Welcome to od|forum

Register now to gain access to all of our features. Once registered and logged in, you will be able to contribute to this site by submitting your own content or replying to existing content. You'll be able to customize your profile, receive reputation points as a reward for submitting content, while also communicating with other members via your own private inbox, plus much more! This message will be removed once you have signed in.

malexander

Members
  • Content count

    732
  • Joined

  • Last visited

  • Days Won

    37

malexander last won the day on February 7

malexander had the most liked content!

Community Reputation

294 Excellent

1 Follower

About malexander

  • Rank
    Houdini Master
  • Birthday 03/06/1974

Contact Methods

  • Website URL
    sidefx.com

Personal Information

  • Name
    Mark Alexander
  1. Another Houdini user submitted a bug to SideFX and managed to resolve it himself, and the bug happened to catch my eye. Similar setup to yours.
  2. Someone found that turning off "Core Performance Boost" in the MSI x399 BIOS fixed crashes for them. Having no experience with that motherboard I don't know where that setting is, though.
  3. Higher RAM speeds do increase performance slightly. It's worth getting if the markup on the price is <10%, but that's rarely the case. Also it's harder to get fast RAM in large DIMM packs that you'd need to populate all the slots (4-8). If you have to choose, always go for more RAM over faster RAM. You can see the effect of RAM speed, and NUMA, in the first page of this article: http://www.anandtech.com/show/11726/retesting-amd-ryzen-threadrippers-game-mode-halving-cores-for-more-performance
  4. Take the 1080Ti. You won't regret it. The iMac, on the other hand.... (^^^)
  5. Well for one, it's really hard to display ptex in realtime using any of the current APIs. The individual textures need to be assigned to an atlas as DX and GL don't support infinite numbers of texture samplers (in most cases), and that texture atlas setup isn't exactly speedy especially if you're still modelling.
  6. The Zen cores are arranged in modules of 4. Intel cores are generally paired together with shared L2, though I think the latest iteration of Skylake-E removes that (7xx0 series). It's pretty common practice to have cores share some resources to keep power requirements down. Ryzen has two of those modules on a die with a memory controller. Threadripper has 4 modules with 2 memory controllers, and that's where the NUMA (non-uniform memory arrangement) and proper OS scheduling comes into play. The first 2 modules have access to one bank of memory, and the other 2 modules have access to the other bank. If a core from one module needs memory from the other module's bank, there's an extra hop to access the memory. That's the "non-uniform" part, since RAM latency can vary based on its physical location. Accessing RAM is already pretty slow, which is why CPUs have large L3 caches, and use SMT (aka Hyperthreading(tm)) to hide the RAM access latency. Thread stalled on a memory request? Switch to the other one that's parked on the core and continue crunching numbers. The OS scheduler is also responsible for keeping threads on one module or the other if possible, so these days NUMA doesn't have quite the hit that it used to on the older multi-socket servers. That's why sometimes a software or firmware update is needed for new CPUs.
  7. Before VEX Houdini had TOPs, which were Texture OPs. But the new TOPs is not a reincarnation of them. Try again
  8. I believe the intention was always to post them after the conference, and they were accidentally made public and that's been fixed. But from what I saw of the them, they'll be worth the wait
  9. The SideFX sessions will be posted to the GoProcedural channel on Vimeo once the conference is over.
  10. You'll be able to get a better picture on August 14th, when the cards are released. Drivers play such a crucial role these days that hardware numbers' analysis isn't very accurate.
  11. Houdini either uses OpenCL 1.1 or 1.2. OpenCL 2.0 doesn't expose any features which Houdini needs right now. Single precision is also more important at the moment, and as Atom says, only 1 compute device is currently supported.
  12. EXR is a linear-space format. No conversions are done when writing from mantra (which working in linear natively) to EXR.
  13. COPs has a standard color scheme, which was implemented with the original design: Generators are green VEX operators are purple Operators which don't affect image data are beige (timing operations, control flow, etc) Collapsible Color Corrections (precursor of Compile SOP networks) are blue The last three had special meanings with regards to cooking, which is why they were colored by default. VEX operators could bind planes named the same as VEX function parameters, Timing operators didn't take long to cook because they didn't modify image data, and Color Correction nodes would be collapsed into a single operation if there were no other non-color correction operations between them, saving memory and improving performance. But other than that, I don't believe there are any standard color schemes in Houdini.
  14. Crowd display unfortunately doesn't work on Mac because the GLSL shader just... doesn't draw anything (?!). The same shader works on other platforms. If you switch to wireframe you can at least see the rigs.