gpuOwL: an OpenCL program for Mersenne primality testing - Page 249

DrobinsonPE · 2021-08-24, 04:46

Code:

GPUOWL, AMD Ryzen 5 5600G, ASROCK B450-HDV R4.0, DDR4-3600 RAM
----------------------------------------------------------------
C:\Users\User\GPUOWL\v611380>gpuowl-win -log 10000 -iters 200000 -prp 77936867
2021-08-23 20:55:06 gpuowl v6.11-380-g79ea0cc
2021-08-23 20:55:06 Note: not found 'config.txt'
2021-08-23 20:55:06 config: -log 10000 -iters 200000 -prp 77936867
2021-08-23 20:55:06 device 0, unique id ''
2021-08-23 20:55:06 gfx90c-0 77936867 FFT: 4M 1K:8:256 (18.58 bpw)
2021-08-23 20:55:06 gfx90c-0 Expected maximum carry32: 583B0000
2021-08-23 20:55:06 gfx90c-0 OpenCL args "-DEXP=77936867u -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=8u -DPM1=0 -DAMDGPU=1 -DMM_CHAIN=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -DWEIGHT_STEP_MINUS_1=0xa.c42d0d7cec038p-5 -DIWEIGHT_STEP_MINUS_1=-0x8.0e50c8817ddf8p-5  -cl-unsafe-math-optimizations -cl-std=CL2.0 -cl-finite-math-only "
2021-08-23 20:55:06 gfx90c-0 ASM compilation failed, retrying compilation using NO_ASM
2021-08-23 20:55:08 gfx90c-0 OpenCL compilation in 1.72 s
2021-08-23 20:55:12 gfx90c-0 77936867 OK   200000 loaded: blockSize 400, f0b04b45b0855bd2
2021-08-23 20:55:12 gfx90c-0 validating proof residues for power 8
2021-08-23 20:55:12 gfx90c-0 Proof using power 8
2021-08-23 20:55:22 gfx90c-0 77936867 OK   200800   0.26%; 8494 us/it; ETA 7d 15:25; 895b034c5473a608 (check 3.43s)
2021-08-23 20:56:43 gfx90c-0 77936867 OK   210000   0.27%; 8463 us/it; ETA 7d 14:43; 43eb2fc2424d8aac (check 3.42s)
2021-08-23 20:58:11 gfx90c-0 77936867 OK   220000   0.28%; 8459 us/it; ETA 7d 14:36; a1081c6dc6a7689f (check 3.42s)
2021-08-23 20:59:39 gfx90c-0 77936867 OK   230000   0.30%; 8459 us/it; ETA 7d 14:36; 2387818d3d3d0d01 (check 3.42s)
2021-08-23 21:01:07 gfx90c-0 77936867 OK   240000   0.31%; 8458 us/it; ETA 7d 14:33; a9deae45055e5216 (check 3.42s)
2021-08-23 21:02:35 gfx90c-0 77936867 OK   250000   0.32%; 8461 us/it; ETA 7d 14:35; 89fcab15218f7cac (check 3.42s)
2021-08-23 21:04:03 gfx90c-0 77936867 OK   260000   0.33%; 8459 us/it; ETA 7d 14:31; 55da428da4cf928a (check 3.42s)
2021-08-23 21:05:31 gfx90c-0 77936867 OK   270000   0.35%; 8459 us/it; ETA 7d 14:29; dc349756c5f05abf (check 3.42s)
2021-08-23 21:06:59 gfx90c-0 77936867 OK   280000   0.36%; 8459 us/it; ETA 7d 14:28; 3564af24488443f4 (check 3.42s)
2021-08-23 21:08:28 gfx90c-0 77936867 OK   290000   0.37%; 8459 us/it; ETA 7d 14:27; 63fb281a06f78198 (check 3.42s)
2021-08-23 21:09:56 gfx90c-0 77936867 OK   300000   0.38%; 8459 us/it; ETA 7d 14:25; 990aa099aad5bf9c (check 3.42s)
2021-08-23 21:11:24 gfx90c-0 77936867 OK   310000   0.40%; 8466 us/it; ETA 7d 14:33; 61e14297a2cc0096 (check 3.42s)
2021-08-23 21:12:52 gfx90c-0 77936867 OK   320000   0.41%; 8459 us/it; ETA 7d 14:23; 37e630c5f956cf8a (check 3.42s)
2021-08-23 21:14:20 gfx90c-0 77936867 OK   330000   0.42%; 8461 us/it; ETA 7d 14:23; 66ccde7e28ce2b33 (check 3.42s)
2021-08-23 21:15:48 gfx90c-0 77936867 OK   340000   0.44%; 8467 us/it; ETA 7d 14:30; d4a7cff61adaa84e (check 3.50s)
2021-08-23 21:17:16 gfx90c-0 77936867 OK   350000   0.45%; 8459 us/it; ETA 7d 14:18; d57b659cc1ca2753 (check 3.42s)
2021-08-23 21:18:44 gfx90c-0 77936867 OK   360000   0.46%; 8463 us/it; ETA 7d 14:22; 992df79b843f90de (check 3.42s)
2021-08-23 21:20:12 gfx90c-0 77936867 OK   370000   0.47%; 8459 us/it; ETA 7d 14:16; 10b0b99eba490a1e (check 3.42s)
2021-08-23 21:21:40 gfx90c-0 77936867 OK   380000   0.49%; 8459 us/it; ETA 7d 14:14; 56b1e40cd2666109 (check 3.42s)
2021-08-23 21:23:08 gfx90c-0 77936867 OK   390000   0.50%; 8459 us/it; ETA 7d 14:13; ecccd874a8a0d961 (check 3.42s)
2021-08-23 21:24:29 gfx90c-0 Stopping, please wait..
2021-08-23 21:24:36 gfx90c-0 77936867 OK   400000   0.51%; 8459 us/it; ETA 7d 14:12; c03f94396a5aa29e (check 3.42s)
2021-08-23 21:24:36 gfx90c-0 Exiting because "stop requested"
2021-08-23 21:24:36 gfx90c-0 Bye

kriesel · 2021-09-11, 21:21

RX550 in condorella HP Z600 workstation, dual(xeon E5645 6 core & HT), Windows 7 Pro x64; stock clock & power levels, GPU driver version given by GPU-Z: 25.20.14007.1000(Adrenalin 18.10.2) / Win7 64
Other system loads: prime95 on all 12 actual cpu cores, gpuowl on RX480 GPU, Windows remote desktop

Code:

\gpuowl-compile\gpuowl-v6.11-364-g36f4e2a\rx550>gpuowl-win -prp 77936867
2021-09-11 15:09:00 gpuowl v6.11-364-g36f4e2a
2021-09-11 15:09:00 config: -device 1 -user kriesel -cpu condorella/rx550 -maxAlloc 3600 -proof 9 -use NO_ASM
2021-09-11 15:09:00 config: -prp 77936867
2021-09-11 15:09:00 device 1, unique id ''
2021-09-11 15:09:00 condorella/rx550 77936867 FFT: 4M 1K:8:256 (18.58 bpw)
2021-09-11 15:09:00 condorella/rx550 Expected maximum carry32: 583B0000
2021-09-11 15:09:02 condorella/rx550 OpenCL args "-DEXP=77936867u -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=8u -DPM1=0 -DAMDGPU=1 -DMM_CHAI
N=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -DWEIGHT_STEP_MINUS_1=0xa.c42d0d7cec038p-5 -DIWEIGHT_STEP_MINUS_1=-0x8.0e50c8817ddf8p-5 -DNO_ASM=1  -cl
-unsafe-math-optimizations -cl-std=CL2.0 -cl-finite-math-only "
2021-09-11 15:09:07 condorella/rx550 OpenCL compilation in 4.96 s
2021-09-11 15:09:12 condorella/rx550 77936867 OK        0 loaded: blockSize 400, 0000000000000003
2021-09-11 15:09:12 condorella/rx550 validating proof residues for power 9
2021-09-11 15:09:12 condorella/rx550 Proof using power 9
2021-09-11 15:09:27 condorella/rx550 77936867 OK      800   0.00%; 12181 us/it; ETA 10d 23:42; 1579c241dc63eca6 (check 5.00s)
2021-09-11 15:50:16 condorella/rx550 77936867 OK   200000   0.26%; 12267 us/it; ETA 11d 00:54; f0b04b45b0855bd2 (check 5.32s)

GTX1650 in Lenovo D20 workstation dual(xeon e5-2670 6 core & HT), Windows 7 Pro x64; stock clocks; gpu temp 63C, GPU driver version given by GPU-Z: 26.21.14.4219 (NVIDIA 442.19) / Win7 64
Other system loads: prime95 on all 12 actual cpu cores, Windows remote desktop, 8 mfactor threads using the HT

Code:

\gpuowl-v6.11-380-g79ea0c>gpuowl-win -prp 77936867
2021-09-11 15:41:38 gpuowl v6.11-380-g79ea0cc
2021-09-11 15:41:38 config: -user Kriesel -d 0 -cpu emu_gtx1650
2021-09-11 15:41:38 config: -prp 77936867
2021-09-11 15:41:38 device 0, unique id ''
2021-09-11 15:41:38 emu_gtx1650 77936867 FFT: 4M 1K:8:256 (18.58 bpw)
2021-09-11 15:41:38 emu_gtx1650 Expected maximum carry32: 583B0000
2021-09-11 15:41:40 emu_gtx1650 OpenCL args "-DEXP=77936867u -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=8u -DPM1=0 -DMM_CHAIN=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -
DWEIGHT_STEP_MINUS_1=0xa.c42d0d7cec038p-5 -DIWEIGHT_STEP_MINUS_1=-0x8.0e50c8817ddf8p-5  -cl-unsafe-math-optimizations -cl-std=CL2.0 -cl-finite-math-only "
2021-09-11 15:41:46 emu_gtx1650

2021-09-11 15:41:46 emu_gtx1650 OpenCL compilation in 6.37 s
2021-09-11 15:41:50 emu_gtx1650 77936867 OK        0 loaded: blockSize 400, 0000000000000003
2021-09-11 15:41:50 emu_gtx1650 validating proof residues for power 8
2021-09-11 15:41:50 emu_gtx1650 Proof using power 8
2021-09-11 15:42:02 emu_gtx1650 77936867 OK      800   0.00%; 9270 us/it; ETA 8d 08:42; 1579c241dc63eca6 (check 3.88s)
2021-09-11 16:13:06 emu_gtx1650 77936867 OK   200000   0.26%; 9340 us/it; ETA 8d 09:42; f0b04b45b0855bd2 (check 3.93s)

GTX1050Ti in condorette HP Z600 workstation dual(xeon x5650 6 core & HT); Windows 7 Home x64; stock clocks; GPU power level 62W cap, GPU when switched from TF 78C; 71C after Gpuowl a while; GPU driver version given by GPU-Z: 21.21.13.7866(NVIDIA 378.66)/Win7 64
Other system loads: CUDAPm1 on Quadro 2000, Windows remote desktop, prime95 on all 12 actual cpu cores

Code:

\gpuowl-v6.11-380-g79ea0cc>gpuowl-win -prp 77936867
2021-09-11 15:12:36 gpuowl v6.11-380-g79ea0cc
2021-09-11 15:12:36 config: -user kriesel -cpu condorette/gtx1050ti -d 0 -maxAlloc 3500 -yield
2021-09-11 15:12:36 config:
2021-09-11 15:12:36 config: -prp 77936867
2021-09-11 15:12:36 device 0, unique id ''
2021-09-11 15:12:36 condorette/gtx1050ti 77936867 FFT: 4M 1K:8:256 (18.58 bpw)
2021-09-11 15:12:36 condorette/gtx1050ti Expected maximum carry32: 583B0000
2021-09-11 15:12:37 condorette/gtx1050ti OpenCL args "-DEXP=77936867u -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=8u -DPM1=0 -DMM_CH
AIN=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -DWEIGHT_STEP_MINUS_1=0xa.c42d0d7cec038p-5 -DIWEIGHT_STEP_MINUS_1=-0x8.0e50c8817ddf8p-5  -cl
-unsafe-math-optimizations -cl-std=CL2.0 -cl-finite-math-only "
2021-09-11 15:12:42 condorette/gtx1050ti

2021-09-11 15:12:42 condorette/gtx1050ti OpenCL compilation in 4.89 s
2021-09-11 15:12:48 condorette/gtx1050ti 77936867 OK        0 loaded: blockSize 400, 0000000000000003
2021-09-11 15:12:48 condorette/gtx1050ti validating proof residues for power 8
2021-09-11 15:12:48 condorette/gtx1050ti Proof using power 8
2021-09-11 15:13:01 condorette/gtx1050ti 77936867 OK      800   0.00%; 11334 us/it; ETA 10d 05:22; 1579c241dc63eca6 (check 4.65s)
2021-09-11 15:51:10 condorette/gtx1050ti 77936867 OK   200000   0.26%; 11463 us/it; ETA 10d 07:31; f0b04b45b0855bd2 (check 4.69s)

GTX 1050Ti in peregrine Dell G3 3579 laptop i7-8750H 6 core & HT; Windows 7 Home x64; stock clock & power levels; GPU temp 91C & stable during gpuowl benchmark; GPU driver version as given by GPU-Z: 27.21.14.6231(Nvidia 462.31) DCH/ Win10 64
Other system loads: TightVNC remote access, mlucas V20.1 PRP DC on 4 threads, prime95 v30.6b4 on 4 cores

Code:

\gpuowl-v6.11-380-g79ea0cc>gpuowl-win -prp 77936867
2021-09-11 15:19:32 gpuowl v6.11-380-g79ea0cc
2021-09-11 15:19:32 config: -cpu peregine/gtx1050Ti -user kriesel -device 0 -log 10000 -safeMath -proof 8 -maxAlloc 3200 -use NO_ASM -yield
2021-09-11 15:19:32 config: -prp 77936867
2021-09-11 15:19:32 device 0, unique id ''
2021-09-11 15:19:32 peregine/gtx1050Ti 77936867 FFT: 4M 1K:8:256 (18.58 bpw)
2021-09-11 15:19:32 peregine/gtx1050Ti Expected maximum carry32: 583B0000
2021-09-11 15:19:38 peregine/gtx1050Ti OpenCL args "-DEXP=77936867u -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=8u -DPM1=0 -DMM_CHAIN=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -DWEIGHT_STEP_MINUS_1=0xa.c42d0d7cec038p-5 -DIWEIGHT_STEP_MINUS_1=-0x8.0e50c8817ddf8p-5 -DNO_ASM=1  -cl-std=CL2.0 -cl-finite-math-only "
2021-09-11 15:19:46 peregine/gtx1050Ti

2021-09-11 15:19:46 peregine/gtx1050Ti OpenCL compilation in 8.42 s
2021-09-11 15:19:52 peregine/gtx1050Ti 77936867 OK        0 loaded: blockSize 400, 0000000000000003
2021-09-11 15:19:52 peregine/gtx1050Ti validating proof residues for power 8
2021-09-11 15:19:52 peregine/gtx1050Ti Proof using power 8
2021-09-11 15:20:07 peregine/gtx1050Ti 77936867 OK      800   0.00%; 12234 us/it; ETA 11d 00:51; 1579c241dc63eca6 (check 5.17s)
2021-09-11 15:22:06 peregine/gtx1050Ti 77936867 OK    10000   0.01%; 12372 us/it; ETA 11d 03:48; fc4f135f7cf4ad29 (check 5.44s)
2021-09-11 15:24:23 peregine/gtx1050Ti 77936867 OK    20000   0.03%; 13062 us/it; ETA 11d 18:42; 3cd1bd9d5e09cbc5 (check 5.64s)
2021-09-11 15:26:42 peregine/gtx1050Ti 77936867 OK    30000   0.04%; 13387 us/it; ETA 12d 01:43; c4e0ff35e3290d98 (check 5.69s)
2021-09-11 15:29:03 peregine/gtx1050Ti 77936867 OK    40000   0.05%; 13542 us/it; ETA 12d 05:02; dffe1b1b0d748128 (check 5.63s)
2021-09-11 15:31:25 peregine/gtx1050Ti 77936867 OK    50000   0.06%; 13567 us/it; ETA 12d 05:31; 52e286945371ed29 (check 5.80s)
2021-09-11 15:33:47 peregine/gtx1050Ti 77936867 OK    60000   0.08%; 13622 us/it; ETA 12d 06:41; 0945da4dc08bdd95 (check 5.85s)
2021-09-11 15:36:09 peregine/gtx1050Ti 77936867 OK    70000   0.09%; 13615 us/it; ETA 12d 06:29; 7131fa4eb77f4bb2 (check 5.79s)
2021-09-11 15:38:32 peregine/gtx1050Ti 77936867 OK    80000   0.10%; 13771 us/it; ETA 12d 09:50; 8d76071d27ee4221 (check 5.69s)
2021-09-11 15:40:55 peregine/gtx1050Ti 77936867 OK    90000   0.12%; 13718 us/it; ETA 12d 08:38; 0bacff453b2f470e (check 5.78s)
2021-09-11 15:43:19 peregine/gtx1050Ti 77936867 OK   100000   0.13%; 13767 us/it; ETA 12d 09:40; 6d7296b9e2830f50 (check 5.80s)
2021-09-11 15:45:42 peregine/gtx1050Ti 77936867 OK   110000   0.14%; 13758 us/it; ETA 12d 09:25; 8cbfd4435622bda7 (check 5.83s)
2021-09-11 15:48:06 peregine/gtx1050Ti 77936867 OK   120000   0.15%; 13776 us/it; ETA 12d 09:47; 79ae5dad855057ad (check 5.81s)
2021-09-11 15:50:29 peregine/gtx1050Ti 77936867 OK   130000   0.17%; 13768 us/it; ETA 12d 09:34; 50c97bcbf876231f (check 5.86s)
2021-09-11 15:52:53 peregine/gtx1050Ti 77936867 OK   140000   0.18%; 13773 us/it; ETA 12d 09:38; e1db15f897271496 (check 5.85s)
2021-09-11 15:55:16 peregine/gtx1050Ti 77936867 OK   150000   0.19%; 13758 us/it; ETA 12d 09:17; 127631386c6a9b17 (check 5.82s)
2021-09-11 15:57:40 peregine/gtx1050Ti 77936867 OK   160000   0.21%; 13799 us/it; ETA 12d 10:07; 25b7b6206fc6f085 (check 5.73s)
2021-09-11 16:00:04 peregine/gtx1050Ti 77936867 OK   170000   0.22%; 13772 us/it; ETA 12d 09:30; 416816b0d9f4bba8 (check 5.84s)
2021-09-11 16:02:28 peregine/gtx1050Ti 77936867 OK   180000   0.23%; 13841 us/it; ETA 12d 10:57; 6bee5d054f770861 (check 5.79s)

kriesel · 2021-09-14, 13:39

Ancient V1.9 can be run on it (although not with -fft DP, and it produces less throughput, than its negative impact on prime95 on the CPU)

