Accel-Sim: An extensible simulation framework for validated GPU modeling

M Khairy, Z Shen, TM Aamodt… - 2020 ACM/IEEE 47th …, 2020 - ieeexplore.ieee.org
In computer architecture, significant innovation frequently comes from industry. However, the
simulation tools used by industry are often not released for open use, and even when they …

A case for exploiting subarray-level parallelism (SALP) in DRAM

Y Kim, V Seshadri, D Lee, J Liu, O Mutlu - ACM SIGARCH Computer …, 2012 - dl.acm.org
Modern DRAMs have multiple banks to serve multiple memory requests in parallel.
However, when two requests go to the same bank, they have to be served serially …

Figaro: Improving system performance via fine-grained in-dram data relocation and caching

Y Wang, L Orosa, X Peng, Y Guo… - 2020 53rd Annual …, 2020 - ieeexplore.ieee.org
Main memory, composed of DRAM, is a performance bottleneck for many applications, due
to the high DRAM access latency. In-DRAM caches work to mitigate this latency by …

A robust method for speech signal time-delay estimation in reverberant rooms

MS Brandstein, HF Silverman - 1997 IEEE International …, 1997 - ieeexplore.ieee.org
Conventional time-delay estimators exhibit dramatic performance degradations in the
presence of multipath signals. This limits their application in reverberant enclosures …

Improving DRAM performance by parallelizing refreshes with accesses

KKW Chang, D Lee, Z Chishti… - 2014 IEEE 20th …, 2014 - ieeexplore.ieee.org
Modern DRAM cells are periodically refreshed to prevent data loss due to leakage.
Commodity DDR (double data rate) DRAM refreshes cells at the rank level. This degrades …

[PDF][PDF] Research problems and opportunities in memory systems

O Mutlu, L Subramanian - Supercomputing frontiers and …, 2014 - superfri.susu.ru
The memory system is a fundamental performance and energy bottleneck in almost all
computing systems. Recent system design, application, and technology trends that require …

Simultaneous multi-layer access: Improving 3D-stacked memory bandwidth at low cost

D Lee, S Ghose, G Pekhimenko, S Khan… - ACM Transactions on …, 2016 - dl.acm.org
3D-stacked DRAM alleviates the limited memory bandwidth bottleneck that exists in modern
systems by leveraging through silicon vias (TSVs) to deliver higher external memory …

What your DRAM power models are not telling you: Lessons from a detailed experimental study

S Ghose, AG Yaglikçi, R Gupta, D Lee… - Proceedings of the …, 2018 - dl.acm.org
Main memory (DRAM) consumes as much as half of the total system power in a computer
today, due to the increasing demand for memory capacity and bandwidth. There is a …

Row buffer locality aware caching policies for hybrid memories

HB Yoon, J Meza, R Ausavarungnirun… - 2012 IEEE 30th …, 2012 - ieeexplore.ieee.org
Phase change memory (PCM) is a promising technology that can offer higher capacity than
DRAM. Unfortunately, PCM's access latency and energy are higher than DRAM's and its …

Decoupled direct memory access: Isolating CPU and IO traffic by leveraging a dual-data-port DRAM

D Lee, L Subramanian… - 2015 International …, 2015 - ieeexplore.ieee.org
Memory channel contention is a critical performance bottleneck in modern systems that have
highly parallelized processing units operating on large data sets. The memory channel is …