Platform: Portable Computing Language
  Device: pthread-AMD EPYC 7763 64-Core Processor
    Driver version  : 3.0-rc2 (Linux x64)
    Compute units   : 128
    Clock frequency : 2450 MHz

    Global memory bandwidth (GBPS)
      float   : 30.71
      float2  : 30.89
      float4  : 28.91
      float8  : 33.49
      float16 : 27.35

    Single-precision compute (GFLOPS)
      float   : 88.22
      float2  : 165.52
      float4  : 344.33
      float8  : 636.12
      float16 : 159.04

    No half precision support! Skipped

    Double-precision compute (GFLOPS)
      double   : 87.14
      double2  : 170.55
      double4  : 312.85
      double8  : 80.29
      double16 : 105.41

    Integer compute (GIOPS)
      int   : 199.11
      int2  : 391.47
      int4  : 765.45
      int8  : 1513.98
      int16 : 2490.43

    Integer compute Fast 24bit (GIOPS)
      int   : 131.65
      int2  : 190.44
      int4  : 372.82
      int8  : 659.86
      int16 : 153.00

    Transfer bandwidth (GBPS)
      enqueueWriteBuffer              : 19.15
      enqueueReadBuffer               : 15.29
      enqueueWriteBuffer non-blocking : 15.87
      enqueueReadBuffer non-blocking  : 19.75
      enqueueMapBuffer(for read)      : 5067.21
        memcpy from mapped ptr        : 14.73
      enqueueUnmap(after write)       : 4620.23
        memcpy to mapped ptr          : 20.45

    Kernel launch latency : 106.67 us