Slashdot Mirror

Looks like one of these doodads to me:

http://www.xbitlabs.com/articles/memory/display/oc z-booster.html

Secondly, EM64T processors are expensive, server-oriented Xeons.

It wouldn't make much sense to compared them with cheap desktop Athlon64s.

It would make perfect sense to compare socket 939 Athlon64s to EM64T Pentium 4s on 925X chipset, but I don't think EM64T P4s are easy to get without purchasing a whole workstation (oddly, boxed EM64T P4s are available in Japan). Can't Anandtech mooch a CPU from Intel for review purposes?

But a dual-core Itanium with 24 MB of on chip cache is much harder to make than an Opteron with 2 MB of cache. AMD will pass through 10,000 chips/month well ahead of Intel.

Somehow a Slashdot thread on Itanium and Opteron did not get into the Intel section.

Putting two Opterons next to each other with their hypertransports talking to each other is so easy that I suspect AMD's first silicon worked.

Note that Intel has shown a wafer of dual-core Itanics but has not yet shown a working one. Surely they would rather have shown a working one if they could.

Maybe he is looking for a computer with built in perfumer:
First Look at ABIT DiGiDice: What Does a Barebone Smell Like?

Seriously, some problems with computers might be related to them being infumigated with
bromine-based flame-retardants. Which is as useful and effective as DDT were, in more ways than intended.

I still don't agree, since I don't see any scenario in which anyone would *care* about the very, very SMALL loss of precision in the output device. Well, okay - YOU seem to care, but I can't for the life of me figure out why.

Personally I don't care particularly, I'm not going to notice, but it's virtually free. Why have "almost good enough" or "good enough for most people" or even "good enough for virtually everyone", when you can do better at almost no cost. To me, your stance is really quite similar to "640K should be enough for anyone". It's an unnecessary and artifical arbitrary limitation.

Your arguments about monitor variation are fine as far as they go, but they don't apply in every case. You can color calibrate monitors to be accurate across the screen and to a standard. People who care about color do these things now. LCD monitors also don't suffer from the same degree of variation as CRT montiors. See those links above.

Do a bit of research and it's clear that increased color precision isn't just considered a good idea by a lot of people, it's on the way. You can buy graphics cards today with 10 bit DACs, and I'm sure even better for broadcast systems. You can buy LCD monitors with > 8 bit precision (like this one). 8 bits may be good enough for you, but some people are clearly willing to pay for better.

I won't get into the CD debate. Obviously plenty of people feel 16 bit 44 kHz isn't good enough or there wouldn't be several competing higher quality formats around. But for most people the addition of video and more than two channels are far more compelling than increased music quality, which is why plan old DVD seems to be winning the next generation music format war.

Though Xeon-Nocona has been available for more than a month it seems there there are no substantial reports on 64-bit performance of Nocona. Is there anyone here who can report anything about the 64-bit performance of Nocona?

IO-0--1--2--3-IO
| |\/| |
| |/\| |
IO-4--5--6--7-IO

Most of these worms exploit buffer overflows.

Just like most exploits under Unix systems.

I think we'll see less occurances of theses worms when NX-compatible processors become common.

Like AMD64 processors...

Correct link: Meeting First Socket 939 Processors: AMD Athlon 64 3800+ and Athlon 64 3500+

That's a big assumption. AMD has always tried to keep a per-die cost lead on Intel. They do this by keeping their die-size down so that they achieve higher yields. That's why most of AMD's future low-end Athlon 64s have 1/2 as much L2 cache as the Pentium-M or P4 Prescott.
Actually Intel's adoption of 90nm & especially 300mm wafers make most analysts believe they have cheaper production costs. AMD before had smaller die size on athlons to compensate for 200mm wafers, but the athlon64 is 192mm^2, while pentium-m is 82mm^2 and the next gen pentium-m will be 84mm^2.

Um, AMD announced this in September last year.

"With coherent HyperTransport, it is inevitable that we will have multiple cores on a single chip. This is a tremendous opportunity because with our architecture the scaling is far superior to anything else that's out there., The Register quoted Mr. Sanders."

Also, see this: AMD CEO: "Dual-Core Opteron Will Shock the Hell Out of Everyone". Ruiz confirms dual core Opteron in 2005.

They say that Intel Tulsa (dual core Xeon) will arrive in about a year and Jonah (dual core Pentium M) is planned for 2005/2006.

So, nothing new here for AMD.

Um, AMD announced this in September last year.

"With coherent HyperTransport, it is inevitable that we will have multiple cores on a single chip. This is a tremendous opportunity because with our architecture the scaling is far superior to anything else that's out there., The Register quoted Mr. Sanders."

