Yes, it won't affect which client is fastest, but in terms of what sort of performance you can expect from that particular processor, it would be nice to see how it performs under real world conditions - ie when hyperthreading 2 proceses.

But you're right - firstly we should establish which client is fastest on each processor.

When I receive cpu times with one unit running or two units running simultaneously on HT processors I will post it just as I have for my P4 Prescott 3,0 in the listing.

Anyone benchtested an Athlon XP yet?

No, not yet.

Greetings,
Speedy67

---

I'm currently testing 3 clients on my Althonxp 2200+, but they take time and should be ready before 7 pm

tony

Atlon64 3.200+ Winchester

around 1.10 with the R7 Version

P4 3.2 with HT about 1:50 for 2 WUs

Athlon XP 2.500+ on an Nforce Mobo, also the R7 Version

about 2:45

Greetings from Germany NRW
Ulli

Greetings from Germany NRW
Ulli

Hi Ulli, He's looking for Exact numbers by processor when using the "Reference WU".

thanks though

tony

Intel P4 (Northwood) 2.4GHz@3.3GHz 512KBytes L2 cache
5878s with YAOSCW-N-r8.1

---

Intel P4 2.4GHz(Northwood) 512KBytes L2 cache
Bus Speed 400MHz

YAOSCW-N-r8.1

7298.366606


YAOSCW-N-r7

7493.216787

Hi StokeyBob,

Are these times crunching 2 workunits simultaneously?

Greetings,
Speedy67

---

Hi StokeyBob,

Are these times crunching 2 workunits simultaneously?

Greetings,
Speedy67

No. I don't have hyperthreading on that processor.

---

@Speedy67

Here's the numbers from running the "Reference WU" on my:

Mobile AMD Athlon XP2200+
AMD Athlon XP-M
Thoroughbred core
mmx, 3dnow,SSE
1788.4 Mhz
Buss 265 Mhz
FSB 132.5 Mhz
L1 128
L2 256
512M ram

Listed in increasing order:

K r8.1 (22869 seconds)
K r7 (24116 seconds)
P3.zip (26717 seconds)

---

@Speedy67

Here's the numbers from running the "Reference WU" on my:

Mobile AMD Athlon XP2200+
AMD Athlon XP-M
Thoroughbred core
mmx, 3dnow,SSE
1788.4 Mhz
Buss 265 Mhz
FSB 132.5 Mhz
L1 128
L2 256
512M ram

Listed in increasing order:

K r8.1 (22869 seconds)
K r7 (24116 seconds)
P3.zip (26717 seconds)

Geez, that's way too slow. You must have something wrong there.

My Athlon XP 2100+ does about 8-9000 seconds in a 133MHz fsb board with PC133 SDRAM. You're taking nearly 3 times as long!

I know Maverick's Windows clients aren't nearly 3 times slower than my linux client.

Ned

---

*** My Guide to Compiling Optimised BOINC and SETI Clients ***
*** Download Optimised BOINC and SETI Clients for Linux Here ***

I always thought it was slow. I've run mem tests, HD tests and that's what it does. During my test I had the "Taskmanager" window open and the "Windows Explorer" window open so I could tell when the tests ended. Seti got a consistant 98% of my cpu.

[edit] the benchmarks are 956 whet and 1951 dhry


Maybe you could compare my clock speeds to yours. I got mine from CPUZ.
Any other suggestions Ned?

I always thought it was slow. I've run mem tests, HD tests and that's what it does. During my test I had the "Taskmanager" window open and the "Windows Explorer" window open so I could tell when the tests ended. Seti got a consistant 98% of my cpu.

[edit] the benchmarks are 956 whet and 1951 dhry


Maybe you could compare my clock speeds to yours. I got mine from CPUZ.
Any other suggestions Ned?

I suspect some kind of power management facility has kicked in and has throttled the speed. Perhaps you could disable the power management from the BIOS and the properties page in Windows temporarily for the benchmark.

---

@mmciastro
Is that you laptop, I have my laptop on a cooling platform $20 from Compusa.
If the cpu is running hot most laptops reduce the cpu cycles so it doesn't burn up.

---

Fred
BOINC Alpha, BOINC Beta, LHC Alpha, Einstein Alpha

Hi StokeyBob,

Are these times crunching 2 workunits simultaneously?

Greetings,
Speedy67

No. I don't have hyperthreading on that processor.

I know that, but I guess I kinda didn't think about that when I asked you that question. :)

Greetings,
Speedy67

---

I always thought it was slow. I've run mem tests, HD tests and that's what it does. During my test I had the "Taskmanager" window open and the "Windows Explorer" window open so I could tell when the tests ended. Seti got a consistant 98% of my cpu.

[edit] the benchmarks are 956 whet and 1951 dhry


Maybe you could compare my clock speeds to yours. I got mine from CPUZ.
Any other suggestions Ned?

I suspect some kind of power management facility has kicked in and has throttled the speed. Perhaps you could disable the power management from the BIOS and the properties page in Windows temporarily for the benchmark.

I agree. I just noticed it was an XP-M.

Go to power schemes and make sure it's set to Desktop/Home Office, NOT Laptop and that should stop it throttling. But keep an eye on temps as it will get hot. My laptop (XP-M 1400+) gets up to 70C in the summer crunching at 100% and runs at 50C normally when Idle. I try to keep it in a cool room and keep the temp at 65C. I find Linux easier to use as I can throttle back the CPU by 10% which keeps it just cool enough in summer, whereas windows just throttles right back to 500MHz or runs flat out at 100%.

My Athlon XP 2100+ is running stock (1730MHz [13x133]) in an old Abit KT7A (KT100a) motherboard at 133fsb with PC133 memory, and is the older Pali core. You should be looking at about 2h15mins (8000 secs) at full sped with an optimized client.

Ned

---

*** My Guide to Compiling Optimised BOINC and SETI Clients ***
*** Download Optimised BOINC and SETI Clients for Linux Here ***

FYI: once, while running benchmarks on my dual-boot P4 Prescott box, I forgot to change the HT-enable setting in BIOS. So I ran benchmarks in the wrong mode and had to re-run it with HT setting reversed.
What I found out was that running a single seti client ends up in the sime CPU time both with HT enabled and disabled (give or take a couple of seconds).

---

Metod ...

Hi StokeyBob,

Are these times crunching 2 workunits simultaneously?

Greetings,
Speedy67

No. I don't have hyperthreading on that processor.

I know that, but I guess I kinda didn't think about that when I asked you that question. :)

Greetings,
Speedy67

It is kind of confusing with all the different versions of the P4 processor. Another thing that may make my times a little peculiar is that I have a socket 478 processor in a 423 socket motherboard. I have one of those adapters a PowerLeap PL-P4/N I think. It seems to work ok. It has been running a couple of years now if I am remembering right. I also have Rambus ram which probably helps some.

The actual cycle time for work units run about the same for my 2.4GHz machine as the 3.2GHz machine except that the 3.2 does two at a time (around 1hr 40 to 1hr 50min or so).

Edit; Opps, I looked it up. The adaptor was a <a> StrattonComputer[/url] SCS-P478.

---

I always thought it was slow. I've run mem tests, HD tests and that's what it does. During my test I had the "Taskmanager" window open and the "Windows Explorer" window open so I could tell when the tests ended. Seti got a consistant 98% of my cpu.

[edit] the benchmarks are 956 whet and 1951 dhry


Maybe you could compare my clock speeds to yours. I got mine from CPUZ.
Any other suggestions Ned?

My standard XP 2200+ runs 1689 FP and 2848 Integer at 1799.6MHz with 266.6MHz FSB.

hmmmm, My bios is a Phoenix and doesn't list any power or overclocking fields. It's been elevated for quite a while (months). I changed power options from laptop to desktop, and NO change. I sent this in for repair, is it possible they replaced my bios with one that limits it's performance/heat?

Pull the battery and run it on AC. Does it improve performance?

@ mmciastro:

Download this freebie system analysis program and it should be able to tell you which Phoenix Bios version you have. In the left menu choose Motherboard > Bios. The program can also tell some other info such as Ram timings, FSB, Multiplier, etc. Hope this helps.

http://www.lavalys.com/products/overview.php?pid=1&lang=en