AMD’s Phenom X4 9750 and 9850 processors

Most of you are aware by now of the problems with AMD’s quad-core Phenom processors. As we have chronicled closely, the chips were late to market and debuted with unexpectedly low clock frequencies. As a result, their performance was underwhelming compared to Intel’s Core 2 offerings. Worse yet, shortly before its release, AMD discovered a bug in the Phenom that could cause a system hang in certain, very specific circumstances. This so called “TLB erratum” caused AMD to cease shipments of the Phenom’s server-oriented counterpart, the Opteron 2300 series, but the firm went ahead with its plans to sell Phenoms in consumer PCs. For those systems, AMD offered a workaround in the form of a BIOS update, but the cure was arguably worse than the affliction, causing substantial performance hit in many applications.

During our coverage of the unfolding TLB erratum story, AMD told us it planned to deliver a new revision of its quad-core silicon in “mid-to-late Q1” of this year. This revision, dubbed B3, would include a proper chip-level fix for the TLB erratum. Since then, we’ve been waiting impatiently for these new chips to arrive while agitating for AMD to provide consumers with more information about whether and how they might disable the TLB workaround on existing Phenoms.

Fortunately, today, the wait appears to be over. Like a tired cliché rising from the keyboard of a website author, the Phenom has been resurrected in the form of silicon revision B3. Accordingly, AMD is announcing a whole new lineup of Phenom processors that should be available for purchase almost immediately. Even better, AMD seems to have found some additional clock frequency headroom in the B3 chips, so that lineup extends to new territory in the form of the Phenom X4 9750 and 9850 Black Edition processors.

New Phenoms: It’s all about the Xs

As expected, AMD’s new Phenom lineup includes a number of “xx50” model numbers intended to denote the presence of B3 silicon and a proper hardware fix for the TLB erratum. For instance, the Phenom 9550 replaces the Phenom 9500. Aside from the silicon rev and the TLB fix, the two products are essentially the same: both have four cores, a 2.2GHz core clock, 2MB of L3 cache, and all the rest. Of course, the Phenom 9550 should be faster in a default configuration because it doesn’t suffer the performance penalty caused by the TLB workaround.

The new Phenom line includes a number of surprises, though. Here’s a look at the whole list, with vitals for each model.

Model Clock speed North
bridge

speed

Cores TDP Price OEM
only
Rev.
B3
Phenom
X3 8400
2.1GHz 1.8GHz 3 95W ~$150 x
Phenom
X3 8600
2.3GHz 1.8GHz 3 95W ~$175 x
Phenom
X4 9100e
1.8GHz 1.6GHz 4 65W ~$200 x
Phenom
X4 9550
2.2GHz 1.8GHz 4 95W $195 x
Phenom
X4 9650
2.3GHz 1.8GHz 4 95W x x
Phenom
X4 9750
2.4GHz 1.8GHz 4 95W x x
Phenom
X4 9750
2.4GHz 1.8GHz 4 125W $215 x
Phenom
X4 9850 Black Edition
2.5GHz 2.0GHz 4 125W $235 x

Perhaps the biggest surprise for the pedantic little man inside of 98.2% of geeks is the addition of “X3” and “X4” indicators in the new Phenom model names, whose numbers correspond to the number of active processing cores on each chip. This naming scheme harkens back to the Athlon 64 X2, of course. We saw the “Phenom X4” name bandied about prior to the Phenom’s initial release, but then AMD canned it and went with straight model numbers. Apparently, that didn’t take. AMD says its customers liked the Xs, and so they’re back—this time, presumably, for good.

Once you’re over the shock of that nomenclature recalibration, you’ll probably notice the “X3” Phenoms in the list. Yep, these are the vaunted triple-core variants of the Phenom we’ve expected for some time; they’re official now, but only for large PC makers known as original equipment manufacturers (OEMs). Over half the new Phenom lineup is intended only for OEMs, in fact, and that’s why we have only approximate prices listed for those processors, if we have them at all. The big dawgs get all sorts of interesting stuff, including the tri-core chips, a low-power variant of the Phenom with a 65W thermal/power envelope (or TDP), and a Phenom X4 9750 with a 95W TDP. We can expect to see consumer versions of these products eventually; those should all be B3 silicon when they arrive.

AMD saved some of the fun for the rest of us, though. It claims the Phenom X4 9550 is the lowest-priced quad-core CPU on the market at under $200, and the 9750 at 2.4GHz doesn’t look like a bad deal, either. The most intriguing product of the lot, however, is the Phenom X4 9850 Black Edition. This puppy comes with a 2.5GHz core clock and a 2GHz north bridge clock—important because the north bridge clock governs the speed of the L3 cache. That should make the 9850 a little bit quicker than it might otherwise be. Like AMD’s other “Black Edition” processors, the 9850 has an unlocked upper clock multiplier that makes overclocking ridiculously, guilt-inducingly easy. And although it’s AMD’s flagship model, the 9850 lists for only $235, well below the list prices for ostensible competitors like the Core 2 Quad Q6600. This combination of attributes should make the 9850 the one to have, in my view.

Keeping tabs on the competition

The new Phenoms have the fortune of making it to market just as Intel is struggling to meet demand for its new 45nm chips, which means the Phenoms face a slightly less lethal mix of competitors.

For instance, this review is our first look at Intel’s new 45nm Core 2 Duo E8400 and E8500 processors. Although they have only two cores to the Phenom’s four, those two cores run at 3GHz and 3.16GHz frequencies, with (roughly) up to 20% higher clock-for-clock performance than the 65nm version of the Core 2 Duo. As a result, they’re able to give the lower frequency Phenoms a run for their money, even in widely multithreaded applications. But, as we’ve noted, the availability of these processors at online vendors is rather spotty, and prices have risen where they are available. The E8500’s ostensible $266 list price is already higher than the Phenom X4 9850’s, too.

The Phenom will face even deadlier competition in the form of Intel’s new 45nm Core 2 Quad processors, but those are even harder to find right now. We pinged Intel about those CPUs in preparation for this review, and the company says all of the new 45nm Core 2 Duo and Quad processors are indeed shipping now—including the Core 2 Quad Q9450, Q9550, and the Core 2 Extreme QX9770, interestingly enough. We weren’t able to get any specific ETA for when the availability picture should improve, but Intel says it expects supplies to rise to meet demand as 45nm production ramps up.

One of the more notable developments in Intel’s 45nm lineup, incidentally, is the recent and very quiet introduction of the Core 2 Quad Q9300. The Q9300 runs at 2.5GHz and, like the other 45nm Core 2 Quads, has a 1333MHz front-side bus. However, the Q9300 has only half the L2 cache—6MB total—of its siblings and looks tailor-made to take on the new Phenoms. We’ll try to get our hands on a Q9300 to test soon, along with other speed grades of the 45nm Core 2 Quads.

Test notes

Please note that we’ve included a “Phenom ES 2.6GHz” processor in the results on the following pages. This is an engineering sample chip clocked at 2.6GHz with a 2GHz north bridge that AMD supplied to us back when the Phenom first launched. No real Phenom product is yet shipping at this speed, but we’ve included it for comparison’s sake, nonetheless.

Also, we have included performance results for a couple of very high-end systems, including a dual Xeon X5365 system and a Skulltrail dual Core 2 Extreme QX9775 rig. With eight cores and price tags in the many thousands of dollars, such systems aren’t direct competitors for any Phenom AMD currently offers. If their presence annoys you, hold up two fingers to the screen to block out the bars representing them while reading the performance graphs.

Our testing methods

As ever, we did our best to deliver clean benchmark numbers. Tests were run at least three times, and the results were averaged.

Our test systems were configured like so:

Processor Core 2 Quad Q6600 2.4GHz
Core 2 Extreme QX6800 2.93GHz
Core 2 Duo E6750 2.66GHz
Core 2 Extreme QX6850 3.00GHz
Core
2 Extreme QX9770 3.2GHz
Dual
Xeon
X5365
3.00GHz
Dual
Core
2 Extreme QX9775 3.2GHz
Athlon 64 X2 5600+ 2.8GHz
Athlon 64 X2 6000+ 3.0GHz
Athlon 64 X2 6400+ 3.2GHz
Dual Athlon 64 FX-74 3.0GHz Phenom
9500
2.2GHz
Phenom
9600
2.3GHz

Phenom engineering sample (ES) 2.6GHz
Core 2 Extreme QX9650 3.00GHz Phenom
X4 9750 2.4GHz

Phenom X4 9850 Black Edition 2.5GHz

Core
2 Duo E8400 3.0GHz

Core 2 Duo E8500 3.16GHz

System bus 1066MHz (266MHz quad-pumped) 1333MHz (333MHz quad-pumped) 1600MHz
(400MHz quad-pumped)
1333MHz
(333MHz quad-pumped)
1600MHz
(400MHz quad-pumped)
1GHz HyperTransport 1GHz HyperTransport 1GHz HyperTransport 1GHz HyperTransport
Motherboard Gigabyte GA-P35T-DQ6 Gigabyte GA-P35T-DQ6 Gigabyte
GA-X38-DQ6
Intel
S5000VXN
Intel
D5400XS
Asus M2N32-SLI Deluxe Asus L1N64-SLI WS MSI
K9A2 Platinum
Asus
M3A32-MVP Deluxe
BIOS revision F1 F1 F6b S5000.86B.06.00.0076.

