Hasan Hassan, Nandita Vijaykumar, Samira Khan,

Slides:



Advertisements
Similar presentations
Thank you for your introduction.
Advertisements

Tiered-Latency DRAM: A Low Latency and A Low Cost DRAM Architecture
Page Overlays An Enhanced Virtual Memory Framework to Enable Fine-grained Memory Management Session 2B – 10:45 AM Vivek Seshadri Gennady Pekhimenko, Olatunji.
Software-Based Online Detection of Hardware Defects: Mechanisms, Architectural Support, and Evaluation Kypros Constantinides University of Michigan Onur.
Optimizing DRAM Timing for the Common-Case Donghyuk Lee Yoongu Kim, Gennady Pekhimenko, Samira Khan, Vivek Seshadri, Kevin Chang, Onur Mutlu Adaptive-Latency.
Yu Cai Ken Mai Onur Mutlu
Carnegie Mellon University, *Seagate Technology
Simultaneous Multi-Layer Access Improving 3D-Stacked Memory Bandwidth at Low Cost Donghyuk Lee, Saugata Ghose, Gennady Pekhimenko, Samira Khan, Onur Mutlu.
Optimizing DRAM Timing for the Common-Case Donghyuk Lee Yoongu Kim, Gennady Pekhimenko, Samira Khan, Vivek Seshadri, Kevin Chang, Onur Mutlu Adaptive-Latency.
Quantifying and Controlling Impact of Interference at Shared Caches and Main Memory Lavanya Subramanian, Vivek Seshadri, Arnab Ghosh, Samira Khan, Onur.
Carnegie Mellon University, *Seagate Technology
Genome Read In-Memory (GRIM) Filter: Fast Location Filtering in DNA Read Mapping using Emerging Memory Technologies Jeremie Kim 1, Damla Senol 1, Hongyi.
A Case for Toggle-Aware Compression for GPU Systems
Data Management Program Introduction
Improving Multi-Core Performance Using Mixed-Cell Cache Architecture
Zorua: A Holistic Approach to Resource Virtualization in GPUs
Transparent Offloading and Mapping (TOM) Enabling Programmer-Transparent Near-Data Processing in GPU Systems Kevin Hsieh Eiman Ebrahimi, Gwangsun Kim,
Improving searches through community clustering of information
A Case for Core-Assisted Bottleneck Acceleration in GPUs Enabling Flexible Data Compression with Assist Warps Session 2A: Today, 10:20 AM Nandita Vijaykumar.
Exploiting Inter-Warp Heterogeneity to Improve GPGPU Performance
Azure Allows Global Seed and Plant Industries to Combine Data in Central, Scalable Web App “Having the new product management application Mercado in the.
Aya Fukami, Saugata Ghose, Yixin Luo, Yu Cai, Onur Mutlu
Understanding Latency Variation in Modern DRAM Chips Experimental Characterization, Analysis, and Optimization Kevin Chang Abhijith Kashyap, Hasan Hassan,
A Case for Core-Assisted Bottleneck Acceleration in GPUs Enabling Flexible Data Compression with Assist Warps Nandita Vijaykumar Gennady Pekhimenko, Adwait.
Low-Cost Inter-Linked Subarrays (LISA) Enabling Fast Inter-Subarray Data Movement in DRAM Kevin Chang Prashant Nair, Donghyuk Lee, Saugata Ghose, Moinuddin.
A New Coherence Method Using A Multicast Address Network
Write-hotness Aware Retention Management: Efficient Hot/Cold Data Partitioning for SSDs Saugata Ghose ▪ joint.
Ambit In-Memory Accelerator for Bulk Bitwise Operations Using Commodity DRAM Technology Vivek Seshadri Donghyuk Lee, Thomas Mullins, Hasan Hassan, Amirali.
Thesis Oral Kevin Chang
ChargeCache Reducing DRAM Latency by Exploiting Row Access Locality
Prof. Gennady Pekhimenko University of Toronto Fall 2017
Application Slowdown Model
What Your DRAM Power Models Are Not Telling You: Lessons from a Detailed Experimental Study Saugata Ghose, A. Giray Yağlıkçı, Raghav Gupta, Donghyuk Lee,
Eiman Ebrahimi, Kevin Hsieh, Phillip B. Gibbons, Onur Mutlu
Rachata Ausavarungnirun, Joshua Landgraf, Vance Miller
Genome Read In-Memory (GRIM) Filter Fast Location Filtering in DNA Read Mapping with Emerging Memory Technologies Jeremie Kim, Damla Senol, Hongyi Xin,
Vulnerabilities in MLC NAND Flash Memory Programming: Experimental Analysis, Exploits, and Mitigation Techniques Yu Cai, Saugata Ghose, Yixin Luo, Ken.
GateKeeper: A New Hardware Architecture
7th and 8th Grade Science Weiner High School
Jeremie S. Kim Minesh Patel Hasan Hassan Onur Mutlu
Today, DRAM is just a storage device
Genome Read In-Memory (GRIM) Filter:
Vulnerabilities in MLC NAND Flash Memory Programming: Experimental Analysis, Exploits, and Mitigation Techniques HPCA Session 3A – Monday, 3:15 pm,
Research Methods in Behavior Change Programs
Application Slowdown Model
GRIM-Filter: Fast Seed Location Filtering in DNA Read Mapping
1 مفهوم ارتباطات ارتباطات معادل واژه communications ) ميباشد(. ارتباطات يك فرايند اجتماعي و دو طرفه است كه در آن اطلاعات مبادله شده و نوعي تفاهم بين طرفهاي.
Yixin Luo Saugata Ghose Yu Cai Erich F. Haratsch Onur Mutlu
Lecture 17: Transactional Memories I
Session 1A at am MEMCON Detecting and Mitigating
Linearly Compressed Pages: A Main Memory Compression Framework with Low Complexity and Low Latency Gennady Pekhimenko, Vivek Seshadri , Yoongu Kim, Hongyi.
MEMCON: Detecting and Mitigating Data-Dependent Failures by Exploiting Current Memory Content Samira Khan, Chris Wilkerson, Zhe Wang, Alaa Alameldeen,
DRAM SCALING CHALLENGE
A Case for Richer Cross-layer Abstractions: Bridging the Semantic Gap with Expressive Memory Nandita Vijaykumar Abhilasha Jain, Diptesh Majumdar, Kevin.
Arash Tavakkol, Mohammad Sadrosadati, Saugata Ghose,
Reducing DRAM Latency via
Accelerating Dependent Cache Misses with an Enhanced Memory Controller
Optimization This entails further development and refinements to the design. These developments and refinements may be necessary to correct a problem or.
Yaohua Wang, Arash Tavakkol, Lois Orosa, Saugata Ghose,
Jeremie S. Kim Minesh Patel Hasan Hassan Onur Mutlu
Samira Khan University of Virginia Nov 14, 2018
Linearly Compressed Pages: A Main Memory Compression Framework with Low Complexity and Low Latency Gennady Pekhimenko, Vivek Seshadri , Yoongu Kim, Hongyi.
CROW A Low-Cost Substrate for Improving DRAM Performance, Energy Efficiency, and Reliability Hi, my name is Hasan. Today, I will be presenting CROW, which.
Minesh Patel Jeremie S. Kim
CoNDA: Efficient Cache Coherence Support for Near-Data Accelerators
Computer Architecture Lecture 10b: Memory Latency
Computer Architecture Lecture 6a: ChargeCache
Architecting Phase Change Memory as a Scalable DRAM Alternative
Janus Optimizing Memory and Storage Support for Non-Volatile Memory Systems Sihang Liu Korakit Seemakhupt, Gennady Pekhimenko, Aasheesh Kolli, and Samira.
Presented by Florian Ettinger
Presentation transcript:

