Multifunction content addressable memory for parallel speech understanding Export

@inproceedings{c_cagle_holl_southcon_94, abstract = {Content Addressable Memories (CAMs) allow considerably finer-grained parallelism than conventional shared or distributed memory multi-processors. This fine-grained \“Processor-In-Memory\” concept can be employed to a large degree during Semantic Network processing in support of Artificial Intelligence (AI) with specific applications in speech and natural language processing. A special-purpose CAM configuration is presented based on requirements for a nominally-sized 64 K node semantic network with 8 bit-markers and 32 relationship types. Analysis for a target application shows that the extensive use of parallel Marker-Propagation and Set Theoretic Operations yields approximately 30-fold speedup over systems with standard Random Access Memories}, address = {Orlando, Florida, U.S.A.}, author = {Cagle, R. and Holl, R. and Demara, R.}, citeulike-article-id = {87087}, citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=498125}, journal = {Southcon/94. Conference Record}, keywords = {demara}, pages = {320--325}, posted-at = {2005-02-03 17:43:37}, priority = {2}, title = {Multifunction content addressable memory for parallel speech understanding}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=498125}, year = {1994} }

TY - CONF ID - c_cagle_holl_southcon_94 L3 - citeulike-article-id:87087 N2 - Content Addressable Memories (CAMs) allow considerably finer-grained parallelism than conventional shared or distributed memory multi-processors. This fine-grained “Processor-In-Memory” concept can be employed to a large degree during Semantic Network processing in support of Artificial Intelligence (AI) with specific applications in speech and natural language processing. A special-purpose CAM configuration is presented based on requirements for a nominally-sized 64 K node semantic network with 8 bit-markers and 32 relationship types. Analysis for a target application shows that the extensive use of parallel Marker-Propagation and Set Theoretic Operations yields approximately 30-fold speedup over systems with standard Random Access Memories JF - Southcon/94. Conference Record AD - Orlando, Florida, U.S.A. EP - 325 TI - Multifunction content addressable memory for parallel speech understanding SP - 320 KW - demara AU - Cagle, R AU - Holl, R AU - Demara, R PY - 1994/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=498125 ER -