Radeon Open Compute 1.3 Platform Brings Polaris & Other Features

[juno]

I also don't understand where the expectation comes from. GCN 1.0 has never been on the plan for amdgpu neither ROC. Nobody said it will be able to use the upcoming, free OpenCL implementation with that. People who like to stick with old things, could use catalyst OpenCL with a sufficient (LTS) distribution as well.
I think most people would be happy being able to run the free stack and then the closed OpenCL package on top.

@bridgman: Can you tell if there is work being done concerning Fortran? It is heavily used in HPC, and not only in legacy projects. Nvidia announced there will be a fortran support in LLVM for their GPUs, it was planned for this year (http://arstechnica.com/information-t...s-in-clusters/)

[pal666]

But it doesn't really work :/

but now you don't depend on amd fixing it

[pal666]

I also think, the HD7970 cards should get good OpenCL support (like with Catalyst - but open source, not the MESA one).

why do you hate mesa?

[mibo]

why do you hate mesa?

I don't. (I use MESA currently on an RX480)
But, I would like to have *proper* OpenCL (the MESA one doesn't have picture read/write capabilities, so it doesn't help with darktable, Neatimage and other OpenCL accelerated image editing software).

[pal666]

I don't. (I use MESA currently on an RX480)
But, I would like to have *proper* OpenCL (the MESA one doesn't have picture read/write capabilities, so it doesn't help with darktable, Neatimage and other OpenCL accelerated image editing software).

why then you didn't ask for mesa improvement?

[Amarildo]

you already have opensource opencl support in mesa

Which is crap. I can't use it with Blender to render my projects with my GPU.

Buy a newer card. You're 4 revisions behind.

So? It's not a bad card for 3D rendering neither gaming.

I don't mean to minimize this, but exactly what did you plan on using OpenCL for on a GCN 1.0 GPU anyway? That's outdated enough it's hard to imagine it being good for anything except maybe practice or bragging rights on the internet. For practice, you could just use a CPU based OpenCL implementation.

I'm a 3D artist. I've been using OpenCL to render with my R9 270X on Windows and Linux with proprietary drivers, but I *REALLY* don't like them; not only because they're proprietary and not compatible with GRSec, but they're slow as hell (amdgpu and mesa are so much far ahead in performance). The only stack I can use in this case (if I want OpenCL now) is Catalyst, not AMDGPU-PRO because it still doesn't support SI cards. This means almost a one-year-old driver/stack.
AMDGPU with mesa-git works so much better, that the only advantage of using Catalyst would be OpenCL, really. Instead of taking 8 hours to render an image, it takes only 4 if I render with OpenCL and GPU.

I also don't mean to be disrespectful, but I think that we can't except AMD to provide support for cards that were bought/producted in 2011, especially not since they are working with limited resources to catch up with both OpenGL, OpenCL and Vulkan specs, while stabilizing and improving performance of the driver.

I agree with the sentiment that it might be time to spend a couple hundred bucks on a modern generation, allowing for AMD to focus their resources on a smaller scope.

I would buy a newer card if I could. Mine was launched in 2013, it's not that old, and since AMD is supporting AMDGPU/Vulkan on all GCN cards I thought AMD would also support my card with OpenCL. I mean, John (bridgman) knows what I card I have, and it's been more than a year that I've been asking him about opensource OpenCL and not once did he mention SI cards wouldn't be supported.

If support for OpenCL 2.0 is already present on GCN 1.0 cards with Catalyst, I don't see why not opensource it and make it available for ALL GCN cards, like they did with AMDGPU/Vulkan.

Geez, can't you at least wait for me to respond before blowing up ? I do have to sleep sometimes. First, is it actually "open source OpenCL" you are looking for (ie you are planning to modify the source code yourself) or "OpenCL running with the open source stack" ie dealing with the current IOCTL gap between upstream and hybrid kernel drivers ?

I'm looking for an opensource OpenCL implementation that runs with current OSS drivers (amdgpu,radeon), that can be used with Blender to render with the GPU, and that works with my card (R9 270X).

Or is it just "I decided AMD was going to give me this specific deliverable although they never said they would (we always talked about open source OpenCL running over ROC) but now I decided they aren't going to do it so they suck" ?

I decided nothing, really. Me, you, and one other with the same card as mine, talked about opensource OpenCL, and not once you mentioned SI cards wouldn't be supported. I, for instance, had no idea "ROC" existed.

There will be an open source OpenCL runtime supporting SI and higher and an open source shader compiler supporting SI and higher; what we don't have a plan for yet AFAIK (remember we are still working on the underlying SI amdgpu support) is how to plumb the OpenCL runtime and compiler-generated binaries into the amdgpu IOCTLs for compute queues on non-ROC-supported hardware. Worst case you end up with "mostly open source OpenCL working with the open source graphics stack and Vulkan".

That's great! But when, though? And will it be as good as the OpenCL present in Catalyst? Meaning, can I use this OpenCL to render 3D projects on Blender using my GPU?
If only a few parts of it aren't opensourced (meaning userspace stuff, only a few pieces), than I don't mind waiting a few months more. I just hope my processor can take the load without frying.