Code:

\gpuowl-v1.9-74f1a38>gpuowl -device 0 -user kriesel -cpu martinella-IrisXeIGP -fft M61
gpuOwL v1.9- GPU Mersenne primality checker
Intel(R) Iris(R) Xe Graphics, 96x1300MHz

OpenCL compilation in 45840 ms, with "-I. -cl-fast-relaxed-math -cl-std=CL2.0  -DEXP=77936867u -DWIDTH=1024u -DHEIGHT=2048u -DLOG_NWORDS=22u -DFGT_61=1 -DLOG_ROOT2=49u "
Note: using long carry kernels
PRP-3: FFT 4M (1024 * 2048 * 2) of 77936867 (18.58 bits/word) [2021-09-13 12:35:42 Central Daylight Time]
Starting at iteration 0
OK        0 / 77936867 [ 0.00%], 0.00 ms/it; ETA 0d 00:00; 0000000000000003 [12:36:04]
OK     1000 / 77936867 [ 0.00%], 40.50 ms/it; ETA 36d 12:52; 9711fce020e74461 [12:37:07]
OK     5000 / 77936867 [ 0.01%], 40.58 ms/it; ETA 36d 14:22; 31d8d3401e6fe48d [12:40:11]
OK    10000 / 77936867 [ 0.01%], 39.37 ms/it; ETA 35d 12:13; fc4f135f7cf4ad29 [12:43:49]
OK    20000 / 77936867 [ 0.03%], 38.88 ms/it; ETA 35d 01:36; 3cd1bd9d5e09cbc5 [12:50:40]
OK    40000 / 77936867 [ 0.05%], 38.25 ms/it; ETA 34d 11:34; dffe1b1b0d748128 [13:03:46]
OK    60000 / 77936867 [ 0.08%], 38.51 ms/it; ETA 34d 17:01; 0945da4dc08bdd95 [13:16:56]
OK    80000 / 77936867 [ 0.10%], 38.29 ms/it; ETA 34d 12:08; 8d76071d27ee4221 [13:30:02]
OK   100000 / 77936867 [ 0.13%], 38.53 ms/it; ETA 34d 17:09; 6d7296b9e2830f50 [13:43:14]
OK   150000 / 77936867 [ 0.19%], 38.22 ms/it; ETA 34d 09:49; 127631386c6a9b17 [14:15:26]
OK   200000 / 77936867 [ 0.26%], 38.21 ms/it; ETA 34d 09:05; f0b04b45b0855bd2 [14:47:38]
OK   250000 / 77936867 [ 0.32%], 38.30 ms/it; ETA 34d 10:31; 89fcab15218f7cac [15:19:55]
OK   300000 / 77936867 [ 0.38%], 38.36 ms/it; ETA 34d 11:13; 990aa099aad5bf9c [15:52:14]

V6.11-380 fails to run:

Code:

\gpuowl-v6.11-380-g79ea0cc>gpuowl-win
2021-09-14 08:34:00 gpuowl v6.11-380-g79ea0cc
2021-09-14 08:34:00 config: -cpu martinella-IrisXeIGP -user kriesel -use NO_ASM -device 0 -proof 9
2021-09-14 08:34:00 device 0, unique id ''
2021-09-14 08:34:00 martinella-IrisXeIGP 77936867 FFT: 4M 1K:8:256 (18.58 bpw)
2021-09-14 08:34:00 martinella-IrisXeIGP Expected maximum carry32: 583B0000
2021-09-14 08:34:01 martinella-IrisXeIGP OpenCL args "-DEXP=77936867u -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=8u -DPM1=0 -DMM_CHAIN=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -DWEIGHT_STEP_MINUS_1=0xa.c42d0d7cec038p-5 -DIWEIGHT_STEP_MINUS_1=-0x8.0e50c8817ddf8p-5 -DNO_ASM=1  -cl-unsafe-math-optimizations -cl-std=CL2.0 -cl-finite-math-only "
2021-09-14 08:34:03 martinella-IrisXeIGP ASM compilation failed, retrying compilation using NO_ASM
2021-09-14 08:34:04 martinella-IrisXeIGP OpenCL compilation error -11 (args -DEXP=77936867u -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=8u -DPM1=0 -DMM_CHAIN=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -DWEIGHT_STEP_MINUS_1=0xa.c42d0d7cec038p-5 -DIWEIGHT_STEP_MINUS_1=-0x8.0e50c8817ddf8p-5 -DNO_ASM=1  -cl-unsafe-math-optimizations -cl-std=CL2.0 -cl-finite-math-only  -DNO_ASM=1)
2021-09-14 08:34:04 martinella-IrisXeIGP 1:190:9: error: use of type 'double' requires cl_khr_fp64 extension to be enabled
typedef double T;
        ^
1:191:9: error: unknown type name 'double2'; did you mean 'double'?
typedef double2 T2;
        ^~~~~~~
        double
1:191:9: error: use of type 'double' requires cl_khr_fp64 extension to be enabled
1:201:7: error: use of type 'T' (aka 'double') requires cl_khr_fp64 extension to be enabled
T2 U2(T a, T b) { return (T2)(a, b); }
      ^
1:201:12: error: use of type 'T' (aka 'double') requires cl_khr_fp64 extension to be enabled
T2 U2(T a, T b) { return (T2)(a, b); }
           ^
1:201:1: error: use of type 'T2' (aka 'double') requires cl_khr_fp64 extension to be enabled
T2 U2(T a, T b) { return (T2)(a, b); }
^
1:201:27: error: use of type 'T2' (aka 'double') requires cl_khr_fp64 extension to be enabled
T2 U2(T a, T b) { return (T2)(a, b); }
                          ^
1:207:11: error: use of type 'T' (aka 'double') requires cl_khr_fp64 extension to be enabled
T add1_m2(T x, T y) {
          ^
1:207:16: error: use of type 'T' (aka 'double') requires cl_khr_fp64 extension to be enabled
T add1_m2(T x, T y) {
               ^
1:207:1: error: use of type 'T' (aka 'double') requires cl_khr_fp64 extension to be enabled
T add1_m2(T x, T y) {
^
1:216:11: error: use of type 'T' (aka 'double') requires cl_khr_fp64 extension to be enabled
T sub1_m2(T x, T y) {
          ^
1:216:16: error: use of type 'T' (aka 'double') requires cl_khr_fp64 extension to be enabled
T sub1_m2(T x, T y) {
               ^
1:216:1: error: use of type 'T' (aka 'double') requires cl_khr_fp64 extension to be enabled
T sub1_m2(T x, T y) {
^
1:226:11: error: use of type 'T' (aka 'double') requires cl_khr_fp64 extension to be enabled
T mul1_m2(T x, T y) {
          ^
1:226:16: error: use of type 'T' (aka 'double') requires cl_khr_fp64 extension to be enabled
T mul1_m2(T x, T y) {
               ^
1:226:1: error: use of type 'T' (aka 'double') requires cl_khr_fp64 extension to be enabled
T mul1_m2(T x, T y) {
^
2021-09-14 08:34:04 martinella-IrisXeIGP Exception gpu_error: BUILD_PROGRAM_FAILURE clBuildProgram at clwrap.cpp:246 build
2021-09-14 08:34:04 martinella-IrisXeIGP Bye

DrDerpenberg · 2021-09-22, 23:16

Exact model: XFX Speedster Swift 319 Radeon RX 6900XT
No other systemloads, CPU is a Ryzen 9 5900X, Win10 and 21.8.2 Radeon software version.
With an OC profile I optimized for energy efficiency and some additional gpuowl tuning:

Code:

