Proceedings of the 22nd International Symposium on High-Performance Computer Architecture (HPCA), Barcelona, Spain, March 2016.
Kevin K. Chang, Prashant J. Nair*, Donghyuk Lee, Saugata Ghose, Moinuddin K. Qureshi*, Onur Mutlu
Carnegie Mellon University
* Georgia Institute of Technology
This paper introduces a new DRAM design that enables fast and energy-effi cient bulk data movement across subarrays in a DRAM chip. While bulk data movement is a key operation in many applications and operating systems, contemporary systems perform this movement ine fficiently, by transferring data from DRAM to the processor, and then back to DRAM, across a narrow off -chip channel. The use of this narrow channel for bulk data movement results in high latency and energy consumption. Prior work proposed to avoid these high costs by exploiting the existing wide internal DRAM bandwidth for bulk data movement, but the limited connectivity of wires within DRAM allows fast data movement within only a single DRAM subarray. Each subarray is only a few megabytes in size, greatly restricting the range over which fast bulk data movement can happen within DRAM.
We propose a new DRAM substrate, Low-Cost Inter-Linked Subarrays (LISA), whose goal is to enable fast and effi cient data movement across a large range of memory at low cost. LISA adds low-cost connections between adjacent subarrays. By using these connections to interconnect the existing internal wires (bitlines) of adjacent subarrays, LISA enables wide-bandwidth data transfer across multiple subarrays with little (only 0.8%) DRAM area overhead. As a DRAM substrate, LISA is versatile, enabling an array of new applications. We describe and evaluate three such applications in detail: (1) fast inter-subarray bulk data copy, (2) in-DRAM caching using a DRAM architecture whose rows have heterogeneous access latencies, and (3) accelerated bitline precharging by linking multiple precharge units together. Our extensive evaluations show that each of LISA’s three applications significantly improves performance and memory energy efficiency, and their combined benefit is higher than the benefit of each alone, on a variety of workloads and system configurations.
FULL PAPER: pdf