mersenneforum.org  

Go Back   mersenneforum.org > Great Internet Mersenne Prime Search > Hardware > GPU Computing > GpuOwl

Reply
 
Thread Tools
Old 2022-11-15, 23:39   #2828
moebius
 
moebius's Avatar
 
Jul 2009
Germany

12378 Posts
Default

Quote:
Originally Posted by moebius View Post
You're right only the Arc A310 , A350 and the Alchemist Pro-Series: Arc Pro A40, Pro A50, Pro A30M (will) have FP64 capability but also with OpenCl 3.0 where you don't know exactly if gpuOwl is running at all:
I have to correct myself, OpenCL 3.0 definitely runs with gpuowl v6.11-364 to 7.x since the RTX Geforce 4090 also has OpenCL 3.0 and works, it is just due to FP64.
https://www.techpowerup.com/gpu-specs/geforce-rtx-4090.c3889

Last fiddled with by moebius on 2022-11-15 at 23:42
moebius is offline   Reply With Quote
Old 2022-11-16, 01:13   #2829
kriesel
 
kriesel's Avatar
 
"TF79LL86GIMPS96gpu17"
Mar 2017
US midwest

34·7·13 Posts
Default

Quote:
Originally Posted by moebius View Post
OpenCL 3.0 definitely runs with gpuowl v6.11-364 to 7.x since the RTX Geforce 4090 also has OpenCL 3.0 and works
Does it? Maybe you could help this struggling user with a 4090?
kriesel is online now   Reply With Quote
Old 2022-11-16, 01:45   #2830
moebius
 
moebius's Avatar
 
Jul 2009
Germany

11×61 Posts
Default

Quote:
Originally Posted by kriesel View Post
Does it? Maybe you could help this struggling user with a 4090?
user yuki0831 said v7.x worked for his "flaky" card ...

I suspect bad/faulty memory, he might want to check his warranty claims. Otherwise he should experiment with the values ​​for gpuclock,gpuVoltage,memory clock,memory voltage and fan speed (with GPUTweak II,Afterburner etc) until he has reached a stable configuration. Maybe the card gets too hot under full load.


The error EE usually results from a too high clock frequency of the memory or the gpu

2022-11-15 23:03:21 NVIDIA GeFor ce RTX 4090-0 77936867 EE 800 0.00%; 753 us/it; ETA 0d 16:18; 0000000000000000 (check 0.35s)

In any case, there is no error in the OpenCL compilation, which is what I meant by it's running.

Last fiddled with by moebius on 2022-11-16 at 01:54
moebius is offline   Reply With Quote
Old 2022-11-16, 10:19   #2831
yuki0831
 
"Yuki@karoushi"
Feb 2020
Japan, Chiba pref

3010 Posts
Default GPU-Z/TF range and Exp? 118M 255M 831M

Hello, I bought the RTX 4090 and struggle with PRP.
I cant post PRP bench.

But I could attach some TF results.


GPU TF for manual assianments
Code:
mfaktc v0.21 (64bit built)

Compiletime options
  THREADS_PER_BLOCK         256
  SIEVE_SIZE_LIMIT          32kiB
  SIEVE_SIZE                193154bits
  SIEVE_SPLIT               250
  MORE_CLASSES              enabled

Runtime options
  SievePrimes               25000
  SievePrimesAdjust         1
  SievePrimesMin            5000
  SievePrimesMax            100000
  NumStreams                3
  CPUStreams                3
  GridSize                  3
  GPU Sieving               enabled
  GPUSievePrimes            82486
  GPUSieveSize              2047Mi bits
  GPUSieveProcessSize       16Ki bits
  Checkpoints               enabled
  CheckpointDelay           30s
  WorkFileAddDelay          600s
  Stages                    enabled
  StopAfterFactor           bitlevel
  PrintMode                 full
  V5UserID                  yuki0831
  ComputerID                RTX4090 inside
  AllowSleep                no
  TimeStampInResults        no

CUDA version info
  binary compiled for CUDA  11.20
  CUDA runtime version      11.20
  CUDA driver version       12.0

CUDA device info
  name                      NVIDIA GeForce RTX 4090
  compute capability        8.9
  max threads per block     1024
  max shared memory per MP  102400 byte
  number of multiprocessors 128
  clock rate (CUDA cores)   2520MHz
  memory clock rate:        10501MHz
  memory bus width:         384 bit

Automatic parameters
  threads per grid          1048576
  GPUSievePrimes (adjusted) 82486
  GPUsieve minimum exponent 1055144

running a simple selftest...
Selftest statistics
  number of tests           107
  successfull tests         107

selftest PASSED!

got assignment: exp=118718057 bit_min=77 bit_max=78 (257.82 GHz-days)
Starting trial factoring M118718057 from 2^77 to 2^78 (257.82 GHz-days)
 k_min =  636447947640120
 k_max =  1272895895287678
Using GPU kernel "barrett87_mul32_gs"
Date    Time | class   Pct |   time     ETA | GHz-d/day    Sieve     Wait
Nov 16 18:50 |    0   0.1% |  1.788  28m35s |   12977.71    82485    n.a.%
Nov 16 18:50 |    3   0.2% |  1.784  28m29s |   13006.81    82485    n.a.%
Nov 16 18:50 |    4   0.3% |  1.785  28m28s |   12999.52    82485    n.a.%
Nov 16 18:50 |   12   0.4% |  1.809  28m49s |   12827.06    82485    n.a.%
Nov 16 18:50 |   19   0.5% |  1.790  28m29s |   12963.21    82485    n.a.%
Nov 16 18:50 |   24   0.6% |  1.784  28m22s |   13006.81    82485    n.a.%
Nov 16 18:50 |   27   0.7% |  1.786  28m22s |   12992.24    82485    n.a.%
Nov 16 18:50 |   28   0.8% |  1.791  28m25s |   12955.97    82485    n.a.%
Nov 16 18:50 |   39   0.9% |  1.791  28m23s |   12955.97    82485    n.a.%
Nov 16 18:50 |   48   1.0% |  1.793  28m23s |   12941.52    82485    n.a.%
Nov 16 18:50 |   52   1.1% |  1.794  28m23s |   12934.31    82485    n.a.%
Nov 16 18:50 |   55   1.3% |  1.793  28m20s |   12941.52    82485    n.a.%
Nov 16 18:50 |   60   1.4% |  1.804  28m28s |   12862.61    82485    n.a.%
Nov 16 18:50 |   63   1.5% |  1.845  29m05s |   12576.77    82485    n.a.%
Nov 16 18:50 |   67   1.6% |  1.839  28m58s |   12617.80    82485    n.a.%
Nov 16 18:50 |   72   1.7% |  1.829  28m47s |   12686.79    82485    n.a.%
Nov 16 18:50 |   75   1.8% |  1.901  29m53s |   12206.28    82485    n.a.%
Nov 16 18:50 |   79   1.9% |  1.846  28m59s |   12569.96    82485    n.a.%
Nov 16 18:50 |   87   2.0% |  1.828  28m40s |   12693.73    82485    n.a.%
Nov 16 18:50 |   88   2.1% |  1.847  28m56s |   12563.15    82485    n.a.%
Date    Time | class   Pct |   time     ETA | GHz-d/day    Sieve     Wait
Nov 16 18:50 |  100   2.2% |  1.836  28m44s |   12638.42    82485    n.a.%
Nov 16 18:50 |  103   2.3% |  1.795  28m04s |   12927.10    82485    n.a.%
Nov 16 18:51 |  108   2.4% |  1.797  28m04s |   12912.71    82485    n.a.%
Nov 16 18:51 |  112   2.5% |  1.796  28m01s |   12919.90    82485    n.a.%
Nov 16 18:51 |  115   2.6% |  1.792  27m56s |   12948.74    82485    n.a.%
Nov 16 18:51 |  123   2.7% |  1.830  28m29s |   12679.86    82485    n.a.%
Nov 16 18:51 |  124   2.8% |  1.809  28m08s |   12827.06    82485    n.a.%
Nov 16 18:51 |  132   2.9% |  1.797  27m55s |   12912.71    82485    n.a.%
Nov 16 18:51 |  135   3.0% |  1.800  27m56s |   12891.19    82485    n.a.%
Nov 16 18:51 |  144   3.1% |  1.794  27m48s |   12934.31    82485    n.a.%
Nov 16 18:51 |  147   3.2% |  1.797  27m49s |   12912.71    82485    n.a.%
Nov 16 18:51 |  159   3.3% |  1.805  27m55s |   12855.48    82485    n.a.%
Nov 16 18:51 |  160   3.4% |  1.801  27m50s |   12884.03    82485    n.a.%
Nov 16 18:51 |  163   3.5% |  1.797  27m44s |   12912.71    82485    n.a.%
Nov 16 18:51 |  168   3.6% |  1.826  28m09s |   12707.64    82485    n.a.%
Nov 16 18:51 |  175   3.8% |  1.833  28m14s |   12659.11    82485    n.a.%
Nov 16 18:51 |  180   3.9% |  1.823  28m03s |   12728.55    82485    n.a.%
Nov 16 18:51 |  184   4.0% |  1.810  27m49s |   12819.97    82485    n.a.%
Nov 16 18:51 |  187   4.1% |  1.834  28m09s |   12652.20    82485    n.a.%
Nov 16 18:51 |  192   4.2% |  1.839  28m12s |   12617.80    82485    n.a.%
Date    Time | class   Pct |   time     ETA | GHz-d/day    Sieve     Wait
Nov 16 18:51 |  195   4.3% |  1.797  27m31s |   12912.71    82485    n.a.%
Nov 16 18:51 |  199   4.4% |  1.801  27m33s |   12884.03    82485    n.a.%
Nov 16 18:51 |  207   4.5% |  1.800  27m31s |   12891.19    82485    n.a.%
Nov 16 18:51 |  208   4.6% |  1.794  27m23s |   12934.31    82485    n.a.%
Nov 16 18:51 |  219   4.7% |  1.837  28m01s |   12631.54    82485    n.a.%
Nov 16 18:51 |  220   4.8% |  1.815  27m39s |   12784.65    82485    n.a.%
Nov 16 18:51 |  223   4.9% |  1.850  28m09s |   12542.78    82485    n.a.%
Nov 16 18:51 |  228   5.0% |  1.831  27m50s |   12672.93    82485    n.a.%
Nov 16 18:51 |  235   5.1% |  1.839  27m55s |   12617.80    82485    n.a.%
Nov 16 18:51 |  240   5.2% |  1.859  28m12s |   12482.06    82485    n.a.%
Nov 16 18:51 |  243   5.3% |  1.829  27m43s |   12686.79    82485    n.a.%
Nov 16 18:51 |  244   5.4% |  1.824  27m36s |   12721.57    82485    n.a.%
Nov 16 18:51 |  247   5.5% |  1.861  28m08s |   12468.64    82485    n.a.%
Nov 16 18:51 |  252   5.6% |  1.832  27m40s |   12666.02    82485    n.a.%
Nov 16 18:51 |  255   5.7% |  1.827  27m33s |   12700.68    82485    n.a.%
Nov 16 18:52 |  259   5.8% |  1.832  27m36s |   12666.02    82485    n.a.%
Nov 16 18:52 |  264   5.9% |  1.810  27m14s |   12819.97    82485    n.a.%
Nov 16 18:52 |  268   6.0% |  1.790  26m55s |   12963.21    82485    n.a.%
Nov 16 18:52 |  279   6.1% |  1.790  26m53s |   12963.21    82485    n.a.%
Nov 16 18:52 |  280   6.3% |  1.791  26m52s |   12955.97    82485    n.a.%
Date    Time | class   Pct |   time     ETA | GHz-d/day    Sieve     Wait
Nov 16 18:52 |  283   6.4% |  1.793  26m52s |   12941.52    82485    n.a.%
Nov 16 18:52 |  292   6.5% |  1.791  26m48s |   12955.97    82485    n.a.%
Nov 16 18:52 |  300   6.6% |  1.815  27m08s |   12784.65    82485    n.a.%
works well. Total board power 450W No power limits
------------------------------- 