SoftMC A Flexible and Practical Open-Source Infrastructure for Enabling Experimental DRAM Studies Hasan Hassan, Nandita Vijaykumar, Samira Khan, Saugata Ghose, Kevin Chang, Gennady Pekhimenko, Donghyuk Lee, Oguz Ergin, Onur Mutlu Hello everyone. My name is Hasan and as the last talk of the last session today, I will present SoftMC, which is an infrastructure for testing DRAM.

Characterize, analyze, and understand DRAM behavior Reliability Performance Characterize, analyze, and understand DRAM behavior Reliability and Performance are two important problems of DRAM technology today. They may be even more important in the future, as it is becoming increasingly difficult to scale DRAM cells into smaller technology nodes. In fact, a new reliability issue, RowHammer, has been recently discovered, which exists only on new generation DRAM chips that are manufactured at small technology nodes. So, there is a significant need for new mechanisms that could improve DRAM reliability and performance To design, evaluate, and validate such mechanisms, it is important to accurately characterize, analyze and understand DRAM cell behavior.

SoftMC 1 2 Flexible Easy to Use (C++ API) Open-source Example Use Cases Retention Time Distribution Study 1 To this end, we propose SoftMC, an FPGA-based memory characterization infrastructure. It is flexible, so it can support testing of any DRAM operation, and easy to use thanks to the high-level programming language (C++) API that we provide. We release SoftMC as an open-source tool. SoftMC is available in our github repository. In my talk, later today, I will show you the two use cases that we implemented using SoftMC. First, we implement a Retention Time Distribution Study, using which we find the charge-retaining capability of the DRAM cells. This study serves as a validation of the correctness of SoftMC. Second, we evaluate two recently-proposed latency reduction mechanisms. From the results we obtain using SoftMC, we do not observe the expected latency reduction effect of these two mechanisms. That study shows the effectiveness of SoftMC on validating or refuting ideas that reduce DRAM latency. Evaluating Two Recently-Proposed Latency Reduction Mechanisms 2 github.com/CMU-SAFARI/SoftMC