In particular, we develop new mechanisms that can effectively communicate a program’s data access properties to the OS and hardware and to use it to control data placement in hardware. In this work, we address these challenges with software-defined address mapping (SDAM) that, for the first time, enables user program to obtain a direct control of the low-level memory hardware in a more intelligent and fine-grained manner. Unfortunately, CLP is very sensitive to a program’s data access pattern, which is not made available to OS/hardware by existing mechanisms. However, it is challenging to fully exploit the abundant CLP for performance as the bandwidth utilization is highly dependent on address mapping in the memory controller. 3D-stacking memory such as High-Bandwidth Memory (HBM) and Hybrid Memory Cube (HMC) provides orders of magnitude more bandwidth and significantly increased channel-level parallelism (CLP) due to its new parallel memory architecture.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |