-
Vladislav Vinogradov authored
- 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
281d036f
- 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