Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale.
Zhaoxia DengJongsoo ParkPing Tak Peter TangHaixin LiuJie YangHector YuenJianyu HuangDaya Shanker KhudiaXiaohan WeiEllie WenDhruv ChoudharyRaghuraman KrishnamoorthiCarole-Jean WuNadathur SatishChangkyu KimMaxim NaumovSam NaghshinehMikhail SmelyanskiyPublished in: IEEE Micro (2021)