Login / Signup

An 8.8 TFLOPS/W Floating-Point RRAM-Based Compute-in-Memory Macro Using Low Latency Triangle-Style Mantissa Multiplication.

Xianwu HuYu WangZizhao MaGan WenZeming WangZhichao LuYunlong LiuYanlei LiXingdong LiangXiaoyang ZengYufeng Xie
Published in: IEEE Trans. Circuits Syst. II Express Briefs (2023)
Keyphrases
  • floating point
  • low latency
  • high speed
  • fixed point
  • high throughput
  • high bandwidth
  • real time
  • highly efficient
  • instruction set
  • virtual machine
  • stream processing
  • memory management
  • probabilistic model
  • main memory