Intel's Pentium M Desktop Part II: ASUS' Pentium M to Pentium 4 Socket Adapter
by Anand Lal Shimpi on March 24, 2005 1:31 PM EST- Posted in
- CPUs
Before reading this article, be sure to read our first Desktop Pentium M investigation, as we will not be revisiting any of the discoveries/conclusions in that article.
At this year's Spring IDF, Derek Wilson, Johan De Gelas and I all sat across the table from Intel's Justin Rattner and asked him a question that had been on our minds ever since Prescott's introduction. The question went something like this:
Recently, Intel has shifted their focus away from ramping clock speed to increasing performance through other means such as exploiting TLP (Thread Level Parallelism). Given that Intel's direction today seems to be in sharp contrast to the direction of the NetBurst architecture and especially the direction of Prescott, were the past five years of microarchitecture improvements and innovations essentially a waste?
Rattner's exact answer encompassed a few items, but the main points were as follows:
1) At the time of Prescott's inception, clock speed is what sold, so clock speed was obviously the top priority; and they did quite well at that.
2) The past few years weren't a waste; after all, research continued in the direction of the Pentium M while all of the work on Prescott and Tejas were being done.
The second statement was particularly interesting because it was the first time that we received something tangible from Intel in regards to this question. Clearly, significant elements of future Intel desktop processors will be derived from the Pentium M architecture, but as we saw in our first desktop Pentium M investigation, the time for the Pentium M on the desktop isn't now.
As a mobile architecture, the Pentium M can't be beat. That statement alone is something many assumed that we were contradicting in our desktop Pentium M article, but the purpose of that article was to look at desktop Pentium M performance, where we determined that it fell behind. In the mobile world, without significant engineering investment, it is doubtful that the Pentium M will meet its match anytime soon.
On the desktop, we discovered that there were a handful of limitations to the Pentium M's success:
1) 855GME chipset with only a single-channel DDR333 memory controller
2) Expensive motherboards and high total cost of ownership
3) Low floating point/SSE performance
4) Severely motherboard-limited overclocking
The combination of the four items above meant a few things. While the Pentium M was an excellent contender in general use applications, its total cost of ownership was significantly higher than an Athlon 64 that performed similarly. In other applications, the Pentium M simply fell behind the competition for architectural reasons. In those cases, its high price didn't help it out at all either. The saving grace in many cases required overclocking, but the desktop Pentium M motherboards were far from overclocking monsters for those who were interested.
In the end, our stance on the Pentium M as a desktop solution was that it's more of a wait-and-see proposition. If motherboard manufacturers could produce cheaper, better equipped motherboards and if those elements improved performance, then the Pentium M would be worth another look as a desktop alternative.
We hadn't expected such a solution to come around this soon however, but it has, and not in the form that we originally thought it would. Both AOpen and DFI have indicated that they were working on updated motherboards based on the mobile 915 chipset, but that they were still months away. So when we received word that ASUS had a solution to the Pentium M desktop problem, we were caught off-guard. And rightfully so, as their solution is far from just a new chipset...
Facebook
Twitter
RSS
48 Comments
View All Comments
Spajky - Saturday, May 14, 2005 - link
Spajky - Saturday, May 7, 2005 - link
Some comments:http://www.anandtech.com/cpuchipsets/showdoc.aspx?...
>WinRAR 3.40
Pulling the hard disk out of the equation, we can get a much better idea of which processors are truly best suited for file compression<
>The WinRAR test is particularly memory bandwidth intensive, so the move to a platform that can feed the Pentium M adequately increases performance tremendously. However, even with the boost, the best that the Pentium M can do is match the performance of Intel desktop CPUs. It still can't touch the Athlon 64s<
Data compression, WinRAR 3.42, KB/s - Irrelevant CPU bench/graph !!!
It can be treated as a real life memory subsystem benchmark instead !
WinRAR´s built_in benchmark & hardware test" is NOT a Data Compression Bench :
some tests/benchmarks & explanation HOW IT WORKS, here:
http://freeweb.siol.net/jerman55/HP/benchMem.htm
Spajky - Saturday, May 7, 2005 - link
Some comments:http://www.anandtech.com/cpuchipsets/showdoc.aspx?...
