Systems and methods to accelerate multiplication of sparse matrices
US-2020210517-A1 · Jul 2, 2020 · US
US12417098B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12417098-B2 |
| Application number | US-202318374176-A |
| Country | US |
| Kind code | B2 |
| Filing date | Sep 28, 2023 |
| Priority date | Apr 4, 2019 |
| Publication date | Sep 16, 2025 |
| Grant date | Sep 16, 2025 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A data processing method includes obtaining content of a descriptor when an operand of a first processing instruction includes the descriptor, where the descriptor is configured to indicate a shape of tensor data and to indicate data address of the tensor data, and executing the first processing instruction according to the content of the descriptor by determining the data address of the tensor data corresponding to the operand of the first processing instruction in a data storage space, according to the content of the descriptor, and according to the data address, executing data processing corresponding to the first processing instruction.
Opening claim text (preview).
What is claimed is: 1. A data processing method comprising: obtaining content of a descriptor when an operand of a first processing instruction includes the descriptor from a descriptor storage space, where the descriptor is configured to indicate a shape of tensor data and to indicate a data address of the tensor data, and executing the first processing instruction according to the content of the descriptor, including determining the data address of the tensor data corresponding to the operand of the first processing instruction in a data storage space, according to the content of the descriptor, and according to the data address, executing data processing corresponding to the first processing instruction; wherein the descriptor storage space for storing content of the descriptor is a storage space in an internal memory of a processor. 2. The data processing method of claim 1 , wherein the operand of the first processing instruction includes an identifier of the descriptor, and the content of the descriptor is obtained according to the identifier of the descriptor. 3. The data processing method of claim 1 , wherein the determining of the data address of the tensor data includes: when the operand further includes a data description position for the descriptor, determining the data address of the tensor data corresponding to the operand in the data storage space according to the content of the descriptor and the data description position. 4. The data processing method of claim 1 , wherein the descriptor is used to indicate a shape of N-dimensional tensor data, where N is a positive integer, where the content of the descriptor includes at least one shape parameter indicating the shape of the tensor data and at least one address parameter indicating the data address of the tensor data. 5. The data processing method of claim 4 , wherein the address parameter includes a base address of a datum point of the descriptor in the data storage space of the tensor data, wherein the shape parameter includes at least one of: a size of the data storage space in at least one of the N dimensions, a size of a storage area of the tensor data in at least one of the N dimensions, an offset of the storage area in at least one of the N dimensions, or a position of at least two vertices at diagonal positions in the N dimensions relative to the datum point. 6. The data processing method of claim 1 , wherein the first processing instruction includes a data access instruction, and the operand includes source data and target data, wherein the obtaining content of a descriptor when an operand of a first processing instruction includes the descriptor includes: obtaining, when the source data includes a first descriptor and the target data includes a second descriptor, content of the first descriptor and content of the second descriptor from the descriptor storage space, respectively, the determining a data address of tensor data corresponding to the operand of the first processing instruction in the data storage space according to the content of the descriptor includes: obtaining a first data address of the source data and a second data address of the target data according to the content of the first descriptor and the content of the second descriptor, respectively, and the executing data processing corresponding to the first processing instruction according to the data address includes: reading data from the first data address and writing the data to the second data address. 7. The data processing method of claim 1 , wherein the first processing instruction includes a data access instruction, and the operand includes source data and target data, wherein the obtaining content of a descriptor when an operand of a first processing instruction includes the descriptor includes: obtaining, when the source data includes a third descriptor, content of the third descriptor from the descriptor storage space, the determining a data address of tensor data corresponding to the operand of the first processing instruction in the data storage space according to the content of the descriptor includes: obtaining a third data address of the source data according to the content of the third descriptor, and the executing data processing corresponding to the first processing instruction according to the data address includes: reading data from the third data address and writing the data to the data address of the target data. 8. The data processing method of claim 1 , wherein the first processing instruction includes a data access instruction, and the operand includes source data and target data, wherein the obtaining content of a descriptor when an operand of a first processing instruction includes the descriptor includes: obtaining, when the target data includes a fourth descriptor, content of the fourth descriptor from the descriptor storage space, the determining a data address of tensor data corresponding to the operand of the first processing instruction in the data storage space according to the content of the descriptor includes: obtaining a fourth data address of the target data according to the content of the fourth descriptor, and the executing data processing corresponding to the first processing instruction according to the data address includes: reading data from the data address of the source data and writing the data to the fourth data address. 9. The data processing method of claim 1 , wherein the first processing instruction includes a data access instruction for transmission of data from on-chip to off-chip, or for transmission of data from off-chip to on-chip. 10. The data processing method of claim 1 , further comprising: decoding the received first processing instruction to obtain the first processing instruction, where the first processing instruction includes an operation code and one or more operands, and the operation code is used to indicate a processing type corresponding to the first processing instruction. 11. The data processing method of claim 1 , wherein the data storage space for storing tensor data is a storage space in an internal memory or an external memory of a processor. 12. A data processing apparatus comprising: a controller configured to obtain content of a descriptor from a descriptor storage space when an operand of a first processing instruction includes the descriptor, where the descriptor is configured to indicate a shape of tensor data and to indicate a data address of the tensor data; and a processing circuit configured to execute the first processing instruction according to the content of the descriptor, the execution comprising: determining the data address of the tensor data corresponding to the operand of the first processing instruction in a data storage space, according to the content of the descriptor; and according to the data address, executing data processing corresponding to the first processing instruction; wherein the descriptor storage space for storing content of the descriptor is a storage space in an internal memory of a processor. 13. The data processing apparatus of claim 12 , wherein the operand of the first processing instruction includes an identifier of the descriptor, and the content of the descriptor is obtained according to the identifier of the descriptor. 14. The data processing apparatus of claim 12 , wherein determining the data address of the tensor data corresponding to the operand of the first processing instruction in the data storage space according to the content of the descriptor includes: when the operand further includes a data description position for the descriptor, determining the
according to data descriptor, e.g. dynamic data typing · CPC title
using electronic means · CPC title
PCI express · CPC title
on a serial bus, e.g. I2C bus, SPI bus (on daisy chain buses G06F13/4247) · CPC title
Details of memory controller · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.