0409200070751

XS54010J.86A.0780.

2008.0110.1956

1201 0505 VP.0B7
(No patch)

V1.2B1 (TLB patch)

0307
F4 V1.3
F5c
North bridge P35 Express MCH P35 Express MCH X38
Express MCH
5000X
MCH
5400
MCH
nForce 590 SLI SPP nForce 680a SLI 790FX 790FX
South bridge ICH9R ICH9R ICH9R 6231ESB ICH 6321ESB ICH nForce 590 SLI MCP nForce 680a SLI SB600 SB600
Chipset drivers INF Update 8.3.0.1013

Intel Matrix Storage Manager 7.5

INF Update 8.3.0.1013

Intel Matrix Storage Manager 7.5

INF Update 8.3.0.1013

Intel Matrix Storage Manager 7.5

INF
Update 8.3.0.1013

Intel Matrix Storage Manager 7.5

INF Update
8.5.0.1009

Intel Matrix Storage Manager 7.8

ForceWare 15.01 ForceWare 15.01
Memory size 4GB (4 DIMMs) 4GB (4 DIMMs) 4GB (4 DIMMs) 4GB
(4 DIMMs)
4GB
(2 DIMMs)
4GB (4 DIMMs) 4GB (4 DIMMs) 4GB (4 DIMMs) 4GB (4 DIMMs)
Memory type Corsair TWIN3X2048-1333C9DHX

DDR3 SDRAM at 1066MHz

Corsair TWIN3X2048-1333C9DHX

DDR3 SDRAM at 1333MHz

Corsair TWIN2X2048-8500C5D

DDR2 SDRAM at 800MHz

Samsung ECC DDR2-667
FB-DIMM at 667MHz
Micron
ECC DDR2-800 FB-DIMM at 800MHz
Corsair TWIN2X2048-8500

DDR2 SDRAM at ~800MHz

Corsair TWIN2X2048-8500C5D

DDR2 SDRAM at ~ 800MHz

Corsair TWIN2X2048-8500C5D

DDR2 SDRAM at 800MHz

Corsair TWIN2X2048-8500C5D

DDR2 SDRAM at 800MHz

CAS latency (CL) 8 8 4 5 5 4 4 4 4
RAS to CAS delay (tRCD) 8 9 4 5 5 4 4 4 4
RAS precharge (tRP) 8 9 4 5 5 4 4 4 4
Cycle time (tRAS) 20 24 18 15 18 18 18 18 18
Audio Integrated ICH9R/ALC889A

with Realtek 6.0.1.5449 drivers

Integrated ICH9R/ALC889A

with Realtek 6.0.1.5449 drivers

Integrated
ICH9R/ALC889A

with Realtek 6.0.1.5449 drivers

Integrated
6321ESB/ALC260

with Realtek 6.0.1.5449 drivers

Integrated
6321ESB/STAC9274D5

with SigmaTel 6.10.5511.0 drivers

Integrated nForce 590 MCP/AD1988B

with Soundmax 6.10.2.6100 drivers

Integrated nForce 680a SLI/AD1988B

with Soundmax 6.10.2.6100 drivers

Integrated
SB600/ALC888

with Realtek 6.0.1.5532 drivers

Integrated
SB600/AD1988B

with Soundmax 6.10.2.6180 drivers

Hard drive WD Caviar SE16 320GB SATA
Graphics GeForce 8800 GTX 768MB PCIe with ForceWare 163.11 and 163.71 drivers
OS Windows Vista Ultimate x64 Edition
OS updates KB940105, KB929777 (nForce/790FX systems only), KB938194, KB938979

Please note that testing was conducted in two stages. Non-gaming apps and Supreme Commander were tested with Vista patches KB940105 and KB929777 (nForce systems only) and ForceWare 163.11 drivers. The other games were tested with the additional Vista patches KB938194 and KB938979 and ForceWare 163.71 drivers.

Thanks to Corsair for providing us with memory for our testing. Their products and support are far and away superior to generic, no-name memory.

Our single-socket test systems were powered by OCZ GameXStream 700W power supply units. The dual-socket systems were powered by PC Power & Cooling Turbo-Cool 1KW-SR power supplies. Thanks to OCZ for providing these units for our use in testing.

Also, the folks at NCIXUS.com hooked us up with a nice deal on the WD Caviar SE16 drives used in our test rigs. NCIX now sells to U.S. customers, so check them out.

The test systems’ Windows desktops were set at 1280×1024 in 32-bit color at an 85Hz screen refresh rate. Vertical refresh sync (vsync) was disabled.

We used the following versions of our test applications:

The tests and methods we employ are usually publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them.

Memory subsystem performance

We’ll kick things off with our usual set of synthetic memory performance tests. As always, these tests tell us more about the particular characteristics of each CPU and system architecture than they do about real-world performance prospects. They let us look at how fast (in terms of bandwidth) and quick (in terms of latency) each CPU’s memory subsystem can be.

No big surprises here. The B3-revision Phenoms slide right in where expected given their clock frequencies. As we’ve noted before, the Phenom achieves a nice combination of memory bandwidth and access latencies, due in part to its integrated memory controller. However, its access latencies to main memory are inflated somewhat due to the presence of its L3 cache. The Athlon 64 X2 lacks an L3 cache and is about 10ns quicker to main memory as a result.

Team Fortress 2

We’ll kick off our gaming tests with some Team Fortress 2, Valve’s class-driven multiplayer shooter based on the Source game engine. In order to produce easily repeatable results, we’ve tested TF2 by recording a demo during gameplay and playing it back using the game’s timedemo function. In this demo, I’m playing as the Heavy Weapons Guy, with a medic in tow, dealing some serious pain to the blue team.

We tested at 1024×768 resolution with the game’s detail levels set to their highest settings. HDR lighting and motion blur were enabled. Antialiasing was disabled, and texture filtering was set to trilinear filtering only. We used this relatively low display resolution with low levels of filtering and AA in order to prevent the graphics card from becoming a primary performance bottleneck, so we could show you the performance differences between the CPUs.

Notice the little green plot with four lines above the benchmark results. That’s a snapshot of the CPU utilization indicator in Windows Task Manager, which helps illustrate how much the application takes advantage of up to four CPU cores, when they’re available. I’ve included these Task Manager graphics whenever possible throughout our results. In this case, Team Fortress 2 looks like it probably only takes full advantage of a single CPU core, although Nvidia’s graphics drivers use multithreading to offload some vertex processing chores.

Since TF2 doesn’t make use of any more than two CPU cores, the Phenoms have no advantage over dual-core chips. Clock for clock, Intel’s Core 2 chips are faster here; at 2.4GHz, the Core 2 Quad Q6600 outperforms the Phenom X4 9750. And the Core 2 Duo E8400 and E8500 are both well ahead of the Phenom X4 9850.

Lost Planet: Extreme Condition
Lost Planet puts the latest hardware to good use via DirectX 10 and multiple threads—as many as eight, in fact. Lost Planet‘s developers have built a benchmarking tool into the game, and it tests two different levels: a snow-covered outdoor area with small numbers of large villains to fight, and another level set inside of a cave with large numbers of small, flying creatures filling the air. We’ll look at performance in each.

We tested this game at 1152×864 resolution, largely with its default quality settings. The exceptions: texture filtering was set to trilinear, edge antialiasing was disabled, and “Concurrent operations” was set to match the number of CPU cores available.

I’m not sure what’s happening in the Snow level, but oddly, a couple of the lower-clocked Phenoms do unusually well there. The primary bottleneck in that test is probably the GPU, since scores are bunched tightly together for the various CPUs. Things change rather dramatically in the Cave level, where we get a rare taste of a game that uses more than two CPU cores to good effect. Here, the new Phenoms shine, outperforming the Core 2 Quad Q6600 and nearly matching the Core 2 Extreme QX6800.

BioShock

We tested BioShock by manually playing through a specific point in the game five times while recording frame rates using the FRAPS utility. The sequence? Me trying to fight a Big Daddy, or more properly, me trying not to die for 60 seconds at a pop.

This method has the advantage of simulating real gameplay quite closely, but it comes at the expense of precise repeatability. We believe five sample sessions are sufficient to get reasonably consistent results. In addition to average frame rates, we’ve included the low frame rates, because those tend to reflect the user experience in performance-critical situations. In order to diminish the effect of outliers, we’ve reported the median of the five low frame rates we encountered.

For this test, we largely used BioShock‘s default image quality settings for DirectX 10 graphics cards, but again, we tested at a relatively low resolution of 1024×768 in order to prevent the GPU from becoming the main limiter of performance.

