Abstract | ||
---|---|---|
This paper considers a hybrid memory system composed of memory technologies with different characteristics; in particular a small, near memory exhibiting high bandwidth, i.e., 3D-stacked DRAM, and a larger, far memory offering capacity at lower bandwidth, i.e., off-chip DRAM. In the past, the near memory of such a system has been used either as a DRAM cache or as part of a flat address space combined with a migration mechanism. Caches and migration offer different tradeoffs (between performance, main memory capacity, data transfer costs, etc.) and share similar challenges related to data-transfer granularity and metadata management. This paper proposes Hybrid
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>
, a new hybrid memory system architecture that combines a DRAM cache with a migration scheme. Hybrid
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>
does not deny valuable capacity from the memory system because it uses only a small fraction of the near memory as a DRAM cache; 64MB in our experiments. It further leverages the DRAM cache as a staging area to select the data most suitable for migration. Finally, Hybrid
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>
alleviates the metadata overheads of both DRAM caches and migration using a common mechanism. Using near to far memory ratios of 1:16, 1:8 and 1:4 in our experiments, Hybrid
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>
on average outperforms current state-of-the-art migration schemes by 7.9%, 9.1% and 6.4%, respectively. In the same system configurations, compared to DRAM caches Hybrid
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>
gives away on average only 0.3%, 1.2%, and 5.3% of performance offering 5.9%, 12.1%, and 24.6% more main memory capacity, respectively. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/HPCA47549.2020.00059 | 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA) |
Keywords | DocType | ISSN |
DRAM Cache,Data Migration,Hybrid Memory System,3D stacked DRAM,Memory | Conference | 1530-0897 |
ISBN | Citations | PageRank |
978-1-7281-6150-1 | 1 | 0.35 |
References | Authors | |
28 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Evangelos Vasilakis | 1 | 8 | 2.48 |
Vassilis Papaefstathiou | 2 | 97 | 13.71 |
Pedro Trancoso | 3 | 377 | 43.79 |
Ioannis Sourdis | 4 | 456 | 44.17 |