Join PrimeGrid
Returning Participants
Community
Leader Boards
Results
Other
drummers-lowrise
|
Message boards :
Generalized Fermat Prime Search :
Genefer 3.3.5 testing
| Author |
Message |
|---|
Yves Gallot Volunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
|
genefer 3.3.5 is available. You can help by testing the software on PrimeGrid.
This new version is a CPU app. The transform of genefer 3.3.4 for n <= 20 was based on the x86 extended precision format (80-bit) implemented in the Intel 8087. "x87" is still available for backward compatibility but is slow today. genefer 3.3.5 implements a new transform which is five times faster with AVX/FMA3 instructions. This transform is an Irrational Base Discrete Transform (named irrational).
Four implementations are available for x64 CPUs: FMA, AVX, SSE4 and SSE2. F64 is also available for x86 CPUs (if a processor without SSE2 is still running?). Multithreading is not supported.
Genefer 3.3.5 Linux and Windows (not Mac) is now running on dev.primegrid.com.
GFN16 through GFN 20 are installed. Feel free to test there. No app_info needed!
The preferred method is ramdom tests with app_info. The app_version that must be tested are genefer16, genefer17low, genefer17mega, genefer18, genefer19, genefer20. (with b > 200M, GFN-15 is out of range and GFN-21 and GFN-22 don't use this transform). Note that genefer 3.3.4 was not able to test genefer16 and genefer17mega on CPU then the plan_class must be OCLcudaGFN16 for the tests of these two versions with genefer 3.3.5.
If you can't use app_info, you can test a fixed list of primes: 9875290465536 + 1, 80146408131072 + 1, 11081688262144 + 1, 3638450524288 + 1 and 10590941048576 + 1.
You can test genefer_windows32.exe on Windows-64 and genefer_linux32 on Linux-64.
Binaries are available here (you can download them but clicking on the "download icon" at the top right corner of the page).
Here is the list of the configurations to test. You can reserve some, I will update the list with the reservations. Note that it's better to test sse4i on a computer without AVX extension to check compatibility, etc. But you can also set a specific transform on your computer with the option <cmdline>-x sse4i</cmdline>.
app_info.xml for Win64 is available here.
At least one of each genefer16, genefer17low, genefer17mega, genefer18, genefer19 and genefer20 tasks must be valid. Of course if any task is invalid, it must be reported. If your computer can't test genefer16 and genefer17mega, they will be tested separately.
-
genefer_windows64.exe, fmai Rafael 17Low 18 19 20 Yves Gallot 16 17Mega
-
genefer_windows64.exe, avxi Yves Gallot 16 17Low 17Mega 18 19 20
-
genefer_windows64.exe, sse4i Yves Gallot 16 17Low 17Mega robish 18 19
-
genefer_windows64.exe, sse2i robish 16 17Low 17Mega 18 19
-
genefer_windows32.exe, fmai Millerick 16 17Low 17Mega 18 19 20
-
genefer_windows32.exe, avxi Yves Gallot 16 17Low 17Mega 18 19 20
-
genefer_windows32.exe, sse4i Yves Gallot 16 17Low 17Mega 18 19
-
genefer_windows32.exe, sse2i Yves Gallot 16 17Low 17Mega 18 19
-
genefer_windows32.exe, f64i Yves Gallot 16 17Low 17Mega
-
genefer_linux64, fmai 288larsson 16 17Low 17Mega 18 19 20
-
genefer_linux64, avxi 288larsson 16 17Low 17Mega 18 19 20
-
genefer_linux64, sse4i James 16 17Low 17Mega 18 19
-
genefer_linux64, sse2i James 16 17Low 17Mega 18 19
- genefer_linux32, fmai Millerick
16 17Low 17Mega 18 19 20
-
genefer_linux32, avxi robish 16 17Low 17Mega 18 19 20
-
genefer_linux32, sse4i robish 16 17Low 17Mega 18 19
-
genefer_linux32, sse2i robish 16 17Low 17Mega 18 19
-
genefer_linux32, f64i robish 16 17Low 17Mega
- genefer_macintel64, fmai Ravi Fernando
16 17Low 17Mega 18 19 20
- genefer_macintel64, avxi Ravi Fernando
16 17Low 17Mega 18 19 20
- genefer_macintel64, sse4i Ravi Fernando
16 struckmanntransit 17Low 17Mega 18 19
-
genefer_macintel64, sse2i struckmanntransit 16 17Low 17Mega 18 19
| |
|
|
|
|
Could you include the link for reservations?
____________
My lucky number is 6219*2^3374198+1
 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
Could you include the link for reservations?
You just have to post the reservation here. I will update the first post and hide the reservation. | |
|
 RafaelVolunteer tester
Send message
Joined: 22 Oct 14
Posts: 918
ID: 370496
Credit: 612,332,770
RAC: 585,432
                         
|
|
I have an i5 8400, I should be able to do the x64 FMA tests rather quickly. | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
I have an i5 8400, I should be able to do the x64 FMA tests rather quickly.
OK, reserved "genefer_windows64.exe, fmai" | |
|
RafaelVolunteer tester
Send message
Joined: 22 Oct 14
Posts: 918
ID: 370496
Credit: 612,332,770
RAC: 585,432
|
|
Right... so I'm doing the tests now, 1 20, 2 19 and 3 18 (and I have completed a 17 Low). Can't test 16 and 17 mega on this PC.
But anyway, is 20supposed to take 6d to complete? That's what the estimate says, but I'd expect a little less on an 8th gen CPU running at 3800mhz. | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
Right... so I'm doing the tests now, 1 20, 2 19 and 3 18 (and I have completed a 17 Low). Can't test 16 and 17 mega on this PC.
Fine, I will check 16 and 17mega, that's fast.
But anyway, is 20 supposed to take 6d to complete? That's what the estimate says, but I'd expect a little less on an 8th gen CPU running at 3800mhz.
No, about 60-70 hours. The estimated time is not correct: I think that Boinc starts with the expected time for genefer 3.3.4 and the estimate decreases during the computation.
Benchmark i5-7300HQ @ 3.5GHz:
100000000^65536+1 524289 digits fmai Estimated time: 0:11:50
22000000^131072+1 962387 digits fmai Estimated time: 0:45:40
80000000^131072+1 1035874 digits fmai Estimated time: 0:49:20
12000000^262144+1 1855765 digits fmai Estimated time: 3:12:00
4000000^524288+1 3461381 digits fmai Estimated time: 15:00:00
1500000^1048576+1 6476102 digits fmai Estimated time: 66:10:00 | |
|
RafaelVolunteer tester
Send message
Joined: 22 Oct 14
Posts: 918
ID: 370496
Credit: 612,332,770
RAC: 585,432
|
No, about 60-70 hours. The estimated time is not correct: I think that Boinc starts with the expected time for genefer 3.3.4 and the estimate decreases during the computation.
Benchmark i5-7300HQ @ 3.5GHz:
This is my stderr for the task:
genefer 3.3.5.1 (CPU/Windows/64-bit/gcc-10.2.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: projects/www.primegrid.com/genefer_windows64.exe -boinc -q 1514668^1048576+1
Low priority change succeeded.
fma transform is past its b limit.
avx transform is past its b limit.
sse4 transform is past its b limit.
sse2 transform is past its b limit.
Using fmai transform
Starting initialization...
Initialization complete (3.394 seconds).
Testing 1514668^1048576+1...
Estimated time for 1514668^1048576+1 is 158:00:00
BOINC client requested that we should suspend.
BOINC client requested that we should resume.
It's been 20h already and boinc estimates 14% done. It's using the fraction done exact, so I believe that to be somewhat accurate. And honestly, I think there's something wrong, the CPU is barely hitting 54C whereas the same setup was getting to upwards of 80 on the last DIV challenge. | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
It's been 20h already and boinc estimates 14% done. It's using the fraction done exact, so I believe that to be somewhat accurate. And honestly, I think there's something wrong, the CPU is barely hitting 54C whereas the same setup was getting to upwards of 80 on the last DIV challenge.
Six tasks are running 1 GFN20 + 2 GFN19 + 3 GFN18 (?) and the L3 cache size is 9 MB.
Allocated memory sizes are GFN20: 16 MB, GFN19: 8 MB and GFN18: 4 MB. DIV is similar to GFN18.
The memory bus is the bottleneck. I personally run one "big" task (GFN20/GFN19/GFN18) and some small (GFN17/GFN16).
| |
|
RafaelVolunteer tester
Send message
Joined: 22 Oct 14
Posts: 918
ID: 370496
Credit: 612,332,770
RAC: 585,432
|
It's been 20h already and boinc estimates 14% done. It's using the fraction done exact, so I believe that to be somewhat accurate. And honestly, I think there's something wrong, the CPU is barely hitting 54C whereas the same setup was getting to upwards of 80 on the last DIV challenge.
Six tasks are running 1 GFN20 + 2 GFN19 + 3 GFN18 (?) and the L3 cache size is 9 MB.
Allocated memory sizes are GFN20: 16 MB, GFN19: 8 MB and GFN18: 4 MB. DIV is similar to GFN18.
The memory bus is the bottleneck. I personally run one "big" task (GFN20/GFN19/GFN18) and some small (GFN17/GFN16).
OH. So high N CPU GFN is functionally useless because of the way boinc handles multi project tasks and the lack of multithreading. Good to know. Makes a lot more sense now. | |
|
Crun-chiVolunteer tester
Send message
Joined: 25 Nov 09
Posts: 3250
ID: 50683
Credit: 152,648,376
RAC: 6,240
                      
|
|
Does those upper limit is limited or will be increased?
____________
92*10^1585996-1 NEAR-REPDIGIT PRIME :) :) :)
4 * 650^498101-1 CRUS PRIME
2022202116^131072+1 GENERALIZED FERMAT
Proud member of team Aggie The Pew. Go Aggie! | |
|
HonzaVolunteer moderator
Volunteer tester
Project scientist
Send message
Joined: 15 Aug 05
Posts: 1963
ID: 352
Credit: 6,426,580,351
RAC: 2,445,603
                                   
|
|
Yves, it there a reason why Linux benchmark uses different values than Windows?
Are there different b limits even if CPUs are the same?
While we are testing new version, it might be convenient to have the same benchmark for all OS platforms...if that is a possible way.
____________
My stats | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
Yves, it there a reason why Linux benchmark uses different values than Windows?
Are there different b limits even if CPUs are the same?
While we are testing new version, it might be convenient to have the same benchmark for all OS platforms...if that is a possible way.
I don't understand why Linux benchmark uses different values than Windows.
The values are different for different versions of genefer: it is updated with up-to-date PrimeGrid limits. Genefer 3.3.4 is two years old then the values of genefer 3.3.5 are different. But the values are identical for every platform (Windows-64, Windows-32, Linux-64, Linux-32 and MacOs), CPU and GPU.
If Linux benchmark uses different values than Windows, it means that the versions of genefer are different on PrimeGrid... why?
The values of genefer 3.3.5 are 200000000^32768+1, 100000000^65536+1, 22000000^131072+1, 80000000^131072+1, 12000000^262144+1, 4000000^524288+1, 1500000^1048576+1, 650000^2097152+1, 200000^4194304+1 and 920000^4194304+1. | |
|
RafaelVolunteer tester
Send message
Joined: 22 Oct 14
Posts: 918
ID: 370496
Credit: 612,332,770
RAC: 585,432
|
|
Sorry for the delay, but the tests are done. All but 1 of the tasks validated, which is reporting inconclusive.
https://www.primegrid.com/workunit.php?wuid=683771146 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
Sorry for the delay, but the tests are done. All but 1 of the tasks validated, which is reporting inconclusive. https://www.primegrid.com/workunit.php?wuid=683771146
Thanks, validited now. This is a bug of some versions of Apple OpenCL AMD Radeon driver.
Apparently Apple updated its OpenCL driver with the latest OS X and it's fixed now. | |
|
288larssonVolunteer tester
Send message
Joined: 17 Apr 10
Posts: 136
ID: 58815
Credit: 6,001,345,135
RAC: 3,137,957
                          
|
|
hi
reservation
genefer_linux64, fmai 16 17Low 17Mega 18 19 20
genefer_linux64, avxi 16 17Low 17Mega 18 19 20
fmai 16 https://www.primegrid.com/result.php?resultid=1149147597
fmai 17low https://www.primegrid.com/result.php?resultid=1149174367
fmai 17mega https://www.primegrid.com/result.php?resultid=1149160194 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
hi
reservation[...]
Thanks, I can see your two computers (i5-4670K & i7-6700K) and check outputs. | |
|
288larssonVolunteer tester
Send message
Joined: 17 Apr 10
Posts: 136
ID: 58815
Credit: 6,001,345,135
RAC: 3,137,957
|
|
Hi
genefer_linux64, avxi computer is https://www.primegrid.com/show_host_detail.php?hostid=234230 16 17Low 17Mega 18 done | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
|
genefer 3.3.5 passed the compatibility test.
Intel Atom N280 @ 1667MHz running Windows XP 32-bit:
genefer 3.3.5.1 (CPU/Windows/32-bit/gcc-7.3.0/BOINC-7.17.0)
[...]
Supported transform implementations: sse2 f64 sse2i f64i
Command line: genefer_windows32.exe -q 98679336^65536+1
[...]
Testing 98679336^65536+1...
Using sse2i transform
Starting initialization...
Initialization complete (1.417 seconds).
Estimated time for 98679336^65536+1 is 18:00:00
98679336^65536+1 is a probable prime. (523910 digits) (err = 0.1719) (time = 18:29:57) 09:50:26 | |
|
|
|
|
Hi
Been looking at this thread not really sure I understand it, does this mean in future we will be able to run Genefer tasks on CPU through the project preferences page of this website or have to download an app for it ? Also many tasks don't seem to have you have to be the first person to return the result, which is good as you can download some tasks in advance of internet outage, is that happening with this ? I have a 3990x with 16GB RAM do I need more RAM or does it use swap file I have been told about before that means it uses SSD if I dont have enough RAM ?
Finally, any chance you could add testing to project preferences page so us simpletons could get involved ? Just tick some boxes and have it help you out with tests ?
Regards
Rudi | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
Been looking at this thread not really sure I understand it, does this mean in future we will be able to run Genefer tasks on CPU through the project preferences page of this website or have to download an app for it ?
You are already able to run some of genefer tasks (17low, 18, 19, 20, 21 and 22) through the "PrimeGrid preferences" page. Today the CPU app is genefer 3.3.4 and a new version is tested here "genefer 3.3.5" which is much faster. genefer 3.3.5 is also able to test GFN-16 and GFN-17meg on CPU.
Also many tasks don't seem to have you have to be the first person to return the result, which is good as you can download some tasks in advance of internet outage, is that happening with this ?
One Work Unit is two Tasks. In any case, the two tasks (persons) are credited. If a prime is found then only the name of the first person is recorded in the T5K database.
I have a 3990x with 16GB RAM do I need more RAM or does it use swap file I have been told about before that means it uses SSD if I dont have enough RAM ?
One task is few megabytes then the RAM size is not a problem and swap file is not used.
Finally, any chance you could add testing to project preferences page so us simpletons could get involved ? Just tick some boxes and have it help you out with tests ?
New releases are rare (genefer 3.3.4 is two year old) then the testing process was not automated. I hoped that the tests would be quickly carried out but until now few people contribute and the process is slow... :-( | |
|
VatoVolunteer tester
Send message
Joined: 2 Feb 08
Posts: 863
ID: 18447
Credit: 884,218,235
RAC: 1,191,709
       
|
New releases are rare (genefer 3.3.4 is two year old) then the testing process was not automated. I hoped that the tests would be quickly carried out but until now few people contribute and the process is slow... :-(
Which is a shame.