Our Bioshock results are an object lesson in CPU performance in today’s games: most of the time, you don’t need an especially fast CPU in order to get acceptable performance. Even at this modest display resolution, our graphics card (the very fast GeForce 8800 GTX) or some other constraint looks to be limiting frame rates. That said, the new Phenoms rank in the upper echelon of all of the processors we tested.

Supreme Commander

We tested performance using Supreme Commander‘s built-in benchmark, which plays back a test game and reports detailed performance results afterward. We launched the benchmark by running the game with the “/map perftest” option. We tested at 1024×768 resolution with the game’s fidelity presets set to “High.”

Supreme Commander’s built-in benchmark breaks down its results into several major categories: running the game’s simulation, rendering the game’s graphics, and a composite score that’s simply comprised of the other two. The performance test also reports good ol’ frame rates, so we’ve included those, as well.

The new Phenoms handle Supreme Commander easily, with the 9850 finishing just behind the Core 2 Quad Q6600. Once more, the Core 2 Duo E8400 and E8500 place higher, but the margins of difference here are very small—just a few frames per second, when it comes down to it.

Valve Source engine particle simulation

Next up are a couple of tests we picked up during a visit to Valve Software, the developers of the Half-Life games. They had been working to incorporate support for multi-core processors into their Source game engine, and they cooked up a couple of benchmarks to demonstrate the benefits of multithreading.

The first of those tests runs a particle simulation inside of the Source engine. Most games today use particle systems to create effects like smoke, steam, and fire, but the realism and interactivity of those effects are limited by the available computing horsepower. Valve’s particle system distributes the load across multiple CPU cores.

The Phenom’s four cores give it a clear advantage over the 45nm Core 2 Duo chips here, but the Core 2 Quad Q6600 proves to be even faster.

Valve VRAD map compilation

This next test processes a map from Half-Life 2 using Valve’s VRAD lighting tool. Valve uses VRAD to precompute lighting that goes into games like Half-Life 2. This isn’t a real-time process, and it doesn’t reflect the performance one would experience while playing a game. Instead, it shows how multiple CPU cores can speed up game development.

Much like in the last test, the new Phenoms perform well here, but not quite well enough to catch the Q6600.

WorldBench

WorldBench’s overall score is a pretty decent indication of general-use performance for desktop computers. This benchmark uses scripting to step through a series of tasks in common Windows applications and then produces an overall score for comparison. WorldBench also records individual results for its component application tests, allowing us to compare performance in each. We’ll look at the overall score, and then we’ll show individual application results alongside the results from some of our own application tests. Because WorldBench’s tests are entirely scripted, we weren’t able to capture Task Manager plots for them, as you’ll notice.

Like most of the desktop applications out there today, including its component apps, WorldBench doesn’t gain much from more than two CPU cores. In fact, the Core 2 Duo E8500 nestles into fourth place just behind the quad-core QX6850. Clock for clock, Intel’s Core 2 architecture again looks to be faster, with the Core 2 Quad Q6600 scoring quite a bit higher than the Phenom X4 9750.

Productivity and general use software

MS Office productivity

Firefox web browsing

Multitasking – Firefox and Windows Media Encoder

WinZip file compression

Nero CD authoring

The new Phenoms put in a series of respectable showings in these productivity apps, with the 9850 matching up particularly well against the Core 2 Quad Q6600. The two exceptions are WinZip, where I’d wager the Core 2 chips’ larger caches may be helping them, and Nero, which depends greatly on disk controller performance. Here, the Phenoms’ scores suffer due to the 790FX chipset’s problems with ACHI and NCQ.

Image processing

Photoshop

There’s just no denying the Intel processors’ dominance in this Photoshop test. The 45nm ones are especially potent, as the Core 2 Duo E8500’s third-place finish indicates.

The Panorama Factory photo stitching
The Panorama Factory handles an increasingly popular image processing task: joining together multiple images to create a wide-aspect panorama. This task can require lots of memory and can be computationally intensive, so The Panorama Factory comes in a 64-bit version that’s multithreaded. I asked it to join four pictures, each eight megapixels, into a glorious panorama of the interior of Damage Labs. The program’s timer function captures the amount of time needed to perform each stage of the panorama creation process. I’ve also added up the total operation time to give us an overall measure of performance.

This application uses four and even eight cores quite well. Nonetheless, the Core 2 Duo E8500 is nipping at the heels of the Phenom X4 9750, amazingly enough. Still, the Phenoms perform well for their price range.

picCOLOR image analysis

picCOLOR was created by Dr. Reinert H. G. Müller of the FIBUS Institute. This isn’t Photoshop; picCOLOR’s image analysis capabilities can be used for scientific applications like particle flow analysis. Dr. Müller has supplied us with new revisions of his program for some time now, all the while optimizing picCOLOR for new advances in CPU technology, including MMX, SSE2, and Hyper-Threading. Naturally, he’s ported picCOLOR to 64 bits, so we can test performance with the x86-64 ISA. Eight of the 12 functions in the test are multithreaded, and in this latest revision, five of those eight functions use four threads.

Scores in picCOLOR, by the way, are indexed against a single-processor Pentium III 1 GHz system, so that a score of 4.14 works out to 4.14 times the performance of the reference machine.

Some of picCOLOR’s functions use four threads, yet the E8400 and E8500 outperform the Q6600, as well as both new Phenoms.

Video encoding and editing

VirtualDub and DivX encoding with SSE4

Here’s a brand-new addition to our test suite that should allow us to get a first look at the benefits of SSE4’s instructions for video acceleration. In this test, we used VirtualDub as a front-end for the DivX codec, asking it to compress a 66MB MPEG2 source file into the higher compression DivX format. We used version 6.7 of the DivX codec, which has an experimental full-search function for motion estimation that uses SSE4 when available and falls back to SSE2 when needed. We tested with most of the DivX codec’s defaults, including its Home Theater base profile, but we enabled enhanced multithreading and, of course, the experimental full search option.

Obviously, the 45nm Intel CPUs with SSE4 are fastest here, as expected. The Phenoms, however, finish before the Core 2 Quad Q6600.

Windows Media Encoder x64 Edition video encoding

Windows Media Encoder is one of the few popular video encoding tools that uses four threads to take advantage of quad-core systems, and it comes in a 64-bit version. Unfortunately, it doesn’t appear to use more than four threads, even on an eight-core system. For this test, I asked Windows Media Encoder to transcode a 153MB 1080-line widescreen video into a 720-line WMV using its built-in DVD/Hardware profile. Because the default “High definition quality audio” codec threw some errors in Windows Vista, I instead used the “Multichannel audio” codec. Both audio codecs have a variable bitrate peak of 192Kbps.

Wow, this one’s tight. The Phenom X4 9850 is just one second behind the Q6600—a virtual tie. With only two cores, the E8500 trails.

Windows Media Encoder video encoding

Roxio VideoWave Movie Creator

The virtual tie continues with Worldbench’s Windows Media Encoder test, but the stalemate breaks in VideoWave, where the Core 2 processors take a decisive lead.

LAME MT audio encoding

LAME MT is a multithreaded version of the LAME MP3 encoder. LAME MT was created as a demonstration of the benefits of multithreading specifically on a Hyper-Threaded CPU like the Pentium 4. Of course, multithreading works even better on multi-core processors. You can download a paper (in Word format) describing the programming effort.

Rather than run multiple parallel threads, LAME MT runs the MP3 encoder’s psycho-acoustic analysis function on a separate thread from the rest of the encoder using simple linear pipelining. That is, the psycho-acoustic analysis happens one frame ahead of everything else, and its results are buffered for later use by the second thread. That means this test won’t really use more than two CPU cores.

We have results for two different 64-bit versions of LAME MT from different compilers, one from Microsoft and one from Intel, doing two different types of encoding, variable bit rate and constant bit rate. We are encoding a massive 10-minute, 6-second 101MB WAV file here.

Regardless of which compiler we use, the Phenoms just aren’t that strong, relatively speaking, with LAME audio encoding.

Cinebench rendering

Graphics is a classic example of a computing problem that’s easily parallelizable, so it’s no surprise that we can exploit a multi-core processor with a 3D rendering app. Cinebench is the first of those we’ll try, a benchmark based on Maxon’s Cinema 4D rendering engine. It’s multithreaded and comes with a 64-bit executable. This test runs with just a single thread and then with as many threads as CPU cores are available.

The X4 9850 outduels the Core 2 Quad Q6600 here, and notice how it does so. Although the Q6600 is faster with one thread, the Phenom scales better to four.

POV-Ray rendering

We caved in and moved to the beta version of POV-Ray 3.7 that includes native multithreading. The latest beta 64-bit executable is still quite a bit slower than the 3.6 release, but it should give us a decent look at comparative performance, regardless.

Clock for clock, the Phenom proves faster in POV-Ray than the Core 2 Quad, with one to four threads. However, the tables turn when we use the built-in POV-Ray benchmark scene, which largely relies on a single execution thread.

