Bureaucrats, dave_user, Administrators
4,650
edits
Changes
→Results comparison
== Results comparison ==
The following table compares the results achieved to the ones produced by measured on the [[ML-TN-001 - AI at the edge: comparison of different embedded platforms previously tested- Part 2|i.MX8M-based Mito8M SoM]].
{| class="wikitable" style="margin: auto;"
Prediction times
!Platform
!BSP
!TensorFlow Lite
!ARM cores
(# / Type / Max freq. [GHz])
!Acceleration
!Model
!Prediction time
[ms]
!Notes
|-
| rowspan="6" |'''NXP i.MX8M-based Mito8M SoM'''
| rowspan="6" |
| rowspan="6" |1.12
| rowspan="6" |1.3
| rowspan="6" |no
| rowspan="3" |Floating-point
|unspecified (4)
|220
|
|-
|1
|220
|
|-
|2
|390
|
|-
|Half-quantized
|unspecified (4)
|330
|
|-
| rowspan="2" |Fully-quantized
|unspecified (1)
|200
|
|-
|4
|84
|-| rowspan="5" |'''Xilinx Zynq UltraScale+ MPSoC ZCU104 Evaluation Kit'''|2 cores DPU(through DNNDK API)|Fully-quantized US+ (*)|1|3.7|-| rowspan="4" |2 cores DPU(through VART API)| rowspan="4" |Fully-quantized US+ (*)|1|4.1|-|2|2.3|-|4|1.2|-|6|1.2
|-
| rowspan="7" |'''NXP i.MX8M Plus EVK'''
| rowspan="7" |L5.4.24_2.1.0
| rowspan="7" |2.1
| rowspan="7" |1.8
| rowspan="6" |no
(version 1)
| rowspan="3" |Floating-point
|unspecified (4)
|89
|
|-
|1
|160
|
|-
|2
|130
|
|-
|Half-quantized
|unspecified (4)
|180
|
|-
| rowspan="2" |Fully-quantized
|unspecified (1)
|85
|
|-
|4
|29
|Interestingly, this time is significantly smaller than the one measured on the i.MX8M (84 ms). Probably, this is due to improvements at the TFL inference engine level, besides the increased maximum ARM frequency.
|-
|NPU
(version 2)
|Fully-quantized
|NA
|1.5
|
|}