Also, see this: AMD CEO: "Dual-Core Opteron Will Shock the Hell Out of Everyone". Ruiz confirms dual core Opteron in 2005.

They say that Intel Tulsa (dual core Xeon) will arrive in about a year and Jonah (dual core Pentium M) is planned for 2005/2006.

So, nothing new here for AMD.

Um, AMD announced this in September last year.

"With coherent HyperTransport, it is inevitable that we will have multiple cores on a single chip. This is a tremendous opportunity because with our architecture the scaling is far superior to anything else that's out there., The Register quoted Mr. Sanders."

Also, see this: AMD CEO: "Dual-Core Opteron Will Shock the Hell Out of Everyone". Ruiz confirms dual core Opteron in 2005.

They say that Intel Tulsa (dual core Xeon) will arrive in about a year and Jonah (dual core Pentium M) is planned for 2005/2006.

So, nothing new here for AMD.

Um, AMD announced this in September last year.

"With coherent HyperTransport, it is inevitable that we will have multiple cores on a single chip. This is a tremendous opportunity because with our architecture the scaling is far superior to anything else that's out there., The Register quoted Mr. Sanders."

Also, see this: AMD CEO: "Dual-Core Opteron Will Shock the Hell Out of Everyone". Ruiz confirms dual core Opteron in 2005.

They say that Intel Tulsa (dual core Xeon) will arrive in about a year and Jonah (dual core Pentium M) is planned for 2005/2006.

So, nothing new here for AMD.

Actually, its on the way, and AMD seems damn excited about it :). Yes, im an AMD fanboy, but this seems pretty damn impressive...

much. Unless you are trying to simulate reality I don't understand the continued obsession with improved graphics. With the Dreamcast hadn't we reached the golden age where any game imaginable can be created? What about using stylized graphics like Jet Set Radio instead of realistic graphics? Would The Simpsons be funnier if it had more realistic drawings or real actors instead of voice actors and simple drawings which look less real than Disney's Snow White from the 1930s?

Look how anime gets away with simple "graphics", but is able to quickly communicate emotions. Same with "South Park." We need to be more worried about what we do in games and how we do it (look at the success of novelty items like the eye toy) instead of only trying to push visuals.

I understand the excitement over new graphics when they enabled new games. Pong->Space Invaders->Pac Man->Super Mario->Street Fighter II->Super Mario Cart->Virtua Fighter, but I just don't see the point any more.

Here are three screen shots; which looks most fun?
fake far cry
real far cry
gish
Personally after watching the gish movies I think it looks the most fun :) But even the fake far cry screen shot, which won't happen until far in the future, doesn't really look more fun than the real far cry screen shot.

It's actually closer to Intel's Vanderpool technology that allows you to partition the cpu through firmware.

Example: Windows is running on slice 1, BSD on slice 2, and Linux on slice 3.

BSD gets a kernel panic and crashes, the slice is restarted without affecting the remaining running OS's. It's, for the lack of a better term, Hyperthreading for the whole computer.

You can! There is a Sony external combo drive: burns cds, reads dvds, and plays mp3! Yes it is quite expansive and bulky compared to a regular walkman, but is the only one I know that reads dvds+mp3. here is a review

Here are some more benchmarks

AMDzone

AnandTech

XbitLabs

Ace Hardware

There are even more at AMDZones main page.

Ah, to get a G5 laptop.. oh well, enough dreaming and onwards with my bit offtopic comment:

This kind of article of course provokes x86/Gx comparisons. There's another quite interesting article on the G5 platform that, this being /., probably will only add fuel to the flames :)

IIRC 3DNow is different from SSE and SSE2, it isn't just a marketing name.
Here is an article on the various Intel and AMD x86 Instruction sets.

http://www.xbitlabs.com/news/mobile/display/200402 11101426.html (thank you Google)

I figured that saying this would be more effective than just bombing the parent with all my mod points.

As for Itanium not selling, That's funny. Itanium sold over 100,000 cpus last year which is a big number for the enterprise server market (That's more than some other major RISC processors sold in 2003 (like Power 4)). If you don't believe me Google "Itanium" "100,000" and "Otellini" and you'll see lots of links to Intel pres Paul Otellini's announcement back in Nov that Intel would ship over 100,000 Itanium processors in 2003.

Yes, except that Itanium's biggest competitor in the enterprise server market isn't the Power4, its G5 cousin or any other RISC chip. The Itanium's lunch is being eaten by the Xeon. If you'd Googled on the less specific "itanium sales" your first hit would be IDC Waterfalls its Itanium Sales. As that article observes, "The [100,000] number may seem relatively huge, unless we do not take into account sales of Intel Xeon processors that amount in millions."

