K
Kimish Patel
Researcher at University of Southern California
Publications - 21
Citations - 257
Kimish Patel is an academic researcher from University of Southern California. The author has contributed to research in topics: Cache & Cache-only memory architecture. The author has an hindex of 9, co-authored 21 publications receiving 249 citations. Previous affiliations of Kimish Patel include Nvidia & Polytechnic University of Turin.
Papers
More filters
Book ChapterDOI
Energy-Efficient value-based selective refresh for embedded DRAMs
TL;DR: A value-based selective refresh scheme in which both horizontal and vertical clusters of zeros are identified and used to selectively deactivated refresh of such clusters achieves a net reduction of the number of refresh operations on average of 31%, evaluated on a set of typical embedded applications.
Proceedings ArticleDOI
Dynamic thermal management for MPEG-2 decoding
TL;DR: An effective dynamic thermal management (DTM) scheme for MPEG-2 decoding by allowing some degree of spatiotemporal quality degradation in order to make sure that the microprocessor chip continues to stay in a thermally safe state of operation, albeit with certain amount of image/video quality loss.
Journal ArticleDOI
MRI assessment of the thigh musculature in dermatomyositis and healthy subjects using diffusion tensor imaging, intravoxel incoherent motion and dynamic DTI
Eric E. Sigmund,Steven H. Baete,T. Luo,Kimish Patel,D. Wang,I. Rossi,Alejandra Duarte,Mary Bruno,D. Mossa,Alisa N. Femia,Sarika Ramachandran,David R. Stoffel,James S. Babb,Andrew G. Franks,Jenny T Bencardino +14 more
TL;DR: Static and dynamic diffusion imaging metrics show correlation with conventional imaging scores, reveal spatial heterogeneity, and provide means to differentiate dermatomyositis patients from controls.
Journal ArticleDOI
GOP-Level Dynamic Thermal Management in MPEG-2 Decoding
TL;DR: In this article, a dynamic thermal management (DTM) algorithm based on accurate estimation of the workload of frames in a group of pictures (GOP) in an MPEG-2 video stream and slack borrowing across the GOP frames in order to achieve a thermally safe state of operation in microprocessors during the video decoding process is presented.
Proceedings ArticleDOI
Frame buffer energy optimization by pixel prediction
TL;DR: The proposed architecture allows to dynamically update the locality information, and, unlike previous approaches, it works virtually independent of the size and position of the updates of the display frames.