[alt227]

Why do people care so much about single core performance? We are all professionals here and I bet most of our workloads are multi core. I get that these new arm chips from Apple and Qualcomm are great at one thing at a time, but for professional workloads high end x64 chips still cannot be beaten on the desktop.

[Remnant44]

I agree with you, but also:

outside of anything else, amdahls law means that as the parallel performance grows, we become _more_ limited by the inherently serial code, and thus single core performance, not less.

Given that single core performance is "harder" (can't just throw more cores/sockets at the problem), it's also critically important.

[dagmx]

What x86 chips have the same or higher number of cores in the form factors that these chips are available in and are also more performant?

Strix Halo is 16 cores. Intel Core Ultra 9 285HX is 24. Apple is 18. Qualcomm is something similar too but I can’t recall. NVIDIA is 20.

Until you get to threadripper/epyc or Xeon territories (completely different form factors and TDPs) the arm chips are ahead on both power and perf than the x86. And even when you get to those areas, arm is equivalent or out performs them as can be seen by the recent neoverse x3 and Vera benchmarks.

[wmf]

Nvidia Spark has 10 mid cores and 10 fake cores. Probably all the others are faster.

[hulitu]

> Why do people care so much about single core performance?

Because that't the only part this chip excels.

People are comparing apples with oranges since ages.

[modeless]

Single core performance is the biggest factor for most day-to-day use of a computer, the stuff I do on a laptop. It's more important than peak multi core performance for web browsing and games. I only care about multi core performance when I'm compiling, and I usually do heavy compiles on a remote machine rather than on my laptop.

[pjmlp]

Which hardly matters because in modern OSes there isn't a single thread that runs to completion without being preempted by other OS work.

[pjmlp]

It is a feel good kind of thing usually repeated by folks that don't understand OS scheduling algorithms.

Unless we're talking about RTOS, threads are always interrupted, thus how fast a single one can race is irrelevant in the whole picture.