NDLI: DICE: Compressing DRAM Caches for Bandwidth and Capacity

Please wait, while we are loading the content...

In-Datacenter Performance Analysis of a Tensor Processing Unit

Bespoke Processors for Applications with Ultra-low Area and Power Constraints

Regaining Lost Cycles with HotCalls: A Fast Interface for SGX Secure Enclaves

ThermoGater: Thermally-Aware On-Chip Voltage Regulation

Chasing Away RAts: Semantics and Evaluation for Relaxed Atomics on Heterogeneous Systems

MTraceCheck: Validating Non-Deterministic Behavior of Memory Consistency Models in Post-Silicon Validation

Quality of Service Support for Fine-Grained Sharing on GPUs

EDDIE: EM-Based Detection of Deviations in Program Execution

LogCA: A High-Level Performance Model for Hardware Accelerators

Hardware Translation Coherence for Virtualized Systems

Language-level persistency

Architectural Support for Server-Side PHP Processing

Maximizing CNN Accelerator Efficiency Through Resource Partitioning

Aggressive Pipelining of Irregular Applications on Reconfigurable Hardware

Viyojit: Decoupling Battery and DRAM Capacities for Battery-Backed DRAM

APPROX-NoC: A Data Approximation Framework for Network-On-Chip Architectures

ScaleDeep: A Scalable Compute Architecture for Learning and Evaluating Deep Networks

A Programmable Galois Field Processor for the Internet of Things

InvisiMem: Smart Memory Defenses for Memory Bus Side Channel

PowerChief: Intelligent Power Allocation for Multi-Stage Applications to Improve Responsiveness on Power Constrained CMP

Hiding the Long Latency of Persist Barriers Using Speculative Execution

Redundant Memory Array Architecture for Efficient Selective Protection

Accelerating GPU Hardware Transactional Memory with Snapshot Isolation

Secure Hierarchy-Aware Cache Replacement Policy (SHARP): Defending Against Cache-Based Side Channel Atacks

Plasticine: A Reconfigurable Architecture For Parallel Paterns

Hybrid TLB Coalescing: Improving TLB Translation Coverage under Diverse Fragmented Memory Allocations

ShortCut: Architectural Support for Fast Object Access in Scripting Languages

HeteroOS: OS Design for Heterogeneous Memory Management in Datacenter

Scalpel: Customizing DNN Pruning to the Underlying Hardware Parallelism

Fractal: An Execution Model for Fine-Grain Nested Speculative Parallelism

DICE: Compressing DRAM Caches for Bandwidth and Capacity

There and Back Again: Optimizing the Interconnect in Networks of Memory Cubes

SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks

XPro: A Cross-End Processing Architecture for Data Analytics in Wearables

ObfusMem: A Low-Overhead Access Obfuscation for Trusted Memories

CHARSTAR: Clock Hierarchy Aware Resource Scaling in Tiled ARchitectures

Non-Speculative Load-Load Reordering in TSO

Clank: Architectural Support for Intermittent Computation

Decoupled Affine Computation for SIMT GPUs

Lemonade from Lemons: Harnessing Device Wearout to Create Limited-Use Security Architectures

A Programmable Hardware Accelerator for Simulating Dynamical Systems

Do-It-Yourself Virtual Memory Translation

Understanding and Optimizing Asynchronous Low-Precision Stochastic Gradient Descent

Parallel Automata Processor

The Mondrian Data Engine

Footprint: Regulating Routing Adaptiveness in Networks-on-Chip

MeRLiN: Exploiting Dynamic Instruction Behavior for Fast and Accurate Microarchitecture Level Reliability Assessment

Access Pattern-Aware Cache Management for Improving Data Utilization in GPU

Stream-Dataflow Acceleration

Rethinking TLB Designs in Virtualized Environments: A Very Large Part-of-Memory TLB

Jenga: Software-Defined Cache Hierarchies

EbDa: A New Theory on Design and Verification of Deadlock-free Interconnection Networks

The Reach Profiler (REAPER): Enabling the Mitigation of DRAM Retention Failures via Profiling at Aggressive Conditions

MCM-GPU: Multi-Chip-Module GPUs for Continued Performance Scalability

DICE: Compressing DRAM Caches for Bandwidth and Capacity

Content Provider	ACM Digital Library
Author	Young, Vinson Nair, Prashant J. Qureshi, Moinuddin K.
Abstract	This paper investigates compression for DRAM caches. As the capacity of DRAM cache is typically large, prior techniques on cache compression, which solely focus on improving cache capacity, provide only a marginal benefit. We show that more performance benefit can be obtained if the compression of the DRAM cache is tailored to provide higher bandwidth. If a DRAM cache can provide two compressed lines in a single access, and both lines are useful, the effective bandwidth of the DRAM cache would double. Unfortunately, it is not straight-forward to compress DRAM caches for bandwidth. The typically used Traditional Set Indexing (TSI) maps consecutive lines to consecutive sets, so the multiple compressed lines obtained from the set are from spatially distant locations and unlikely to be used within a short period of each other. We can change the indexing of the cache to place consecutive lines in the same set to improve bandwidth; however, when the data is incompressible, such spatial indexing reduces effective capacity and causes significant slowdown. Ideally, we would like to have spatial indexing when the data is compressible and TSI otherwise. To this end, we propose Dynamic-Indexing Cache comprEssion (DICE), a dynamic design that can adapt between spatial indexing and TSI, depending on the compressibility of the data. We also propose low-cost Cache Index Predictors (CIP) that can accurately predict the cache indexing scheme on access in order to avoid probing both indices for retrieving a given cache line. Our studies with a 1GB DRAM cache, on a wide range of workloads (including SPEC and Graph), show that DICE improves performance by 19.0% and reduces energy-delay-product by 36% on average. DICE is within 3% of a design that has double the capacity and double the bandwidth. DICE incurs a storage overhead of less than 1KB and does not rely on any OS support.
Starting Page	627
Ending Page	638
Page Count	12
File Format	PDF
ISBN	9781450348928
DOI	10.1145/3079856.3080243
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2017-06-24
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Compression Memory Bandwidth Stacked dram
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in