0 Replies Latest reply on Jul 18, 2014 6:36 AM by Raistmer

    What "cache hit %" shows on cacheless devices?

    Raistmer

      First of all I would thank CodeXL developer team for improvements they make in Code XL 1.4. Now it's much more convenient tool.

       

      Now the question:

      On Loveland device there is no cache at all accordingly CLinfo-like enumerating:

       

      OpenCL Platform Name: AMD Accelerated Parallel Processing
      Number of devices: 1
        Max compute units: 2
        Max work group size: 256
        Max clock frequency: 275Mhz
        Max memory allocation: 175374336
        Cache type: None
        Cache line size: 0
        Cache size: 0
        Global memory size: 701497344
        Constant buffer size: 65536
        Max number of constant args: 8
        Local memory type: Scratchpad
        Local memory size: 32768
        Queue properties:
          Out-of-Order: No
        Name: Loveland
        Vendor: Advanced Micro Devices, Inc.
        Driver version: 1268.1 (VM)
        Version: OpenCL 1.2 AMD-APP (1268.1)
        Extensions: cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_gl_sharing cl_ext_atomic_counters_32 cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_d3d10_sharing cl_khr_dx9_media_sharing cl_amd_image2d_from_buffer_read_only

       

      But CodeXL still shows cache hit %, for example:

      Method, ExecutionOrder, ThreadID, CallIndex, GlobalWorkSize, WorkGroupSize, Time, LocalMemSize, VGPRs, SGPRs, ScratchRegs, FCStacks, KernelOccupancy, Wavefronts, LDSFetchInsts, LDSWriteInsts, FetchSize, CacheHit (%), FetchUnitBusy (%), FetchUnitStalled (%), WriteUnitStalled (%), FastPath, PathUtilization (%), LDSBankConflict (%)

      GPU_fetch_array_kernel_twin_1D_persistent_cl__k12_Loveland1, 1540, 548, 9609, {    512       1       1}, {  256     1     1}, 436.32020, 32768, 30, NA, 0, 4, 12.5, 16, 87245.63, 32, 193527.63, 13.31, 30.87, 0.01, 1.75, 0, 0, 0

       

      What its meaning then? Or OpenCL device capabilities quering returns wrong data and Loveland (C-60) device has cache? Please make some comments on this.