mersenneforum.org - gpuOwL: an OpenCL program for Mersenne primality testing

mersenneforum.org (https://www.mersenneforum.org/index.php)

- GpuOwl (https://www.mersenneforum.org/forumdisplay.php?f=171)

- - gpuOwL: an OpenCL program for Mersenne primality testing (https://www.mersenneforum.org/showthread.php?t=22204)

[QUOTE=kriesel;506999]Why?

some clues it goes way back, at[URL="https://github.com/preda/gpuowl"] https://github.com/preda/gpuowl[/URL]
"use opencl 2.0 atomics in carry fused" Jul 27 2018 dd0f2b2
"dont attempt initial CL2.0 compilation anymore" Jan 22 2018 1aee5cc (V1.9?)
"fix opencl 1.x FGT compilation (missing global)" Nov 8 2017 8c2e6d6 (V1.8 or 1.9 time frame)
"add stupid global to pointers everywhere to make it compilable in cl 1.2" Sep 18 2017 d7930ed
"bump version to 1.0; log and result format minor change; persistent c..." Aug 27 2017 676be1c[/QUOTE]

Well, I have a older HD7770 card that doesn't support OpenCL 2.x(funny enough, the rebranded r7 250X does support it.. guess it's just a driver switch) I just remember I was able to run gpuowl on it before.(probably not worth running though considering the electricity cost...)

How difficult would it be to add a version of carryfused which would run on OpenCL 1.x? Old gpus aren't worth much but if that would make it run on Nvidia cards it may be worth doing.

[QUOTE=henryzz;507108]How difficult would it be to add a version of carryfused which would run on OpenCL 1.x? Old gpus aren't worth much but if that would make it run on Nvidia cards it may be worth doing.[/QUOTE]

No, that won't make it run on Nvidia. There are deeper problems with Nvidia's OpenCL than just 1.x vs. 2.x. I've tried in the past to run GpuOwl on an Nvidia GPU, and it failed in funky ways. My take from that was that Nvidia is not interested in fixing their (1.x) OpenCL implementation.

For the past few days I've been running P-1 with GpuOwl (with B1=1M, B2=30M). I'm surprised by the small number of factors found, which seems to be significantly less than the expected 3% - 3.4%. The first suspect is a bug in GpuOwl, particularly in stage2, which would cause it to miss factors. OTOH for all the tests I tried (where I ran GpuOwl on exponents with known factors), the factors were correctly detected in stage2.

Anyway, if anybody finds an exponent with a factor that should be detected (given the bounds) and isn't, that would be proof of a bug and would allow debugging. Until then, I only have a suspicion of a bug in stage2.

[QUOTE=preda;507389]For the past few days I've been running P-1 with GpuOwl (with B1=1M, B2=30M). I'm surprised by the small number of factors found, which seems to be significantly less than the expected 3% - 3.4%. The first suspect is a bug in GpuOwl, particularly in stage2, which would cause it to miss factors. OTOH for all the tests I tried (where I ran GpuOwl on exponents with known factors), the factors were correctly detected in stage2.

Anyway, if anybody finds an exponent with a factor that should be detected (given the bounds) and isn't, that would be proof of a bug and would allow debugging. Until then, I only have a suspicion of a bug in stage2.[/QUOTE]
How many known-factor cases have you run, and what did you find? (See post 811 in this thread for a list of some possible candidates.)

[QUOTE=kriesel;507402]How many known-factor cases have you run, and what did you find? (See post 811 in this thread for a list of some possible candidates.)[/QUOTE]

I've run about 10 from the attached list. All that I've tried were detected correctly.

