PrimeGrid
Please visit donation page to help the project cover running costs for this month

Toggle Menu

Join PrimeGrid

Returning Participants

Community

Leader Boards

Results

Other

drummers-lowrise
1) Message boards : Sophie Germain Prime Search : LLR 6.08/3.8.4 on MacIntel Core1 architecture still bad (Message 27902)
Posted 3203 days ago by LexsProject donor
Sorry for the late answer.
Works for me that way, thanks.
2) Message boards : Sophie Germain Prime Search : LLR 6.08/3.8.4 on MacIntel Core1 architecture still bad (Message 27629)
Posted 3211 days ago by LexsProject donor
although there is no error message anymore, all SGS units on a Intel core1 cpu (T2300) gives invalid results.
But I think it is ok to not support those old core1 cpu's, because there are not much apple's around with those ?
3) Message boards : Sophie Germain Prime Search : LLR 6.06 on MAC needs execution rights (Message 27390)
Posted 3221 days ago by LexsProject donor
Something is completely wrong: SGS doesn't work anymore on mac, and it is not just execution rights now:

See computer #65751: (which is a Core ONE DUO, without 64bit capabilities)

100000000000:T:0:2:3
8402792783805 666666
Fatal error at setup : Number sent to gwsetup is too large for the FFTs to handle.

100000000000:T:0:2:3
8402823241725 666666
Fatal error at setup : Number sent to gwsetup is too large for the FFTs to handle.


$ otool -L primegrid_llr_wrapper_6.07_i686-apple-darwin
primegrid_llr_wrapper_6.07_i686-apple-darwin:
/usr/lib/libstdc++.6.dylib (compatibility version 7.0.0, current version 7.4.0)
/usr/lib/libSystem.B.dylib (compatibility version 1.0.0, current version 88.3.11)
/usr/lib/libgcc_s.1.dylib (compatibility version 1.0.0, current version 1.0.0)


$ otool -L primegrid_llr_6.07_i686-apple-darwin
primegrid_llr_6.07_i686-apple-darwin:
/usr/lib/libSystem.B.dylib (compatibility version 1.0.0, current version 88.3.11)
/usr/lib/libstdc++.6.dylib (compatibility version 7.0.0, current version 7.9.0)
/usr/lib/libgcc_s.1.dylib (compatibility version 1.0.0, current version 1.0.0)

$ ./primegrid_llr_6.07_i686-apple-darwin -v
Primality Testing of k*b^n+/-1 Program - Version 3.8.2


The last valid result on this computer with SGS was on Oct/22 with SGS LLR version 1.05 see workunit: http://www.primegrid.com/workunit.php?wuid=135733943

4) Message boards : Sophie Germain Prime Search : LLR 6.06 on MAC needs execution rights (Message 27367)
Posted 3222 days ago by LexsProject donor
-rw-rw---- 1 boinc_master boinc_project 12430516 22 Okt 19:01 primegrid_llr_6.06_i686-apple-darwin

just do a chmod a+x on the binary and, SGP can be computed again.
5) Message boards : Project Staging Area : PRNet Discussion (Old) (Message 25417)
Posted 3303 days ago by LexsProject donor
/home/mmillerick/Desktop/prpclient-3.3.2beta-linux_64/2-dual-start-prpclient.sh: 2: pushd: not found /home/mmillerick/Desktop/prpclient-3.3.2beta-linux_64/2-dual-start-prpclient.sh: 2: popd: not found

Any clue as to what is going on here?


popd and pushd are shell-builtin commands, be sure to have bash available as your executing shell:
#!/bin/bash

6) Message boards : Project Staging Area : LLR Version 3.8.1 dev is available for testing! (Message 23766)
Posted 3385 days ago by LexsProject donor
This is great news.

As Cuda FFT is compatible to the FFTW calls, it would be easy to make a PS3 version which utilizes the SPU's.
7) Message boards : Number crunching : The Earth Day Challenge (Message 22846)
Posted 3399 days ago by LexsProject donor
YES, that was fun and some very close ones:

reported
30 Apr 2010 17:57:02 UTC
30 Apr 2010 17:59:35 UTC

:-DDD this time the server was greatly available in that last minute !
8) Message boards : Project Staging Area : Servers recommended for my PS3 (Message 22782)
Posted 3405 days ago by LexsProject donor
I realized that --fast-math causes problems, so I removed it.

I had a similar problem with -ffast-math when compiling phrot.
You could check to enable everything that -ffast-math uses, that's:

-fno-math-errno
-fno-rounding-math
-fno-signaling-nans
-fcx-limited-range
-fno-signed-zeros
-fno-trapping-math
-freciprocal-math
-ffinite-math-only

and then disabling:
-fno-associative-math

which caused the trouble for phrot on PS3.


Meanwhile I've changed the FFT to in-place-transformation, it doesn't make much sense for the FFTW version,
but the CUDA version uses the same scheme/plan, and could save memory and transfer times there.
I also started a OpenCL_FFT version, but hell this is really hard to setup.
Another interesting point would be SMP and/or multicore support within the FFT:
http://www.fftw.org/parallel/parallel-fftw.html

Something I discovered is, when using FFTW's MEASURE or PATIENT mode over ESTIMATE
the residue-calculation goes wrong(zero). Don't know why.
The bad thing is, that on Cell/PS3:
"The FFTW_ESTIMATE mode may produce seriously suboptimal plans, and it becomes particularly confused if you enable both the SPEs and Altivec. If you care about performance, please use FFTW_MEASURE or FFTW_PATIENT until we figure out a more reliable performance model."
http://fftw.org/cell/index.html

And some more times from yesterdays run on the PS3:
1076904^65536+1 is a probable composite. (RES=86b640061bf8dce8) (395325 digits) (err = 0.2500) (time = 1:38:40)
874718^131072+1 is a probable composite. (RES=80a0dd44bf881dbe) (778813 digits) (err = 0.2500) (time = 6:28:55)
710492^262144+1 is a probable composite. (RES=9c216faec7e33833) (1533952 digits) (err = 0.2500) (time = 26:01:26)
9) Message boards : Project Staging Area : Servers recommended for my PS3 (Message 22739)
Posted 3407 days ago by LexsProject donor
Only a few short benchmarks, skipping the 64K and above for now,
can't waste that much CPU time during a challenge ;-)


CUDA Emulation Mode sm_13 on a Mac mini 2006 Core Duo 1.66GHz without any NVIDIA chipset
./genefer-2.2cuda-1 genefer.work

5683936^256+1 is a probable composite. (RES=893994a255a3326f) (1730 digits) (err = 0.3750) (time = 0:03:16)
…this is so slow, someone on a faster machine and/or real NVidia card should to this benchmark...



PS3 FFTW-SPU version (using 1 PPU, 6 SPU, on Cell-Blade it should automatically use more SPU's):
./genefer-2.2-ps3 genefer.work

5683936^256+1 is a probable composite. (RES=893994a255a3326f) (1730 digits) (err = 0.2500) (time = 0:00:00)
4616790^512+1 is a probable composite. (RES=05704de8d08c2a0a) (3413 digits) (err = 0.2500) (time = 0:00:00)
3750000^1024+1 is a probable composite. (RES=0f807c291b252057) (6732 digits) (err = 0.2500) (time = 0:00:02)
3045946^2048+1 is a probable composite. (RES=bd72b5713f909aed) (13279 digits) (err = 0.2188) (time = 0:00:08)
2474076^4096+1 is a probable composite. (RES=0b53a7da1c7c9181) (26188 digits) (err = 0.2500) (time = 0:00:26)
2009574^8192+1 is a probable composite. (RES=ab752d28c1e60445) (51636 digits) (err = 0.2500) (time = 0:01:42)
1632282^16384+1 is a probable composite. (RES=eee7f094cb5f4f86) (101791 digits) (err = 0.2500) (time = 0:06:29)
1325824^32768+1 is a probable composite. (RES=7aea6cae5b1b0904) (200622 digits) (err = 0.2500) (time = 0:24:42)
With bigger FFTs PS3 should become really good for this, see http://www.fftw.org/cell/ps3/



Linux 32-bit LLVM-2.7/Clang FFTW version on a Pentium 4 2.8GHz:
./genefer-clang genefer.work

5683936^256+1 is a probable composite. (RES=893994a255a3326f) (1730 digits) (err = 0.2500) (time = 0:00:01)
4616790^512+1 is a probable composite. (RES=05704de8d08c2a0a) (3413 digits) (err = 0.2500) (time = 0:00:00)
3750000^1024+1 is a probable composite. (RES=0f807c291b252057) (6732 digits) (err = 0.3125) (time = 0:00:02)
3045946^2048+1 is a probable composite. (RES=bd72b5713f909aed) (13279 digits) (err = 0.2500) (time = 0:00:06)
2474076^4096+1 is a probable composite. (RES=0b53a7da1c7c9181) (26188 digits) (err = 0.2812) (time = 0:00:27)
2009574^8192+1 is a probable composite. (RES=ab752d28c1e60445) (51636 digits) (err = 0.2812) (time = 0:01:52)
1632282^16384+1 is a probable composite. (RES=eee7f094cb5f4f86) (101791 digits) (err = 0.3125) (time = 0:07:51)
1325824^32768+1 is a probable composite. (RES=7aea6cae5b1b0904) (200622 digits) (err = 0.2812) (time = 0:39:31)
FFTW on Pentium 4 has its highlight on 8K FFTs, see http://www.fftw.org/speed/Pentium4-2.4GHz-gcc/
the Core2 processors seem to shine up to 64K FFTs, see http://www.fftw.org/speed/CoreDuo-3.0GHz-icc/



Linux 32-bit GCC-4.4.2 x86-generic-32 version on a Pentium 4 2.8GHz:
./genefer_x86-gcc genefer.work

5683936^256+1 is a probable composite. (RES=893994a255a3326f) (1730 digits) (err = 0.2767) (time = 0:00:00)
4616790^512+1 is a probable composite. (RES=05704de8d08c2a0a) (3413 digits) (err = 0.3314) (time = 0:00:00)
3750000^1024+1 is a probable composite. (RES=0f807c291b252057) (6732 digits) (err = 0.3495) (time = 0:00:02)
3045946^2048+1 is a probable composite. (RES=bd72b5713f909aed) (13279 digits) (err = 0.3695) (time = 0:00:06)
2474076^4096+1 is a probable composite. (RES=0b53a7da1c7c9181) (26188 digits) (err = 0.3952) (time = 0:00:24)
2009574^8192+1 is a probable composite. (RES=ab752d28c1e60445) (51636 digits) (err = 0.3533) (time = 0:01:42)
1632282^16384+1 is a probable composite. (RES=eee7f094cb5f4f86) (101791 digits) (err = 0.3636) (time = 0:07:10)
1325824^32768+1 is a probable composite. (RES=7aea6cae5b1b0904) (200622 digits) (err = 0.3804) (time = 0:30:23)
the native version is faster so far, but FFTW has a lot of options for tuning and also different CPU models
show completely different speedups
10) Message boards : Project Staging Area : Servers recommended for my PS3 (Message 22717)
Posted 3407 days ago by LexsProject donor

I have a genefer-2.2 build for PS3 which also uses the 6 SPU's, but it is not very stable. Further I have a CUDA version, but only tested in CUDAEMU.
If someone has time to look into it more deeply I'll send you the sources.

It is probably my sources that you are working with. If you e-mail me we can investigate the stability issues.

Yes, its based on your sources of genefer 1.3 with its FFT routines ripped out and replaced by Syoichiro Yamada's FFTW implementation then forward-ported to the checkpointing and checks of genefer 2.2.
Since FFTW gained seemless SPU support in version 3.3.1 it now utilizes the SPU's without any change.

The CUDA version is quite similar, instead of the FFT done with FFTW it uses the CUDAFFT libs.
At least in simulation and for smaller exponents it works OK. But there sure is more work to be done for boundary checking. I'll send you both sources by PM.


Next 10 posts
[Return to PrimeGrid main page]
DNS Powered by DNSEXIT.COM
Copyright © 2005 - 2019 Rytis Slatkevičius (contact) and PrimeGrid community. Server load 1.39, 1.15, 1.10
Generated 21 Aug 2019 | 8:31:21 UTC