Intel’s Pentium M 760 versus AMD’s Turion 64 ML-44

ALTHOUGH INTEL HAS BEEN STRUGGLING on the desktop front of late, things on the mobile side have been going just fine, thank you. In fact, the Pentium M has been doing so well that Intel’s desktop line will eventually be migrating to a processor based on a similar architecture. Heck, even Apple joined in on the fun. Near the top of the heap is the Pentium M 760, which features a 533MHz front-side bus, an operating frequency of 2.0GHz and a whopping 2MB of L2 cache.

AMD’s answer to the Pentium M is the Turion 64, an Athlon 64-based design which rides in a 754-pin socket. The Turion 64’s attributes include an on-die memory controller, a 1GHz HyperTransport link, and of course the ability to run 64-bit code. The model we’ll be looking at today is the ML-44, a new chip with a 2.4GHz operating frequency and 1MB of L2 cache.

We have been watching the mobile processor space for a while now with some interest, wondering whether the Turion 64 really matches up well against the Pentium M. The Pentium M’s power-saving features and performance per watt are the stuff of modern legend. AMD has done well with Opteron in servers and the Athlon 64 in desktops, but surely AMD’s K8-derived mobile competitor doesn’t match up with the likes of the Pentium M. Does it?

Well, we wanted to find out before the game changes again. Intel’s recently announced Core Duo marks the beginning of a transition to multicore processors in the mobile space, and AMD has stated its intention to make a dual-core version of the Turion, as well. Core Duo laptops are just starting to arrive on the market, although volumes are still somewhat limited. With that in mind, let’s take a quick look at the two most widely available mobile processors today: the Pentium M versus the Turion 64.

The combatants
We’ll start off with an up-close and personal view of the two contenders:



The Turion 64 ML-44 (left) and Pentium M 760 (right)

Being mobile chips, neither the Pentium M 760 nor the Turion ML-44 has the protective “heatspreader” cap that’s become standard on desktop processors. Instead these processors look more like an Athlon XP or an old-school Pentium III.

The Turion 64 ML-44
The ML-44 is the latest addition to AMD’s Turion line of mobile processors. On the surface, the Turion has much in common with Socket 754 Athlon 64 chips. It has an on-die memory controller capable of addressing a single channel of DDR400 memory, as well as the ability to run 64-bit code—not even the new Core Duo can do that. Depending on model, the Turion features either 512KB or 1MB of L2 cache. Turions also feature support for the NX bit, which can help prevent malicious exploits based on buffer overflows.

Being a mobile line, low power consumption is a key feature of the Turion 64. All Turions support AMD’s PowerNow! technology, which dynamically scales clock speed and voltage over a wide range in response to CPU loads. Additionally, although Turion 64s bear more than a passing resemblance to the Socket 754 Athlon 64, the Turion can operate at significantly lower voltages relative to desktop chips, which cuts down significantly on power consumption.

Finally, AMD has segmented the Turion 64 into two model lines, one focusing on performance, the other on battery life. This product segmentation shows itself in the TDP—or thermal dissipation rating—of the two lines: The ML line of Turions has a TDP of 35W, while the MT line has a TDP of 25W.

The ML-44 we’re testing today is AMD’s fastest model, featuring 1MB of L2 cache and a maximum operating frequency of 2.4GHz. With PowerNow! enabled, the system will scale the processor’s operating frequency from 2.4GHz all the way down to 800MHz depending on CPU load. The voltage scales from 1.0V at 800MHz to 1.35V at 2.4GHz.

The motherboard we’re using for Turion 64 testing is MSI’s RS482M-IL. This microATX motherboard is based on ATI’s Radeon Xpress 200M mobile chipset, and its integrated graphics should be similar to those on a Turion 64 laptop with the same chipset.

The Pentium M 760
The Pentium M 760 is at the upper end of Intel’s mobile line, and is an example of how the Pentium M has evolved over time. While the first Pentium M processors had 1MB of L2 cache and ran on a 400MHz bus, newer examples such as the 760 have a giant 2MB of L2 and a 533MHz front-side bus. Finally, like the Turion 64, the newer Pentium M chips add support for the NX bit.

In addition to these changes, memory bandwidth has improved considerably over time thanks to newer chipsets. The first chipsets could only address a single channel of DDR333, putting the Pentium M at a disadvantage relative to the competition. The newer 915 chipset we’re looking at today, however, can address dual channel DDR2 at 533MHz, a huge increase in memory bandwidth. While some of this bandwidth will likely go untapped thanks to the relatively slow 533MHz front-side bus, it’s better to have an excess of memory bandwidth, especially when using on-board graphics with shared memory.

The Pentium M 760 has a maximum operating frequency of 2.0GHz. Using Intel’s SpeedStep technology, the system will dynamically clock the processor anywhere from 800MHz up to the maximum 2.0GHz. The voltage scales from 0.714V at 800MHz to 1.315V at 2.0GHz.

Unlike the Turion 64, the Pentium M can’t run 64-bit code. Given that most laptops can’t accept more than 4GB of memory, that limitation may not be much of an issue for the Pentium M. 64-bit computing does have tangible benefits in certain scenarios, but those arguably won’t matter for mobile computing for some time yet.

For our tests, the Pentium M 760 will be sitting in an AOpen motherboard, the i915Ga-HFS. This ATX board features the Intel 915GM mobile chipset. Like the MSI board for the Turion, it should give us a reasonable approximation of a laptop based on the same chipset, in terms of both power consumption and graphics power. Not only that, but both this Pentium M mobo and our Turion 64 motherboard are strong candidates for use in quiet computing applications like home theater PCs, as well.

The match-up
Ours is not a perfect world, and we acknowledge that this is not a perfect match-up, at least not in terms of price. The problem is that AMD’s Turion ML-44, priced at $354 by AMD, lands in the middle of a large gulf in Pentium M pricing. Our two closest options for comparison were the Pentium M 760 at 2.0GHz, with a price of $294, and the Pentium M 770 at 2.13GHz and a price of $423. The $60 price difference between the 760 and the ML-44 was slightly less than that the $69 separating the 770 from the ML-44, so we based our comparison on the former.

Our testing methods
While we ran the majority of tests with integrated graphics, we wanted to get an idea of how these systems would respond with a discrete mobile graphics solution. Therefore, the gaming benchmarks were performed both with the integrated graphics as well as an NVIDIA 6600GT plugged into each board’s PCI-E x16 slot.

