Timeline for In theory, would an erosion algorithm compute faster on a GPU than CPU?
Current License: CC BY-SA 3.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 16, 2017 at 16:16 | history | edited | Pikalek | CC BY-SA 3.0 |
fixed spelling grammar, clarified nature of the question in the title
|
| Feb 16, 2017 at 13:50 | answer | added | Philipp | timeline score: 2 | |
| Feb 16, 2017 at 13:21 | review | Close votes | |||
| Mar 12, 2017 at 3:00 | |||||
| Feb 16, 2017 at 13:12 | comment | added | ratchet freak | depends on the workload, to port it to the gpu you'll need to parallelize it so you may as well make a inbetween stop at cpu multithreading | |
| Feb 16, 2017 at 13:06 | comment | added | LukeG | There's no reliable way to predict that. Is your algorithm highly parallelizable? If yes there's a good change perfomance will be much better on the GPU. But the only way to know for sure: Try it and profile both solutions. | |
| Feb 16, 2017 at 12:58 | history | asked | Werem | CC BY-SA 3.0 |