2021-09-23 00:19:39 GpuOwl VERSION v7.2-69-g23c14a1
2021-09-23 00:19:39 Note: not found 'config.txt'
2021-09-23 00:19:39 config: -prp 77936867 -fft 512:8:512 -iters 200000 -proof 10 -maxAlloc 14.4G -nospin -use NEWEST_FFT8,CARRY32,TRIG_COMPUTE=1,UNROLL_WIDTH=1,OUT_WG=128,OUT_SIZEX=16,OUT_SPACING=2,IN_WG=128,IN_SIZEX=16,IN_SPACING=1 
2021-09-23 00:19:39 device 0, unique id ''
2021-09-23 00:19:39 gfx1030-0 77936867 FFT: 4M 512:8:512 (18.58 bpw)
2021-09-23 00:19:39 gfx1030-0 77936867 OpenCL args "-DEXP=77936867u -DWIDTH=512u -DSMALL_HEIGHT=512u -DMIDDLE=8u -DAMDGPU=1 -DMM_CHAIN=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -DWEIGHT_STEP=0.33644726404543274 -DIWEIGHT_STEP=-0.25174750481886216 -DIWEIGHTS={0,-0.44011820345520131,-0.37306474779553728,-0.29798072935699788,-0.21390437908665341,-0.11975874301407295,-0.014337887291734644,-0.44814572555075455,} -DFWEIGHTS={0,0.78609128957452257,0.5950610473469905,0.42446232150303748,0.2721098723818392,0.1360521812214803,0.014546452690911484,0.81207258201996746,} -DCARRY32=1 -DIN_SIZEX=16 -DIN_SPACING=1 -DIN_WG=128 -DNEWEST_FFT8=1 -DOUT_SIZEX=16 -DOUT_SPACING=2 -DOUT_WG=128 -DTRIG_COMPUTE=1 -DUNROLL_WIDTH=1  -cl-std=CL2.0 -cl-finite-math-only "
2021-09-23 00:19:42 gfx1030-0 77936867 OpenCL compilation in 3.36 s
2021-09-23 00:19:42 gfx1030-0 77936867 trig table : 129 points, cos 72.91 bits, sin 73.11 bits
2021-09-23 00:19:42 gfx1030-0 77936867 trig table : 513 points, cos 72.77 bits, sin 73.11 bits
2021-09-23 00:19:43 gfx1030-0 77936867 trig table : 262145 points, cos 72.03 bits, sin 72.56 bits
2021-09-23 00:19:43 gfx1030-0 77936867 maxAlloc: 14.4 GB
2021-09-23 00:19:43 gfx1030-0 77936867 P1(0) 0 bits
2021-09-23 00:19:43 gfx1030-0 77936867 PRP starting from beginning
2021-09-23 00:19:43 gfx1030-0 77936867 OK         0 on-load: blockSize 400, 0000000000000003
2021-09-23 00:19:43 gfx1030-0 77936867 validating proof residues for power 10
2021-09-23 00:19:43 gfx1030-0 77936867 Proof using power 10
2021-09-23 00:19:44 gfx1030-0 77936867 OK       800   0.00% 1579c241dc63eca6  626 us/it + check 0.28s + save 0.08s; ETA 13:33
2021-09-23 00:19:50 gfx1030-0 77936867        10000   0.01% fc4f135f7cf4ad29  625 us/it
2021-09-23 00:19:56 gfx1030-0 77936867        20000   0.03% 3cd1bd9d5e09cbc5  626 us/it
2021-09-23 00:20:02 gfx1030-0 77936867        30000   0.04% c4e0ff35e3290d98  626 us/it
2021-09-23 00:20:09 gfx1030-0 77936867        40000   0.05% dffe1b1b0d748128  626 us/it
2021-09-23 00:20:15 gfx1030-0 77936867        50000   0.06% 52e286945371ed29  626 us/it
2021-09-23 00:20:21 gfx1030-0 77936867        60000   0.08% 0945da4dc08bdd95  628 us/it
2021-09-23 00:20:27 gfx1030-0 77936867        70000   0.09% 7131fa4eb77f4bb2  626 us/it
2021-09-23 00:20:34 gfx1030-0 77936867        80000   0.10% 8d76071d27ee4221  636 us/it
2021-09-23 00:20:40 gfx1030-0 77936867        90000   0.12% 0bacff453b2f470e  626 us/it
2021-09-23 00:20:46 gfx1030-0 77936867       100000   0.13% 6d7296b9e2830f50  626 us/it
2021-09-23 00:20:53 gfx1030-0 77936867       110000   0.14% 8cbfd4435622bda7  626 us/it
2021-09-23 00:20:59 gfx1030-0 77936867       120000   0.15% 79ae5dad855057ad  626 us/it
2021-09-23 00:21:05 gfx1030-0 77936867       130000   0.17% 50c97bcbf876231f  626 us/it
2021-09-23 00:21:11 gfx1030-0 77936867       140000   0.18% e1db15f897271496  626 us/it
2021-09-23 00:21:18 gfx1030-0 77936867       150000   0.19% 127631386c6a9b17  626 us/it
2021-09-23 00:21:24 gfx1030-0 77936867       160000   0.21% 25b7b6206fc6f085  637 us/it
2021-09-23 00:21:30 gfx1030-0 77936867       170000   0.22% 416816b0d9f4bba8  626 us/it
2021-09-23 00:21:37 gfx1030-0 77936867       180000   0.23% 6bee5d054f770861  626 us/it
2021-09-23 00:21:43 gfx1030-0 77936867       190000   0.24% f37f068f014b18a0  626 us/it
2021-09-23 00:21:49 gfx1030-0 77936867 Stopping, please wait..
2021-09-23 00:21:49 gfx1030-0 77936867 OK    200000   0.26% f0b04b45b0855bd2  626 us/it + check 0.28s + save 0.08s; ETA 13:31
2021-09-23 00:21:49 gfx1030-0 Exiting because "stop requested"
2021-09-23 00:21:49 gfx1030-0 Bye

Energy efficient and no gpuowl tuning:

Code:

2021-09-23 00:57:58 GpuOwl VERSION v7.2-69-g23c14a1
2021-09-23 00:57:58 Note: not found 'config.txt'
2021-09-23 00:57:58 config: -prp 77936867 -iters 200000 -proof 10 -maxAlloc 14.4G -nospin 
2021-09-23 00:57:58 device 0, unique id ''
2021-09-23 00:57:58 gfx1030-0 77936867 FFT: 4M 1K:8:256 (18.58 bpw)
2021-09-23 00:57:58 gfx1030-0 77936867 OpenCL args "-DEXP=77936867u -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=8u -DAMDGPU=1 -DMM_CHAIN=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -DWEIGHT_STEP=0.33644726404543274 -DIWEIGHT_STEP=-0.25174750481886216 -DIWEIGHTS={0,-0.44011820345520131,-0.37306474779553728,-0.29798072935699788,-0.21390437908665341,-0.11975874301407295,-0.014337887291734644,-0.44814572555075455,} -DFWEIGHTS={0,0.78609128957452257,0.5950610473469905,0.42446232150303748,0.2721098723818392,0.1360521812214803,0.014546452690911484,0.81207258201996746,}  -cl-std=CL2.0 -cl-finite-math-only "
2021-09-23 00:58:00 gfx1030-0 77936867 OpenCL compilation in 2.01 s
2021-09-23 00:58:00 gfx1030-0 77936867 trig table : 65 points, cos 73.86 bits, sin 73.34 bits
2021-09-23 00:58:00 gfx1030-0 77936867 trig table : 257 points, cos 72.90 bits, sin 73.11 bits
2021-09-23 00:58:01 gfx1030-0 77936867 trig table : 262145 points, cos 72.03 bits, sin 72.56 bits
2021-09-23 00:58:01 gfx1030-0 77936867 maxAlloc: 14.4 GB
2021-09-23 00:58:01 gfx1030-0 77936867 P1(0) 0 bits
2021-09-23 00:58:01 gfx1030-0 77936867 PRP starting from beginning
2021-09-23 00:58:01 gfx1030-0 77936867 OK         0 on-load: blockSize 400, 0000000000000003
2021-09-23 00:58:01 gfx1030-0 77936867 validating proof residues for power 10
2021-09-23 00:58:01 gfx1030-0 77936867 Proof using power 10
2021-09-23 00:58:02 gfx1030-0 77936867 OK       800   0.00% 1579c241dc63eca6  684 us/it + check 0.30s + save 0.08s; ETA 14:49
2021-09-23 00:58:08 gfx1030-0 77936867        10000   0.01% fc4f135f7cf4ad29  684 us/it
2021-09-23 00:58:15 gfx1030-0 77936867        20000   0.03% 3cd1bd9d5e09cbc5  685 us/it
2021-09-23 00:58:22 gfx1030-0 77936867        30000   0.04% c4e0ff35e3290d98  685 us/it
2021-09-23 00:58:29 gfx1030-0 77936867        40000   0.05% dffe1b1b0d748128  685 us/it
2021-09-23 00:58:36 gfx1030-0 77936867        50000   0.06% 52e286945371ed29  685 us/it
2021-09-23 00:58:43 gfx1030-0 77936867        60000   0.08% 0945da4dc08bdd95  686 us/it
2021-09-23 00:58:49 gfx1030-0 77936867        70000   0.09% 7131fa4eb77f4bb2  685 us/it
2021-09-23 00:58:56 gfx1030-0 77936867        80000   0.10% 8d76071d27ee4221  697 us/it
2021-09-23 00:59:03 gfx1030-0 77936867        90000   0.12% 0bacff453b2f470e  685 us/it
2021-09-23 00:59:10 gfx1030-0 77936867       100000   0.13% 6d7296b9e2830f50  685 us/it
2021-09-23 00:59:17 gfx1030-0 77936867       110000   0.14% 8cbfd4435622bda7  685 us/it
2021-09-23 00:59:24 gfx1030-0 77936867       120000   0.15% 79ae5dad855057ad  685 us/it
2021-09-23 00:59:31 gfx1030-0 77936867       130000   0.17% 50c97bcbf876231f  685 us/it
2021-09-23 00:59:38 gfx1030-0 77936867       140000   0.18% e1db15f897271496  685 us/it
2021-09-23 00:59:44 gfx1030-0 77936867       150000   0.19% 127631386c6a9b17  685 us/it
2021-09-23 00:59:51 gfx1030-0 77936867       160000   0.21% 25b7b6206fc6f085  697 us/it
2021-09-23 00:59:58 gfx1030-0 77936867       170000   0.22% 416816b0d9f4bba8  686 us/it
2021-09-23 01:00:05 gfx1030-0 77936867       180000   0.23% 6bee5d054f770861  685 us/it
2021-09-23 01:00:12 gfx1030-0 77936867       190000   0.24% f37f068f014b18a0  686 us/it
2021-09-23 01:00:19 gfx1030-0 77936867 Stopping, please wait..
2021-09-23 01:00:19 gfx1030-0 77936867 OK    200000   0.26% f0b04b45b0855bd2  686 us/it + check 0.30s + save 0.08s; ETA 14:49
2021-09-23 01:00:19 gfx1030-0 Exiting because "stop requested"
2021-09-23 01:00:19 gfx1030-0 Bye

