• Strange printf behaviour on Vega

    Tested on latest 19.10.1 drivers. Windows 10 x64 1903 I attached cl file and cpp program which would launch this simple addVec kernel. Opencl code: #pragma OPENCL EXTENSION cl_amd_printf : enable __attribute__((req...
    ___
    last modified by ___
  • Neural networks using fast transforms

    I guess you have a FFT library.  You probably should write an efficient Walsh Hadamard transform library to allow people to better experiment with fast transform neural networks: https://community.konduit.ai/t/f...
    seanc4s
    last modified by seanc4s
  • The OpenCL General Tuning Issue

    All OpenCL versions form all vendors have this issue. It is a wrong computation. Please take a look at my blog describing it in detail. Can this be fixed on AMD OpenCL anyhow?   https://iblog.isowa.io/2020/01/04...
    sowson
    last modified by sowson
  • Performance of zero-ing OpenCL buffers on device

    Hello! In my project, I'm running a chain of several kernels in a loop with millions of iterations, and I need to zero out a buffer of up to 5000 floats at the start of every iteration of this loop. I tried using clE...
    jadr
    last modified by jadr
  • CNN DarkNet on OpenCL

    Hello, recently I made the DarkNet on OpenCL that is technology that really passionate me and I started recently PhD studies on AI field. I am using few different GPUs, recently 2 x AMD Radeon VII that works very well...
    sowson
    last modified by sowson
  • OpenCL single memory allocation limit

    AMD OpenCL limits a single buffer allocation (CL_DEVICE_MAX_MEM_ALLOC_SIZE) to 50% of total memory.   So on a 8Gb card there is only 4Gb available for allocation in a single chunk.   This is very sad for ...
    octoboar
    last modified by octoboar
  • Feature request: expose newer AMD GCN / RDNA features as CL extension

    Back in the early days of OpenCL AMD added the famous cl_amd_media_ops (2) to expose hardware features to the programmers. Sadly with some of there more recent or more hidden hardware features like GDS or the cross la...
    lolliedieb
    last modified by lolliedieb
  • ROCm OpenCL freezes on Linux for clCreateCommandQueue

    Hi all.     I have AMD Vega 64 GPU with newest ROCm 2.10 Driver on a Linux headless Server. See clinfo paste down.   My OpenCL Programm freezes always at the clCreateCommandQueue.   I have ...
    linuxperia
    last modified by linuxperia
  • SYCL application development on Windows

    Currently all means of developing SYCL applications on Windows are either discontinued or has missing driver/runtime components.   Codeplays ComputeCpp has prime time support for SPIR, experimental SPIR-V and ha...
    Meteorhead
    last modified by Meteorhead
  • OpenCL memory synchronization issue on Radeon Pro WX9100

    Hi, the attached Program produces errors where it seems that some times writes to a buffer get ignored when run with a Radeon Pro WX9100, driver version 19.Q3.1 on Windows 10 x64 1809. The same Program runs without ...
    mierowsl
    last modified by mierowsl
  • Bug in OpenCL compiler

    I found a bug in OpenCL compiler in the latest drivers. At least it is persistent in Adrenalin 19.5.2 and 19.8.1. Minimal reproducing example is included in the file. It just multiplies several complex numbers in a lo...
    melirius
    last modified by melirius
  • Please add support for image atomics in OpenCL

    Hi,   I have a kernel where I accumulate a lot of values with atomics. The values to accumulate are in a 2D neighborhood, and neighboring threads treat similar regions, but with a small random (x,y) shift. and t...
    mannerov
    last modified by mannerov
  • Experimental OpenCL driver for Ubuntu 16.04

    On Ubuntu 16.04, fglrx support was dropped and currently the opensource driver AMDGPU is still in an early stage and only supports very limited devices. I attempted to make the OpenCL part of fglrx working and made a ...
    victzhang
    last modified by victzhang
  • OpenCL 8 GPU DGEMM (5.1 TFlop/s double precision). Heterogeneous HPL (High Performance Linpack from Top500).

    Pavel Bogdanov, Institute of System Research Russian Academy of Sciences (NIISI), bogdanov@niisi.msk.ru   INTRO   Nowadays heterogeneous computing becomes more and more popular. In november 2011 three of to...
    antonyef
    last modified by antonyef
  • OpenCL occupancy-performance nightmare

    These days I tried to squeeze some performance from a memory-intensive OCL kernel and went for GCN assembly. Saved a few registers here, few instructions there, got a nice occupancy and thought to have a perfect kerne...
    kbala
    last modified by kbala
  • Kernel execution time discrepancy

    I have a kernel that executes a few times per second. There are 2 anomalies that I can't figure out.   1 (less important). Every 3-4 seconds the gap between the end of the kernel execution and the start of the n...
    kbala
    last modified by kbala
  • Optimize LC0 - Leela Chess Zero - for AMD GPUs

    Heyho AMD community,   we are all aware about the neural network hype on gpus, and most have noticed that Nvidia has simply the forehand with their cuDNN framework.   Personally I am convinced that AMD mak...
    smato2018
    created by smato2018
  • Newbie introduction and seeking guidance.

    Hello my name is Ernst. I have a passion for binary level data encoding.  I work on my workstation running a AMD 9590 and recently I made the decision to upgrade my NVIDIA GPU to twin Radeon wx 5100s pros'. I am...
    ernst0
    last modified by ernst0
  • Need tips to hide memory latency - 20x speed-loss when writing to memory

    I have an OpenCL code that does Monte Carlo photon transport simulations in a voxelated space (https://github.com/fangq/mcxcl). The code involves simulating a large number of random photon trajectories, each in a thre...
    FangQ
    last modified by FangQ
  • Running OpenCL Work Groups with >256 Elements

    Hi all,   I am currently re-writing some OpenCL code of mine and would like to split the work of the group to more waves in order to have more waves in flight. The code is a OpenCL 1.2 code (because it needs to ...
    lolliedieb
    last modified by lolliedieb