UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

fbdev: Improve performance of sys_imageblit() 

Improve the performance of sys_imageblit() by manually unrolling
the inner blitting loop and moving some invariants out. The compiler
failed to do this automatically. The resulting binary code was even
slower than the cfb_imageblit() helper, which uses the same algorithm,
but operates on I/O memory.

A microbenchmark measures the average number of CPU cycles
for sys_imageblit() after a stabilizing period of a few minutes
(i7-4790, FullHD, simpledrm, kernel with debugging). The value
for CFB is given as a reference.

  sys_imageblit(), new: 25934 cycles
  sys_imageblit(), old: 35944 cycles
  cfb_imageblit():      30566 cycles

In the optimized case, sys_imageblit() is now ~30% faster than before
and ~20% faster than cfb_imageblit().

v2:
	* move switch out of inner loop (Gerd)
	* remove test for alignment of dst1 (Sam)

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20220223193804.18636-3-tzimmermann@suse.de
This commit is contained in:
Thomas Zimmermann 2022-02-23 20:38:01 +01:00
parent 7dbc515f5c
commit 6f29e04938
1 changed files with 38 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
drivers/video/fbdev/core/sysimgblt.c
View File

@ -188,23 +188,29 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
{
u32 fgx = fgcolor, bgx = bgcolor, bpp = p->var.bits_per_pixel;
u32 ppw = 32/bpp, spitch = (image->width + 7)/8;
u32 bit_mask, end_mask, eorx, shift;
u32 bit_mask, eorx;
const char *s = image->data, *src;
u32 *dst;
const u32 *tab = NULL;
const u32 *tab;
size_t tablen;
u32 colortab[16];
int i, j, k;
switch (bpp) {
case 8:
tab = fb_be_math(p) ? cfb_tab8_be : cfb_tab8_le;
tablen = 16;
break;
case 16:
tab = fb_be_math(p) ? cfb_tab16_be : cfb_tab16_le;
tablen = 4;
break;
case 32:
default:
tab = cfb_tab32;
tablen = 2;
break;
default:
return;
}
for (i = ppw-1; i--; ) {
@ -218,19 +224,40 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
eorx = fgx ^ bgx;
k = image->width/ppw;
for (i = 0; i < tablen; ++i)
colortab[i] = (tab[i] & eorx) ^ bgx;
for (i = image->height; i--; ) {
dst = dst1;
shift = 8;
src = s;
for (j = k; j--; ) {
shift -= ppw;
end_mask = tab[(*src >> shift) & bit_mask];
*dst++ = (end_mask & eorx) ^ bgx;
if (!shift) {
shift = 8;
src++;
switch (ppw) {
case 4: /* 8 bpp */
for (j = k; j; j -= 2, ++src) {
*dst++ = colortab[(*src >> 4) & bit_mask];
*dst++ = colortab[(*src >> 0) & bit_mask];
}
break;
case 2: /* 16 bpp */
for (j = k; j; j -= 4, ++src) {
*dst++ = colortab[(*src >> 6) & bit_mask];
*dst++ = colortab[(*src >> 4) & bit_mask];
*dst++ = colortab[(*src >> 2) & bit_mask];
*dst++ = colortab[(*src >> 0) & bit_mask];
}
break;
case 1: /* 32 bpp */
for (j = k; j; j -= 8, ++src) {
*dst++ = colortab[(*src >> 7) & bit_mask];
*dst++ = colortab[(*src >> 6) & bit_mask];
*dst++ = colortab[(*src >> 5) & bit_mask];
*dst++ = colortab[(*src >> 4) & bit_mask];
*dst++ = colortab[(*src >> 3) & bit_mask];
*dst++ = colortab[(*src >> 2) & bit_mask];
*dst++ = colortab[(*src >> 1) & bit_mask];
*dst++ = colortab[(*src >> 0) & bit_mask];
}
break;
}
dst1 += p->fix.line_length;
s += spitch;