Here are the factor found results. The ones without AID are test cases of known factors.
[QUOTE]
2019-01-25 22:30:53 vega1 {"exponent":"86014009", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.1"}, "timestamp":"2019-01-25 11:30:53 UTC", "user":"preda", "computer":"vega1", "fft-length":4718592, "B1":10000, "B2":1000000, "factors":["262147231459344118478999"]}
2019-01-26 22:46:37 vega1 {"exponent":"86001449", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.1"}, "timestamp":"2019-01-26 11:46:37 UTC", "user":"preda", "computer":"vega1", "fft-length":4718592, "B1":10000, "B2":300000, "factors":["64262023024984019615711"]}
2019-01-26 22:53:56 vega1 {"exponent":"86001449", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.1"}, "timestamp":"2019-01-26 11:53:56 UTC", "user":"preda", "computer":"vega1", "fft-length":4718592, "B1":20000, "B2":1000000, "factors":["64262023024984019615711"]}
2019-01-26 23:00:41 vega1 {"exponent":"86001449", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.1"}, "timestamp":"2019-01-26 12:00:41 UTC", "user":"preda", "computer":"vega1", "fft-length":4718592, "B1":30000, "B2":1000000, "factors":["64262023024984019615711"]}
2019-01-26 23:07:37 vega1 {"exponent":"86001449", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.1"}, "timestamp":"2019-01-26 12:07:37 UTC", "user":"preda", "computer":"vega1", "fft-length":4718592, "B1":30000, "B2":1000000, "factors":["64262023024984019615711"]}
2019-01-29 15:00:59 vega1 {"exponent":"90389279", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.1"}, "timestamp":"2019-01-29 04:00:59 UTC", "user":"preda", "computer":"vega1", "aid":"446A4C8D876E30929CFF650BC1510296", "fft-length":5242880, "B1":1000000, "B2":30000000, "factors":["596345629997606032958593"]}
2019-01-30 15:27:56 vega1 {"exponent":"90399973", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.2"}, "timestamp":"2019-01-30 04:27:56 UTC", "user":"preda", "computer":"vega1", "aid":"D551E55210FEDE3B539CAC488B140DC0", "fft-length":5242880, "B1":1000000, "B2":30000000, "factors":["2691899164164806875763639"]}
2019-01-30 19:14:29 vega1 {"exponent":"90555943", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.2"}, "timestamp":"2019-01-30 08:14:29 UTC", "user":"preda", "computer":"vega1", "fft-length":5242880, "B1":1000000, "B2":30000000, "factors":["2849951345359023265136617"]}

2019-01-14 23:57:42 vega0 {"exponent":"86005021", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.0"}, "timestamp":"2019-01-14 12:57:42 UTC", "user":"preda", "computer":"vega0", "fft-length":4718592, "B1":"20000, "B2":"600000, "factors":["43592319559794136631809"]}
2019-01-26 23:42:18 vega0 {"exponent":"86896181", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.1"}, "timestamp":"2019-01-26 12:42:18 UTC", "user":"preda", "computer":"vega0", "fft-length":5242880, "B1":250000, "B2":1000000, "factors":["27645613040037353343863"]}
2019-01-28 04:01:43 vega0 {"exponent":"86897623", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.1"}, "timestamp":"2019-01-27 17:01:43 UTC", "user":"preda", "computer":"vega0", "fft-length":5242880, "B1":300000, "B2":10000000, "factors":["184649453011014777569639"]}
2019-01-29 01:38:33 vega0 {"exponent":"90547781", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.2"}, "timestamp":"2019-01-28 14:38:33 UTC", "user":"preda", "computer":"vega0", "fft-length":5242880, "B1":500000, "B2":15000000, "factors":["171971868822535851152989810327"]}
2019-01-30 20:38:52 vega0 {"exponent":"90391841", "worktype":"PM1", "status":"F", "program":{"name":"gpuowl", "version":"6.2"}, "timestamp":"2019-01-30 09:38:52 UTC", "user":"preda", "computer":"vega0", "fft-length":5242880, "B1":1000000, "B2":30000000, "factors":["1704260124325096144766123992129"]}
[/QUOTE]

GPU OWL crashes upon starting?

I recently updated to the newest adrenaline 19.2.1 driver and no matter what version of GPUOWL I use it would just crash and freeze my system when my GPU is 100% stable in anything else. What can I do to resolve that?

[QUOTE=xx005fs;507489]I recently updated to the newest adrenaline 19.2.1 driver and no matter what version of GPUOWL I use it would just crash and freeze my system when my GPU is 100% stable in anything else. What can I do to resolve that?[/QUOTE]That must be frustrating. Why upgrade to it? What OS version? What clues are present in system logs? Could you downgrade the driver?

I'm running drver version 18.10.2 on Win7 x64 and gpuowl runs for weeks on it. I've found that usually driver upgrades reduce gpuowl performance, so I delay upgrades.

[QUOTE=kriesel;507496]That must be frustrating. Why upgrade to it? What OS version? What clues are present in system logs? Could you downgrade the driver?

I'm running drver version 18.10.2 on Win7 x64 and gpuowl runs for weeks on it. I've found that usually driver upgrades reduce gpuowl performance, so I delay upgrades.[/QUOTE]

I was originally using 18.9.1 driver which was perfectly fine. I reckon I wanted to update the driver to check out the new features, and that's when I realized it broke. Downgraded driver and everything was okay again. I am using windows 10 home with the newest update and there is nothing in the logs beside just saying what FFT is used. It doesn't even pass the first 800 iters initial test before freezing my entire system. This issue was originally there when I first upgraded to adrenaline 2019 and 2018 versions are perfectly okay (FYI).

gpuowl V6.0-b7bb1c3 Win64 build and first takes

Help output:
[CODE]C:\msys64\home\ken\gpuowl-compile\v6.0-b7bb1c3>openowl -h
2019-02-04 23:01:34 gpuowl 6.0-b7bb1c3

Command line options:

-user <name> : specify the user name.
-cpu <name> : specify the hardware name.
-time : display kernel profiling information.
-fft <size> : specify FFT size, such as: 5000K, 4M, +2, -1.
-block <value> : PRP GEC block size. Default 400. Smaller block is slower but detects errors sooner.
-carry long|short : force carry type. Short carry may be faster, but requires high bits/word.
-list fft : display a list of available FFT configurations.
-tf <bit-offset> : enable auto trial factoring before PRP. Pass 0 to bit-offset for default TF depth.
-device <N> : select a specific device:
Ellesmere-36x1266-@28:0.0 Radeon (TM) RX 480 Graphics
gfx804-8x1203-@3:0.0 Radeon 550 Series
[/CODE]fft length list not available without a worktodo file with a valid first entry[CODE]
C:\msys64\home\ken\gpuowl-compile\v6.0-b7bb1c3>openowl -list fft
2019-02-04 23:01:53 gpuowl 6.0-b7bb1c3
2019-02-04 23:01:53 -list fft
2019-02-04 23:01:53 Can't open 'worktodo.txt' (mode 'rb')
2019-02-04 23:01:53 Bye[/CODE]New shorter fft lengths[CODE]
C:\msys64\home\ken\gpuowl-compile\v6.0-b7bb1c3>openowl -list fft
2019-02-04 23:05:21 gpuowl 6.0-b7bb1c3
2019-02-04 23:05:21 -list fft
2019-02-04 23:05:21 FFT 8K [ 0.01M - 0.18M] 64-64
2019-02-04 23:05:21 FFT 24K [ 0.04M - 0.51M] 64-64-3
2019-02-04 23:05:21 FFT 32K [ 0.05M - 0.68M] 64-256 256-64
2019-02-04 23:05:21 FFT 40K [ 0.06M - 0.85M] 64-64-5
2019-02-04 23:05:21 FFT 64K [ 0.10M - 1.34M] 64-512 512-64
2019-02-04 23:05:21 FFT 72K [ 0.11M - 1.50M] 64-64-9
2019-02-04 23:05:21 FFT 96K [ 0.15M - 1.99M] 64-256-3 256-64-3
2019-02-04 23:05:21 FFT 128K [ 0.20M - 2.63M] 1K-64 64-1K 256-256
2019-02-04 23:05:21 FFT 160K [ 0.25M - 3.27M] 64-256-5 256-64-5
2019-02-04 23:05:21 FFT 192K [ 0.29M - 3.91M] 64-512-3 512-64-3