manual assignment for CPU using GPU
##omit prefernce##
got assignment: exp=255495797 bit_min=74 bit_max=75 (14.97 GHz-days)
Starting trial factoring M255495797 from 2^74 to 2^75 (14.97 GHz-days)
 k_min =  36966294851640
 k_max =  73932589707057
Using GPU kernel "barrett76_mul32_gs"
Date    Time | class   Pct |   time     ETA | GHz-d/day    Sieve     Wait
Nov 16 18:55 |    0   0.1% |  0.106    n.a. |   12714.60    82485    n.a.%
Nov 16 18:55 |    3   0.2% |  0.107    n.a. |   12595.77    82485    n.a.%
Nov 16 18:55 |    4   0.3% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |   12   0.4% |  0.106    n.a. |   12714.60    82485    n.a.%
Nov 16 18:55 |   15   0.5% |  0.104    n.a. |   12959.11    82485    n.a.%
Nov 16 18:55 |   19   0.6% |  0.104    n.a. |   12959.11    82485    n.a.%
Nov 16 18:55 |   24   0.7% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |   28   0.8% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |   39   0.9% |  0.104    n.a. |   12959.11    82485    n.a.%
Nov 16 18:55 |   43   1.0% |  0.104    n.a. |   12959.11    82485    n.a.%
Nov 16 18:55 |   52   1.1% |  0.104    n.a. |   12959.11    82485    n.a.%
Nov 16 18:55 |   60   1.3% |  0.102    n.a. |   13213.21    82485    n.a.%
Nov 16 18:55 |   63   1.4% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |   64   1.5% |  0.104    n.a. |   12959.11    82485    n.a.%
Nov 16 18:55 |   67   1.6% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |   72   1.7% |  0.104    n.a. |   12959.11    82485    n.a.%
Nov 16 18:55 |   75   1.8% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |   79   1.9% |  0.104    n.a. |   12959.11    82485    n.a.%
Nov 16 18:55 |   87   2.0% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |   88   2.1% |  0.104    n.a. |   12959.11    82485    n.a.%
Date    Time | class   Pct |   time     ETA | GHz-d/day    Sieve     Wait
Nov 16 18:55 |   99   2.2% |  0.104    n.a. |   12959.11    82485    n.a.%
Nov 16 18:55 |  100   2.3% |  0.102    n.a. |   13213.21    82485    n.a.%
Nov 16 18:55 |  103   2.4% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |  108   2.5% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |  112   2.6% |  0.105    n.a. |   12835.69    82485    n.a.%
Nov 16 18:55 |  115   2.7% |  0.104    n.a. |   12959.11    82485    n.a.%
Nov 16 18:55 |  120   2.8% |  0.102    n.a. |   13213.21    82485    n.a.%
Nov 16 18:55 |  123   2.9% |  0.102    n.a. |   13213.21    82485    n.a.%
Nov 16 18:55 |  124   3.0% |  0.102    n.a. |   13213.21    82485    n.a.%
Nov 16 18:55 |  127   3.1% |  0.102    n.a. |   13213.21    82485    n.a.%
Nov 16 18:55 |  135   3.2% |  0.106    n.a. |   12714.60    82485    n.a.%
Nov 16 18:55 |  144   3.3% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |  147   3.4% |  0.102    n.a. |   13213.21    82485    n.a.%
Nov 16 18:55 |  148   3.5% |  0.102    n.a. |   13213.21    82485    n.a.%
Nov 16 18:55 |  159   3.6% |  0.104    n.a. |   12959.11    82485    n.a.%
Nov 16 18:55 |  163   3.8% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |  168   3.9% |  0.102    n.a. |   13213.21    82485    n.a.%
Nov 16 18:55 |  175   4.0% |  0.104    n.a. |   12959.11    82485    n.a.%
Nov 16 18:55 |  180   4.1% |  0.106    n.a. |   12714.60    82485    n.a.%
Nov 16 18:55 |  184   4.2% |  0.106    n.a. |   12714.60    82485    n.a.%
Date    Time | class   Pct |   time     ETA | GHz-d/day    Sieve     Wait
Nov 16 18:55 |  187   4.3% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |  192   4.4% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:55 |  199   4.5% |  0.102    n.a. |   13213.21    82485    n.a.%
Nov 16 18:55 |  204   4.6% |  0.101    n.a. |   13344.04    82485    n.a.%
~~~~~~~~~~~~~~~~~
Nov 16 18:56 | 4600  99.7% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:56 | 4603  99.8% |  0.106    n.a. |   12714.60    82485    n.a.%
Nov 16 18:56 | 4608  99.9% |  0.103    n.a. |   13084.93    82485    n.a.%
Nov 16 18:56 | 4615 100.0% |  0.104    n.a. |   12959.11    82485    n.a.%
no factor for M255495797 from 2^74 to 2^75 [mfaktc 0.21 barrett76_mul32_gs]
tf(): total time spent:  1m 45.807s

TF for 831M 
got assignment: exp=831199679 bit_min=87 bit_max=88 (37708.08 GHz-days)
Starting trial factoring M831199679 from 2^87 to 2^88 (37708.08 GHz-days)
 k_min =  93083833415837880
 k_max =  186167666831681409
Using GPU kernel "barrett88_mul32_gs"

found a valid checkpoint file!
  last finished class was: 112
  found 0 factor(s) already

Date    Time | class   Pct |   time     ETA | GHz-d/day    Sieve     Wait
Nov 16 19:05 |  120   2.7% | 299.40   3d05h |   11335.06    82485    n.a.%
Nov 16 19:10 |  121   2.8% | 299.17   3d05h |   11344.00    82485    n.a.%
Nov 16 19:15 |  132   2.9% | 299.69   3d05h |   11324.31    82485    n.a.%
Less than 12000Ghz/day benchmark on GPU assignment.

GPU factoring >1000M has makes coil noise. Its not fan noise.
its dangerous to work on.I think.

Do you need Power limit 80% benchmark?
Its ecology (90W cut)and efficient Watt performance.

If I post wrong shread, I apologize.
Attached Thumbnails
Click image for larger version

Name:	info about RTX 4090.gif
Views:	17
Size:	24.2 KB
ID:	27629   Click image for larger version

Name:	TF 118M No Power limit 450W TBP.gif
Views:	14
Size:	28.7 KB
ID:	27630   Click image for larger version

Name:	TF CPU assign using RTX4090.gif
Views:	13
Size:	27.7 KB
ID:	27631   Click image for larger version

Name:	831M TF.gif
Views:	13
Size:	25.7 KB
ID:	27632  

Last fiddled with by VBCurtis on 2022-11-16 at 16:39 Reason: added code blocks
yuki0831 is offline   Reply With Quote
Old 2022-11-16, 10:41   #2832
yuki0831
 
"Yuki@karoushi"
Feb 2020
Japan, Chiba pref

2×3×5 Posts
Default Cant run PRP but CUDAlucus go on

RTX 4090 cant run PRP,but Cuda-lucus can iterate.


CUDALucas v2.06 64-bit build, compiled May 20 2019 @ 16:50:35
Code:
binary compiled for CUDA   10.10
CUDA runtime version       10.10
CUDA driver version        12.0

---------------- DEVICE 0 ----------------
Device Name               NVIDIA GeForce RTX 4090
ECC Support?              Disabled
Compatibility             8.9
clockRate (MHz)           2520
memClockRate (MHz)        10501
totalGlobalMem            25756565504
totalConstMem             65536
l2CacheSize               75497472
sharedMemPerBlock         49152
regsPerBlock              65536
warpSize                  32
memPitch                  2147483647
maxThreadsPerBlock        1024
maxThreadsPerMP           1536
multiProcessorCount       128
maxThreadsDim[3]          1024,1024,64
maxGridSize[3]            2147483647,65535,65535
textureAlignment          512
deviceOverlap             1
pciDeviceID               0
pciBusID                  1

You may experience a small delay on 1st startup to due to Just-in-Time Compilation

Using threads: square 256, splice 128.

Continuing M57885161 @ iteration 277020 with fft length 3136K,  0.48% done

|   Date     Time    |   Test Num     Iter        Residue        |    FFT   Error     ms/It     Time  |       ETA      Done   |
|  Nov 16  19:35:58  |  M57885161    278000  0xcbe0ce0d325a9ae2  |  3136K  0.15625   0.8064    0.79s  |     22:48:58   0.48%  |
|  Nov 16  19:35:59  |  M57885161    279000  0xae4d2eae39a72c0a  |  3136K  0.15625   0.8238    0.82s  |     22:46:52   0.48%  |
|  Nov 16  19:36:00  |  M57885161    280000  0x678b32b35f88d73d  |  3136K  0.15625   0.8025    0.80s  |     22:44:42   0.48%  |
|  Nov 16  19:36:01  |  M57885161    281000  0xd1efe3cfd147c085  |  3136K  0.15625   1.0704    1.07s  |     22:43:28   0.48%  |
|  Nov 16  19:36:02  |  M57885161    282000  0x714d25f8d37cf836  |  3136K  0.15234   0.7911    0.79s  |     22:41:18   0.48%  |
|  Nov 16  19:36:03  |  M57885161    283000  0xa4bd8bc9244b8b28  |  3136K  0.15625   0.7874    0.78s  |     22:39:08   0.48%  |
|  Nov 16  19:36:04  |  M57885161    284000  0x0becc6cf5e8fcc44  |  3136K  0.15625   0.7891    0.78s  |     22:36:59   0.49%  |
|  Nov 16  19:36:04  |  M57885161    285000  0xf10ac139a4525617  |  3136K  0.14844   0.7908    0.79s  |     22:34:51   0.49%  |
|  Nov 16  19:36:05  |  M57885161    286000  0x2034bd93db568f5f  |  3136K  0.17188   0.7919    0.79s  |     22:32:45   0.49%  |
|  Nov 16  19:36:06  |  M57885161    287000  0x219f109a761009cd  |  3136K  0.14844   0.7983    0.79s  |     22:30:40   0.49%  |
|  Nov 16  19:36:07  |  M57885161    288000  0x466e03a991973c16  |  3136K  0.15039   0.7978    0.79s  |     22:28:37   0.49%  |
|  Nov 16  19:36:07  |  M57885161    289000  0x363ab3c286190751  |  3136K  0.16406   0.7963    0.79s  |     22:26:33   0.49%  |
|  Nov 16  19:36:09  |  M57885161    290000  0x4f51138c1f7f6301  |  3136K  0.15625   0.7981    0.79s  |     22:24:32   0.50%  |
|  Nov 16  19:36:09  |  M57885161    291000  0x47d0933bf7609619  |  3136K  0.17188   1.0655    1.06s  |     22:23:24   0.50%  |
|  Nov 16  19:36:10  |  M57885161    292000  0xf7956adfe310f162  |  3136K  0.15625   0.7806    0.78s  |     22:21:20   0.50%  |
|  Nov 16  19:36:11  |  M57885161    293000  0xd1876d7e5052e366  |  3136K  0.15625   0.7878    0.78s  |     22:19:18   0.50%  |
|  Nov 16  19:36:12  |  M57885161    294000  0x12b2c2dce3f0d96a  |  3136K  0.17188   0.7858    0.78s  |     22:17:17   0.50%  |
|  Nov 16  19:36:12  |  M57885161    295000  0x04c641d7f906f863  |  3136K  0.16699   0.7795    0.77s  |     22:15:15   0.50%  |
|   Date     Time    |   Test Num     Iter        Residue        |    FFT   Error     ms/It     Time  |       ETA      Done   |
|  Nov 16  19:36:13  |  M57885161    296000  0xcc2487fa86bbf9db  |  3136K  0.17188   0.7794    0.77s  |     22:13:14   0.51%  |
|  Nov 16  19:36:14  |  M57885161    297000  0x929084c59e172141  |  3136K  0.15625   0.7810    0.78s  |     22:11:15   0.51%  |
|  Nov 16  19:36:15  |  M57885161    298000  0xa51033a6780ab4d0  |  3136K  0.16406   0.7778    0.77s  |     22:09:15   0.51%  |
|  Nov 16  19:36:16  |  M57885161    299000  0x2f3ba2a9df8a1e88  |  3136K  0.17969   0.7825    0.78s  |     22:07:17   0.51%  |
|  Nov 16  19:36:17  |  M57885161    300000  0x4332497b4eefcf79  |  3136K  0.15273   0.7900    0.79s  |     22:05:22   0.51%  |
|  Nov 16  19:36:17  |  M57885161    301000  0x3ca858e58ecb6497  |  3136K  0.15820   1.0687    1.06s  |     22:04:21   0.52%  |
|  Nov 16  19:36:18  |  M57885161    302000  0xad2b7c3bb6afbb76  |  3136K  0.15625   0.7892    0.78s  |     22:02:26   0.52%  |
|  Nov 16  19:36:19  |  M57885161    303000  0xc06b0569ac6a5b53  |  3136K  0.17969   0.7945    0.79s  |     22:00:34   0.52%  |
|  Nov 16  19:36:24  |  M57885161    304000  0xd3e2d7502d321f14  |  3136K  0.16406   5.0163    5.01s  |     22:12:04   0.52%  |
|  Nov 16  19:36:25  |  M57885161    305000  0xd772dc54351e7188  |  3136K  0.15625   0.8012    0.80s  |     22:10:12   0.52%  |
|  Nov 16  19:36:26  |  M57885161    306000  0x4288eb5692301fbe  |  3136K  0.15234   0.7904    0.79s  |     22:08:18   0.52%  |
|  Nov 16  19:36:26  |  M57885161    307000  0x2ed247b622866dc2  |  3136K  0.15625   0.7952    0.79s  |     22:06:25   0.53%  |
|  Nov 16  19:36:27  |  M57885161    308000  0x5a3c25644778eacb  |  3136K  0.16406   0.7976    0.79s  |     22:04:34   0.53%  |
|  Nov 16  19:36:28  |  M57885161    309000  0x15b198b6bf3f6e3c  |  3136K  0.15723   0.7905    0.79s  |     22:02:43   0.53%  |
|  Nov 16  19:36:29  |  M57885161    310000  0x059d1c9593b10de5  |  3136K  0.15820   0.7833    0.78s  |     22:00:51   0.53%  |
|  Nov 16  19:36:30  |  M57885161    311000  0xf22b8762e3d0abfb  |  3136K  0.16406   1.0625    1.06s  |     21:59:51   0.53%  |
|  Nov 16  19:36:31  |  M57885161    312000  0x308e63c9a234bd02  |  3136K  0.16406   0.7845    0.78s  |     21:58:00   0.53%  |
|  Nov 16  19:36:31  |  M57885161    313000  0x75fbc5b8df3a3623  |  3136K  0.15918   0.7815    0.78s  |     21:56:10   0.54%  |
|   Date     Time    |   Test Num     Iter        Residue        |    FFT   Error     ms/It     Time  |       ETA      Done   |
|  Nov 16  19:36:32  |  M57885161    314000  0x8ed3cdea870b0522  |  3136K  0.15625   0.7813    0.78s  |     21:54:20   0.54%  |
|  Nov 16  19:36:33  |  M57885161    315000  0xc5ebfe0aa8032ed9  |  3136K  0.17578   0.7820    0.78s  |     21:52:30   0.54%  |
|  Nov 16  19:36:34  |  M57885161    316000  0xae4cd8c05f6115f3  |  3136K  0.15820   0.7828    0.78s  |     21:50:42   0.54%  |
|  Nov 16  19:36:35  |  M57885161    317000  0x585f6932fa9b94d6  |  3136K  0.15820   0.7802    0.78s  |     21:48:54   0.54%  |
|  Nov 16  19:36:35  |  M57885161    318000  0x1d67abbc3a6c5334  |  3136K  0.17188   0.7846    0.78s  |     21:47:07   0.54%  |
