Checkpointing

A method of operating a first subsystem comprising one or more first processors;

• the method comprising, by running a first program on the first subsystem:
• sending data from the first subsystem to a second subsystem comprising one or more second processors, wherein a second program is arranged to run on the one or more second processors, the second program being configured to operate on the data sent from the first subsystem;
• setting a checkpoint at a point in time, including recording in a memory of the first subsystem i) a program state of the second program, comprising at least a state of one or more registers on each of the one or more second processors at the point in time of the checkpoint, and ii) a copy of the data sent to the second subsystem in a time since the checkpoint;
• and
• upon detection of a replay event, re-sending from the first subsystem to the second subsystem the data recorded since the checkpoint, and controlling the second subsystem to replay at least part of the second program on at least one of the one or more second processors from the checkpoint, starting with the recorded program state and operating on the re-sent data.

A first program comprising code embodied on non-transitory computer-readable storage and configured so as when run on a first subsystem comprising one or more first processors to perform operations of:

• sending data from the first subsystem to a second program run on a second subsystem comprising one or more second processors, the second program being configured to operate on the data sent from the first subsystem;
• setting a checkpoint at a point in time, including recording in a memory of the first subsystem i) a program state of the second program, comprising at least a state of one or more registers on each of the one or more second processors at the point in time of the checkpoint, and ii) a copy of the data sent to the second subsystem in a time since the checkpoint;
• and
• upon detection of a replay event, re-sending from the first subsystem to the second subsystem the data recorded since the checkpoint, and controlling the second subsystem to replay at least part of the second program on at least one of the one or more second processors from the checkpoint, starting with the recorded program state and operating on the re-sent data.