Comment by cogman10

2 months ago

I'm not claiming that software will be more efficient. I'm claiming that things that make it easy to go fast in hardware make it easy to go fast in software.

Bit masking/shifting is certainly more expensive in software, but it's also about the cheapest software operation. In most cases it's a single cycle transform. In the best cases, it's something that can be done with some type of SIMD instruction. And in even better cases, it's a repeated operation which can be distributed across the array of GPU vector processors.

What kills both hardware and software performance is data dependency and conditional logic. That's the sort of thing that was limited in the AV1 stream.

5 comments

cogman10

Reply
IshKebab  2 months ago

> Bit masking/shifting is certainly more expensive in software, but it's also about the cheapest software operation. In most cases it's a single cycle transform.

He's not talking about simple bit shifts. Imagine if you had to swap every other bit of a value. In hardware that's completely free; just change which wires you connect to. In software it takes several instructions. The 65 bit example is good too. In hardware it makes basically no difference to go from 64 bits to 65 bits. In software it is significantly more complete - it can more than double computation time.

I think where software has the advantage is sheer complexity. It's harder to design and verify complex algorithms in hardware than it is in software, so you need to keep things fairly simple. The design of even state-of-the-art CPUs is surprisingly simple; a cycle accurate model might only be a few tens of thousands of lines of code.

  • Neywiny  2 months ago

    Right. It's bit packing and unpacking. Currently dealing with a 32 bit system that needs to pack 8 11 bit quantities each subsisting of 3 multi bit values into a 96 bit word. As you can imagine, the assembly is a mess of bit manipulation and it takes forever. Ridiculously it's to talk to a core that extracts them effortlessly. I'm seriously considering writing an accelerator to do this for me

  • cogman10  2 months ago

    I just have to repeat myself

    > I'm not claiming that software will be more efficient. I'm claiming that things that make it easy to go fast in hardware make it easy to go fast in software.