S
Srinivas Devadas
Researcher at Massachusetts Institute of Technology
Publications - 498
Citations - 35003
Srinivas Devadas is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Sequential logic & Combinational logic. The author has an hindex of 88, co-authored 480 publications receiving 31897 citations. Previous affiliations of Srinivas Devadas include University of California, Berkeley & Cornell University.
Papers
More filters
Judicious Thread Migration When Accessing Distributed Shared Caches
TL;DR: This approach can better exploit shared data locality for NUCA designs by effectively replacing multiple round-trip remote cache accesses with a smaller number of migrations, and improves the performance by 18% on average and at best by 2.3X over the standard N UCA design that only uses remote accesses.
Journal ArticleDOI
ISDL: An Instruction Set Description Language for Retargetability and Architecture Exploration
TL;DR: The structure and features of ISDL are presented and how the information in an ISDL description may be used to retarget or generate assemblers, disassemblers,compilers, simulators, and hardware models are described.
Library Cache Coherence
TL;DR: Library Cache Coherence is presented, which requires neither broadcast/multicast for invalidations nor waiting for invalidation acknowledgements, and has 1.85X less average memory latency than a MESI directory-based protocol on a set of benchmarks, even with a simple timestamp choosing algorithm.
Journal ArticleDOI
Taurus: lightweight parallel logging for in-memory database management systems
TL;DR: Taurus is presented, an efficient parallel logging scheme that uses multiple log streams, and is compatible with both data and command logging, and tracks and encodes transaction dependencies using a vector of log sequence numbers (LSNs).
Proceedings ArticleDOI
Exact algorithms for output encoding, state assignment and four-level Boolean minimization
Srinivas Devadas,A.R. Newton +1 more
TL;DR: Computationally efficient heuristic approaches based on the exact algorithms are proposed for output encoding, state assignment, and four-level Boolean minimization for prime-implicant generation and covering and for state assignment.