2019-02-04 23:05:21 FFT 256K [ 0.39M - 5.18M] 64-2K 256-512 512-256 2K-64
2019-02-04 23:05:21 FFT 288K [ 0.44M - 5.81M] 64-256-9 256-64-9
2019-02-04 23:05:21 FFT 320K [ 0.49M - 6.44M] 64-512-5 512-64-5
2019-02-04 23:05:21 FFT 384K [ 0.59M - 7.69M] 1K-64-3 64-1K-3 256-256-3
2019-02-04 23:05:21 FFT 512K [ 0.79M - 10.18M] 1K-256 256-1K 512-512 4K-64
2019-02-04 23:05:21 FFT 576K [ 0.88M - 11.42M] 64-512-9 512-64-9
2019-02-04 23:05:21 FFT 640K [ 0.98M - 12.66M] 1K-64-5 64-1K-5 256-256-5
2019-02-04 23:05:21 FFT 768K [ 1.18M - 15.12M] 64-2K-3 256-512-3 512-256-3 2K-64-3
2019-02-04 23:05:21 FFT 1M [ 1.57M - 20.02M] 1K-512 256-2K 512-1K 2K-256
2019-02-04 23:05:21 FFT 1152K [ 1.77M - 22.45M] 1K-64-9 64-1K-9 256-256-9
2019-02-04 23:05:21 FFT 1280K [ 1.97M - 24.88M] 64-2K-5 256-512-5 512-256-5 2K-64-5
2019-02-04 23:05:21 FFT 1536K [ 2.36M - 29.72M] 1K-256-3 256-1K-3 512-512-3 4K-64-3
2019-02-04 23:05:21 FFT 2M [ 3.15M - 39.34M] 1K-1K 512-2K 2K-512 4K-256
2019-02-04 23:05:21 FFT 2304K [ 3.54M - 44.13M] 64-2K-9 256-512-9 512-256-9 2K-64-9
2019-02-04 23:05:21 FFT 2560K [ 3.93M - 48.90M] 1K-256-5 256-1K-5 512-512-5 4K-64-5
2019-02-04 23:05:21 FFT 3M [ 4.72M - 58.41M] 1K-512-3 256-2K-3 512-1K-3 2K-256-3
2019-02-04 23:05:21 FFT 4M [ 6.29M - 77.30M] 1K-2K 2K-1K 4K-512
2019-02-04 23:05:21 FFT 4608K [ 7.08M - 86.70M] 1K-256-9 256-1K-9 512-512-9 4K-64-9
2019-02-04 23:05:21 FFT 5M [ 7.86M - 96.07M] 1K-512-5 256-2K-5 512-1K-5 2K-256-5
2019-02-04 23:05:21 FFT 6M [ 9.44M - 114.74M] 1K-1K-3 512-2K-3 2K-512-3 4K-256-3
2019-02-04 23:05:21 FFT 8M [ 12.58M - 151.83M] 2K-2K 4K-1K
2019-02-04 23:05:21 FFT 9M [ 14.16M - 170.28M] 1K-512-9 256-2K-9 512-1K-9 2K-256-9
2019-02-04 23:05:21 FFT 10M [ 15.73M - 188.68M] 1K-1K-5 512-2K-5 2K-512-5 4K-256-5
2019-02-04 23:05:21 FFT 12M [ 18.87M - 225.32M] 1K-2K-3 2K-1K-3 4K-512-3
2019-02-04 23:05:21 FFT 16M [ 25.17M - 298.13M] 4K-2K
2019-02-04 23:05:21 FFT 18M [ 28.31M - 334.34M] 1K-1K-9 512-2K-9 2K-512-9 4K-256-9
2019-02-04 23:05:21 FFT 20M [ 31.46M - 370.44M] 1K-2K-5 2K-1K-5 4K-512-5
2019-02-04 23:05:21 FFT 24M [ 37.75M - 442.34M] 2K-2K-3 4K-1K-3
2019-02-04 23:05:21 FFT 36M [ 56.62M - 656.22M] 1K-2K-9 2K-1K-9 4K-512-9
2019-02-04 23:05:21 FFT 40M [ 62.91M - 727.03M] 2K-2K-5 4K-1K-5
2019-02-04 23:05:21 FFT 48M [ 75.50M - 868.07M] 4K-2K-3
2019-02-04 23:05:21 FFT 72M [113.25M - 1287.53M] 2K-2K-9 4K-1K-9
2019-02-04 23:05:21 FFT 80M [125.83M - 1426.38M] 4K-2K-5
2019-02-04 23:05:21 FFT 144M [226.49M - 2525.23M] 4K-2K-9
2019-02-04 23:05:21 332220523 FFT 18432K: Width 256x4, Height 256x4, Middle 9; 17.60 bits/word
2019-02-04 23:05:21 using short carry kernels
2019-02-04 23:05:21 Exiting because "No OpenCL device"
2019-02-04 23:05:21 Bye[/CODE]but did not default to device zero and just run afterward.