The problem, when push comes to shove, is that for "enterprise" customers, 64-bit CPUs are still a solution in search of a problem. As of right now there aren't any applications I can think of that most businesses use where the Itanium has a pure performance advantage that outweighs the Xeon's much higher price-performance advantage. The High Performance Computing market, which is what you really referred to above, is not the enterprise market, and as flashy as HPC is, it's not where the money is, either -- go into any business using Intel architecture machines and you will see server rooms filled with HP ProLiants and Dell PowerEdges, and all of those will be P4/Xeon boxes.

It doesn't matter whether Mr. Otellini tells people he's happy with "over" 100,000 Itanium processors being shipped or not. Compared to the amount of money Intel sank into the processor, this is peanuts. If they deliver a 64-bit x86 processor and it outsells the Itanium by an order of magnitude in its first year or two, which is not unlikely, it's going to be very hard to justify not end-of-lifing the Itanium line and migrating customers to the new processor.

The other big news today was AMD's announcement of the HE and EE (wtf they mean is anyone's guess) of low-power Opterons. With these lines you get a full-scale Opteron that only puts out 35 or 50 watts! True they're expensive as heck, but they seem perfect for blades and other large-scale installations where power and AC requirements cost more than the CPUs themselves.

More information: AMD, Intel at xbit
Discussion: AMD, Intel at Ace's

The other big news today was AMD's announcement of the HE and EE (wtf they mean is anyone's guess) of low-power Opterons. With these lines you get a full-scale Opteron that only puts out 35 or 50 watts! True they're expensive as heck, but they seem perfect for blades and other large-scale installations where power and AC requirements cost more than the CPUs themselves.

More information: AMD, Intel at xbit
Discussion: AMD, Intel at Ace's

Every buyer likes prices cuts. Me, too.

But I was hoping to see a little more information about availability of the next performance jump of the Opteron to 2.40 GHz, apart from this old rumour.

It's "early 2004". I'm ready to buy a dual Opteron, but I want the best performance I can get.

AMD has arranged external financing and government support of approximately $1.5 billion during that period. The external financing is expected to include up to approximately $700 million in loans from a consortium of banks, including an 80% residual guarantee from Germany and Saxony, approximately $500 million in anticipated grants and allowances from the Germany and Saxonian governments (pending European Union Commission approval), and up to approximately $320 million in equity funding from Saxony and a group of European investors led by M+W Zander.

Some excellent points on the on the HLT/STPGNT issue--thanks for bringing it up. Based on what I've read, AMD's implementation has been buggy for a long time and they advised motherboard manufacturers to disable the required features for the sake of stability. More recently, however, they got their act together and many Athlon XP boards now properly support HLT/STPGNT. If you visit AMD's recommended motherboard list for the Athlon XP you'll notice many have listed in their notes "Advanced Power Savings with Halt/Disconnect Clock Ramping supported." There's more about the issue here.

However, I think to say that they now "just finally caught-up" isn't quite right when all issues are considered. AMD were behind on HALT, but their dynamic throttling of the CPU speed and voltage is a first on the desktop. Combine this with the lower maximum power dissipation of the Athlons compared to P4s of similar performance, and I'd say AMD has lept ahead.

Tech-Report Prescott Review
accelenation Prescott Review
Ace's Hardware Prescott Review
Gamers Depot Prescott Review
HardTecs4U
Hexus
K-Hardware Prescott Review,
Legit Reviews Prescott Review
LostCircuits
MBReview Prescott Review
VR-Zone
X-bit labs Prescott Review
XtremeSystems Prescott Review
Extreme-tech Prescott Review

I'm sure Intel will have SSE3 and SSE4 out soon and eventually AMD will license those as well

Apparently SSE3 is already in the prescott.

Sorry pal, the latest SiS/XGI Volari chip is nothing but a joke. Even with cheating drivers, the Volari Duo V8 Ultra can't even match a mid range card. Read the Club 3D preview.

If there was a functional difference, I'd be glad to concede that HP was being completely, undeniably, 100% evil. However, all the searching I've done seems to indicate that the only difference between rv250 and rv280 is AGP8X support. Probably, ATI's product portfolio is assuming that the 9200 is faster when running under 8X (which it presumably is). That's irrelevent to the current issue.

In the old Pentium days, the leap from 33MHz to 66MHz was large, and a chip that might perform well at, say, 61MHz would be sold as a 33MHz chip.

I wasn't aware that original Pentium chips were ever "sold as ... 33MHz" Thought they started at the Pentium 60 (MHz) ...link?

As for the modifying of frequencies (overclocking) and the like, as enthusiast can testify, this is nothing new. Original ATi Radeon 9500 could be hacked into 9700 pro's which I think a bigger graphics headline than this will be, since the 5950 still barely keeps up with a 9800 Pro XT.

Also, as the parent hinted at, when I was working at a local SoCal white box shop, a few articles came out over at xbitlabs about the AMD Athlon XP thuroughbred cores (_1_ and _2_). I ended up snagging a few and sure enough, if the chip had the right numbers, we could get the as high as 2800+! This, I suppose, was because they didn't pass QA testing for the model number they were intended, and had to be underclocked and sold as lower models. Great for the geeks though! :) Stability was about 99.5%. Yummy.

Keep it up chipzillas so the hackers have more things to tinker with...

In the old Pentium days, the leap from 33MHz to 66MHz was large, and a chip that might perform well at, say, 61MHz would be sold as a 33MHz chip.

I wasn't aware that original Pentium chips were ever "sold as ... 33MHz" Thought they started at the Pentium 60 (MHz) ...link?

As for the modifying of frequencies (overclocking) and the like, as enthusiast can testify, this is nothing new. Original ATi Radeon 9500 could be hacked into 9700 pro's which I think a bigger graphics headline than this will be, since the 5950 still barely keeps up with a 9800 Pro XT.

Also, as the parent hinted at, when I was working at a local SoCal white box shop, a few articles came out over at xbitlabs about the AMD Athlon XP thuroughbred cores (_1_ and _2_). I ended up snagging a few and sure enough, if the chip had the right numbers, we could get the as high as 2800+! This, I suppose, was because they didn't pass QA testing for the model number they were intended, and had to be underclocked and sold as lower models. Great for the geeks though! :) Stability was about 99.5%. Yummy.

Keep it up chipzillas so the hackers have more things to tinker with...

High end gaming cards are good for running high resolutions on a computer monitor like 1024x768 and higher. They're a total waste at 640x480 on a TV. Any budget 3D chip can play games well enough at that resolution. If the reviews are correct, the S3 Deltachrome chip in this thing is competitive with midrange cards from Nvidia and ATI.

X-bit labs - Hardware news - AMD Athlon 64 3400+ Processor is available now

AMD launches new mobile, desktop Athlon chips (IT World)

Reviews: Athlon 64 3400+

AMD extends Athlon 64 family

AMD Athlon 64 3400+ Processor launched

AMD Athlon 64 Processor 3400+ Joins the Line-Up

Anandtech is generally the best place to find information on anything you're looking for and is where all the cool kids go. They go above and beyond the call of duty in all of their reviews, and their monitor reviews are unsurpassed.

I remember that. I hate Creative for that. They hit Aureal with eroneous lawsuits, none of which they won. All the while developers and, stores steered clear of Aureal because of Creative's accusations. When Aureals money ran dry, Creative came to the 'rescue' bought them and ripped the company apart. I haven't bought a creative card since the Awe64 gold. On my lastest PC I proudly own a Nvidia Soundstorm sound processor integrated on the motherboard. Nvidia announced they are intending to sell this as a stand alone product so Creative better watch out!

According to the Mercury Research numbers released just a couple weeks ago (found here), the overall graphics market is split as follows:

Intel: 35%
nVidia: 25%
ATI: 22%
Via: 9%
SiS: 8%
Matrox: 1%

For discreet graphics chips, ATI and nVidia absolutely dominate with over 90% combined market share. nVidia has the lead in desktop discreet units with 62% (ATI has 32%). ATI has the lead in mobile discreet units with 71% (nVidia has 21%).

However, in the quickly growing integrated space, Intel does quite well with 67% desktop units and 45% mobile units, enough to give them the overall market share lead.

Particularly given that we don't know if he left the spool on his IDE drive (fragmented) and copied it to (a presumably contiguous section of) his SCSI drive.

Frankly that's the ONLY way these numbers make sense.

Yes: SCSI can be faster -- but in my experience it's very rarely more than 10-20% for middle of the road scsi vs ide mainstream cheap (often very close to top of the line!)

Found one study that did the IDE RAID vs SCSI SLED comparison.

AIST is getting a similar scale Linux cluster using Opteron processors, a bit larger (are all the G5 dual proc boxes? If so things are still in the same ball park). about 1100 dual opteron systems, and a few other Intel boxes tossed in. One good article is here.

I have submitted this as story, but it evidently never news like the G5 cluster... Linux and AMD no longer our favorite 'underdogs' anymore?