Because these are mobile processors, we tested with power management features like SpeedStep and PowerNow! enabled throughout our benchmark suite, with the lone exception of CPU-Z’s memory access latency test. That test reports its results in terms of CPU cycles, and it could be thrown off by processor clock speed changes.

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 Pentium M 760 2.0GHz Turion ML-44 2.4GHz
System bus 533MHz (133MHz quad-pumped) 1GHz HyperTransport
Motherboard Asus AOpen i915Ga-HFS MSI RS482M-IL
BIOS revision 1.01 080012
North bridge 915G MCH Radeon RS482
South bridge ICH6 SB400
Chipset drivers INF Update 7.2.2.1006
Catalyst 6.2
Memory size 1GB (2 DIMMs) 1GB (2 DIMMs)
Memory type Crucial Ballistix PC2-8000
DDR2 SDRAM
at 533MHz
Crucial Ballistix PC3200
DDR SDRAM
at 400MHz
CAS latency (CL) 4 2
RAS to CAS delay (tRCD) 4 4
RAS precharge (tRP) 4 4
Cycle time (tRAS) 15 8
Hard drive Maxtor DiamondMax 10 250GB SATA 150
Audio Integrated ICH7R/STAC9221D5
with SigmaTel 5.10.4825.0 drivers
Integrated nForce4/ALC850
with Realtek 5.10.0.5970 drivers
Graphics Integrated i915G with 6.14.10.4277 drivers
GeForce 6600GT PCI-E with ForceWare 81.98 drivers
Integrated RS482 with Catalyst 6.2 drivers
GeForce 6600GT PCI-E with ForceWare 81.98 drivers
OS Windows XP Professional with Service Pack 2

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

Also, all of our test systems were powered by OCZ PowerStream power supply units. The PowerStream was one of our Editor’s Choice winners in our latest PSU round-up.

The test systems’ Windows desktops were set at 1024×768 in 32-bit color at a 75Hz screen refresh rate. Vertical refresh sync (vsync) was disabled for all tests.

We used the following versions of our test applications:

The tests and methods we employ are generally publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them. Update 02/15/2006: After the publication of this review, two issues with the testing were found and corrected. See this link for more information.

Memory performance
These synthetic tests don’t always mirror real-world performance, but they can tell us some interesting things about the CPUs and their memory subsystems, so we’ll start here.

With double the number of channels and 33% higher memory speed than the Turion, it’s no surprise that the Pentium M wins handily here. In fact, it’s likely that the disparity would be significantly larger were it not for the Pentium M’s pokey 533MHz bus.

This Linpack benchmark is always useful for showing the size and speed of a processor’s caches and the speed of its main memory. Unfortunately, running this test on the Pentium M is sort of like sending Joe Montana into a high school football game—it’s just not fair. With a massive L2 cache that spans the entire range of test matrix sizes, the 760 blows away the Linpack test, then makes rude references to its parentage involving hamsters and elderberries.

While the Pentium M definitely has the edge in terms of raw memory bandwidth, you don’t tug on Superman’s cape, and you don’t mess around with an on-die memory controller. The Turion crushes the Intel chip on this one, with access latencies nearly half those of the Pentium M.

Gaming performance

Unreal Tournament 2004
Reasoning that newer games like F.E.A.R. are going to have the frame rate of a PowerPoint presentation on integrated graphics, we stuck with older benchmarks on the gaming side of things. As a reminder, on this test we benchmarked not only with the integrated graphics but also with a GeForce 6600GT card.

The Turion ekes out a win here, although neither integrated solution even makes it to 30 frames per second. More interesting, perhaps, is the fact that, graphics being equal, the Pentium M comes in ahead of the Turion 64. That’s right, Intel wins a gaming benchmark! This is not your father’s Netburst chip. 3DMark05
As with UT2004, we tested 3DMark05 with both integrated graphics and the 6600GT.

Neither integrated solution is, err. . . competitive in 3DMark05, but that’s hardly shocking. If the integrated graphics are in the cellar, however, the ATI Radeon Xpress 200M is at least halfway up the stairs relative to the Intel GMA 900, for whatever that’s worth. As with UT2004, however, the Pentium M comes out ahead of the Turion 64 when integrated graphics is taken out of the equation.

The individual gaming tests mimic the overall score, with the Turion 64 system with ATI graphics consistently beating the Pentium M with Intel graphics. With the discrete GeForce 6600 GT, The Pentium M outruns the Turion in all tests, though the margin of victory varies considerably.

While the Pentium M takes the gaming tests, the Turion roars back to win (or in one case tie) all of 3DMark’s CPU tests.

WorldBench overall performance
WorldBench uses scripting to step through a series of tasks in common Windows applications and then produces an overall score for comparison. More impressively, WorldBench spits out 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.

The Turion 64 ekes out a win here, though it’s not a huge win on a percentage basis. Audio editing and encoding

LAME MP3 encoding
We have results for two different versions of LAME 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, as we have done in our previous CPU reviews.

The Turion 64 goes four for four in the LAME benchmarks, though the Pentium M at least stays competitive. MusicMatch Jukebox

Although the overall WorldBench score showed a modest win for the Turion, there’s still plenty of drama in the individual tests. Here the Turion 64 hands the Pentium M 760 a convincing defeat.

Video editing and encoding

Windows Media Encoder Advanced Profile
We asked Windows Media Encoder to convert a gorgeous 1080-line WMV HD video clip into a 320×240 streaming format using the Windows Media Video 8 Advanced Profile codec.

Windows Media Encoder

Adobe Premiere

VideoWave Movie Creator

The margin of victory varies, but the Turion 64 beats the Pentium M across the board in our video editing tests.

Image processing

Adobe Photoshop

ACDSee PowerPack

Though the victories aren’t as convincing as some of the video tests, the Turion 64 still wins both of the WorldBench image processing tests.

picCOLOR
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.

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

The picCOLOR test is tight; the two chips trade positions in the individual tests. When the dust settles, however, the Pentium M 760 comes out on top.

Multitasking and office applications

MS Office

WorldBench’s Office test involves switching between the various components of the Office suite, which are all running at once. This one is basically a tie.

Mozilla

Mozilla and Windows Media Encoder

Apparently after the tie in MS Office, the Turion 64 wanted to make a statement, and that’s exactly what it did on both of these tests.

Other applications

Sphinx speech recognition
Ricky Houghton first brought us the Sphinx benchmark through his association with speech recognition efforts at Carnegie Mellon University. Sphinx is a high-quality speech recognition routine. We use two different versions, built with two different compilers, in an attempt to ensure we’re getting the best possible performance.

Call this one a tie. Move along, nothing to see here. WinZip

Nero

It’s not a huge margin of victory, but the Pentium M manages to add a couple of checks to the win column.

3D modeling and rendering

Cinebench 2003
Cinebench measures performance in Maxon’s Cinema 4D modeling and rendering app.

The Turion 64 looks like the better processor for 3D rendering, at least with Cinema 4D.

The most notable result here is the Pentium M’s commanding lead in the hardware OpenGL test. This may be the due to problems with ATI’s OpenGL drivers. POV-Ray rendering

The Turion 64 shows its floating point prowess in this rendering test, as well, beating the Pentium M by a significant margin.

SiSoft Sandra
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 and SSE/2. 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.

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 at once.

The Pentium D owns this test among desktop processors, but the crown switches hands in the mobile world. The Turion 64 bests the Pentium M on both the integer and floating point tests.

Power consumption
We measured the power consumption of our entire test systems, except for the monitor, at the wall outlet using a Kill A Watt watt meter. The test rigs were all equipped with OCZ PowerStream 520W power supply units. The idle results were measured at the Windows desktop, and we used Prime95 to load up the CPUs.

As I mentioned in our testing methods section, both processors were tested with their power-saving features—SpeedStep for the Pentium M and PowerNow! for the Turion 64—enabled. Because of a bug in the BIOS of the MSI motherboard used for the Turion 64 tests, RMClock was used on that configuration to match the maximum voltage to the official spec of the processor.

The power consumption tests are actually very interesting. While it’s true that the Pentium M beats the Turion 64 by a substantial margin under load, the fact is that typical laptop usage leaves the system at idle the vast majority of the time. At idle, the Turion 64 system actually comes in with slightly lower power consumption than the Pentium M rig. This result suggests that, depending on usage patterns, the Turion could prove a worthy alternative to the Pentium M in terms of battery life.

Conclusions
From a performance perspective, it’s clear that the Turion 64 is the winner. By my count, the Pentium M was faster in only five of the tests, and one of those (the hardware OpenGL test in Cinebench) was probably due to graphics drivers. The rest were either a toss-up or a win for the Turion 64. The other thing that struck me about the results was that even in the tests the Pentium M did win, its margin of victory was fairly small. A number of the Turion 64 wins, however, were by an impressively large margin. From a power consumption perspective, the Turion 64 surprised me. Yes, our Turion 64 test system consumed 19W more power than the Pentium M system at 100% CPU load, but unless you’re using your laptop to crunch that Folding@Home work unit on the plane, maximum power consumption isn’t usually all that important. For typical use, it seems likely the Turion 64 would be reasonably competitive with the Pentium M on the battery life front, as well.

Comments closed
    • Chaos-Storm
    • 12 years ago

    Are you suggesting that since the A64 only goes to 3 ghz, no p4 chips over 3 ghz should be used? the fastest pentium M is 2.16 Ghz, which, when comparing many benchmarks, would still give the turion the win overall. Plus, the comparison was done with respect to price.

    • IntelMole
    • 14 years ago

    A day of boredom just led to the following.

    When idle, Turion power < P-M
    When loaded, Turion power > P-M

    So at some fraction of idle usage, a, they will be equal.

    So we get:
    53a + 94(1-a) = 56a + 75(1-a)
    -41a +94 = -19a +75
    -22a = 19

    -> a = 0.86

    So, if your processor is at idle more than 86% of the time, the Turion comes out ahead. Otherwise the P-M is your best bet.

    ‘Course, this does ignore the fact that the motherboard, memory, and integrated components are all different. The memory at least is platform-dependant, as is the motherboard to a certain extent.
    -Mole

    • psece
    • 14 years ago

    Aren’t Turion’s bin parts? Meaning that AMD takes regular Athlon 64’s and finds the most efficient and tags them as Turions? Just wondering if this chip starts to make inroads against Intel, will AMD have the capacity to keep up with demand.

    • ardmin
    • 14 years ago

    it is a nonsense to compare mobile CPUs only without taking into account the whole notebook. What about the laptop weight? Centrino is always thinner. Mobile means you are carring it with you right? Also why did not you check Napa with dual core instead this PM 760?

    Nonsense testing laptops for games as well – no body will play Quake 4 at 14” screen right? and using small laptop keybord without proper mouse??
    Laptops are for business, you should use PCmark instead of 3Dmark etc.

    The power consumption difference maight not look very big – just 8-10W but this could mean 1 more hour in battery mode i.e. you have 1 more hour to close the deal – how valuable is this uh??

    • Damage
    • 14 years ago

    Please note that we have made some corrections and updates to the original benchmark data and text of this review. For an explanation, see here:

    §[<https://techreport.com/onearticle.x/9386<]§

      • Dposcorp
      • 14 years ago

      Thank you for making the corrections, as it is nice to see a site take constructive criticisms, and use them to not get offended, but to actually admit their were some errors and correct them.

      Bravo to you, sir, and the entire TR gang.
      Nice to see Dr. Evil come and and be evil as well.

      Also, I am very happy to the AMD chip do even better.

      It offers all the P-M does, and then some with it being 64Bit.

      And yes, it will matter as a lot of us are now running 64Bit code and Vista is around the corner.

