Slashdot Mirror
Previewing the Performance of the Intel Conroe
pirate rtt writes "bit-tech has spent some time with an Intel Conroe system and has published a preview of its performance as compared to the current Intel flagship chip - the Presler 965. From the article: 'Core 2 Duo is clearly a very capable processor. We found that it was faster than the current 965 processor in most situations on the desktop, and far more proficient at gaming - an area where Intel has traditionally been weak. The added memory bandwidth that will come from having faster RAM enabled on the Core 2 Extreme chips will be an extra bonus for those looking to Conroe as a gaming platform.'"
Core 2 Duo is clearly a very capable processor
Version 1 of anything always sucks. I'm waiting for the Core 2 Duo II v2 Second Edition.
I'll probably be modded down for this...
And now for Conroe vs. AMD's Athlon FX-62 (and presler).
Yes, the FX-62 does lose... badly in several cases..
I've been holding out upgrade from my old pre-MT 2.8 GHz P4 for a while now, and the Intel Conroe was going to by my choice for my new computer. Glad to read that it's actually kicking ass for games like it's supposed to. I still haven't decided if I'm going to go with ATI or Nvidia, though.
Bruce
Are reviews like this of any real significance?
Every non-trivial chip has errata.
They get fixed in microcode, or they're published in the errata of the chip so OS developers can work around them. Bugs that end up visible to userspace are very rare indeed.
I rarely criticize things I don't care about.
There have been Conroe previews several sites, all of them using intel preconfigured boxes. The only way to make sure of Conroe's performance is to benchmark it once its bought. I'm sorry if I'm a bit of a sceptic, but I don't trust these boxes made by Intel to market Conroe.
I'm waiting for the 400 page Tom's Hardware review!
So take these results with an even smaller grain of salt. Goddamn benchmarks.
I can see it now... snoop dogg sitting with a laptop getting his hair braided on the porch; camera pans up to his head and snoop yells, "Not that Cornrow my shizzel". The camera pans back down and focuses on the laptop. Intel Logo appears *Cha-Ching*
---------
http://akurl.com/ - Long Urls Don't Stand a chance
It's good they are faster than Core 1, but it's interesting to see if they've surpassed the top P4 chips in speed.
As you know Intel basically dropped the P4 architecture (netburst) in favor continuing the hardware line of Pentium III -> Pentium M (Core 1 was a mod of Pentium M, Core 2 is a more serious change adding back 64-bit, but still a development of the same architecture).
Both the operating system and benchmarks were installed by Intel performance engineers, so we cannot guarantee that the bit-tech configured operating system was in the same state as the one on the Intel-built Core 2 Duo machine. We were not allowed to make any changes to the Intel-built system. ...
The real question to most of the rest of the world is: how do these chips handle regular desktop duty? I mean, all we've seen tested is a high end chip versus a high end chip, not mid-range testing. Conroe is supposed to replace Pentium 4s almost everywhere, with single-core variants or Pentium Ds handling the low end. Where does that put us for a $1200 or $1500 computer from Dell or Gateway that everyone else is going to be buying. In my mind, the real issue is how this helps the huge mid-range of consumers and computers, not the 2% upper end that can afford ATI Crossfire X1900XTXs.
.. Beowulf cluster of these?
The benchmarks show a serious drop in multi-tasking capabilities in Conroe relative to the P XE 965. In some cases, a multi-tasking Conroe was beaten by a multi-tasking PXE.
However, we have some worries about its multi-tasking performance, which doesn't appear to be quite as good as the chip that Conroe will be replacing later this year.
We found that it was faster than the current flagship Pentium Extreme Edition 965 processor in nearly every single-threaded scenario, but there were times where Conroe fell behind in multi-tasking scenarios.
That seems pretty bad if we're trying to move to a more multi-threaded and multi-tasking computer system (yes, I know the difference between the two).
So, this isn't so much as Intel stealing the crown as re-claiming the thrown.
<shrugs>No big deal .. I just get tired of the Intel bashing crowd. "OMG INTEL IS TEH DEVIL, AMD IS OUR SAVIOR!!"
/dev/random
Looking forward to seeing graphics/rendering benchmark comparisons such as with Softimage, Maya, Modo and server benchmarks testing OpenSSL, DB, etc. performance. So far I see perhaps one game benchmark that stands out while the rest are ho hum. Not impressed.