|  Nov 16  19:36:36  |  M57885161    319000  0xc5190142b9332ea1  |  3136K  0.15625   0.7822    0.78s  |     21:45:21   0.55%  |
|  Nov 16  19:36:37  |  M57885161    320000  0xee0f3a7707935e5b  |  3136K  0.16406   0.7800    0.78s  |     21:43:35   0.55%  |
|  Nov 16  19:36:38  |  M57885161    321000  0xbb9f4aa2f72de99d  |  3136K  0.15625   1.0530    1.05s  |     21:42:39   0.55%  |
|  Nov 16  19:36:39  |  M57885161    322000  0x755c62bd416eac4e  |  3136K  0.15234   0.7955    0.79s  |     21:40:56   0.55%  |
|  Nov 16  19:36:40  |  M57885161    323000  0x8dc2a016db4d6ba2  |  3136K  0.17188   0.7991    0.79s  |     21:39:16   0.55%  |
|  Nov 16  19:36:40  |  M57885161    324000  0x6edbef666a3725e6  |  3136K  0.16406   0.7977    0.79s  |     21:37:35   0.55%  |
|  Nov 16  19:36:41  |  M57885161    325000  0x70fdfc9380ce9d49  |  3136K  0.16406   0.8006    0.80s  |     21:35:56   0.56%  |
|  Nov 16  19:36:42  |  M57885161    326000  0xc64234e82e227b76  |  3136K  0.16797   0.8055    0.80s  |     21:34:18   0.56%  |
|  Nov 16  19:36:43  |  M57885161    327000  0xa7a41ce0c8529a52  |  3136K  0.15625   0.7962    0.79s  |     21:32:39   0.56%  |
|  Nov 16  19:36:44  |  M57885161    328000  0xea02b43e37d0d8e0  |  3136K  0.15625   0.7971    0.79s  |     21:31:00   0.56%  |
|  Nov 16  19:36:44  |  M57885161    329000  0xd7d3a67d5eb5d18a  |  3136K  0.15820   0.8018    0.80s  |     21:29:24   0.56%  |
|  Nov 16  19:36:45  |  M57885161    330000  0xdd2afd1922b7f066  |  3136K  0.16211   0.7949    0.79s  |     21:27:46   0.57%  |
|  Nov 16  19:36:46  |  M57885161    331000  0xe56e7eea11e1dec2  |  3136K  0.17188   1.0773    1.07s  |     21:26:59   0.57%  |
|   Date     Time    |   Test Num     Iter        Residue        |    FFT   Error     ms/It     Time  |       ETA      Done   |
|  Nov 16  19:36:47  |  M57885161    332000  0x97b714bcc595281d  |  3136K  0.17188   0.7989    0.79s  |     21:25:23   0.57%  |
|  Nov 16  19:36:48  |  M57885161    333000  0x706e5a2c18fdb1c8  |  3136K  0.18750   0.7940    0.79s  |     21:23:47   0.57%  |
|  Nov 16  19:36:49  |  M57885161    334000  0xc45cc19cccc7c685  |  3136K  0.17188   0.7884    0.78s  |     21:22:11   0.57%  |
|  Nov 16  19:36:49  |  M57885161    335000  0x78268d4e2471e1ab  |  3136K  0.17188   0.7961    0.79s  |     21:20:36   0.57%  |
|  Nov 16  19:36:50  |  M57885161    336000  0xca4242603357908c  |  3136K  0.15625   0.7934    0.79s  |     21:19:02   0.58%  |
|  Nov 16  19:36:51  |  M57885161    337000  0x0cd88ed23ba5f828  |  3136K  0.15625   0.7962    0.79s  |     21:17:28   0.58%  |
|  Nov 16  19:36:52  |  M57885161    338000  0x474d2323354d95e2  |  3136K  0.16406   0.7937    0.79s  |     21:15:55   0.58%  |
|  Nov 16  19:36:53  |  M57885161    339000  0xe99454ec5989f399  |  3136K  0.16406   0.8022    0.80s  |     21:14:24   0.58%  |
|  Nov 16  19:36:54  |  M57885161    340000  0x5501bbab37c0ad02  |  3136K  0.16406   0.8011    0.80s  |     21:12:53   0.58%  |
|  Nov 16  19:36:54  |  M57885161    341000  0x9529e56c7295f7db  |  3136K  0.15625   1.0705    1.07s  |     21:12:08   0.58%  |
|  Nov 16  19:36:55  |  M57885161    342000  0x265b0c9432d32428  |  3136K  0.17188   0.8064    0.80s  |     21:10:39   0.59%  |
|  Nov 16  19:36:56  |  M57885161    343000  0x299a8cf366a86436  |  3136K  0.16406   0.7974    0.79s  |     21:09:09   0.59%  |
|  Nov 16  19:36:57  |  M57885161    344000  0x8139a466ba5006ea  |  3136K  0.16016   0.7990    0.79s  |     21:07:40   0.59%  |
|  Nov 16  19:36:58  |  M57885161    345000  0xdfe7c53fe764be6d  |  3136K  0.15625   0.8009    0.80s  |     21:06:11   0.59%  |
|  Nov 16  19:36:58  |  M57885161    346000  0x6b35184501596b83  |  3136K  0.15820   0.8005    0.80s  |     21:04:43   0.59%  |
|  Nov 16  19:36:59  |  M57885161    347000  0xd2a6ffe0eee8b2ae  |  3136K  0.15625   0.8027    0.80s  |     21:03:16   0.59%  |
|  Nov 16  19:37:00  |  M57885161    348000  0x7710c124302c2b1e  |  3136K  0.15625   0.8137    0.81s  |     21:01:51   0.60%  |
|  Nov 16  19:37:05  |  M57885161    349000  0xf49b9775e57bd3d1  |  3136K  0.16406   4.7653    4.76s  |     21:11:20   0.60%  |
|   Date     Time    |   Test Num     Iter        Residue        |    FFT   Error     ms/It     Time  |       ETA      Done   |
|  Nov 16  19:37:06  |  M57885161    350000  0x0c5e8318e5fbc827  |  3136K  0.18750   0.7934    0.79s  |     21:09:51   0.60%  |
|  Nov 16  19:37:07  |  M57885161    351000  0xd67a69f26f12923f  |  3136K  0.15938   1.0702    1.07s  |     21:09:08   0.60%  |
|  Nov 16  19:37:08  |  M57885161    352000  0x4f4da146fc6f4deb  |  3136K  0.15625   0.7872    0.78s  |     21:07:39   0.60%  |
|  Nov 16  19:37:08  |  M57885161    353000  0x8ed9e9fbb3461476  |  3136K  0.16406   0.7843    0.78s  |     21:06:10   0.60%  |
|  Nov 16  19:37:09  |  M57885161    354000  0x2cfa8dab340f4d66  |  3136K  0.17969   0.7918    0.79s  |     21:04:42   0.61%  |
|  Nov 16  19:37:10  |  M57885161    355000  0xd8c32be888059057  |  3136K  0.15625   0.8050    0.80s  |     21:03:17   0.61%  |
|  Nov 16  19:37:11  |  M57885161    356000  0x2cdadc8ee4f6c83e  |  3136K  0.16797   0.7924    0.79s  |     21:01:51   0.61%  |
|  Nov 16  19:37:11  |  M57885161    357000  0xbb3a009e3e3de19d  |  3136K  0.16016   0.8034    0.80s  |     21:00:27   0.61%  |
|  Nov 16  19:37:12  |  M57885161    358000  0x6d887f925885a3de  |  3136K  0.16406   0.7992    0.79s  |     20:59:03   0.61%  |
|  Nov 16  19:37:17  |  M57885161    359000  0x0adc87a09a62ce6d  |  3136K  0.17188   4.7653    4.76s  |     21:08:16   0.62%  |
|  Nov 16  19:37:18  |  M57885161    360000  0xab10b38e0069070d  |  3136K  0.16797   0.7875    0.78s  |     21:06:49   0.62%  |
|  Nov 16  19:37:19  |  M57885161    361000  0x90271cb4f8068d8f  |  3136K  0.16797   1.0607    1.06s  |     21:06:06   0.62%  |
|  Nov 16  19:37:20  |  M57885161    362000  0xa0694fc6874b293c  |  3136K  0.16406   0.7876    0.78s  |     21:04:40   0.62%  |
|  Nov 16  19:37:20  |  M57885161    363000  0x2d56a86f9bc2855e  |  3136K  0.16406   0.7908    0.79s  |     21:03:14   0.62%  |
|  Nov 16  19:37:21  |  M57885161    364000  0xfa7d3259a1182fe5  |  3136K  0.16406   0.7946    0.79s  |     21:01:50   0.62%  |
|  Nov 16  19:37:22  |  M57885161    365000  0xc2d445b8ce279c54  |  3136K  0.15625   0.7976    0.79s  |     21:00:27   0.63%  |

