Search
Friday, July 03, 2009 ..:: Home ::.. Register  Login
Blog roll

Topic search

UsersOnline
Membership Membership:
Latest New User Latest: freshvine
New Today New Today: 0
New Yesterday New Yesterday: 0
User Count Overall: 137

People Online People Online:
Visitors Visitors: 0
Members Members: 0
Total Total: 0

Online Now Online Now:

Blogs
Nov 13

Written by: George Ou
11/13/2008 9:11 PM

AMD launched its 45nm Shanghai processors today for the server market ahead of Intel's Nehalem processor launch.  AMD lists a series of benchmarks here but they omit many of the better results from Intel.  To get the full official results, here are the benchmarks based on the best scores available from AMD and Intel as of November 13th 2008.

CPU GHz Socket Cores SPECint SPECfp SPECjbb SPECweb SPECpower SAP
Intel X5482 3.2 2 4 156 93.4        
AMD 2384 2.7 2 4 136 118 352700   860  
Intel L5430 2.66 2 4         1135  
Intel X5470 3.33 2 4     316728      
Intel X7460 2.66 4 6 294 156        
AMD 8384 2.7 4 4 249 210        
AMD 2356 2.3 2 4       30007    
Intel X5460 3.166 2 4       29591    
Intel X7460 2.66 8 6           9200
AMD 8384 2.7 8 4           7010

It appears that AMD has made some important gains and it has taken the lead in SPECjbb, SPECweb, expanded its lead in SPECfp, and Virtualization (due to Nested Paging).  AMD still trails in SPECint, SPECpower, and SAP but this is an important victory for AMD which has been plagued with delays in 2007 and 2008 with its previous Barcelona processor.  Shanghai is a major milestone for AMD because it required a shift to a whole new 45nm immersion lithography process and it shows that AMD can launch a product on time and put Barcelona behind them.

However, Intel is expected to launch its Nehalem-EP processors for the mainstream two-socket server market within a few months and Nehalem is expected to be a huge jump in performance on the server platform.  While the new triple-channel DDR3 unbuffered memory subsystem doesn't do too much for the Intel i7 Nehalem desktop processors, it is expected to unleash a huge increase in performance for Intel Nehalem.

Intel's Penryn class of processors launched last year will be the last generation of Intel processors to use the Front Side Bus (FSB) and a single North Bridge memory controller located on the motherboard.  The FSB and single North Bridge memory controller wasn't a problem for most of Intel's product line but it significantly hampered Penryn's performance in the two-socket market at higher clock speeds.  But this wasn't a problem since AMD had trouble launching its Barcelona products early enough and at high enough clock speeds to threaten Penryn on the high end, and only now are the newest AMD Shanghai processors competing head to head with Intel Penryn.  Some people wondered why Intel stuck with the FSB architecture for so long, but the timing seems to have been appropriate given the outcome in the last two years.

Intel's Nehalem will be too fast to run on FSB architecture which is why Intel designed it with QuickPath.  Nehalem will have no such memory bandwidth limitations as it transitions to QuickPath architecture with a memory controller on each microprocessor.  Nehalem also catches up with AMD on nested paging support for improved virtualization, but the late timing doesn't seem to have hurt Intel given the fact that virtualization hypervisors are only now beginning to support nested paging.  So the race is on to see how quickly AMD can ramp up Shanghai processors and how long it takes Intel to launch Nehalem.

Tags:

4 comments so far...

Re: AMD Shanghai 45nm launch - Server benchmarks roundup

AMD still leads by huge margin in FP, almost 50% if compare clock-by-clock and 26% at the clocks mentioned above. That's like one generation ahead. For my science only FP matter

By Slava on   11/14/2008 3:01 PM

Slava, be prepared to watch the SPECfp lead change hands for 2 sockets or less in a few months

Slava, be prepared to watch the SPECfp lead change hands for 2 sockets or less in a few months. If you're purchasing today and you only care about SPECfp, you're probably buying AMD. However, note that SPECfp is an average of a larger set of applications. A small percentage of those applications do work better on Intel CPUs. Nehalem changes that of course.

By host on   11/14/2008 3:04 PM

Re: AMD Shanghai 45nm launch - Server benchmarks roundup

George, are you a dealer of Intel? Or you think that only Intel do in all things in the right way? Integer performance matter on web servers, still AMD have other strong points (virtualization seems a strong point for me still). Your posts seems biased.

I am not going to buy both Nehalem for server and Shanghai. Probably the next iteration which has 6 cores from AMD sounds more nicer (which is a Tick from Intel naming) and probably will match the quad Nehalem.

What should I say, for sure I will buy the next CPU+Mainboard that offer the best for me on matter of what I use. And putting a biased conclusion on raw numbers seems inappropriate. Is right to say both on AMD achievements. In games (which Nehalem did not succed so great comparing with Peryn) Phenom II in early benchmarks match Peryn and probably is 10%-15% lower than Negaken. But putting the cheaper mainboard + DDR2 price, you can buy a nice video board and you can beat in any benchmark an Intel (in games).

So please put all in equation seems a fair benchmark and comparison. Elsewhere seems as .NET beat always Java in a Microsoft benchmark, or C beats again Java in a XML processing.

For now AMD seems very less power hungry and good (as were even the TLB free Barcelona) for server workloads and less powerful for games. Right now AMD have a bigger cache to achieve more for games and a bit lower power consumption. For me seems enough for a shrink. Intel did extend their power by offering a compatible by idea with AMD and 20% more in row numbers on bandwidth and frequency. Seems enough to beat AMD? Probably, but seems to not be enough on power consumption and virtualization.

By Ciprian Mustiata on   11/27/2008 10:21 AM

Re: AMD Shanghai 45nm launch - Server benchmarks roundup

First of all, I call it like I see it. I've given AMD praise on where they deserve it and criticize them where they deserve it.

AMD has to fudge the results to claim a power advantage.
http://www.formortals.com/Home/tabid/36/EntryID/130/Default.aspx

Single Nehalem beats two Shanghai
http://www.formortals.com/Home/tabid/36/EntryID/141/Default.aspx

The truth about AMD's TDP rating
http://www.formortals.com/Home/tabid/36/EntryID/137/Default.aspx

Lastly, 6-core Shanghai isn't here yet and when it does get here, it has to deal with 8-core Nehalem-EX.

By host on   11/27/2008 10:32 AM

Your name:
Title:
Comment:
Add Comment    Cancel  

Links

Blog_Archive

New_Blog
You must be logged in and have permission to create or edit a blog.

Search_Blog
Print  

Copyright 2008 by George Ou, Charles N Burns, or Justin James   Terms Of Use  Privacy Statement
DotNetNuke® is copyright 2002-2009 by DotNetNuke Corporation