Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cycles X

code.blender.org

Post reply on HN
Print view View original

91–100 of 151 posts

Re: Cycles X

#91

Post by Olumde »

qwertox wrote: post #30
ravenstine wrote: post #3

I've kept an eye on Blender for the last 15 years and tried it again recently after having almost exclusively used Maya. It's continually improved in just about every way, is relatively easy to use with just a trackpad, and it performs really well. In contrast, Maya is has more features overall but is... a piece of shit in many ways. It doesn't matter what hardware I've used; it's a rule that Maya has to crash random…

I learned Maya on Irix, then purchased a License for Plug In development on Windows around 2004, which was pre-Python support. I really got to knew the DAG very well, as well as rendering custom helper tools in the viewport. It was extremely flexible to extend. I've also kept an eye on Blender since then, and no other piece of OSS causes me so much joy to see the improvements it makes version after version, specially…

This is precisely the point I made in my comment [1]. The lack of a C++ API is a huge let down in every Blender release.

[1] https://news.ycombinator.com/item?id=26921528

Re: Cycles X

#92

Post by pcwalton »

542458 wrote: post #90
gmueckl wrote: post #25

Earlier quoted context omitted.

What do you mean by blank pixels? Cycles is a MC path tracer. This means that it will always trace some paths that don't find high contributions to the final image. When this happens for the first couple of iterations when rendering progressively, these pixels stay darker than the rest. This is just how the algorithm works. You could try to apply a denoiser, but then you're not using the computational power to shoot…

Sorry, what is MC an acronym for here?

Monte Carlo.

Re: Cycles X

#93

Post by abledon »

ravenstine wrote: post #3

I've kept an eye on Blender for the last 15 years and tried it again recently after having almost exclusively used Maya. It's continually improved in just about every way, is relatively easy to use with just a trackpad, and it performs really well. In contrast, Maya is has more features overall but is... a piece of shit in many ways. It doesn't matter what hardware I've used; it's a rule that Maya has to crash random…

Maya's UI is like it is stuck on Windows95 and can't get up

Re: Cycles X

#94

Post by RaisingSpear »

birktj wrote: post #23

> Deprecation > OpenCL rendering kernels. The combination of the limited Cycles split kernel implementation, driver bugs, and stalled OpenCL standard has made maintenance too difficult. I am not really up to date on the GPGPU world, but is OpenCL in such a bad shape that it is not really usable? If so that is very sad. Are there any alternative open hardware agnostic GPGPU apis or has CUDA eaten the entire market?

OpenCL is old, and everyone seemingly wants to abandon it, but it's your only option for a bunch of configurations (such as AMD on Windows, even though AMD has pulled all their OpenCL stuff from their website).

As someone who's done a fair bit of SIMD programming on CPU, and heard many scream that wide SIMD (like AVX512) is pointless when you have GPGPU, it's certainly eye-opening to see how poor a state cross-platform GPGPU development is in. Well, I suppose if you only care about Nvidia, CUDA does seem to be pretty good. Too bad it's Nvidia only.

I've heard people consider Vulkan Compute as an alternative. I had a quick look, and it doesn't seem like it supports integer operations (what I'm mostly doing), so doesn't seem viable for me, but I guess it could for a bunch of folk. Not familiar with Vulkan myself though, so corrections welcome.

Re: Cycles X

#95

Post by pavlov »

RaisingSpear wrote: post #94
birktj wrote: post #23

> Deprecation > OpenCL rendering kernels. The combination of the limited Cycles split kernel implementation, driver bugs, and stalled OpenCL standard has made maintenance too difficult. I am not really up to date on the GPGPU world, but is OpenCL in such a bad shape that it is not really usable? If so that is very sad. Are there any alternative open hardware agnostic GPGPU apis or has CUDA eaten the entire market?

OpenCL is old, and everyone seemingly wants to abandon it, but it's your only option for a bunch of configurations (such as AMD on Windows, even though AMD has pulled all their OpenCL stuff from their website). As someone who's done a fair bit of SIMD programming on CPU, and heard many scream that wide SIMD (like AVX512) is pointless when you have GPGPU, it's certainly eye-opening to see how poor a state cross-platfo…

I'm genuinely surprised that AMD didn't put in an effort to implement CUDA themselves. It's been almost 15 years. They should have started a skunkworks project to get CUDA running immediately.

Intel didn't take long to eat crow and ship the AMD64 instruction set in their CPUs as soon as it became clear they'd lost the 64-bit ISA game. AMD should have taken a lesson from that: if the market wants the other guy's API, you can implement it, customers will be pleased, and that gives you power over the API that you wouldn't have otherwise.

