192 lines
4.8 KiB
JSON
192 lines
4.8 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": 69526848,
|
|
"DDR bytes per run": 69526848,
|
|
"DDR bytes per second": 6007224548,
|
|
"DDR megabytes per frame": 66.306,
|
|
"DDR megabytes per run": 66.306,
|
|
"DDR megabytes per second": 5728.9,
|
|
"FPS": 86.4,
|
|
"HBDK version": "3.49.15",
|
|
"compiling options": "-f hbir -m /tmp/tmp0plq7oph/main_graph_subgraph_2.hbir -o /tmp/tmp0plq7oph/main_graph_subgraph_2.hbm --march bayes-e --progressbar --input-layout NHWC --output-layout NHWC",
|
|
"frame per run": 1,
|
|
"frame per second": 86.4,
|
|
"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"
|
|
],
|
|
[
|
|
"/model.23/Reshape_output_0_quantized",
|
|
"1x1x4x6400"
|
|
],
|
|
[
|
|
"/model.23/Reshape_1_output_0_quantized",
|
|
"1x1x4x1600"
|
|
],
|
|
[
|
|
"/model.23/Reshape_3_output_0_quantized",
|
|
"1x1x4x6400"
|
|
],
|
|
[
|
|
"/model.23/Reshape_4_output_0_quantized",
|
|
"1x1x4x1600"
|
|
]
|
|
],
|
|
"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,
|
|
0.157,
|
|
0.081,
|
|
0.075,
|
|
0.081,
|
|
0.088,
|
|
0.306,
|
|
0.215,
|
|
0.665,
|
|
0.293,
|
|
0.186,
|
|
0.04
|
|
],
|
|
"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,
|
|
0.157,
|
|
0.081,
|
|
0.075,
|
|
0.081,
|
|
0.088,
|
|
0.306,
|
|
0.215,
|
|
0.665,
|
|
0.293,
|
|
0.186,
|
|
0.04
|
|
],
|
|
"interval loading bandwidth (megabytes/s)": [
|
|
3201,
|
|
2992,
|
|
2422,
|
|
1226,
|
|
830,
|
|
2343,
|
|
3369,
|
|
3361,
|
|
3314,
|
|
4400,
|
|
5767,
|
|
4176,
|
|
2968,
|
|
3307,
|
|
3182,
|
|
3782,
|
|
3875,
|
|
3431,
|
|
2435,
|
|
2139,
|
|
2077,
|
|
1788,
|
|
2890,
|
|
1952
|
|
],
|
|
"interval number": 24,
|
|
"interval storing bandwidth (megabytes/s)": [
|
|
3021,
|
|
3283,
|
|
3521,
|
|
4563,
|
|
5338,
|
|
3978,
|
|
2983,
|
|
3096,
|
|
3125,
|
|
1674,
|
|
351,
|
|
1289,
|
|
2402,
|
|
2529,
|
|
2602,
|
|
2379,
|
|
2306,
|
|
2694,
|
|
2816,
|
|
2836,
|
|
1861,
|
|
1879,
|
|
2413,
|
|
1197
|
|
],
|
|
"interval time (ms)": 0.5,
|
|
"latency (ms)": 11.57,
|
|
"latency (ms) by segments": [
|
|
11.479,
|
|
0.0,
|
|
0.095
|
|
],
|
|
"latency (us)": 11573.9,
|
|
"loaded bytes per frame": 36598144,
|
|
"loaded bytes per run": 36598144,
|
|
"model json CRC": "7202325c",
|
|
"model json file": "/tmp/tmp0plq7oph/main_graph_subgraph_2.hbir",
|
|
"model name": "main_graph_subgraph_2",
|
|
"model param CRC": "00000000",
|
|
"multicore sync time (ms)": 0.0,
|
|
"run per second": 86.4,
|
|
"runtime version": "3.15.55.0",
|
|
"stored bytes per frame": 32928704,
|
|
"stored bytes per run": 32928704,
|
|
"worst FPS": 86.4
|
|
}
|
|
}
|