Sigmastar Technology Ltd.

Bo Lin

Wei Zhu

Chao Li

Ming-Yong Sun

Jian Liu

Chengwei Zheng

Jian-Zhi Wang

Xiaofeng Li

Bing-Jie He

An operation method of a direct memory access (DMA) circuit comprising a buffer circuit and two channels includes following steps: determining first and second start addresses from the buffer circuit respectively according to first and second read requests of first and second channels that respectively correspond to first and second data; determining a read address according to the first start address and a read count; reading a first part of the first data from the buffer circuit according to the read address and updating the read count; reading at least one part of the second data from the buffer circuit according to the second start address after reading the first part of the first data; updating the read address according to the first start address and the updated read count; and reading a second part of the first data from the buffer circuit according to the updated read address.

Direct memory access (DMA) circuit and operation method thereof

An operation device includes a quantizer circuit, a buffer circuit, a convolution core circuit and a multiply-add circuit. The quantizer circuit receives first feature data and performs asymmetric uniform quantization on the first feature data to obtain and store in the buffer circuit second feature data. The quantizer circuit further receives a first weighting coefficient and performs symmetric uniform quantization on the first weighting coefficient to obtain and store in the buffer circuit a second weight coefficient. The convolution core circuit performs a convolution operation on the initial operation result, an actual quantization scale factor and an actual bias value to obtain a final operation result.

Operation device and operation method

A virtual memory management method applied to an intelligent processor including an operation accelerator includes: determining m storage units from a physical memory, the m storage units forming a virtual memory; dividing the m storage units into n storage groups; determining an address mapping relationship for each storage group to obtain n address mapping relationships, the n address mapping relationship being correspondence of between n virtual addresses of the virtual memory and physical addresses of the m storage units, where m and n are dynamically updated according to requirements of the operation accelerator. In the method, the number of the storage units in each storage group can be configured according to requirements of the operation accelerator, and a data storage bit width and a data storage depth of the virtual memory are dynamically updated to thereby improve data access efficiency.

Virtual memory management method and processor

A data temporary storage apparatus includes a moving unit coupled to a first storage unit and multiple second storage units. The moving unit receives a moving instruction having contents including a read address, a destination address and a predetermined moving rule. The moving unit further executes the moving instruction to fetch input data by row from the first storage unit according to the read address, and to temporarily stores one after another in an alternate and sequential manner the data in each row to each of the second storage units indicated by the destination address. The data moving, data reading and convolution approaches of the present invention implement in parallel data moving and a convolution operation, achieving a ping-pong operation of convolution units and enhancing convolution efficiency, while reducing memory costs since configuring two data storage spaces in a memory is not necessary.

Growing community of inventors

Xiamen, China

Bo Lin