Computing How to compute with large sensitive data? Biomedical data - PowerPoint PPT Presentation

Aug 08, 2023 •377 likes •514 views

U SING T RUSTED E XECUTION E NVIRONMENTS O N H IGH -P ERFORMANCE C OMPUTING P LATFORMS Ayaz Akram, Anna Giannakou, Venkatesh Akella, Jason Lowe-Power, Sean Peisert Secure High-Performance Computing How to compute with large sensitive data?

U SING T RUSTED E XECUTION E NVIRONMENTS O N H IGH -P ERFORMANCE C OMPUTING P LATFORMS Ayaz Akram, Anna Giannakou, Venkatesh Akella, Jason Lowe-Power, Sean Peisert
Secure High-Performance Computing How to compute with large sensitive data? Biomedical data Proprietary data Secure from both external and internal threats Integrity or confidentiality or both 2
High-Performance Computing Workloads Common characteristics Large data sets (10s – 100s GB per node) Limited user interaction (batch) Often highly multithreaded Dedicated (super computers) or shared (cloud) nodes Diverse compute, memory, and security requirements 3
We Analyze Two TEEs [1] [1] Technology Ensures TCB Size Secure Memory Size Application Integrity Changes Intel SGX Yes Small 128 MB (useable: 94MB) Required AMD SEV No Large Up to RAM size Not Required 4 [1] Christian Göttel et al. "Security, performance and energy trade-offs of hardware-assisted memory protection mechanisms." IEEE Symposium on Reliable Distributed Systems (SRDS), 2018.
Methodology • Benchmarks used: NAS parallel benchmarks, LightGBM and GAPBS • Platforms used: Intel Core i7-8700 (12 threads/socket) for SGX and AMD EPYC 7451 (dual socket with 48 threads/socket) for SEV study • Use of SCONE (SGX) and Kata (SEV) containers • Measured slowdown of the used workloads under secure execution on both platforms • Relate the slowdown to other collected metrics 5
Performance Impact of SGX High slowdown, especially for graph workloads 100 145 NPB (Class C) GAPBS (synth) GAPBS (road) LGBM (mslr) 6
Enclave Page Cache (EPC) Faults NPB (Class C) GAPBS (synth) GAPBS (road) LGBM (mslr) 360 500 7
Enclave Page Cache (EPC) Faults All the benchmarks have large resident memory except ep & tc_synth 8
Impact of Increasing Execution Threads (under SGX) Don't scale well, as they have large resident memory 9
Impact of Increasing Execution Threads (under SGX) Scales normally under SGX and has a small memory footprint 10
Performance Impact of SEV NPB (Class C) GAPBS (synth) GAPBS (road) LGBM (mslr) 11
Performance Impact of SEV Virtualization appears to be the biggest reason of slowdown 12
Preliminary Takeaways Future TEEs should support HPC apps Smaller slowdowns for SEV Performance issues for SGX EPC faults Multiple execution threads SEV and SGX slowdowns Dynamic choice of threat model 13

Recommend

Ray Wu Presentation to School of Computing, National University of Singapore Computing Evolution

Ray Wu Presentation to School of Computing, National University of Singapore Computing Evolution Internet Cloud/Mobile Computing Mainframe Client/Server Computing Everywhere Computing Computing Microsoft Apple TBD Yahoo IBM Google

614 views • 13 slides

Cloud Computing SENY KAMARA MICROSOFT RESEARCH Computing as a Service 2 Computing is a

Cloud Security & Cryptography I Cloud Computing SENY KAMARA MICROSOFT RESEARCH Computing as a Service 2 Computing is a vital resource Enterprises, governments, scientists, consumers, Computing is manageable at small

955 views • 51 slides

Bridging The Gap Between Networking And Computing A vision of future end-host computing Noa

Bridging The Gap Between Networking And Computing A vision of future end-host computing Noa Zilberman Andrew W. Moore April 2015 Can Networking Answer rack-scale Computing Challenges? Scalability Resilience Predictability Computing

345 views • 9 slides

DNA computing and self- -assembly assembly DNA computing and self Jie Gao References: Erik

DNA computing and self- -assembly assembly DNA computing and self Jie Gao References: Erik Winfree and Ashish Goel Computing Computing Human technology Electronic circuits. Biological systems Biochemical circuits.

1.41k views • 95 slides

15-292 History of Computing Growth of Analog Computing & the Birth of Computing Theory

1/27/20 15-292 History of Computing Growth of Analog Computing & the Birth of Computing Theory Analog Computers Instead of computing with numbers, one builds a physical model (an analog) of the system to be investigated Used when

233 views • 21 slides

COMPUTING COMMUNITY CONSORTIUM The mission of the Computing Research Association's Computing

COMPUTING COMMUNITY CONSORTIUM The mission of the Computing Research Association's Computing Community Consortium (CCC) is to catalyze the computing research community and enable the pursuit of innovative, high-impact research. Bring the computing

784 views • 30 slides

LHC Computing LHC Computing Nick Brook The LHC & experiments Requirements

LHC Computing LHC Computing Nick Brook The LHC & experiments Requirements Computing models Experiences so far Interoperability LCG Baseline service group Future requirements Summary 1 st EGEE User forum

821 views • 30 slides

Science One Math March 11, 2019 Applications of Integration Computing areas Computing

Science One Math March 11, 2019 Applications of Integration Computing areas Computing changes Computing volumes Computing probabilities Locating centre of mass of a lamina Key ideas slicing, approximating, adding

566 views • 28 slides

Science One Math March 1, 2017 Applications of Integration Computing areas Computing

Science One Math March 1, 2017 Applications of Integration Computing areas Computing changes Computing volumes Computing probabilities Locating centre of mass of an object Work done by a non constant force Application of

