Slashdot Mirror
The Mother of All CPU Charts
||Plazm|| writes "Tom's Hardware has an entertaining read on the latest offerings from processor makers Intel and AMD. Not only does it contain a plethora of benchmarks on the latest Dual core CPU's, but it also includes benchmarks from over 60 other legacy processors. Better yet, they let the benchmarks speak for themselves and let you draw your own conclusions. You may want to fill up your 44oz mug before sifting through this one, though."
Summary: AMD wins every single result except the synthetic Sandra benchmarks, which Intel wins quite convincingly (all except one test). Something tells me there's something slightly wrong with that benchmark.
It's a lot like slashdot used to be
You must be new here
[Fuck Beta]
o0t!
I'd like to see a comparison of average cost against the speed, since the real question is what's the fastest speed I can get for the money.
KeepTrackOfIt.com - Find the lowest gas prices in your area graphically
Processor throughput has increased tremendously. Clock speed has not increased. Issue widths are wider. Larger, faster, and more effective caches are being used, in addition to the introduction of trace caches. Branch prediction continues to gets better, along with speculation techniques. More physical registers and larger lookahead windows allow modern CPUs to pull more parallelism out of single threaded programs than ever before.
Features like hyper-threading and dual cores give a much greater system wide speedup than simply raising the clock rate, and avoid all the problems of power consumption. Even on single thread performance, having another core to run the OS, so your not constantly context switching, can make a differance.
Reading this article made me sick, because they equate speed with clock rate. This is patently false, as the last two years of computer architecture have shown us.
-- the computer doesn't want any beer, no matter how much you think it does. NEVER, EVER feed your computer beer.
I didn't say that clock speed = performance, however, an increase in clock speed on the same architecture does indicate a probable increase in performance. I'm also sure you know that it is arguable at best that hyperthreading increases performance.
I'm also not sure where you got the impression that the article equated speed with clock rate - if they did, why did they bother with all those benchmarks?
As an example of the stagnation of the past few years, I have some code whose critical loop is unparallelizable (each instruction relies on the result of the previous instruction). My dual core Opteron running in 64 bit mode performs only about 15% better than my dual Athlon MP system from about 3 years ago. Synthetic benchmarks show a little more improvement, but largely only when memory access becomes a factor.
I'm not talking about servers, where parallelism is a necessity, or even general computing, I'm talking about unparallelizable, single threaded code. In this area, progress has been very slow. I'll grant you that the market is not as important in the scheme of things, but it is still there. Given how obsessed Intel in particular has been with clock speed to this point, it makes me wonder if they have gone to dual cores and such because they couldn't get more clock speed, which raises the question of whether we are hitting the physical limits of miniaturization.
btw, if you're the R K Callaghan i think you are i know where you live ;)
:)
~Rebecca
That just might be the creepiest reply I've ever gotten on Slashdot. Though, all the same, feel free to send your guess to my userid at gmail.com
I'm probably not the only one on slashdot who tends to accumulate old hardware. As I think many of the collectors here might sympathize, often the pieces are obscure/generic brands for which not much information is available. In fact, even some of the brand names often no longer have any documentation. Locating drivers has become an easier task, but performance features and such are still hard to find. I have an old 486 class motherboard which I found out (only from talking to older folks) was very well regarded by those who used it. But it was very hard work trying to find anything to coroborate those casual conversations on the web. Charts and tables like the ones compiled by THG can give a good idea about which pieces should be paired up for an appropriate system that avoids unnecessary bottlenecks. I really wish this kind of information exists for soundcards, video cards, and modems in the form of a giant database of hardware products from the past as well as the present.
Stay sentient. Don't drink bad milk.
Tom's hardware makes the list.
It's a massive undertaking to create it.
That's news.
Is it really news every time they update the list?
Yes, this is news. This is the time of year that many people, myself included, plan on buying computer upgrades. Based on Tom's charts, I can see my (older) CPU, compare it to newer CPUs using the video card, memory, etc. as a control, and decide if the upgrade is worth it. Although Tom talks about the latest and greatest all the time, only once or twice a year does he put things in perspective with older hardware. Personally, I want to see the same thing but with video cards, because Tom's article showed me that upgrading my CPU isn't worth the money.
Besides, Tom is talking about computer hardware. Nerds (myself included) love this stuff. So yes, this is news for nerds. And it does matter.
24 beers in a case, 24 hours in a day. Coincidence? I think not!