Normally, I'd be straight on this, but app_info.xml is challenging way of doing this for most people - especially with a challenge imminent :-(
____________
 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
Normally, I'd be straight on this, but app_info.xml is challenging way of doing this for most people - especially with a challenge imminent :-(
Oh, if app_info is a problem, I will create a list of residues. I thought that app_info was better because of crediting. Now that genefer_windows64 and genefer_linux64 fma and avx are validated with app_info, the other tests can be performed with a fixed set of residues. But of course after Magellan's challenge ;-)
| |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
                 
|
|
Yves
I'll take genefer_windows64.exe, sse4i 18 19 for a start
Cheers
____________
My lucky number 10590941048576+1 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
Yves
I'll take genefer_windows64.exe, sse4i 18 19 for a start
Cheers
Reserved, thanks. | |
|
|
|
|
Cheers for the explanation and doing this, will be great doing quick 17 mega on CPU ! | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
genefer_windows64.exe, sse4i 18 on Intel(R) Core(TM) i9-9900K CPU
genefer_windows64.exe -q "4246258^262144+1" -x sse4i
genefer 3.3.5.1 (CPU/Windows/64-bit/gcc-10.2.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: genefer_windows64.exe -q 4246258^262144+1 -x sse4i
Low priority change succeeded.
Testing 4246258^262144+1...
Using sse4i transform
Starting initialization...
Initialization complete (0.499 seconds).
Estimated time for 4246258^262144+1 is 7:58:00
4246258^262144+1 is a probable prime. (1737493 digits) (err = 0.0034) (time = 7:33:57) 22:27:58
____________
My lucky number 10590941048576+1 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
4246258^262144+1 is a probable prime. (1737493 digits) (err = 0.0034) (time = 7:33:57)
Robish's GFN-18 is still prime :-)
| |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
4246258^262144+1 is a probable prime. (1737493 digits) (err = 0.0034) (time = 7:33:57)
Robish's GFN-18 is still prime :-)
:-) So is Mike's :P
genefer_windows64.exe -q "75898^524288+1" -x sse4i
genefer 3.3.5.1 (CPU/Windows/64-bit/gcc-10.2.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: genefer_windows64.exe -q 75898^524288+1 -x sse4i
Low priority change succeeded.
Testing 75898^524288+1...
Using sse4i transform
Resuming 75898^524288+1 from a checkpoint (8408722 iterations left)
Estimated time remaining for 75898^524288+1 is 23:40:00
Testing 75898^524288+1... 1559688 steps to go (4:05:56 remaining) Testing 75898^524288+1... 1559596 steps to go (4:05:55 remaining) Testing 75898^524288+1... 1559497 steps to go (4:05:55 remaining) Testing 75898^524288+1... 15593075898^524288+1 is a probable prime. (2558647 digits) (err = 0.0000) (time = 22:42:13)
____________
My lucky number 10590941048576+1 | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
I'll take genefer_windows64.exe, sse2i 16 17Low 17Mega 18 19 also.
____________
My lucky number 10590941048576+1 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
I'll take genefer_windows64.exe, sse2i 16 17Low 17Mega 18 19 also.
Thanks. If you check primes, which is complementary to the tests already performed with other tranforms, it's better to test one of the largest primes @ http://www.primegrid.com/primes/primes.php. (because rounding error is greater). | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
GFN16 to 18 sse2i
19 will take a while longer.
GFN16
genefer_windows64.exe -q "98752904^65536+1" -x sse2i
genefer 3.3.5.1 (CPU/Windows/64-bit/gcc-10.2.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: genefer_windows64.exe -q 98752904^65536+1 -x sse2i
Low priority change succeeded.
Testing 98752904^65536+1...
Using sse2i transform
Starting initialization...
Initialization complete (0.068 seconds).
Estimated time for 98752904^65536+1 is 0:41:20
98752904^65536+1 is a probable prime. (523931 digits) (err = 0.1875) (time = 0:39:46)
________________________________________________________________
GFN17Low
genefer_windows64.exe -q "21582550^131072+1" -x sse2i
genefer 3.3.5.1 (CPU/Windows/64-bit/gcc-10.2.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: genefer_windows64.exe -q 21582550^131072+1 -x sse2i
Low priority change succeeded.
Testing 21582550^131072+1...
Using sse2i transform
Starting initialization...
Initialization complete (0.222 seconds).
Estimated time for 21582550^131072+1 is 2:36:00
21582550^131072+1 is a probable prime. (961296 digits) (err = 0.0273) (time = 2:35:48)
________________________________________________________________
GFN17Mega
genefer_windows64.exe -q "80146408^131072+1" -x sse2i
genefer 3.3.5.1 (CPU/Windows/64-bit/gcc-10.2.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: genefer_windows64.exe -q 80146408^131072+1 -x sse2i
Low priority change succeeded.
Testing 80146408^131072+1...
Using sse2i transform
Starting initialization...
Initialization complete (0.204 seconds).
Estimated time for 80146408^131072+1 is 2:50:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 2:40:09)
________________________________________________________________
GFN18
genefer_windows64.exe -q "11081688^262144+1" -x sse2i
genefer 3.3.5.1 (CPU/Windows/64-bit/gcc-10.2.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: genefer_windows64.exe -q 11081688^262144+1 -x sse2i
Low priority change succeeded.
Testing 11081688^262144+1...
Using sse2i transform
Resuming 11081688^262144+1 from a checkpoint (1380298 iterations left)
Estimated time remaining for 11081688^262144+1 is 2:17:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0156) (time = 10:07:14)
____________
My lucky number 10590941048576+1 | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
GFN19 sse2i
genefer_windows64.exe -q "3638450^524288+1" -x sse2i
genefer 3.3.5.1 (CPU/Windows/64-bit/gcc-10.2.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: genefer_windows64.exe -q 3638450^524288+1 -x sse2i
Low priority change succeeded.
Testing 3638450^524288+1...
Using sse2i transform
Resuming 3638450^524288+1 from a checkpoint (1894673 iterations left)
Estimated time remaining for 3638450^524288+1 is 7:09:00
3638450^524288+1 is a probable prime. (3439810 digits) (err = 0.0039) (time = 38:11:11)
____________
My lucky number 10590941048576+1 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
GFN19 sse2i
Great! genefer_windows64 3.3.5 is validated. | |
|
JamesProject administrator
Volunteer tester
Send message
Joined: 19 Sep 14
Posts: 101
ID: 366225
Credit: 1,566,000,014
RAC: 59,284
      
|
|
It seems no one is running linux64 sse2i and sse4i. I'll take those.
Eventually, when the above is done, I'll contemplate genefer_linux32... | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
It seems no one is running linux64 sse2i and sse4i. I'll take those.
Eventually, when the above is done, I'll contemplate genefer_linux32...
Reserved, thanks. genefer_linux64 priority is higher because few people should still use Linux32... if they still exist. | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
Yves,
I'm attempting setting up a Linux32 virtual machine.
If I get it going I'll take some Linux 32bit tests.
I'll keep you informed.
Cheers
Rob.
____________
My lucky number 10590941048576+1 | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
Ok it's working
I'll reserve genefer_linux32, sse2i 16 17Low 17Mega 18 19
:)
____________
My lucky number 10590941048576+1 | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
Ha! I cloned the VM x 4, so now I can test five at a time :)
Tried ./genefer_linux32 -q "98752904^65536+1" -x fmai
Transform "fmai" not recognised. Valid transforms are: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Fatal error (1). Genefer is terminating.
Any ideas Yves?
____________
My lucky number 10590941048576+1 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
Tried ./genefer_linux32 -q "98752904^65536+1" -x fmai
Transform "fmai" not recognised. Valid transforms are: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Fatal error (1). Genefer is terminating.
Any ideas Yves?
