By: -.- (blarg.delete@this.mailinator.com), November 19, 2020 3:34 pm
Room: Moderated Discussions
Doug S (foo.delete@this.bar.bar) on November 19, 2020 9:13 am wrote:
> So if you believe it is unfair that the x264 test doesn't allow using hand tuned SIMD assembly,
> would you also allow use of on chip h.264 hardware, as well as Apple's IPU or NPU if those
> proved more appropriate for some other benchmark instead of using their CPU cores?
It's not a valid comparison, because they (x264 vs hardware encoder) don't even produce the same output. However, if you could figure out a way to integrate the IPU/NPU in a way which generates the same output as x264, I'd be less opposed, but it's questionable as to whether it's a CPU test.
> So if you believe it is unfair that the x264 test doesn't allow using hand tuned SIMD assembly,
> would you also allow use of on chip h.264 hardware, as well as Apple's IPU or NPU if those
> proved more appropriate for some other benchmark instead of using their CPU cores?
It's not a valid comparison, because they (x264 vs hardware encoder) don't even produce the same output. However, if you could figure out a way to integrate the IPU/NPU in a way which generates the same output as x264, I'd be less opposed, but it's questionable as to whether it's a CPU test.