0
$\begingroup$

What is the reason NVIDIA's Turing has twice the FP16 performance compared to it's FP32 whereas AMD has same performance in FP16 and FP32?

Like GTX 1650 Super has around 8 teraflops in FP16 but half of that in FP32.

RX 580 has around 6.174 teraflops in FP16 and same number in FP32.

$\endgroup$
1
$\begingroup$

I remember that around 2010 to 2012, AMD had always a greater portion of GPU core units able to perform FP32 computations (1 out of 2 cores), whereas consumer grade Nvidia cards had a lower ratio (1 to 8). I guess this is still the same kind of problematic.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.