FMA is not supported. Does the processor support FMA? What is the version of Linux32... too old for FMA support? | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
Tried ./genefer_linux32 -q "98752904^65536+1" -x fmai
Transform "fmai" not recognised. Valid transforms are: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Fatal error (1). Genefer is terminating.
Any ideas Yves?
FMA is not supported. Does the processor support FMA? What is the version of Linux32... too old for FMA support?
Probably the processor I'll check. lubuntu Version 19.04.
____________
My lucky number 10590941048576+1 | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
Might as well do them all :)
GFN16 avxi
./genefer_linux32 -q "98752904^65536+1" -x avxi
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 98752904^65536+1 -x avxi
Low priority change succeeded.
Testing 98752904^65536+1...
Using avxi transform
Starting initialization...
Initialization complete (0.134 seconds).
Estimated time for 98752904^65536+1 is 0:15:50
98752904^65536+1 is a probable prime. (523931 digits) (err = 0.1875) (time = 0:17:04) 14:13:25
____
GFN 17Low avxi
./genefer_linux32 -q "21582550^131072+1" -x avxi
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 21582550^131072+1 -x avxi
Low priority change succeeded.
Testing 21582550^131072+1...
Using avxi transform
Starting initialization...
Initialization complete (0.384 seconds).
Estimated time for 21582550^131072+1 is 1:10:00
21582550^131072+1 is a probable prime. (961296 digits) (err = 0.0273) (time = 1:02:03) 15:19:54
_________
GFN16 sse4i
./genefer_linux32 -q "98752904^65536+1" -x sse4i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 98752904^65536+1 -x sse4i
Low priority change succeeded.
Testing 98752904^65536+1...
Using sse4i transform
Starting initialization...
Initialization complete (0.147 seconds).
Estimated time for 98752904^65536+1 is 0:41:30
98752904^65536+1 is a probable prime. (523931 digits) (err = 0.1875) (time = 0:40:22) 14:41:28
_____
GFN16 sse2i
./genefer_linux32 -q "98752904^65536+1" -x sse2i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 98752904^65536+1 -x sse2i
Low priority change succeeded.
Testing 98752904^65536+1...
Using sse2i transform
Resuming 98752904^65536+1 from a checkpoint (1064912 iterations left)
Estimated time remaining for 98752904^65536+1 is 0:35:40
Testing 98752904^65536+1... 1046520 steps to go (0:28:28 remaining)
98752904^65536+1 is a probable prime. (523931 digits) (err = 0.1875) (time = 0:44:19) 14:19:46
_____
GFN16 f64i
./genefer_linux32 -q "98752904^65536+1" -x f64i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 98752904^65536+1 -x f64i
Low priority change succeeded.
Testing 98752904^65536+1...
Using f64i transform
Starting initialization...
Initialization complete (0.146 seconds).
Estimated time for 98752904^65536+1 is 1:17:00
98752904^65536+1 is a probable prime. (523931 digits) (err = 0.1875) (time = 1:16:12) 15:15:54
____________
My lucky number 10590941048576+1 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
Might as well do them all :)
Thanks! What is your processor? GFN-19 with sse2i and sse4i are slow and GFN-17Mega with f64i quite tedious but it has to be done... even if a processor without sse2 should be very old.
| |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
Might as well do them all :)
Thanks! What is your processor? GFN-19 with sse2i and sse4i are slow and GFN-17Mega with f64i quite tedious but it has to be done... even if a processor without sse2 should be very old.
Intel(R) Core(TM) i9-9900K CPU @ 3.60GHz
I have the boost turned off as the CPU gets too hot.
./genefer_linux32 -q "80146408^131072+1" -x avxi
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 80146408^131072+1 -x avxi
Low priority change succeeded.
Testing 80146408^131072+1...
Using avxi transform
Starting initialization...
Initialization complete (0.380 seconds).
Estimated time for 80146408^131072+1 is 1:10:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 1:13:14) 16:43:41
____________
My lucky number 10590941048576+1 | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
./genefer_linux32 -q "21582550^131072+1" -x sse2i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 21582550^131072+1 -x sse2i
Low priority change succeeded.
Testing 21582550^131072+1...
Using sse2i transform
Starting initialization...
Initialization complete (0.387 seconds).
Estimated time for 21582550^131072+1 is 2:52:00
Testing 21582550^131072+1... 1860296 steps to go (1:47:53 remaining)
21582550^131072+1 is a probable prime. (961296 digits) (err = 0.0273) (time = 2:59:37) 18:33:20
______
./genefer_linux32 -q "21582550^131072+1" -x sse4i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 21582550^131072+1 -x sse4i
Low priority change succeeded.
Testing 21582550^131072+1...
Using sse4i transform
Starting initialization...
Initialization complete (0.416 seconds).
Estimated time for 21582550^131072+1 is 2:49:00
21582550^131072+1 is a probable prime. (961296 digits) (err = 0.0273) (time = 2:43:38) 18:19:15
___
____________
My lucky number 10590941048576+1 | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
./genefer_linux32 -q "11081688^262144+1" -x avxi
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 11081688^262144+1 -x avxi
Low priority change succeeded.
Testing 11081688^262144+1...
Using avxi transform
Starting initialization...
Initialization complete (0.919 seconds).
Estimated time for 11081688^262144+1 is 5:06:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0156) (time = 4:34:16) 21:19:43
____________
My lucky number 10590941048576+1 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
|
Thanks Rob, table was updated.
I still don't know why FMA is not supported on your Linux32 virtual machine... it was set for another processor?
There is a ticket FMA and BMI extensions are not supported on VirtualBox. It's 3 years old but it's not indicated that it was fixed. | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
./genefer_linux32 -q "80146408^131072+1" -x sse4i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 80146408^131072+1 -x sse4i
Low priority change succeeded.
Testing 80146408^131072+1...
Using sse4i transform
Starting initialization...
Initialization complete (0.386 seconds).
Estimated time for 80146408^131072+1 is 3:02:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 2:54:21) 21:43:26
___
./genefer_linux32 -q "80146408^131072+1" -x sse2i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 80146408^131072+1 -x sse2i
Low priority change succeeded.
Testing 80146408^131072+1...
Using sse2i transform
Starting initialization...
Initialization complete (0.402 seconds).
Estimated time for 80146408^131072+1 is 3:16:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 3:11:12) 21:54:12
___
./genefer_linux32 -q "11081688^262144+1" -x avxi
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 11081688^262144+1 -x avxi
Low priority change succeeded.
Testing 11081688^262144+1...
Using avxi transform
Starting initialization...
Initialization complete (0.919 seconds).
Estimated time for 11081688^262144+1 is 5:06:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0156) (time = 4:34:16) 21:19:43
____________
My lucky number 10590941048576+1 | |
|
|
|
|
win32 fmai gfn16
I'll try to do more tomorrow
$ ./genefer_windows32.exe -x fmai -q "98752904^65536+1"
genefer 3.3.5.1 (CPU/Windows/32-bit/gcc-7.3.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 f64 fmai avxi sse4i sse2i f64i
Command line: C:\Users\Millerick\Downloads\genefer_windows32.exe -x fmai -q 98752904^65536+1
Low priority change succeeded.
Testing 98752904^65536+1...
Using fmai transform
Starting initialization...
Initialization complete (0.113 seconds).
Estimated time for 98752904^65536+1 is 0:12:30
98752904^65536+1 is a probable prime. (523931 digits) (err = 0.1562) (time = 0:12:43) 22:02:27
____________
 | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
./genefer_linux32 -q "11081688^262144+1" -x sse2i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 11081688^262144+1 -x sse2i
Low priority change succeeded.
Testing 11081688^262144+1...