------------------------------------------------------------------
seems to low power cumsumption of GPU
If going to work on. I use CUDAlucus instead of PRP (gpuowl)
Attached Thumbnails
Click image for larger version

Name:	CUDA LUCUS on known prime.gif
Views:	16
Size:	29.0 KB
ID:	27633  

Last fiddled with by VBCurtis on 2022-11-16 at 16:40 Reason: added code block
yuki0831 is offline   Reply With Quote
Old 2022-11-16, 18:06   #2833
storm5510
Random Account
 
storm5510's Avatar
 
Aug 2009
Not U. + S.A.

2×7×181 Posts
Default

Quote:
Originally Posted by kriesel View Post
Please reconsider. A PRP-C result is definitely composite, no "probably" about it. In the rare case of PRP-P (or LL-P) that is not a software bug, multiple LL tests must be run to confirm the newly discovered Mersenne prime. We haven't needed to do that in nearly four years now.

Code:
Primality test     Error rate at ~100M    Error rate at ~100Mdigit    Effort to prove a composite
LL                        2%                         20%                      2.04 - 2.5
PRP/GEC                 ~0ppm                      ~0ppm                         2.00
PRP/GEC/proof           ~0ppm                      ~0ppm                <1.01 (~1+1/2proofpower)
Any time someone runs an LL first test, it is essentially wasted cycles. It is quicker and more reliable to double check an LL first test's Mersenne number with PRP/GEC/proof (effort ~1.01) than with an additional LL DC, & TC & QC when needed (effort ~1.04 at wavefront, increasing to ~+1.50 at 100Mdigit and worsening at longer run times for higher exponents).

PRP with GEC is far more reliable than LL with every available error check for LL. Error rate of PRP/GEC is essentially zero, orders of magnitude lower error rate than LL in practice on real hardware. PRP with proof generation means primality can be certainly determined composite for the overwhelming majority that are composite.

PRP with proof generation means a Mersenne number can be ruled out as a prime with effort < 1.01 primality tests (proof power 8 or higher). PRP with GEC but without proof takes two PRP runs, which will have extremely low error rate so require ~2.00 primality tests effort. Due to the typical LL error rate of 2%/test, LL needs 2.04 primality tests on average, to show a Mersenne number composite, at more than double the cost and with less certainty than PRP first test & proof.

PRP with proof generation and cert is also immune to deliberately faking results, even if the person running the Cert assignment issued by the server is the same person that submitted the proof file to the server.

The one drawback of PRP with proof is it needs more disk space, either locally or elsewhere on the network, in which to store many temporary residues. Longer cert time can be traded for reduced space requirements. A proof power 5 still saves ~97% of verification effort while needing ~3% of the temporaries space of a power 10 proof.

See also https://www.mersenneforum.org/showpo...06&postcount=9
It takes roughly 6.5 hours for Prime95 to finish one wavefront P-1 on my best hardware. gpuOwl can do it in a little over 2 hours. So, the choice is obvious.

Most of what is above sails over my head. A good reason to stay away from it in my case. I have a 30.x release of mprime on my Ubuntu box. I have not done much with it though. On the surface, all of this would seem to take a lot of time, like LL does. I do not know that I have the patience for it.

When I built this i7 system back in 2018, I ran a lot of LL-DC's. They took about 36 hours on average to complete. They were much lower magnitude, in the 60M area if memory serves. I did not mind that. Anything taking multiple days, or more, I would rather stay away from.

Most here have far more advanced and recent hardware that myself. I have to stay with what I can run in a reasonable amount of time.
storm5510 is offline   Reply With Quote
Old 2022-11-16, 18:29   #2834
kriesel
 
kriesel's Avatar
 
"TF79LL86GIMPS96gpu17"
Mar 2017
US midwest

34×7×13 Posts
Default

Quote:
Originally Posted by yuki0831 View Post
RTX 4090 cant run PRP, but Cuda-lucas can iterate.


CUDALucas v2.06 64-bit build, compiled May 20 2019 @ 16:50:35
Code:
binary compiled for CUDA   10.10
CUDA runtime version       10.10
CUDA driver version        12.0

---------------- DEVICE 0 ----------------
Device Name               NVIDIA GeForce RTX 4090
ECC Support?              Disabled
Compatibility             8.9
clockRate (MHz)           2520
memClockRate (MHz)        10501
...
Using threads: square 256, splice 128.

Continuing M57885161 @ iteration 277020 with fft length 3136K,  0.48% done

|   Date     Time    |   Test Num     Iter        Residue        |    FFT   Error     ms/It     Time  |       ETA      Done   |
|  Nov 16  19:35:58  |  M57885161    278000  0xcbe0ce0d325a9ae2  |  3136K  0.15625   0.8064    0.79s  |     22:48:58   0.48%  |
|  Nov 16  19:35:59  |  M57885161    279000  0xae4d2eae39a72c0a  |  3136K  0.15625   0.8238    0.82s  |     22:46:52   0.48%  |
...
|  Nov 16  19:37:21  |  M57885161    364000  0xfa7d3259a1182fe5  |  3136K  0.16406   0.7946    0.79s  |     21:01:50   0.62%  |
|  Nov 16  19:37:22  |  M57885161    365000  0xc2d445b8ce279c54  |  3136K  0.15625   0.7976    0.79s  |     21:00:27   0.63%  |

------------------------------------------------------------------
seems to low power consumption of GPU
If going to work on. I use CUDAlucas instead of PRP (gpuowl)
CUDALucas might be working right, or just not detecting errors. (It lacks the Jacobi check, which only detects 50% of errors that elude other checks such as round-off error.) Please only run DC assignments on it. (LL first test is a complete waste of time.) First prove it's working correctly, by reproducing some of the known-good interim LL residues posted in an attachment at https://www.mersenneforum.org/showpo...82&postcount=4 and/or the post at https://www.mersenneforum.org/showpo...4&postcount=12
kriesel is online now   Reply With Quote
Old 2022-11-16, 21:22   #2835
Magellan3s
 
Mar 2022
Earth

5×23 Posts
Default

Quote:
Originally Posted by yuki0831 View Post
RTX 4090 cant run PRP,but Cuda-lucus can iterate.


CUDALucas v2.06 64-bit build, compiled May 20 2019 @ 16:50:35
Code:
binary compiled for CUDA   10.10
