• Welcome to Overclockers Forums! Join us to reply in threads, receive reduced ads, and to customize your site experience!

CPUz bad for benchmarking?? (cache and branch predicition)

Overclockers is supported by our readers. When you click a link to make a purchase, we may earn a commission. Learn More.

EarthDog

Gulper Nozzle Co-Owner
Joined
Dec 15, 2008
Location
Cbus!
From a Tom's Hardware article..... I found this to be an interesting read. :)

It's a really short read, but:
The cache is a small amount of memory integrated into processors to lower the time spent communicating with RAM, which is much slower. The CPU-Z benchmark is less than 32KB large, which fits into the L1 (first level) cache of even old CPUs. While technically very efficient, it also makes for a benchmark that can't stress a CPU's cache, so CPUs with better cache don't score any better.



Branch prediction is the process of a chip attempting to guess upcoming tasks. Correct predictions mean faster execution, while wrong predictions lose time. In CPU-Z, Chips and Cheese found that even the infamous FX-8150 Bulldozer CPU had a branch prediction success rate of 95%. That's pretty generous for a CPU that received universally bad reviews when it launched in 2011.

 
I honestly never thought it was good (for no real reason, lol). That said, I never looked at a results table to see if things were wonky in the first place. I suppose it really depends on how cache heavy the application is as to how much it would matter in skewing the results. :shrug:
 
Linp.. nvm :D
I pretty much 100% install CPU-Z on every system I have, so it is always there. Linpack suffers from that there isn't a single great reference implementation, and the ones you can find out there usually are pretty ancient and don't support past AVX2. Prime95 would be my go to for AVX-512 support also, but I don't always have it, and it is a bit more fiddly if you want to turn it on and off easily.
 
Back