    • Hector
    • 14 years ago

    I stopped reading after you crippled the Turion by setting mem to 2-4-4 probably 2T CMD too. No one runs at those slow timings with DDR. And Ballistix will run all day at 2-2-2-6 1T!!!

    y[

      • Damage
      • 14 years ago

      Calm down, Mr. Ruiz! Actually, if you look at the overall picture, the minor memory timings settings, tRP and tRCD, aren’t that big of a deal. We’ve found that even going from 2-2-2 to 2.5-4-4 doesn’t impact performance terribly much:

      §[<https://techreport.com/etc/2005q4/mem-latency/index.x?pg=1<]§ On top of that, I think you are being naive if you expect a laptop PC to come with 2-2-2 RAM. That seems highly unlikely. As for 1T/2T, that can have something of an impact in certain settings (though not too much, see the link above), but unfortunately, this motherboard didn't allow us to adjust that setting--much like most OEM systems, including (especially) laptops don't. Accordingly, we tested both systems with somewhat conservative timings. The 4-4-4 timings we used for the Pentium M's DDR2 isn't as fast as an enthusiast might push things in a desktop, either, but it's a reasonable setting. I don't think you can say Andy was being unfair, even if you are a green-tinted uber-fanboy. :)

        • Hector
        • 14 years ago

        y[https://techreport.com/etc/2005q4/mem-latency/farcry-medium-8×6.gif<]§ And if you did winrar you'd see up to 20% delta.. See my testing here: §[<http://forums.anandtech.com/messageview.aspx?catid=28&threadid=1475190&enterthread=y<]§ Winrar in KB/s PC2300 - 3-3-3 1T- 496 PC3000 - 3-3-3 1T- 564 PC3000 - 2-2-2 1T- 636 PC4700 - 3-4-3 1T- 651 PC3800 - 2.5-2-2-1T - 703!!! While I generally shy away from "high performance" ram 2-4-4 is totally rediculous since no turion laptop comes with that but 3-3-3 instead is as the cheap alternative. I'm confindent the ferrari comes Cas 2 1T based on forum members responses. But I don't own one to confim. y[

          • Furen
          • 14 years ago

          Latency is probably not that big (I’d expect less than 5% compared to 2-2-2). The Command rate is, however, since it lowers bandwidth quite a bit on an already bandwidth-starved CPU.

          Dr. Evil: I must admit that it sounds like you’re right about picCOLOR but if you “suspected” that the video bandwidth was the issue why didn’t you simply test it both ways so you could dispel any possible doubts we might have had instead of leaving us high and dry with a number that looks so wrong (even if it isn’t). You could have said something like “while on integrated video Turion performs horribly due to bandwidth contention, having discrete video makes it perform much more competitively” or something of the sort. Also, instead of getting so pissy you should have thought of the fact that ANY article that deals with AMD vs Intel, in any shape or form, always turns into a flamefest with doubters all over the place. I’m glad that you actually took care to join in the discussion but saying “When you little scamps get together, you’re worse than a sewing circle…” to part of your readership is hardly respectful.

          Hattig: From what I hear S1 will be a dual-channel DDR2 socket. Since AMD is “tweaking” it for a smaller form factor I’d guess that it’ll only have the bare minimum amount of pins possible (2 DDR2 channels, a single HT link, and the various power/identification pins, which could be doable with 638 pins… maybe).

          EDIT: Various grammar/spelling corrections, heh.

          • Damage
          • 14 years ago

          Our tests involve the impact of CAS latency, as well. CAS latency generally is more important to overall RAM performance than tRP and tRCD, as I understand it. So I would disagree with you there.

          Can you help me understand how your tests at different RAM clock speeds tell us anything relevant to this question? We’re supposed to think 3-3-3 is faster at 400MHz because you found a particular clock speed/timings combo to be faster? Adding clock speed to the mix seems to muddle things entirely to me.

          • Lazier_Said
          • 14 years ago

          In your own thread on the Anandtech forum, you concluded that WinRAR was the only test to show significant differences and you yourself were sticking with value RAM.

          In the only test conducted at equal frequency, which was PC3000 at both 2-2-2 and 3-3-3, even WinRAR only showed a 12% delta.

    • totoro
    • 14 years ago

    .r[

    • Nelliesboo
    • 14 years ago

    This seems like it is a little late to the table unless someone is trying to build a desktop around these parts. At the current time Core Duo laptops can be had at pretty much the same price points single core Pentium M’s can. Also why are the cpu’s not the same speed. I kinda ran through the review and didn’t read everything so i could be wrong about something. But it seems like it would have been a little different had it been 2ghz vs. 2ghz. The platforms have differences that hurt and benefit both cpu’s but clock speed seems to not make it a fair go.

    • tilted
    • 14 years ago

    So if the AMD has an onboard mem controller, how much juice does the Pentium take when a board memory controller is added to the power-consumption equation?

    Would be nice to see how much power is/ or could actually be saved by not using the board memory controller.

    • Kocur
    • 14 years ago

    Hi guys,

    A very nice review. However, I have to point out three things:
    abnormally low score in PiColor for Turion. There is no way that it would be twice as slow as FX53 in that benchmark
    the differences in power draw results come mainly from the mainboard. I think that with mainboards being equal in power draw, P-M would be only several watts better
    you could also run A64 in 64-bit environment.

    You can find P-M and A64 comparison (and much more) on
    §[<http://www.digit-life.com/articles2/cpu/method-2005-overall.html<]§

      • accord1999
      • 14 years ago

      I doubt it, this is the third review which shows under load, the P-M uses less than half the power of the Turion ML. It’s much more likely that the P-M’s motherboard consumes more power.

        • Koly
        • 14 years ago

        The P-M motherboard might consume more power, but the problem is that, as several people noted, the Turion is overvolted (1.45V instead of 1.35V), thus the power measurements under load are invalid.

          • Dr. Evil
          • 14 years ago

          “the Turion is overvolted (1.45V instead of 1.35V), thus the power measurements under load are invalid.”

          <sigh> First I’m running the memory at DDR333, now I’m overvolting the processor. Can we put away the Jump To Conclusions Mat now?

          The Turion was not overvolted. The MSI motherboard doesn’t even have voltage adjustments. The numbers I gave for minimum and maximum voltage were measured by CPU-Z at idle and full load respectively. Why does it show 1.45V? Several possible reasons spring to mind:

          1. The accuracy of the motherboard voltage measurements is off.

          2. The motherboard is incorrectly supplying 1.45V when the processor is only requesting 1.35V.

          3. The processor is getting 1.45V because 1.45V is within its voltage range.

          I’m partial to this last one, mostly because I can fire up RMClock and see that the VID range programmed into the processor is 0.800V to 1.500V. 1.45 < 1.5 = No overvolt.

          When you little scamps get together, you’re worse than a sewing circle.

            • Koly
            • 14 years ago

            Andy, you have an obvious error in the review, as is clear from the link posted by impar (#66). The correct voltage is 1.35V. The motherboard supplies 1.45V most probably because the cheapo board does not recognize the mobile CPU correctly. I know the motherboard does not have voltage adjustments, I have used it. Use RMClock instead.

