I actually have a mini ITX sized(mini ITX was not a standard back then) socket 370 motherboard here that I need to recap. It has a S3 savage 4 integrated graphics chip and a single PCI slot. Although not quite the same thing I have also considere a mini itx build for a retro pc.
The only issue I can see is finding drivers that will work for older operating systems, the atom should easily have enough grunt to use the voodoo3

That board wouldn't be affected since it's a rather old one, but you have to watch out with newer hardware. Some mini-itx boards have begun using exclusively UEFI boot options, no more legacy boot settings so things become far more complicated with older operating systems.

I've been using Atom N270 netbook as a student, back when the netbook thing was new and popular. To my experience, it was somewhere near average P4 performance-wise. It is a nice platform for older games; I have completed Max Payne on it. Games like Heroes III, Fallout 1-2 work and look great, much better than on bigger LCDs. Mine has 1024x600 screen, so 800x600 is the default playable resolution.

RacoonRider wrote:

I've been using Atom N270 netbook as a student, back when the netbook thing was new and popular. To my experience, it was somewhere near average P4 performance-wise. It is a nice platform for older games; I have completed Max Payne on it. Games like Heroes III, Fallout 1-2 work and look great, much better than on bigger LCDs. Mine has 1024x600 screen, so 800x600 is the default playable resolution.

I have one of those too - an ASUS eeePC 1001HE. It would be perfect for older games if the keyboard wasn't such a steaming pile. 😒

Battery is great though. I mainly use it as a lightweight video watching and emulation machine for flights and stuff.

dexter311 wrote:

RacoonRider wrote:

I've been using Atom N270 netbook as a student, back when the netbook thing was new and popular. To my experience, it was somewhere near average P4 performance-wise. It is a nice platform for older games; I have completed Max Payne on it. Games like Heroes III, Fallout 1-2 work and look great, much better than on bigger LCDs. Mine has 1024x600 screen, so 800x600 is the default playable resolution.

I have one of those too - an ASUS eeePC 1001HE. It would be perfect for older games if the keyboard wasn't such a steaming pile. 😒

Battery is great though. I mainly use it as a lightweight video watching and emulation machine for flights and stuff.

I should have gone with Asus then... Mine is hp Compaq mini 110c. The battery is half-dead and can only hold for 15 minutes at zero load. New batteries are more expensive then a similar used notebook. The keyboard is perfect though, it failed and I changed it for rediculous money, so no more Russian symbols 😜

Last time I used to as a low-power torrent machine back when my internet lacked bandwith a lot... It's not noticeable if you leave it on for the night.

Atom is (markedly) worse per-clock than P4, so performance will be worse than higher-tier P3s (e.g. Tualatin) and AthlonXP in many cases. That may or may not be a bad thing, and keep in mind Atom is fairly power efficient (it uses less power than the 945 chipset that it's commonly paired to). It wouldn't be bad if you had a system that ran Windows 98 or Windows 2000 and wasn't meant to run very heavy games (like Fallout 1/2 that were mentioned earlier), but it should not be considered a suitable P4 replacement - if you need that level of performance but have some hang-up on NetBurst, look at Pentium M, Core Solo/Duo, or Core 2.

RacoonRider wrote:

Last time I used to as a low-power torrent machine back when my internet lacked bandwith a lot... It's not noticeable if you leave it on for the night.

Yeah I used mine with a few external HDDs as a low power home server for 2 years. Ran 24/7 without a problem, serving up media and torrenting.

dexter311 wrote:

I have one of those too - an ASUS eeePC 1001HE. It would be perfect for older games if the keyboard wasn't such a steaming pile. 😒

I have a eee PC 1000HE, with atom N280 at 1666 MHz. It is told to perform about the same as the celeron 900MHz of the earlier eee PCs. With the difference that it has a hyperthreading core. The original HD was replaced with a 32 GB SSD.
It is nice to have such a small portable x86 system, but the CPU and GPU are indeed very limited. A friend of mine installed Call of Duty (2003) on a N270 atom, and it ran, though too sluggish for my taste. I read about someone installing Windows 98 on it, but I doubt the realtek sound was functional in that OS.