Exits if smallest fft length is too large for first worktodo entry. (why not comment out first entry, and go on to next?)[CODE]
C:\msys64\home\ken\gpuowl-compile\v6.0-b7bb1c3>openowl -device 0 -user kriesel -cpu condorella/rx-480
2019-02-04 23:17:18 gpuowl 6.0-b7bb1c3
2019-02-04 23:17:18 condorella/rx-480 -device 0 -user kriesel -cpu condorella/rx-480
2019-02-04 23:17:18 condorella/rx-480 11213 FFT 8K: Width 8x8, Height 8x8; 1.37 bits/word
2019-02-04 23:17:18 condorella/rx-480 FFT size too large for exponent (1.37 bits/word).
2019-02-04 23:17:18 condorella/rx-480 Exiting because "FFT size too large"
2019-02-04 23:17:18 condorella/rx-480 Bye[/CODE]Had a problem with 216091 (default, long or short carry):[CODE]
2019-02-04 23:22:47 condorella/rx-480 216091 FFT 24K: Width 8x8, Height 8x8, Middle 3; 8.79 bits/word
2019-02-04 23:22:47 condorella/rx-480 using long carry kernels
2019-02-04 23:22:50 condorella/rx-480 OpenCL compilation in 2510 ms, with "-DEXP=216091u -DWIDTH=64u -DSMALL_HEIGHT=64u -DMIDDLE=3u -
cl-std=CL2.0 "
2019-02-04 23:22:50 condorella/rx-480 216091.owl not found, starting from the beginning.
2019-02-04 23:22:50 condorella/rx-480 216091 EE loaded: 0, blockSize 400, 0000000000000000 (expected 0000000000000003)
2019-02-04 23:22:50 condorella/rx-480 Exiting because "error on load"
2019-02-04 23:22:50 condorella/rx-480 Bye[/CODE]Similar issue with 756839:[CODE]
C:\msys64\home\ken\gpuowl-compile\v6.0-b7bb1c3>openowl -device 0 -user kriesel -cpu condorella/rx-480 -carry long
2019-02-04 23:25:27 gpuowl 6.0-b7bb1c3
2019-02-04 23:25:27 condorella/rx-480 -device 0 -user kriesel -cpu condorella/rx-480 -carry long
2019-02-04 23:25:27 condorella/rx-480 756839 FFT 40K: Width 8x8, Height 8x8, Middle 5; 18.48 bits/word
2019-02-04 23:25:27 condorella/rx-480 using long carry kernels
2019-02-04 23:25:34 condorella/rx-480 OpenCL compilation in 3007 ms, with "-DEXP=756839u -DWIDTH=64u -DSMALL_HEIGHT=64u -DMIDDLE=5u -
cl-std=CL2.0 "
2019-02-04 23:25:34 condorella/rx-480 756839.owl not found, starting from the beginning.
2019-02-04 23:25:34 condorella/rx-480 756839 EE loaded: 0, blockSize 400, 0000000000000000 (expected 0000000000000003)
2019-02-04 23:25:34 condorella/rx-480 Exiting because "error on load"
2019-02-04 23:25:34 condorella/rx-480 Bye

C:\msys64\home\ken\gpuowl-compile\v6.0-b7bb1c3>openowl -device 0 -user kriesel -cpu condorella/rx-480
2019-02-04 23:25:45 gpuowl 6.0-b7bb1c3
2019-02-04 23:25:45 condorella/rx-480 -device 0 -user kriesel -cpu condorella/rx-480
2019-02-04 23:25:45 condorella/rx-480 756839 FFT 40K: Width 8x8, Height 8x8, Middle 5; 18.48 bits/word
2019-02-04 23:25:45 condorella/rx-480 using short carry kernels
2019-02-04 23:25:51 condorella/rx-480 OpenCL compilation in 2980 ms, with "-DEXP=756839u -DWIDTH=64u -DSMALL_HEIGHT=64u -DMIDDLE=5u -
cl-std=CL2.0 "
2019-02-04 23:25:51 condorella/rx-480 756839.owl not found, starting from the beginning.
2019-02-04 23:25:51 condorella/rx-480 756839 EE loaded: 0, blockSize 400, 0000000000000000 (expected 0000000000000003)
2019-02-04 23:25:51 condorella/rx-480 Exiting because "error on load"
2019-02-04 23:25:51 condorella/rx-480 Bye[/CODE]The 4.5M fft length appeared to be a few percent faster than the previous best (V3.8) on RX-480.

