[8192kjshad09-]

Out of curiosity what jobs need a good CPU but also can't take advantage of a good GPU?

It seems like most of the high performance numerical computing software today is GPU-accelerated. If performance for your job is super important, why isn't your software GPU-accelerated?

I might just be naive but it's honestly hard for me to imagine why anybody would need a good CPU and not also want a good GPU.

[mbarbar]

I work on static analysis (points-to analysis) that does not use any GPU at all and is mostly single threaded.

[katbyte]

Static code analysis on 100s of mb of code. Pins my m1max for 3min, my 2015 for 15-20ish.

[imwillofficial]

Because here in the real world software isn’t GPU optimized in many cases.

[wmf]

Since this is HN... compiling.

[8192kjshad09-]

Good point, not sure how I didn't see that, I'm a software engineer too.

[invalidname]

Compiling is IO/RAM bound. CPU has impact but not much for most cases.

[jcelerier]

Nah, I only see minimal difference when building on a ram disk (source tree copied there too) compared to a nvme SSD.

[olliej]

You clearly aren't writing c++ :D