            The incorect voltage is not a minor issue. One would expect you to know that supplying correct voltage to a mobile CPU is extremely important in order to maintain the power envelope guaranteed by the manufacturer. The difference can be of order of tens of percent. For example, the whole difference between the 35W ML series and the 25W MT series is the voltage, 1.35V vs. 1.2V. You have tested a 1.45V “MA” series with power draw higher than that of a desktop chip.

            Please, save face for Techreport and redo the power measurements using 1.35V under load for Turion. It would be nice if you could also try to run it at 1.2V and a lower multiplier (let’s say 10x for 2.0GHz) to emulate an MT Turion.

            • Hattig
            • 14 years ago

            To be fair, at 35W max @ 1.35V, going to 1.45V shouldn’t increase power consumption that much – maybe another 2.5W – 5W under load. Still, it isn’t a fair test and should be redone just to keep us quiet!

            And I like the idea of emulating a 2GHz Turion MT processor – that way the review could have tested the Pentium M against both a price-equivalent chip, and a speed equivalent chip.

            • Koly
            • 14 years ago

            Remember that as a general rule, power consumption increases as a square of voltage. Furthermore, the 90nm process is known to be tricky in this regard, so it might increase even exponentionally. Compare the ML vs MT Turion series, a 12% increase in voltage (1.35/1.2V) results in a 40% higher power draw (35/25W). Here we are talking about a 7% increase in voltage, which might therefore bring around 30% increase in power consumption, that is something like 10W. Count in the inefficiency of the PSU, say 75% at such low loads and the increased strain on the voltage regulators and we are possibly talking about 15W total system power consumption.

            • Palek
            • 14 years ago

            That sounds right to me.

            Andy (and Scott), for the sake of your readership and to protect yourself from more nagging, could you please redo those measurements if possible? If not, or the effort required is too great, I am sure that the promise of rectifying these problems in a future article would quell the complaints. 😉

      • Dr. Evil
      • 14 years ago

      “abnormally low score in PiColor for Turion. There is no way that it would be twice as slow as FX53 in that benchmark”

      Riiiight…. except it was. Three times in a row, and even a couple more after a reboot because I didn’t believe it at first either. I’m not exactly sure what you’re trying to say with this statement. That I misread the output file several times in a row? That Intel snuck in and recompiled picCOLOR with a –turion-suck flag when I wasn’t looking?

      Perhaps a better explanation is the one I gave right under the graph in the review: picCOLOR updates the screen a LOT, and these updates likely caused the integrated graphics to make unusual demands on the system memory, lowering bandwidth and thus performance.

      If my theory is correct, running the picCOLOR benchmark with discrete graphics would result in a huge performance increase. And it does: With the GeForce 6600GT installed, the Turion system scores a 3.61 overall in picCOLOR.

      Or is that score abnormally high?

    • Shintai
    • 14 years ago

    Just a few notes.

    In the testconfig it says ICH6 southbridge but ICH7R audio etc. (It is ICH6)

    The RS482 also seems more like a superior mobile solution compared to a vanilla P4 oriented i915. Why wasn´t the Aopen i915Gmm-HFS used?

    There is also only a 19W idle difference on the P-M. Tho its more like 25W in real life when it changes from 100% load to 800 or 900mhz in idle mode (Specially from AC side). Maybe the chipset didnt support it, but it did on the AMD setup? You can use utilitize like trottlewatch to ensure its doing it.

    The Turion is overvolted aswell, so those numbers cant be trusted either.

    So, nice try, now start again 😛

      • accord1999
      • 14 years ago

      19W is quite accurate, since that’s really how little power Dothan uses. Not even the 2.26 Dothan ever comes close to 27W even with a power virus.

      • Furen
      • 14 years ago

      The MSI RS482M-IL is a $70 motherboard for Semprons and old A64s, so I’d hardly call it a “superior mobile solution compared to a vanilla P4 oriented i915.” In fact, I’d guess that the Aopen board uses a more powerefficient chipset, better power regulators, etc, since it’s a $220 part.

      Regardless, I’d guess that some of the data is either wrong or Turions perform significantly worse than A64s clock for clock (the Pentium M being at a 20% clockspeed disadvantage and still being faster in games seems inaccurate to me, considering that A64s and Dothans pretty much match each other clock for clock).

    • impar
    • 14 years ago

    Greetings!

    Turion voltage should have been 1,35v:
    §[<http://fab51.com/cpu/guide/opn-s754-e.html<]§

    • Furen
    • 14 years ago

    I think your PicColor numbers are a bit wrong on the Turion…

    Your overall score was 1.94? On your FX-53 review your A64 3400+ scores 3.95 (on a 2.2GHz clock rate, no less) so I think your CPU is throttling in some way.

    It’s also a bit weird how your 6600GT performs so badly on the Turion system (Perhaps your ATI drivers are messing it up?)… Your CPU power graphs are pretty nice, though I’d hope to see just how much of a difference going for the MT series makes.

    • lindy01
    • 14 years ago

    “Ours is not a perfect world, and we acknowledge that this is not a perfect match-up, at least not in terms of price.”

    Orrrrrrrrrrrrrrrr……………………..ability. I am sorry this test was kind of lame. Why not test the fastest each has to offer?

    Go ahead and STATE the intel is more expensive….STATE that the 760 is closer in price….but test the 760, 765, 770, 780 and the T2600(with its 667mhz memory bus). The latest and greatest of each. You do the same when it comes a crazy priced Intel desktop CPU’s

    §[<http://www.techreport.com/reviews/2006q1/fx60-vs-955xe/index.x?pg=1<]§ You had your chance to show it all, what most people wanted to see....but you dropped the ball. You should have tested them with 7800GTX's so with some current games....so we could see what kind of gaming we could have gotten out of it, Winzip runs great on most laptops and I dont really care if takes a few extra seconds....compared to a game and its performance. Lastly you could have tested Windows XP 64 bit on the AMD CPU to show everyone how much 64bit compatibility does NOT matter currently or probably for another year or so. Heck run a test against the Core Duo running 32 bit and the Turon running 64 bit. Sorry I like your site but I am currently shopping for a new laptop and right now the Dell 9400 is probably going to be it for me....unless the Turon could have been shown to best it....but with this review I am going to ASSUME that the T2600 would hand the Turon its @$$ if the 760 is even with it. At $2000+ for a loaded laptop what is another $100 or even $200 when your trying to make it last a long time?