Re: Cycles X

#97

Post by RaisingSpear »

pavlov wrote: post #95
RaisingSpear wrote: post #94

Earlier quoted context omitted.

OpenCL is old, and everyone seemingly wants to abandon it, but it's your only option for a bunch of configurations (such as AMD on Windows, even though AMD has pulled all their OpenCL stuff from their website). As someone who's done a fair bit of SIMD programming on CPU, and heard many scream that wide SIMD (like AVX512) is pointless when you have GPGPU, it's certainly eye-opening to see how poor a state cross-platfo…

I'm genuinely surprised that AMD didn't put in an effort to implement CUDA themselves. It's been almost 15 years. They should have started a skunkworks project to get CUDA running immediately. Intel didn't take long to eat crow and ship the AMD64 instruction set in their CPUs as soon as it became clear they'd lost the 64-bit ISA game. AMD should have taken a lesson from that: if the market wants the other guy's API,…

> I'm genuinely surprised that AMD didn't put in an effort to implement CUDA themselves

I think HIP is their attempt at that, as it's very similar to CUDA and is meant to be easy to port. Maybe there's reasons why they (or anyone else really) can't just adopt CUDA (licensing?), though that's beyond my knowledge.

Re: Cycles X

#98

Post by raphlinus »

RaisingSpear wrote: post #94
birktj wrote: post #23

> Deprecation > OpenCL rendering kernels. The combination of the limited Cycles split kernel implementation, driver bugs, and stalled OpenCL standard has made maintenance too difficult. I am not really up to date on the GPGPU world, but is OpenCL in such a bad shape that it is not really usable? If so that is very sad. Are there any alternative open hardware agnostic GPGPU apis or has CUDA eaten the entire market?

OpenCL is old, and everyone seemingly wants to abandon it, but it's your only option for a bunch of configurations (such as AMD on Windows, even though AMD has pulled all their OpenCL stuff from their website). As someone who's done a fair bit of SIMD programming on CPU, and heard many scream that wide SIMD (like AVX512) is pointless when you have GPGPU, it's certainly eye-opening to see how poor a state cross-platfo…

Vulkan supports integer operations just fine, but tool support for just about everything is extremely primitive. Sizes other than 32 bits are available, but generally as an option. You can check https://vulkan.gpuinfo.org/listfeaturescore10.php to see the fraction of drivers that support the various integer sizes (and lots other optional features).

Re: Cycles X

#99

Post by henrikf »

w-m wrote: post #81
birktj wrote: post #23

> Deprecation > OpenCL rendering kernels. The combination of the limited Cycles split kernel implementation, driver bugs, and stalled OpenCL standard has made maintenance too difficult. I am not really up to date on the GPGPU world, but is OpenCL in such a bad shape that it is not really usable? If so that is very sad. Are there any alternative open hardware agnostic GPGPU apis or has CUDA eaten the entire market?

Yes it’s that bad unfortunately. Ok, so you got you kernel working and it performs well. That’s quite an achievement, because most tooling is atrocious, and profiling tools nonexistent for many platforms. Now you want to run this on the users machine. You are of course using an ancient OpenCL version, because very few vendors updates their OpenCL drivers. Situation has gotten so bad that the consortium had to basical…

Even worse than error message is incorrect results. I worked on the OpenCL neural net evaluation backend used in Leela Zero and lc0 Go and chess bots. We had reports of several OpenCL drivers being so broken that they gave incorrect results while appearing to work correctly without giving any error messages. Intel integrated GPUs on Apple were the worst offender and it looks like the drivers are never going to get fixed. Some older AMD cards had similar issues. We had to add a check that GPU NN evaluation matches CPU reference to catch these broken drivers.

Re: Cycles X

#100

Post by sagarm »

MattGaiser wrote: post #43
actinium226 wrote: post #41

Earlier quoted context omitted.

> * Blenders licensing is a deterrent. Very few people want to deal with GPL. Why would a studio care about this? A tech firm would certainly care, but the entertainment industry? They probably don't know what GPL is and would probably just associate it with "free"

GPL may as well mean radioactive as far as legal is concerned. A friend worked at a company where they banned GIMP as they feared that editing logos and other trademarks in it could invalidate them. Even working for a tech company, I don't think I would suggest using anything GPL as it would cause a fuss.

Tons of widely used software -- Linux, for one -- is GPL.
Post reply on HN