274 lines
6.2 KiB
JSON
274 lines
6.2 KiB
JSON
{
|
|
"summary": {
|
|
"BPU OPs per frame (effective)": 2136627200,
|
|
"BPU OPs per run (effective)": 2136627200,
|
|
"BPU PE number": 1,
|
|
"BPU core number": 1,
|
|
"BPU march": "B25E",
|
|
"DDR bytes per frame": 149824064,
|
|
"DDR bytes per run": 149824064,
|
|
"DDR bytes per second": 6365457415,
|
|
"DDR megabytes per frame": 142.883,
|
|
"DDR megabytes per run": 142.883,
|
|
"DDR megabytes per second": 6070.6,
|
|
"FPS": 42.49,
|
|
"HBDK version": "3.49.15",
|
|
"compiling options": "-f hbir -m /tmp/tmp0plq7oph/main_graph_subgraph_1.hbir -o /tmp/tmp0plq7oph/main_graph_subgraph_1.hbm --march bayes-e --progressbar --input-layout NHWC --output-layout NHWC",
|
|
"frame per run": 1,
|
|
"frame per second": 42.49,
|
|
"input features": [
|
|
[
|
|
"input name",
|
|
"input size"
|
|
],
|
|
[
|
|
"/model.10/m/m.0/attn/Transpose_1_output_0_calibrated_quantized",
|
|
"1x2x400x400"
|
|
],
|
|
[
|
|
"/model.10/m/m.0/attn/Split_nhwc2nchw_transposed_output2",
|
|
"1x2x64x400"
|
|
],
|
|
[
|
|
"/model.10/m/m.0/attn/pe/conv/Conv_nchw2nhwc_transposed_input0",
|
|
"1x20x20x128"
|
|
],
|
|
[
|
|
"/model.10/Split_output_1_quantized",
|
|
"1x20x20x128"
|
|
],
|
|
[
|
|
"/model.10/Split_output_0_quantized",
|
|
"1x20x20x128"
|
|
],
|
|
[
|
|
"/model.6/cv2/act/Mul_output_0_quantized",
|
|
"1x40x40x128"
|
|
],
|
|
[
|
|
"/model.4/cv2/act/Mul_output_0_quantized",
|
|
"1x80x80x128"
|
|
]
|
|
],
|
|
"interval computing unit utilization": [
|
|
0.101,
|
|
0.101,
|
|
0.199,
|
|
0.154,
|
|
0.112,
|
|
0.108,
|
|
0.101,
|
|
0.079,
|
|
0.106,
|
|
0.185,
|
|
0.096,
|
|
0.355,
|
|
0.093,
|
|
0.139,
|
|
0.152,
|
|
0.124,
|
|
0.185,
|
|
0.039,
|
|
0.128,
|
|
0.103,
|
|
0.117,
|
|
0.112,
|
|
0.085,
|
|
0.148,
|
|
0.134,
|
|
0.137,
|
|
0.093,
|
|
0.163,
|
|
0.118,
|
|
0.124,
|
|
0.173,
|
|
0.106,
|
|
0.219,
|
|
0.144,
|
|
0.157,
|
|
0.064,
|
|
0.128,
|
|
0.1,
|
|
0.186,
|
|
0.072,
|
|
0.108,
|
|
0.126,
|
|
0.226,
|
|
0.159,
|
|
0.084,
|
|
0.031,
|
|
0.084,
|
|
0.021
|
|
],
|
|
"interval computing units utilization": [
|
|
0.101,
|
|
0.101,
|
|
0.199,
|
|
0.154,
|
|
0.112,
|
|
0.108,
|
|
0.101,
|
|
0.079,
|
|
0.106,
|
|
0.185,
|
|
0.096,
|
|
0.355,
|
|
0.093,
|
|
0.139,
|
|
0.152,
|
|
0.124,
|
|
0.185,
|
|
0.039,
|
|
0.128,
|
|
0.103,
|
|
0.117,
|
|
0.112,
|
|
0.085,
|
|
0.148,
|
|
0.134,
|
|
0.137,
|
|
0.093,
|
|
0.163,
|
|
0.118,
|
|
0.124,
|
|
0.173,
|
|
0.106,
|
|
0.219,
|
|
0.144,
|
|
0.157,
|
|
0.064,
|
|
0.128,
|
|
0.1,
|
|
0.186,
|
|
0.072,
|
|
0.108,
|
|
0.126,
|
|
0.226,
|
|
0.159,
|
|
0.084,
|
|
0.031,
|
|
0.084,
|
|
0.021
|
|
],
|
|
"interval loading bandwidth (megabytes/s)": [
|
|
3201,
|
|
2992,
|
|
2422,
|
|
1226,
|
|
830,
|
|
2343,
|
|
3369,
|
|
3361,
|
|
3314,
|
|
4400,
|
|
5767,
|
|
4176,
|
|
2968,
|
|
3160,
|
|
3091,
|
|
3270,
|
|
2892,
|
|
2888,
|
|
3125,
|
|
3881,
|
|
3804,
|
|
3113,
|
|
3257,
|
|
3351,
|
|
3364,
|
|
3207,
|
|
2952,
|
|
3133,
|
|
3392,
|
|
2887,
|
|
2981,
|
|
3392,
|
|
3286,
|
|
3127,
|
|
3018,
|
|
2975,
|
|
3132,
|
|
3628,
|
|
2591,
|
|
1769,
|
|
2832,
|
|
3808,
|
|
4208,
|
|
3242,
|
|
2314,
|
|
3034,
|
|
3506,
|
|
1721
|
|
],
|
|
"interval number": 48,
|
|
"interval storing bandwidth (megabytes/s)": [
|
|
3021,
|
|
3283,
|
|
3521,
|
|
4563,
|
|
5338,
|
|
3978,
|
|
2983,
|
|
3096,
|
|
3125,
|
|
1674,
|
|
351,
|
|
1289,
|
|
2402,
|
|
2939,
|
|
2861,
|
|
2539,
|
|
2782,
|
|
3369,
|
|
3389,
|
|
2392,
|
|
2421,
|
|
2929,
|
|
2929,
|
|
2832,
|
|
2636,
|
|
2788,
|
|
3193,
|
|
2944,
|
|
2573,
|
|
3218,
|
|
2852,
|
|
2454,
|
|
2415,
|
|
2336,
|
|
2602,
|
|
3137,
|
|
3250,
|
|
2570,
|
|
3364,
|
|
4348,
|
|
3632,
|
|
2462,
|
|
1638,
|
|
2343,
|
|
3786,
|
|
3648,
|
|
3115,
|
|
1647
|
|
],
|
|
"interval time (ms)": 0.5,
|
|
"latency (ms)": 23.54,
|
|
"latency (ms) by segments": [
|
|
23.537
|
|
],
|
|
"latency (us)": 23537.0,
|
|
"loaded bytes per frame": 77695040,
|
|
"loaded bytes per run": 77695040,
|
|
"model json CRC": "d4eae3d3",
|
|
"model json file": "/tmp/tmp0plq7oph/main_graph_subgraph_1.hbir",
|
|
"model name": "main_graph_subgraph_1",
|
|
"model param CRC": "00000000",
|
|
"multicore sync time (ms)": 0.0,
|
|
"run per second": 42.49,
|
|
"runtime version": "3.15.55.0",
|
|
"stored bytes per frame": 72129024,
|
|
"stored bytes per run": 72129024,
|
|
"worst FPS": 42.49
|
|
}
|
|
}
|