float: high precision floating point. Generally 32 bits, just like float type in regular programming languages.
half: medium precision floating point. Generally 16 bits, with a range of -60000 to +60000 and 3.3 decimal digits of precision.
fixed: low precision fixed point. Generally 11 bits, with a range of -2.0 to +2.0 and 1/256th precision.
Optimal precision for GPU family
• 11/12bit per-component (fixed) - SGX pre543, Tegra
• 16bit per-component (half) - SGX 543, Mali 4xx
• 32bit per-component (float) - Adreno, Mali T6xx
Сейчас этот форум просматривают: нет зарегистрированных пользователей и гости: 3