too many exit(0)s

Hi there, I've got some error WUs that I can't make any sense from. They got this stderr (or similar):

[pre]6.10.17

too many exit(0)s

n time in seconds: 2099.5565
------> Time stamp (MJD): 51039.128816081604
------> Number of samples/record: 0
------> Center freq in MHz: 1231.5
------> Channel band in MHz: 3
------> Number of channels/record: 96
------> Nifs: 1
------> RA (J2000): 151546.764
------> DEC (J2000): -583428.594999
------> Galactic l: 0
------> Galactic b: 0
------> Name: G4832496
------> Lagformat: 0
------> Sum: 1
------> Level: 3
------> AZ at start: 0
------> ZA at start: 0
------> AST at start: 0
------> LST at start: 0
------> Project ID: --
------> Observers: --
------> File size (bytes): 0
------> Data size (bytes): 0
------> Number of samples: 4194304
------> Trial dispersion measure: 208 cm^-3 pc
------> Scale factor: 15.875
[19:58:23][30891][INFO ] Seed for random number generator is 1057030660.
[19:58:24][30891][ERROR] Error creating CUDA FFT plan (error code: 2)
[19:58:24][30891][ERROR] Demodulation failed (error: 1011)!
[19:58:24][30891][WARN ] CUDA memory allocation problem encountered!
------> Returning control to BOINC, delaying restart for at least five minutes...
------> If this problem persists you should consider aborting this task.
[19:58:24][30894][INFO ] Starting data processing...
[19:58:24][30894][INFO ] CUDA global memory status (initial GPU state, including context):
------> Used in total: 341 MB (171 MB free / 512 MB total) -> Used by this application (assuming a single GPU task): 0 MB
[19:58:24][30894][INFO ] Using CUDA device #0 "GeForce GT 240" (96 CUDA cores / 385.92 GFLOPS)
[19:58:24][30894][INFO ] Version of installed CUDA driver: 4000
[19:58:24][30894][INFO ] Version of CUDA driver API used: 3020
[19:58:24][30894][INFO ] Checkpoint file unavailable: status.cpt (No such file or directory).
------> Starting from scratch...
[19:58:24][30894][INFO ] Header contents:
------> Original WAPP file: /BOINC/projects/EinsteinAtHome/temp_working/BRP3/PM0061_03451/PM0061_03451_DM208.00
------> Sample time in microseconds: 500
------> Observation time in seconds: 2099.5565
------> Time stamp (MJD): 51039.128816081604
------> Number of samples/record: 0
------> Center freq in MHz: 1231.5
------> Channel band in MHz: 3
------> Number of channels/record: 96
------> Nifs: 1
------> RA (J2000): 151546.764
------> DEC (J2000): -583428.594999
------> Galactic l: 0
------> Galactic b: 0
------> Name: G4832496
------> Lagformat: 0
------> Sum: 1
------> Level: 3
------> AZ at start: 0
------> ZA at start: 0
------> AST at start: 0
------> LST at start: 0
------> Project ID: --
------> Observers: --
------> File size (bytes): 0
------> Data size (bytes): 0
------> Number of samples: 4194304
------> Trial dispersion measure: 208 cm^-3 pc
------> Scale factor: 15.875
[19:58:26][30894][INFO ] Seed for random number generator is 1057030660.
[19:58:27][30894][ERROR] Error creating CUDA FFT plan (error code: 2)
[19:58:27][30894][ERROR] Demodulation failed (error: 1011)!
[19:58:27][30894][WARN ] CUDA memory allocation problem encountered!
------> Returning control to BOINC, delaying restart for at least five minutes...
------> If this problem persists you should consider aborting this task.
[19:58:28][30896][INFO ] Starting data processing...
[19:58:28][30896][INFO ] CUDA global memory status (initial GPU state, including context):
------> Used in total: 341 MB (171 MB free / 512 MB total) -> Used by this application (assuming a single GPU task): 0 MB
[19:58:28][30896][INFO ] Using CUDA device #0 "GeForce GT 240" (96 CUDA cores / 385.92 GFLOPS)
[19:58:28][30896][INFO ] Version of installed CUDA driver: 4000
[19:58:28][30896][INFO ] Version of CUDA driver API used: 3020
[19:58:28][30896][INFO ] Checkpoint file unavailable: status.cpt (No such file or directory).
------> Starting from scratch...

[snip some lines]

------> Starting from scratch...
[20:00:06][31004][INFO ] Header contents:
------> Original WAPP file: /BOINC/projects/EinsteinAtHome/temp_working/BRP3/PM0061_03451/PM0061_03451_DM208.00
------> Sample time in microseconds: 500
------> Observation time in seconds: 2099.5565
------> Time stamp (MJD): 51039.128816081604
------> Number of samples/record: 0
------> Center freq in MHz: 1231.5
------> Channel band in MHz: 3
------> Number of channels/record: 96
------> Nifs: 1
------> RA (J2000): 151546.764
------> DEC (J2000): -583428.594999
------> Galactic l: 0
------> Galactic b: 0
------> Name: G4832496
------> Lagformat: 0
------> Sum: 1
------> Level: 3
------> AZ at start: 0
------> ZA at start: 0
------> AST at start: 0
------> LST at start: 0
------> Project ID: --
------> Observers: --
------> File size (bytes): 0
------> Data size (bytes): 0
------> Number of samples: 4194304
------> Trial dispersion measure: 208 cm^-3 pc
------> Scale factor: 15.875
[20:00:08][31004][INFO ] Seed for random number generator is 1057030660.
[20:00:09][31004][ERROR] Error creating CUDA FFT plan (error code: 2)
[20:00:09][31004][ERROR] Demodulation failed (error: 1011)!
[20:00:09][31004][WARN ] CUDA memory allocation problem encountered!
------> Returning control to BOINC, delaying restart for at least five minutes...
------> If this problem persists you should consider aborting this task.

]]>[/pre]

As you can see in my complete WU-list, it's nothing common on my machine, but has happened on several WUs in a kind of bunches.