64-bit App Build Windows XP x64

Message boards : Number crunching : 64-bit App Build Windows XP x64
Message board moderation

To post messages, you must log in.

Previous · 1 · 2 · 3 · 4 · Next

AuthorMessage
Profile zoom3+1=4
Volunteer tester
Avatar

Send message
Joined: 30 Nov 03
Posts: 66336
Credit: 55,293,173
RAC: 49
United States
Message 419764 - Posted: 13 Sep 2006, 5:26:22 UTC - in response to Message 419728.  

Oops thanks, title changed. Even on my intel chip, I felt like the see2 app worked faster than sse3. I didn't really test sse4 since I was eager to try out emt64. When I have some time this week I might try a sse4 app too.

Please Note: Most of the work that went into the app over the default was already in place in Simon's source. I just made the modifications to get it to do a 64-bit compile.

--Bob Delkhoon (DeNitro)

Ok, It's working without any problems, Was this a Generic SSE2 originally?
Savoir-Faire is everywhere!
The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST

ID: 419764 · Report as offensive
EricVonDaniken

Send message
Joined: 17 Apr 04
Posts: 177
Credit: 67,881
RAC: 0
United States
Message 419810 - Posted: 13 Sep 2006, 9:46:52 UTC - in response to Message 419728.  
Last modified: 13 Sep 2006, 9:48:20 UTC

Oops thanks, title changed. Even on my intel chip, I felt like the see2 app worked faster than sse3. I didn't really test sse4 since I was eager to try out emt64. When I have some time this week I might try a sse4 app too.

On dual core AMD and Intel chips, one should compile for at least SSE3.

Intel Core2 chips have support for SSE4 in them and if you have icc and intel's MKL you should compile w/ SSE4 support.

If you are getting weird results like SSE2 being better then SSE3 or SSE3 being better than SSE4, something is wrong.
Note that to make best use of Intel's MKL may require some source changes to use functions that Intel has optimized for the Core2 architecture rather than their more generic equivalents.

Benher mentioned that the code is not taking good advantage of the all the registers available in the IA32 or x86-64 architecture. Fixing this might require non-trivial understanding of the source.

Also, it's =E=xtended =M=emory =64=b =T=echnology. EM64T.


ID: 419810 · Report as offensive
Profile BORG
Volunteer tester
Avatar

Send message
Joined: 3 Aug 99
Posts: 305
Credit: 6,157,052
RAC: 0
Canada
Message 419834 - Posted: 13 Sep 2006, 11:48:17 UTC

With the exception of the unit that was crunched partially by Chickens app and finnished by DeNitros, which finnished with a computation error the next 4 finnihesd without error. One verified and three pending as of this time.

Times show little improvement over the 32 app. But would need to pull a unit over to comparison run with both apps.


ID: 419834 · Report as offensive
Profile Sutehk
Volunteer tester
Avatar

Send message
Joined: 11 Jun 99
Posts: 42
Credit: 1,443,674
RAC: 0
United States
Message 419836 - Posted: 13 Sep 2006, 11:58:13 UTC

Downloaded and installed on a AMD X2 3800+. Seems to be running at a few hundred Mflops faster then the SSE2 app I was running earlier, at least according to boincview. Hope this helps some.
ID: 419836 · Report as offensive
Profile BORG
Volunteer tester
Avatar

Send message
Joined: 3 Aug 99
Posts: 305
Credit: 6,157,052
RAC: 0
Canada
Message 419860 - Posted: 13 Sep 2006, 13:30:07 UTC

DeNitro

I would appreciate very much the steps you took to get this client working. I've been trying for a couple months with no luck.

Maybe the Chicken can do a how to with your help.

Borg :-)
ID: 419860 · Report as offensive
Profile zoom3+1=4
Volunteer tester
Avatar

Send message
Joined: 30 Nov 03
Posts: 66336
Credit: 55,293,173
RAC: 49
United States
Message 419896 - Posted: 13 Sep 2006, 15:40:15 UTC - in response to Message 419860.  
Last modified: 13 Sep 2006, 15:41:53 UTC

DeNitro

I would appreciate very much the steps you took to get this client working. I've been trying for a couple months with no luck.

Maybe the Chicken can do a how to with your help.

Borg :-)


Borg, It's an app that You were tryin to get working, not the client. Your replaceing a 32bit app with a 64bit app and the app info file is replaced too(copied over).

Oh and It works fine here, I'll have to do some detective work to find the results that It's done of course. later.
Savoir-Faire is everywhere!
The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST

ID: 419896 · Report as offensive
Profile zoom3+1=4
Volunteer tester
Avatar

Send message
Joined: 30 Nov 03
Posts: 66336
Credit: 55,293,173
RAC: 49
United States
Message 419904 - Posted: 13 Sep 2006, 15:50:29 UTC
Last modified: 13 Sep 2006, 15:53:05 UTC

Here's the first unit crunched, there is one other unit reporting, But It was an invalid WU made by a Pentium M(1.86GHz). It still has not been validated yet, But at least It's not errored out.
http://setiathome.berkeley.edu/result.php?resultid=378760482

<stderr_txt>
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 5920 MHz

Work Unit Info
True angle range: 0.426464

Flopcounter: 16093243232437.539000

Spike count: 1
Pulse count: 0
Triplet count: 4
Gaussian count: 2
</stderr_txt>
Savoir-Faire is everywhere!
The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST

ID: 419904 · Report as offensive
Alex Kan
Volunteer developer

Send message
Joined: 4 Dec 03
Posts: 127
Credit: 29,269
RAC: 0
United States
Message 419914 - Posted: 13 Sep 2006, 16:22:07 UTC - in response to Message 419810.  

On dual core AMD and Intel chips, one should compile for at least SSE3.

Intel Core2 chips have support for SSE4 in them and if you have icc and intel's MKL you should compile w/ SSE4 support.

If you are getting weird results like SSE2 being better then SSE3 or SSE3 being better than SSE4, something is wrong.
Note that to make best use of Intel's MKL may require some source changes to use functions that Intel has optimized for the Core2 architecture rather than their more generic equivalents.

It seems a bit simplistic to assume that using SSE3 and SSE4 wherever possible will automatically be faster than not using it. For example, using HADDPS to sum across a register has greater latency and lower throughput than other combinations of instructions, especially on Core2 chips.

As for SSE4 (which I suppose I should be calling SSSE3 now), I think it's been discussed a couple times before--the only new instructions that could be useful for us are PSHUFB and PALIGNR, but only if we find places where using them is faster. If you can find a use for all those other SIMD integer instructions in a primarily floating-point application, all the more power to you.

I imagine the Intel compiler knows much more about choosing and scheduling these instructions than I do, but it's definitely interesting that the SSE2 app has performed so well.
Benher mentioned that the code is not taking good advantage of the all the registers available in the IA32 or x86-64 architecture. Fixing this might require non-trivial understanding of the source.

I think when Ben originally said this, he wasn't implying that it was a problem to be fixed. :) A lot of SETI code is simple loopy code, and there are arguments against doing a ton of loop unrolling on Core2, like a 64-byte loop buffer and the increase in code size that you've taken by moving to x86-64.

So, EricVonDaniken, have you signed up on Simon's board yet?
ID: 419914 · Report as offensive
Profile zoom3+1=4
Volunteer tester
Avatar

Send message
Joined: 30 Nov 03
Posts: 66336
Credit: 55,293,173
RAC: 49
United States
Message 419948 - Posted: 13 Sep 2006, 17:31:50 UTC

Ok I have had a few WU validate so far and none have errored out or proved invalid:

http://setiathome.berkeley.edu/result.php?resultid=378753828

<stderr_txt>
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 2368 MHz

Work Unit Info
True angle range: 0.657409

Flopcounter: 11664317036572.797000

Spike count: 1
Pulse count: 1
Triplet count: 0
Gaussian count: 0
</stderr_txt>

And here's the earliest WU:
http://setiathome.berkeley.edu/result.php?resultid=378753820

<stderr_txt>
Optimized Windows SETI@Home Enhanced application
Version info: Windows SSE2 32-bit V5.15 'Chicken Good!' (R-1.2|+fversion|xW)
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

Work Unit Info
True angle range: 0.657409
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 2368 MHz

Work Unit Info
True angle range: 0.657409
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 2368 MHz

Work Unit Info
True angle range: 0.657409
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 2368 MHz

Work Unit Info
True angle range: 0.657409
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 2368 MHz

Work Unit Info
True angle range: 0.657409

Flopcounter: 11663872942514.479000

Spike count: 2
Pulse count: 0
Triplet count: 0
Gaussian count: 0
</stderr_txt>

Note the earliest WU has more than one entry cause I did more than one benchmark as the Floating Point was at or near 4047(4046 and 4042 seen) and the Interger was around 8800 and I was used to seeing the Interger around 13000, But since Floating Point is what used here, It does pretty good. WU
Savoir-Faire is everywhere!
The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST

ID: 419948 · Report as offensive
kevint
Volunteer tester

Send message
Joined: 17 May 99
Posts: 414
Credit: 11,680,240
RAC: 0
United States
Message 420009 - Posted: 13 Sep 2006, 19:04:00 UTC - in response to Message 419904.  

Here's the first unit crunched, there is one other unit reporting, But It was an invalid WU made by a Pentium M(1.86GHz). It still has not been validated yet, But at least It's not errored out.
http://setiathome.berkeley.edu/result.php?resultid=378760482

<stderr_txt>
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 5920 MHz

Work Unit Info
True angle range: 0.426464

Flopcounter: 16093243232437.539000

Spike count: 1
Pulse count: 0
Triplet count: 4
Gaussian count: 2
</stderr_txt>



This does not look like it is being tested on the beta site - is this a production release already ? Or should it be tested on Beta fully before allowing it to be used in production ????


ID: 420009 · Report as offensive
Profile zoom3+1=4
Volunteer tester
Avatar

Send message
Joined: 30 Nov 03
Posts: 66336
Credit: 55,293,173
RAC: 49
United States
Message 420023 - Posted: 13 Sep 2006, 19:28:30 UTC - in response to Message 420009.  

Here's the first unit crunched, there is one other unit reporting, But It was an invalid WU made by a Pentium M(1.86GHz). It still has not been validated yet, But at least It's not errored out.
http://setiathome.berkeley.edu/result.php?resultid=378760482

<stderr_txt>
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 5920 MHz

Work Unit Info
True angle range: 0.426464

Flopcounter: 16093243232437.539000

Spike count: 1
Pulse count: 0
Triplet count: 4
Gaussian count: 2
</stderr_txt>



This does not look like it is being tested on the beta site - is this a production release already ? Or should it be tested on Beta fully before allowing it to be used in production ????



This is a 64bit compile of the Generic SSE2 seti app made by the Chicken, That has been recompiled into a 64bit app by Bob Delkhoon and It's making valid units and so No It should not be in Seti Beta as this is a 5.15 release, Not 5.17 or 5.18.
Savoir-Faire is everywhere!
The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST

ID: 420023 · Report as offensive
Profile KWSN - Chicken of Angnor
Volunteer developer
Volunteer tester
Avatar

Send message
Joined: 9 Jul 99
Posts: 1199
Credit: 6,615,780
RAC: 0
Austria
Message 420063 - Posted: 13 Sep 2006, 22:14:18 UTC - in response to Message 419661.  
Last modified: 13 Sep 2006, 22:39:00 UTC

Great to hear it's working, very sorry about that mix up. Again, I'm not sure what the speed difference will be. On my machine, I don't see a significant difference over Simon's (awesome) optimized app that this was based off but hopefully it's a start.

Simon, Sure I'd like to work together. There's some more I want to change in the code base to make it totally cross compatabile with 32-bit and 64-bit builds. There's also still a bit of warnings I want to check into. This was just a rought edit to get valid results and check initial performacne since I'm kinda time limited with school atm. As long as it's not any slower than the 32-bit apps, I hope it's an ok start.

Again PLEASE remember, this is just a test. Make sure you do a test run first on your platform with test work units before you try it on the actuall BOINC app!!!

Thanks,
--Bob Delkhoon (DeNitro)

Great :o)

I've given you access to the pre-release and development boards on lunatics.at, check your personal messages there for more information.

Running a benchmark (offline) of your version vs. mine currently, will let you know the results. The second build you posted now runs fine on my system.

Regards,
Simon.

<edit>
Run results indicate that your app is quicker on some WUs and the same speed on others as my 32-bit ones. Great work! All my test WUs had valid results.
</edit>
Donate to SETI@Home via PayPal!

Optimized SETI@Home apps + Information
ID: 420063 · Report as offensive
Profile Benher
Volunteer developer
Volunteer tester

Send message
Joined: 25 Jul 99
Posts: 517
Credit: 465,152
RAC: 0
United States
Message 420234 - Posted: 14 Sep 2006, 7:00:10 UTC - in response to Message 419914.  
Last modified: 14 Sep 2006, 7:00:39 UTC

Benher mentioned that the code is not taking good advantage of the all the registers available in the IA32 or x86-64 architecture. Fixing this might require non-trivial understanding of the source.

I think when Ben originally said this, he wasn't implying that it was a problem to be fixed. :) A lot of SETI code is simple loopy code, and there are arguments against doing a ton of loop unrolling on Core2, like a 64-byte loop buffer and the increase in code size that you've taken by moving to x86-64.


Hey Alex,

Can you think of a function that might benefit from 16 x 4 simd regs (in seti)? Would it keep the register pressure down somewhere? Your most complex simd seti use seems to be your chirp sse3, but compiler seemed to use only registers and not store values in temp memory when I looked at the assembly output.

=Ben
ID: 420234 · Report as offensive
Profile Sutehk
Volunteer tester
Avatar

Send message
Joined: 11 Jun 99
Posts: 42
Credit: 1,443,674
RAC: 0
United States
Message 420309 - Posted: 14 Sep 2006, 13:19:10 UTC

Thought you guys might like to know, not sure if its my comp or the app, but I have gotten a few "client errors".

stderr out is as follows:

<core_client_version>5.4.11</core_client_version>
<message>
Incorrect function. (0x1) - exit code 1 (0x1)
</message>

Check it out here: http://setiathome.berkeley.edu/result.php?resultid=379101082
ID: 420309 · Report as offensive
Pepperammi

Send message
Joined: 3 Apr 99
Posts: 200
Credit: 737,775
RAC: 0
United Kingdom
Message 420411 - Posted: 14 Sep 2006, 16:18:47 UTC - in response to Message 420309.  

Hi. Haven't been back to the SAH for a bit and know I find this :).

I've grabbed the app and have started full testing for validity and run time with Kna's nice benchmark tool. Ive used the Imagecfg tool to limit it to one core as have been doing for the other testing.

I'l just let it run and let you know how it goes.

Nice Work :D
ID: 420411 · Report as offensive
Pepperammi

Send message
Joined: 3 Apr 99
Posts: 200
Credit: 737,775
RAC: 0
United Kingdom
Message 420579 - Posted: 14 Sep 2006, 20:45:35 UTC

Heres a full copy of the full test run results. Included in the run is KWSN's sse3-1.3-p4 app and Bens test sse3-xP-ipo-ben-B as they're currently the fastest on this machine. This give somthing to compaire times to as well as the Default 5.15 app.

All results where Strongly similar.

Thank you Bob (DeNitro)

============================================================================
============
default-515.exe -nographics / testWU-1.wu :
Started at : 17:14:21
Ended at : 17:26:33
Elapsed time: 732 seconds
CPU time : 695 secs - Flops: 0 (rev: 0.00)

Stderr.txt :
Can't set up shared mem: -1
ar=0.604884 NumCfft=3005 NumGauss= 16222892 NumPulse= 3112845952 NumTriplet= 405094842368
------------
5.15-DeNitro-emt64.exe / testWU-1.wu :
Started at : 17:26:33
Ended at : 17:34:26
Elapsed time: 473 seconds
CPU time : 401 secs - Flops: 282842 (rev: 0.00)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 3209 MHz

Work Unit Info
True angle range: 0.604884

Flopcounter: 636752282842.789430

Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
------------
5.15-kwsn-sse3-p4.exe / testWU-1.wu :
Started at : 17:34:26
Ended at : 17:41:39
Elapsed time: 432 seconds
CPU time : 414 secs - Flops: 331767 (rev: 1.30)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows P4 SSE3 32-bit V5.15 'Chicken Good!' (R-1.3|+freq|xP+)
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPU real speed: 3210 MHz

Work Unit Info
True angle range: 0.604884

Flopcounter: 636752331767.789060

Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
------------
sse3-xP-ipo-ben-B.exe / testWU-1.wu :
Started at : 17:41:39
Ended at : 17:49:35
Elapsed time: 476 seconds
CPU time : 415 secs - Flops: 276161 (rev: 1.50)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows SSE3 32-bit V5.15 'Chicken Good!' (R-1.5|+freq|xP [Ben Opt])
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPUID: 'Intel PD Pentium D (Smithfield)'
cpus: 1 cores: 2 threads: 2 cache: L1=16K L2=1024K L3=0K
features: mmx sse sse2 sse3
speed: 3209 MHz

Work Unit Info
True angle range: 0.604884

Flopcounter: 636727276161

Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
------------
default-515.exe -nographics / testWU-2.wu :
Started at : 17:49:35
Ended at : 18:03:49
Elapsed time: 854 seconds
CPU time : 835 secs - Flops: 0 (rev: 0.00)

Stderr.txt :
Can't set up shared mem: -1
ar=0.443732 NumCfft=3539 NumGauss= 22080918 NumPulse= 4202890368 NumTriplet= 457641934848
------------
5.15-DeNitro-emt64.exe / testWU-2.wu :
Started at : 18:03:49
Ended at : 18:12:14
Elapsed time: 505 seconds
CPU time : 473 secs - Flops: 721325 (rev: 0.00)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 3209 MHz

Work Unit Info
True angle range: 0.443732

Flopcounter: 785466721325.214600

Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
------------
5.15-kwsn-sse3-p4.exe / testWU-2.wu :
Started at : 18:12:14
Ended at : 18:20:30
Elapsed time: 496 seconds
CPU time : 472 secs - Flops: 635430 (rev: 1.30)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows P4 SSE3 32-bit V5.15 'Chicken Good!' (R-1.3|+freq|xP+)
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPU real speed: 3210 MHz

Work Unit Info
True angle range: 0.443732

Flopcounter: 785466635430.214600

Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
------------
sse3-xP-ipo-ben-B.exe / testWU-2.wu :
Started at : 18:20:31
Ended at : 18:29:06
Elapsed time: 515 seconds
CPU time : 470 secs - Flops: 321748 (rev: 1.50)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows SSE3 32-bit V5.15 'Chicken Good!' (R-1.5|+freq|xP [Ben Opt])
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPUID: 'Intel PD Pentium D (Smithfield)'
cpus: 1 cores: 2 threads: 2 cache: L1=16K L2=1024K L3=0K
features: mmx sse sse2 sse3
speed: 3209 MHz

Work Unit Info
True angle range: 0.443732

Flopcounter: 785445321748

Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
------------
default-515.exe -nographics / testWU-3.wu :
Started at : 18:29:07
Ended at : 18:45:06
Elapsed time: 958 seconds
CPU time : 871 secs - Flops: 0 (rev: 0.00)

Stderr.txt :
Can't set up shared mem: -1
ar=0.425877 NumCfft=3631 NumGauss= 23035130 NumPulse= 4453686656 NumTriplet= 526987509760
------------
5.15-DeNitro-emt64.exe / testWU-3.wu :
Started at : 18:45:06
Ended at : 18:54:11
Elapsed time: 545 seconds
CPU time : 528 secs - Flops: 224326 (rev: 0.00)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 3209 MHz

Work Unit Info
True angle range: 0.425877

Flopcounter: 817199224326.900760

Spike count: 0
Pulse count: 0
Triplet count: 1
Gaussian count: 0
------------
5.15-kwsn-sse3-p4.exe / testWU-3.wu :
Started at : 18:54:12
Ended at : 19:03:01
Elapsed time: 529 seconds
CPU time : 473 secs - Flops: 347850 (rev: 1.30)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows P4 SSE3 32-bit V5.15 'Chicken Good!' (R-1.3|+freq|xP+)
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPU real speed: 3210 MHz

Work Unit Info
True angle range: 0.425877

Flopcounter: 817199347850.900760

Spike count: 0
Pulse count: 0
Triplet count: 1
Gaussian count: 0
------------
sse3-xP-ipo-ben-B.exe / testWU-3.wu :
Started at : 19:03:01
Ended at : 19:12:08
Elapsed time: 546 seconds
CPU time : 534 secs - Flops: 11798 (rev: 1.50)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows SSE3 32-bit V5.15 'Chicken Good!' (R-1.5|+freq|xP [Ben Opt])
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPUID: 'Intel PD Pentium D (Smithfield)'
cpus: 1 cores: 2 threads: 2 cache: L1=16K L2=1024K L3=0K
features: mmx sse sse2 sse3
speed: 3209 MHz

Work Unit Info
True angle range: 0.425877

Flopcounter: 817183011798

Spike count: 0
Pulse count: 0
Triplet count: 1
Gaussian count: 0
------------
default-515.exe -nographics / testWU-4.wu :
Started at : 19:12:08
Ended at : 19:15:41
Elapsed time: 213 seconds
CPU time : 172 secs - Flops: 0 (rev: 0.00)

Stderr.txt :
Can't set up shared mem: -1
ar=1.279649 NumCfft=1663 NumGauss= 0 NumPulse= 843636224 NumTriplet= 301563183104
------------
5.15-DeNitro-emt64.exe / testWU-4.wu :
Started at : 19:15:41
Ended at : 19:17:38
Elapsed time: 117 seconds
CPU time : 59 secs - Flops: 680427 (rev: 0.00)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 3209 MHz

Work Unit Info
True angle range: 1.279649

Flopcounter: 243253680427.522030

Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
------------
5.15-kwsn-sse3-p4.exe / testWU-4.wu :
Started at : 19:17:38
Ended at : 19:19:37
Elapsed time: 119 seconds
CPU time : 59 secs - Flops: 680437 (rev: 1.30)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows P4 SSE3 32-bit V5.15 'Chicken Good!' (R-1.3|+freq|xP+)
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPU real speed: 3210 MHz

Work Unit Info
True angle range: 1.279649

Flopcounter: 243253680437.522030

Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
------------
sse3-xP-ipo-ben-B.exe / testWU-4.wu :
Started at : 19:19:38
Ended at : 19:22:22
Elapsed time: 164 seconds
CPU time : 114 secs - Flops: 770583 (rev: 1.50)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows SSE3 32-bit V5.15 'Chicken Good!' (R-1.5|+freq|xP [Ben Opt])
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPUID: 'Intel PD Pentium D (Smithfield)'
cpus: 1 cores: 2 threads: 2 cache: L1=16K L2=1024K L3=0K
features: mmx sse sse2 sse3
speed: 3209 MHz

Work Unit Info
True angle range: 1.279649

Flopcounter: 243250770583

Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
------------
default-515.exe -nographics / testWU-5.wu :
Started at : 19:22:22
Ended at : 19:37:05
Elapsed time: 883 seconds
CPU time : 816 secs - Flops: 0 (rev: 0.00)

Stderr.txt :
Can't set up shared mem: -1
ar=0.439957 NumCfft=3557 NumGauss= 22302084 NumPulse= 4217568640 NumTriplet= 457910337536
------------
5.15-DeNitro-emt64.exe / testWU-5.wu :
Started at : 19:37:06
Ended at : 19:45:35
Elapsed time: 509 seconds
CPU time : 474 secs - Flops: 794676 (rev: 0.00)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 3209 MHz

Work Unit Info
True angle range: 0.439957

Flopcounter: 790412794676.046260

Spike count: 0
Pulse count: 0
Triplet count: 1
Gaussian count: 0
------------
5.15-kwsn-sse3-p4.exe / testWU-5.wu :
Started at : 19:45:35
Ended at : 19:53:52
Elapsed time: 497 seconds
CPU time : 475 secs - Flops: 810695 (rev: 1.30)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows P4 SSE3 32-bit V5.15 'Chicken Good!' (R-1.3|+freq|xP+)
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPU real speed: 3209 MHz

Work Unit Info
True angle range: 0.439957

Flopcounter: 790412810695.046260

Spike count: 0
Pulse count: 0
Triplet count: 1
Gaussian count: 0
------------
sse3-xP-ipo-ben-B.exe / testWU-5.wu :
Started at : 19:53:52
Ended at : 20:02:29
Elapsed time: 517 seconds
CPU time : 472 secs - Flops: 291752 (rev: 1.50)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows SSE3 32-bit V5.15 'Chicken Good!' (R-1.5|+freq|xP [Ben Opt])
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPUID: 'Intel PD Pentium D (Smithfield)'
cpus: 1 cores: 2 threads: 2 cache: L1=16K L2=1024K L3=0K
features: mmx sse sse2 sse3
speed: 3209 MHz

Work Unit Info
True angle range: 0.439957

Flopcounter: 790391291752

Spike count: 0
Pulse count: 0
Triplet count: 1
Gaussian count: 0
------------
default-515.exe -nographics / testWU-6.wu :
Started at : 20:02:30
Ended at : 20:25:59
Elapsed time: 1409 seconds
CPU time : 1350 secs - Flops: 0 (rev: 0.00)

Stderr.txt :
Can't set up shared mem: -1
ar=0.033858 NumCfft=2557 NumGauss= 0 NumPulse= 8272970368 NumTriplet= 542472847360
------------
5.15-DeNitro-emt64.exe / testWU-6.wu :
Started at : 20:25:59
Ended at : 20:35:12
Elapsed time: 553 seconds
CPU time : 531 secs - Flops: 295541 (rev: 0.00)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 3209 MHz

Work Unit Info
True angle range: 0.033858

Flopcounter: 745955295541.180420

Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
------------
5.15-kwsn-sse3-p4.exe / testWU-6.wu :
Started at : 20:35:13
Ended at : 20:44:33
Elapsed time: 560 seconds
CPU time : 535 secs - Flops: 295541 (rev: 1.30)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows P4 SSE3 32-bit V5.15 'Chicken Good!' (R-1.3|+freq|xP+)
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPU real speed: 3209 MHz

Work Unit Info
True angle range: 0.033858

Flopcounter: 745955295541.180420

Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
------------
sse3-xP-ipo-ben-B.exe / testWU-6.wu :
Started at : 20:44:33
Ended at : 20:53:05
Elapsed time: 512 seconds
CPU time : 476 secs - Flops: 397150 (rev: 1.50)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows SSE3 32-bit V5.15 'Chicken Good!' (R-1.5|+freq|xP [Ben Opt])
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPUID: 'Intel PD Pentium D (Smithfield)'
cpus: 1 cores: 2 threads: 2 cache: L1=16K L2=1024K L3=0K
features: mmx sse sse2 sse3
speed: 3209 MHz

Work Unit Info
True angle range: 0.033858

Flopcounter: 745950397150

Spike count: 0
Pulse count: 0
Triplet count: 0
Gaussian count: 0
------------
default-515.exe -nographics / testWU-7.wu :
Started at : 20:53:05
Ended at : 21:02:55
Elapsed time: 590 seconds
CPU time : 533 secs - Flops: 0 (rev: 0.00)

Stderr.txt :
Can't set up shared mem: -1
ar=0.775000 NumCfft=1169 NumGauss= 6087368 NumPulse= 1224262784 NumTriplet= 304384294912
------------
5.15-DeNitro-emt64.exe / testWU-7.wu :
Started at : 21:02:55
Ended at : 21:08:25
Elapsed time: 330 seconds
CPU time : 295 secs - Flops: 68628 (rev: 0.00)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows EMT64 64-bit V5.15 Test 1
Modified & Compiled by Bob Delkhoon (DeNitro)
Source downloaded from Simon Zadra (KWSN - Chicken of Angnor)

CPU real speed: 3209 MHz

Work Unit Info
True angle range: 0.775000

Flopcounter: 266377068628.250240

Spike count: 7
Pulse count: 5
Triplet count: 5
Gaussian count: 6
------------
5.15-kwsn-sse3-p4.exe / testWU-7.wu :
Started at : 21:08:25
Ended at : 21:13:21
Elapsed time: 296 seconds
CPU time : 238 secs - Flops: 114356 (rev: 1.30)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows P4 SSE3 32-bit V5.15 'Chicken Good!' (R-1.3|+freq|xP+)
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPU real speed: 3209 MHz

Work Unit Info
True angle range: 0.775000

Flopcounter: 266377114356.250240

Spike count: 7
Pulse count: 5
Triplet count: 5
Gaussian count: 6
------------
sse3-xP-ipo-ben-B.exe / testWU-7.wu :
Started at : 21:13:21
Ended at : 21:18:34
Elapsed time: 313 seconds
CPU time : 297 secs - Flops: 562621 (rev: 1.50)

Result : strongly similar.
Stderr.txt :
Can't set up shared mem: -1
Optimized Windows SETI@Home Enhanced application
Version info: Windows SSE3 32-bit V5.15 'Chicken Good!' (R-1.5|+freq|xP [Ben Opt])
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPUID: 'Intel PD Pentium D (Smithfield)'
cpus: 1 cores: 2 threads: 2 cache: L1=16K L2=1024K L3=0K
features: mmx sse sse2 sse3
speed: 3209 MHz

Work Unit Info
True angle range: 0.775000

Flopcounter: 266372562621

Spike count: 7
Pulse count: 5
Triplet count: 5
Gaussian count: 6
------------
CPU:
Number of CPUs 2
Specification Intel(R) Pentium(R) D CPU 3.00GHz
Code name SmithField
Instructions Sets MMX, SSE, SSE2, SSE3, EM64T
Clock Speed 2995.9 MHz
Stock frequency 3000 MHz
Clock multiplier x14.0
Front Side Bus Frequency 214.0 MHz
Bus Speed 856.0 MHz
L1 Data Cache 16 KBytes, 8-way set associative, 64 Bytes line size
L2 Cache 1024 KBytes, 8-way set associative, 64 Bytes line size
------------
Chipset:
Northbridge Intel i945P rev. A1
Southbridge Intel 82801GB (ICH7) rev. 01
------------
RAM:
Memory Type DDR2
Memory Size 3072 MBytes
Memory Frequency 285.3 MHz (3:4)
Max bandwidth PC4300 (266 MHz)
CAS# 4.0
RAS# to CAS# 4
RAS# Precharge 4
Cycle Time (tRAS) 12
------------
OS:
Windows Version Microsoft Windows XP x64 Professional Service Pack 2 (Build 3790)
============
ID: 420579 · Report as offensive
Profile zoom3+1=4
Volunteer tester
Avatar

Send message
Joined: 30 Nov 03
Posts: 66336
Credit: 55,293,173
RAC: 49
United States
Message 420665 - Posted: 14 Sep 2006, 22:56:33 UTC - in response to Message 419728.  

Oops thanks, title changed. Even on my intel chip, I felt like the see2 app worked faster than sse3. I didn't really test sse4 since I was eager to try out emt64. When I have some time this week I might try a sse4 app too.

Please Note: Most of the work that went into the app over the default was already in place in Simon's source. I just made the modifications to get it to do a 64-bit compile.

--Bob Delkhoon (DeNitro)


Ok Bob(DeNitro), I just got an error after windows update required a reboot for XP x64, Here's the error:

9/14/2006 3:46:33 PM||Starting BOINC client version 5.5.0 for windows_intelx86
9/14/2006 3:46:33 PM||libcurl/7.15.3 OpenSSL/0.9.8a zlib/1.2.3
9/14/2006 3:46:33 PM||Data directory: C:\\Program Files (x86)\\BOINC
9/14/2006 3:46:33 PM|SETI@home|Found app_info.xml; using anonymous platform
9/14/2006 3:46:33 PM||Processor: 2 AuthenticAMD Dual Core AMD Opteron(tm) Processor 270
9/14/2006 3:46:33 PM||Memory: 2.00 GB physical, 3.87 GB virtual
9/14/2006 3:46:33 PM||Disk: 74.52 GB total, 5.98 GB free
9/14/2006 3:46:33 PM|Einstein@Home|URL: http://einstein.phys.uwm.edu/; Computer ID: 732308; location: home; project prefs: default
9/14/2006 3:46:33 PM|SETI@home|URL: http://setiathome.berkeley.edu/; Computer ID: 2483868; location: home; project prefs: default
9/14/2006 3:46:33 PM||General prefs: from SETI@home (last modified 2006-09-12 13:16:38)
9/14/2006 3:46:33 PM||General prefs: no separate prefs for home; using your defaults
9/14/2006 3:46:33 PM||Local control only allowed
9/14/2006 3:46:33 PM||Listening on port 31416
9/14/2006 3:46:33 PM|SETI@home|Resuming task 13jn02aa.24708.4433.104806.3.111_0 using setiathome_enhanced version 515
9/14/2006 3:46:34 PM|SETI@home|Resuming task 08my06aa.24732.12352.653412.3.140_3 using setiathome_enhanced version 515
9/14/2006 3:46:59 PM|SETI@home|Unrecoverable error for result 08my06aa.24732.12352.653412.3.140_3 ( - exit code -1073741811 (0xc000000d))
9/14/2006 3:46:59 PM|SETI@home|Deferring scheduler requests for 1 minutes and 0 seconds
9/14/2006 3:46:59 PM||Rescheduling CPU: application exited
9/14/2006 3:46:59 PM|SETI@home|Computation for task 08my06aa.24732.12352.653412.3.140_3 finished
9/14/2006 3:46:59 PM|SETI@home|Starting task 01my06ab.15625.3984.115896.3.101_1 using setiathome_enhanced version 515
9/14/2006 3:47:01 PM|SETI@home|Started upload of file 08my06aa.24732.12352.653412.3.140_3_0
9/14/2006 3:47:02 PM|SETI@home|Unrecoverable error for result 13jn02aa.24708.4433.104806.3.111_0 ( - exit code -1073741811 (0xc000000d))
9/14/2006 3:47:02 PM|SETI@home|Deferring scheduler requests for 1 minutes and 0 seconds
9/14/2006 3:47:02 PM||Rescheduling CPU: application exited
9/14/2006 3:47:02 PM|SETI@home|Computation for task 13jn02aa.24708.4433.104806.3.111_0 finished
9/14/2006 3:47:02 PM|SETI@home|Starting task 08my06aa.24732.12352.653412.3.143_1 using setiathome_enhanced version 515
9/14/2006 3:47:03 PM|SETI@home|Finished upload of file 08my06aa.24732.12352.653412.3.140_3_0
9/14/2006 3:47:03 PM|SETI@home|Throughput 44567 bytes/sec
9/14/2006 3:47:05 PM|SETI@home|Started upload of file 13jn02aa.24708.4433.104806.3.111_0_0
9/14/2006 3:47:07 PM|SETI@home|Finished upload of file 13jn02aa.24708.4433.104806.3.111_0_0
9/14/2006 3:47:07 PM|SETI@home|Throughput 45315 bytes/sec
9/14/2006 3:48:05 PM|SETI@home|Sending scheduler request to http://setiboinc.ssl.berkeley.edu/sah_cgi/cgi
9/14/2006 3:48:05 PM|SETI@home|Reason: To report completed tasks
9/14/2006 3:48:05 PM|SETI@home|Reporting 2 tasks
9/14/2006 3:48:11 PM|SETI@home|Scheduler request succeeded


Hopefully this will be of help. :D
Savoir-Faire is everywhere!
The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST

ID: 420665 · Report as offensive
Profile zoom3+1=4
Volunteer tester
Avatar

Send message
Joined: 30 Nov 03
Posts: 66336
Credit: 55,293,173
RAC: 49
United States
Message 420675 - Posted: 14 Sep 2006, 23:02:30 UTC

And yes I've gotten a few of the other errors, So I don't think It's totally related to being 64bit as It also happens with the 32bit SSE2 Chicken app.

http://setiathome.berkeley.edu/result.php?resultid=378753838
<message>
Incorrect function. (0x1) - exit code 1 (0x1)
</message>
<stderr_txt>
Optimized Windows SETI@Home Enhanced application
Version info: Windows SSE2 32-bit V5.15 'Chicken Good!' (R-1.3|+freq|xW)
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPU real speed: 2368 MHz

Work Unit Info
True angle range: 0.426463
Optimized Windows SETI@Home Enhanced application
Version info: Windows SSE2 32-bit V5.15 'Chicken Good!' (R-1.3|+freq|xW)
Compiled by Simon Zadra (KWSN - Chicken of Angnor) - Member of the Knights who say Ni! (http://www.kwsn.net)
Download Updates at: http://www.zadra.org/seti_enhanced/

CPU real speed: 2368 MHz

Work Unit Info
True angle range: 0.426463

</stderr_txt>
Savoir-Faire is everywhere!
The T1 Trust, T1 Class 4-4-4-4 #5550, America's First HST

ID: 420675 · Report as offensive
Bob Delkhoon

Send message
Joined: 15 May 99
Posts: 11
Credit: 201,827
RAC: 0
United States
Message 420867 - Posted: 15 Sep 2006, 2:18:55 UTC

Thank you guys for the feedback. I believe I've been able to pull a little more speed out of the 64-bit app. It's hard to tell from the quicker test units how much faster it is but the results were valid. I'm going to run the client overnight to see if there's a noticable speed difference and make sure it's all ok. If it checks out I'll probably submit the code over on Simon's developer board tomorrow.

Side note: It is supposed to be "EM64T", sorry about that. Got it mixed with AMD64 =)

Thanks,
Bob Delkhoon (DeNitro)
ID: 420867 · Report as offensive
Profile BORG
Volunteer tester
Avatar

Send message
Joined: 3 Aug 99
Posts: 305
Credit: 6,157,052
RAC: 0
Canada
Message 420872 - Posted: 15 Sep 2006, 2:27:36 UTC - in response to Message 420867.  

Thank you guys for the feedback. I believe I've been able to pull a little more speed out of the 64-bit app. It's hard to tell from the quicker test units how much faster it is but the results were valid. I'm going to run the client overnight to see if there's a noticable speed difference and make sure it's all ok. If it checks out I'll probably submit the code over on Simon's developer board tomorrow.

Side note: It is supposed to be "EM64T", sorry about that. Got it mixed with AMD64 =)

Thanks,
Bob Delkhoon (DeNitro)


It runs faster on the Intel machine then on the AMD. If anything it slowed down the AMD so I removed it.

Running great on the intel machine.

Borg :-)
ID: 420872 · Report as offensive
Previous · 1 · 2 · 3 · 4 · Next

Message boards : Number crunching : 64-bit App Build Windows XP x64


 
©2024 University of California
 
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.