[QUOTE=kriesel;507684]Help output:
[CODE]C:\msys64\home\ken\gpuowl-compile\v6.0-b7bb1c3>openowl -h
2019-02-04 23:01:34 gpuowl 6.0-b7bb1c3

Command line options:

-user <name> : specify the user name.
-cpu <name> : specify the hardware name.
-time : display kernel profiling information.
-fft <size> : specify FFT size, such as: 5000K, 4M, +2, -1.
-block <value> : PRP GEC block size. Default 400. Smaller block is slower but detects errors sooner.
-carry long|short : force carry type. Short carry may be faster, but requires high bits/word.
-list fft : display a list of available FFT configurations.
-tf <bit-offset> : enable auto trial factoring before PRP. Pass 0 to bit-offset for default TF depth.
-device <N> : select a specific device:
Ellesmere-36x1266-@28:0.0 Radeon (TM) RX 480 Graphics
gfx804-8x1203-@3:0.0 Radeon 550 Series
[/CODE]fft length list not available without a worktodo file with a valid first entry[CODE]
C:\msys64\home\ken\gpuowl-compile\v6.0-b7bb1c3>openowl -list fft
2019-02-04 23:01:53 gpuowl 6.0-b7bb1c3
2019-02-04 23:01:53 -list fft
2019-02-04 23:01:53 Can't open 'worktodo.txt' (mode 'rb')
2019-02-04 23:01:53 Bye[/CODE]New shorter fft lengths[CODE]
C:\msys64\home\ken\gpuowl-compile\v6.0-b7bb1c3>openowl -list fft
2019-02-04 23:05:21 gpuowl 6.0-b7bb1c3
2019-02-04 23:05:21 -list fft
2019-02-04 23:05:21 FFT 8K [ 0.01M - 0.18M] 64-64
2019-02-04 23:05:21 FFT 24K [ 0.04M - 0.51M] 64-64-3
2019-02-04 23:05:21 FFT 32K [ 0.05M - 0.68M] 64-256 256-64
2019-02-04 23:05:21 FFT 40K [ 0.06M - 0.85M] 64-64-5
2019-02-04 23:05:21 FFT 64K [ 0.10M - 1.34M] 64-512 512-64
2019-02-04 23:05:21 FFT 72K [ 0.11M - 1.50M] 64-64-9
2019-02-04 23:05:21 FFT 96K [ 0.15M - 1.99M] 64-256-3 256-64-3
2019-02-04 23:05:21 FFT 128K [ 0.20M - 2.63M] 1K-64 64-1K 256-256
2019-02-04 23:05:21 FFT 160K [ 0.25M - 3.27M] 64-256-5 256-64-5
2019-02-04 23:05:21 FFT 192K [ 0.29M - 3.91M] 64-512-3 512-64-3
2019-02-04 23:05:21 FFT 256K [ 0.39M - 5.18M] 64-2K 256-512 512-256 2K-64
2019-02-04 23:05:21 FFT 288K [ 0.44M - 5.81M] 64-256-9 256-64-9
2019-02-04 23:05:21 FFT 320K [ 0.49M - 6.44M] 64-512-5 512-64-5
2019-02-04 23:05:21 FFT 384K [ 0.59M - 7.69M] 1K-64-3 64-1K-3 256-256-3
2019-02-04 23:05:21 FFT 512K [ 0.79M - 10.18M] 1K-256 256-1K 512-512 4K-64
2019-02-04 23:05:21 FFT 576K [ 0.88M - 11.42M] 64-512-9 512-64-9
