236
M. Tsuji et.al.
0
100
200
300
400
500
600
700
64
256
512
1024
Execution time (sec)
(procs/task)
20480x20480 Matrix, 1024 processes in total
02x02
04x04
08x08
Fig. 16 Execution time with FT for the number of cores for each task under fake errors. The graph
legends show the number of blocks
MTBF (90,000 s). Figure 16 shows the performance of the fault-tolerant mSPMD
programming execution under fake errors. Unfortunately, for the case of 1 × 1 block
and 1024 processes per task, it was not possible to complete the workflow, since
the face error ratio used in the experiment is higher than real systems. For the other
cases, the applications can be completed. The best combination of the number of
blocks and the number of processes per task is 4 × 4 blocks and 256 processes,
while it was 512 processes under the “no-error” condition. This is because the tasks
executed on a relatively small number of nodes are relatively easy to recover when
they fail.
8 Runtime Correctness Check for the mSPMD
Programming Model
8.1 Overview and Implementation
The mSPMD programming model has been proposed to realize scalability for large
scale systems. Additionally, as we discussed in Sect. 7, we support fault-tolerant