The Core 2 Duo chips are all x86-64 (or ia32e as Intel calls it). I can't believe that it has taken them so long to do this for (what will be) their main consumer line.
One of the things I did't like about the MacBook Pro (and that helped me decide to stick with my 1.67 GHz PB G4) was the Core Duo. I know was much faster than what I had, but I don't want to buy a new laptop just to have it be 32 bit and obsolete (as far as I'm concerned). I wanted a laptop that would last me years. I wanted something with a 64 Bit processor.
There are other little things, like the reports of how noisy they are (relative to my PowerBook) worry me some. I think Intel still has a massive heat issue.
But really. It's about time Intel started shipping 64-bit processors to everyone. I think that is the important thing here. After all, if they could find a way to clock a P4 to 6 GHz it may cream AMD but it could still be 32 bit (depeding).
Comment forecast: Bits of genius surrounded by a sea of mediocrity.
Is this really necessary for gaming ? An Athlon 64 with a decent videocard and a gig of RAM is enough to run any game well and keep it looking great. Why do I need this ? High end CPUs out now are more than good enough.
Unless of course, you're one of "those" types of gamers, needing to buy the latest, greatest and most expensive tech possible in order to run your games as well as someone else who spent $1000 on their system.
Intel is a much bigger company, they have a lot more money, a lot of smart people, the nastiest, sleaziest marketers in the business, many more fabs, and great lawyers to fend off the AMD legal strikes too. The Intel 'Prescott' was supposed to do the job on AMD but it never came close. Now, though, the 'Conroe' looks like it is FINALLY the answer to AMDs stuff. Based on the benchmarks using Intel-supplied hardware and software, it looks like the 'Conroe' line of processors totally destroys the AMD FX-60 which is the fastest AMD processor sold today. Of course, you can't buy the 'Conroe' until September, 2006 but it will be worth the wait, based on the benchmarks anyway.
The only thing AMD has to offer is a little bit faster clock speed (aka FX62) and their upcoming AM2 socket systems which don't seem to do much of anything new other than allow DDR2 memory and a bigger cache. Looks like AMD is headed back to the bargain bin.
Listen p*ssy. I'm sure your the same homo that posted earlier about alf's boner and you just want to remain anonymous fo
With AMD taking the performance lead now and Intel gearing up for getting the top performer position again, I think we are going to see nicer battles now, much nicer than the GHz ones with AMD now much better in its market position and its new fabs.
Listen p*ssy. I'm sure your the same homo that posted earlier about alf's boner and you just want to remain anonymous fo
Okay, let's start the official pool for how big Tom's Hardware review will be.
I'm guessing 23 pages.
When I was studying Computer Science in College I took a Parrellel Programming class. One of the first things my professor taught my class was that not all tasks are well suited for parrallel processing. In many cases it is more difficult to break the task up into smaller tasks and hand off to other processors or cores. In many cases performance will be significantly degraded by parallelizing a task that is not well suited to multiprocessing.
During several of the tests, the author of the article ran single threaded and multithreaded tests. In some of these tests, the performance of both the Conroe and Pressler chips decreased. The author incorrectly states that the multitasking performance of the Conroe chip is lower than the Pressler chips. He is incorrect becuase his own graphs reference multi-threaded performance. These are two entirely different things. While the multi-threaded perfomance of Conroe is slower in some cases, the single threaded performance was faster in most cases. These tasks obviously are not tasks well suited for parallel processing, and as such should be coded to run as a single thread to keep performace high.
While the rest of the benchmark seems solid, his analyis should be brought into question as he doesn't seem to have a solid grasp on his technology vocabulary. That or his editors don't know what they are reading either. If that is the case their reviews should not be showcased.
I really hope that boards based on 965 chipset will be cheaper than current ones since a good s775 overclocking board retails here around 160 euros (955) and 180 euros (975). That's quite steep indeed. Otherwise for example celeron 356 would be ideal for budget overclocking. Anyways I'm happy to see more competition which will lower the prices and force fanboys to come up with new arguments. Funnily enough everything has worked so far no matter the brand, even the z80.
I'm sure there's more than enough people here who remember how intel poorly comparbadly the K6 ran Doom, for example.
