Commits on Sep 29, 2023

1. ocl: GCN atomics for Mi-GPUs and other improvements …

   * GCN: Rely on builtin atomics (Mi-GPUs); TODO: tuned params and feature-check can be improved.
   * Allow relying on platform name instead of device name (c_dbcsr_acc_opencl_device_vendor).
   * Introduced optional kernel-flags (opencl_libsmm_smm_t); needs some followup work later.
   * Improved kernel by relying on work_group_broadcast in general.
   
   * Improved documentation for CUDA/OpenCL stand-alone drivers
   * Fixed warnings about unused variable (kernel code).
   * Modernized Shell script (acc_opencl.sh).
   * Improved some runtime error messages.
   * Some more debug/developer settings.

   

   hfp committed Sep 29, 2023
   Configuration menu

   • View commit details
   • Copy full SHA for 06cfde0
   • Browse repository at this point

   Copy the full SHA

   06cfde0 View commit details

   Browse the repository at this point in the history