Alibaba Group Holding Limited

Alibaba (china) Co., Ltd.

Samsung Electronics Co., Ltd.

T-head (shanghai) Semiconductor Co., Ltd.

Alibaba Damo (hangzhou) Technology Co., Ltd.

Shuangchen Li

Hongzhong Zheng

Dimin Niu

Tianchan Guan

Fei Xue

Wei Han

Krishna Teja Malladi

Fei Sun

Yuan Xie

Yuhao Wang

Lide Duan

Bob Brennan

Yijin Guan

Jilan Lin

Heng Liu

Zhe Zhang

Feng Zhu

Weifeng Zhang

Yuanwei Fang

Guoyang Chen

Hongyu Liu

Xiaoxin Fan

Shengcheng Wang

Zhenyu Gu

Yingmin Li

Liu Liu

Jingjun Chu

Xipeng Shen

Honzhong Zheng

This specification describes methods and systems for accessing attribute data in graph neural network (GNN) processing. An example system includes: a plurality of cores, each of the plurality of cores comprises a key-value fetcher and a filter, and is programmable using a software interface to support a plurality of data formats of the GNN attribute data, wherein: the key-value fetcher is programmable using the software interface to perform key-value fetching associated with accessing the GNN attribute data, and the filter of at least one of the plurality of cores is programmable using the software interface to sample node identifiers associated with accessing the GNN attribute data; and a first memory communicatively coupled with the plurality of cores, wherein the first memory is configured to store data shared by the plurality of cores.

Programmable access engine architecture for graph neural network and graph application

The present disclosure discloses a processor. The processor is used to perform parallel computation and includes a logic die and a memory die. The logic die includes a plurality of processor cores and a plurality of networks on chip, wherein each processor core is programmable. The plurality of networks on chip are correspondingly connected to the plurality of processor cores, so that the plurality of processor cores form a two-dimensional mesh network. The memory die and the processor core are stacked vertically, wherein the memory die includes a plurality of memory tiles, and when the processor performs the parallel computation, the plurality of memory tiles do not have cache coherency; wherein, the plurality of memory tiles correspond to the plurality of processor cores in a one-to-one or one-to-many manner.

Two-dimensional processing array with a vertically stacked memory tile array

A processor includes a plurality of memory units, each of the memory units including a plurality of memory cells, wherein each of the memory units is configurable to operate as memory, as a computation unit, or as a hybrid memory-computation unit.

Scaling out architecture for dram-based processing unit (DPU)

This application describes systems and methods for facilitating memory access for graph neural network (GNN) processing. An example method includes fetching, by an access engine circuitry implemented on a circuitry board, a portion of structure data of a graph from a pinned memory in a host memory of a host via a first peripheral component interconnect express (PCIe) connection; performing node sampling using the fetched portion of the structure data of the graph to select one or more sampled nodes; fetching, by the access engine circuitry, a portion of attribute data of the graph from the pinned memory via the first PCIe connection; sending the fetched portion of the attribute data of the graph to one or more processors; and performing, by the one or more processors, GNN processing for the graph using the fetched portion of the attribute data of the graph.

Graph acceleration solution with cloud FPGA

A system-in-package including a logic die and one or more memory dice can include a reliability availability serviceability (RAS) memory management unit (MMU) for memory error detection, memory error prediction and memory error handling. The RAS MMU can receive memory health information, on-die memory error information, system error information and read address information for the one or more memory dice. The RAS MMU can manage the memory blocks of the one or more memory dice based on the memory health information, on-die memory error type, system error type and read address. The RAS MMU can also further manage the memory blocks based on received on-die memory temperature information and or system temperature information.

Error detection, prediction and handling techniques for system-in-package memory architectures

The presented systems enable efficient and effective network communications. The presented systems enable efficient and effective network communications. In one embodiment a memory device includes a memory module, including a plurality of memory chips configured to store information; and an inter-chip network (ICN)/shared smart memory extension (SMX) memory interface controller (ICN/SMX memory interface controller) configured to interface between the memory module and an inter-chip network (ICN), wherein the ICN is configured to communicatively couple the memory device to a parallel processing unit (PPU). In one exemplary implementation, the ICN/SMX memory controller includes a plurality of package buffers, an ICN physical layer interface, a PRC/MAC interface, and a switch. The memory device and be a memory card including memory module (e.g., DDR DIMM, etc.).

