When the --txt
or --txt_summary
option is used, vaitrace prints an ASCII
table as shown in the following figure:
Figure 1. ASCII Table
The fields are defined in the following list:
- DPU Id
- Name of the DPU instance .
- Bat
- Batch size of the DPU instance.
- SubGraph
- Name of subgraph in the xmodel.
- WL(Workload)
- Computation workload (MAC indicates two operations), unit is GOP
- RT(Run time)
- The execution time in milliseconds, unit is ms.
- Perf
- The DPU performance in unit of GOP per second, unit is GOP/s.
- LdFM (Load Size of Feature Map)
- External memory load size of feature map, unit is MB.
- LdWB (Load Size of Weight and Bias)
- External memory load size of bias and weight, unit is MB.
- StFM (Store Size of Feature Map)
- External memory store size of feature map, unit is MB.
- AvgBw(Average bandwidth)
- Average DDR memory access bandwidth.
AvgBw = (total load size of the subgraph (including feature map and weight/bias, from DDR/HBM to DPU bank mem) + total store size of the subgraph (from DPU bank mem to DDR/HBM)) / subgraph runtime