See Rambus XDR 128-bit 6.4GHz DRAM (100GB/sec+ bandwidth) due in 2006.

Sorry to reply to my own post - I was wrong. The G5 dissipates 95 watts of heat. The PIV dissipates between 85 and >100 watts

Here are some more benchmarks

AMDzone
AnandTech
XbitLabs
Ace Hardware

There are even more at AMDZones main page.

NVIDIA doit ce bon resultat au GeForce FX 5200, puisque la firme de Santa Clara s'octroie 70 % de parts de marche sur le segment des GPU DirectX 9 d'entree de gamme.

C'est comprehensible, son principal rival ATI n'a que le Radeon 9600 (non-pro) a mettre BSD face au GeForce FX 5200, et il est plus couteux que ce dernier.

On ne peut pas vraiment dire qu'ATI soit present BSD sur le marche des GPU DirectX 9 d'entree de gamme. Sur ce segment "value", dans sa globalite, ATI en est encore a DirectX 8.1 avec le Radeon 9200 qui mine de rien est base sur une architecture commencant a prendre de lage.

Ceci etant dit, on se focalise sur DirectX9, alors que ce n'est pas forcement le cas des grands fabricants de PC BSD. On aura bientot l'occasion d'en reparler, ATI annoncera quelques design vin que NVIDIA aura probablement du mal a digerer FreeBSD.

Sur le marche des chipsets integres Mercury Reseach rapporte que NVIDIA perd du terrain, ses parts de marche passant de 7 a 3% Neanmoins, ces chiffres ne sont pas significatifs car Mercury Reseach a modifie son mode de calcul BSD. En effet au premier trimestre Mercury Research prenait en compte les southbridge MCP dans le comptage des chipsets integres alors que desormais, et c'est plus logique BSD seuls les IGP sont comptabilises. Au deuxieme trimestre NVIDIA aurait livre 600 000 IGP pour 1.1 millions de SPP.

Le marche des portables est toujours domine par ATI (voir cette news), et NVIDIA aurait encore perdu du terrain au deuxieme trimestre. NVIDIA compte neanmoins BSD sur ses GeForce FX Go pour se refaire un sante au troisieme trimestre.

NVIDIA doit ce bon resultat au GeForce FX 5200, puisque la firme de Santa Clara s'octroie 70 % de parts de marche sur le segment des GPU DirectX 9 d'entree de gamme.

C'est comprehensible, son principal rival ATI n'a que le Radeon 9600 (non-pro) a mettre BSD face au GeForce FX 5200, et il est plus couteux que ce dernier.

On ne peut pas vraiment dire qu'ATI soit present BSD sur le marche des GPU DirectX 9 d'entree de gamme. Sur ce segment "value", dans sa globalite, ATI en est encore a DirectX 8.1 avec le Radeon 9200 qui mine de rien est base sur une architecture commencant a prendre de lage.

Ceci etant dit, on se focalise sur DirectX9, alors que ce n'est pas forcement le cas des grands fabricants de PC BSD. On aura bientot l'occasion d'en reparler, ATI annoncera quelques design vin que NVIDIA aura probablement du mal a digerer FreeBSD.

Sur le marche des chipsets integres Mercury Reseach rapporte que NVIDIA perd du terrain, ses parts de marche passant de 7 a 3% Neanmoins, ces chiffres ne sont pas significatifs car Mercury Reseach a modifie son mode de calcul BSD. En effet au premier trimestre Mercury Research prenait en compte les southbridge MCP dans le comptage des chipsets integres alors que desormais, et c'est plus logique BSD seuls les IGP sont comptabilises. Au deuxieme trimestre NVIDIA aurait livre 600 000 IGP pour 1.1 millions de SPP.

Le marche des portables est toujours domine par ATI (voir cette news), et NVIDIA aurait encore perdu du terrain au deuxieme trimestre. NVIDIA compte neanmoins BSD sur ses GeForce FX Go pour se refaire un sante au troisieme trimestre.

"3ware has on-board logic to handle most of the RAID protocols independently of the main CPU, including RAID 5 and variants. The low-end guys do all this work in their driver, which is one of the reasons the are unlikely IMO to open source them."

That's because they have an on-board cpu, coupled with some FPGA's, and memory.

Obviously the only reason you chose Opteron was to get the price as high as G5's, because performance it certainly wasn't. It barely beats the Athlon, and is totally toasted by the P4.

Not that I'm surprised though. It's the modus operandi of comparions trying to prove that Macs really aren't that expensive to show the specs for a completely pointless PC so as to get the price really high and keep performance down.