This 1000HE has an OK keyboard, "Chiclet" style. Once I modified an older eee PC by ordering and installing a 1000HE Chiclet keyboard; it fits fine.

Some years ago I was very interested in Mini-ITX compactness, and I build a Mini-ITX Core Duo system, using parts from a dead laptop. It was surprisingly hard to install hardware and route cables in such a small box. I had to make some compromises.

obobskivich wrote:

Atom is (markedly) worse per-clock than P4, so performance will be worse than higher-tier P3s (e.g. Tualatin) and AthlonXP in many cases. That may or may not be a bad thing, and keep in mind Atom is fairly power efficient (it uses less power than the 945 chipset that it's commonly paired to). It wouldn't be bad if you had a system that ran Windows 98 or Windows 2000 and wasn't meant to run very heavy games (like Fallout 1/2 that were mentioned earlier), but it should not be considered a suitable P4 replacement - if you need that level of performance but have some hang-up on NetBurst, look at Pentium M, Core Solo/Duo, or Core 2.

Source? Atom maybe slower than most P4 overall because of it's low clock rate but I am pretty sure it is faster per clock.

I think it would depend on the model of Atom and P4 you are comparing. A non-ht Northwood vs a 1.67 dual core Atom would be a lot different compared to a 3.0+ ht Prescott.

obobskivich wrote:

Atom is (markedly) worse per-clock than P4, so performance will be worse than higher-tier P3s (e.g. Tualatin) and AthlonXP in many cases. That may or may not be a bad thing, and keep in mind Atom is fairly power efficient (it uses less power than the 945 chipset that it's commonly paired to). It wouldn't be bad if you had a system that ran Windows 98 or Windows 2000 and wasn't meant to run very heavy games (like Fallout 1/2 that were mentioned earlier), but it should not be considered a suitable P4 replacement - if you need that level of performance but have some hang-up on NetBurst, look at Pentium M, Core Solo/Duo, or Core 2.

Not even close. At best a P4 is very slightly faster than an Atom per clock, but in many benchmarks the Atom wins handily.

I have personally run the old unixbench program against a D510 1.66 GHz and a P4 1.5 GHz (what I had). The P4 was about 12% faster. Hardly "markedly" worse. Note the version of unixbench I used did not benefit from the Atom's extra core.

However in Passmark the P4 gets its ass handed to it. The D510 is nearly 5x the speed of the P4 1.5. Even taking the extra core into account the atom is over double the speed of the P4.

I really depends on what you are doing, but an atom will at least be as fast as a P4 and in some cases much faster assuming similar clocks.

smeezekitty wrote:

Source? Atom maybe slower than most P4 overall because of it's low clock rate but I am pretty sure it is faster per clock.

I own one of each at similar clocks, and the P4 system is overall faster. But benchmarks also support this, for example Passmark:
http://www.cpubenchmark.net/cpu_lookup.php?cp … 270+%40+1.60GHz (this is the Atom model I have; notice that it's fairly close to fast P3s, slow AthlonXPs, etc - fast P4s are quite a bit up the list)

Tom's also did a more comprehensive test with multi-core Atom:
http://www.tomshardware.com/reviews/atom-d510 … top,2649-4.html

The multi-core performs somewhat better in some tasks that are weighted towards multi-core/multi-thread, but in terms of single-thread performance (which is what we care about for gaming) the P4 comes out ahead. There are some cases where the P4s actually outpace the dual-core Atom as well. The big "gotcha" is that Atom's overall platform is inferior to that of P4 - things like I/O, memory bandwidth, etc are all heavily limited on the Atom, whereas the P4 can have the full benefit of dual DDR/DDR2 and PCIe x16 graphics if you like.

