Intel and AMD in a Web Application Shoot-out
by Jason Clark on October 18, 2004 12:05 AM EST- Posted in
- IT Computing
Microsoft .NET
This was probably the most interesting test out of the bunch, as there was a recognizable difference in the two architectures. Our .NET test was run on the recently released FuseTalk .NET collaboration application.The .NET platform is the new framework for building Windows-based and web-based applications from Microsoft. It not only replaces the older ASP platform, but introduces some up-to-date languages that run on the Common Language Runtime, which is the backbone of .NET. The three main languages used with .NET are: C# (similar to C++), VB.NET (somewhat similar to VB), and J# (fairly close to JAVA). Whatever language in which you write your code, it is compiled into an intermediate language, CIL (Common Intermediate Language). It is then managed and executed by the CLR (Common Language Runtime).
As you can see from the test results below, the Xeon managed to take the lead by approximately 8%. Why? Well, the one interesting piece of information that the .NET JIT (Just in Time) compiler takes into account during the compilation to native code is CPU architecture. According to a Microsoft MSDN article published by Allan McNaughton from Intel, the .NET JIT compiler takes CPU architecture into account during the last phase of compilation to native code. Specifically, during compilation, the JIT will detect Intel processors and produce code that takes advantage of Intel NetBurstTM and Hyper-Threading technology. With version 1.1 of the JIT compiler, Intel's Streaming SIMD Extensions 2 can also be a factor. At the time of publication, no information regarding any performance enhancing optimizations that occur for the AMD Opteron were found.
Facebook
Twitter
RSS
48 Comments
View All Comments
Questar - Monday, October 18, 2004 - link
#25,RTFA, the numbers are all there. Now who's the joke?
Phiro - Monday, October 18, 2004 - link
Good article - we currently exclusively use clustered dual-P4 cpu boxes w/hyperthreading enabled & Windows 2003 for our web clusters, and the .net side of it gets larger every day, so this quick review was right on the money. The one thing I would have added was a quick cost comparison for the like servers.People, you may all beg and cry for things like Linux testing, Windows 64 testing, etc. etc. but given the simple constraints on this article - basic web server comparison using hardware & OS's and software that's actually in production at most Fortune 500 companies - that's useful to some of us. I'm sorry they didn't benchmark this with Raptors, 42 sticks of ram and the latest beta nvidia drivers, but this wasn't a "how high can we max out web server performance" - they write those on odd-numbered days :)
PrinceXizor - Monday, October 18, 2004 - link
That infoworld "review" was a joke. No benchmarking numbers, just the reviewers own subjective opinions. There may be some grain of truth in the multi-tasking vs. non multi-tasking strengths of the Xeons. But, its impossible to say from that "review". There was virtually no useful information for evaluating the platforms. Its no wonder that most useful reviews are from on-line hardware sites like AT, [H], TechReport, THG, etc.P-X
WooDaddy - Monday, October 18, 2004 - link
BIG problem with this review. HOW MUCH DO THEY COST!?!No self-respecting company would purchase a server without performing a cost/performance ratio.
My assumption is that the Opteron system is less expensive.. that being said, then the review is moot. Equally priced systems should be used. My next assumption is that then the new Opteron system would spank the Intel...
But unfortunately, I'm an AMD fanman.
Questar - Monday, October 18, 2004 - link
That should say that testing of Opteron vs Xeon with workstation class loads has already been done by othersQuestar - Monday, October 18, 2004 - link
Testing of Opteron vs Xeon has already been done by others:http://www.infoworld.com/article/04/08/13/33TCwork...
To quote:
"What we found was eye-opening. The Opteron machine outperformed the Xeons when lightly loaded with minimal multitasking, but once the real work started, the Opteron stopped. It was effectively shut down by the same multitasking load that the two Xeons performed with ease. In the clean environment, it still performed at less than half the speed of the older and allegedly less-capable Xeons."
allnighter - Monday, October 18, 2004 - link
I feel sorry for all my fellow AMD fans for getting so defensive over one test result. Especially when clearly stated that the application uses optimized code for Intel processors. What's the big deal? Anyone surprised?Jeff7181 - Monday, October 18, 2004 - link
#19... since you obviously didn't read the other posts or the article and just looked at the graphs... the fact that the Intel solution was faster than the AMD solution in .NET is more likely due to the fact that .NET has been optimized for the P4.MightyB - Monday, October 18, 2004 - link
I think it is nice to see Intel finally beat a opteron .. they only had to make a 3.6Ghz and beef up the cache before they could match it :-).. The only thing this review lacks like all others is to mention the prize difference.. how much more do u pay to get those 8% in .NET....??Best regards
LittleB69
Rohde - Monday, October 18, 2004 - link
#10 - Since they only used a single pair of memory sticks, Numa would not have made a difference.If instead they attached 1GB of memory to each processor, we probably would have seen better performance in all benchmarks since one CPU would not be taking a memory latency hit with each access.