    • Vaughn
    • 14 years ago

    Thought it was a very good review damage, And I agree with the part about Idle Load vs Full load.

      • jobodaho
      • 14 years ago

      Check out who wrote it.

    • IntelMole
    • 14 years ago

    Perhaps this power consumption thing could be settled by a “middle ground” test, measuring the power consumption watching an mpeg4 movie or something, i.e. something around the 25-50% CPU level…
    -Mole

      • SpotTheCat
      • 14 years ago

      I think DVD viewing would be a good power consumption test. it’s something people like to do with their laptops that is very battery sensitive.

        • IntelMole
        • 14 years ago

        That was my first thought, but I rejected it. People do it, but it’s not *especially* CPU power intensive. Also, it puts another variable in the equation – the dvd drive. Granted for this test, the same drive could be used, but it won’t be the same for different laptops.

        At the same time, people will want to watch movies and stuff like that they’ve put on their computer already, so this is still a fairly sensible “moderate use” measure…
        -Mole

    • Bensam123
    • 14 years ago

    “That’s right, Intel wins a gaming benchmark!”

    Best quote ever.

    • LicketySplit
    • 14 years ago

    #44…Me too:)

    • Koly
    • 14 years ago

    Finally a P-M vs. Turion review, good job except:

    1) MSI RS482M does not have a mobile Ati chipset. AFAIK, and I used this board for one build, It’s a regular Xpress200 desktop chipset. Just think about it, how could such a budget board use a mobile chipset?

    2) The memory in the AMD system seems to run at DDR333, as indicated by the memory bandwidth benchmark. It’s logical, as many s.754 boards put the memory automatically to DDR333 when two DIMMs are used.

    The power measurements are intriguing. The 46W difference between idle and load seems way too much when compared to your own measurments of desktop systems:

    §[<http://www.techreport.com/reviews/2005q3/athlon64-x2-3800/index.x?pg=13<]§ It was a 37W delta for a desktop A64 3800+, which is running at 2.4GHz as well, and 48w for A64 X2 3800+. I have build a X2 3800+ system too and it had (according to the UPS) roughly a 20W difference per core under load. Is it better to buy a desktop chip instead of a mobile one? Part of the problem might be that I doubt a little that the Turion should run at 1.45V, when a regular Venice core runs at 1.35-1.4V and a X2 at 1.3-1.4V, depending on the version.

      • Damage
      • 14 years ago

      Andy confirmed the memory clock speed before his testing. Don’t forget that the systems are using integrated graphics, and the graphics controllers will take their cut of memory bandwidth. That is the likely reason that the Turion’s memory bandwidth scores came out lower than one might expect for DDR400.

      I don’t think you’re thinking about the difference between idle and load power consumption in the right way. The larger delta between idle and load for laptop CPUs makes perfect sense, in that mobile processors have more extensive clock gating and the like–shutting down parts of the chip not in use–at idle than desktop processors. Naturally, a chip with more aggressive optimizations for power use at idle will have a larger power consumption delta when going to fuller utilization.

        • Koly
        • 14 years ago

        Ok, the memory speed seems to be correct as Andy confirmed in his post #50.

        On the other hand, I don’t think the delta between idle and load should be bigger for a mobile chip, quite the opposite. The power optimization like clock gating should make a difference under load, not idle. A regular desktop 90nm A64 with C’N’Q enabled draws only a few watts idle (<5W), there is no room for a higher delta. I suspect the voltage for the Turion (1.45V) was set too high, I don’t see a reason why it should be higher than the voltage of desktop chips. The board, which does not allow to change the voltage in BIOS, might automatically set it to the highest possible value for a 90nm K8 when not recognizing the mobile CPU, and that is 1.45V. I would expect more like 1.3V. I suggest confirming the voltage with AMD and if I am right, updating the power measurements (using a utility like RMClock to set the proper voltage).

        • Hattig
        • 14 years ago

        The effect of integrated graphics is an interesting one.

        Clearly the dual-channel Intel chipset is not being affected as much here, whereas the single-channel AMD processor will have to share bandwidth (and the higher the resolution, the higher the bandwidth).

        Socket S1 (or whatever the next AMD mobile socket is called) may help, with DDR2 support, even though it is 95% likely to be single-channel. DDR2-667 sounds like a viable option here, and would double the bandwidth over DDR-333.

        The alternative are the mythical mobile chipsets with on-die memory controller for the integrated graphics, allowing Turbocache or Hypermemory like configurations.

        Edit: and yes, the power consumption figures should be done again with 1.35V.

      • highlandsun
      • 14 years ago

      Agreed, the power graphs are funky. The CPU is only supposed to draw 35W maximum, so how can running at full load produce a 46W delta vs idle?

    • IntelMole
    • 14 years ago

    Good review as always. These results back up what I’ve read from other sources, that the Turion is at least comparable to the Pentium-M, beating it in some places, losing in others.

    The Power consumption thing, in my view, essentially ends in a tie, and wavers either way depending on what your load pattern is. I’d rate the transistor library selection as the reason for the Pentium M’s better performance under load.

    Whether it offers better value for money than the Pentium M, again, depends entirely what you’re doing. But at the end of the day, if you’re given a Turion in your laptop rather than a Pentium M, you’d likely not notice the gulf in performance some would have you believe…
    -Mole

    • Sumache
    • 14 years ago

    Would be interesting if you can downclock the Turion to the same speed and have a matchup there :p

      • IntelMole
      • 14 years ago

      Why? So that we can see that the P-M has superior clock for clock performance in most areas?

      For further information, see: Athlon64 vs. P-4,
      -Mole

        • A_Pickle
        • 14 years ago

        …what? The Pentium M has WAY more power per clock cycle than the Pentium 4….

        -Pikl

          • IntelMole
          • 14 years ago

          My point was, comparison at the same clock speed is meaningless. Just as it is with the Athlon64 vs. P4 thing.
          -Mole

            • wierdo
            • 14 years ago

            Yep, I don’t know why that’s necessary, the two products are looking competetive as it is.

    • spiralscratch
    • 14 years ago

    Overall a good review.

    My only complain is with the graphs. The two processors kept switching places, which made it harder to make comparisons across graphs (e.g. the power consumption graphs). Please keep the positions of the items being tested consistent.

      • crichards
      • 14 years ago

      Seconded.

