258 lines
5.9 KiB
JSON
258 lines
5.9 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": 138583616,
|
|
"DDR bytes per run": 138583616,
|
|
"DDR bytes per second": 6348938021,
|
|
"DDR megabytes per frame": 132.164,
|
|
"DDR megabytes per run": 132.164,
|
|
"DDR megabytes per second": 6054.8,
|
|
"FPS": 45.81,
|
|
"HBDK version": "3.49.15",
|
|
"compiling options": "-f hbir -m /tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_1.hbir -o /tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_1.hbm --march bayes-e --progressbar --input-layout NHWC --output-layout NHWC",
|
|
"frame per run": 1,
|
|
"frame per second": 45.81,
|
|
"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,
|
|
0.16,
|
|
0.172,
|
|
0.132,
|
|
0.178,
|
|
0.172,
|
|
0.155,
|
|
0.041,
|
|
0.159,
|
|
0.132,
|
|
0.102,
|
|
0.108,
|
|
0.106,
|
|
0.092,
|
|
0.258,
|
|
0.211,
|
|
0.005,
|
|
0.068,
|
|
0.063
|
|
],
|
|
"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,
|
|
0.16,
|
|
0.172,
|
|
0.132,
|
|
0.178,
|
|
0.172,
|
|
0.155,
|
|
0.041,
|
|
0.159,
|
|
0.132,
|
|
0.102,
|
|
0.108,
|
|
0.106,
|
|
0.092,
|
|
0.258,
|
|
0.211,
|
|
0.005,
|
|
0.068,
|
|
0.063
|
|
],
|
|
"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,
|
|
3170,
|
|
3187,
|
|
3041,
|
|
2923,
|
|
3186,
|
|
3201,
|
|
3079,
|
|
3135,
|
|
3143,
|
|
3389,
|
|
1956,
|
|
1806,
|
|
3369,
|
|
4712,
|
|
4296,
|
|
1800,
|
|
2998,
|
|
3677,
|
|
2265
|
|
],
|
|
"interval number": 44,
|
|
"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,
|
|
2832,
|
|
2645,
|
|
2539,
|
|
2726,
|
|
2529,
|
|
2333,
|
|
2513,
|
|
3134,
|
|
3191,
|
|
2505,
|
|
4209,
|
|
4556,
|
|
2963,
|
|
1693,
|
|
1549,
|
|
3476,
|
|
3214,
|
|
3125,
|
|
3059
|
|
],
|
|
"interval time (ms)": 0.5,
|
|
"latency (ms)": 21.83,
|
|
"latency (ms) by segments": [
|
|
21.828
|
|
],
|
|
"latency (us)": 21827.8,
|
|
"loaded bytes per frame": 72009792,
|
|
"loaded bytes per run": 72009792,
|
|
"model json CRC": "f7a1faaa",
|
|
"model json file": "/tmp/tmpo3cnuwll/Extracted from {main_graph}_subgraph_1.hbir",
|
|
"model name": "Extracted from {main_graph}_subgraph_1",
|
|
"model param CRC": "00000000",
|
|
"multicore sync time (ms)": 0.0,
|
|
"run per second": 45.81,
|
|
"runtime version": "3.15.55.0",
|
|
"stored bytes per frame": 66573824,
|
|
"stored bytes per run": 66573824,
|
|
"worst FPS": 45.81
|
|
}
|
|
}
|