3ds max modeling and rendering

Once again, the Phenoms can’t quite keep pace with the Q6600. It’s close, though.

Folding@Home

Next, we have a slick little Folding@Home benchmark CD created by notfred, one of the members of Team TR, our excellent Folding team. For the unfamiliar, Folding@Home is a distributed computing project created by folks at Stanford University that investigates how proteins work in the human body, in an attempt to better understand diseases like Parkinson’s, Alzheimer’s, and cystic fibrosis. It’s a great way to use your PC’s spare CPU cycles to help advance medical research. I’d encourage you to visit our distributed computing forum and consider joining our team if you haven’t already joined one.

The Folding@Home project uses a number of highly optimized routines to process different types of work units from Stanford’s research projects. The Gromacs core, for instance, uses SSE on Intel processors, 3DNow! on AMD processors, and Altivec on PowerPCs. Overall, Folding@Home should be a great example of real-world scientific computing.

notfred’s Folding Benchmark CD tests the most common work unit types and estimates performance in terms of the points per day that a CPU could earn for a Folding team member. The CD itself is a bootable ISO. The CD boots into Linux, detects the system’s processors and Ethernet adapters, picks up an IP address, and downloads the latest versions of the Folding execution cores from Stanford. It then processes a sample work unit of each type.

On a system with two CPU cores, for instance, the CD spins off a Tinker WU on core 1 and an Amber WU on core 2. When either of those WUs are finished, the benchmark moves on to additional WU types, always keeping both cores occupied with some sort of calculation. Should the benchmark run out of new WUs to test, it simply processes another WU in order to prevent any of the cores from going idle as the others finish. Once all four of the WU types have been tested, the benchmark averages the points per day among them. That points-per-day average is then multiplied by the number of cores on the CPU in order to estimate the total number of points per day that CPU might achieve.

This may be a somewhat quirky method of estimating overall performance, but my sense is that it generally ought to work. We’ve discussed some potential reservations about how it works here, for those who are interested. I have included results for each of the individual WU types below, so you can see how the different CPUs perform on each.

The Phenoms place well here on the strength of decent all-around performance, especially with the Tinker and Amber WU types.

MyriMatch proteomics

Our benchmarks sometimes come from unexpected places, and such is the case with this one. David Tabb is a friend of mine from high school and a long-time TR reader. He recently offered to provide us with an intriguing new benchmark based on an application he’s developed for use in his research work. The application is called MyriMatch, and it’s intended for use in proteomics, or the large-scale study of protein. I’ll stop right here and let him explain what MyriMatch does:

In shotgun proteomics, researchers digest complex mixtures of proteins into peptides, separate them by liquid chromatography, and analyze them by tandem mass spectrometers. This creates data sets containing tens of thousands of spectra that can be identified to peptide sequences drawn from the known genomes for most lab organisms. The first software for this purpose was Sequest, created by John Yates and Jimmy Eng at the University of Washington. Recently, David Tabb and Matthew Chambers at Vanderbilt University developed MyriMatch, an algorithm that can exploit multiple cores and multiple computers for this matching. Source code and binaries of MyriMatch are publicly available.
In this test, 5555 tandem mass spectra from a Thermo LTQ mass spectrometer are identified to peptides generated from the 6714 proteins of S. cerevisiae (baker’s yeast). The data set was provided by Andy Link at Vanderbilt University. The FASTA protein sequence database was provided by the Saccharomyces Genome Database.

MyriMatch uses threading to accelerate the handling of protein sequences. The database (read into memory) is separated into a number of jobs, typically the number of threads multiplied by 10. If four threads are used in the above database, for example, each job consists of 168 protein sequences (1/40th of the database). When a thread finishes handling all proteins in the current job, it accepts another job from the queue. This technique is intended to minimize synchronization overhead between threads and minimize CPU idle time.

The most important news for us is that MyriMatch is a widely multithreaded real-world application that we can use with a relevant data set. MyriMatch also offers control over the number of threads used, so we’ve tested with one to eight threads.

I should mention that performance scaling in MyriMatch tends to be limited by several factors, including memory bandwidth, as David explains:

Inefficiencies in scaling occur from a variety of sources. First, each thread is comparing to a common collection of tandem mass spectra in memory. Although most peptides will be compared to different spectra within the collection, sometimes multiple threads attempt to compare to the same spectra simultaneously, necessitating a mutex mechanism for each spectrum. Second, the number of spectra in memory far exceeds the capacity of processor caches, and so the memory controller gets a fair workout during execution.

Here’s how the processors performed.

When sorted by their best times, the Phenoms bracket the Q6600, and look at how they manage it. Although the Q6600 is quicker with one and two threads, the Phenoms scale better to four threads.

STARS Euler3d computational fluid dynamics

Charles O’Neill works in the Computational Aeroservoelasticity Laboratory at Oklahoma State University, and he contacted us to suggest we try the computational fluid dynamics (CFD) benchmark based on the STARS Euler3D structural analysis routines developed at CASELab. This benchmark has been available to the public for some time in single-threaded form, but Charles was kind enough to put together a multithreaded version of the benchmark for us with a larger data set. He has also put a web page online with a downloadable version of the multithreaded benchmark, a description, and some results here.

In this test, the application is basically doing analysis of airflow over an aircraft wing. I will step out of the way and let Charles explain the rest:

The benchmark testcase is the AGARD 445.6 aeroelastic test wing. The wing uses a NACA 65A004 airfoil section and has a panel aspect ratio of 1.65, taper ratio of 0.66, and a quarter-chord sweep angle of 45º. This AGARD wing was tested at the NASA Langley Research Center in the 16-foot Transonic Dynamics Tunnel and is a standard aeroelastic test case used for validation of unsteady, compressible CFD codes.
The CFD grid contains 1.23 million tetrahedral elements and 223 thousand nodes . . . . The benchmark executable advances the Mach 0.50 AGARD flow solution. A benchmark score is reported as a CFD cycle frequency in Hertz.

So the higher the score, the faster the computer. Charles tells me these CFD solvers are very floating-point intensive, but oftentimes limited primarily by memory bandwidth. He has modified the benchmark for us in order to enable control over the number of threads used. Here’s how our contenders handled the test with different thread counts.

Sometimes, having a better building block trumps having more blocks. Here, for example, the Core 2 Duo E8500 exactly ties with the Phenom X4 9850, despite the fact that this test can benefit from even eight threads on the right system. The Phenom’s showing is respectable, but the E8500’s is remarkable.

SiSoft Sandra Mandelbrot

Next up is SiSoft’s Sandra system diagnosis program, which includes a number of different benchmarks. The one of interest to us is the “multimedia” benchmark, intended to show off the benefits of “multimedia” extensions like MMX, SSE, and SSE2. According to SiSoft’s FAQ, the benchmark actually does a fractal computation:

This benchmark generates a picture (640×480) of the well-known Mandelbrot fractal, using 255 iterations for each data pixel, in 32 colours. It is a real-life benchmark rather than a synthetic benchmark, designed to show the improvements MMX/Enhanced, 3DNow!/Enhanced, SSE(2) bring to such an algorithm.
The benchmark is multi-threaded for up to 64 CPUs maximum on SMP systems. This works by interlacing, i.e. each thread computes the next column not being worked on by other threads. Sandra creates as many threads as there are CPUs in the system and assignes [sic] each thread to a different CPU.

We’re using the 64-bit version of Sandra. The “Integer x16” version of this test uses integer numbers to simulate floating-point math. The floating-point version of the benchmark takes advantage of SSE2 to process up to eight Mandelbrot iterations in parallel.

Yep, uh, there you have it.

Power consumption and efficiency

Now that we’ve had a look at performance in various applications, let’s bring power efficiency into the picture. Our Extech 380803 power meter has the ability to log data, so we can capture power use over a span of time. The meter reads power use at the wall socket, so it incorporates power use from the entire system—the CPU, motherboard, memory, graphics solution, hard drives, and anything else plugged into the power supply unit. (We plugged the computer monitor into a separate outlet, though.) We measured how each of our test systems used power across a set time period, during which time we ran Cinebench’s multithreaded rendering test.

Almost all of the systems had their power management features (such as SpeedStep and Cool’n’Quiet) enabled during these tests via Windows Vista’s “Balanced” power options profile. The exception here was the Skulltrail system, since its BIOS didn’t support SpeedStep.

Anyhow, here are the results:

Let’s slice up the data in various ways in order to better understand them. We’ll start with a look at idle power, taken from the trailing edge of our test period, after all CPUs have completed the render.

The new Phenoms’ idle power use is in line with their predecessors’, but not quite a nice as the quad-core Intel systems’, overall.

Next, we can look at peak power draw by taking an average from the ten-second span from 30 to 40 seconds into our test period, during which the processors were rendering.