CUDA runtime version       10.10
CUDA driver version        12.0

---------------- DEVICE 0 ----------------
Device Name               NVIDIA GeForce RTX 4090
ECC Support?              Disabled
Compatibility             8.9
clockRate (MHz)           2520
memClockRate (MHz)        10501
totalGlobalMem            25756565504
totalConstMem             65536
l2CacheSize               75497472
sharedMemPerBlock         49152
regsPerBlock              65536
warpSize                  32
memPitch                  2147483647
maxThreadsPerBlock        1024
maxThreadsPerMP           1536
multiProcessorCount       128
maxThreadsDim[3]          1024,1024,64
maxGridSize[3]            2147483647,65535,65535
textureAlignment          512
deviceOverlap             1
pciDeviceID               0
pciBusID                  1

You may experience a small delay on 1st startup to due to Just-in-Time Compilation

Using threads: square 256, splice 128.

Continuing M57885161 @ iteration 277020 with fft length 3136K,  0.48% done

|   Date     Time    |   Test Num     Iter        Residue        |    FFT   Error     ms/It     Time  |       ETA      Done   |
|  Nov 16  19:35:58  |  M57885161    278000  0xcbe0ce0d325a9ae2  |  3136K  0.15625   0.8064    0.79s  |     22:48:58   0.48%  |
|  Nov 16  19:35:59  |  M57885161    279000  0xae4d2eae39a72c0a  |  3136K  0.15625   0.8238    0.82s  |     22:46:52   0.48%  |
|  Nov 16  19:36:00  |  M57885161    280000  0x678b32b35f88d73d  |  3136K  0.15625   0.8025    0.80s  |     22:44:42   0.48%  |
|  Nov 16  19:36:01  |  M57885161    281000  0xd1efe3cfd147c085  |  3136K  0.15625   1.0704    1.07s  |     22:43:28   0.48%  |
|  Nov 16  19:36:02  |  M57885161    282000  0x714d25f8d37cf836  |  3136K  0.15234   0.7911    0.79s  |     22:41:18   0.48%  |
|  Nov 16  19:36:03  |  M57885161    283000  0xa4bd8bc9244b8b28  |  3136K  0.15625   0.7874    0.78s  |     22:39:08   0.48%  |
|  Nov 16  19:36:04  |  M57885161    284000  0x0becc6cf5e8fcc44  |  3136K  0.15625   0.7891    0.78s  |     22:36:59   0.49%  |
|  Nov 16  19:36:04  |  M57885161    285000  0xf10ac139a4525617  |  3136K  0.14844   0.7908    0.79s  |     22:34:51   0.49%  |
|  Nov 16  19:36:05  |  M57885161    286000  0x2034bd93db568f5f  |  3136K  0.17188   0.7919    0.79s  |     22:32:45   0.49%  |
|  Nov 16  19:36:06  |  M57885161    287000  0x219f109a761009cd  |  3136K  0.14844   0.7983    0.79s  |     22:30:40   0.49%  |
|  Nov 16  19:36:07  |  M57885161    288000  0x466e03a991973c16  |  3136K  0.15039   0.7978    0.79s  |     22:28:37   0.49%  |
|  Nov 16  19:36:07  |  M57885161    289000  0x363ab3c286190751  |  3136K  0.16406   0.7963    0.79s  |     22:26:33   0.49%  |
|  Nov 16  19:36:09  |  M57885161    290000  0x4f51138c1f7f6301  |  3136K  0.15625   0.7981    0.79s  |     22:24:32   0.50%  |
|  Nov 16  19:36:09  |  M57885161    291000  0x47d0933bf7609619  |  3136K  0.17188   1.0655    1.06s  |     22:23:24   0.50%  |
|  Nov 16  19:36:10  |  M57885161    292000  0xf7956adfe310f162  |  3136K  0.15625   0.7806    0.78s  |     22:21:20   0.50%  |
|  Nov 16  19:36:11  |  M57885161    293000  0xd1876d7e5052e366  |  3136K  0.15625   0.7878    0.78s  |     22:19:18   0.50%  |
|  Nov 16  19:36:12  |  M57885161    294000  0x12b2c2dce3f0d96a  |  3136K  0.17188   0.7858    0.78s  |     22:17:17   0.50%  |
|  Nov 16  19:36:12  |  M57885161    295000  0x04c641d7f906f863  |  3136K  0.16699   0.7795    0.77s  |     22:15:15   0.50%  |
|   Date     Time    |   Test Num     Iter        Residue        |    FFT   Error     ms/It     Time  |       ETA      Done   |
|  Nov 16  19:36:13  |  M57885161    296000  0xcc2487fa86bbf9db  |  3136K  0.17188   0.7794    0.77s  |     22:13:14   0.51%  |
|  Nov 16  19:36:14  |  M57885161    297000  0x929084c59e172141  |  3136K  0.15625   0.7810    0.78s  |     22:11:15   0.51%  |
|  Nov 16  19:36:15  |  M57885161    298000  0xa51033a6780ab4d0  |  3136K  0.16406   0.7778    0.77s  |     22:09:15   0.51%  |
|  Nov 16  19:36:16  |  M57885161    299000  0x2f3ba2a9df8a1e88  |  3136K  0.17969   0.7825    0.78s  |     22:07:17   0.51%  |
|  Nov 16  19:36:17  |  M57885161    300000  0x4332497b4eefcf79  |  3136K  0.15273   0.7900    0.79s  |     22:05:22   0.51%  |
|  Nov 16  19:36:17  |  M57885161    301000  0x3ca858e58ecb6497  |  3136K  0.15820   1.0687    1.06s  |     22:04:21   0.52%  |
|  Nov 16  19:36:18  |  M57885161    302000  0xad2b7c3bb6afbb76  |  3136K  0.15625   0.7892    0.78s  |     22:02:26   0.52%  |
|  Nov 16  19:36:19  |  M57885161    303000  0xc06b0569ac6a5b53  |  3136K  0.17969   0.7945    0.79s  |     22:00:34   0.52%  |
|  Nov 16  19:36:24  |  M57885161    304000  0xd3e2d7502d321f14  |  3136K  0.16406   5.0163    5.01s  |     22:12:04   0.52%  |
|  Nov 16  19:36:25  |  M57885161    305000  0xd772dc54351e7188  |  3136K  0.15625   0.8012    0.80s  |     22:10:12   0.52%  |
|  Nov 16  19:36:26  |  M57885161    306000  0x4288eb5692301fbe  |  3136K  0.15234   0.7904    0.79s  |     22:08:18   0.52%  |
|  Nov 16  19:36:26  |  M57885161    307000  0x2ed247b622866dc2  |  3136K  0.15625   0.7952    0.79s  |     22:06:25   0.53%  |
|  Nov 16  19:36:27  |  M57885161    308000  0x5a3c25644778eacb  |  3136K  0.16406   0.7976    0.79s  |     22:04:34   0.53%  |
|  Nov 16  19:36:28  |  M57885161    309000  0x15b198b6bf3f6e3c  |  3136K  0.15723   0.7905    0.79s  |     22:02:43   0.53%  |
|  Nov 16  19:36:29  |  M57885161    310000  0x059d1c9593b10de5  |  3136K  0.15820   0.7833    0.78s  |     22:00:51   0.53%  |
|  Nov 16  19:36:30  |  M57885161    311000  0xf22b8762e3d0abfb  |  3136K  0.16406   1.0625    1.06s  |     21:59:51   0.53%  |
|  Nov 16  19:36:31  |  M57885161    312000  0x308e63c9a234bd02  |  3136K  0.16406   0.7845    0.78s  |     21:58:00   0.53%  |
|  Nov 16  19:36:31  |  M57885161    313000  0x75fbc5b8df3a3623  |  3136K  0.15918   0.7815    0.78s  |     21:56:10   0.54%  |
|   Date     Time    |   Test Num     Iter        Residue        |    FFT   Error     ms/It     Time  |       ETA      Done   |
|  Nov 16  19:36:32  |  M57885161    314000  0x8ed3cdea870b0522  |  3136K  0.15625   0.7813    0.78s  |     21:54:20   0.54%  |
|  Nov 16  19:36:33  |  M57885161    315000  0xc5ebfe0aa8032ed9  |  3136K  0.17578   0.7820    0.78s  |     21:52:30   0.54%  |