Flexible memory extension systems and methods

A memory management method of a data processing system is provided. The memory management method includes: creating a first memory zone and a second memory zone related to a first node of a first server, wherein the first server is located in the data processing system, and the first node includes a processor and a first memory; mapping the first memory zone to the first memory; and mapping the second memory zone to a second memory of a second server, wherein the second server is located in the data processing system, and the processor is configured to access the second memory of the second server through an interface circuit of the first server and through an interface circuit of the second server.

Data processing system and memory management method of data processing system

An embodiment of the present disclosure relates to a graph node sampling system and a computer-implemented method, where structure information of nodes in a graph neural network is stored in a set of data structures, and attribute data of the nodes is stored in another set of data structures. Node sampling may be performed by a sampling unit in a solid state drive. A node sampling unit selects, reads, and collects attribute data of a sampled node and a neighboring node of the sampled node, and transfers the data to a main memory. The method and system according to the embodiments of the present disclosure can save bandwidth consumed by node sampling in large applications such as a graph neural network.

System for graph node sampling and method implemented by computer

The present invention provides systems and methods for efficiently and effectively priming and initializing a memory. In one embodiment, a memory controller includes a normal data path and a priming path. The normal data path directs storage operations during a normal memory read/write operation after power startup of a memory chip. The priming path includes a priming module, wherein the priming module directs memory priming operations during a power startup of the memory chip, including forwarding a priming pattern for storage in a write pattern mode register of a memory chip and selection of a memory address in the memory chip for initialization with the priming pattern. The priming pattern includes information corresponding to proper initial data values. The priming pattern can also include proper corresponding error correction code (ECC) values. The priming module can include a priming pattern register that stores the priming pattern.

Memory priming and initialization systems and methods

A data processing system includes a first server and a second server. The first server includes a first processor group, a first memory space and a first interface circuit. The second server includes a second processor group, a second memory space and a second interface circuit. The first memory space and the second memory space are allocated to the first processor group. The first processor group is configured to perform memory error detection to generate an error log corresponding to a memory error. When the memory error occurs in the second memory space, the first interface circuit is configured to send the error log to the second interface circuit, and the second processor group is configured to log the memory error according to the error log received by the second interface circuit. The data processing system is capable of realizing memory reliability architecture supporting operations across different servers.

Data processing system

Embodiments of the disclosure provide devices and methods for performing a top-k function. The device can include: a memory comprising a plurality of register files for storing the data elements, the plurality of register files comprising a parent register file and a first child register file associated with the parent register file, wherein the parent register file is associated with: first interface circuitry configured for reading a first parent data element from the parent register file and receiving a first child data element and a second child data element from the first child register file; and first comparison circuitry configured for updating the parent register file and the first child register file based on the first parent data element, the first child data element, and the second child data element according to a given principle.

Performing a top-k function using a binary heap tree

Scaling out architecture for DRAM-based processing unit (DPU)

Systems and methods for dynamically executing sparse neural networks are provided. In one implementation, a system for providing dynamic sparsity in a neural network may include at least one memory storing instructions and at least one processor configured to execute the instructions to: reduce an input vector and a set of weights of the neural network, execute an input layer of the neural network using the reduced input vector and set of weights to generate a reduced output vector; expand the reduced output vector to a full output vector using first predictable output neurons (PONs); using a PON map, reduce a dimension of the full output vector; execute subsequent layers of the neural network using the reduced full output vector to produce a second reduced output vector; and expand the second reduced output vector to a second full output vector using second PONs.

Systems and methods for accelerating sparse neural network execution

This specification describes methods and systems for accelerating attribute data access for graph neural network (GNN) processing. An example method includes: receiving a root node identifier corresponding to a node in a graph for GNN processing; determining one or more candidate node identifiers according to the root node identifier, wherein attribute data corresponding to the one or more candidate node identifiers are sequentially stored in a memory; and sampling one or more graph node identifiers at least from the one or more candidate node identifiers for the GNN processing.

Access friendly memory architecture of graph neural network sampling

This application describes a hardware accelerator, a computer system, and a method for accelerating Graph Neural Network (GNN) node attribute fetching. The hardware accelerator comprises a GNN attribute processor; and a first memory, wherein the GNN attribute processor is configured to: receive a graph node identifier; determine a target memory address within the first memory based on the graph node identifier; determine, based on the received graph node identifier, whether attribute data corresponding to the received graph node identifier is cached in the first memory at the target memory address; and in response to determining that the attribute data is not cached in the first memory: fetch the attribute data from a second memory, and write the fetched attribute data into the first memory at the target memory address.

Growing community of inventors

Sunnyvale, CA, United States of America

Shuangchen Li