Under load, our test systems based on the new Phenoms consume just about as much power as those based on Intel’s fastest 65nm quad-core CPUs. That’s not too bad, but Intel’s 45nm processors draw quite a bit less power than their 65nm counterparts.

Another way to gauge power efficiency is to look at total energy use over our time span. This method takes into account power use both during the render and during the idle time. We can express the result in terms of watt-seconds, also known as joules.

The Phenom systems’ combination of idle and peak power draw ends up requiring more total power than those based on the Core 2 Quad Q6600 and Core 2 Duo E8500.

We can quantify efficiency even better by considering the amount of energy used to render the scene. Since the different systems completed the render at different speeds, we’ve isolated the render period for each system. We’ve then computed the amount of energy used by each system to render the scene. This method should account for both power use and, to some degree, performance, because shorter render times may lead to less energy consumption.

AMD hasn’t quite caught up with Intel’s 65nm quad-core processors in terms of power-efficient performance. Thus, they have quite a bit of work to do in order to match Intel’s 45nm parts.

Overclocking

We’ve haven’t had much luck with Phenom overclocking in the past, but our experiences with the 9850 Black Edition were more pleasant. I was able to get it running stable at 3GHz using some extra voltage and the same Cooler Master Hyper 212 cooler we used with the Phenom 9600 Black Edition. Rather than tell you a long tale of what I ran into during my overclocking attempts, I’ll give you a look at my notes, which look like so:

2.7GHz/stock – pass

2.8GHz/stock – pass

2.9GHz/stock – no POST

2.9GHz/1.36V – pass

3.0GHz/1.36V – hang on Windows boot

3.0GHz/1.403V – BSOD on boot

3.0GHz/1.442V – BSOD on boot

3.0GHz/1.481V – pass

3.1GHz/1.481V – hang on boot

3.1GHz/1.519V – hang on boot

A “pass” means the CPU made it through 4-5 minutes of the stability test in the AMD Overdrive utility. Getting to 2.9GHz was very easy; the 9850 needed only a minor bump in voltage to make it there. Hitting the 3GHz mark took more effort and a lot more voltage. In fact, I finally settled on 1.519V at 3GHz for my testing, and even then, the system wasn’t perfectly stable. I’d say this is a 2.9GHz chip for most intents and purposes. Still, I was able to take a screenshot and do some testing at 3GHz.

The CPU-Z voltage readout lies! It lies!

At 3GHz, the Phenom looks primed to take on the QX6800, at least in these two apps. I think I might have been able to extract some additional performance out of the Phenom by overclocking its north bridge (and thus its L3 cache), but sadly, our MSI K9A2 Platinum motherboard’s BIOS doesn’t allow for that. We may have to try it on another board soon.

I’m more than curious to find out whether my experiences here were in any way representative of what most folks will experience with the 9850. Who knows?

Conclusions

The best thing I can say about the Phenom X4 9750 and 9850 is this: AMD is back in the game. The banishment of the TLB erratum to the history books is, of course, a welcome development, and the higher clock frequencies now available are a small but important step in the right direction. The Phenom X4 9850 Black Edition can’t always keep pace with the Core 2 Quad Q6600 or the Core 2 Duo E8500, but it’s close. AMD still hasn’t caught up to Intel’s 65nm “Kentsfield” processors in terms of overall performance or power efficiency, yet it has produced a credible alternative to those products. That fact, combined with aggressive pricing and the bold move of offering an unlocked upper multiplier on a $235 quad-core processor, has enabled the Phenom to grab our attention. We can finally say with confidence that if you have an existing Socket AM2 system and want to upgrade, buying a Phenom looks like a more attractive upgrade path than making the switch to Intel.

Around here, we tend to think in terms of guide-worthiness, in reference to our helpful system guides with specs for building a new PC. I think we can now say that the Phenom is also a guide-worthy proposition, if not as a primary recommendation, then at least as an alternate. The MSI K9A2 Platinum motherboard we used in our Phenom test rig sells for as little as $159 online and would make a nice foundation for a Phenom system—we’re talking about a board with four second-gen PCIe x16 slots, a board capable of three- and four-way CrossFire X configs. AMD’s so-called “Spider” platform has had an incredibly rough childhood, but it’s beginning to mature into a reasonable proposition, believe it or not—not the fastest or the best in any sense, but a potentially solid value.

That, for now, is enough to get AMD back onto the PC enthusiast’s radar and into contention in the middle of the market, thanks in part to the window opened up by the slow ramp of Intel’s 45nm chips. The next steps for AMD may prove to be considerably harder, but they’ve at least established a toehold again.

Comments closed
    • charged3800z24
    • 11 years ago

    the 9850 BE, 9750, 9550, are all on newegg.com now. Like 5mins ago, it is 10:49pm est.

    §[< http://www.newegg.com/Product/ProductList.aspx?Submit=ENE&N=2+50001028+40000343+1050733654&name=Phenom+9000+Series<]§

    • raymin
    • 11 years ago

    GREAT TO SEE SOME GOOD NEWS FOR AMD COMING OUT OF THIS CAMP!

    • dpaus
    • 11 years ago

    If a 2.4 GHz X4 is called a 9750, and a 2.5 GHz is called a 9850, that only leaves room for one more speed increment – presumably 2.6 GHz “9950” – before the naming scheme gets awkward. Is this just an unbelievable lack of foresight on the part of the Marketing team, or is the X4 line going to top out at 2.6 GHz?

      • DaveJB
      • 11 years ago

      I can’t see them really getting above 2.6GHz on the 65nm process; they’ll probably move to a new naming scheme when they go to 45nm.

        • StashTheVampede
        • 11 years ago

        The current yields can’t be fantastic, right? If they were good, they may not have introduced the X3 chips at all (simply a failed core). Also, look at how long its taken to get the B3s out — several months.

        Now that the B3 is out, they can focus on making the yields better (allowing for higher speeds and overclocking room) and start a separate process of 45nm transition (it isn’t so simple to shrink, otherwise the 800lbs gorilla Intel would have more quads in the market right now).

    • redpriest
    • 11 years ago

    My Q6600 requires tremendous effort to be stable at 3 ghz. And by stable, I mean it runs everything nonstop, 24 hours a day, with all 4 cores utilized. And this is watercooled.

    • Xenolith
    • 11 years ago

    In the conclusions… “We can finally say with confidence that if you have an existing Socket AM2 system and want to upgrade, buying a Phenom looks like a more attractive upgrade path than making the switch to Intel.”

    I am assuming he meant AM2+. I have an AM2 board, but I know it doesn’t take the previous phenoms.

      • flip-mode
      • 11 years ago

      Some AM2 boards work though. Mine does.

        • Xenolith
        • 11 years ago

        But most don’t. The way the quote reads is that these new phenoms are fully AM2 compatible. No need to worry about AM2+ compatibility.

    • JustAnObserver
    • 11 years ago

    I love seeing you morons arguing about who has THE best, clock per clock, top extreme black super duper alpha and omega overclocking part. When the enthusiast processor is more like a ferrari. Nice to show, but who really mekes the big money is Toyota and their common cars. You see MOST people won’t overclock, MOST people won’t CrossFire nor SLI, MOST people just want an average system for a day in day out workload. So the only thing that really mather is this:

    Keep struggling for the Extremely Over priced parts, so that the average parts (AMD or Intel, whatever) keep coming cheaper and cheaper every day. After all, I’ll get, let’s say, 75% of your performance, but pay less than 50% what you paid. Sounds nice to me.

    But hey, thats just me.

    Ps.: You americans are funny, you can’t even realize that the US only answers for 7% of the world processor market. And the rest of the world is a bit smarter about how to spend their money.

      • charged3800z24
      • 11 years ago

      You could have at Least put a capital “A” on “americans”…..Make me feel less important ^_^

      • Flying Fox
      • 11 years ago

      But most of those people don’t read sites like this one.

        • A_Pickle
        • 11 years ago

        Well said.

        I especially liked the part where you pretty much turned his own several-paragraph argument against him in a single sentence.

      • Kurotetsu
      • 11 years ago

      Reading the article….aaaand nowhere does it state that the Phenom is inferior because it isn’t the most powerful overclocking superchip in the universe.

      Reading the forums…aaand I can’t find a single post that recommends buying the absolute most expensive hardware you can possibly find. In fact, posts that suggest doing so are largely ridiculed. People looking to build a system are generally guided toward best value parts, rather than bleeding edge performance.

      So I’m going to assume your post came entirely out of your rear end.

      You come to a website targeted toward enthusiasts, who are inherently in the minority, just to rant how only the opinion of the majority matters? Do you really have nothing better to do with your life?

      • flip-mode
      • 11 years ago

      Bitter much?

      • Majiir Paktu
      • 11 years ago

      Must be that time of month…

      P.S. You U.S.-haters are funny, you can’t even realize that it’s the United States that invents this stuff in the first place.

    • pluscard
    • 11 years ago

    Looks like the AMD vs. Intel debate is cranking up once again. AMD had the lead from 2003-2006. Intel will have had it back for two years by mid-2008.