|  Nov 16  19:36:34  |  M57885161    316000  0xae4cd8c05f6115f3  |  3136K  0.15820   0.7828    0.78s  |     21:50:42   0.54%  |
|  Nov 16  19:36:35  |  M57885161    317000  0x585f6932fa9b94d6  |  3136K  0.15820   0.7802    0.78s  |     21:48:54   0.54%  |
|  Nov 16  19:36:35  |  M57885161    318000  0x1d67abbc3a6c5334  |  3136K  0.17188   0.7846    0.78s  |     21:47:07   0.54%  |
|  Nov 16  19:36:36  |  M57885161    319000  0xc5190142b9332ea1  |  3136K  0.15625   0.7822    0.78s  |     21:45:21   0.55%  |
|  Nov 16  19:36:37  |  M57885161    320000  0xee0f3a7707935e5b  |  3136K  0.16406   0.7800    0.78s  |     21:43:35   0.55%  |
|  Nov 16  19:36:38  |  M57885161    321000  0xbb9f4aa2f72de99d  |  3136K  0.15625   1.0530    1.05s  |     21:42:39   0.55%  |
|  Nov 16  19:36:39  |  M57885161    322000  0x755c62bd416eac4e  |  3136K  0.15234   0.7955    0.79s  |     21:40:56   0.55%  |
|  Nov 16  19:36:40  |  M57885161    323000  0x8dc2a016db4d6ba2  |  3136K  0.17188   0.7991    0.79s  |     21:39:16   0.55%  |
|  Nov 16  19:36:40  |  M57885161    324000  0x6edbef666a3725e6  |  3136K  0.16406   0.7977    0.79s  |     21:37:35   0.55%  |
|  Nov 16  19:36:41  |  M57885161    325000  0x70fdfc9380ce9d49  |  3136K  0.16406   0.8006    0.80s  |     21:35:56   0.56%  |
|  Nov 16  19:36:42  |  M57885161    326000  0xc64234e82e227b76  |  3136K  0.16797   0.8055    0.80s  |     21:34:18   0.56%  |
|  Nov 16  19:36:43  |  M57885161    327000  0xa7a41ce0c8529a52  |  3136K  0.15625   0.7962    0.79s  |     21:32:39   0.56%  |
|  Nov 16  19:36:44  |  M57885161    328000  0xea02b43e37d0d8e0  |  3136K  0.15625   0.7971    0.79s  |     21:31:00   0.56%  |
|  Nov 16  19:36:44  |  M57885161    329000  0xd7d3a67d5eb5d18a  |  3136K  0.15820   0.8018    0.80s  |     21:29:24   0.56%  |
|  Nov 16  19:36:45  |  M57885161    330000  0xdd2afd1922b7f066  |  3136K  0.16211   0.7949    0.79s  |     21:27:46   0.57%  |
|  Nov 16  19:36:46  |  M57885161    331000  0xe56e7eea11e1dec2  |  3136K  0.17188   1.0773    1.07s  |     21:26:59   0.57%  |
|   Date     Time    |   Test Num     Iter        Residue        |    FFT   Error     ms/It     Time  |       ETA      Done   |
|  Nov 16  19:36:47  |  M57885161    332000  0x97b714bcc595281d  |  3136K  0.17188   0.7989    0.79s  |     21:25:23   0.57%  |
|  Nov 16  19:36:48  |  M57885161    333000  0x706e5a2c18fdb1c8  |  3136K  0.18750   0.7940    0.79s  |     21:23:47   0.57%  |
|  Nov 16  19:36:49  |  M57885161    334000  0xc45cc19cccc7c685  |  3136K  0.17188   0.7884    0.78s  |     21:22:11   0.57%  |
|  Nov 16  19:36:49  |  M57885161    335000  0x78268d4e2471e1ab  |  3136K  0.17188   0.7961    0.79s  |     21:20:36   0.57%  |
|  Nov 16  19:36:50  |  M57885161    336000  0xca4242603357908c  |  3136K  0.15625   0.7934    0.79s  |     21:19:02   0.58%  |
|  Nov 16  19:36:51  |  M57885161    337000  0x0cd88ed23ba5f828  |  3136K  0.15625   0.7962    0.79s  |     21:17:28   0.58%  |
|  Nov 16  19:36:52  |  M57885161    338000  0x474d2323354d95e2  |  3136K  0.16406   0.7937    0.79s  |     21:15:55   0.58%  |
|  Nov 16  19:36:53  |  M57885161    339000  0xe99454ec5989f399  |  3136K  0.16406   0.8022    0.80s  |     21:14:24   0.58%  |
|  Nov 16  19:36:54  |  M57885161    340000  0x5501bbab37c0ad02  |  3136K  0.16406   0.8011    0.80s  |     21:12:53   0.58%  |
|  Nov 16  19:36:54  |  M57885161    341000  0x9529e56c7295f7db  |  3136K  0.15625   1.0705    1.07s  |     21:12:08   0.58%  |
|  Nov 16  19:36:55  |  M57885161    342000  0x265b0c9432d32428  |  3136K  0.17188   0.8064    0.80s  |     21:10:39   0.59%  |
|  Nov 16  19:36:56  |  M57885161    343000  0x299a8cf366a86436  |  3136K  0.16406   0.7974    0.79s  |     21:09:09   0.59%  |
|  Nov 16  19:36:57  |  M57885161    344000  0x8139a466ba5006ea  |  3136K  0.16016   0.7990    0.79s  |     21:07:40   0.59%  |
|  Nov 16  19:36:58  |  M57885161    345000  0xdfe7c53fe764be6d  |  3136K  0.15625   0.8009    0.80s  |     21:06:11   0.59%  |
|  Nov 16  19:36:58  |  M57885161    346000  0x6b35184501596b83  |  3136K  0.15820   0.8005    0.80s  |     21:04:43   0.59%  |
|  Nov 16  19:36:59  |  M57885161    347000  0xd2a6ffe0eee8b2ae  |  3136K  0.15625   0.8027    0.80s  |     21:03:16   0.59%  |
|  Nov 16  19:37:00  |  M57885161    348000  0x7710c124302c2b1e  |  3136K  0.15625   0.8137    0.81s  |     21:01:51   0.60%  |
|  Nov 16  19:37:05  |  M57885161    349000  0xf49b9775e57bd3d1  |  3136K  0.16406   4.7653    4.76s  |     21:11:20   0.60%  |
|   Date     Time    |   Test Num     Iter        Residue        |    FFT   Error     ms/It     Time  |       ETA      Done   |
|  Nov 16  19:37:06  |  M57885161    350000  0x0c5e8318e5fbc827  |  3136K  0.18750   0.7934    0.79s  |     21:09:51   0.60%  |
|  Nov 16  19:37:07  |  M57885161    351000  0xd67a69f26f12923f  |  3136K  0.15938   1.0702    1.07s  |     21:09:08   0.60%  |
|  Nov 16  19:37:08  |  M57885161    352000  0x4f4da146fc6f4deb  |  3136K  0.15625   0.7872    0.78s  |     21:07:39   0.60%  |
|  Nov 16  19:37:08  |  M57885161    353000  0x8ed9e9fbb3461476  |  3136K  0.16406   0.7843    0.78s  |     21:06:10   0.60%  |
|  Nov 16  19:37:09  |  M57885161    354000  0x2cfa8dab340f4d66  |  3136K  0.17969   0.7918    0.79s  |     21:04:42   0.61%  |
|  Nov 16  19:37:10  |  M57885161    355000  0xd8c32be888059057  |  3136K  0.15625   0.8050    0.80s  |     21:03:17   0.61%  |
|  Nov 16  19:37:11  |  M57885161    356000  0x2cdadc8ee4f6c83e  |  3136K  0.16797   0.7924    0.79s  |     21:01:51   0.61%  |
|  Nov 16  19:37:11  |  M57885161    357000  0xbb3a009e3e3de19d  |  3136K  0.16016   0.8034    0.80s  |     21:00:27   0.61%  |
|  Nov 16  19:37:12  |  M57885161    358000  0x6d887f925885a3de  |  3136K  0.16406   0.7992    0.79s  |     20:59:03   0.61%  |
|  Nov 16  19:37:17  |  M57885161    359000  0x0adc87a09a62ce6d  |  3136K  0.17188   4.7653    4.76s  |     21:08:16   0.62%  |
|  Nov 16  19:37:18  |  M57885161    360000  0xab10b38e0069070d  |  3136K  0.16797   0.7875    0.78s  |     21:06:49   0.62%  |
|  Nov 16  19:37:19  |  M57885161    361000  0x90271cb4f8068d8f  |  3136K  0.16797   1.0607    1.06s  |     21:06:06   0.62%  |
|  Nov 16  19:37:20  |  M57885161    362000  0xa0694fc6874b293c  |  3136K  0.16406   0.7876    0.78s  |     21:04:40   0.62%  |
