Search papers, labs, and topics across Lattice.
Samsung Electronics
2
0
3
17
HBM-PIM can achieve impressive matrix multiplication throughput (14.9 GFLOP/s) using a novel reduction-free outer-product dataflow, even without native reduction support.
On-device LLM inference with PIM is now more practical: PIM-SHERPA resolves memory inconsistencies, slashing memory capacity needs by ~50% without sacrificing performance.
