Announcement

Collapse
No announcement yet.

Beignet 1.3 Released With OpenCL 2.0 Support

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • #11
    Originally posted by darkbasic View Post
    Ouch, my laptop is a Broadwell one
    Same here :/ Still though, Broadwell was a great step forward from Haswell and I'm glad I didn't wait on Skylake for the most part. That being said, I think my next laptop will be AMD when the Zen based APUs come out later this year. I was really thinking Kabylake would be a little more competitive with its integrated graphics, but now I don't think we are going to see any real improvement from Intel in the laptop space until 10nm rolls around.

    Comment


    • #12
      Originally posted by darkblu View Post
      So SNB, IVB, HSW and BDW can go suck a lemon.
      or wait a little more better than amd who don't give a crap about opensource drivers

      Comment


      • #13
        Originally posted by darkblu View Post
        So SNB, IVB, HSW and BDW can go suck a lemon.
        Out of those, SNB has no GPU OCL support, IVB and HSW can only support 1.2. Only reminder is BDW, which we can hope either they or someone from the community will tackle.

        Comment


        • #14
          Originally posted by illwieckz View Post

          It's not “Beginet” it’s “Beignet”, the “i” is before the “g”. See Wikipedia article: https://en.wikipedia.org/wiki/Beignet
          Pronounce it “Benyey”, with “Be” like in “Betty”, “ny” like in “nyan cat” and “ey” like in “they”
          It's a pastry, there is many kind of beignets: dougnuts are one kind of beignet for example.
           
          I pronounce it "beige net".

          And I have a great-great-grandfather who was French, and is turning in his grave...

          Comment


          • #15
            Originally posted by Linuxhippy View Post
            I am usually a big fan of AMDs open-source efforts, but when it comes to OpenCL on Linux - there have been a lot of promises but no working code (same as with Vulkan).
            How can you say there has been no working code when you are commenting about benchmarks on the developer preview ?

            There is typically a big pile of work that has to happen before code can be open-sourced... most of that work is now done. You can write something from scratch in public open source but you can't take something written to be proprietary and "replace or re-write the stuff you can't publish" in public, so the "open source" part always has to come last when you are dealing with cross-platform proprietary code.

            If we had actually done a clean implementation as you suggest then we could have done more of the work in public, but that was not at all the case.

            Originally posted by Linuxhippy View Post
            From what I understand, AMD does not plan to open-source their Catalyst OpenCL-2 implementation - but instead the LLVM based RocM approach - which is a clean implementation, and shows completly different characteristics (just have a look at the phoronix benchmarks).
            Other than replacing the old back-end with a ROCM-based one all of the other changes we have made also appear in the Catalyst version. We are moving the Windows implementation to a different back-end as well BTW.

            The new Linux implementation is clean as in IP-clean (or at least pretty close now) but I think you are suggesting clean as in new implementation. That is not what we did - same code will be running on Linux & Windows other than the GPU back end (maybe 5-10% of the total stack).

            Originally posted by Linuxhippy View Post
            I really hope AMD will provide a useable and fully-fledged open-source OpenCL-2 implementation soon as promised ... I've been waiting for that to happen for years.
            I don't think we ever promised an open source OpenCL 2 implementation, did we ? What we said (and can we please stop replacing "said" with "promised" ?) was that the OpenCL implementation in AMDGPU-PRO would be replaced with an equivalent open source implementation.

            We also said that work on amdgpu was just starting and that the full transition would take a few years (I think we said 2-3 years).

            AFAIK the plan is what we are calling "1.2+", which is 1.2 plus a few 2.0 features that people actually seem to be using. Some of the OpenCL 2.0 features do not seem to have really caught on in OpenCL (just on CUDA) so we are addressing those with HCC/HIP.
            Last edited by bridgman; 21 January 2017, 02:08 PM.
            Test signature

            Comment


            • #16
              Seems like the GPGPU market is divided in two segments: Nvidia, the leader, which can’t be bothered with OpenCL, and all the others, who do support it, but cannot offer the same level of performance.

              Is the market simply not big enough to be properly competitive?

              Comment


              • #17
                Originally posted by Krejzi View Post

                Out of those, SNB has no GPU OCL support, IVB and HSW can only support 1.2. Only reminder is BDW, which we can hope either they or someone from the community will tackle.
                I know SNB never received OCL, open-source or otherwise. I also know why: https://software.intel.com/en-us/for...l/topic/285869
                (^f resource constrain)
                As per IVB and HSW, allow me to make a parallel - AMD support OCL 2 on 1st gen GCN onwards (that's a 2011 product line). In comparison, Intel have been actively dragging their GPU feet, because their CPUs are oh-so-great at OCL.
                Last edited by darkblu; 22 January 2017, 06:23 AM.

                Comment


                • #18
                  Originally posted by bridgman View Post
                  I don't think we ever promised an open source OpenCL 2 implementation, did we ? What we said ...
                  Is OpenCL 2 not even a long term plan to support?

                  Comment


                  • #19
                    Originally posted by ekondis View Post
                    Is OpenCL 2 not even a long term plan to support?
                    Depends on whether the features get used, I guess. We supported 2.0 for years but most of the applications stayed with 1.2 or lower.
                    Test signature

                    Comment


                    • #20
                      Originally posted by bridgman View Post
                      Depends on whether the features get used, I guess. We supported 2.0 for years but most of the applications stayed with 1.2 or lower.
                      I understand it but if OpenCL 2 is not supported by a single discrete GPU vendor how will the developers be encouraged to use its features? One brings the other.

                      Comment

                      Working...
                      X