|  Nov 16  19:37:20  |  M57885161    363000  0x2d56a86f9bc2855e  |  3136K  0.16406   0.7908    0.79s  |     21:03:14   0.62%  |
|  Nov 16  19:37:21  |  M57885161    364000  0xfa7d3259a1182fe5  |  3136K  0.16406   0.7946    0.79s  |     21:01:50   0.62%  |
|  Nov 16  19:37:22  |  M57885161    365000  0xc2d445b8ce279c54  |  3136K  0.15625   0.7976    0.79s  |     21:00:27   0.63%  |

------------------------------------------------------------------
seems to low power cumsumption of GPU
If going to work on. I use CUDAlucus instead of PRP (gpuowl)

I would definitely recommend getting GPUOWL working if possible. Here is an older generation RTX 3080ti running that same benchmark.

Quote:
Originally Posted by Magellan3s View Post
GPU is an EVGA 3080ti FTW3
OS is Linux 20.04.4

Slight GPU Overclock @
+200 MHZ +1000 Mhz Memory




Code:
jesus@Magellan:~/gpuowl-6$ ./gpuowl -prp 57885161 -iters 30000
2022-04-19 10:51:02 gpuowl 
2022-04-19 10:51:02 config: -user Magallan3s -cpu Magellan -maxAlloc 10500M -yield
2022-04-19 10:51:02 config: -prp 57885161 -iters 30000 
2022-04-19 10:51:02 device 0, unique id ''
2022-04-19 10:51:02 Magellan 57885161 FFT: 3M 1K:6:256 (18.40 bpw)
2022-04-19 10:51:02 Magellan Expected maximum carry32: 42500000
2022-04-19 10:51:02 Magellan OpenCL args "-DEXP=57885161u -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=6u -DPM1=0 -DMAX_ACCURACY=1 -DWEIGHT_STEP_MINUS_1=0x1.07673850f37p-1 -DIWEIGHT_STEP_MINUS_1=-0x1.5bd9e39e14a3dp-2  -cl-unsafe-math-optimizations -cl-std=CL2.0 -cl-finite-math-only "
2022-04-19 10:51:02 Magellan 

2022-04-19 10:51:02 Magellan OpenCL compilation in 0.00 s
2022-04-19 10:51:03 Magellan 57885161 OK    30000 loaded: blockSize 400, fe1565094c7f7b47
2022-04-19 10:51:03 Magellan validating proof residues for power 8
2022-04-19 10:51:03 Magellan Proof using power 8
2022-04-19 10:51:04 Magellan 57885161 OK    30800   0.05%; 1194 us/it; ETA 0d 19:11; 4f153add2832ca8a (check 0.50s)
2022-04-19 10:51:38 Magellan Stopping, please wait..
2022-04-19 10:51:38 Magellan 57885161 OK    60000   0.10%; 1148 us/it; ETA 0d 18:27; 175901ec29adfa87 (check 0.47s)
2022-04-19 10:51:39 Magellan Exiting because "stop requested"
2022-04-19 10:51:39 Magellan Bye

Magellan3s is offline   Reply With Quote
Old 2022-11-17, 02:07   #2836
kriesel
 
kriesel's Avatar
 
"TF79LL86GIMPS96gpu17"
Mar 2017
US midwest

1CCB16 Posts
Default

[QUOTE=yuki0831;617911 I use CUDAlucus[/QUOTE]Run the selftest.
Do you get this?
Code:
Starting self test M57885161 fft length = 3200K
Iteration 10000 / 57885161, 0x76c27556683cd84d, 3200K, CUDALucas v2.06beta, error = 0.11133, real: 0:27, 2.6851 ms/iter
This residue is correct.

Last fiddled with by kriesel on 2022-11-17 at 02:08
kriesel is online now   Reply With Quote
Old 2022-11-17, 03:31   #2837
yuki0831
 
"Yuki@karoushi"
Feb 2020
Japan, Chiba pref

2·3·5 Posts
Cool Exp57885161 is prime

Ok. finish the task.

CUDALucas v2.06 64-bit build, compiled May 20 2019 @ 16:50:35

binary compiled for CUDA 10.10
CUDA runtime version 10.10
CUDA driver version 12.0

---------------- DEVICE 0 ----------------
Device Name NVIDIA GeForce RTX 4090
ECC Support? Disabled
Compatibility 8.9
clockRate (MHz) 2520
memClockRate (MHz) 10501
totalGlobalMem 25756565504
totalConstMem 65536
l2CacheSize 75497472
sharedMemPerBlock 49152
regsPerBlock 65536
warpSize 32
memPitch 2147483647
maxThreadsPerBlock 1024
maxThreadsPerMP 1536
multiProcessorCount 128
maxThreadsDim[3] 1024,1024,64
maxGridSize[3] 2147483647,65535,65535
textureAlignment 512
deviceOverlap 1
pciDeviceID 0
pciBusID 1

You may experience a small delay on 1st startup to due to Just-in-Time Compilation

Using threads: square 256, splice 128.

Continuing M57885161 @ iteration 55000001 with fft length 3136K, 95.02% done

| Date Time | Test Num Iter Residue | FFT Error ms/It Time | ETA Done |
| Nov 17 11:50:04 | M57885161 55500000 0x2db660ec951cce7b | 3136K 0.19531 0.7828 391.40s | 30:59 95.87% |
| Nov 17 11:56:38 | M57885161 56000000 0xcfaa4c0630ed7995 | 3136K 0.20703 0.7877 393.85s | 24:29 96.74% |
| Nov 17 12:03:14 | M57885161 56500000 0x8f507f080c29dfb8 | 3136K 0.20313 0.7912 395.61s | 18:00 97.60% |
| Nov 17 12:09:47 | M57885161 57000000 0x6af2aa160ae1e879 | 3136K 0.19531 0.7863 393.15s | 11:30 98.47% |
| Nov 17 12:16:17 | M57885161 57500000 0xdb3b855f331709c5 | 3136K 0.18750 0.7808 390.41s | 5:00 99.33% |
M( 57885161 )P, n = 3136K, CUDALucas v2.06, estimated total time = 12:32:28

M57885161 is known to be prime. My RTX 4090 also says prime.
I consider running PRP on gpuowl. It tooks several days to stable crunch.
yuki0831 is offline   Reply With Quote
Old 2022-11-18, 03:10   #2838
moebius
 
moebius's Avatar
 
Jul 2009
Germany

67110 Posts
Default

Quote:
Originally Posted by moebius View Post
Update: gpuOwl benchmarks online (new link)
There are now 78 gpus/igps in the list
Now are 135 values for the estimated gpuOwl performance in the table.
moebius is offline   Reply With Quote
Reply

Thread Tools


Similar Threads
Thread Thread Starter Forum Replies Last Post
mfakto: an OpenCL program for Mersenne prefactoring Bdot GPU Computing 1719 2023-01-16 15:51
GPUOWL AMD Windows OpenCL issues xx005fs GpuOwl 0 2019-07-26 21:37
Testing an expression for primality 1260 Software 17 2015-08-28 01:35
Testing Mersenne cofactors for primality? CRGreathouse Computer Science & Computational Number Theory 18 2013-06-08 19:12
Primality-testing program with multiple types of moduli (PFGW-related) Unregistered Information & Answers 4 2006-10-04 22:38

All times are UTC. The time now is 04:11.


Mon Feb 6 04:11:49 UTC 2023 up 172 days, 1:40, 1 user, load averages: 0.77, 0.90, 0.96

Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2023, Jelsoft Enterprises Ltd.

This forum has received and complied with 0 (zero) government requests for information.

Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation.
A copy of the license is included in the FAQ.

≠ ± ∓ ÷ × · − √ ‰ ⊗ ⊕ ⊖ ⊘ ⊙ ≤ ≥ ≦ ≧ ≨ ≩ ≺ ≻ ≼ ≽ ⊏ ⊐ ⊑ ⊒ ² ³ °
∠ ∟ ° ≅ ~ ‖ ⟂ ⫛
≡ ≜ ≈ ∝ ∞ ≪ ≫ ⌊⌋ ⌈⌉ ∘ ∏ ∐ ∑ ∧ ∨ ∩ ∪ ⨀ ⊕ ⊗ 𝖕 𝖖 𝖗 ⊲ ⊳
∅ ∖ ∁ ↦ ↣ ∩ ∪ ⊆ ⊂ ⊄ ⊊ ⊇ ⊃ ⊅ ⊋ ⊖ ∈ ∉ ∋ ∌ ℕ ℤ ℚ ℝ ℂ ℵ ℶ ℷ ℸ 𝓟
¬ ∨ ∧ ⊕ → ← ⇒ ⇐ ⇔ ∀ ∃ ∄ ∴ ∵ ⊤ ⊥ ⊢ ⊨ ⫤ ⊣ … ⋯ ⋮ ⋰ ⋱
∫ ∬ ∭ ∮ ∯ ∰ ∇ ∆ δ ∂ ℱ ℒ ℓ
𝛢𝛼 𝛣𝛽 𝛤𝛾 𝛥𝛿 𝛦𝜀𝜖 𝛧𝜁 𝛨𝜂 𝛩𝜃𝜗 𝛪𝜄 𝛫𝜅 𝛬𝜆 𝛭𝜇 𝛮𝜈 𝛯𝜉 𝛰𝜊 𝛱𝜋 𝛲𝜌 𝛴𝜎𝜍 𝛵𝜏 𝛶𝜐 𝛷𝜙𝜑 𝛸𝜒 𝛹𝜓 𝛺𝜔