I also don't understand where the expectation comes from. GCN 1.0 has never been on the plan for amdgpu neither ROC. Nobody said it will be able to use the upcoming, free OpenCL implementation with that. People who like to stick with old things, could use catalyst OpenCL with a sufficient (LTS) distribution as well.
I think most people would be happy being able to run the free stack and then the closed OpenCL package on top.

It's not that we "like" to use older hardware, but we can't buy newer one. Or do you think I love rendering via CPU, which is at least twice as slow as my GPU, while frying it (because I can't even afford an after-market cooler)? :T

I don't. (I use MESA currently on an RX480)
But, I would like to have *proper* OpenCL (the MESA one doesn't have picture read/write capabilities, so it doesn't help with darktable, Neatimage and other OpenCL accelerated image editing software).

Mesa is wonderful for OpenGL. However, it's OpenCL implementation is not even close to AMD's proprietary one. Blender's Kernel can't even compile with it.

[fakenmc]

but now you don't depend on amd fixing it

True.

why then you didn't ask for mesa improvement?

The problems with Clover, the mesa OpenCL implementation, are not limited to the not yet implemented capabilities. For example, a minimally complex kernel will simply not work. A lot of work is still required before Clover has any serious applications. On the other hand, AMD's proprietary OpenCL implementation is solid and reliable, and it's unfortunate that it's not currently available for modern kernels/distros for the GCN 1.0 architecture (because of the switch from fglrx to AMDGPU-PRO).

[Amarildo]

Unapproved. Gonna wait to see if Michael approves my post.

[bridgman]

I would buy a newer card if I could. Mine was launched in 2013, it's not that old, and since AMD is supporting AMDGPU/Vulkan on all GCN cards I thought AMD would also support my card with OpenCL. I mean, John (bridgman) knows what I card I have, and it's been more than a year that I've been asking him about opensource OpenCL and not once did he mention SI cards wouldn't be supported.

I don't actually have everyone's hardware memorized... occasionally I remember but generally I don't unless it's in the post I am responding to (rather than 11 posts back from same user).

Main point though is that there are at least three different things that get discussed when we talk about "OpenCL on SI":

- Catalyst/PRO OpenCL on SI via AMDGPU-PRO
- Catalyst/PRO OpenCL (and Vulkan) on SI with Mesa 3D
- fully open source OpenCL on SI

The first one is happening, the second is very likely but with caveats (interop APIs) and I don't think I have *ever* talked about the third (although it's possible I did without realizing context had shifted from one of the other topics).

If support for OpenCL 2.0 is already present on GCN 1.0 cards with Catalyst, I don't see why not opensource it and make it available for ALL GCN cards, like they did with AMDGPU/Vulkan.

It's not "like we did" it's "like we are doing" and in both cases we have to make some big changes in order to open up the code. In both cases we are replacing the proprietary shader compiler with the LLVM-based open source shader compiler, and in both cases we are rewriting some of the lower level code. In the case of Vulkan we don't have an existing open platform to use so we have to do all that work from scratch, while in the case of OpenCL we already have HSA/ROC and so are using it.

I'm looking for an opensource OpenCL implementation that runs with current OSS drivers (amdgpu,radeon), that can be used with Blender to render with the GPU, and that works with my card (R9 270X).

If it does everything you want but is only partially open source how much does that matter ? Will you actually be modifying the code yourself or just running Blender over it ?

I decided nothing, really. Me, you, and one other with the same card as mine, talked about opensource OpenCL, and not once you mentioned SI cards wouldn't be supported. I, for instance, had no idea "ROC" existed.

I'm having trouble remembering this, and it seems unlikely that I would talk about open sourcing OpenCL without mentioning HSA/ROC in the same paragraph. Can you point me to an example ?

[ermo]

Geez, can't you at least wait for me to respond before blowing up ? I do have to sleep sometimes. First, is it actually "open source OpenCL" you are looking for (ie you are planning to modify the source code yourself) or "OpenCL running with the open source stack" ie dealing with the current IOCTL gap between upstream and hybrid kernel drivers ?

Or is it just "I decided AMD was going to give me this specific deliverable although they never said they would (we always talked about open source OpenCL running over ROC) but now I decided they aren't going to do it so they suck" ?

There will be an open source OpenCL runtime supporting SI and higher and an open source shader compiler supporting SI and higher; what we don't have a plan for yet AFAIK (remember we are still working on the underlying SI amdgpu support) is how to plumb the OpenCL runtime and compiler-generated binaries into the amdgpu IOCTLs for compute queues on non-ROC-supported hardware. Worst case you end up with "mostly open source OpenCL working with the open source graphics stack and Vulkan".

Thanks for the heads up.

I'm saving up for a potential Vega purchase but that card would go into my Windows box while my pair of 7970 GHz Ed. cards would go into my FX-8350 Linux box, so I'm obviously delighted to hear that you gentlemen are still planning to add GCN 1.0 support to the gpu stack, especially considering that I'll potentially then be able to unleash around 2 teraflops of double precision compute power for whatever nefarious purposes I can dream up (for those who don't know, a HD 7970 GHz Ed. GCN 1.0 card has about twice the DP flops performance of a R9 Fury X).

As always, some of us do appreciate simply being kept in the loop.

/me sends a *thumbs up* in the general direction of bridgman & co.