2019-02-04 23:05:21 FFT 640K [ 0.98M - 12.66M] 1K-64-5 64-1K-5 256-256-5
2019-02-04 23:05:21 FFT 768K [ 1.18M - 15.12M] 64-2K-3 256-512-3 512-256-3 2K-64-3
2019-02-04 23:05:21 FFT 1M [ 1.57M - 20.02M] 1K-512 256-2K 512-1K 2K-256
2019-02-04 23:05:21 FFT 1152K [ 1.77M - 22.45M] 1K-64-9 64-1K-9 256-256-9
2019-02-04 23:05:21 FFT 1280K [ 1.97M - 24.88M] 64-2K-5 256-512-5 512-256-5 2K-64-5
2019-02-04 23:05:21 FFT 1536K [ 2.36M - 29.72M] 1K-256-3 256-1K-3 512-512-3 4K-64-3
2019-02-04 23:05:21 FFT 2M [ 3.15M - 39.34M] 1K-1K 512-2K 2K-512 4K-256
2019-02-04 23:05:21 FFT 2304K [ 3.54M - 44.13M] 64-2K-9 256-512-9 512-256-9 2K-64-9
2019-02-04 23:05:21 FFT 2560K [ 3.93M - 48.90M] 1K-256-5 256-1K-5 512-512-5 4K-64-5
2019-02-04 23:05:21 FFT 3M [ 4.72M - 58.41M] 1K-512-3 256-2K-3 512-1K-3 2K-256-3
2019-02-04 23:05:21 FFT 4M [ 6.29M - 77.30M] 1K-2K 2K-1K 4K-512
2019-02-04 23:05:21 FFT 4608K [ 7.08M - 86.70M] 1K-256-9 256-1K-9 512-512-9 4K-64-9
2019-02-04 23:05:21 FFT 5M [ 7.86M - 96.07M] 1K-512-5 256-2K-5 512-1K-5 2K-256-5
2019-02-04 23:05:21 FFT 6M [ 9.44M - 114.74M] 1K-1K-3 512-2K-3 2K-512-3 4K-256-3
2019-02-04 23:05:21 FFT 8M [ 12.58M - 151.83M] 2K-2K 4K-1K
2019-02-04 23:05:21 FFT 9M [ 14.16M - 170.28M] 1K-512-9 256-2K-9 512-1K-9 2K-256-9
2019-02-04 23:05:21 FFT 10M [ 15.73M - 188.68M] 1K-1K-5 512-2K-5 2K-512-5 4K-256-5
2019-02-04 23:05:21 FFT 12M [ 18.87M - 225.32M] 1K-2K-3 2K-1K-3 4K-512-3
2019-02-04 23:05:21 FFT 16M [ 25.17M - 298.13M] 4K-2K
2019-02-04 23:05:21 FFT 18M [ 28.31M - 334.34M] 1K-1K-9 512-2K-9 2K-512-9 4K-256-9
2019-02-04 23:05:21 FFT 20M [ 31.46M - 370.44M] 1K-2K-5 2K-1K-5 4K-512-5
2019-02-04 23:05:21 FFT 24M [ 37.75M - 442.34M] 2K-2K-3 4K-1K-3
2019-02-04 23:05:21 FFT 36M [ 56.62M - 656.22M] 1K-2K-9 2K-1K-9 4K-512-9
2019-02-04 23:05:21 FFT 40M [ 62.91M - 727.03M] 2K-2K-5 4K-1K-5
2019-02-04 23:05:21 FFT 48M [ 75.50M - 868.07M] 4K-2K-3
2019-02-04 23:05:21 FFT 72M [113.25M - 1287.53M] 2K-2K-9 4K-1K-9
2019-02-04 23:05:21 FFT 80M [125.83M - 1426.38M] 4K-2K-5
2019-02-04 23:05:21 FFT 144M [226.49M - 2525.23M] 4K-2K-9
2019-02-04 23:05:21 332220523 FFT 18432K: Width 256x4, Height 256x4, Middle 9; 17.60 bits/word
2019-02-04 23:05:21 using short carry kernels
2019-02-04 23:05:21 Exiting because "No OpenCL device"
2019-02-04 23:05:21 Bye[/CODE]but did not default to device zero and just run afterward.

