News for hackers. Stuff that matters.
Re:Moore’s law really is dead this time by puppetmaster3 on Tuesday February 16, 2016 @03:34AM (#11108573)
Disagree. GPU. Vector computing. Ex: SSL is faster.
Re:Moore’s law really is dead this time by lumpypua on Tuesday February 16, 2016 @03:43AM (#11108604)
Those are proof Moore's law is dying. We're stuck eeking out more work per transistor with specialized approaches because we can't just throw more transistors at the problem.
Re:Moore’s law really is dead this time by leereeves on Tuesday February 16, 2016 @04:06AM (#11108666)
Parallel computing became important recently because even though transistor density was still increasing, heat issues forced the division of CPUs into multiple cores. Parallel computing was required to use all the transistors.

With the end of Moore's law, we won't get more performance with that approach either.

Re:Moore’s law really is dead this time by setra on Tuesday February 16, 2016 @04:06AM (#11108668)
While what he said was a bad argument, on a related note GPUs have continued to show good performance increases.
Re:Moore’s law really is dead this time by CyberDildonics on Tuesday February 16, 2016 @07:05AM (#11109303)
What do you think a GPU is? They are the ones benefiting the most from more transistors.
Re:Moore’s law really is dead this time by ascorbic on Tuesday February 16, 2016 @05:14AM (#11108912)
Is there any situation now where SSL is a bottleneck?