With factory OC settings and same gpuowl tuning:

Code:

2021-09-23 00:24:59 GpuOwl VERSION v7.2-69-g23c14a1
2021-09-23 00:24:59 Note: not found 'config.txt'
2021-09-23 00:24:59 config: -prp 77936867 -fft 512:8:512 -iters 400000 -proof 10 -maxAlloc 14.4G -nospin -use NEWEST_FFT8,CARRY32,TRIG_COMPUTE=1,UNROLL_WIDTH=1,OUT_WG=128,OUT_SIZEX=16,OUT_SPACING=2,IN_WG=128,IN_SIZEX=16,IN_SPACING=1 
2021-09-23 00:24:59 device 0, unique id ''
2021-09-23 00:25:00 gfx1030-0 77936867 FFT: 4M 512:8:512 (18.58 bpw)
2021-09-23 00:25:00 gfx1030-0 77936867 OpenCL args "-DEXP=77936867u -DWIDTH=512u -DSMALL_HEIGHT=512u -DMIDDLE=8u -DAMDGPU=1 -DMM_CHAIN=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -DWEIGHT_STEP=0.33644726404543274 -DIWEIGHT_STEP=-0.25174750481886216 -DIWEIGHTS={0,-0.44011820345520131,-0.37306474779553728,-0.29798072935699788,-0.21390437908665341,-0.11975874301407295,-0.014337887291734644,-0.44814572555075455,} -DFWEIGHTS={0,0.78609128957452257,0.5950610473469905,0.42446232150303748,0.2721098723818392,0.1360521812214803,0.014546452690911484,0.81207258201996746,} -DCARRY32=1 -DIN_SIZEX=16 -DIN_SPACING=1 -DIN_WG=128 -DNEWEST_FFT8=1 -DOUT_SIZEX=16 -DOUT_SPACING=2 -DOUT_WG=128 -DTRIG_COMPUTE=1 -DUNROLL_WIDTH=1  -cl-std=CL2.0 -cl-finite-math-only "
2021-09-23 00:25:03 gfx1030-0 77936867 OpenCL compilation in 3.42 s
2021-09-23 00:25:03 gfx1030-0 77936867 trig table : 129 points, cos 72.91 bits, sin 73.11 bits
2021-09-23 00:25:03 gfx1030-0 77936867 trig table : 513 points, cos 72.77 bits, sin 73.11 bits
2021-09-23 00:25:03 gfx1030-0 77936867 trig table : 262145 points, cos 72.03 bits, sin 72.56 bits
2021-09-23 00:25:04 gfx1030-0 77936867 maxAlloc: 14.4 GB
2021-09-23 00:25:04 gfx1030-0 77936867 P1(0) 0 bits
2021-09-23 00:25:04 gfx1030-0 77936867 PRP starting from beginning
2021-09-23 00:25:04 gfx1030-0 77936867 OK         0 on-load: blockSize 400, 0000000000000003
2021-09-23 00:25:04 gfx1030-0 77936867 validating proof residues for power 10
2021-09-23 00:25:04 gfx1030-0 77936867 Proof using power 10
2021-09-23 00:25:05 gfx1030-0 77936867 OK       800   0.00% 1579c241dc63eca6  539 us/it + check 0.24s + save 0.08s; ETA 11:40
2021-09-23 00:25:10 gfx1030-0 77936867        10000   0.01% fc4f135f7cf4ad29  544 us/it
2021-09-23 00:25:15 gfx1030-0 77936867        20000   0.03% 3cd1bd9d5e09cbc5  547 us/it
2021-09-23 00:25:21 gfx1030-0 77936867        30000   0.04% c4e0ff35e3290d98  548 us/it
2021-09-23 00:25:26 gfx1030-0 77936867        40000   0.05% dffe1b1b0d748128  551 us/it
2021-09-23 00:25:32 gfx1030-0 77936867        50000   0.06% 52e286945371ed29  552 us/it
2021-09-23 00:25:37 gfx1030-0 77936867        60000   0.08% 0945da4dc08bdd95  552 us/it
2021-09-23 00:25:43 gfx1030-0 77936867        70000   0.09% 7131fa4eb77f4bb2  553 us/it
2021-09-23 00:25:48 gfx1030-0 77936867        80000   0.10% 8d76071d27ee4221  563 us/it
2021-09-23 00:25:54 gfx1030-0 77936867        90000   0.12% 0bacff453b2f470e  553 us/it
2021-09-23 00:25:59 gfx1030-0 77936867       100000   0.13% 6d7296b9e2830f50  554 us/it
2021-09-23 00:26:05 gfx1030-0 77936867       110000   0.14% 8cbfd4435622bda7  554 us/it
2021-09-23 00:26:11 gfx1030-0 77936867       120000   0.15% 79ae5dad855057ad  555 us/it
2021-09-23 00:26:16 gfx1030-0 77936867       130000   0.17% 50c97bcbf876231f  555 us/it
2021-09-23 00:26:22 gfx1030-0 77936867       140000   0.18% e1db15f897271496  555 us/it
2021-09-23 00:26:27 gfx1030-0 77936867       150000   0.19% 127631386c6a9b17  556 us/it
2021-09-23 00:26:33 gfx1030-0 77936867       160000   0.21% 25b7b6206fc6f085  566 us/it
2021-09-23 00:26:38 gfx1030-0 77936867       170000   0.22% 416816b0d9f4bba8  556 us/it
2021-09-23 00:26:44 gfx1030-0 77936867       180000   0.23% 6bee5d054f770861  556 us/it
2021-09-23 00:26:50 gfx1030-0 77936867       190000   0.24% f37f068f014b18a0  557 us/it
2021-09-23 00:26:55 gfx1030-0 77936867 OK    200000   0.26% f0b04b45b0855bd2  557 us/it + check 0.25s + save 0.09s; ETA 12:01
2021-09-23 00:27:01 gfx1030-0 77936867       210000   0.27% 43eb2fc2424d8aac  556 us/it
2021-09-23 00:27:07 gfx1030-0 77936867       220000   0.28% a1081c6dc6a7689f  557 us/it
2021-09-23 00:27:12 gfx1030-0 77936867       230000   0.30% 2387818d3d3d0d01  567 us/it
2021-09-23 00:27:18 gfx1030-0 77936867       240000   0.31% a9deae45055e5216  557 us/it
2021-09-23 00:27:23 gfx1030-0 77936867       250000   0.32% 89fcab15218f7cac  557 us/it
2021-09-23 00:27:29 gfx1030-0 77936867       260000   0.33% 55da428da4cf928a  558 us/it
2021-09-23 00:27:35 gfx1030-0 77936867       270000   0.35% dc349756c5f05abf  558 us/it
2021-09-23 00:27:40 gfx1030-0 77936867       280000   0.36% 3564af24488443f4  557 us/it
2021-09-23 00:27:46 gfx1030-0 77936867       290000   0.37% 63fb281a06f78198  558 us/it
2021-09-23 00:27:51 gfx1030-0 77936867       300000   0.38% 990aa099aad5bf9c  558 us/it
2021-09-23 00:27:57 gfx1030-0 77936867       310000   0.40% 61e14297a2cc0096  568 us/it
2021-09-23 00:28:03 gfx1030-0 77936867       320000   0.41% 37e630c5f956cf8a  558 us/it
2021-09-23 00:28:08 gfx1030-0 77936867       330000   0.42% 66ccde7e28ce2b33  559 us/it
2021-09-23 00:28:14 gfx1030-0 77936867       340000   0.44% d4a7cff61adaa84e  559 us/it
2021-09-23 00:28:19 gfx1030-0 77936867       350000   0.45% d57b659cc1ca2753  560 us/it
2021-09-23 00:28:25 gfx1030-0 77936867       360000   0.46% 992df79b843f90de  559 us/it
2021-09-23 00:28:31 gfx1030-0 77936867       370000   0.47% 10b0b99eba490a1e  560 us/it
2021-09-23 00:28:36 gfx1030-0 77936867       380000   0.49% 56b1e40cd2666109  560 us/it
2021-09-23 00:28:42 gfx1030-0 77936867       390000   0.50% ecccd874a8a0d961  571 us/it
2021-09-23 00:28:47 gfx1030-0 77936867 Stopping, please wait..
2021-09-23 00:28:48 gfx1030-0 77936867 OK    400000   0.51% c03f94396a5aa29e  562 us/it + check 0.25s + save 0.08s; ETA 12:06
2021-09-23 00:28:48 gfx1030-0 Exiting because "stop requested"
2021-09-23 00:28:48 gfx1030-0 Bye

Factory OC and no tuning:

Code:

2021-09-23 01:03:54 GpuOwl VERSION v7.2-69-g23c14a1
2021-09-23 01:03:54 Note: not found 'config.txt'
2021-09-23 01:03:54 config: -prp 77936867 -iters 400000 -proof 10 -maxAlloc 14.4G -nospin 
2021-09-23 01:03:54 device 0, unique id ''
2021-09-23 01:03:54 gfx1030-0 77936867 FFT: 4M 1K:8:256 (18.58 bpw)
2021-09-23 01:03:54 gfx1030-0 77936867 OpenCL args "-DEXP=77936867u -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=8u -DAMDGPU=1 -DMM_CHAIN=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -DWEIGHT_STEP=0.33644726404543274 -DIWEIGHT_STEP=-0.25174750481886216 -DIWEIGHTS={0,-0.44011820345520131,-0.37306474779553728,-0.29798072935699788,-0.21390437908665341,-0.11975874301407295,-0.014337887291734644,-0.44814572555075455,} -DFWEIGHTS={0,0.78609128957452257,0.5950610473469905,0.42446232150303748,0.2721098723818392,0.1360521812214803,0.014546452690911484,0.81207258201996746,}  -cl-std=CL2.0 -cl-finite-math-only "
2021-09-23 01:03:56 gfx1030-0 77936867 OpenCL compilation in 1.98 s
2021-09-23 01:03:56 gfx1030-0 77936867 trig table : 65 points, cos 73.86 bits, sin 73.34 bits
2021-09-23 01:03:56 gfx1030-0 77936867 trig table : 257 points, cos 72.90 bits, sin 73.11 bits
2021-09-23 01:03:57 gfx1030-0 77936867 trig table : 262145 points, cos 72.03 bits, sin 72.56 bits
2021-09-23 01:03:57 gfx1030-0 77936867 maxAlloc: 14.4 GB
2021-09-23 01:03:57 gfx1030-0 77936867 P1(0) 0 bits
2021-09-23 01:03:57 gfx1030-0 77936867 PRP starting from beginning
2021-09-23 01:03:57 gfx1030-0 77936867 OK         0 on-load: blockSize 400, 0000000000000003
2021-09-23 01:03:57 gfx1030-0 77936867 validating proof residues for power 10
2021-09-23 01:03:57 gfx1030-0 77936867 Proof using power 10
2021-09-23 01:03:58 gfx1030-0 77936867 OK       800   0.00% 1579c241dc63eca6  597 us/it + check 0.26s + save 0.08s; ETA 12:55
2021-09-23 01:04:04 gfx1030-0 77936867        10000   0.01% fc4f135f7cf4ad29  602 us/it
2021-09-23 01:04:10 gfx1030-0 77936867        20000   0.03% 3cd1bd9d5e09cbc5  606 us/it
2021-09-23 01:04:16 gfx1030-0 77936867        30000   0.04% c4e0ff35e3290d98  608 us/it
2021-09-23 01:04:22 gfx1030-0 77936867        40000   0.05% dffe1b1b0d748128  610 us/it
2021-09-23 01:04:28 gfx1030-0 77936867        50000   0.06% 52e286945371ed29  611 us/it
2021-09-23 01:04:34 gfx1030-0 77936867        60000   0.08% 0945da4dc08bdd95  612 us/it
2021-09-23 01:04:40 gfx1030-0 77936867        70000   0.09% 7131fa4eb77f4bb2  612 us/it
2021-09-23 01:04:46 gfx1030-0 77936867        80000   0.10% 8d76071d27ee4221  623 us/it
2021-09-23 01:04:53 gfx1030-0 77936867        90000   0.12% 0bacff453b2f470e  613 us/it
2021-09-23 01:04:59 gfx1030-0 77936867       100000   0.13% 6d7296b9e2830f50  613 us/it
2021-09-23 01:05:05 gfx1030-0 77936867       110000   0.14% 8cbfd4435622bda7  614 us/it
2021-09-23 01:05:11 gfx1030-0 77936867       120000   0.15% 79ae5dad855057ad  614 us/it
2021-09-23 01:05:17 gfx1030-0 77936867       130000   0.17% 50c97bcbf876231f  614 us/it
2021-09-23 01:05:23 gfx1030-0 77936867       140000   0.18% e1db15f897271496  615 us/it
2021-09-23 01:05:29 gfx1030-0 77936867       150000   0.19% 127631386c6a9b17  615 us/it
2021-09-23 01:05:36 gfx1030-0 77936867       160000   0.21% 25b7b6206fc6f085  625 us/it
2021-09-23 01:05:42 gfx1030-0 77936867       170000   0.22% 416816b0d9f4bba8  615 us/it
2021-09-23 01:05:48 gfx1030-0 77936867       180000   0.23% 6bee5d054f770861  616 us/it
2021-09-23 01:05:54 gfx1030-0 77936867       190000   0.24% f37f068f014b18a0  616 us/it
2021-09-23 01:06:01 gfx1030-0 77936867 OK    200000   0.26% f0b04b45b0855bd2  616 us/it + check 0.27s + save 0.08s; ETA 13:18
2021-09-23 01:06:07 gfx1030-0 77936867       210000   0.27% 43eb2fc2424d8aac  615 us/it
2021-09-23 01:06:13 gfx1030-0 77936867       220000   0.28% a1081c6dc6a7689f  616 us/it
2021-09-23 01:06:19 gfx1030-0 77936867       230000   0.30% 2387818d3d3d0d01  627 us/it
2021-09-23 01:06:25 gfx1030-0 77936867       240000   0.31% a9deae45055e5216  616 us/it
2021-09-23 01:06:32 gfx1030-0 77936867       250000   0.32% 89fcab15218f7cac  616 us/it
2021-09-23 01:06:38 gfx1030-0 77936867       260000   0.33% 55da428da4cf928a  617 us/it
2021-09-23 01:06:44 gfx1030-0 77936867       270000   0.35% dc349756c5f05abf  617 us/it
2021-09-23 01:06:50 gfx1030-0 77936867       280000   0.36% 3564af24488443f4  617 us/it
2021-09-23 01:06:56 gfx1030-0 77936867       290000   0.37% 63fb281a06f78198  618 us/it
2021-09-23 01:07:02 gfx1030-0 77936867       300000   0.38% 990aa099aad5bf9c  617 us/it
2021-09-23 01:07:09 gfx1030-0 77936867       310000   0.40% 61e14297a2cc0096  628 us/it
2021-09-23 01:07:15 gfx1030-0 77936867       320000   0.41% 37e630c5f956cf8a  619 us/it
2021-09-23 01:07:21 gfx1030-0 77936867       330000   0.42% 66ccde7e28ce2b33  619 us/it
2021-09-23 01:07:27 gfx1030-0 77936867       340000   0.44% d4a7cff61adaa84e  620 us/it
2021-09-23 01:07:33 gfx1030-0 77936867       350000   0.45% d57b659cc1ca2753  620 us/it
2021-09-23 01:07:40 gfx1030-0 77936867       360000   0.46% 992df79b843f90de  620 us/it
2021-09-23 01:07:46 gfx1030-0 77936867       370000   0.47% 10b0b99eba490a1e  620 us/it
2021-09-23 01:07:52 gfx1030-0 77936867       380000   0.49% 56b1e40cd2666109  621 us/it
2021-09-23 01:07:58 gfx1030-0 77936867       390000   0.50% ecccd874a8a0d961  630 us/it
2021-09-23 01:08:05 gfx1030-0 77936867 Stopping, please wait..
2021-09-23 01:08:05 gfx1030-0 77936867 OK    400000   0.51% c03f94396a5aa29e  621 us/it + check 0.27s + save 0.08s; ETA 13:23
2021-09-23 01:08:05 gfx1030-0 Exiting because "stop requested"
2021-09-23 01:08:05 gfx1030-0 Bye

moebius · 2021-10-11, 22:01

gpuOwl-ComparisonList updated

Format: Unified Office Format (.ods)
created with: LibreOffice Calc 7.1.2.1
size of file: 1007 KB
downloadable
best viewable in Google Drive with: Zoho Sheet App

moebius · 2021-10-13, 10:39

Sapphire Nitro+ RX 6700XT

Dobri · 2021-11-14, 05:33

Quote:

Originally Posted by kracker

2) Download and install AMD APP SDK(make sure you use the 64bit version) for Windows: https://developer.amd.com/amd-accele...ssing-app-sdk/

AMD APP SDK was removed from AMD's official website in 2018 because the required libraries are now included with the drivers, see https://en.wikipedia.org/wiki/AMD_APP_SDK.
Anyway, it still could be downloaded for Windows at https://www.softpedia.com/get/Progra...ream-SDK.shtml, and Linux at https://sourceforge.net/projects/nic...nt%20Platform/.

