projects / babl.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 34aef49) | patch
avx2-int8: add gamma u8 -> linear float conversions
authorEll <ell_se@yahoo.com>
Sun, 12 Apr 2020 14:42:16 +0000 (17:42 +0300)
committerEll <ell_se@yahoo.com>
Sun, 12 Apr 2020 14:52:46 +0000 (17:52 +0300)
commit57bd10c3f114a2f785ca6325204f035665d2892e
tree1948b9276564eb481fdca80809017c937785abd9tree | snapshot
parent34aef492273b4c4ac4210e032c79506bcb9545b7commit | diff
avx2-int8: add gamma u8 -> linear float conversions

Add AVX2 conversions from u8 Y', Y'A, R'G'B, and R'G'B'A to float
Y, YA, RGB, and RGBA, respectively.  The conversions use an LUT
together with the AVX2 gather instructions to process 8 values a
 once.  Depending on the formats and cache utilization, the new
conversions are between 1.25x to 2.2x faster than the existing
conversions.
extensions/avx2-int8-tables.h diff | blob | history
extensions/avx2-int8.c diff | blob | history
Unnamed repository; edit this file 'description' to name the repository.