Timeline for Fast "index of minimum" for distances to points on single thread
Current License: CC BY-SA 4.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 23, 2019 at 4:47 | comment | added | Jerry Coffin | Just for what it's worth, this is exactly the sort of problem for which octrees were invented. | |
| Jul 21, 2019 at 23:31 | answer | added | user555045 | timeline score: 2 | |
| Jul 21, 2019 at 22:59 | comment | added | user555045 | AVX (aka AVX1) then? That does require some workarounds but nothing too bad | |
| Jul 21, 2019 at 22:53 | comment | added | HerpDerpington | @harold I think AVX2 would be incompatible with the machines I am using. It should be compatible with Ivy Bridge and KBL microarchitecture. | |
| Jul 21, 2019 at 21:16 | comment | added | user555045 | A whole bunch even just for x86 processors, and different architectures have their own kinds. Maybe you're OK with AVX2? (requires Haswell or newer from Intel, or from AMD Excavator or Ryzen) If some older hardware is a concern, maybe SSE4.1? | |
| Jul 21, 2019 at 21:09 | comment | added | HerpDerpington | @harold I'm new to SIMD so my question would be "which versions are there" :D | |
| Jul 21, 2019 at 19:09 | comment | added | user555045 | You've tagged this SIMD, but which versions of SIMD would you accept? | |
| Jul 21, 2019 at 18:08 | history | edited | HerpDerpington | CC BY-SA 4.0 |
edited title
|
| Jul 21, 2019 at 18:01 | history | edited | HerpDerpington | CC BY-SA 4.0 |
added 109 characters in body
|
| Jul 21, 2019 at 17:55 | history | asked | HerpDerpington | CC BY-SA 4.0 |