Michael Gschwind  Michael Gschwind photo       

contact information

Chief Engineer, Machine Learning and Deep Learning
IBM TJ Watson Research Center


Professional Associations

Professional Associations:  ACM  |  ACM Distinguished Speaker   |  ACM SIGMICRO  |  Executive Board, ACM SIGMICRO  |  Fellow, IEEE  |  IEEE   |  IEEE Computer Society

I/O Virtualization and System Acceleration in POWER8
Hot Chips 27, Cupertino, CA, 2015.

Harnessing Ubiquitous Heterogeneous Multicore Design 
Keynote Speech, delivered at 2015 Workshop on Programming Models, Languages and Compilers for Manycore and Heterogeneous Architectures (PLC 2015), IPDPS 2015, Hyderabad, India, May 2015.

Introducing the Little-Endian OpenPOWER Software Development Environment and its application programming interfaces
OpenPOWER Summit 2015, GPU Technology Conference, San Jose, CA, March 2015.

POWER8 — the first OpenPOWER processor
OpenPOWER Summit 2015, GPU Technology Conference, San Jose, CA, March 2015.

OpenPOWER: Liberating Large-Scale Data Centers with Power8
Keynote Speech, delivered at 11th IFIP Conference on Network and Parallel Computing, Ilan, Taiwan, 2014.

Unchaining the Data Center with OpenPower: Reengineering a Server Ecosystem for Large-Scale Data Centers
Hot Chips 26, Cupertino, CA, 2014.

Perking Up Code: Architecting High-Performing Dynamic Compilation Systems for the Future
Invited Workshop Opening Speech delivered at HiPEAC 2014 Dynamic Compilation Everywhere Workshop, Vienna, Austria, January 2014.

Blue Gene/Q: Design for Sustained Multi-Petaflop Computing
Keynote Speech delivered at International Conference on Supercomputing ICS 2012, Venice, Italy, June 2012.  

SoftBeam: Precise Tracking of Transient Faults and Vulnerability Analysis at Processor Design Time
29th International Conference on Computer Design ICCD 2011, Amherst, MA, October 2011.

High-Performance Architecture and Heterogeneous Computing
Panel on Heterogeneous Computing, 29th International Conference on Computer Design ICCD 2011, Amherst, MA, October 2011.

Programmable acceleration of data processing intensive workloads
Keynote Speech at 9th International Conference on Parallel Processing and Applied Mathematics (PPAM 2009), Wroclaw, Poland, September 2009.

Multicore Computing and the Cloud – Optimizing Systems with Virtualization
Keynote Speech at 8th International Symposium on Parallel and Distributed Computing (ISPDC 2009) , Lisboa, Portugal, July 2009.

Chip Multiprocessing: It's all about software
Keynote Speech at IBM Zurich Research Lab Software Symposium, Zürich, Switzerland, October 2008.

Optimizing Data Sharing and Address Translation for the Cell BE Heterogeneous Chip Multiprocessor
ICCD 2008, Squaw Creek, CA, October 2008.

Cell Broadband Engine - Enabling Density Computing for Data-Rich Environments
ISCA 2006 Tutorial, Boston, MA, June 2006.

Chip Multiprocessing and the Cell Broadband Engine
Keynote Speech delivered at ACM Computing Frontiers 2006, Ischia, Italy, May 2006.

Dynamic Compilation at the System Level
CGO 2006 Tutorial, New York, May 2006.

Compiler mediated performance of a Cell Processor
CGO 2006 Tutorial, New York, May 2006.

A Novel SIMD Architecture for the Cell Heterogeneous Chip Multiprocessor
Hot Chips 17, Palo Alto, CA, August 2005.

BOA: a Second Generation DAISY Architecture
ISCA 2004 Tutorial, Munich, June 2004.