Jump to content

it's more about the cpu architecture than either of those.

if your picking between cpu's of the same architecture then I'd say look in this order.

more cores.

higher clock speed.

more cache

Linus Sebastian said:

The stand is indeed made of metal but I wouldn't drive my car over a bridge made of it.

 

https://youtu.be/X5YXWqhL9ik?t=552

Link to post
Share on other sites

at do u mean by cpu architecture
the innerworkings of the cpu.

transistor count,features like integrated memory controllers,things like the tri-gate transistor used on ivybridge.

innovations in the cpu's inner workings that improved performance.

basically the stuff people don't care about.

simply look for reviews like guru3d,anandtech,tomshardware,etc and look for the part where they compare the cpu to other cpu's performance.

Linus Sebastian said:

The stand is indeed made of metal but I wouldn't drive my car over a bridge made of it.

 

https://youtu.be/X5YXWqhL9ik?t=552

Link to post
Share on other sites

think of it like this... the cpu is the engine and how many cylinder is the gigahertz but the size of the engine is the cache memory size... cache memory is used to store information to be processed and the results as well, so too big of a cache wudnt affect the performance drasticly... gigahertz/cache size is generally proportional so the end product is optimal :)

hope i clear it a little :D

Link to post
Share on other sites

GHz is more important than cache, but you can only really use these things to compare processors that are the same architecture. For example, comparing two Sandy Bridge processors the one with the higher clock speed will be faster (if they have the same number of cores, if they have different core counts it depends on what you're doing for which one is faster). However in between CPUs that are different, you cannot compare with specs and numbers like these. A 3.5GHz Ivy Bridge Hyper-Threaded Quad Core is faster than a 3.5GHz Sandy Bridge Hyper-Threaded Quad Core because it has a higher performing underlying architecture. Similarly, an AMD Phenom II X4 965 (3.4GHz, Quad-Core, 6MB Cache) is completely annihilated by an Intel Core i5-3570K (3.4GHz, Quad-Core, 6MB Cache) because the architecture on the Intel is newer and much better than the older Phenom II. Clock speed and Cache are only useful for comparing processors that are otherwise the same, most importantly from the same maker, generation, and series. Otherwise, a CPUs performance really can't be determined from its specifications. You will have to look at benchmark results on various review websites.

Link to post
Share on other sites

Cache won't help much even with CPUs of the same architecture. Take the i5 3570k and the i7 3770k for example, the i7 3770k has 8mb of L3 cache vs 6mb for the i5 3570k. If you disable hyperthreading on the i7 3770k and reduce the MHZ to the same as the i5 3570k and benchmark both of them, the 3770k will usually be like 1% faster because of the 2 extra MB of cache, so it's not much. The difference is more noticeable if you compare a cpu without L3 cache with a cpu with it but the increase is still not as good as more MHZ.

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×