[FFmpeg-devel] [PATCH][RFC] JPEG2000: SSE optimisation for DWT decoding

Carl Eugen Hoyos ceffmpeg at gmail.com
Fri Jul 21 00:43:48 EEST 2017

2017-07-20 18:07 GMT+02:00 maxime taisant <maximetaisant at hotmail.fr>:
> From: Maxime Taisant <maximetaisant at hotmail.fr>

> I am currently working on SSE optimisations for the dwt functions used to decode JPEG2000.
> For the moment, I have only managed to produce a SSE-optimized version of the sr_1d97_float function

> (with relatively good results).

Please add some numbers.

> +           if (ARCH_X86)
> +                ff_sr_1d97_float_sse(line, mh, mh + lh);
> +           else
> +                sr_1d97_float(line, mh, mh + lh);

This is not correct, look at ff_jpeg2000dsp_init_x86() and Jpeg2000DSPContext
to see what has to be done.

Others will comment on the asm code.

Thank you, Carl Eugen

More information about the ffmpeg-devel mailing list