Timeline for When does NDSolve parallelize ODE system solving?
Current License: CC BY-SA 4.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 11, 2019 at 11:56 | comment | added | Michael E2 |
@xzczd Thank you for the bounty. Your comment explains why I couldn't find this chat message. Comparing the ParallelOptions" suggests internal parallelization has changed in V12. In V11.3 with n = 4096, I get up to 200% kernel activity (which I interpret as 2 of 4 cores being used), but I cannot find a way to control a threshold for it (neither "VectorArithmeticThresholds" nor "MachineFunctionParallelThresholds" made a difference).
|
|
| Nov 11, 2019 at 7:01 | vote | accept | xzczd♦ | ||
| Nov 11, 2019 at 7:01 | history | bounty ended | xzczd♦ | ||
| Nov 11, 2019 at 7:01 | comment | added | xzczd♦ |
Just a side note: in v11.3 there's no VectorParallelLengthThresholds option. There's a "MachineFunctionParallelThresholds" option whose option value is {196608, 98304, 98304, 65536, 49152}, but lowering the option value doesn't seem to trigger parallelization.
|
|
| Nov 4, 2019 at 13:37 | comment | added | Michael E2 | @ilian Thanks for pointing it out. | |
| Nov 4, 2019 at 13:36 | history | edited | Michael E2 | CC BY-SA 4.0 |
Fixed typo
|
| Nov 4, 2019 at 13:28 | comment | added | ilian | +1, perhaps 'autocompilation' is not quite the right term | |
| Nov 4, 2019 at 13:16 | history | edited | Michael E2 | CC BY-SA 4.0 |
Fixed typo
|
| Nov 4, 2019 at 13:07 | history | answered | Michael E2 | CC BY-SA 4.0 |