|
bah, tried to find my opencl error log with "struct float3 aka struct ___do_not_use_float3_type_not_supported___" but it's nowhere to be found
|
#
¿
Sep 29, 2017 09:41
|
|
|
|
| # ¿ May 22, 2024 16:56 |
|
|
my fellow, have you heard of SPIR-V???
|
|
#
¿
Sep 30, 2017 10:51
|
|
|
gpus have video encoders so you can do screen capture without sending a full image of the screen back down the bus to main memory to be encoded on the CPU, which is slow and would also cut into the CPU resource available for xtreme gaming action. nvidia had H.264 running in CUDA but it was kinda slow and crappy and also cut into the amount of GPU time available for graphics drawing, and they already had a video decoder up there so w/e. fun fact: the nvidia hardware encoder supports something silly like 8 simultaneous encode streams so you can put out an entire HLS block at once.
|
|
#
¿
Oct 3, 2017 11:16
|
|
|
ate all the Oreos posted:mind directing me to this, because i'd really like to be able to actually use graphics card acceleration for encoding jobs on my server and i wasn't able to find anything like it this was back in ~2013 and i think they've removed/broken it since. it was called NVCUVENC, anyhow, and it claimed to be CUDA but it's possible they were lying.
|
|
#
¿
Oct 3, 2017 11:35
|
|
|
ate all the Oreos posted:yeah that's the "special" one that uses the dedicated hardware. they call it CUDA or CUVENC to make it seem like it's normal CUDA but it actually uses a separate little module on the card. it still works fine / isn't broken but it can't really do "real" CUDA i don't mean NVENC, which replaced it, but the thing they're talking about taking out of the driver here, which worked on pre-kepler cards which afaik didn't have encoding hardware: https://web.archive.org/web/20150804115020/https://developer.nvidia.com/nvidia-video-codec-sdk oh, apparently mainconcept had something similar at the time but i assume all this stuff got swept away by the proliferation of hardware encoders
|
|
#
¿
Oct 3, 2017 14:00
|
|
|
atomicthumbs posted:why does opencl suck so bad vulkan sapped all it's momentum
|
|
#
¿
Oct 3, 2017 21:36
|
|
|
Condiv posted:is vulkan capable of the same stuff as opencl? cool i mean, believe it when you actually see it running, but the intermediate language spec should mean that you can directly load and run unchanged cl kernels from vulkan
|
|
#
¿
Oct 3, 2017 21:49
|
|
|
Doc Block posted:isn't part of the reason that opencl never caught on was because apple was the only one really invested in it? it was basically an apple invention, iirc, until they lost interest in favour of Metal. nvidia were interested exactly as far as making sure opencl support wasn't a reason to not buy an nvidia card, amd were interested because they needed to compete with cuda but they've put more effort into various hokey run-cuda-by-parsing solutions for the last few years. and a whole host of other companies (especially mobiles) were briefly interested in it as a selling point, but google shot that down by not supporting opencl on nexuses in favour of something called renderscript as part of an internal google turf war
|
|
#
¿
Oct 4, 2017 10:55
|
|
|
ate all the Oreos posted:so i dabbled in a tiny bit of opencl a while ago and eventually i'd like to come back around to it and play around with it a bit because i'm a turbodork who finds this kinda thing interesting, should i even bother with it if it's going out of style or should i look into something else instead? it still has the advantage of being multi-platform and multi-manufacturer. on my macbook pro i can run tasks on both the internal gpus etc. and nvidia added opencl 1.2 support to their driver in the last two years so they all support roughly the same featureset. it's just sad reading about cl 2.0 and not being able to get any of the nice features unless you have a specific AMD card and do the magic driver rain dance.
|
|
#
¿
Oct 5, 2017 11:48
|
|
|
altera sell fpgas which run opencl, i've only had a cursory look at them though, and i suspect you'd still be doing a lot of work specific to the fpga to get decent results.
|
|
#
¿
Oct 5, 2017 12:29
|
|
|
echinopsis posted:gpu facts - my r7 290 is no longer supported in belnder open cl so now I have no gpu pathways in cucles at all weird, what changed? ate all the Oreos posted:sorry, could you also explain what the hell a 1-bit texture is or how that's useful? is it just for like, masking? in the valve paper they're drawing a 2D vector shape (the text "no trespassing") with no built-in texturing onto a 3D object, so the 1-bit texture is a high-res mask of the vector shape. the point is to draw a crisp vector image at any distance, but only using a raster texture on the gpu.
|
|
#
¿
Oct 18, 2017 13:51
|
|
|
assume the generated textures are more difficult to compress, too. dunno how limiting that is for how many you'd use.
|
|
#
¿
Oct 18, 2017 15:29
|
|
|
look i know they play it up a lot for marketing, but "machine learning" isn't really all that close to machine intelligence.
|
|
#
¿
Oct 24, 2017 02:50
|
|
|
you should definitely be able to, all the pre-compiling stuff is motivated primarily by being able to lock people out of your source code files and, if anything, complicates matters
|
|
#
¿
Oct 27, 2017 15:52
|
|
|
amd's newest pro driver has a feature where you can ''host" and toggle between up to two consumer radeon drivers. only works with wx and vega cards though, so no extreme gaming for me.
|
|
#
¿
Nov 13, 2017 11:17
|
|
|
Sapozhnik posted:as a matter of fact, the only widely-deployed hardware platform at the moment that does not in principle support it is the raspberry pi boards released thus far with their vc4 socs. is this snark about macos not being widely-deployed
|
|
#
¿
Nov 16, 2017 22:33
|
|
|
|
| # ¿ May 22, 2024 16:56 |
|
|
webcl is dead in the water, if that's what you mean.
|
|
#
¿
Nov 24, 2017 19:49
|
|