    Will it flip again as it has before?

      • indeego
      • 11 years ago

      Nothing I see shows AMD has anything to rival Intel. Perhaps on price? Not on features/performance/solidg{<.<}g

      • coldpower27
      • 11 years ago

      Not likely unless Intel makes another gigantic oops like Prescott NetBurst. AMD’s success is pretty contigent on Intel misteping. With Intel firing on all cylinders, AMD has to wait for another opportunity.

    • Jypster
    • 11 years ago

    Any chance of some FSB overclocking? While changing the multiplier is the best (easy and simple ) it is fun screwing every bit out of a CPU <grins>

    Also I am not sure if I missed it but how where the temps at stock and overclocked for the CPU and systemboard ? Think water cooling may help squeeze a little bit more due to the higher voltage you can pump into it?

    Some different system boards would be good to see as well for this and how they handle the memory speeds/settings and NB overclocking.

    I enjoyed the review and I am glad I held off on an upgrade for my AM2+ board. Bang for buck still looks pretty good for me, now to talk to the War and Finance Minster ( Wife )

      • Nitrodist
      • 11 years ago

      AMD chipsets lack a FSB, so it’s impossible.

    • CB5000
    • 11 years ago

    Hmm… I think I’ll wait for the 45nm version before I upgrade my X2 5000+…

    • Chrispy_
    • 11 years ago

    I still won’t be buying one as I’m now enjoying being able to afford high-end parts, but I’ll start recommending them again for new builds on a budget.

    It’s nice to see that there is a low-end alternative again. Having AMD on top of intel was nice while it lasted but it was the kick intel needed to start producing competetive products again.

    AMD overtook intel from a worse position than this almost a decade ago, they can likely do it again if (when) Intel gets lazy again.

    • no51
    • 11 years ago

    This review totally sold me on the 84/8500. As much as I’d like the extra inches a quad will grant my e-peen, the only time I’d see that advantage is when I’m re-encoding video. Maybe i should hold off upgrading till the 45nm Phenoms come out; or maybe I should just OC my E6600…

      • Flying Fox
      • 11 years ago

      You can show that with Folding ppd. 😉

    • charged3800z24
    • 11 years ago

    I have no problem over clocking the NB on my K9A2 Platinum 1.3 bios and 1.4 bios. Easy over clocking. I have been running 2000mhz NB and 2.7ghz Core with that bios on my 9600 BE.

    • thermistor
    • 11 years ago

    4 words:

    Kentsfield available December 2006.

    Since then, incremental increases.

    We need another ‘Core2’ release with Nehalem to really keep things going. Not just more cores, but better single core performance.

    The E8500 is really the unexpected star of this test and aligns better with most usage models outside media-heads.

      • coldpower27
      • 11 years ago

      No need for anything more, when the competition is barely competitive.

        • charged3800z24
        • 11 years ago

        What are you saying? They fixed a bad chip. This was not an attempt to take the performance crown. They have a 45nm chip that is geared for better perfromance. And they are very competitive at the price.

          • coldpower27
          • 11 years ago

          /[

            • SPOOFE
            • 11 years ago

            “meaning Intel has NO COST advantage.”

            That is not at all what that data means. Intel has a mature 65nm process with an excellent design which is selling like hotcakes and earning them lots of money; AMD has a new 65nm process with a new design that doesn’t look terribly interesting which will probably not earn them lots of money.

            The manufacturing process is only part of the issue; further, the graph you linked to shows Intel transitioning to mostly 45nm by Q3, a point at which AMD will probably not even have a 45nm product available. I would love to know how all that doesn’t translate into a “cost advantage”.

            • Flying Fox
            • 11 years ago

            q[

            • dkadc
            • 11 years ago

            There is more 45nm product coming out of Intel right now than there is any product coming out of AMD.

            Until recently all Intel 45nm product was coming out of the ramp in their R&D fab.

            Now that Intel’s D1D R&D fab has proven they can do HVM at 45nm, the process is being ramped at other 12″ fabs. As you can see by the chart that someone else linked, sometime around Q2-Q3 Intel 45nm output will surpass Intel 65nm output. That’s in the next 3-6 months in case you had not noticed.

            Meanwhile, AMD’s fastest clocked processors are still made on AMD’s obsolete 90nm process. AMD’s fastest quad cores get spanked by AMD’s own mid range dual cores.

            AMD is stuck with SOI, conventional transistor gates and immersion lithography at 45nm. SOI and immersion add to AMD’s expenses while AMD’s old-school transistors add to AMD’s thermal and performance troubles. You won’t see a single AMD 45nm chip for sale in all of 2008. It might launch, but it will be another paper launch just like Barcelona.

            • charged3800z24
            • 11 years ago

            Um…. The dual cores from AMD do not Spank the AMD Quad cores. The new Quad cores are over all the fastest from AMD. And AMD’s fab36 is rolling on track last I heard. As long as AMD can keep in the fight they don’t have to have the fastest chip out. Besides, Intel and AMD profit better in the middle any how.

    • Prion
    • 11 years ago

    So, now that the silicon is fixed, will we be seeing K10 Opterons hit the market again? K10 just isn’t that exciting on the desktop.

    • echo_seven
    • 11 years ago

    Wow, despite the fact that AMD has really taken a huge step forward today, finally releasing a (non-buggy) Phenom that can almost do as much clockspeed as the AX2’s, those charts were still quite embarrassing.

    They absolutely, absolutely, must not screw up on the 45nm (on the AMD side).

    • Mr Bill
    • 11 years ago

    I just can’t get over Intel’s absolutely dominant integer performance in the mandelbrot test. Its probably also integer performance that makes Intel shine in Linpack bandwidth. I’d like to see an article explaining the huge disparity.

      • Xylker
      • 11 years ago

      Me too! r[< <]r

    • LicketySplit
    • 11 years ago

    Great review Scott…im happy to see AMD getting their act together…competition is $$ saved for us all. I’ll support the lil guy as well to help in this endeavor.

    • Dposcorp
    • 11 years ago

    Another awesome, incredible, outstanding TR review.
    Excellent Job by Scott and the TR staff.

    Also, no one writes articles with funnier lines then you guys do:
    q[

      • eitje
      • 11 years ago

      excellent observation – though the CPU might not be the best, the platform offers some interesting things that are not available in the Intel camp yet.

      • Flying Fox
      • 11 years ago

      Actually the multiple x16 slots mean we can have the graphics and a big RAID controller (or multiple of them) to build a gigantic file server. Get a lower power quad it can do folding at the same time too? 😀

    • Prototyped
    • 11 years ago
      • flip-mode
      • 11 years ago

      Not worth getting your panties in a twist. Overclocking should never be attempted if 100% stability is required. The benches provided at those speeds that are of questionable stability are for information only, and it’s still information worth knowing. It’s worth knowing how the K10 performs at those speeds even if those speeds aren’t 100% stable. These articles are about information.

        • Stranger
        • 11 years ago

        on to of that dmg is only testing one processor its already a rough estimate as is.

    • lex-ington
    • 11 years ago

    At least by the time I’m ready to upgrade all my machines – I’ll have some money for the three proc’s. I would think an X3 would be nice for my HTPC.

    • flip-mode
    • 11 years ago

    Hm, up to 100 watts power difference between the Qs and the X4s is unfortunate. That’s a significant amount of additional heat to pump out of a system. (edited for disambiguation)

      • cygnus1
      • 11 years ago

      where do you see a 100 watt difference?

      the idle difference between the Q6600 and the X4 9850 is 23 watts, and the load difference is is 61 watts.

      you should work on graph reading comprehension

        • flip-mode
        • 11 years ago

        QX9650 Load: 215 watts
        X4 9850 Load: 302 watts

        87 watt difference so I rounded a fair bit.

          • cygnus1
          • 11 years ago

          that is entirely the wrong product to compare to.

          did you not read the article, all throughout they were comparing the two X4’s to the Q6600. it’s on the same process node, performance is fairly close, and price is closest.

            • flip-mode
            • 11 years ago

            Right, I should compare AMD’s product of today to Intels product of more than a year ago. Whatev. You are being rude. I read the graphs correctly and I read the article. Please get manners.

            • cygnus1
            • 11 years ago

            I’m sorry you think i’m being rude. but the only point of comparison between the over $1000, new .45nm process, QX9650 and the X4’s is their release date being somewhat close. even that isn’t accurate, as the QX9650 is over 5 months old.

            based on the price, performance and process generation, clearly the top X4 is aimed at the Q6600.

            do you really think AMD is comparing the X4 9850 to the QX9650?

            i’m not a fanboi for either camp, but it is wholly unfair to compare the QX9650 to any of the X4.

            that would be like comparing a Bently to a Honda Accord.

            just my 2 cents

            • flip-mode
            • 11 years ago

            Heh, it’s nothing like comparing a Bently to a Honda – those car analogies are often used and seldom useful. What it is like is comparing Intel’s most miserly quad to AMD’s least miserly quad, nothing more. It’s a comparison based not on price or performance or process tech, just on power consumption.

