Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_0ee33b0e3e7398cf6fc957eeee59d510 http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_8bb531ac161ea927fd276b48f26bc7af |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F2212-454 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F2212-1021 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-30047 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-30043 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F12-0875 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-30141 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F17-16 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-30036 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-3012 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F12-0875 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F9-312 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F17-16 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F9-30 |
filingDate |
2021-08-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_37aa70439f5c0d5fddf3904e4e50ca22 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4aaec9e382d42c66537214ed50f47eff http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ee2c91b269478c06adc5ca9b0e9567f0 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9cca91ff266e5ee18d8970c41a3de232 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2f1329d2304193d8e7f6773a09d982e3 |
publicationDate |
2021-11-30-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-113721982-A |
titleOfInvention |
Sparse matrix storage method, vector calculation method and electronic equipment |
abstract |
The present application relates to a sparse matrix storage method of storing a sparse matrix for vector calculation in a memory of a computing device, a vector calculation method executed by the computing device, an electronic device, and a computer-readable storage medium. The sparse matrix storage method comprises the following steps: determining a column number of a vector register in a computing device for vector computation; determining the number of non-zero elements of each row of the sparse matrix; determining a group of the sparse matrix comprising a plurality of matrix rows based on the number of non-zero elements of each row of the sparse matrix and the number of columns of the vector register for vector calculation, wherein a difference between the number of non-zero elements of each of the plurality of matrix rows in each group is less than a first threshold, and storing the non-zero elements corresponding to the same matrix row in each group in the memory in columns, respectively. Thus, the storage performance of the sparse matrix is improved, and the vector calculation process is simplified. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-116186526-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-116186526-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115576895-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115576895-A |
priorityDate |
2021-08-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |