Page 1 of 2 12 LastLast
Results 1 to 10 of 11

Thread: NVIDIA Issues CUDA 5.5 RC: Better Debugging, Etc

  1. #1
    Join Date
    Jan 2007
    Posts
    14,911

    Default NVIDIA Issues CUDA 5.5 RC: Better Debugging, Etc

    Phoronix: NVIDIA Issues CUDA 5.5 RC: Better Debugging, Etc

    For those registered developers with NVIDIA Corp, the company has released their first release candidate of the forthcoming CUDA 5.5 platform...

    http://www.phoronix.com/vr.php?view=MTM4Nzk

  2. #2
    Join Date
    Dec 2011
    Posts
    2,062

    Default Thanks, but no thanks

    Source or gtfo!

  3. #3
    Join Date
    Jan 2013
    Posts
    1,458

    Default

    Meh, who needs their proprietary crap, we have OpenCL...

  4. #4
    Join Date
    May 2011
    Posts
    1,516

    Default

    riiiiiiiiiiiiiiiight... right. CUDA's never going to take off in the HPC space. /sarcasm

  5. #5
    Join Date
    Feb 2012
    Location
    Barcelona, Spain
    Posts
    308

    Default

    I won't buy and amd card, and opencl are slow on nvidia, I prefer cuda.

  6. #6
    Join Date
    Oct 2009
    Posts
    59

    Default

    http://arstechnica.com/apple/2013/06...e-new-mac-pro/

    Apple may be trying to not-so-delicately nudge everyone to move their code from CUDA to OpenCL, but Iíve seen a first-hand failure of AMDís OpenCL support with V-Ray RT for Maya. Chaos Group built V-Ray RT on OpenCL, but after extensive work trying to get the GPU variant of its RT render engine running on AMD hardware and an effort by yours truly to light a fire under Apple and AMD, Chaos Group gave up and ported it to CUDA instead. So V-Ray RTís GPU mode only works with OpenCL and CUDAóon Nvidia hardware.
    OpenCL isn't very good in reality and AMD drivers and OpenCL support is a joke. If you want to get real work done, you can only depend on Nvidia.

  7. #7
    Join Date
    Oct 2012
    Location
    Washington State
    Posts
    470

    Default

    CUDA will be relegated to a has-been technology in 24 months.

    Not a single large vendor of heavy computing will continue with CUDA over OpenCL which by then will be in the 2.x range.

    On board 100%:

    1. APPLE
    2. AMD
    3. INTEL
    4. ADOBE
    5. ORACLE
    6. SAMSUNG
    7. SONY
    8. IBM
    9. CRAY
    10. IMAGETECH
    11. ARM
    12. QUALCOMM
    13. UNITY
    14. GOOGLE
    15. NINTENDO
    16. MOTOROLA MOBILITY
    17. US DoE
    18. and hundreds more


    Kicking and screaming

    • NVIDIA
    • MICROSOFT

  8. #8
    Join Date
    Jan 2013
    Posts
    1,458

    Default

    Microsoft hates anything that has an open standard - unless they can usurp and abuse it.

  9. #9
    Join Date
    May 2011
    Posts
    1,516

    Default

    I have a hard time believing that AMD is committed more to OpenCL than DirectCompute. It seems like they can't stop slobbering over DC.

  10. #10
    Join Date
    Oct 2012
    Location
    Washington State
    Posts
    470

    Default

    Quote Originally Posted by johnc View Post
    I have a hard time believing that AMD is committed more to OpenCL than DirectCompute. It seems like they can't stop slobbering over DC.
    I don't. Their entire HSA platform is centered around OpenCL.

    http://hsafoundation.com/

    The HSA Foundation.

    The HSA (Heterogeneous System Architecture) Foundation is a not-for-profit consortium of SoC IP vendors, OEMs, academia, SoC vendors, OSVs and ISVs whose challenging the normal of how whole system architecture is structured for combing CPU’s, GPU’s, DSP’s, and other accelerators to bring about forward progress in computing’s foundation to make it dramatically easier to program heterogeneous parallel devices. HSA Foundation is driving this via Royalty Free Specifications and open source software: HSA runtimes and low level compilation tools based on open source technologies like LLVM and GCC.
    HSA Foundation members are building a heterogeneous compute software ecosystem which is rooted on open royalty free industry standards. We are looking to bring about applications that blend scalar processing on the CPU, parallel processing on the GPU, and optimized processing of DSP via high bandwidth shared memory access with greater application performance at low power consumption. HSA Foundation is defining key interfaces and for parallel computation utilizing CPU, GPU, DSP’s and other programmable and fixed function devices, which will support a diverse set of high-level programming languages creating the next foundation in general purpose computing. Most importantly we are driving to bring greater developer productivity to heterogeneous computing by removing many of the barriers of traditional heterogeneous programing so they can focus on their algorithms and not managing system resources. One of the key attributes of Cache Coherent Shared Virtual Memory (“CC-SVM”) is begin looking at larger dataset then traditionaly supported by today co-processor devices with fixed memory pools.
    Swap out OpenCL for the red highlighted. The entire foundation and future GCN architecture direction utilizes OpenCL/OpenGL as a marriage with LLVM/Clang and also GCC [Adobe working with AMD GPGPU solutions is OpenCL].

    AMD is on record stating DirectX 11.1 is a dead end. DirectCompute will have to compete with OpenCL, not the other way around. The nearly 99% in the world of Embedded Computing is OpenCL fullsteam ahead.
    Last edited by Marc Driftmeyer; 06-12-2013 at 05:47 PM.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •