CUDA error in func 'search' at line 346 : unknown error.

[philejmath]

not sure if this is related to the other issues reported around search. seems to be a different line and message. miner hangs and attempts to kill the process crash my whole rig.

ubuntu 16.04, no OC, version .0.12.0.dev0 4x Asus 1060 Turbo

error:

CUDA error in func 'search' at line 346 : unknown error. 
05:07:10|cudaminer2  Error CUDA mining: unknown error
CUDA error in func 'search' at line 346 : unknown error. 
05:07:10|cudaminer3  Error CUDA mining: unknown error

strace:

prctl(PR_GET_NAME, "ethminer") = 0
write(2, "\33[32m m \33[35m00:15:25\33[0m\33[30m"..., 112) = 112
write(2, "\n", 1) = 1
nanosleep({0, 200000000}, NULL) = 0
stat("/etc/localtime", {st_mode=S_IFREG|0644, st_size=3545, ...}) = 0
prctl(PR_GET_NAME, "ethminer") = 0
write(2, "\33[32m m \33[35m00:15:25\33[0m\33[30m"..., 112) = 112
write(2, "\n", 1) = 1
nanosleep({0, 200000000}, NULL) = 0
futex(0x7ffeece242a8, FUTEX_WAIT_PRIVATE, 2, NULL

[mauadib]

I have asus GTX 1070 cards and I have hangs and random computer resets while mining..

[rizwansarwar]

@philejmath @mauadib check #72

[mauadib]

These are happening at stock frequencies NO OC at all, it is intermittent, I'm also using cuda-parallel-hash 1. The latest NVidia drivers 384.

[rizwansarwar]

@mauadib what card and what OS?

[philejmath]

I'm using drivers 381.22, I'm going to try and upgrade to 384 and see if I get the same error as #72

[mauadib]

Asus GTX 1070 gaming, Win 10, 384.54 drivers.

[ultimakaz]

palit gtx 1060 3gb, win 10, 382.74 drivers.

CUDA error in func 'ethash_cuda_miner::search' at line 365 : unspecified launch failure.
X 21:44:37|cudaminer1 Error CUDA mining: unspecified launch failure

[bartocc]

Same here with the following setup:

• drivers 381.22
• GPU: 6x Asus gtx 1060 3Gb Dual OC
• OS: Ubuntu 16.04

[FabianGabor]

Same here:

driver: 384.76
GPU: GTX 1060 6GB
OS: Win 10 x64 (latest updates)

[derubm]

Windows:

(linux should be easier to do)
(https://github.com/derubm/Ethminer_Watchdog)

[Malapha]

see here [Issue 72] There are some solutions with batch|powershell|php available..

[MariusVanDerWijden]

Is this still relevant?

[AndreaLanfranchi]

Yes it is still relevant.
Especially in junction with the fact that to avoid this you have to lower too much your overclock settings.
To avoid this error you have to stay 12%~15% less overclocked than in Claymore's which is a lot.

[DeadManWalkingTO]

GTX1060 +150/+500/65%TDP @ 23-24MHs

1. Try Update Drivers.
   Download and install the latests.

2. Try Update Ethminer.
   Download (or beter build) the latest.

3. Try use -U for CUDA devices.
   CUDA Hardware Test Launch Command:
   ethminer -RH -U -S eu1.ethermine.org:4444 -FS us1.ethermine.org:4444 -O 0x7013275311fc37ccc1e40193D75086293eCb43A4.issue128

4. Try to change P2 State and Power managment mode.
   You can use NVidiaProfileInspectorDmW.
   For the best mining hashrate choose from sector "5 - Common":

   • CUDA - Force P2 State (Set to "Off")
   • Power managment mode (Set to "Prefer maximum performance")

5. Try Tweak Win10.
   You can use Windows10MiningTweaksDmW (Solution for 100% CPU usage (Win10 - CUDA - OpenCL) #695).

6. Try Optimize/Overclock GPUs.
   You can use MSI Afterburner for GPU OverClock/Optimize.

7. Try use a WatchDog
   You can use ETHminerWatchDogDmW (Simple Script WatchDog #735).

Please feedback.
Thank you!