Using sse2i transform
Resuming 11081688^262144+1 from a checkpoint (2414944 iterations left)
Estimated time remaining for 11081688^262144+1 is 4:11:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0156) (time = 13:52:36) 15:43:44
____________
My lucky number 10590941048576+1 | |
|
Michael GoetzVolunteer moderator
Project administrator
Send message
Joined: 21 Jan 10
Posts: 14045
ID: 53948
Credit: 485,590,703
RAC: 673,563
            
|
|
ANNOUNCEMENT
Genefer 3.3.5 Is now running on dev.primegrid.com. So far, only Linux and Windows are installed. (Mac isn't because... Mac)
GFN16 through GFN 20 are installed.
Feel free to test there. No app_info needed!
____________
My lucky number is 75898524288+1 | |
|
|
|
|
linux32 fmai gfn16
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 f64 fmai avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -x fmai -q 98752904^65536+1
Low priority change succeeded.
Testing 98752904^65536+1...
Using fmai transform
Starting initialization...
Initialization complete (0.130 seconds).
Estimated time for 98752904^65536+1 is 0:17:10
98752904^65536+1 is a probable prime. (523931 digits) (err = 0.1562) (time = 0:17:25) 17:02:35
linux32 fmai gfn17low
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 f64 fmai avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -x fmai -q 21582550^131072+1
Low priority change succeeded.
Testing 21582550^131072+1...
Using fmai transform
Starting initialization...
Initialization complete (0.384 seconds).
Estimated time for 21582550^131072+1 is 1:09:00
21582550^131072+1 is a probable prime. (961296 digits) (err = 0.0234) (time = 1:09:09) 18:04:35
linux32 fmai gfn17mega
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 f64 fmai avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -x fmai -q 80146408^131072+1
Low priority change succeeded.
Testing 80146408^131072+1...
Using fmai transform
Starting initialization...
Initialization complete (0.379 seconds).
Estimated time for 80146408^131072+1 is 1:16:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 1:13:58) 18:35:41
linux32 fmai gfn18
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 f64 fmai avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -x fmai -q 11081688^262144+1
Low priority change succeeded.
Testing 11081688^262144+1...
Using fmai transform
Starting initialization...
Initialization complete (0.924 seconds).
Estimated time for 11081688^262144+1 is 4:45:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0137) (time = 4:52:26) 21:48:49
____________
| |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
linux32 fmai gfn16
linux32 fmai gfn17low
linux32 fmai gfn17mega
linux32 fmai gfn18
Thanks, table updated. | |
|
|
|
|
I checked and the gfn19 and gfn20 checks for linux32 fmai are going to be too long to complete on the ephemeral linux servers I can use. Someone else should take those. I'll continue working through the win32 fmai tests.
____________
| |
|
|
|
|
win32 fmai gfn17low
genefer 3.3.5.1 (CPU/Windows/32-bit/gcc-7.3.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 f64 fmai avxi sse4i sse2i f64i
Command line: C:\Users\Millerick\Downloads\genefer\17low\genefer_windows32.exe -x fmai -q 21582550^131072+1
Low priority change succeeded.
Testing 21582550^131072+1...
Using fmai transform
Starting initialization...
Initialization complete (0.320 seconds).
Estimated time for 21582550^131072+1 is 0:48:40
21582550^131072+1 is a probable prime. (961296 digits) (err = 0.0234) (time = 1:05:07) 19:43:55
win32 fmai gfn17mega
genefer 3.3.5.1 (CPU/Windows/32-bit/gcc-7.3.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 f64 fmai avxi sse4i sse2i f64i
Command line: C:\Users\Millerick\Downloads\genefer\17mega\genefer_windows32.exe -x fmai -q 80146408^131072+1
Low priority change succeeded.
Testing 80146408^131072+1...
Using fmai transform
Starting initialization...
Initialization complete (0.618 seconds).
Estimated time for 80146408^131072+1 is 1:18:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 1:14:01) 21:12:00
win32 fmai gfn18
genefer 3.3.5.1 (CPU/Windows/32-bit/gcc-7.3.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 f64 fmai avxi sse4i sse2i f64i
Command line: C:\Users\Millerick\Downloads\genefer\18\genefer_windows32.exe -x fmai -q 11081688^262144+1
Low priority change succeeded.
Testing 11081688^262144+1...
Using fmai transform
Starting initialization...
Initialization complete (0.790 seconds).
Estimated time for 11081688^262144+1 is 4:52:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0137) (time = 4:44:20) 23:23:41
win32 fmai gfn19 and win32 fmai gfn20 will come in a few days
____________
| |
|
Crun-chiVolunteer tester
Send message
Joined: 25 Nov 09
Posts: 3250
ID: 50683
Credit: 152,648,376
RAC: 6,240
|
|
I have to report "cosmetic" bug
Intel I5 -9600K
When I do calculating upper limit with fmai option then program start and stop at first calculation.
1. run Generalized Fermat Prime Search benchmarks
2. run specific benchmarks
3. run primality tests
4. run residue tests
5. compute approximate upper limits
6. test probable primality (fast)
7. test primality (slow)
8. compute Selfridge-Hurwitz residue (Fermat number)
5
The following transform types are available:
fma avx sse4 sse2 fmai avxi sse4i sse2i
Which transform?
fmai
Generalized Fermat Number b limits for transform implementation "fmai"
Checking limit for N = 1024. Testing b = 1638400000
But when I do real job, calculating is going without any problem
C:\Users\I5-ALPHA>Desktop\g.exe -q "31415678^131072+1"
genefer 3.3.5.1 (CPU/Windows/64-bit/gcc-10.2.0/BOINC-7.17.0)
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: Desktop\g.exe -q 31415678^131072+1
Low priority change succeeded.
fma transform is past its b limit.
avx transform is past its b limit.
sse4 transform is past its b limit.
sse2 transform is past its b limit.
Testing 31415678^131072+1...
Using fmai transform
Starting initialization...
Initialization complete (0.175 seconds).
Estimated time for 31415678^131072+1 is 0:42:30
Testing 31415678^131072+1... 2913930 steps to go (0:38:49 remaining)
____________
92*10^1585996-1 NEAR-REPDIGIT PRIME :) :) :)
4 * 650^498101-1 CRUS PRIME
2022202116^131072+1 GENERALIZED FERMAT
Proud member of team Aggie The Pew. Go Aggie! | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
I have to report "cosmetic" bug
It will have to be fixed but this function is not used with Boinc.
We have:
Generalized Fermat Number b limits for transform implementation "fmai"
N = 131072, maxErr(b = 153.18M) = 0.3438, maxErr(b = 153.19M) = 0.3750, maxErr(b = 180.97M) = 0.4375, maxErr(b = 180.98M) = 0.5000
But this function is not accurate: because of rare errors, the computation of the real limit requires the full test of many GFN-17. But we can expect that the limit is about 150M.
With GFN17-mega (80M): error ~ 0.2. | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
win32 fmai gfn17low
win32 fmai gfn17mega
win32 fmai gfn18
win32 fmai gfn19 and win32 fmai gfn20 will come in a few days
Thanks! I'm completing avxi gfn20 and sse4i gfn18 gfn19 and win32 will be validated. | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
./genefer_linux32 -q "3638450^524288+1" -x avxi
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 3638450^524288+1 -x avxi
Low priority change succeeded.
Testing 3638450^524288+1...
Using avxi transform
Resuming 3638450^524288+1 from a checkpoint (3903530 iterations left)
Estimated time remaining for 3638450^524288+1 is 6:16:00
3638450^524288+1 is a probable prime. (3439810 digits) (err = 0.0039) (time = 27:24:19) 03:53:37
___
./genefer_linux32 -q "21582550^131072+1" -x f64i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 21582550^131072+1 -x f64i
Low priority change succeeded.
Testing 21582550^131072+1...
Using f64i transform
Resuming 21582550^131072+1 from a checkpoint (3179181 iterations left)
Estimated time remaining for 21582550^131072+1 is 5:10:00
21582550^131072+1 is a probable prime. (961296 digits) (err = 0.0234) (time = 9:04:59) 01:48:11
____________
My lucky number 10590941048576+1 | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
./genefer_linux32 -q "80146408^131072+1" -x f64i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 80146408^131072+1 -x f64i
Low priority change succeeded.