Exits if smallest fft length is too large for first worktodo entry. (why not comment out first entry, and go on to next?)[CODE]
C:\msys64\home\ken\gpuowl-compile\v6.0-b7bb1c3>openowl -device 0 -user kriesel -cpu condorella/rx-480
2019-02-04 23:17:18 gpuowl 6.0-b7bb1c3
2019-02-04 23:17:18 condorella/rx-480 -device 0 -user kriesel -cpu condorella/rx-480
2019-02-04 23:17:18 condorella/rx-480 11213 FFT 8K: Width 8x8, Height 8x8; 1.37 bits/word
2019-02-04 23:17:18 condorella/rx-480 FFT size too large for exponent (1.37 bits/word).
2019-02-04 23:17:18 condorella/rx-480 Exiting because "FFT size too large"
2019-02-04 23:17:18 condorella/rx-480 Bye[/CODE]Had a problem with 216091 (default, long or short carry):[CODE]
2019-02-04 23:22:47 condorella/rx-480 216091 FFT 24K: Width 8x8, Height 8x8, Middle 3; 8.79 bits/word
2019-02-04 23:22:47 condorella/rx-480 using long carry kernels
2019-02-04 23:22:50 condorella/rx-480 OpenCL compilation in 2510 ms, with "-DEXP=216091u -DWIDTH=64u -DSMALL_HEIGHT=64u -DMIDDLE=3u -
cl-std=CL2.0 "
2019-02-04 23:22:50 condorella/rx-480 216091.owl not found, starting from the beginning.
2019-02-04 23:22:50 condorella/rx-480 216091 EE loaded: 0, blockSize 400, 0000000000000000 (expected 0000000000000003)
2019-02-04 23:22:50 condorella/rx-480 Exiting because "error on load"
2019-02-04 23:22:50 condorella/rx-480 Bye[/CODE]Similar issue with 756839:[CODE]
C:\msys64\home\ken\gpuowl-compile\v6.0-b7bb1c3>openowl -device 0 -user kriesel -cpu condorella/rx-480 -carry long
2019-02-04 23:25:27 gpuowl 6.0-b7bb1c3
2019-02-04 23:25:27 condorella/rx-480 -device 0 -user kriesel -cpu condorella/rx-480 -carry long
2019-02-04 23:25:27 condorella/rx-480 756839 FFT 40K: Width 8x8, Height 8x8, Middle 5; 18.48 bits/word
2019-02-04 23:25:27 condorella/rx-480 using long carry kernels
2019-02-04 23:25:34 condorella/rx-480 OpenCL compilation in 3007 ms, with "-DEXP=756839u -DWIDTH=64u -DSMALL_HEIGHT=64u -DMIDDLE=5u -
cl-std=CL2.0 "
2019-02-04 23:25:34 condorella/rx-480 756839.owl not found, starting from the beginning.
2019-02-04 23:25:34 condorella/rx-480 756839 EE loaded: 0, blockSize 400, 0000000000000000 (expected 0000000000000003)
2019-02-04 23:25:34 condorella/rx-480 Exiting because "error on load"
2019-02-04 23:25:34 condorella/rx-480 Bye

C:\msys64\home\ken\gpuowl-compile\v6.0-b7bb1c3>openowl -device 0 -user kriesel -cpu condorella/rx-480
2019-02-04 23:25:45 gpuowl 6.0-b7bb1c3
2019-02-04 23:25:45 condorella/rx-480 -device 0 -user kriesel -cpu condorella/rx-480
2019-02-04 23:25:45 condorella/rx-480 756839 FFT 40K: Width 8x8, Height 8x8, Middle 5; 18.48 bits/word
2019-02-04 23:25:45 condorella/rx-480 using short carry kernels
2019-02-04 23:25:51 condorella/rx-480 OpenCL compilation in 2980 ms, with "-DEXP=756839u -DWIDTH=64u -DSMALL_HEIGHT=64u -DMIDDLE=5u -
cl-std=CL2.0 "
2019-02-04 23:25:51 condorella/rx-480 756839.owl not found, starting from the beginning.
2019-02-04 23:25:51 condorella/rx-480 756839 EE loaded: 0, blockSize 400, 0000000000000000 (expected 0000000000000003)
2019-02-04 23:25:51 condorella/rx-480 Exiting because "error on load"
2019-02-04 23:25:51 condorella/rx-480 Bye[/CODE]The 4.5M fft length appeared to be a few percent faster than the previous best (V3.8) on RX-480.[/QUOTE]

That is an old version. Now at version 6.2 ...