“Brilliant idea, but if ever implemented would require an absolutely transparent audit process by as many people as possible because of security implications... That being said, it's a brilliant idea! In fact, I'll do you one better -- publicly accessible CPU or CPU's inside of each memory chip, having access to that chip's RAM... Great idea for speed/s…”
In-DRAM Bulk Bitwise Execution Engine
Many applications heavily use bitwise operations on large bitvectors as part of their computation. In existing systems, performing such bulk bitwise operations requires the processor to transfer a large amount of data on the memory channel, thereby consuming high latency, memory bandwidth, and energy. In this paper, we describe Ambit, a recently-proposed mechanism to perform bulk bitwise operations completely inside main memory. Ambit exploits the internal organization and analog operation of DRAM-based memory to achieve low cost, high performance, and low energy. Ambit exposes a new bulk bitwise execution model to the host processor. Evaluations show that Ambit significantly improves the performance of several applications that use bulk bitwise operations, including databases.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)- In-DRAM Bulk Bitwise Execution Engine ↗lainon · 2019-05-27 · 1 分
- In-DRAM Bulk Bitwise Execution Engine ↗godelmachine · 2019-05-28 · 4 分
- In-DRAM Bulk Bitwise Execution Engine ↗matt_d · 2019-06-03 · 4 分