一句话：提出 Infinity Stream，用可移植、程序员友好的抽象自动并行化并调度存内/近存计算融合。
大型末级缓存上的存内计算可缓解数据移动瓶颈并释放位线级并行，但其独特执行模型仍面临自动并行化、为位串行逻辑透明编排数据转置/对齐/广播，以及混合存内与近存计算等挑战；同时方案须程序员友好且跨平台可移植。为此，作者提出 Infinity Stream，一个面向存内/近存融合的可移植编程与执行方案，试图屏蔽底层细节、自动完成并行化与数据编排，并统一存内/近存计算。摘要未报告具体实现细节与量化评估结果。
In-memory computing with large last-level caches is promising to dramatically alleviate data movement bottlenecks and expose massive bitline-level parallelization opportunities. However, key challenges from its unique execution model remain unsolved: automated parallelization, transparently orchestrating data transposition/alignment/broadcast for bit-serial logic, and mixing in-/near-memory computing. Most importantly, the solution should be programmer friendly and portable across platforms.
@inproceedings{paperbot10067,
title = {Infinity Stream: Portable and Programmer-Friendly In-/Near-Memory Fusion},
author = {Zhengrong Wang and Christopher Liu and Aman Arora and Lizy John and Tony Nowatzki},
booktitle = {ASPLOS},
year = {2023},
doi = {10.1145/3582016.3582032}
}