Testing 80146408^131072+1...
Using f64i transform
Resuming 80146408^131072+1 from a checkpoint (386619 iterations left)
Estimated time remaining for 80146408^131072+1 is 0:40:40
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 8:22:15) 16:36:24
____________
My lucky number 10590941048576+1 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
./genefer_linux32 -q "80146408^131072+1" -x f64i
The slowest transform (32-bit x87 code) is validated!
The most boring test is finished :) | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
./genefer_linux32 -q "80146408^131072+1" -x f64i
The slowest transform (32-bit x87 code) is validated!
The most boring test is finished :)
Phew :D
____________
My lucky number 10590941048576+1 | |
|
|
|
|
win32 fmai gfn19
genefer 3.3.5.1 (CPU/Windows/32-bit/gcc-7.3.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 f64 fmai avxi sse4i sse2i f64i
Command line: C:\Users\Millerick\Downloads\genefer\19\genefer_windows32.exe -x fmai -q 3638450^524288+1
Low priority change succeeded.
Testing 3638450^524288+1...
Using fmai transform
Starting initialization...
Initialization complete (3.428 seconds).
Estimated time for 3638450^524288+1 is 23:50:00
3638450^524288+1 is a probable prime. (3439810 digits) (err = 0.0037) (time = 23:17:11) 21:09:59
The win32 fmai gfn20 will finish in three more days.
____________
| |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
./genefer_linux32 -q "3638450^524288+1" -x sse4i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 3638450^524288+1 -x sse4i
Low priority change succeeded.
Testing 3638450^524288+1...
Using sse4i transform
Resuming 3638450^524288+1 from a checkpoint (3814335 iterations left)
Estimated time remaining for 3638450^524288+1 is 15:50:00
3638450^524288+1 is a probable prime. (3439810 digits) (err = 0.0039) (time = 51:59:26) 05:49:36
__
./genefer_linux32 -q "11081688^262144+1" -x sse4i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 11081688^262144+1 -x sse4i
Low priority change succeeded.
Testing 11081688^262144+1...
Using sse4i transform
Resuming 11081688^262144+1 from a checkpoint (3343247 iterations left)
Estimated time remaining for 11081688^262144+1 is 6:04:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0156) (time = 13:22:07) 21:41:40
__
./genefer_linux32 -q "3638450^524288+1" -x sse2i
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 3638450^524288+1 -x sse2i
Low priority change succeeded.
Testing 3638450^524288+1...
Using sse2i transform
Resuming 3638450^524288+1 from a checkpoint (4393048 iterations left)
Estimated time remaining for 3638450^524288+1 is 17:20:00
3638450^524288+1 is a probable prime. (3439810 digits) (err = 0.0039) (time = 55:14:38) 09:07:26
____________
My lucky number 10590941048576+1 | |
|
JamesProject administrator
Volunteer tester
Send message
Joined: 19 Sep 14
Posts: 101
ID: 366225
Credit: 1,566,000,014
RAC: 59,284
|
|
linux64 sse4i. These took longer than I expected; sse2i tests will be done soon
root@thisisapi:~/genefer-3_3_5-test# ./gfn3.3.5 -q "98752904^65536+1" -x sse4i
genefer 3.3.5.1 (CPU/Linux/64-bit/gcc-7.5.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 avxi sse4i sse2i
Command line: ./gfn3.3.5 -q 98752904^65536+1 -x sse4i
Low priority change succeeded.
Testing 98752904^65536+1...
Using sse4i transform
Starting initialization...
Initialization complete (0.144 seconds).
Estimated time for 98752904^65536+1 is 0:47:30
98752904^65536+1 is a probable prime. (523931 digits) (err = 0.1875) (time = 0:46:21) 12:24:06
root@thisisapi:~/genefer-3_3_5-test# ./gfn3.3.5 tests -x sse4i
genefer 3.3.5.1 (CPU/Linux/64-bit/gcc-7.5.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 avxi sse4i sse2i
Command line: ./gfn3.3.5 tests -x sse4i
Low priority change succeeded.
Start test of file 'tests' - 14:09:05
Testing 80146408^131072+1...
Using sse4i transform
Starting initialization...
Initialization complete (0.319 seconds).
Estimated time for 80146408^131072+1 is 3:15:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 3:17:10) 17:26:15
Testing 11081688^262144+1...
Using sse4i transform
Starting initialization...
Initialization complete (0.790 seconds).
Estimated time for 11081688^262144+1 is 12:00:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0156) (time = 12:16:19) 05:42:34
Testing 3638450^524288+1...
Using sse4i transform
Starting initialization...
Initialization complete (2.538 seconds).
Estimated time for 3638450^524288+1 is 47:10:00
3638450^524288+1 is a probable prime. (3439810 digits) (err = 0.0039) (time = 53:54:45) 11:37:19
Test of file 'tests' completed - 11:37:19
| |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
linux64 sse4i. These took longer than I expected; sse2i tests will be done soon
Thanks. x4 at each step... tests in reversed order are more satisfying and hopefully DYFL doesn't have to be validated ;-)
| |
|
JamesProject administrator
Volunteer tester
Send message
Joined: 19 Sep 14
Posts: 101
ID: 366225
Credit: 1,566,000,014
RAC: 59,284
|
sse2i tests will be done soon
I take this back. Something in the kitchen tripped the RCD and the machine I was running the tests on was not on an UPS.
EDIT: ah genefer checkpoints. The tests will be done soon :) | |
|
robishVolunteer moderator
Volunteer tester
Send message
Joined: 7 Jan 12
Posts: 2223
ID: 126266
Credit: 7,990,315,060
RAC: 5,325,758
|
|
./genefer_linux32 -q "1059094^1048576+1" -x avxi
genefer 3.3.5.1 (CPU/Linux/32-bit/gcc-5.4.0 20160609/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: avx sse4 sse2 f64 avxi sse4i sse2i f64i
Command line: ./genefer_linux32 -q 1059094^1048576+1 -x avxi
Low priority change succeeded.
Testing 1059094^1048576+1...
Using avxi transform
Resuming 1059094^1048576+1 from a checkpoint (12867889 iterations left)
Estimated time remaining for 1059094^1048576+1 is 48:00:00
1059094^1048576+1 is a probable prime. (6317602 digits) (err = 0.0010) (time = 83:52:20) 10:14:26
____________
My lucky number 10590941048576+1 | |
|
JamesProject administrator
Volunteer tester
Send message
Joined: 19 Sep 14
Posts: 101
ID: 366225
Credit: 1,566,000,014
RAC: 59,284
|
|
linux64 SSE2i
I think the times are wrong for 3638450^524288+1 (maybe because it was unexpectedly terminated?)
The result seems fine.
3638450^524288+1
daohe@daohe-XPS-15-9570:~/Documents/genefer335test/s3$ ../gfn3.3.5 -q "3638450^524288+1" -x sse2i
genefer 3.3.5.1 (CPU/Linux/64-bit/gcc-7.5.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: ../gfn3.3.5 -q 3638450^524288+1 -x sse2i
Low priority change succeeded.
Testing 3638450^524288+1...
Using sse2i transform
Resuming 3638450^524288+1 from a checkpoint (1840338 iterations left)
Estimated time remaining for 3638450^524288+1 is 5:02:00
3638450^524288+1 is a probable prime. (3439810 digits) (err = 0.0039) (time = 28:36:32) 20:46:04
11081688^262144+1
daohe@daohe-XPS-15-9570:~/Documents/genefer335test/s2$ ../gfn3.3.5 -q "11081688^262144+1" -x sse2i
genefer 3.3.5.1 (CPU/Linux/64-bit/gcc-7.5.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: ../gfn3.3.5 -q 11081688^262144+1 -x sse2i
Low priority change succeeded.
Testing 11081688^262144+1...
Using sse2i transform
Starting initialization...
Initialization complete (0.565 seconds).
Estimated time for 11081688^262144+1 is 11:20:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0156) (time = 12:47:47) 04:56:53
80146408^131072+1
daohe@daohe-XPS-15-9570:~/Documents/genefer335test/s1$ ../gfn3.3.5 -q "80146408^131072+1" -x sse2i
genefer 3.3.5.1 (CPU/Linux/64-bit/gcc-7.5.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: ../gfn3.3.5 -q 80146408^131072+1 -x sse2i
Low priority change succeeded.
Testing 80146408^131072+1...
Using sse2i transform
Starting initialization...
Initialization complete (0.211 seconds).
Estimated time for 80146408^131072+1 is 2:49:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 3:50:20) 19:58:59
98752904^65536+1
daohe@daohe-XPS-15-9570:~/Documents/genefer335test/s0$ ../gfn3.3.5 -q "98752904^65536+1" -x sse2i
genefer 3.3.5.1 (CPU/Linux/64-bit/gcc-7.5.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 fmai avxi sse4i sse2i
Command line: ../gfn3.3.5 -q 98752904^65536+1 -x sse2i
Low priority change succeeded.
Testing 98752904^65536+1...
Using sse2i transform
Starting initialization...
Initialization complete (0.057 seconds).
Estimated time for 98752904^65536+1 is 0:37:20
98752904^65536+1 is a probable prime. (523931 digits) (err = 0.1875) (time = 0:57:28) 17:05:26
| |
|
Michael GoetzVolunteer moderator
Project administrator
Send message
Joined: 21 Jan 10
Posts: 14045
ID: 53948
Credit: 485,590,703
RAC: 673,563
|
|
** ANNOUNCEMENT **
Thank you all for your help in testing this new version of Genefer.
I just installed the new Windows and Linux (but not Mac) CPU versions for the following GFN projects:
GFN-16 Yes, you can run GFN16 on CPUs again!
GFN-17-LOW
GFN-17-MEGA Yes, you can run GFN-17-MEGA on CPUs again!
GFN-18
GFN-19
GFN-20
Genefer 3.3.5 provides substantial speed boosts for CPU on those projects.
GFN-21 has not been updated because it's still capable of running the FP64 transforms, which are the fastest. At least for a little while longer.
I have removed the CPU GFN-22 app. It was a mistake.
We still need to test the Mac version of the app.
____________
My lucky number is 75898524288+1 | |
|
Ravi FernandoProject administrator
Volunteer tester
Project scientist
Send message
Joined: 21 Mar 19
Posts: 211
ID: 1108183
Credit: 14,604,950
RAC: 10,112
           
|
|
Since I only mentioned this on Discord before: I tried the Mac CPU app several days ago, and it failed to run. I am told that it's an issue with statically vs. dynamically linked libraries, and that a fix is on the way. | |
|
Ravi FernandoProject administrator
Volunteer tester
Project scientist
Send message
Joined: 21 Mar 19
Posts: 211
ID: 1108183
Credit: 14,604,950
RAC: 10,112
|
|
I'm now running 16 fmai with the updated Mac app. I'll post the results for this and subsequent tests here when they're done. | |
|
|
|
|
win32 fmai gfn20
genefer 3.3.5.1 (CPU/Windows/32-bit/gcc-7.3.0/BOINC-7.17.0)
Copyright 2001-2020, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2018, Iain Bethune
Genefer is free source code, under the MIT license.
Supported transform implementations: fma avx sse4 sse2 f64 fmai avxi sse4i sse2i f64i
Command line: C:\Users\Millerick\Downloads\genefer\20\genefer_windows32.exe -x fmai -q 1059094^1048576+1
Low priority change succeeded.
Testing 1059094^1048576+1...
Using fmai transform
Starting initialization...
Initialization complete (6.558 seconds).
Estimated time for 1059094^1048576+1 is 101:00:00
1059094^1048576+1 is a probable prime. (6317602 digits) (err = 0.0010) (time = 88:08:46) 15:35:03
____________
| |
|
|
|
|
I've started running sse2i transforms on my Mac (Broadwell i5 2.9). I can't seem to figure out how the app_info works so I'm testing the primes individually
____________
Just a poor Mac user with no fancy GPUs
Tested GFN CPU transforms | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
|
Thanks to Michael Millerick, James and 288larsson, genefer_windows32.exe and genefer_linux64 are validated :) | |
|
Ravi FernandoProject administrator
Volunteer tester
Project scientist
Send message
Joined: 21 Mar 19
Posts: 211
ID: 1108183
Credit: 14,604,950
RAC: 10,112
|
|
Here's Mac fmai for 16, 17mega, and 18. The timings are funny because I was running BOINC and other things on and off during all three tests.
Command line: ./genefer_macintel64 -q 98679336^65536+1
Low priority change succeeded.
fma transform is past its b limit.
avx transform is past its b limit.
sse4 transform is past its b limit.
sse2 transform is past its b limit.
Testing 98679336^65536+1...
Using fmai transform
Starting initialization...
Initialization complete (0.182 seconds).
Estimated time for 98679336^65536+1 is 0:45:50
98679336^65536+1 is a probable prime. (523910 digits) (err = 0.1719) (time = 0:26:17) 14:50:03
Command line: ./genefer_macintel64 -q 80146408^131072+1
Low priority change succeeded.
fma transform is past its b limit.
avx transform is past its b limit.
sse4 transform is past its b limit.
sse2 transform is past its b limit.
Testing 80146408^131072+1...
Using fmai transform
Starting initialization...
Initialization complete (0.358 seconds).
Estimated time for 80146408^131072+1 is 1:52:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 2:47:18) 17:40:07
Command line: ./genefer_macintel64 -q 11081688^262144+1
Low priority change succeeded.
fma transform is past its b limit.
avx transform is past its b limit.
sse4 transform is past its b limit.
sse2 transform is past its b limit.
Testing 11081688^262144+1...
Using fmai transform
Starting initialization...
Initialization complete (0.726 seconds).
Estimated time for 11081688^262144+1 is 6:40:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0156) (time = 9:33:58) 03:26:06 | |
|
|
|
|
Here's the MacIntel64 sse2i for 16, 17low, and 17mega
Command line: $PATH/genefer_macintel64 -q 98752904^65536+1 -x sse2i
Low priority change succeeded.
Testing 98752904^65536+1...
Using sse2i transform
Starting initialization...
Initialization complete (0.082 seconds).
Estimated time for 98752904^65536+1 is 0:40:20
98752904^65536+1 is a probable prime. (523931 digits) (err = 0.1875) (time = 0:43:40) 22:58:31
Command line: $PATH/genefer_macintel64 -q 80146408^131072+1 -x sse2i
Low priority change succeeded.
Testing 80146408^131072+1...
Using sse2i transform
Starting initialization...
Initialization complete (0.249 seconds).
Estimated time for 80146408^131072+1 is 2:47:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 2:59:27) 02:02:15
Command line: $PATH/genefer_macintel64 -q 11081688^262144+1 -x sse2i
Low priority change succeeded.
Testing 11081688^262144+1...
Using sse2i transform
The checkpoint doesn't match current test: 11081688^262144+1 != 80146408^131072+1. Current test will be restarted
Starting initialization...
Initialization complete (0.749 seconds).
Estimated time for 11081688^262144+1 is 12:50:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0156) (time = 10:38:30) 11:45:49
I'll run 18, 19, and 20 today, and check my old iMac Desktop (it's on a Core 2 Duo, from 2007) for sse4i to check compatibility
____________
Just a poor Mac user with no fancy GPUs
Tested GFN CPU transforms | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
Here's the MacIntel64 sse2i for 16, 17low, and 17mega
I'll run 18, 19, and 20 today, and check my old iMac Desktop (it's on a Core 2 Duo, from 2007) for sse4i to check compatibility
Thanks, the Mac's strike back! Note that 20 is not tested for sse2i and sse4. It's unnecessary because GFN-20 is too big for being tested with a CPU without AVX instructions.
| |
|
Ravi FernandoProject administrator
Volunteer tester
Project scientist
Send message
Joined: 21 Mar 19
Posts: 211
ID: 1108183
Credit: 14,604,950
RAC: 10,112
|
|
I also did 16 with Mac sse4i and avxi (on the same computer, an i5-5250U). I will do Mac fmai 19 next.
