Show simple item record

dc.contributorKhatri, Sunil
dc.creatorGulati, Kanupriya
dc.date.accessioned2010-07-15T00:15:25Z
dc.date.accessioned2010-07-23T21:46:22Z
dc.date.accessioned2017-04-07T19:57:17Z
dc.date.available2010-07-15T00:15:25Z
dc.date.available2010-07-23T21:46:22Z
dc.date.available2017-04-07T19:57:17Z
dc.date.created2009-12
dc.date.issued2010-07-14
dc.identifier.urihttp://hdl.handle.net/1969.1/ETD-TAMU-2009-12-7471
dc.description.abstractWith the advances in very large scale integration (VLSI) technology, hardware is going parallel. Software, which was traditionally designed to execute on single core microprocessors, now faces the tough challenge of taking advantage of this parallelism, made available by the scaling of hardware. The work presented in this dissertation studies the acceleration of electronic design automation (EDA) software on several hardware platforms such as custom integrated circuits (ICs), field programmable gate arrays (FPGAs) and graphics processors. This dissertation concentrates on a subset of EDA algorithms which are heavily used in the VLSI design flow, and also have varying degrees of inherent parallelism in them. In particular, Boolean satisfiability, Monte Carlo based statistical static timing analysis, circuit simulation, fault simulation and fault table generation are explored. The architectural and performance tradeoffs of implementing the above applications on these alternative platforms (in comparison to their implementation on a single core microprocessor) are studied. In addition, this dissertation also presents an automated approach to accelerate uniprocessor code using a graphics processing unit (GPU). The key idea is to partition the software application into kernels in an automated fashion, such that multiple instances of these kernels, when executed in parallel on the GPU, can maximally benefit from the GPU?s hardware resources. The work presented in this dissertation demonstrates that several EDA algorithms can be successfully rearchitected to maximally harness their performance on alternative platforms such as custom designed ICs, FPGAs and graphic processors, and obtain speedups upto 800X. The approaches in this dissertation collectively aim to contribute towards enabling the computer aided design (CAD) community to accelerate EDA algorithms on arbitrary hardware platforms.
dc.language.isoeng
dc.subjectHardware Acceleration
dc.subjectGraphics Processing Units
dc.subjectFPGA
dc.subjectCustom IC
dc.subjectBoolean Satisfiability
dc.subjectFault Simulation
dc.titleHardware Acceleration of Electronic Design Automation Algorithms
dc.typeBook
dc.typeThesis


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record