TechReport also tested a "high end" Atom netbook some years ago, and even with GeForce 8/9 graphics it struggled at low resolution/settings in games that were years older than it: http://techreport.com/review/15940/asus-n10jc-a1-netbook/5

It's just not a good platform for demanding DX8/9 gaming. However as a super-light Pentium II/III replacement it would be fantastic. If you want to fully replace the P4 with another single-core, lower power Intel, go with the Pentium M. There are more complete desktop board options available (there are i915 Pentium M motherboards with full PCIe x16 and dual-channel RAM for example), and it's generally more on par with P4/A64 performance while using comparatively little power (I think max TDP for Pentium M is around 30W, vs 80-130W for P4/A64/etc). For example see this benchmark review:
http://techreport.com/review/7927/the-pentium … fi-855gme-mgf/7

washu wrote:

Not even close. At best a P4 is very slightly faster than an Atom per clock, but in many benchmarks the Atom wins handily. […]
Show full quote

Not even close. At best a P4 is very slightly faster than an Atom per clock, but in many benchmarks the Atom wins handily.

I have personally run the old unixbench program against a D510 1.66 GHz and a P4 1.5 GHz (what I had). The P4 was about 12% faster. Hardly "markedly" worse. Note the version of unixbench I used did not benefit from the Atom's extra core.

However in Passmark the P4 gets its ass handed to it. The D510 is nearly 5x the speed of the P4 1.5. Even taking the extra core into account the atom is over double the speed of the P4.

I really depends on what you are doing, but an atom will at least be as fast as a P4 and in some cases much faster assuming similar clocks.

I really dislike "not even close" or "gets its ass handed to it" or "kills everything" kind of over-generalizations because they aren't generally accurate and usually lead to a tug-of-war exchange that eventually degrades into name calling. I'm not insinuating that you're trying to create such a conflict, mind you, just stating my issue with such constructions. 😊

Regarding your results: you've run a single test, which actually confirms what I said originally. The Atom is clocked around 10% faster, and still performs 12% slower, that's significant. We don't have to see 3000% variations for it to be noteworthy - even the often argued-about differences between Pentium 4 and Athlon or Pentium 3 aren't all that big (see this old Anand review for an example: http://www.anandtech.com/show/818). Sure, Atom can handle some tasks better - especially the multi-core chips in applications that make use of multi-threading, but that isn't important for running old games where single-thread performance is king.

With Passmark, you cannot directly compare overall scores between single and multi-core processors - Passmark heavily favors multi-core hardware (and the developers of Passmark even acknowledge this), and you will never see that "5x the speed" in a real world application as a result. If you look at the single-thread score for the Atom D510, it scores measurably lower than the 1.6GHz P4 (I know, you don't have that chip and it isn't what you used to look up Passmark, but since we're looking up synth results from a huge database, I figured I'd just "equalize" things), by around 30%. However the P4 gets a very low overall score because it cannot do the multi-core portions of Passmark (which is largely irrelevant for our purposes).

And if you bump up to a more typical P4, in the ~3GHz range, it will perform even better (see the Tom's comparison - they have a 3.2HT against a D510 - in a lot of cases the 3.2HT is leading the way, in some cases multiple times over the Atom's performance). This also doesn't account for the gorilla in the room: most Atom platforms don't have AGP/PCIe expansion, and the ability to hook up a discrete graphics card will give a bigger advantage for gaming than the differences between the CPUs. You also only get the one expansion slot, so if the onboard sound is bad/incompatible/etc you're up against that too.

HOWEVER, all of this is utterly moot (and this is a good example why browsing on your phone is a bad idea 🤣 - I didn't open the ebay link the first time I read this thread 😊 ): the ITX board linked in the first post does not have an Atom. It has a Celeron, which has never been based on the Atom core. I'm having trouble finding which Celeron it specifically is though (looking up the model number brings me back to this thread, and a lot of places selling the board without a lot of specifics - maybe someone else will have better luck on the Intel website) - absolute "worst-case" scenario it's Pentium M based (which still makes it faster than Atom, a lot of slower P4s, etc - that would be Celeron M 310 or 205 or M ULV 443), but it could be Core based (there are various single and dual-core Penryn, Nehalem, and Sandy Bridge chips that are all 1.2GHz). No matter which it is, they will have higher IPC than Pentium 4, Atom, and potentially Athlon64 (depending on exactly which variant it is), and performance will be pretty good (probably to the point of being a serious issue with "speed sensitive" games, just like high end P4s, A64s, Core 2s, etc can be). The auction doesn't specify what the IGP is, so it's tough to gauge if that'd be good for any gaming (or would have compatibility problems, etc etc). With a Voodoo3, assuming none of the games care about the CPU's speed, it should be a very competent (and neat) little machine - like a fast P3 or Athlon at worst (e.g. if it's a Pentium M, worst-case you're basically clock-for-clock with P3), maybe even faster at best. I think Dodge Garage has some benchmarks with a V3 paired up with an AthlonXP that you can review to get a rough idea of what kind of performance you could be looking at.

