Slashdot Mirror

If you goto the link in the article, which leads you to their review of the Savvio 15k, you'll notice a noise comparison on page 12:

http://techreport.com/reviews/2004q4/seagate-savvi o/index.x?pg=12

even better than solid caps is NO caps with Digital VRM

I have posted an update to my initial look at AMD's 65nm processors here:

http://techreport.com/onearticle.x/11486

The update addresses some anomalies in L2 cache performance and raises some possibly related questions about die sizes for the 65nm Athlon 64 X2. It appears this chip is not just a die shrink with the same performance characteristics, after all.

http://techreport.com/reviews/2006q4/xeon-vs-opter on/index.x?pg=7

Very interesting. The benchmark uses a database and is the only one I've seen that seems to test the limits of the CPU cache with a database.. and low and behold, at 8 threads, performance degrades for the 5355 and it's actually slower than the opteron 2218.

Or it could just be that this benchmark isn't coded well - it might use a global lock frequently so as you add more threads there's more contention. In any case someone with more time than me should dig into this benchmark which might show a weakness in the core 2 architecture.

Finally, good benchmarks. Where were these guys a month ago before I ordered those 5320s and when will those 5355's be available for the rest of us.

I would love to see the creation of a drive that can accept ECC-capable memory (perhaps 8 slots that can handle up to a 4GB stick each), utilizes the SATA-2 (3.0Gb/s) interface, and has a series of rechargeable batteries as a backup when power is completely out.

Em, I think you can already get them.. Why bother with SATA-2 etc when you can hook directly onto the PCI or PCIe bus?

I believe you're right. Lets do some simple calculation:

This HD has 600 000 hr MTBF max and transfer rate of 300MB/s.
Say you transfer at this rate for all its MTBF life thats
600 000 hr * 3600s/hr * 300MB/s = 648 000 000 000 MB or 6.48 petabytes max transfer in its life

MTBF(sec.) * Transfer rate = Max lifetime transfer

Normal flash has 300,000 write cycles/block amortized among N GB blocks (block = byte) so thats 300,000 * N cycles with (comparable)max rate of 300MB/s or 90 000 000 * N MB max transfer in its lifetime.

(WC * n blocks) * Transfer rate = Max lifetime transfer

MTBF = WC * N blocks

N = MTBF/WC -> higher write-cycle flash needs less space to approach MTBF of HDs

N would need to be about 64 800/9 MB or ~7.2 GB capacity to approach the lifetime transfer of a hard drive. I realize that with each failing block, size of the flash would be shrinking, but the total failure of the flash would occur when no blocks could be written to. This is just a rough comparison of the two. Also I assumed the same transfer rate as the HD which is not very realistic, but its there to show a rough comparison.

As you can see a 100GB or so flash disk with a 1,000,000 block write-cycle would more than surpass the MTBF in current Hard Drives.

I think the ultimate point will be the $/GB. I don't think that Flash can compete with Hard Drives in that department, not yet anyway. Perhaps we will see them as a buffer(it's already being used in Vista) between Hard Drive and main memory. And eventually(!?) overtake HDs. We can always hope..

anandtech's review of the Core 2 Duos indicated that power consumption was really about the same across the board. The AMD EE chips were the least-power hungry, with just about every other chip all in a small span. Methinks someone's test procedures aren't quite accurate

A Tech Report article on AM2 chipsets shows that the nForce 590 chipset consumes about 20 watts more than the ATI RD580 (CrossFire XPress 3200) chipset at load. However, the power-hungry nForce 590 chipset has more integrated features: 2 gigabit ethernet chips (RD580 has none), 6 SATA ports (RD580 has 4), and more RAID options. That's probably why most high-end CPU reviews I've seen have used the nForce 590 chipset.

An Anandtech article shows that the Intel 975X chipset consumes about 3-5 watts more than the more current P965 chipset for certain apps, but unfortunately they don't have "load" comparisons. The P965 chipset lacks SLI support, so that's probably why reviewers are using 975X.

So a comparison of platforms that "most people buy" should probably use the Intel P965 chipset and the nForce 570 Ultra chipset. It's too bad review sites tend to use the SLI uber-chipsets.

anandtech's review of the Core 2 Duos indicated that power consumption was really about the same across the board. The AMD EE chips were the least-power hungry, with just about every other chip all in a small span. Methinks someone's test procedures aren't quite accurate

A Tech Report article on AM2 chipsets shows that the nForce 590 chipset consumes about 20 watts more than the ATI RD580 (CrossFire XPress 3200) chipset at load. However, the power-hungry nForce 590 chipset has more integrated features: 2 gigabit ethernet chips (RD580 has none), 6 SATA ports (RD580 has 4), and more RAID options. That's probably why most high-end CPU reviews I've seen have used the nForce 590 chipset.

An Anandtech article shows that the Intel 975X chipset consumes about 3-5 watts more than the more current P965 chipset for certain apps, but unfortunately they don't have "load" comparisons. The P965 chipset lacks SLI support, so that's probably why reviewers are using 975X.

So a comparison of platforms that "most people buy" should probably use the Intel P965 chipset and the nForce 570 Ultra chipset. It's too bad review sites tend to use the SLI uber-chipsets.

Another smart (but a little slimy) marketing move Intel has made is in the power dissipation numbers. AMD quotes their CPU's maximum dissipation, and Intel quotes a power figure for some arbitrary (under 100%) CPU load. Intel looks good here....until you actually measure a system's power draw at the outlet, and find that again, there's not that much difference.

However, there appears to be a very significant difference in power usage (at the outlet) that favors Intel's platform at all price/performance levels. The Tech Report's recent review of Intel's quad-core CPU showed the Core 2 Duo systems drawing way less power than comparable Athlon x2 systems. For example, the E6300 system drew 153 watts at load while the x2 4200+ drew 191 watts. The E6700 system, which clobbers AMD high-end CPUs in price/performance, only drew 156 watts at load while high-end Athlon 64 x2 CPUs drew 200 watts and the FX-62 drew 230 watts.

Also, what's up with the AMD x2 3800+ EE system (35W TDP) drawing the same power at load (153W) as the Intel E6300 (65W TDP)? I doubt the AMD motherboard (NVIDIA 590 chipset) is drawing about 30W more than the Intel motherboard (975X chipset).

Check out The Tech Report's review, if it's scientific real-world benchmarking you want.

the FX-70 uses two dual-cores in two sockets

Only problem then is that as it currently stands, Intel is, allegedly, ahead in the process game: "Intel to hit 65nm-45nm cross-over in 2008"

I like AMD for Hypertranspart, and Intel need to go there too sooner or later, but elegance isn't going to get AMD the win in the mass market; only performance can do that (and performance per dollar at that).

Sadly (for reasons of competition), I'm afraid that Intel may remain on top unless they run into problems with 45nm and AMD can sneak up on them by things going better than smooth.

As somewhat of an aside, maybe AMD could make some gains on features, so I still think they should implement a next generation PadLock (VIAs Crypto-Engine-On-CPU). I'd like for both AMD and Intel to go there together (compatible implementations), but one is better than none.

Once you've PadLock'ed, you can't go back.

Except GPU's are at least as high transistor count as CPU's these days and based on transistor count growth GPU's will exceed CPU's in the next one to two generations.

Current GPU's are already ahead of current CPU's:
Amd X2 1mbit cache: 233.2 million transistors
Intel Core 2 Quad: 582million transistors
Nvidia 8800 GTX: 681 million transistors

http://techreport.com/onearticle.x/11109
"Furthermore, users who go through such upgrades will be allowed to re-active their copy of Vista up to 10 times."

I really dont think its as big of a deal as a lot of people are making it out to be. Here's an example of how it worked in XP:

"User swaps the motherboard and CPU chip for an upgraded one, swaps the video adapter, adds a second hard drive for additional storage, doubles the amount of RAM, and swaps the CD ROM drive for a faster one.

Result: Reactivation is NOT required."

http://www.microsoft.com/technet/prodtechnol/winxp pro/evaluate/xpactiv.mspx

Again you'd have to change so much hardware, it would be no different than installing on a new machine. And you can just call them and they give you a new key in just a few minutes... not a big deal.

Over at Tech Report

This is where I think AMD gets themselves a big win. Intel's FSB, even clocked at 1333MHz (actually it's 333MHz QDR, but we'll not quibble) pushes only 10.6GB/s. And that's not accounting for the off-die memory controller. Even with dual buses (like the 5000 series chipsets tout) they only just barely have enough aggregate throughput to handle memory transfers.

Of course, four FSBs (plus a snoop filter) is still not as efficient as AMD's Direct Connect Architecture, but Intel's current dual-processor server architecture seems to have no problem competing against AMD's current 2P Opteron.

Hahahahha. You're trolling right?

Here is the FEAR benchmark you listed only updated for Core 2 Duo and Athlon FX62.

Notice how the Core 2 Duo comes in at 44 FPS higher than the top end Athlon FX 57 from the article you linked? And that even the lower end E6600 comes in higher than the FX62 - despite costing less than half as much?

FX 60 vs Core Duo 2600? Core two duo is 6600, 6300, 6700, and 6800 all NOT on that test.
here same site correct review:

http://techreport.com/reviews/2006q3/core2/index.x ?pg=6

you pull up and old review with the wrong cpus and then say AMD is better then the newer cpus which are not even on the review.

so you can't be sucking AMD's dick, your head is up their (or your own) ass

peak power use (just okay)

The core 2 duo has a TDP of 65W (75 for the "Extreme"). The X2s had 85, then 65, and now a mere 35W, or basically half of the core 2 duo.


memory bandwidth and latency is still behind X2s, but I know you don't really care about those "facts"

Well, considering I mentioned them, you might not want to assume quite so much...

And yes, I called them "abysmal", because they haven't even caught up to the X2, despite having a year and a half since the X2s came out to play catch-up.



Poor overall performance

Would you like links to a similarly stacked test showing the X2s trouncing the C2D?

Here, how about one that matches a few of your linked benchmarks, yet shows the opposite result? Funny how that works.

Again, Intel has merely "caught up". Performing on par with an 18-month old chip, I consider a poor showing indeed - particularly when you consider that, while Intel has played its hand, AMD (beyond releasing lower power versions) still hasn't fully revealed its next gen yet.



You need to pull AMD's dick out of your mouth and try again.

Did I mumble?

Poor overall performance ... abysmal memory performance*, ... okay peak power use (just okay), it still comes in several times that of the X2s when idle

Ah, and best of all, "And I write that not as an AMD fanboy".

You need to pull AMD's dick out of your mouth and try again. If this was a troll attempt, congratulations, you got me to reply.

* - memory bandwidth and latency is still behind X2s, but I know you don't really care about those "facts"

Poor overall performance ... abysmal memory performance*, ... okay peak power use (just okay), it still comes in several times that of the X2s when idle

Ah, and best of all, "And I write that not as an AMD fanboy".

You need to pull AMD's dick out of your mouth and try again. If this was a troll attempt, congratulations, you got me to reply.

* - memory bandwidth and latency is still behind X2s, but I know you don't really care about those "facts"

Poor overall performance ... abysmal memory performance*, ... okay peak power use (just okay), it still comes in several times that of the X2s when idle

Ah, and best of all, "And I write that not as an AMD fanboy".

You need to pull AMD's dick out of your mouth and try again. If this was a troll attempt, congratulations, you got me to reply.

* - memory bandwidth and latency is still behind X2s, but I know you don't really care about those "facts"

Poor overall performance ... abysmal memory performance*, ... okay peak power use (just okay), it still comes in several times that of the X2s when idle

Ah, and best of all, "And I write that not as an AMD fanboy".

You need to pull AMD's dick out of your mouth and try again. If this was a troll attempt, congratulations, you got me to reply.

* - memory bandwidth and latency is still behind X2s, but I know you don't really care about those "facts"

Poor overall performance ... abysmal memory performance*, ... okay peak power use (just okay), it still comes in several times that of the X2s when idle

Ah, and best of all, "And I write that not as an AMD fanboy".

