This discussion has been locked.
You can no longer post new replies to this discussion. If you have a question you can start a new discussion

Is there practical examples of Half-float (FP16) ?

Greetings,

After reading“PHENOMENAL COSMIC POWERS! Itty-bitty living space!” from edplowman, I'm wondering how the FP16 type can actually be used ?

When reading the ARMv7 and ARMv8 architectures manuals, the only instructions that I found to refer to half-precision floating-points are VCVT (ARMv7) or FCVT (ARMv8).

So, my questions are :

  • Can CPU do anything with half-precision floating points beside converting them ? Can you add/subtract/multiply/divide half-precision floating-points natively ?
  • How do you use half-precision floating points values efficiently with OpenGL ? Do you do all the operations with single-precision floats and do a conversion before sending the data to the GPU ?
  • Is there any example showing how to use this data type efficiently ?
Parents
  • At the moment the most one can do is save space and not worry much about the conversion. They are useful in artificial intelligence type applications and in graphics where quite often a high bandwidth is required but not high accuracy. There is more extensive support for them in graphics units and a later version of ARMv8 will also add support for calculations using them

    ARMv8-A architecture evolution

Reply
  • At the moment the most one can do is save space and not worry much about the conversion. They are useful in artificial intelligence type applications and in graphics where quite often a high bandwidth is required but not high accuracy. There is more extensive support for them in graphics units and a later version of ARMv8 will also add support for calculations using them

    ARMv8-A architecture evolution

Children