Login / Signup

A 16.38TOPS and 4.55POPS/W SRAM Computing-in-Memory Macro for Signed Operands Computation and Batch Normalization Implementation.

Xin QiaoQingyu GuoXiyuan TangJiahao SongRenjie WeiMeng LiRunsheng WangYuan Wang
Published in: IEEE Trans. Circuits Syst. I Regul. Pap. (2024)
Keyphrases
  • random access memory
  • efficient computation
  • efficiently computing
  • preprocessing
  • data transmission
  • information systems
  • efficient implementation
  • shared memory
  • parallel computation