>WinRAR 3.40
Pulling the hard disk out of the equation, we can get a much better idea of which processors are truly best suited for file compression<
>The WinRAR test is particularly memory bandwidth intensive, so the move to a platform that can feed the Pentium M adequately increases performance tremendously. However, even with the boost, the best that the Pentium M can do is match the performance of Intel desktop CPUs. It still can't touch the Athlon 64s<
Data compression, WinRAR 3.42, KB/s - Irrelevant CPU bench/graph !!!
It can be treated as a real life memory subsystem benchmark instead !
WinRAR´s built_in benchmark & hardware test" is NOT a Data Compression Bench :
some tests/benchmarks & explanation HOW IT WORKS, here:
http://freeweb.siol.net/jerman55/HP/benchMem.htm
Spajky - Saturday, May 7, 2005 - link
Some comments:http://www.anandtech.com/cpuchipsets/showdoc.aspx?...
>WinRAR 3.40
Pulling the hard disk out of the equation, we can get a much better idea of which processors are truly best suited for file compression<
>The WinRAR test is particularly memory bandwidth intensive, so the move to a platform that can feed the Pentium M adequately increases performance tremendously. However, even with the boost, the best that the Pentium M can do is match the performance of Intel desktop CPUs. It still can't touch the Athlon 64s<
Data compression, WinRAR 3.42, KB/s - Irrelevant CPU bench/graph !!!
It can be treated as a real life memory subsystem benchmark instead !
WinRAR´s built_in benchmark & hardware test" is NOT a Data Compression Bench :
some tests/benchmarks & explanation HOW IT WORKS, here:
http://freeweb.siol.net/jerman55/HP/benchMem.htm
Anemone - Sunday, April 17, 2005 - link
Curious how the XPS Gen2 would have faired in this battery of testing... the 915M seems to slightly better exploit the P-M from what I've been seeing, even though the XPS doesn't really focus on things other than gaming. However it would show what a performance focused chipset (and one that is meant to attempt to bring out the most in Dothan) is able to do under these same conditions. Yonah seems to be the magic juice though, but its sad that is really so far away from market. Intel would do well if they could bring Yonah faster to market, even if they had to keep speeds to the 2.2-2.4 range to do it.Quite an interesting article, and one I read carefully on every point.
ty
Calin - Tuesday, March 29, 2005 - link
An overclocked PM on top of the competition - even in a single benchmark? This chip is a big win for Intel, too bad that the big money come from the laptop world, where there is no competition. This is a guarantee for never decreasing prices for the Pentium M platformZebo - Monday, March 28, 2005 - link
Why's it so expensive? As far as overclocking, I don't see as it has value compared to A64, an already better rounded processor. You get a A64 3000 (which BTW has PCIe support) for $145 slam it to 2600Mhz pretty easy, 2900Mhz when Veince comes and it will destory any clock you can get out of PM. $145 super screamer :::slobber:::Meh. I'm not as excited as I once was about this chip. Everyone was saying how it's bandwidth staved in the 855 reveiws, turns out, yet again this was wishful thinking for the PM crowd desperate to see any light at end of intel tunnel. I notice no change in benchmarks with added BW.:|
fitten - Sunday, March 27, 2005 - link
#33, there's also the issue about how many data pins are exposed to the outside world. System memory DDR is 64-bits wide, as is the data bus external to the Pentium-M. Having dual channel (basically 128-bit wide memory) memory will help because the memory controller can read, in effect, two times the width each clock, but it still takes two transfers to get it across. The Athlon64 (S939 and S940) have 128-bit wide paths to memory and can transfer the entire width each transfer.valnar - Sunday, March 27, 2005 - link
I think many people, including Anand, are missing the point of the Pentium M. It was made to be a low powered, low heat processor. The fact it can even HANG with the big boys at their level is a remarkable achievement. (You can't say that about the VIA C3 processor.)Megahertz for megahertz, and watt for watt, it is easily the best processor on the market. You're comparing that against 3.8Ghz CPU's!! Of course it won't be first place. After all, it's just a 2.13Ghz. It uses 1/4 the power of the highest P4's. Compared against any other processor which comes close to those speed/power specs, it'll wipe the floor with them.
If Shuttle made their XPC's with this processor, I'd buy it in a heartbeat.
Rob
Slaimus - Sunday, March 27, 2005 - link
The real gem is the Celeron M Dothan. Need some benchmarks for that chip.