An efficient sparse LSTM accelerator on embedded FPGAs with bandwidth-oriented pruning
Long short-term memory (LSTM) networks have been widely used in natural language processing applications. Although over 80% weights can be pruned to reduce the memory requirement with little accuracy loss, the pruned model still cannot be buffered on-chip for small embedded FPGAs. Considering that w...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/172603 |