            • grantmeaname
            • 11 years ago

            Bentleys aren’t even fast. They’re luxury cars. It’s more like comparing a Ferrari to a Mazda.

      • coldpower27
      • 11 years ago

      You’ve seen nothing yet, the Phenom X4 9950 coming in Q3 is rumored to have a 140W TDP to start with the lower 125W coming later.

      But at least AMD has the sense to price these as price/peformance parts, they know they ain’t Intel..

      Intel was here once too,

      §[< https://techreport.com/articles.x/9262/15<]§ It just sucks more when AMD does it as it relegates them to a low cost option.

    • Thresher
    • 11 years ago

    I am pulling for AMD, even thought I’ve switched to intel. Competition is always a good thing.

    I think the thing to take away from this is that AMD may be lagging at present, but that this architecture has promise. If they could ramp the speeds up to the 3.0GHz range and scaled down to 45nm, this chip would be at least on par with what intel is turning out right now. They’re just one step behind, at present.

    It will be interesting to see how this plays out. I don’t think intel is in any huge hurry at the moment to scale down again and until Nehalem, AMD has a really good chance at catching up.

    • srg86
    • 11 years ago

    Although I’d still rather go for a 65nm or 45nm Core 2 Quad (I’m only running S939, so chip switch is out of the question), this shows that AMD are finally back in the game and we can finally have some competition for the new 45nm Core 2 quads when they come out. Hopefully this will force Intel to price their chips better.

    • Krogoth
    • 11 years ago

    Yawn, near-Conroe performance over a year later. While, newly-released Penyrn-based units outrun both K10 and Conroe for less power.

    The only thing that prehaps saves Phenom is its lower MSRP.

      • eitje
      • 11 years ago

      …which is exactly how Intel intends it to be.

      • charged3800z24
      • 11 years ago

      Do you not remember the P4 erra? People still loved Intel when they WERE not competive in performane by power consomption/speed per dollar. AMD always gets hammered.

        • Krogoth
        • 11 years ago

        Netburst sucked for the most part.

        Northwood was the one decent design that came out of it. Prescott on the other hand was a complete embarrassment.

          • charged3800z24
          • 11 years ago

          I went back through all the CPU reviews by TR. AMD was holding there own for several Years and except for a very few benchies did the intel chip excel over AMD before Conroe. And AMD had better performance pre dollar when 300 dollar AMD64 chips were faster than 800 dollar Intel chips. But yet Intel still sold large quanitities of those chips. AMD has 2 bad years and it is “oh bad little AMD”. Intel has had the capital to do great things from All the partners backing them. AMD has just finally broke into having a few partners helping them out. I think they are doing very well based on there situation.

            • SPOOFE
            • 11 years ago

            Back when AMD’s chips were better than Intel’s, their total reliance on 3rd-party chipsets was a major setback. Even when Intel’s performance wasn’t there, they still offered a top-to-bottom solution, which is what was attractive for big system builders, which is what kept Intel alive.

            AMD lacked that diversity; they’re trying to make it up now, but it won’t work with a dud of a chip.

        • coldpower27
        • 11 years ago

        Intel is just far more attractive and chic then AMD is, so if AMD is sucking wind, one of their major target markets “the people in the know” are going to notice.

        Intel has supreme brand name recognition, which matters alot in the real world. With that kind of thing people don’t care as much about how you perform as long as it is “sufficient” which the Pentium 4 was.

        People care about having “Intel inside”

          • charged3800z24
          • 11 years ago

          Sorta like Bose….LOL ” I have a Bose surround system”.. Wait there might be Bose fans on here …..

      • ew
      • 11 years ago

      I doesn’t matter to me that it is a year late because my current desktop is three years old. The latest and greatest is always a waste of money.

    • flip-mode
    • 11 years ago

    Top notch review. The X4s do a little better than I expected.

    Those CPU usage charts in the video encoding section don’t show anywhere near 100%, which is surprising to me. Maybe that’s why there’s not as much spread between the duals and the quads as I expected? I expected video encoding to be able to peg four cores.

      • dkadc
      • 11 years ago

      “I expected video encoding to be able to peg four cores.”

      Nope. Hard drives are not fast enough to keep four cores fed with video.

      I running RAID0 with three 500Gb SATA II drives with my swapfile on a seperate two drive RAID0 and although it did get a lot faster, it sill can’t saturate all 4 cores on my Q6600 O/C @ 3Ghz.

      The only way I can possibly render faster is either improved algorithms or faster hard drives.

        • flip-mode
        • 11 years ago

        Ah ha. Thanks.

    • MrJP
    • 11 years ago

    Very nice review as usual Mr Damage. Just a couple of polite suggestions for the next one:

    1. A summary table showing % gain/loss for all the benchmarks, just for a couple of the interesting comparisons e.g. X4 9850 vs Q6600, and/or E8400 vs Q6600. It’s just a consolidation of all the exisiting scores on a single page but would help relieve my addled brain from keeping a running score.

    2. One of the gaming benchmarks repeated at more “normal” settings, i.e. allowing the GPU to be more of a bottleneck. While this wouldn’t tease out the differences between the CPUs as clearly, it would be a more realistic test of how people actually use their PCs.

    As an overall conclusion, it’s very hard to look much beyond a E8xxx as the best choice unless you’re a render monkey.

    • eitje
    • 11 years ago

    what was the power consumption like, when it was OCed?

    • Fighterpilot
    • 11 years ago

    Good….but not good enough once the 45nm Yorkfield quads arrive.
    You can add 10% or so to the gap between these Phenoms and the Q6600 already plus way more overclocking headroom.

      • pluscard
      • 11 years ago

      Did Intel ever explain why the 45nm yorkfields have been delayed? A quick google says the delay came to light back in December.

        • grantmeaname
        • 11 years ago

        so they can sell the 65nm procs

          • charged3800z24
          • 11 years ago

          This is not correct. They had Problems… At least what I read arround the web.

            • Flying Fox
            • 11 years ago

            The yield/manufacturing problem is only part of it. The inventory is another side of it. If they can still sell the old stuff at the same price (thus more profit), why not?

      • Flying Fox
      • 11 years ago

      They don’t have to outright beat Intel, as long as the pricing reflect that. Looks like the prices are good right now in terms of performance/watt/$.

        • SPOOFE
        • 11 years ago

        They DO have to outright beat Intel, in certain key regards, if they want to become consistently profitable. Making an expensive chip and selling it at a Low Low Price is good for bargain-conscious consumers, but tends to make shareholders unhappy.

          • Flying Fox
          • 11 years ago

          At this stage, one step at a time. 😉

    • boing
    • 11 years ago

    Am I the only one seeing absolutely no reason, unless you use your computer to run specialized exotic apps, to buy a quadcore cpu just yet?

    For everyday computer use, and 99% of all gaming, I see it as a waste of money not buying a faster clocked c2d or x2 cpu compared to slower clocked and more expensive quadcore.

      • stdRaichu
      • 11 years ago

      For most people, yes, it’s complete overkill – they’d be better off buying more RAM or a faster hard drive.

      Quad core comes into its own for video encoding though, which isn’t as uncommon as you might think. x264 is very processor hungry, but scales very well, and since it’s only marginally more expensive to get a quad over a dual it makes alot of sense if you do certain types of commodity video work.

      • Flying Fox
      • 11 years ago

      Cheap Folding rig?

        • Gerbil Jedidiah
        • 11 years ago

        Exactly. My Q6600 is mopping the floor with my AM2 X2 Black Edition. It’s not even close to being close to being close.

      • notfred
      • 11 years ago

      Software development isn’t that exotic, a lot of compiles can be done in parallel, “make -j4” is a real productivity boost on large projects.

      • Krogoth
      • 11 years ago

      A healthy dose of memory, soild I/O performance and a quad-core CPU makes multi-tasking very painless. 😉

      I cannot really go back to single-core CPUs.

      • StashTheVampede
      • 11 years ago

      If you don’t know if you need the cores or not: skip buying specifically for quad and stay within your budget.

      For those that know they need the quads: consider your apps and buy accordingly. My apps are iMovie/iDVD — I’m stuck with Intel for hackintosh (yes, the AMD solutions are there, but aren’t as common as Intel P35s). iMovie/iDVD take time to process 1080i video, quads are the fastest method to reduce the time to takes to process one movie.

    • fellix
    • 11 years ago

    It’s sad, that the FO4 inversion logic in AMD’s 65nm tech isn’t optimized for fast switching, e.g. high clock rates. The main reason for poor clock increments, relative to the power consumption.

    • Jigar
    • 11 years ago

    After OCing the chip .. It looked quiet compatible… This chips has potential, now only if AMD can crank the speed of the chips and they are back on track for sure.

    • PrincipalSkinner
    • 11 years ago

    Good but not great news for AMD. Lets hope they will get the 45nm right.

