Training convolutional neural networks (CNNs) requires intense compute
t...
Main memory (DRAM) consumes as much as half of the total system power in...
This paper summarizes the idea of ChargeCache, which was published in HP...
This paper summarizes the SoftMC DRAM characterization infrastructure, w...
This paper summarizes the idea of Low-Cost Interlinked Subarrays (LISA),...
This paper summarizes our work on experimental characterization and anal...
This article summarizes key results of our work on experimental
characte...
In existing systems, to perform any bulk data movement operation (copy o...
This paper summarizes the idea of Subarray-Level Parallelism (SALP) in D...
This paper summarizes the idea of Tiered-Latency DRAM (TL-DRAM), which w...
This paper summarizes the idea of Adaptive-Latency DRAM (AL-DRAM), which...
Modern DRAM cells are periodically refreshed to prevent data loss due to...
The energy consumption of DRAM is a critical concern in modern computing...
Bitwise operations are an important component of modern day programming....
Variation has been shown to exist across the cells within a modern DRAM ...
In modern systems, DRAM-based main memory is significantly slower than t...
This paper summarizes the idea of Adaptive-Latency DRAM (AL-DRAM), which...