You need to pull AMD's dick out of your mouth and try again. If this was a troll attempt, congratulations, you got me to reply.

* - memory bandwidth and latency is still behind X2s, but I know you don't really care about those "facts"

Poor overall performance ... abysmal memory performance*, ... okay peak power use (just okay), it still comes in several times that of the X2s when idle

Ah, and best of all, "And I write that not as an AMD fanboy".

You need to pull AMD's dick out of your mouth and try again. If this was a troll attempt, congratulations, you got me to reply.

* - memory bandwidth and latency is still behind X2s, but I know you don't really care about those "facts"

You can have one hell of a CPU and memory, planted on a motherboard that would serve better as toilet paper. Anyway thats enough out of me, for now.
Thats what dogged AMD for years and probably a major reason for ondie Memeory controller The AMD boards from Super Socket 7, through to Athlon XP had really great and truly terrible north bridge chipsets giving the general market vision of poor or flakey performance.
The market for an Athlon board is fairly easy compared components
However the decrepencies in memory performance of the reviewed Core2 boards is amazing.
I still think AMD bought into ATI purely to make a rocksolid server and mobile platform
They don't want to squeeze or directly compete with NVIDIA, they are aiming at competing with Intels trusted platforms. google returned hundreds of Opteron/NVIDIA based systems due to instability.
http://techreport.com/reviews/2006q3/core2-chipset s/index.x?pg=4

All of those benchmarks where for Core 2 Duo processors (see http://techreport.com/reviews/2006q3/core2-chipset s/index.x?pg=3). While the NVidia chipset implemented hypertransport between the chipset components, none of them showed an Opteron or Athlon64 using hypertransport as a linkage to the CPU (or between CPU cores).

Why do the new Intel chipsets have just one P-ATA channel, if any at all?

It is ridiculous. 95% of all optical drives are P-ATA...

...and P-ATA hard drives as of yet are just as fast, if not faster thanks to more mature drivers and technology, than their SATA counterparts.

What do they expect people with 2+ perfectly fine last-generation PATA hard drives to do when upgrading to Core 2 Duo?

Even without the performance advantages, SATA connectors/cables are a heck of a lot more convenient. Modern motherboards have four to six little SATA ports with no master/slave nonsense. The cables/connectors (including power) are so much thinner, easier to work with, and less likely to get loose. Haven't you ever had a boot problem from a bad PATA or power connection to your hard drive (like I have)?

Why do the new Intel chipsets have just one P-ATA channel, if any at all?

It is ridiculous. 95% of all optical drives are P-ATA...

...and P-ATA hard drives as of yet are just as fast, if not faster thanks to more mature drivers and technology, than their SATA counterparts.

What do they expect people with 2+ perfectly fine last-generation PATA hard drives to do when upgrading to Core 2 Duo?

Even without the performance advantages, SATA connectors/cables are a heck of a lot more convenient. Modern motherboards have four to six little SATA ports with no master/slave nonsense. The cables/connectors (including power) are so much thinner, easier to work with, and less likely to get loose. Haven't you ever had a boot problem from a bad PATA or power connection to your hard drive (like I have)?

The K8's integrated memory controller supports much better memory throughput.

Two of the chipsets tested support SLI, the nForce 570 SLI and the nForce4 SLI X16. http://techreport.com/reviews/2006q3/core2-chipset s/index.x?pg=10 Your precious P5N32-SLI SE is even tested in the article! So what was your problem again?

Socket AM2 chipset comparison here: http://techreport.com/reviews/2006q2/am2-chipsets/ index.x?pg=1

A few corrections... yes it was a 7600gs. An 3800 X2 is not "33% more FPS" than the 3800 64. On the benchmarks it is -10% to 10% in performance depending on the game. It's basically 2 cpus@2.0ghz vs 1 cpu@2.4ghz. Which ends up benchmarking at basically the same speed for games, and also for anything else not actively using more than one thread at a time typically the X2 will actually be significantly slower.