    • Forge
    • 11 years ago

    #2, Scott mentioned that the mobo used didn’t have the needed options for NB OCing. Bottom of the OCing page, IIRC.

      • charged3800z24
      • 11 years ago

      I have that board.. unless B3 is different for some resson… I have the option to over clock the NB on my Phenom 9600 BE. Which Bios was used?

        • Damage
        • 11 years ago

        All documented on the Testing Methods page (as ever). Never seen that option in MSI’s Cell menu. You can modify the HT and DRAM clocks, but not the north bridge base clock.

          • charged3800z24
          • 11 years ago

          I will post a screen shot when I get home… Since the bios 1.3 I have been using the bios to overclock my Phenom.. it is more stable for some reason. I now have 1.4 on but it was there on 1.3.. I just updated 1.4.

          ..I did notice the bios on the setup page.. sorry. I am at work and have PCs going mad everywhere… I will try to think before I post LOL

            • charged3800z24
            • 11 years ago

            Here is how I adjust the NB. It was confusing to me in the Bios based on how everything is worded. But it was the only way I could achieve this. I am not able to Adjust this in AOD for what ever reason.

            §[< http://3800z24.info/Phenom/<]§

    • ssidbroadcast
    • 11 years ago

    Hey how about that, roughly performance-per-dollar parity with Intel’s offerings (the Uber-Intel machines I don’t really count). Way to go.

    • shank15217
    • 11 years ago

    If you look at the performance between K8 and K10, its almost 20% faster across the board core for core on multithreaded apps.

    • indeego
    • 11 years ago

    Conclusion, I skimmed, saw the word /[

    • mentaldrano
    • 11 years ago

    This is why I fold for TR – the F@H benchmark page!!! Thanks again!

    Any chance of benching the new 45nm Xeons?

    • just brew it!
    • 11 years ago

    Whoa… they’re here.

    So tempting… must… resist…

    So when are these expected to hit the retail channels?

    • crazybus
    • 11 years ago

    In another time, a 20% overclock on a top of the range cpu would have been considered phenomenal (heh). Now it’s merely ok to marginally disappointing. How times have changed.

      • willyolio
      • 11 years ago

      yeah, the 9600 black edition was quite a disappointment, barely hitting 2.5, iirc.

      this TLB fix seems to have fixed a lot.

      • Flying Fox
      • 11 years ago

      People are spoiled. I’m still old school so I’m really happy on my 50% overclock on a lowender. 😉

        • Dodger
        • 11 years ago

        Celeron 300A for the win!

      • provoko
      • 11 years ago

      Q6600 doesn’t OC more than 25% on average. It’s possible obviously, but not as easy. The first conroes I OCed about 65% (EASY), but the kentsfields always averaged about 25%. The QX average 20-30% which is crap when you consider they cost $1000.

      So this 20% figure everyone is throwing around as a bad thing is stupid especially when that’s normal for a quad core and they’re cheaper than the competition.

        • Krogoth
        • 11 years ago

        Wrong, Q6600 overclock almost as well as their E6600 brethren. The problem with Q6600 is a lot harder to keep thermal envelope under check because you have twice the dies to cool off.

          • provoko
          • 11 years ago

          How am I wrong then?

          You’re basically agreeing with me. I used the words not as easy, you used the words “the problem” and “that harder”.

            • crazybus
            • 11 years ago

            If by “easy” you mean stock cooling and stock voltages then yes, I would agree with you, but 3.2-3.4ghz overclocks on Q6600s are pretty much the norm around here.

            In any event, even the QX9650 can be overclocked 25-30% without tremendous effort.

            • Convert
            • 11 years ago

            If by “norm” you mean trophy shots and not what I would call stable then yes, I would agree with you.

            I have 4 C2D systems and not one of them OC’s stably to what most consider the “norm” for C2D’s. I can post at those levels, I can even run windows without issues but they will occasionally dump WU’s until they are edged back down to 3.0 territory.

            At work we all upgraded to C2D machines and I personally went through every single one of them and checked to see which one would OC the most (because I wanted it for myself). The results all followed the same trend,3GHZ was pretty much the limit for stability.

            All of my “computer friends” are in the same boat, all OCing on their own without help from me and we have boards from asus and gigabyte (P5B and DS3 flavors).

            Or a friend with a xeon X3220 that tops out at 3GHZ.

            So either every single one of us have motherboards that can’t handle it or people are smoking crack when it comes to reporting their clockspeeds. One of my friends would claim the same thing, that his 6600 ran at 3.2GHZ, yet when I bought it from him it could reach those speeds but it would dump WU’s unless bumped down to 2.8.

            I am not saying 3.2 is out of the question, I have seen a couple of those in person reach those speeds, but the “norm” is a bunch of crock.

            I did however just pick up a E8400 and I have high hopes for it, hopefully the cracksmokers are right on this one.

            I think people get too excited because C2D’s will post at darn near anything, that Xeon mentioned above would post at 3.8 without much fiddling.

            • flip-mode
            • 11 years ago

            Is that with or without voltage bumps?

            • Convert
            • 11 years ago

            With. I’m completely off my rocker aren’t I?

            • lethal
            • 11 years ago

            While I can’t comment on F@H stability, most people report their OC as stable by testing Prime 95 or similar, so it could be that they are stable on one and not the other =/.

            • Flying Fox
            • 11 years ago

            Not quite, most reports are a simple SuperPi run. /shrugs

            • flip-mode
            • 11 years ago

            No, not at all. I’m quite surprised at this news though as I’ve been led to believe that practically every Core 2 based CPU out there will make it to 3.2 if the mobo is up to it and 3.4 with some good cooling.

            • Convert
            • 11 years ago

            I have been told the same, yet I just never see it.

            My E8400 however seems to be doing quite well, 3.6 (FSB is at 1600, I *[

            • provoko
            • 11 years ago

            Thanks Convert for the back up. 😉

            Although, I hope no one is really smoking crack, haha.

            • crazybus
            • 11 years ago

            I should have refrained from stating absolute frequencies then. Of course with overclocking YMMV but my point is simply that take a typical Core 2 Quad and a typical Phenom and the C2Q is likely to exhibit higher headroom.

            The behaviour often seen with processors of a given stepping is that the lower clocked chips usually* will run at the clock speed of the highest clocked chip of that stepping with possibly a moderate voltage bump and commensurate cooling. For the 65nm quads that would be 3GHz. Anything above that I would consider bonus, while a chip only capable of >3Ghz I would consider a relative dud.

            With quads there are additional complexities when it comes to successful overclocking. Past nVidia chipsets have been terrible quad overclockers so if one is reporting poor overclocking on an nVidia platform well there’s your problem. As well, cooling at anything close to or exceeding 3GHz belongs to realm of the upper crust of air coolers.

            Note that the 45nm quads change the equation as overclocking is likely to be limited more by chipset FSB constraints than by thermal or pure clockspeed headroom caps.

            *disclaimer: purely based on anecdotal evidence

        • lethal
        • 11 years ago

        25% out of a Q6600 is 3.0 Ghz. Which is the bare minimum you are going to get out of a G0 Q6600 on /[

          • Nictron
          • 11 years ago

          I have not been able to get my Q6600 above 3.08 GHz on a ASUS P5N32Sli so I think you are just very lucky is you get those high frequencies. so 3Ghz for the Phenom is very good. BTW I have a Antec P180 and two seperate water cooling systems for CPU and 2x GTX’s, my CPU under load never even reached 55 degrees and my GTX’s never goes above 45 degrees under load.

            • lethal
            • 11 years ago

            the 680i chipset is known to have difficulty overclocking quadcores, so its likely that your motherboard and not your cpu is what’s holding you back.

    • BoBzeBuilder
    • 11 years ago

    Great review indeed, and very nice overclocking results. I wouldn’t mind switching to phenom when their 45nm parts hit the streets.

    • Sargent Duck
    • 11 years ago

    Sleep…read review…sleep…read review. Screw it, I don’t have class till 1 tomorrow.

    edit: /[

    • Nitrodist
    • 11 years ago

    I am the most excited about the overclocking. Perhaps a Phenom is in my future…

      • epsilon
      • 11 years ago

      LOL so a 20% O/C to 3GHz (non stable) is considered ‘exciting’… I guess the bar is set pretty low for AMD these days. 😉

        • Jigar
        • 11 years ago

        It’s not a big dawg mate…

        • eitje
        • 11 years ago

        troll post. 😛

        • Nitrodist
        • 11 years ago

        Troll.

    • dragmor
    • 11 years ago

    Typo? Page 7 – MS Office productivity – 9750 is beating the 9850?

    Looks like AMD fixed a couple of other things as well since the 9850 is beating the 2.6ghz version in a few tests.

    Also with the overclocking tests could you overclock the NB as well as the cores and see what performance gains that brings.

    • imtheunknown176
    • 11 years ago

    Great review! I’m looking forward to see how overclocking the northbridge affects performance.

Pin It on Pinterest

Share This