Not to mention the atrocious record of motherboard chipsets for >K6 AMD processors that, alone, contributed more to slowing their uptake by the market than any other factor (it astounds me that VIA has managed to stay in business).
Next Gen CPU faster than today's
We found that it was faster than the current flagship Pentium Extreme Edition 965 processor in nearly every single-threaded scenario, but there were times where Conroe fell behind in multi-tasking scenarios.
I think that's a very funny quote. This is exactly what I was expecting all along. The reason most people have been running Super-PI and other toy benchmarks is because they are single-threaded, and that is the one area where Conroe really shines.
If the Conroe can't beat the Pentium Extreme Edition 965 how is it going "own" or "destroy" an Athlon 64 FX-64? The Conroe myth gets busted a little bit every day.
I am a viral sig. Please help me spread.
The main problem is that most benchmarks used today are really lame throwbacks to a time when all code was single threaded running on machines without any other processes. Even the recent supposed "multithreaded" benchmarks run the same code on every thread sharing the instruction cache between threads. A better benchmark would to run a dozen unrelated Linux tasks simultaneously with data sets 100 times larger than CPU cache and measure the aggregate time. This would be a better approximation of what actually goes on in a typical web server or desktop PC running all sorts of multimedia apps.
Intel asskissers from all over the world, this is your chance. Lick Intel's ass and maybe you'll get a discount for the next version of the Celeron.
Well, the claim is that the chip they were testing wasn't a flagship chip like the Pentium EE. In other words, they were testing a chip that's supposed to debut a couple price points below (2.67 GHz clock) the top-clocked (2.93 GHz) Conroe EE.
The inference being that the new top Intel chip will totally kick the Pentium EE's butt. Or, if you like, that this chip offers the same or better performance than the Pentium EE at what will probably be something like $200-$300 less.
Of course, that's all speculation, but the fact remains that this is not the top Conroe chip that's ocasionally losing out to the fastest Intel currently offers.
You can't even buy an FX-62 yet (I just checked newegg). How is it tried and true?
Guess how those who benchmarked the FX-62s got them? They got them as favors from AMD. And they were given them on the condition they not benchmark them against Conroe! So why do you trust them and not the Conroe reviewers?
Anyway, the people on xtremesystems.org have Conroes already, and on their systems, not under the eye of Intel. They seem to like it.
This just seems like more smokescreen from the AMD fanboys. Why do people suddenly develop a case of not trusting internet benchmarkers when it starts to make Intel look good?
http://lkml.org/lkml/2005/8/20/95
No self respecting gamer will run a game at 640 x 480 resolution, especially with minimum detail, so posting benchmarks at that resolution is moot.
There are many sites that do good benchmarking, and I wish other sites would follow the lead of anandtech and tom's hardware. Rather then a bunch of numbers for unrealistic senarios, put together tests that cover all the bases. Where is video encoding benchmarks, where is compiling benchmarks? Where are REAL benchmarks for senarios we all use. Showing us how well the CPU can run at some obscure resolution with no graphics details just proves that CPU's today are more then capable of running a game at 100+ fps in VGA mode.
Also, why not post results running same the benchmarks at least on AMD's flagship. I don't care if the Conroe performs faster for gaming then the PEE 965, I want to know if Intel finaly can outperform AMD with their next generation architeture for gaming, of if I should stick with AMD for another generation.
I haven't thought of anything clever to put here, but then again most of you haven't either.
Hyperthreading was added to the Pentium 4 to counter the defficiencies of the architecture:
* DEEP pipeline
* relatively small (12K words) trace cache
* tiny 16KB L1 data cache
* huge main memory latency (compared to on-die memory controllers)
By running two threads in parallel, if one thread encounters a cache miss or a branch mispredict, the execution units are not left entirely empty while waiting for a pipeline flush or context switch. Instead, the parallel thread takes over and makes good use of the core.
You are correct that it is no longer necessary. The much shorter pipeline, combined with larger, lower-latency caches of Core and Core 2 make cache misses much less likely, and reduce the performance hit for branch mispredictions, which allow the processor to more fully utilize performance units.
Man is the animal that laughs.
And occasionally whores for Karma.
For AMDroids picking up on that statement, I would like to remind you that the 965 EE has 2 cores + 2 hyperthreaded virtual cores. Despite HT being much maligned it is useful in exactly the kind of situations where the Presler handily beat Conroe.