White Papers

6 Deep Learning using iAbra stack on Dell EMC PowerEdge Servers with Intel technology
1.1 Deep Learning Inferencing
After a model is trained, the generated model may be deployed (forward propagation only) e.g., on FPGAs,
CPUs or GPUs to perform a specific business-logic function or task such as identification, classification,
recognition and segmentation. [Figure 2].
For this model deployment and inferencing stage, FPGAs are getting more and more attractive for CNN
because of their increasing floating-point operation (FLOP) performance with hardened support in Intel’s
Generation 10 FPGA’s, and secondly
their support for both sparse data and compact data types. These trends are favoring FPGA-based platforms
since FPGAs are designed to handle irregular parallelism and fine-grained computations compared to GPUs
and CPUs. The focus of this blog will be on FPGA as accelerated inference platform for CNNs.
Inference Flow.