What happen with the error log "errors: 1579 (DIED!)" ?

[HenryJan]

Hi,

The system replies "errors: 1579 (DIED!)", the log is showed below and attached.

================================
1.6% proc'd: -1 (52755 Gflop/s) errors: 1579 (DIED!) temps: 29 C Initialized device 0 with 16108 MB of memory (15422 MB available, using 13880 MB of it), using FLOATS

If anyone know what happened and the direction to solve it?
Thanks.

gpu_burn_error_log_0108.txt

[wilicc]

Hi @HenryJan! Can you attach dmesg logs right after the faulty run? That should tell whether the GPU actually died (dropped off the bus) or if this is just the software malfunctioning.

[HenryJan]

Hi @wilicc

I didn't try dmesg, but "nvtop" was staied online.
The GPU status was always showed on nvtop console.

If it has the documents for "errors: 2...errors: 3...errors: 1573" log meaning reference?

Thanks.

[wang-davie]

I met a similar issue when I executed the command "./gpu_burn 60" .
The terminal printed like these:
"30.0% proc'd: -1 (0 Gflop/s) - -1 (0 Gflop/s) - -1 (0 Gflop/s) - -1 (0 Gflop/s) - -1 (0 Gflop/s) - -1 (0 Gflop/s) - -1 (0 Gflop/s) - -1 (0 Gflop/s) errors: -533715488 (DIED!)- -533715488 (DIED!)- -533715488 (DIED!)- -533715488 (DIED!)- -533715488 (DIED!)- -533715488 (DIED!)- -533715488 (DIED!)- 1278531568 (DIED!) temps: 30 C - 30 C - 30 C - 30 C - 29 C - 31 C - 30 C - 30 C

No clients are alive! Aborting"