Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_6963a306ec33074f03fcf967dc0b4148 |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06E1-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F8-41 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F7-78 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-5027 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06E1-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F8-4441 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F7-523 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-3836 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F7-50 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-063 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F8-41 |
filingDate |
2020-06-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_cf2df9e0b7b4abdad161ab1de2070666 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ab111991cfd3304ab88b1d08f8b61e07 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9484860dc0f7be5d5c769b186e006a07 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6734e9059b1ff7bc68d57c39487b8371 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_01771ed5163726d51395a05e4f1e58f9 |
publicationDate |
2022-04-07-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
DE-112020003066-T5 |
titleOfInvention |
TRANSPOSE OPERATIONS WITH PROCESSING ELEMENT ARRAY |
abstract |
Systems and methods for transposing a tensor using processing element array operations are provided. In some cases it may be necessary to transpose elements of a tensor to perform a matrix operation. The tensor can be broken down into blocks of data elements whose dimensions match the dimensions of a systolic array. Identity multiplication can be performed on each block of data elements loaded into a systolic array and the multiplication products are summed in column partitions of a result buffer. The data elements in the column portions of the result buffer can then be mapped to row portions of a buffer memory for further processing. |
priorityDate |
2019-06-27-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |