Hi Am 17.02.22 um 12:05 schrieb Gerd Hoffmann:
- for (j = k; j--; ) { - shift -= ppw; - end_mask = tab[(*src >> shift) & bit_mask]; - *dst++ = (end_mask & eorx) ^ bgx; - if (!shift) { - shift = 8; - src++; + for (j = k; j; j -= jdecr, ++src) { + switch (ppw) { + case 4: /* 8 bpp */ + *dst++ = colortab[(*src >> 4) & bit_mask]; + *dst++ = colortab[(*src >> 0) & bit_mask]; + break; + case 2: /* 16 bpp */ + *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 */ + *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; }How about moving the switch out of the loop, i.e. switch (ppw) { case 4: for (j = ...) { *dst++ = colortab[(*src >> 4) & bit_mask]; *dst++ = colortab[(*src >> 0) & bit_mask]; } [ ... ] } ?
No difference. Values for the microbenchmark (rdtsc around sys_imageblit()) and the directory listing stabilize at the same numbers. I'll still go with you suggestion, because the code is more readable.
Best regards Thomas
take care, Gerd
-- Thomas Zimmermann Graphics Driver Developer SUSE Software Solutions Germany GmbH Maxfeldstr. 5, 90409 Nürnberg, Germany (HRB 36809, AG Nürnberg) Geschäftsführer: Ivo Totev
Attachment:
OpenPGP_signature
Description: OpenPGP digital signature