For instance, this link for reference on X2 vs 64:
http://techreport.com/reviews/2005q3/athlon64-x2-3 800/index.x?pg=1

In actuality this core 2 duo vs 3800 is probably at gaming somewhere between 1x-1.3x judging by the benchmarks I've seen (which didn't directly compare the two). So 2.5x more expensive for even maybe 1/3 faster at everyday things (games, web browser, etc) is a pretty hard sell. At 3.5x when I bought in it was a poor choice.

I've used a dual-core for almost a year at work, where I do development, and most of the time anything is actually being done, one CPU is idle and the other at 100% (gnome-panel has a nice little rolling cpu chart so I see both CPUs all the time). Yeah core-duo is a good chip technology wise, but for the prices even 250 for e6400 is still just a fairly good deal... nothing to write home about. For everyday stuff, the second core is occasionally very fast, but no help at all the vast majority of the time.

To that end, I predict harddrive companies effectively setting up a raid 1 array on a single drive; Probably by platter.

Slow down, cowboy. I misstated my post a little: I agree that they're already a big player in embedded graphics. What I meant to say is that they're trying to gain ground in mid-level and possibly high-end graphics, where they definitely don't have products.

Why do I say this? Because of articles like these:

http://techreport.com/onearticle.x/10564

http://www.theinquirer.net/default.aspx?article=33 836

http://www.theinquirer.net/default.aspx?article=33 720

http://www.theinquirer.net/default.aspx?article=32 268

- http://www.madshrimps.be/gotoartik.php?articID=482
- http://www.hothardware.com/viewarticle.aspx?articl eid=861&cid=1
- http://www.hexus.net/content/item.php?item=6538
- http://www.mvktech.net/content/view/3357/48/
- http://pcper.com/article.php?aid=287
- http://uk.theinquirer.net/?article=33872
- http://www.reghardware.co.uk/2006/08/23/review_ati _radeon_x1950_xtx/
- http://www.techpowerup.com/reviews/ATI/X1950XTX
- http://www.bjorn3d.com/read.php?cID=954
- http://techreport.com/reviews/2006q3/radeon-x1950x tx/index.x?pg=1
- http://www.extremetech.com/article2/0,1697,2007324 ,00.asp
- http://www.tgdaily.com/2006/08/23/ati_releases_rad eon_x1950/
- http://www.guru3d.com/article/Videocards/375/
- http://www.hardwaresecrets.com/article/131
- http://www.hardwarezone.com/articles/view.php?id=2 020&cid=3&pg=1
- http://www.firingsquad.com/hardware/ati_radeon_x19 50_xtx_performance/
- http://www.driverheaven.net/reviews/X1950XTXreview /

up to date list: http://www.madshrimps.be/forums/showthread.php?s=& threadid=26526

Pretty sure a low-end AMD X2 will draw less (/w Cool'n'Quiet taken into consideration) than your P4. It wouldn't be as cheap though. In fact, the X2s will draw about the same as the single cores. The P4 is great for short-term up front cost, but long term, not so nice.

http://cmusphinx.sourceforge.net/html/cmusphinx.ph p
http://sourceforge.net/projects/cmusphinx/

It's been around for a while. I think it's pretty good, though quite resource-demanding. The peeps at the tech-report usually benchmark it.

Here for instance:

http://techreport.com/reviews/2006q3/core2/index.x ?pg=12 -core 2 duo

http://techreport.com/reviews/2002q1/athlonxp-2100 /index.x?pg=6 -early Athlon XP vs P4
    (middle of the page)

As you can see, we can do real-time sphinx now.

http://cmusphinx.sourceforge.net/html/cmusphinx.ph p
http://sourceforge.net/projects/cmusphinx/

It's been around for a while. I think it's pretty good, though quite resource-demanding. The peeps at the tech-report usually benchmark it.

Here for instance:

http://techreport.com/reviews/2006q3/core2/index.x ?pg=12 -core 2 duo

http://techreport.com/reviews/2002q1/athlonxp-2100 /index.x?pg=6 -early Athlon XP vs P4
    (middle of the page)

As you can see, we can do real-time sphinx now.