DrobinsonPE · 2021-12-03, 14:57

Moebius, here is another one for the bottom of your list.
MSI GT 730, N730K-2GD3H

Code:

C:\Users\User\gpuowl>gpuowl-win -iters 200000 -prp 77936867
2021-12-02 06:49:54 gpuowl v6.11-380-g79ea0cc
2021-12-02 06:49:54 config: -log 20000 -safeMath
2021-12-02 06:49:54 config: -iters 200000 -prp 77936867
2021-12-02 06:49:54 device 0, unique id ''
2021-12-02 06:49:54 NVIDIA GeForce GT 730-0 77936867 FFT: 4M 1K:8:256 (18.58 bpw)
2021-12-02 06:49:54 NVIDIA GeForce GT 730-0 Expected maximum carry32: 583B0000
2021-12-02 06:49:54 NVIDIA GeForce GT 730-0 OpenCL args "-DEXP=77936867u -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=8u -DPM1=0 -DMM_CHAIN=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -DWEIGHT_STEP_MINUS_1=0xa.c42d0d7cec038p-5 -DIWEIGHT_STEP_MINUS_1=-0x8.0e50c8817ddf8p-5  -cl-std=CL2.0 -cl-finite-math-only "
2021-12-02 06:49:54 NVIDIA GeForce GT 730-0 OpenCL compilation in 0.03 s
2021-12-02 06:50:11 NVIDIA GeForce GT 730-0 77936867 OK    40000 loaded: blockSize 400, dffe1b1b0d748128
2021-12-02 06:50:11 NVIDIA GeForce GT 730-0 validating proof residues for power 8
2021-12-02 06:50:11 NVIDIA GeForce GT 730-0 Proof using power 8
2021-12-02 06:50:58 NVIDIA GeForce GT 730-0 77936867 OK    40800   0.05%; 38503 us/it; ETA 34d 17:08; d10fb3f9fc9c42b7 (check 15.53s)
2021-12-02 07:03:33 NVIDIA GeForce GT 730-0 77936867 OK    60000   0.08%; 38516 us/it; ETA 34d 17:12; 0945da4dc08bdd95 (check 15.48s)
2021-12-02 07:16:39 NVIDIA GeForce GT 730-0 77936867 OK    80000   0.10%; 38543 us/it; ETA 34d 17:34; 8d76071d27ee4221 (check 15.46s)
2021-12-02 07:29:37 NVIDIA GeForce GT 730-0 77936867 OK   100000   0.13%; 38125 us/it; ETA 34d 08:19; 6d7296b9e2830f50 (check 15.27s)
2021-12-02 07:42:33 NVIDIA GeForce GT 730-0 77936867 OK   120000   0.15%; 38042 us/it; ETA 34d 06:19; 79ae5dad855057ad (check 15.26s)
2021-12-02 07:55:29 NVIDIA GeForce GT 730-0 77936867 OK   140000   0.18%; 38042 us/it; ETA 34d 06:06; e1db15f897271496 (check 15.26s)
2021-12-02 08:08:25 NVIDIA GeForce GT 730-0 77936867 OK   160000   0.21%; 38042 us/it; ETA 34d 05:54; 25b7b6206fc6f085 (check 15.26s)
2021-12-02 08:21:21 NVIDIA GeForce GT 730-0 77936867 OK   180000   0.23%; 38044 us/it; ETA 34d 05:43; 6bee5d054f770861 (check 15.26s)
2021-12-02 08:34:18 NVIDIA GeForce GT 730-0 77936867 OK   200000   0.26%; 38044 us/it; ETA 34d 05:30; f0b04b45b0855bd2 (check 15.34s)
2021-12-02 08:47:14 NVIDIA GeForce GT 730-0 77936867 OK   220000   0.28%; 38042 us/it; ETA 34d 05:15; a1081c6dc6a7689f (check 15.26s)
2021-12-02 08:59:39 NVIDIA GeForce GT 730-0 Stopping, please wait..
2021-12-02 09:00:10 NVIDIA GeForce GT 730-0 77936867 OK   240000   0.31%; 38042 us/it; ETA 34d 05:02; a9deae45055e5216 (check 15.26s)
2021-12-02 09:00:10 NVIDIA GeForce GT 730-0 Exiting because "stop requested"
2021-12-02 09:00:10 NVIDIA GeForce GT 730-0 Bye

Xyzzy · 2021-12-04, 00:40

6900XT (XTXH)

Code:

20211203 17:16:17 GpuOwl VERSION v7.2-86-gddf3314
20211203 17:16:17 config: -maxAlloc 12288
20211203 17:16:17 config: -prp 77936867 
20211203 17:16:17 device 0, unique id ''
20211203 17:16:17 gfx1030-0 77936867 FFT: 4M 1K:8:256 (18.58 bpw)
20211203 17:16:17 gfx1030-0 77936867 OpenCL args "-DEXP=77936867u -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=8u -DAMDGPU=1 -DMM_CHAIN=1u -DMM2_CHAIN=2u -DMAX_ACCURACY=1 -DWEIGHT_STEP=0.33644726404543274 -DIWEIGHT_STEP=-0.25174750481886216 -DIWEIGHTS={0,-0.44011820345520131,-0.37306474779553728,-0.29798072935699788,-0.21390437908665341,-0.11975874301407295,-0.014337887291734644,-0.44814572555075455,} -DFWEIGHTS={0,0.78609128957452257,0.5950610473469905,0.42446232150303748,0.2721098723818392,0.1360521812214803,0.014546452690911484,0.81207258201996746,}  -cl-std=CL2.0 -cl-finite-math-only "
20211203 17:16:19 gfx1030-0 77936867 OpenCL compilation in 1.63 s
20211203 17:16:19 gfx1030-0 77936867 maxAlloc: 12.0 GB
20211203 17:16:19 gfx1030-0 77936867 P1(0) 0 bits
20211203 17:16:19 gfx1030-0 77936867 PRP starting from beginning
20211203 17:16:19 gfx1030-0 77936867 OK         0 on-load: blockSize 400, 0000000000000003
20211203 17:16:19 gfx1030-0 77936867 validating proof residues for power 8
20211203 17:16:19 gfx1030-0 77936867 Proof using power 8
20211203 17:16:20 gfx1030-0 77936867 OK       800   0.00% 1579c241dc63eca6  571 us/it + check 0.26s + save 0.08s; ETA 12:21
20211203 17:16:26 gfx1030-0 77936867     10000 fc4f135f7cf4ad29  573
20211203 17:16:31 gfx1030-0 77936867     20000 3cd1bd9d5e09cbc5  574
20211203 17:16:37 gfx1030-0 77936867     30000 c4e0ff35e3290d98  574
20211203 17:16:43 gfx1030-0 77936867     40000 dffe1b1b0d748128  574
20211203 17:16:49 gfx1030-0 77936867     50000 52e286945371ed29  575
20211203 17:16:54 gfx1030-0 77936867     60000 0945da4dc08bdd95  576
20211203 17:17:00 gfx1030-0 77936867     70000 7131fa4eb77f4bb2  576
20211203 17:17:06 gfx1030-0 77936867     80000 8d76071d27ee4221  578
20211203 17:17:12 gfx1030-0 77936867     90000 0bacff453b2f470e  578
20211203 17:17:17 gfx1030-0 77936867    100000 6d7296b9e2830f50  579
20211203 17:17:23 gfx1030-0 77936867    110000 8cbfd4435622bda7  580
20211203 17:17:29 gfx1030-0 77936867    120000 79ae5dad855057ad  580
20211203 17:17:35 gfx1030-0 77936867    130000 50c97bcbf876231f  580
20211203 17:17:41 gfx1030-0 77936867    140000 e1db15f897271496  581
20211203 17:17:46 gfx1030-0 77936867    150000 127631386c6a9b17  581
20211203 17:17:52 gfx1030-0 77936867    160000 25b7b6206fc6f085  582
20211203 17:17:58 gfx1030-0 77936867    170000 416816b0d9f4bba8  582
20211203 17:18:04 gfx1030-0 77936867    180000 6bee5d054f770861  582
20211203 17:18:10 gfx1030-0 77936867    190000 f37f068f014b18a0  583
20211203 17:18:16 gfx1030-0 77936867 OK    200000   0.26% f0b04b45b0855bd2  583 us/it + check 0.26s + save 0.09s; ETA 12:35
20211203 17:18:22 gfx1030-0 77936867    210000 43eb2fc2424d8aac  582
20211203 17:18:28 gfx1030-0 77936867    220000 a1081c6dc6a7689f  584
20211203 17:18:33 gfx1030-0 77936867    230000 2387818d3d3d0d01  585
20211203 17:18:39 gfx1030-0 77936867    240000 a9deae45055e5216  584
20211203 17:18:45 gfx1030-0 77936867    250000 89fcab15218f7cac  584
20211203 17:18:51 gfx1030-0 77936867    260000 55da428da4cf928a  585
20211203 17:18:57 gfx1030-0 77936867    270000 dc349756c5f05abf  585
20211203 17:19:03 gfx1030-0 77936867    280000 3564af24488443f4  585
20211203 17:19:08 gfx1030-0 77936867    290000 63fb281a06f78198  585
20211203 17:19:14 gfx1030-0 77936867    300000 990aa099aad5bf9c  585
20211203 17:19:20 gfx1030-0 77936867    310000 61e14297a2cc0096  596
20211203 17:19:26 gfx1030-0 77936867    320000 37e630c5f956cf8a  585
20211203 17:19:32 gfx1030-0 77936867    330000 66ccde7e28ce2b33  585
20211203 17:19:38 gfx1030-0 77936867    340000 d4a7cff61adaa84e  585
20211203 17:19:44 gfx1030-0 77936867    350000 d57b659cc1ca2753  585
20211203 17:19:50 gfx1030-0 77936867    360000 992df79b843f90de  585
20211203 17:19:55 gfx1030-0 77936867    370000 10b0b99eba490a1e  585
20211203 17:20:01 gfx1030-0 77936867    380000 56b1e40cd2666109  586
20211203 17:20:07 gfx1030-0 77936867    390000 ecccd874a8a0d961  586
20211203 17:20:13 gfx1030-0 77936867 OK    400000   0.51% c03f94396a5aa29e  587 us/it + check 0.27s + save 0.09s; ETA 12:38
20211203 17:20:19 gfx1030-0 77936867    410000 bf44242560060429  587
20211203 17:20:25 gfx1030-0 77936867    420000 7f656173fb521927  586
20211203 17:20:31 gfx1030-0 77936867    430000 b6c7618e60b71bb7  586
20211203 17:20:37 gfx1030-0 77936867    440000 200cbc3b887fcfb2  587
20211203 17:20:43 gfx1030-0 77936867    450000 4811fce58ccc9cab  588
20211203 17:20:49 gfx1030-0 77936867    460000 15cb337858fe7eb1  587
20211203 17:20:54 gfx1030-0 77936867    470000 ad96b1f48c8bf011  587
20211203 17:21:00 gfx1030-0 77936867    480000 93e184ebad6d3cd4  587
20211203 17:21:06 gfx1030-0 77936867    490000 70160baec6378071  587
20211203 17:21:12 gfx1030-0 77936867    500000 591eecd8448042ad  587
20211203 17:21:18 gfx1030-0 77936867    510000 8afd187213816739  588
20211203 17:21:24 gfx1030-0 77936867    520000 74e993308f33ac5b  587
20211203 17:21:30 gfx1030-0 77936867    530000 57c0f9c504186096  587
20211203 17:21:36 gfx1030-0 77936867    540000 bcb42100a7c391ad  587
20211203 17:21:41 gfx1030-0 77936867    550000 ff6f9c39e0347941  587
20211203 17:21:47 gfx1030-0 77936867    560000 9a740c005539ec84  587
20211203 17:21:53 gfx1030-0 77936867    570000 a82132fa0e95b673  587
20211203 17:21:59 gfx1030-0 77936867    580000 200fc0c1347e2854  587
20211203 17:22:05 gfx1030-0 77936867    590000 48edfb50a88114d1  588
20211203 17:22:11 gfx1030-0 77936867 OK    600000   0.77% b9decd65ca71b629  587 us/it + check 0.27s + save 0.09s; ETA 12:37
20211203 17:22:17 gfx1030-0 77936867    610000 15a66f18e764db77  598
20211203 17:22:23 gfx1030-0 77936867    620000 e35adf8422264428  587
20211203 17:22:29 gfx1030-0 77936867    630000 fd5849d82defeb62  587
20211203 17:22:35 gfx1030-0 77936867    640000 45736f195df56074  587
20211203 17:22:41 gfx1030-0 77936867    650000 947e1ab8b4dc318d  588
20211203 17:22:46 gfx1030-0 77936867    660000 acec19d8201699ce  589
20211203 17:22:52 gfx1030-0 77936867    670000 a513b29e0a46fc34  588
20211203 17:22:58 gfx1030-0 77936867    680000 8cccb6612f0f52c0  588
20211203 17:23:04 gfx1030-0 77936867    690000 1518615a0cf6e034  588
20211203 17:23:10 gfx1030-0 77936867    700000 310e1a3255551a62  589
20211203 17:23:16 gfx1030-0 77936867    710000 591e3891de6d29a1  588
20211203 17:23:22 gfx1030-0 77936867    720000 f61357a1e2bf3240  588
20211203 17:23:28 gfx1030-0 77936867    730000 9b186483d53f0d88  588
20211203 17:23:33 gfx1030-0 77936867    740000 7a12be1526255968  588
20211203 17:23:39 gfx1030-0 77936867    750000 b4f2e6d7a6a6615c  588
20211203 17:23:45 gfx1030-0 77936867    760000 0a1ba085f801c4c5  588
20211203 17:23:51 gfx1030-0 77936867    770000 9d7bbfb9f93deb22  588
20211203 17:23:57 gfx1030-0 77936867    780000 8600d4ab710627c0  588
20211203 17:24:03 gfx1030-0 77936867    790000 9a71d05fe3b961ff  588
20211203 17:24:09 gfx1030-0 77936867 OK    800000   1.03% 21ebf3636148f663  588 us/it + check 0.27s + save 0.09s; ETA 12:36
20211203 17:24:15 gfx1030-0 77936867    810000 52386f2e497aa955  587
20211203 17:24:21 gfx1030-0 77936867    820000 c481c083465a7b07  588
20211203 17:24:27 gfx1030-0 77936867    830000 96aea2b137ce50af  588
20211203 17:24:33 gfx1030-0 77936867    840000 84be20a8d22048ad  588
20211203 17:24:39 gfx1030-0 77936867    850000 78f3bbdeabd2bc02  588
20211203 17:24:44 gfx1030-0 77936867    860000 10c80cdb7eebced2  588
20211203 17:24:50 gfx1030-0 77936867    870000 b4cbb9d09f0fd89f  589
20211203 17:24:56 gfx1030-0 77936867    880000 5a5645c14acb870e  588
20211203 17:25:02 gfx1030-0 77936867    890000 2fc993d10648bd75  589
20211203 17:25:08 gfx1030-0 77936867    900000 518b906b58c64c40  589
20211203 17:25:14 gfx1030-0 77936867    910000 431308ea83b6c0ce  588
20211203 17:25:20 gfx1030-0 77936867    920000 62f61b11720d5394  599
20211203 17:25:26 gfx1030-0 77936867    930000 febec5e60548f928  589
20211203 17:25:32 gfx1030-0 77936867    940000 45c594641c8b2e5f  588
20211203 17:25:38 gfx1030-0 77936867    950000 ec9dfef8e2deb9bf  590
20211203 17:25:43 gfx1030-0 77936867    960000 259e2b4b65b85c03  588
20211203 17:25:49 gfx1030-0 77936867    970000 abd30602b41f18ec  588
20211203 17:25:55 gfx1030-0 77936867    980000 16471b2f3972a667  588
20211203 17:26:01 gfx1030-0 77936867    990000 1a6a0fc93f328b02  589
20211203 17:26:07 gfx1030-0 77936867 OK   1000000   1.28% 9bf9d9e6bff4286e  589 us/it + check 0.27s + save 0.09s; ETA 12:35

tServo · 2021-12-06, 22:31

Is there any place that explains how to optimize Gpuowl ? I didn't see it in Kriesel's docs.
Is there a script that assists in selecting the parameters?

kriesel · 2021-12-06, 22:46

Quote:

Originally Posted by tServo

Is there any place that explains how to optimize Gpuowl ? I didn't see it in Kriesel's docs.
Is there a script that assists in selecting the parameters?

Yes, there was a lot of discussion and benchmark posting a while back (beginning ~https://www.mersenneforum.org/showpo...postcount=1528, going up to V6.11-2xx days I think).
A detailed multiple-version-specific treatise/tutorial? No. There were a great many commits, in V6.11 through v7.2, and along the way, some of the tune -use options best choices got incorporated into the code as defaults for AMD GPUs or for NVIDIA GPUs or became obsolete. One easy way to tune is to look at already collected benchmarks, and select a gpuowl version that does well for what you want to do.
There's also a little performance variables guidance.

What are you planning to run, on what hardware, and what parameters concern or interest you?

2021-10-11, 22:01	#2733
moebius Jul 2009 Germany 2·353 Posts	gpuOwl-ComparisonList updated Format: Unified Office Format (.ods) created with: LibreOffice Calc 7.1.2.1 size of file: 1007 KB downloadable best viewable in Google Drive with: Zoho Sheet App Last fiddled with by moebius on 2021-10-11 at 22:03

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
mfakto: an OpenCL program for Mersenne prefactoring	Bdot	GPU Computing	1724	2023-06-04 23:31
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

2021-10-13, 10:39	#2734
moebius Jul 2009 Germany 706₁₀ Posts	Sapphire Nitro+ RX 6700XT

2021-12-06, 22:31	#2738
tServo "Marv" May 2009 near the Tannhäuser Gate 3×269 Posts	Is there any place that explains how to optimize Gpuowl ? I didn't see it in Kriesel's docs. Is there a script that assists in selecting the parameters?