On Thu, Jun 25, 2009 at 9:51 PM, Michael Niedermayer<[email protected]> wrote:
> On Wed, Jun 24, 2009 at 05:59:19PM +0000, Jai Menon wrote:
>> On Wed, Jun 24, 2009 at 3:58 PM, Michael Niedermayer<[email protected]> wrote:
>> > On Wed, Jun 24, 2009 at 01:42:08PM +0000, Jai Menon wrote:
>> >> On Wed, Jun 24, 2009 at 1:27 PM, Michael Niedermayer<[email protected]>
>> >> wrote:
>> >> > On Sun, Jun 21, 2009 at 04:35:20PM +0000, Jai Menon wrote:
>> > [...]
>> >> > [...]
>> >> >> @@ -806,6 +815,26 @@
>> >> >>
>> >> >> line += s->picture.linesize[0];
>> >> >> }
>> >> >> + } else {
>> >> >> + for (; y < tile->comp[0].coord[1][1] - s->image_offset_y;
>> >> >> y++) {
>> >> >> + uint16_t *dst;
>> >> >> + x = tile->comp[0].coord[0][0] - s->image_offset_x;
>> >> >> + dst = line + x * s->ncomponents * 2;
>> >> >> + for (; x < tile->comp[0].coord[0][1] - s->image_offset_x;
>> >> >> x++) {
>> >> >> + for (compno = 0; compno < s->ncomponents; compno++) {
>> >> >
>> >> >> + *src[compno] = av_rescale(*src[compno], (1 << 16)
>> >> >> - 1,
>> >> >> + (1 << s->cbps[compno])
>> >> >> - 1);
>> >> >
>> >> > av_rescale is too slow
>> >>
>> >> So just (*src[compno]/((1 << s->cbps[compno]) - 1)) * ((1 << 16) - 1) ?
>> >
>> > * is slow
>> > / s slower
>> >
>> > "src" << C
>> > it should be
>>
>> <possibly dumb question ahead>
>>
>> I understand that * and / are slower but how can I achieve the same
>> effect with a single <<?
>
> well, not the same but close enough IMHO
> src<<C
> or
> (src<<C) + (src>>(16-C))
> should be close enough, my point was mainly that av_rescale() is too slow
> to be done per pixel and anything else is better
Okay, modified patch attached.
--
Regards,
Jai
Index: j2kdec.c
===================================================================
--- j2kdec.c (revision 4434)
+++ j2kdec.c (working copy)
@@ -55,6 +55,7 @@
uint8_t sgnd[4]; ///< if a component is signed
uint8_t properties[4];
+ int precision;
int ncomponents;
int tile_width, tile_height; ///< tile size
int numXtiles, numYtiles;
@@ -225,6 +226,7 @@
for (i = 0; i < s->ncomponents; i++){ // Ssiz_i XRsiz_i, YRsiz_i
uint8_t x = bytestream_get_byte(&s->buf);
s->cbps[i] = (x & 0x7f) + 1;
+ s->precision = FFMAX(s->cbps[i], s->precision);
s->sgnd[i] = (x & 0x80) == 1;
if (bytestream_get_byte(&s->buf) != 1)
return -1;
@@ -251,8 +253,14 @@
s->avctx->height = s->height - s->image_offset_y;
switch(s->ncomponents){
- case 1: s->avctx->pix_fmt = PIX_FMT_GRAY8; break;
- case 3: s->avctx->pix_fmt = PIX_FMT_RGB24; break;
+ case 1: if (s->precision > 8) {
+ s->avctx->pix_fmt = PIX_FMT_GRAY16;
+ } else s->avctx->pix_fmt = PIX_FMT_GRAY8;
+ break;
+ case 3: if (s->precision > 8) {
+ s->avctx->pix_fmt = PIX_FMT_RGB48;
+ } else s->avctx->pix_fmt = PIX_FMT_RGB24;
+ break;
case 4: s->avctx->pix_fmt = PIX_FMT_BGRA; break;
}
@@ -788,6 +796,7 @@
if (s->avctx->pix_fmt == PIX_FMT_BGRA) // RGBA -> BGRA
FFSWAP(int *, src[0], src[2]);
+ if (s->precision <= 8) {
for (; y < tile->comp[0].coord[1][1] - s->image_offset_y; y++){
uint8_t *dst;
@@ -806,6 +815,22 @@
line += s->picture.linesize[0];
}
+ } else {
+ for (; y < tile->comp[0].coord[1][1] - s->image_offset_y; y++) {
+ uint16_t *dst;
+ x = tile->comp[0].coord[0][0] - s->image_offset_x;
+ dst = line + x * s->ncomponents * 2;
+ for (; x < tile->comp[0].coord[0][1] - s->image_offset_x; x++) {
+ for (compno = 0; compno < s->ncomponents; compno++) {
+ *src[compno] = *src[compno] << (16 - s->cbps[compno]);
+ *src[compno] += 1 << 15;
+ *src[compno] = av_clip(*src[compno], 0, (1 << 16) - 1);
+ *dst++ = *src[compno]++;
+ }
+ }
+ line += s->picture.linesize[0];
+ }
+ }
return 0;
}
_______________________________________________
FFmpeg-soc mailing list
[email protected]
https://lists.mplayerhq.hu/mailman/listinfo/ffmpeg-soc