464 views • 20 slides

Cloud Computing & Cloud Models Cloud Models Topics Defining cloud computing

Cloud Computing & Cloud Models Cloud Models Topics Defining cloud computing Understanding: Distributed Application Design Resource Management Automation Virtualized Computing Environments High-performance Computing

1.02k views • 49 slides

Secure Outsourcing Computation Li Xiong Outline Cloud computing Computing on encrypted

CS573 Data Privacy and Security Secure Outsourcing Computation Li Xiong Outline Cloud computing Computing on encrypted data Homomorphic encryption What is Cloud Computing ? Cloud computing Type of computing that relies on sharing

1.29k views • 62 slides

MSc Advanced Computing, MSc Computing (Spec.) Comp. 4th year, ISE 4th year & JMC 4th year 480

Imperial College London - Department of Computing MSc Advanced Computing, MSc Computing (Spec.) Comp. 4th year, ISE 4th year & JMC 4th year 480 AUTOMATED REASONING CBC Otter Practice (Assessed) Issued: 30 October 2012 Due: 12 November 2011

202 views • 4 slides

Ubiquitous Computing Gabriela Avram IxDM13 The Trends in Computing Technology 1970s 1990s

Ubiquitous Computing Gabriela Avram IxDM13 The Trends in Computing Technology 1970s 1990s Late 1990s Now and Tomorrow ? Pervasive Computing Era Computing Evolution Ubiquitous Computing Mark Weiser, Xerox PARC 1988 Ubiquitous

525 views • 29 slides

GPU Computing and Accelerators: Part V Jens Saak Scientific Computing II 237/348 Open

Chapter 4 GPU Computing and Accelerators: Part V Jens Saak Scientific Computing II 237/348 Open Computing Language (OpenCL) Main Message The abstraction for the programming and hardware models are very similar to the CUDA concepts. Mainly

813 views • 32 slides

THE COMPUTING COMMUNITY CONSORTIUM (CCC) COMPUTING COMMUNITY CONSORTIUM The mission of Computing

THE COMPUTING COMMUNITY CONSORTIUM (CCC) COMPUTING COMMUNITY CONSORTIUM The mission of Computing Research Association's Computing Community Consortium (CCC) is to catalyze the computing research community and enable the pursuit of innovative,

317 views • 28 slides

Table of Contents Why DNA Computing? The Structure of DNA DNA Computing Operations on DNA

Table of Contents Why DNA Computing? The Structure of DNA DNA Computing Operations on DNA Molecules Reading DNA Example of a Molecular Computer Information Processing with DNA Molecules Christian Jacob Why DNA Computing?

223 views • 9 slides

Table of Contents Why DNA Computing? The Structure of DNA DNA Computing Operations on

400 views • 7 slides

Neural Computing for Scientific Computing Applications: More than Just Machine Learning

Photos placed in horizontal position with even amount of white space between photos and header Neural Computing for Scientific Computing Applications: More than Just Machine Learning Neuromorphic Computing Workshop, Knoxville TN, 7/17/17 Brad

410 views • 22 slides

The MNM-CloudLab -- Ideas, Concepts & Implemenation 17.7. 22.7. 2011 Nils gentschen Felde

DEUTSCH-FRANZSISCHE SOMMERUNIVERSITT UNIVERSIT DT FRANCO-ALLEMANDE FR NACHWUCHSWISSENSCHAFTLER 2011 POUR JEUNES CHERCHEURS 2011 CLOUD COMPUTING : CLOUD COMPUTING : CLOUD COMPUTING : CLOUD COMPUTING : DFIS ET OPPORTUNITS

968 views • 50 slides

Cloud Computing Tom Hendrickx RESEARCH QUESTION Define Cloud Computing in context of the higher

Cloud Computing Tom Hendrickx RESEARCH QUESTION Define Cloud Computing in context of the higher education and research community in general and of an NREN in specific. CLOUD COMPUTING SaaS PaaS STaaS IaaS Utility GRID computing

458 views • 9 slides

CMS Computing Using the Worldwide LHC Computing Grids Lothar A. T. Bauerdick/Fermilab Talk at

CMS CMS CMS Computing Using the Worldwide LHC Computing Grids Lothar A. T. Bauerdick/Fermilab Talk at the International Symposium for Grid Computing 2006 Academia Sinica, Taipei, May 2006 LATBauerdick Fermilab ISGC 2006 CMS Computing

683 views • 22 slides

CEPH FileSystem Course: Computing Clusters, Computing Grids, Computing Clouds Presenter: An Pham

CEPH FileSystem Course: Computing Clusters, Computing Grids, Computing Clouds Presenter: An Pham (ptan1991@gmail.com) Professor: Andrey Y Shevel ITMO University, St. Petersburg, Russia June 2018. 1 An Pham - ITMO - Summer 2018 Outlines 1.

408 views • 17 slides

Computing Sparse Hessians with AD Andrea Walther Institute of Scientific Computing TU Dresden

Computing Sparse Hessians with AD Andrea Walther Institute of Scientific Computing TU Dresden Hatfield, May 21, 2007 Overview Motivation 1 Computing Sparsity Patterns 2 Evaluating Hessian-matrix Products 3 Numerical Results 4

667 views • 35 slides

Wearable Computing Gabriel Reyes CS-HCI PhD Student School of Interactive Computing CS 4470 /

Wearable Computing Gabriel Reyes CS-HCI PhD Student School of Interactive Computing CS 4470 / CS 6456 W. Keith Edwards Quick Experiment How many forms of computing are you wearing today? (Dont count whats in your purse or

819 views • 60 slides