OTOH, a P3 will be pretty similar in terms of performance, and they aren't really power hogs, so it may be more practical to go that route and have an AGP slot, ISA slots, etc for expansion. It won't be ITX though. Really depends on what exactly you want/need in terms of size vs features.

ODwilly wrote:

I think it would depend on the model of Atom and P4 you are comparing. A non-ht Northwood vs a 1.67 dual core Atom would be a lot different compared to a 3.0+ ht Prescott.

The Tom's comparison has all of this, and a single-core Atom, if you're curious how it plays out. 😀

I own one of each at similar clocks, and the P4 system is overall faster. But benchmarks also support this, for example Passmark:
http://www.cpubenchmark.net/cpu_lookup. ... 40+1.60GHz (this is the Atom model I have; notice that it's fairly close to fast P3s, slow AthlonXPs, etc - fast P4s are quite a bit up the list)

Check again. The closest Pentium 4 to the 1.6GHz atom is 2.4GHz

Hardly markedly slower per clock.

The multi-core performs somewhat better in some tasks that are weighted towards multi-core/multi-thread, but in terms of single-thread performance (which is what we care about for gaming) the P4 comes out ahead. There are some cases where the P4s actually outpace the dual-core Atom as well. The big "gotcha" is that Atom's overall platform is inferior to that of P4 - things like I/O, memory bandwidth, etc are all heavily limited on the Atom, whereas the P4 can have the full benefit of dual DDR/DDR2 and PCIe x16 graphics if you like.

At 120x the power consumption. And if you are going to run DDR2 and PCI-E then why not just run Core2?

Obob, that board has a Celeron 220. Its a single core based on the early Core series.

Regarding the board/CPU from the ebay link: E26314 leads to http://www.intel.com/products/motherboard/D20 … LY2/configs.htm which specifies Celeron 220. That's a 1.2GHz CPU so that fits, Conroe so it's a (very) cut down Core 2 Duo (single core, 512KB L2).
This board (or a very similar one, also called D201GLY2) is reviewed here: http://www.tomshardware.com/reviews/Celeron-M … ni-PC,1978.html

Regarding Atom/P4: I agree that it really depends on the software and the specific CPU models.
If you want to compare some more benchmarks you can check this list: http://www.notebookcheck.net/Mobile-Processor … bit=0&daysold=0

obobskivich wrote:

With Passmark, you cannot directly compare overall scores between single and multi-core processors - Passmark heavily favors multi-core hardware (and the developers of Passmark even acknowledge this), and you will never see that "5x the speed" in a real world application as a result. If you look at the single-thread score for the Atom D510, it scores measurably lower than the 1.6GHz P4 (I know, you don't have that chip and it isn't what you used to look up Passmark, but since we're looking up synth results from a huge database, I figured I'd just "equalize" things), by around 30%. However the P4 gets a very low overall score because it cannot do the multi-core portions of Passmark (which is largely irrelevant for our purposes).

The passmark scores you linked to don't show this at all. The best P4 1.6 GHz scores on the passmark site is 194, and that is a mobile version. The normal P4 1.6 GHz only gets 131.

Your own SINGLE CORE Atom N270 gets 282. The D510 has a SINGLE CORE rating of 266. Even taking the best P4 score and the worst atom one that is a clear win for the Atom.

obobskivich wrote:

Tom's also did a more comprehensive test with multi-core Atom:
http://www.tomshardware.com/reviews/atom-d510 … top,2649-4.html

Ignoring the graphics tests because they used different GPUs, when the clock speed is taken into account the Atom 230 1.6 is faster than the P4 2.2 per clock in all but three benchmarks (AES 256, iTunes and Lame). In all other benchmarks the Atom is faster than the P4 2.2 if the clock speed is taken into account. Even without taking the clock speed into account the Atom won a few benchmarks and almost tied a couple more. The Atom is clearly faster clock for clock.

