Recent content by mr-robot

  1. M

    Difference between the HTP and DSP delegate?

    Thanks for the quick reply. Are you familiar with the internal components of the HTP? Eg the difference between the HTA, HVX and HMX: HVX being the "Hexagon Vector Extensions", HMX the "Hexagon Matrix Extension" and HTA the "Hexagon Tensor Acceleration" (seem to be deprecated in later devices)...
  2. M

    Difference between the HTP and DSP delegate?

    Hi, In the footnote of the rankings the following abbreviations are provided: qh - Qualcomm QNN HTP Delegate qd - Qualcomm QNN DSP Delegate What is the difference between the HTP and DSP delegate? In Qualcomm jargon, I thought that the HTP = DSP = HMX + HVX. Therefore I'm confused...
  3. M

    Questions about Apple Benchmarks

    Hi, In the full ranking results presented here: https://ai-benchmark.com/ranking_processors_detailed.html, the following values are provided for the A15 Bionic chipset for the SRGAN model: - Int8: 485 ms - Float16: 167 ms I have a few questions regarding these data points. 1. As far as I...
  4. M

    Interpretation of Benchmark Score & Runtime

    Hi, Regarding the AI benchmarks, it has been stated in a previous post that the scores presented are geometric averages of runtime. Take the example of Realme GT2 Pro, with FP16 (NNAPI 1.3) score of 88,036 and INT8 (NNAPI 1.3) 422,097. INT8 results are 4.8 times larger. Does this imply that...
Top