    • Ricardo Dawkins
    • 14 years ago

    where is Shintain when intel needs him the most ?

    • Kurlon
    • 14 years ago

    I’m surprised the Turon can only throttle down to 800mhz. Under FreeBSD 6.0, on a box sporting a pair of Opty 246s, powerd can clock them down to 200mhz. I’ve not played with a P-M, but it wouldn’t surprise me to find it can clock far lower as well.

      • coldpower27
      • 14 years ago

      They are keeping the normal FSB and just throtling using the multiplier, the lowest of which is x4 on Athlon 64’s I believe, and x6 on Pentium M’s, hence you get 133×6 and 200×4 both of which are 800MHZ.

      Yonah also has this limitation hence you can only throttle down to 1GHZ on Yonah based Laptop I believe.

      Here is to hoping Conroe/Allendale can throttle to a x3 Multiplier, that would be perfect for a 266/333 FSB, as that would translate to 800MHZ and 1GHZ respectively.

        • Kurlon
        • 14 years ago

        Well, they need to include FSB downclocks as well then, as the Opty can appearently do it. : )

        It’s pretty easy to test, install FreeBSD 6. (6.1 is in beta, good enough for this purpose)

        Boot with ACPI enabled, the default.

        sysctl dev.cpu

        That’ll list available speeds and the estimated wattage draw for each speed.

        Let me borrow the hardware and I’ll happily test. : )

    • swaaye
    • 14 years ago

    I’ve found my Dothan 2.13 can outrun my Barton 2.4 with Xvid encoding. Probably by like 5% or something, I don’t remember the numbers anymore. And it does that while sucking 1/3 the power at the outlet. I hooked up my Killawatt doodad and found the laptop pulling ~50W encoding while the desktop was sucking 160W+. I wouldn’t really say it has poor video encoding performance if you take that into consideration.

    I just built a Opteron 165 setup. OCed to 2.6GHz/1.45v. So it’s basically a FX60 at 1.45v. Now, granted that this is very, very fast, but it sucks around 260W while encoding. I get about 80fps on each pass with Divx6.1.1 Pro. That is approx 3x as fast as my laptop with a 5x power disparity. 🙂

    And we’re talking a Dell Inspiron 9300 with GF6800 Go and 2GB DDR2 here. It’s just way more efficient.

    • indeego
    • 14 years ago

    And while AMD pulls ahead in performance, Intel Marketing and teamwork pulls off coup againg{<:<}g §[<http://news.com.com/Intels+mantra+Lets+make+a+deal/2100-1006_3-6038282.html?tag=nefd.lede<]§

    • UberGerbil
    • 14 years ago

    It’s worth noting that (according to pricegrabber) the Turion mobo is typically available for about $70, whereas the P-M board is more like $250. If you’re building an HTPC, that’s a pretty big difference.

      • Chrispy_
      • 14 years ago

      Yep, much as I like the Pentium-M architecture, the whole thing’s a fecking rip-off.

      Should be good to see the next gen intel desktop stuff thought. I was an Intel fan until they stupidly gunked up their fanbase with pentium 4 rubbish, and if they’re switching back to a more useful architecture then I’d certainly give them another shot.

        • muyuubyou
        • 14 years ago

        The disparity in game benches onboard vs card seems to indicate there is an advantage to the P-M more than just memory bandwidth. Must be the chipset performing better on P-M’s side.

        I’d like to see a “best 2000$ P-M laptop” against “best 2000$ Turion laptop” with the rest of the specs matched as much possible.

          • Koly
          • 14 years ago

          I don’t think it has anything to do with the chipset, that plays a very minor role in the K8 architecture. Most probably (see my post #45) the memory in the AMD system is running at DDR333.

            • Dr. Evil
            • 14 years ago

            The memory is definitely running at DDR400 speeds, verified by both Sandra and CPU-Z. You are taking into account that some of the memory bandwidth is going to the integrated graphics, right? Just for giggles, I put the 6600GT card in and got a Sandra score of 2934/2924. Is that closer to what you were expecting?

            • Koly
            • 14 years ago

            Ahh, ok, that would be more like it. But what about the voltage, are you sure the Turion should run at 1.45V, higher than the desktop chips? If you overvolt the CPU, the power measurments do not give a correct picture.

    • accord1999
    • 14 years ago

    So it looks like AMD and Intel’s mobile TDP situation is switched compared to desktops, AMD being far closer to hitting, or exceeding its 35W TDP while Intel isn’t even close to 27W.

    Of course, the idle power consumption of a desktop system is not easily translatable to a notebook, a typical P-M system under idle is in the 10W-20W range, depending on the video card and screen.

    • Convert
    • 14 years ago

    Great review.

    It would have been interesting to see what a MT turion could have done power wise. IIRC though they top out at 2.2.

    I would say the 760 wins this battery of tests overall, at least for the things I would do with the laptop.

    While they are priced similar it is exciting to see the pm @ 2GHz giving the 2.4GHz turion a hard time, though the turion really needs that second memory channel.

    • Afty
    • 14 years ago

    I’m not sure about those power consumption numbers. If you’re going to make the argument that the idle consumption is more important than load consumption, then you really need a number for idle consumption /[

    • absinthexl
    • 14 years ago

    What kind of load does playing a DVD put on the processor?

      • UberGerbil
      • 14 years ago

      It’s going to depend a lot on how much the GPU can offload. But even with no help from the GPU I wouldn’t expect more than 50% load on these processors with standard def and a decent codec.

      It would be a good test, though. Power consumption under that load would be interesting as well.

    • Dposcorp
    • 14 years ago

    Excellent review TR.

    I always knew the P-M wasnt that much better then the Turion, and this proves it. I very much like the P-M too, but people were always un-fairly saying how it killed the Turion.

    What will be interesting is the next Turion, which will probably be S939 or M2, based on a X2 core.

    Nice to see that matchup, what with two lower power cores, and the Turion with dual channel DDR2 SODIMM memory.

    Also I want my next notebook to have a 64Bit chip.

    I think I’ll wait for a dual core Turion Vista notebook.
    64bit cpu, dual channel DDR2, 64Bit OS.

      • DaveJB
      • 14 years ago

      AFAIK, when the Turion changes socket it’ll be to a single-channel DDR2 socket.

        • Wajo
        • 14 years ago

        Actually, Turion is going to go move to socket S1 i think (600 or so pins), dual core with dual channel ddr2… :p

      • fatpipes
      • 14 years ago

      The P-M is the one with the DDR2 dual channel

    • flip-mode
    • 14 years ago

    Thanks for the review. I’ve been waiting for a mobile showdown, TR style, for a looong time. 🙂

    • DreadCthulhu
    • 14 years ago

    So, this time around its AMD for video editing, and Intel for gaming? Seems like an odd turn around. 😉

      • tfp
      • 14 years ago

      I would be iterested to see if that holds of for chips of the same clockspeed, just for fun.

        • UberGerbil
        • 14 years ago

        Uh– “if that holds”? The P-M runs at 2.0GHz, the Turion at 2.4 — that’s a 20% advantage in favor of the Turion, and the P-M won the game benches (on the discrete GPU tests). It would be interesting to see how much weaker the Turion would be on those tests without the clockspeed advantage, I guess.

          • tfp
          • 14 years ago

          It normally doesn’t work as a strait 20% that’s what I was interested in. More of a performance per lock then per dollar.

          • Dposcorp
          • 14 years ago

          This reveiw may favor the entire Intel platform, but that doesnt mean the just the CPU.

          Put the Turion a S939, dual channel, Nforce4 chipset and things will change.

          For the differences in performance, I think the single channel memory amd weak chipset could be playing a factor.

          Yes, the P4 is 400Mhz slower. Yes, it draws less power then the TL-44.
          And yes, it still beats the TL-44 a lot of the time.
          The P-M/Centrino platform is a great one, and no one can argue that.

          The main thing I am saying it that you can not take the CPUs and compare them without keeping in mind the core logic they are working with these days.

          A S754 Turion may run ok on the very first VIA based S754 boards, but it would probably run a lot better on the latest Nforce based S754 boards.

          Like this one:

          EPoX EP-8NPA7I Socket 754 NVIDIA nForce4 4X ATX AMD Motherboard

          §[<http://www.newegg.com/Product/Product.asp?Item=N82E16813123255<]§ TR has reviewed more then a few ATI and has said that the chipsets have a few kinks to work out before they get to Nvidias level.

            • coldpower27
            • 14 years ago

            For the moment though Dual Channel Memory isn’t available on the Turion platform, and neither to my knowledge are Nforce 4 Chipsets, most Turion’s used the Radeon Xpress 200 to get it’s integrated graphics.

    • FireGryphon
    • 14 years ago

    Good review, even if it shortly precedes a wave of newer products. Dual core laptops? Me want…

    • blastdoor
    • 14 years ago

    I think this review goes too far in letting the Turion off the hook on power consumption. The argument appears to be that “well, people don’t use laptops for CPU-intensive stuff, so power consumption under load doesn’t matter”. If people don’t use laptops for CPU-intensive stuff, then why bother buying a laptop with a fast CPU? (in fact, my wife has a 1 GHz pentium M laptop that she is perfectly happy with for this very reason — she just doesn’t need that much CPU power in a laptop)

    But if people play games on the plane or want to do work (and their work invovles video or image processing), then CPU usage under load definitely does matter. For people who don’t do those things, why buy this laptop?

      • lex-ington
      • 14 years ago

      Aaahhhh blastdoor. . . . . I think you know the answer to your question.

      I’ll just doa little hint – people like gadgets, no matter how functional it is. A laptop is a cool gadget. And we all know why people drop money on gadgets. . . . . . But people like gadgets MORE if they don’t chew through batteries.

      I, for one, know quite a few people with top-of-the-line laptops that just turn them on to look cool.

        • droopy1592
        • 14 years ago

        I know some that /[

          • quarantined
          • 14 years ago

          Raises hand. Well, I left my PM 1.5GHz on to fold for months on end untill the good ole hard drive crapped out. Knowing full well the likeliness that that would happen, I didn’t lose anything important. Man how I hate today’s hard drives.

          Great review.

            • Usacomp2k3
            • 14 years ago

            I fold on my 1.5ghz P-m 24/7, well at least when it’s not summer. Then I can’t take the heat 8)

            • sativa
            • 14 years ago

            wait are you saying the turion is better for your use?

            • Usacomp2k3
            • 14 years ago

            I was just stating that I am less likely to have it on idle when using, also. Wonder about the relationship between cpu load and power consumption, whether it’s linear. When you factor in the IPC factor, that would further complicate such an equation. However, that would be something that I would find quite fun to try and figure out 8)

            • tfp
            • 14 years ago

            Not sure I can under volt my Pentium-M by a good amount and still run at normal speeds. Any one know if the Turion is the same way?

            • dragmor
            • 14 years ago

            If ever a TR article needed custom undervolting this is it.

            In answer to your question, Yes you can undervolt the Turions, you can actually undervolt any A64. I’ve yet to see a Venice core CPU that doesnt run at stock speed with 1.2v (default 1.4v). My 3500+ runs 2.2ghz with 1.1v (requires 1.2v to boot, but is fine after that with 1.1v) and 800mhz with 0.8v.

            Its not as low as the PM can go, but its good for a desktop processor.

            • tfp
            • 14 years ago

            Yeah I run my PM-1600 at .8v for low and 1.0V for full. I might be able to make it go lower but no need to mess with it.

      • KeillRandor
      • 14 years ago

      I know a number of people who use a laptop as a desktop replacement, simply because they can use it both at work and at home AND on the train in between… Since it’s always plugged into the wall – (even on the train), the power consumption dosen’t mean so much…

      • Lazier_Said
      • 14 years ago

      A desktop workload that leaves the processor essentially idle 95% of the time doesn’t at all suggest performance doesn’t matter. The hourglass hiccups the other 5% of the time are the performance the user actually notices.

      To me, that performance (or lack thereof) is much more disruptive than some encoding task taking 6 minutes instead of 5, or a game running 50fps instead of 60.

      • leor
      • 14 years ago

      the point is when you are on the battery (on a plane for example) you are much less likely to be running it at full load.

    • droopy1592
    • 14 years ago

    FP

    maybe AMD should put anoder memuh-ree channer on that bad boy.

      • Dark*staR
      • 14 years ago

      memuh-ree, the ever-living!

        • emkubed
        • 14 years ago

        I have one word for you: Schnarf !

        • droopy1592
        • 14 years ago

        HAHAHAHAHAHA

        old school

Pin It on Pinterest

Share This