Sure a high clocked P4 is faster than an Atom at most tasks but that is not the point. The point is that the Atom has a higher IPC than the P4. At the same clock the Atom is almost always faster.

Private_Ops wrote:

Obob, that board has a Celeron 220. Its a single core based on the early Core series.

So there's no point in even discussing Atom - that's a much more efficient/capable CPU. As long as the integrated audio/video/whatever aren't problematic with whatever OS or game you need to run, and the limitation of a single expansion card is not a problem wrt the same, and it isn't "too fast," it would be a fine ITX solution to retro gaming. 😀

And I know that sounds massively contingent, but it's all worth thinking about with such a heavily integrated platform as an ITX board. You don't have much flexibility for expansion, so it has to be basically "right" out of the box.

smeezekitty wrote:

Check again. The closest Pentium 4 to the 1.6GHz atom is 2.4GHz

Hardly markedly slower per clock.

The Tom's review by itself invalidates this statement, with the 2.2GHz P4 outperforming both Atom offerings in a variety of benchmarks, and the Passmark scores support that assertion as well (and for what feels like the millionth time: you CAN NOT take the "overall" passmark score when comparing multi-core to single-core processors).

Pentium 4 1.6GHz Passmark Single-core: 344
Pentium 4 2.4GHz Passmark Single-core: 564
Atom N270 Passmark Single-core: 240
Atom D510 Passmark Single-core: 266

My original statement of 30% is based on the 1.6GHz P4 vs the Atom D510 - it's 29.3% faster, but it's easier to just round that off for the sake of conversation.

At 120x the power consumption. And if you are going to run DDR2 and PCI-E then why not just run Core2?

Atom D510 is 13W TDP. 120*13 = 1560W. 🤣 On it's absolute worst day even a Pentium 4 Extreme Edition will barely scratch at 1/10th of that. The 1.6GHz and 2.4GHz chips mentioned thus far are about half of that - 50-70W TDPs, versus the 100W+ of later Prescott models. As far as picking power efficiency goes, the Celeron on the linked board has a TDP of 19W, and that's not too far away from a P3. Just using my 1GHz CuMine as an example, it has a TDP of 29W. Performance wise I wouldn't expect them to be all that far apart for our purposes, and if you need the additional expansion (especially ISA) the P3 will make more sense. If we're only talking about games that need a Voodoo3 (or for which a Voodoo3 is overkill), the Celeron, P3, etc are much more efficient choices - their performance difference to a P4, Core 2, Core i7, etc whatever will be largely irrelevant.

If you're wanting to step up to DX8/DX9 gaming, and are worried about power efficiency, Pentium M is a fine choice versus Athlon64 or Pentium 4. A Core 2 would also work fine, and may even become required depending on how far into the future you need to go. My point in bringing up expansion options for the P4 wasn't really aiming at that though - it's more that Atom, and other integrated solutions (like the Celeron ITX linked, or the VIA ITX boards, etc) lack expansion options relative to more conventional desktop platforms, which can limit their suitability for gaming. For example in the Tom's comparison, it's no contest in 3DMark between the Pentium 4 and Atom systems, simply because the Pentium 4 systems can have a Radeon X800 installed in them, which is substantially faster than the Intel GMA. Core 2 is of course a better choice than Pentium 4, when available, and has all of the same basic advantages over a mostly integrated platform. Pentium M *can be* as good, as there are some Pentium 4 motherboards (like P4P800) that will support it, as well as motherboards designed exclusively for it (like the DFI in the TechReport article). For our purposes here, which are primarily gaming related, this is probably more pertinent than absolute power efficiency of a highly integrated ITX machine vs a conventional desktop. Of course if the ITX machine will meet all of your needs, go ahead and save the power and complexity. 😀

washu wrote:

The passmark scores you linked to don't show this at all. The best P4 1.6 GHz scores on the passmark site is 194, and that is a mobile version. The normal P4 1.6 GHz only gets 131.

Again, you cannot take the "overall" Passmark score when comparing multi-core to single-core processors or single-threaded performance, because Passmark is unevenly weighted towards multi-thread execution. Nobody is arguing that in an ideal, modern, parallelized workload the dual-core Atom is at a disadvantage to a single-core Netburst (although the Tom's article does show some situations where the P4 outperforms the dual-core Atom). But that kind of performance is largely irrelevant here - none of these chips are going to be fast enough for games that require multi-core processors, and for older games (like would run on a Voodoo3, from the original post) single-threaded performance is all that you have to worry about.

Your own SINGLE CORE Atom N270 gets 282. The D510 has a SINGLE CORE rating of 266. Even taking the best P4 score and the worst atom one that is a clear win for the Atom.

The "best" P4 score, coming from the Pentium D 965 (it's the fastest/highest-spec NetBurst - if you have another meaning for "best" please clarify) is an overall rating of 1000, and a single-thread score of 845. The D510's single thread rating is 266, and "overall" is 667. In both cases the EE 965 is consistently higher. See above for the comparison numbers for the 1.6GHz, 2.4GHz, D510, and N270. The Mobile 1.6GHz achieves a single-core rating of 392, which is better than the desktop variant (344; to save scrolling). As a side note: mobile Pentium 4s are potentially dubious to use as benchmark sources, because many laptops with P4m will end up aggressively throttling due to heat (there's a thread in System Specs that explores this somewhat). This isn't to say P4m always performs badly, just that there seems to be more potential for variation between P4m-based machines due to throttling.

I'm not seeing a "clear win" here - it instead looks like you're cherry-picking data to perpetuate an argument. And remember: none of this actually matters for this thread/discussion. The ITX board in question has a Core-based Celeron, the Celeron 220. That chip has a Passmark single-thread rating of 427, putting it well ahead of anything that's been mentioned here short of the EE 965 and 2.4GHz P4. And it's far more power efficient than either of those chips.

washu wrote:

At the same clock the Atom is almost always faster.

You've yet to actually demonstrate this. You've cited your own testing which showed a 10% slower-clocked P4 scoring 12% higher than Atom, you've cited Passmark which show consistently higher single-thread scores for similarly clocked NetBurst chips, and you've tried to compare the numbers from Tom's with some unknown weighting metric/methodology.

I will agree on removing the graphics tests for comparing CPUs, but the caveat here is that a lot of Atom platforms (like Netbooks) can't just wave their hands and "remove the graphics consideration." Instead, they're tied to some integrated solution like the GMA. This probably doesn't matter for a lot of old 2D games, as long as there aren't compatibility issues (and I have no idea how the Intel GMA does with old games, for better or for worse - I've never had a mind to try it), but I would expect it to become a problem as you move into more complex 3D titles (and the Tom's 3DMark test does show this to an extent). This is more of a consideration than a condemnation, and you can certainly find Atom boards that have expansion slots if you look for them.

obobskivich wrote:

The Tom's review by itself invalidates this statement, with the 2.2GHz P4 outperforming both Atom offerings in a variety of benc […]
Show full quote

The Tom's review by itself invalidates this statement, with the 2.2GHz P4 outperforming both Atom offerings in a variety of benchmarks, and the Passmark scores support that assertion as well (and for what feels like the millionth time: you CAN NOT take the "overall" passmark score when comparing multi-core to single-core processors).

Pentium 4 1.6GHz Passmark Single-core: 344
Pentium 4 2.4GHz Passmark Single-core: 564
Atom N270 Passmark Single-core: 240
Atom D510 Passmark Single-core: 266

Sorry but your P4 single core numbers are obviously ridiculous and are an error. If it was really 344 as you claim that puts it faster than a 1.6 GHz Athlon XP 1900 which is crazy.

The P4 1.6 has a score of 131, the 2.4 has a score of 224. The N270 has a score of 282. Are you seriously saying that just hyperthreading (the N270 is NOT dual-core) makes it get over double the score of the P4?

Edit: The slowest P4 on the chart with hyperthreading appears to be the 2.6 GHz. P4 2.6, single core with hyperthreading: 291 An Atom 1.6 N270, single core with hyperthreading: 282. The Atom is obviously faster clock for clock.