Vladislav Vinogradov 281d036fcf optimizations:
- new reduce implementation (with kepler optimizations)
- saturate_cast via asm command
- video SIMD instructions in element operations
- float arithmetics instead of double
- new deviceSupports function
2013-01-23 21:05:07 +04:00
..
2013-01-23 21:05:07 +04:00
2013-01-14 17:58:27 +04:00
2013-01-23 21:05:07 +04:00
2013-01-14 17:58:27 +04:00
2013-01-14 17:58:27 +04:00
2012-11-28 18:17:33 +04:00
2012-02-03 11:26:49 +00:00