[HH] cores: AMD vs Intel

[Federico Lucifredi]

On Mar 13, 2013, at 1:47 PM, markw at mohawksoft.com wrote:

> For the price, an AMD chip is quite a bargain for
> servers and processing.

That's what it looks like, but I expect a tradeoff, and I am trying to locate it.

My use case is a headless server, power consumption is irrelevant, number crunching ability is relevant.

> The 8 core AMD chip has 8 real processing cores and 4 floating point
> processors. It isn't really really 8 cores, but it is pretty damn close.

what is missing that makes you say "close", just the 4 FPUs? 

> The intel chips are 4 cores with four hyper-threads. Hyper-threads are
> extremely limited pseudo cores, they are basically a parasitic add on a
> single processing core that shares the instruction processor and
> instruction cache. Unless the OS does a good job scheduling,
> hyper-threading will reduce processing performance.

my assumption is that hyper-threading helps mitigate branch prediction failures, if your app can feed twice the threads, that is.
> 
> In a database, workstation, or server environment, threads rule. The
> processing is marginally different, and if you choose your I/O carefully,
> cost vs performance ratio is better with AMD.

Okay, that sounds right - cost/performance looks on AMD's side here.  But technically, comparing 4 Intel cores and 4 AMD cores, what did I give up in the (amazing) price difference? Did I trade in some cache? What else?

Thanks for the already insightful response!

Best -F

PS: Shankar, I don't mind to hear about your preference, so don't hold it back :)

>> Hello HH,
>> Any nice comparison of per-core performance between AMD and Intel?
>> Because, looking at the FX processors six and eight core prices, they are
>> nowhere near what a 6 core Intel chip costs… so i'd like to educate myself
>> on the why.
>> 
>> I have seen this before with the Phenom chips… but it seems to be going
>> even farther with the FX.
>> 
>> Thanks -F
>> 
>> 
>> _________________________________________
>> -- "'Problem' is a bleak word for challenge" - Richard Fish
>> (Federico L. Lucifredi) - flucifredi at acm.org - GnuPG 0x4A73884C
>> 
>> 
>> 
>> 
>> 
>> 
>> 
>> _______________________________________________
>> Hardwarehacking mailing list
>> Hardwarehacking at blu.org
>> http://lists.blu.org/mailman/listinfo/hardwarehacking
>> 
> 
> 

_________________________________________
-- "'Problem' is a bleak word for challenge" - Richard Fish
(Federico L. Lucifredi) - flucifredi at acm.org - GnuPG 0x4A73884C