Announcement

Collapse
No announcement yet.

AMD Publishes Open-Source Linux HSA Kernel Driver

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

  • #21
    I was beginning to seriously consider Intel gear for a single workstation. I haven't had one since my P3-1200, which I keep as my sexy little over-sized firewall, wewts...oh wait I have an Intel ivy7 laptop, derp (with AMD GFX =)

    But this newspiece and subsequent user posts brought me back. Thank you to all and sundry!

    Shit's crackin'!

    Comment


    • #22
      Oh wow. So HSA actually becomes reality. It seems somewhat unreal to me, but a lot of things do since I dropped out of work into unemployment last week (after 7 months of 70... 100 h/week workload everything seems strange when you suddenly stop).
      I guess this might be an underrated start for something much larger. Well, future will show. Thanks to the developer team for all the effort and AMD in general for providing specs and free drivers.
      Time for me to show my support by buying another APU (while money still lasts ).
      Stop TCPA, stupid software patents and corrupt politicians!

      Comment


      • #23
        Originally posted by Adarion View Post
        Oh wow. So HSA actually becomes reality. It seems somewhat unreal to me, but a lot of things do since I dropped out of work into unemployment last week (after 7 months of 70... 100 h/week workload everything seems strange when you suddenly stop).
        I guess this might be an underrated start for something much larger. Well, future will show. Thanks to the developer team for all the effort and AMD in general for providing specs and free drivers.
        Time for me to show my support by buying another APU (while money still lasts ).
        If you're in an uncivilized country like the US as I am save your cash for food and bills. At this point it's probably better to wait for the next gen version with mobos sporting DDR4 as DDR4 hardware was all the rage at Computex a few weeks ago. With those maybe we'll also get on mobo GDDR5 for some real fun with memory bandwidth...

        Comment


        • #24
          Originally posted by Kivada View Post
          If you're in an uncivilized country like the US as I am save your cash for food and bills. At this point it's probably better to wait for the next gen version with mobos sporting DDR4 as DDR4 hardware was all the rage at Computex a few weeks ago. With those maybe we'll also get on mobo GDDR5 for some real fun with memory bandwidth...
          GDD5 mounted where on the hardware? On-die, the motherboard or maybe socketed like in the old FPU days? You sound like you saw or heard something about it. Now spill the beans!

          And when's the official DDR4 launch? I heard it was 'real soon now', but it's been like that for a couple years now. Coincidentally, about as long as the DDR3 price inflation occured.

          EDIT: Oh, and I think 'dynamic' instead of 'uncivilised' will will get you a few less scowls from the Muhrican's =D

          Comment


          • #25
            Originally posted by nigeil View Post
            Very excited to hear about this release. Glad to see AMD making strides, however slow they are in coming, to push this support out to the open source community. Hopefully we can put it to good use; I was waiting to take advantage of this in some of my own scientific modelling software.
            is this even implemented in fglrx? I think windows catalyst has hsa, but on linux with fglrx? does somebody know if oss has a lead here?

            Comment


            • #26
              Just a few questions:
              Does that mean that until now for HSA hardware you had to move data between main mem and gpu dedicated mem?
              If so will these patches be used by the radeon driver to stop this to save bandwith?
              Would it be possible to write 3D engine in HSAIL and will there be benefit other than being portable to all HSA hw (kaveri and next gen phones, maybe PS4 and xbox1)?

              Comment


              • #27
                Originally posted by tomtomme View Post
                is this even implemented in fglrx? I think windows catalyst has hsa, but on linux with fglrx? does somebody know if oss has a lead here?
                http://www.phoronix.com/scan.php?pag...tem&px=MTY0MDY

                How does this benefit other architectures, and OpenCL in general (for Sea Islands and previous, including R600)?

                Comment


                • #28
                  Originally posted by asdfblah View Post
                  http://www.phoronix.com/scan.php?pag...tem&px=MTY0MDY

                  How does this benefit other architectures, and OpenCL in general (for Sea Islands and previous, including R600)?
                  I know the story about canceling fglrx-kernelside and bring it to floss. So I take your hint / link as: HSA is not implemented in fglrx, oss has a lead as planned by bringing kernel-side of fglrx into the oss driver
                  However I would like to have a reliable source / confirmation from a dev or a link that actually states this information explicetly.

                  Comment


                  • #29
                    Originally posted by Kivada View Post
                    Got any multimedia task? The GPU would absolutely destroy any CPU on the market with ease in these tasks. Think how VDPAU/VA-API help with video playback, apply that to editing and transcoding file, which is a very time consuming task, especially as we move to 4K and eventually 8K video.
                    For this Task the GPUs have a separate ASIC for this. Only things like deinterlacing oder other Filters are processed on the gpu but not the decoding and encoding.

                    Comment


                    • #30
                      Thanks, Bridgman! Can't wait to see HSA in real applications

                      Comment

                      Working...
                      X