readb(p + k);
writeb(p + k, m >> (8 * (1 - k)));
}
}
p += line_width;
}
outw(GDCIDX, 0x1003); /* data rotate/function select (or) */
p = scp->sc->adp->va_window + line_width*y + x/8;
if (x < scp->xpixel - 8) {
for (i = y, j = 0; i < ymax; ++i, ++j) {
m = mouse_or_mask[j] >> xoff;
readb(p);
writeb(p, m >> 8);
readb(p + 1);
writeb(p + 1, m);
p += line_width;
}
} else {
for (i = y, j = 0; i < ymax; ++i, ++j) {
m = mouse_or_mask[j] >> xoff;
readb(p);
writeb(p, m);
p += line_width;
for (i = y, j = 0; i < ymax; ++i, ++j) {
m = mouse_or_mask[j] >> xoff;
for (k = 0; k < 2; ++k) {
if (x + 8 * k < scp->xpixel) {
readb(p + k);
writeb(p + k, m >> (8 * (1 - k)));
}
}
p += line_width;
}
outw(GDCIDX, 0x0003); /* data rotate/function select */
}