Intel's New Chimera: Alder Lake • Hacker News Board

Re: Intel's New Chimera: Alder Lake

#251

Post by ByteJockey » Tue, May 17, 2022, 1:52 AM UTC

paulmd wrote: post #230

ByteJockey wrote: post #144

Earlier quoted context omitted.

> they just don’t want to pay licensing fees to use them Can you blame browser makers for this? When was the last time you saw someone pay for a browser? Pre-2005 Opera?

Google makes enough money off Chrome and youtube they could afford to pay licensing fees so that end-users have a good experience. Software decoding vs hardware decoding is a massive difference in user experience.

> Google makes enough money off Chrome and youtube

Chrome is free and youtube notoriously doesn't make a profit (unless this changed in 2021).

Their money comes mostly from search.

Re: Intel's New Chimera: Alder Lake

#252

Post by urthor » Tue, May 17, 2022, 2:46 AM UTC

Traster wrote: post #247

urthor wrote: post #242

Earlier quoted context omitted.

"What Andy giveth, Bill Taketh away." Big little is fundamentally the correct architecture. It's not Intel's fault that the software guys making the Linux Kernel haven't fully supported heterogeneous yet. In the long term, it'll be the optimal call for so many workloads. Thousands of server and laptop workloads care only about performance per watt, not peak single thread.

It's true that the software kills the theoretical performance that the hardware makes available. But I actually think this is an indictment of hardware not software engineers. It's basically "We've created this incredibly difficult problem for you, good luck" from the hardware engineers. How the hell is the OS meant to know whether this thread is going to turn out to be a rendering operation or a logging thread? With…

"How the hell is the OS meant to know whether this thread is going to turn out to be a rendering operation or a logging thread?"

Because this problem is incredibly well solved (I believe?).

Scheduling priorities in operating systems an enormously well explored topic.

Put simply: you must incorporate heterogenous cores into the OS thread scheduler.

There's three actors here:

Hardware developers.

OS developers.

End user software engineers.

The hardware developers are running into physical constraints.

The fix is to shift the prioritisation between the different core types, big little, to the operating system scheduler.

Re: Intel's New Chimera: Alder Lake

#253

Post by jamiek88 » Tue, May 17, 2022, 12:58 PM UTC

paulmd wrote: post #119

jamiek88 wrote: post #114

Earlier quoted context omitted.

Userbenchmark.com is worse than useless. It’s straight up lies.

And like I said, I knew I was gonna get my head bitten off for that. This is where you distinguish the bandwagon hangers-on from the people actually interested in technical discussion. The commentary UserBenchmark provides is terrible and the “effective speed” composite rating is terrible. The actual int/fp benchmarks are perfectly fine and actually tend to be more reflective of actual benchmarks like spec than Passm…

Yeah life’s too short to see what part of lies are true.