222 lines
5.2 KiB
JSON
222 lines
5.2 KiB
JSON
{
|
|
"summary": {
|
|
"BPU OPs per frame (effective)": 236339200,
|
|
"BPU OPs per run (effective)": 236339200,
|
|
"BPU PE number": 1,
|
|
"BPU core number": 1,
|
|
"BPU march": "B25E",
|
|
"DDR bytes per frame": 44277504,
|
|
"DDR bytes per run": 44277504,
|
|
"DDR bytes per second": 6318416482,
|
|
"DDR megabytes per frame": 42.226,
|
|
"DDR megabytes per run": 42.226,
|
|
"DDR megabytes per second": 6025.7,
|
|
"FPS": 142.7,
|
|
"HBDK version": "3.49.15",
|
|
"compiling options": "-f hbir -m /tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_2.hbir -o /tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_2.hbm --march bayes-e --progressbar --input-layout NHWC --output-layout NHWC",
|
|
"frame per run": 1,
|
|
"frame per second": 142.7,
|
|
"input features": [
|
|
[
|
|
"input name",
|
|
"input size"
|
|
],
|
|
[
|
|
"/model.22/m.0/m.0.1/attn/Transpose_1_output_0_calibrated_quantized",
|
|
"1x2x400x400"
|
|
],
|
|
[
|
|
"/model.22/m.0/m.0.1/attn/Split_nhwc2nchw_transposed_output2",
|
|
"1x2x64x400"
|
|
],
|
|
[
|
|
"/model.22/m.0/m.0.1/attn/pe/conv/Conv_nchw2nhwc_transposed_input0",
|
|
"1x20x20x128"
|
|
],
|
|
[
|
|
"/model.22/m.0/m.0.0/Add_output_0_quantized",
|
|
"1x20x20x128"
|
|
],
|
|
[
|
|
"/model.22/Split_output_0_quantized",
|
|
"1x20x20x128"
|
|
],
|
|
[
|
|
"/model.22/Split_output_1_quantized",
|
|
"1x20x20x128"
|
|
]
|
|
],
|
|
"interval computing unit utilization": [
|
|
0.062,
|
|
0.124,
|
|
0.098,
|
|
0.168,
|
|
0.05,
|
|
0.267,
|
|
0.229,
|
|
0.072,
|
|
0.12,
|
|
0.192,
|
|
0.192,
|
|
0.0,
|
|
0.088,
|
|
0.092,
|
|
0.179,
|
|
0.092,
|
|
0.087,
|
|
0.088,
|
|
0.092,
|
|
0.092,
|
|
0.179,
|
|
0.087,
|
|
0.0,
|
|
0.231,
|
|
0.231,
|
|
0.0,
|
|
0.231,
|
|
0.231,
|
|
0.615,
|
|
0.053,
|
|
0.08,
|
|
0.094,
|
|
0.137,
|
|
0.202,
|
|
0.122,
|
|
0.015
|
|
],
|
|
"interval computing units utilization": [
|
|
0.062,
|
|
0.124,
|
|
0.098,
|
|
0.168,
|
|
0.05,
|
|
0.267,
|
|
0.229,
|
|
0.072,
|
|
0.12,
|
|
0.192,
|
|
0.192,
|
|
0.0,
|
|
0.088,
|
|
0.092,
|
|
0.179,
|
|
0.092,
|
|
0.087,
|
|
0.088,
|
|
0.092,
|
|
0.092,
|
|
0.179,
|
|
0.087,
|
|
0.0,
|
|
0.231,
|
|
0.231,
|
|
0.0,
|
|
0.231,
|
|
0.231,
|
|
0.615,
|
|
0.053,
|
|
0.08,
|
|
0.094,
|
|
0.137,
|
|
0.202,
|
|
0.122,
|
|
0.015
|
|
],
|
|
"interval loading bandwidth (megabytes/s)": [
|
|
3916,
|
|
3024,
|
|
3019,
|
|
2929,
|
|
2502,
|
|
3547,
|
|
2578,
|
|
800,
|
|
244,
|
|
244,
|
|
488,
|
|
479,
|
|
2166,
|
|
3848,
|
|
3448,
|
|
2996,
|
|
2807,
|
|
3103,
|
|
3678,
|
|
3833,
|
|
3401,
|
|
2827,
|
|
4333,
|
|
5733,
|
|
5182,
|
|
5985,
|
|
6007,
|
|
4590,
|
|
2693,
|
|
2304,
|
|
3413,
|
|
3548,
|
|
3477,
|
|
3290,
|
|
3187,
|
|
1519
|
|
],
|
|
"interval number": 36,
|
|
"interval storing bandwidth (megabytes/s)": [
|
|
2539,
|
|
3234,
|
|
3166,
|
|
3147,
|
|
3772,
|
|
2322,
|
|
2589,
|
|
5149,
|
|
6193,
|
|
5762,
|
|
5251,
|
|
5956,
|
|
4636,
|
|
2612,
|
|
2683,
|
|
3135,
|
|
3654,
|
|
3371,
|
|
2780,
|
|
2612,
|
|
2730,
|
|
3320,
|
|
2469,
|
|
573,
|
|
292,
|
|
313,
|
|
292,
|
|
858,
|
|
1367,
|
|
2343,
|
|
3125,
|
|
2783,
|
|
2490,
|
|
2294,
|
|
2157,
|
|
1165
|
|
],
|
|
"interval time (ms)": 0.2,
|
|
"latency (ms)": 7.01,
|
|
"latency (ms) by segments": [
|
|
7.008
|
|
],
|
|
"latency (us)": 7007.7,
|
|
"loaded bytes per frame": 22904576,
|
|
"loaded bytes per run": 22904576,
|
|
"model json CRC": "29e36293",
|
|
"model json file": "/tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_2.hbir",
|
|
"model name": "Extracted from {main_graph}_subgraph_2",
|
|
"model param CRC": "00000000",
|
|
"multicore sync time (ms)": 0.0,
|
|
"run per second": 142.7,
|
|
"runtime version": "3.15.55.0",
|
|
"stored bytes per frame": 21372928,
|
|
"stored bytes per run": 21372928,
|
|
"worst FPS": 142.7
|
|
}
|
|
}
|