The 150 MHz Project, Part 2 – THG.RU

Introduction

Part one of the 150 MHz Project included some general information about the FSB, including its history and all the important coherencies. Our benchmarks were run on an Asus P3V4X motherboard, which is using the VIA Apollo Pro 133A chipset.

I can imagine that many people are curious about the performance which could be achieved on a BX motherboard at 150 MHz FSB. As a matter of fact, BX is still the undisputed king of SDRAM performance. This second part will now deal with the 150 MHz results on an ABit BE6-II motherboard. It is one of the most famous overclocker boards, since it allows setting the FSB speed MHz by MHz and the core voltage in 0.05V increments.

Apology to the Asus V6600

In the first part of this article I also mentioned 160 MHz bus speed and pointed out that my AGP card (Asus V6600, 32 MByte GeForce) hadn’t been able to run at > 80 MHz AGP clock, as the system didn’t want to start up.

One of our readers, Hanni Ghattas, told me about his Asus V6600 running stable at 88 MHz. After some additional tests I have to correct myself, finally “blaming” the VIA chipset. Graphics card, RAM and my hard disk worked for some in the ABit board running at 160 MHz FSB, proving that those components are definitely able to boot up at 40 MHz PCI (hard disc), 106 MHz AGP (graphics card) and 160 MHz FSB and memory speed (main memory). Going into detail about this 160 MHz FSB issue would lead to far however.

The Test System

Besides the motherboard, the test setup has not changed since part one of this article.

Speeding up the BX

First I ran all benchmarks at 100 MHz FSB, clocking Coppermine at 600, 650, 700, 750 and 800 MHz. As higher multipliers than x8.0 have never been specified (Intel is using x5 and x5.5 for x9 and x9.5 with their new Celerons), it wasn’t possible to clock the CPU higher when only running 100 MHz FSB. I continued with runs at 133 MHz FSB, which – although being out of the chipset’s specs – did not cause the slightest problem. The 133 MHz FSB tests were run with CPU clocks of 533, 600, 667, 733, 800, 866, 933 and 1000 MHz.

The most interesting benchmarks were run at 600, 675, 750, 825, 900 and 975 MHz, using a FSB speed of 150 MHz. I would have liked to include 1050 MHz as well, but our test sample did not want to run stable at this speed. Running a BX system at 150 MHz FSB pushes the AGP card and chipset far beyond their specifications as both are overclocked by 50%, resulting in 150 instead of 100 MHz for the BX-chipset and 100 instead of 66 MHz regarding AGP speed. I had to use a fan for the graphics card, since the Asus V6600 card became rather hot at 100 MHz AGP clock.

AGP at 100 MHz

When running a Pentium III at 100 MHz FSB, the BE6-II gives you two AGP clock choices: 2/3 FSB or 1/1 FSB. The normal setting to get 66 MHz is 2/3. Selecting 1/1 will clock the AGP at 100 MHz as well, resulting in a maximum bandwidth of 800 MByte/s instead of usual 533 MByte/s. I did not finish those test runs, because the results are pretty much the same as at 66 MHz AGP clock. WE received several mails where people held the overclocked AGP responsible for the superior performance of BX133 over i820/i840. This reasoning is illogical in the first place, since i820/i840 support AGP4x, resulting in an AGP-bandwidth that’s still higher than AGP2x overclocked to 89 or even 100 MHz. My benchmarks prove that the higher AGP-clock is hardly able to improve any scores.

3D games today are not taking much advantage of AGP-bandwidths of more than AGP2x. The improved scores in 3D games of BX133 or BX150 systems are due to the improved performance of main memory, where the reduced latency of SDRAm clocked at 133 or even 150 MHz seems to be more important than the increased bandwidth. This is the reason why RDRAM-systems don’t show the same high frame rates. RDRAM does improve bandwidth, but at the cost of latency.

SYSmark 2000 – Windows 98 SE

The test results using BAPCo’s SYSmark 2000 show the following facts:

A Pentium III 600/150 is about 8% faster than a Pentium III 600/100 and 3% faster than a 600/133.

The Giga-Coppermine is clearly the fastest processor for Windows applications, followed by two clock speeds that make use of 150 MHz FSB.

Using 150 instead of 133 MHz FSB increases system performance to the level of the next faster 133 MHz CPU. Coppermine CPUs clocked at 100 MHz FSB are clearly the losers.

Game Benchmarks: Expendable Timedemo

Expendable can benefit much more from the higher bus speed. As you can see, the fastest clock speed used in the Expendable tests is 975/150 MHz. Even at “only” 900/150 the scores are almost as high as with the Giga-PIII. Of course such CPUs are only affordable for a minority. Therefore I expect the 600/150 setting to become quite popular. Using the multiplier of x4.0, you will require a Pentium III 533EB to run it at 600/150 (Just make sure that you get a Coppermine CPU!). Running it at this clock speed you’ll get almost the same performance than when using a Pentium III 750/100 (Pentium III 750E) at a much lower price.

The same applies for the Pentium III 600/133. Running this processor at 150 MHz FSB results in 675 MHz core speed. That is almost as fast as the Pentium III 733/133. Or get a 667 to achieve the performance of a Pentium III 800E.

Game Benchmarks: Quake III Arena – Demo001

Quake III is even more clock speed sensitive. It’s incredible how a CuMine 900/150 is still slightly faster than the Gigahertz-CPU at 133 MHz FSB! Clocked at 750/150 MHz using a Common Pentium III 667 model, Quake III runs just as fast as on a Pentium III 866! Did you notice the bad performance of the Pentium III 800/100? At 150 MHz FSB, you will only need 600 MHz core clock in order to have higher frame rates.

What about Windows NT Benchmarks?

As you’ve seen, I had to do a lot of runs to collect all these results. The results of the 150 MHz Project on the VIA Apollo Pro 133A using Windows 98 do absolutely correspond to the Windows NT results. After the first runs on BX, I gave up NT benchmarking as the NT chart would only give you some higher numbers, but no different result. I hope you understand that I canceled NT this time.

What comes next?

Maybe this little piece will make some of you trying out his/her motherboard to get the system running at 150 MHz. As always, we need to inform you that we are not responsible for any damage or data loss this overclocking may cause to your system. Please be aware of the fact that sometimes it just doesn’t work!

Looking at the Quake III results we can really look forward to first systems using DDR SDRAM. As this kind of memory is able to transfer data by using both edges of the clock signal, we will see the memory performance doubling. I expect most bandwidth-intensive games to run at least two speed grades faster. This means that a Pentium III 800/133 using DDR memory could perform at least as fast as a Giga-Pentium at 133 MHz SDR. This will hopefully bring us even more performance for the same amount of money, as DDR memory is not supposed to be significantly more expensive than PC133 SDRAM.

Follow-up by reading the article ‘The 150 MHz Project, Part 3‘.