I'm not sure where you get that idea, but this chart says the x2 4000 uses between 120 and 150 watts

http://techreport.com/reviews/2005q2/athlon64-x2/i ndex.x?pg=15

The Techreport benchmarks (details here) were performed on Win XP 64 bit, with a number of the applications tested being 64 bit editions. If you look at the 64 bit app benchmarks, there's some variation (e.g. Windows Media Encoder it comes out slightly ahead of AMD's best, POVray it comes out slightly behind), but it seems pretty much neck-and-neck with AMD's current chips on 64 bit code.

The NDAs have lifted on the Core 2 Duo reviews, and you can surf on over to your review site of choice for a boatload of benchmarks and bar graphs. The Tech Report's Core 2 Duo review was the only one that didn't make me want to jab my own eyes out with my mechanical pencil after reading it, so it's the only one I'm actually going to link up here. In fact, I was so frustrated after reading a few of these reviews, that I surfed over to CNN and read up on the latest developments in the Middle East to lighten my mood.

http://techreport.com/onearticle.x/10091

There are, in fact, other uses for computers than games, believe it or not.

Tech Report's reviews are typically the best I've seen, and these are no exception, adding rendering, video encoding, audio encoding, voice recognition, and in the past, scientific benchmarks as well.

The Core 2 Duo beats the crap out of the A64 architecture just about everywhere - and LAME encoding, voice recognition, rendering, image processing, etc. By large margins - 25% or more.

The pure integer performance of the Core 2 Duo is ridiculous. The last iterations of the Netburst were still faster performers than the A64s, due to their higher clock speeds, but in Sandra's Mandelbrot iterations test, the Core 2 Duo was almost triple the performance of the fastest Netburst. Triple! And the floating-point performance is much better than the Pentium 4s, basically on par with the Athlons.

Now I know why I stopped reading HardOCP. So what if I can't see any benefit in games right now? The entire rest of the system will be faster. By far. And I'd bet you'd see performance gains in games if the system was doing other things at the same time, for instance.

June 23, though.

http://techreport.com/etc/2006q2/ecs-factory/index .x?pg=1

From techreport.com: "ExtremeTech does point out, however, that Microsoft licensed Ageia's PhysX SDK for an apparently unrelated robotics project." Could the unrelated project be related?

I have to agree. And the high-end system with only 1GB ram and a 7600 GT?

I spent only $1100 recently (would cost around $1000 today) buying a system with 2GB ram, an A64 3800+ X2 and a 7900 GT. This included a 250 GB hard drive (remember folks, Raid 0 does NOTHING for game load times), optical drive and case + PS. Not only is my system CHEAPER than Tom's top-flight system, it also performs substantally better, uses less power and DOESN'T require you to mess with annoying water cooling. It's even overclockable, I clocked it up to 2.4 GHz on stock voltage using the RETAIL AMD COOLER, and it could go much higher if I kicked up the voltage and shelled out 30 bucks for a better cooler.

Ultimately, you could build the low-end box for a similar price with a 3800+ X2, and again you could do away with that annoying watercooling. Anyone who has ever wasted a weekend chasing leaks knows what I'm talking about. If you actually want to PLAY your games instead of spending all your time fixing your system, air cooling is king.

"..as long as we move the GeForce up a few inches in the picture to compensate!" See those backplates?

Processor does not determine whether system supports SLI - chipset and GPU video configuration does so you could use Yonah without using the default Intel chipset. For instance, several vendor have Nvidia SLI validated solutions for Intel procesors. Can't think of any Core Duo ones yet, but frankly it will make more sense to do this with it's 64-bit big brother Core 2 Duo (Merom) this summer. Dell has Intel SLI desktops planned for the 'Conroe' dekstop version this summer so there's really no reason they can't do a laptop - probably will. This will be so much faster than the wimpy Turion chip it won't be funny. Since Conroe is faster than the fastest single socket cpu AMD has It's abundantly clear that Conroe will be the fastest CPU in town when it hits in a few weeks' time. It pulverises all present CPUs in the majority of CPU-based benchmarks.

1. The more data you pack in a volume, the higher the risk for data loss due to mechanical breaks.
2. 7 100 Gb disks (that would cost less than USD 430) will be at least 7 times more reliable than the 7200.10 with possibile similar performances.