holt@inco.UUCP (07/14/87)
<I'm posting this for Bryan Wolf, McDonnell Douglas - Inco, Inc.> How many concurrent *Ada* tasks has anyone out there in net.land managed to have running simultaneously, with regards to performance and on what hardware? -- /*--------------------------------------------------------------* * Mark L Holt * * McDonnell Douglas - Inco, Inc. * * ...!seismo!sundc!hadron!inco!holt * * "If you ain't the lead dog, the scenery never changes" * * DISCLAIMER: The opinions expressed are my own and in no way * * reflect the views of McDonnell Douglas or its subsidiaries. * *--------------------------------------------------------------*/
Bryan@SIERRA.STANFORD.EDU (Doug Bryan) (07/15/87)
> How many concurrent *Ada* tasks has anyone out there in net.land > managed to have running simultaneously, with regards to performance > and on what hardware? one (aren't all validiated compilers for single CPU targets?) doug -------
stt@inmet.UUCP (07/17/87)
As a test case, we created and executed a program which spawned more than 500 Ada tasks using the Intermetrics Real-Time MVS Ada compiler on a 4341. This compiler uses one MVS task for each Ada task, and provides for "true" concurrency on a multi-processor such as a 3090. The primary performance problem involved certain linear-list algorithms inherent in MVS dealing with task creation. Once the tasks were created, performance was "fine." Tucker Taft c/o Intermetrics, Inc. Cambridge, MA 02138