Command line: ./genefer_macintel64 -x sse4i -q 98679336^65536+1
Low priority change succeeded.
Testing 98679336^65536+1...
Using sse4i transform
Starting initialization...
Initialization complete (0.157 seconds).
Estimated time for 98679336^65536+1 is 1:32:00
98679336^65536+1 is a probable prime. (523910 digits) (err = 0.1719) (time = 1:31:43) 10:44:20
Command line: ./genefer_macintel64 -x avxi -q 98679336^65536+1
Low priority change succeeded.
Testing 98679336^65536+1...
Using avxi transform
Starting initialization...
Initialization complete (0.182 seconds).
Estimated time for 98679336^65536+1 is 0:59:20
98679336^65536+1 is a probable prime. (523910 digits) (err = 0.1719) (time = 0:45:08) 12:14:18 | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
I also did 16 with Mac sse4i and avxi (on the same computer, an i5-5250U). I will do Mac fmai 19 next.
Thanks. The U-series are slow because of their TPD = 15 Watt. Same problem with the new Apple M1, TPD is 15W.
| |
|
Ravi FernandoProject administrator
Volunteer tester
Project scientist
Send message
Joined: 21 Mar 19
Posts: 211
ID: 1108183
Credit: 14,604,950
RAC: 10,112
|
|
Mac fmai 19 (same disclaimers about other stuff running on and off):
Command line: ./genefer_macintel64 -q 3638450^524288+1
Low priority change succeeded.
fma transform is past its b limit.
avx transform is past its b limit.
sse4 transform is past its b limit.
sse2 transform is past its b limit.
Testing 3638450^524288+1...
Using fmai transform
Starting initialization...
Initialization complete (3.785 seconds).
Estimated time for 3638450^524288+1 is 52:40:00
3638450^524288+1 is a probable prime. (3439810 digits) (err = 0.0039) (time = 34:58:58) 00:43:54 | |
|
|
|
|
Finished another MacIntel64 sse2i
Command line: $PATH/genefer_macintel64 -q 3638450^524288+1 -x sse2i
Low priority change succeeded.
Testing 3638450^524288+1...
Using sse2i transform
Starting initialization...
Initialization complete (1.799 seconds).
Estimated time for 3638450^524288+1 is 42:40:00
3638450^524288+1 is a probable prime. (3439810 digits) (err = 0.0039) (time = 47:57:42) 14:16:47
____________
Just a poor Mac user with no fancy GPUs
Tested GFN CPU transforms | |
|
Yves GallotVolunteer developer
Project scientist
Send message
Joined: 19 Aug 12
Posts: 846
ID: 164101
Credit: 306,572,235
RAC: 5,460
|
Finished another MacIntel64 sse2i
Thanks, MacIntel64 sse2i is validated :)
| |
|
Ravi FernandoProject administrator
Volunteer tester
Project scientist
Send message
Joined: 21 Mar 19
Posts: 211
ID: 1108183
Credit: 14,604,950
RAC: 10,112
|
|
I'm starting 17Mega and 18 with avxi on Mac. I will do the same with sse4i afterwards if no one else claims them. | |
|
Ravi FernandoProject administrator
Volunteer tester
Project scientist
Send message
Joined: 21 Mar 19
Posts: 211
ID: 1108183
Credit: 14,604,950
RAC: 10,112
|
I'm starting 17Mega and 18 with avxi on Mac. I will do the same with sse4i afterwards if no one else claims them.
Done:
Command line: ./genefer_macintel64 -x avxi -q 80146408^131072+1
Low priority change succeeded.
Testing 80146408^131072+1...
Using avxi transform
Starting initialization...
Initialization complete (0.372 seconds).
Estimated time for 80146408^131072+1 is 2:18:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 2:45:58) 12:26:20
Command line: ./genefer_macintel64 -x avxi -q 11081688^262144+1
Low priority change succeeded.
Testing 11081688^262144+1...
Using avxi transform
Starting initialization...
Initialization complete (1.440 seconds).
Estimated time for 11081688^262144+1 is 13:10:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0156) (time = 9:45:09) 05:14:24
Moving on to sse4i. | |
|
|
|
Moving on to sse4i.
What a coincidence I just did 80146408 on sse4i and have 7 hours left on 11081688
Command line: $PATH/genefer_macintel64 -q 80146408^131072+1 -x sse4i
Low priority change succeeded.
Testing 80146408^131072+1...
Using sse4i transform
The checkpoint doesn't match current test: 80146408^131072+1 != 11081688^262144+1. Current test will be restarted
Starting initialization...
Initialization complete (0.449 seconds).
Estimated time for 80146408^131072+1 is 6:56:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 3:33:16) 17:14:22
____________
Just a poor Mac user with no fancy GPUs
Tested GFN CPU transforms | |
|
Ravi FernandoProject administrator
Volunteer tester
Project scientist
Send message
Joined: 21 Mar 19
Posts: 211
ID: 1108183
Credit: 14,604,950
RAC: 10,112
|
What a coincidence I just did 80146408 on sse4i and have 7 hours left on 11081688
Thanks for posting. I finished the same one you did (results below), and just started the other. Your run will finish first, so I'm canceling mine.
Command line: ./genefer_macintel64 -x sse4i -q 80146408^131072+1
Low priority change succeeded.
Testing 80146408^131072+1...
Using sse4i transform
Starting initialization...
Initialization complete (0.342 seconds).
Estimated time for 80146408^131072+1 is 4:16:00
80146408^131072+1 is a probable prime. (1035978 digits) (err = 0.1875) (time = 4:11:16) 16:48:29 | |
|
|
|
Command line: $PATH/genefer_macintel64 -q 11081688^262144+1 -x sse4i
Low priority change succeeded.
Testing 11081688^262144+1...
Using sse4i transform
The checkpoint doesn't match current test: 11081688^262144+1 != 1059094^1048576+1. Current test will be restarted
Starting initialization...
Initialization complete (0.828 seconds).
Estimated time for 11081688^262144+1 is 18:30:00
11081688^262144+1 is a probable prime. (1846702 digits) (err = 0.0156) (time = 14:13:23) 03:52:24 | |
|
Ravi FernandoProject administrator
Volunteer tester
Project scientist
Send message
Joined: 21 Mar 19
Posts: 211
ID: 1108183
Credit: 14,604,950
RAC: 10,112
|
|
I'm starting Mac avxi 19, which should take a day or two. | |
|
Ravi FernandoProject administrator
Volunteer tester
Project scientist
Send message
Joined: 21 Mar 19
Posts: 211
ID: 1108183
Credit: 14,604,950
RAC: 10,112
|
I'm starting Mac avxi 19, which should take a day or two.
Done:
Command line: ./genefer_macintel64 -x avxi -q 3638450^524288+1
Low priority change succeeded.
Testing 3638450^524288+1...
Using avxi transform
Starting initialization...
Initialization complete (2.245 seconds).
Estimated time for 3638450^524288+1 is 28:50:00
3638450^524288+1 is a probable prime. (3439810 digits) (err = 0.0039) (time = 30:03:53) 18:00:23 | |
|
Michael GoetzVolunteer moderator
Project administrator
Send message
Joined: 21 Jan 10
Posts: 14045
ID: 53948
Credit: 485,590,703
RAC: 673,563
|
|
The Mac 3.3.5 is up and running on Dev if anyone wants to test it.
____________
My lucky number is 75898524288+1 | |
|
Message boards :
Generalized Fermat Prime Search :
Genefer 3.3.5 testing |
