Samsung Electronics Co., Ltd.

Sandisk Technologies Inc.

Jingpei Yang

Changho Choi

Rekha Pitchumani

Rajinikanth Pandurangan

Jing Yang

Vijay Balakrishnan

Janki Bhimani

Nisha D Talagala

Swaminathan Sundararaman

Jason Martineau

Ned Plasson

Jianjian Huo

Ramaraj Pandian

Gregory N Gillis

YangSeok Ki

Robert Barry Wood

Sungwook Ryu

Hingkwan Huen

Anahita Shayesteh

Manu Awasthi

Dhananjoy Das

Anand Subramanian

A multi-stream memory system includes an in-device data processor including a first data processing engine and a second data processing engine, a controller processor, and a processor memory coupled to the controller processor, wherein the processor memory has stored thereon instructions that, when executed by the controller processor, cause the controller processor to perform: identifying a stream ID of an input stream, identifying the first data processing engine as being associated with the stream ID based on a stream assignment table, and applying the first data processing engine to the input stream to generate processed data.

System and method for in-SSD data processing engine selection based on stream IDs

Workload distribution in a system including a non-volatile memory device is disclosed. A request is received including an address associated with a memory location of the non-volatile memory device. A hash value is calculated based on the address. A list of node values is searched, and one of the node values in the list is identified based on the hash value. A processor is identified based on the one of the node values, and the address is stored in association with the processor. The request is transmitted to the processor for accessing the memory location.

Systems and methods for workload distribution across processing units

A multi-stream solid-state device (SSD) includes a normal-access memory associated with a first stream ID, a high-access memory having a higher endurance than the normal-access memory and being associated with a second stream ID, a controller processor, and a processor memory coupled to the controller processor, wherein the processor memory has stored thereon instructions that, when executed by the controller processor, cause the controller processor to perform identifying a data stream ID of an input data stream as one of the first and second stream IDs, in response to identifying the data stream ID as the first stream ID, storing the input data stream in the normal-access memory, and in response to identifying the data stream ID as the second stream ID, storing the input data stream in the high-access memory.

System and method for stream based data placement on hybrid SSD

A storage device is disclosed. The storage device may include storage for data. A host interface logic may receive a dataset and a logical address from a host. A stream assignment logic may assign a stream identifier (ID) to a compressed dataset based on a compression characteristic of the compressed dataset. The stream ID may be one of at least two stream IDs; the compressed dataset may be determined based on the dataset. A logical-to-physical translation layer may map the logical address to a physical address in the storage. A controller may store the compressed dataset at the physical address using the stream ID.

Automatic data separation and placement for compressed data in a storage device

A storage device includes non-volatile memory, a storage controller including a first controller processor connected to the non-volatile memory, and a second controller processor connected to the non-volatile memory, and shared memory to store a mapping table. The shared memory may be connected to the first controller processor and the second controller processor to share mapping table information between the first controller processor and the second controller processor. The storage controller may set a power mode of the first controller processor and the second controller processor based on an input/output intensity.

Storage device and method of data management on a storage device

A storage device is disclosed. The storage device may include storage to store data, which may include a first storage of a first type and a second storage of a second type. The storage device may support a number of device streams, some of which associated with the first storage and some associated with the second storage. The storage device may also include a streaming capabilities analyzer that may inventory the streaming capabilities for the storage device. Finally, the storage device may include a transmitter to transmit the streaming capabilities of the storage device to a storage manager.

Multistreaming in heterogeneous environments

System and method for in-SSD data processing engine selection based on stream IDS

A Solid State Drive (SSD) is disclosed. The SSD may include flash memory to store data and may support a plurality of device streams. A SSD controller may manage reading and writing data to the flash memory, and may store a submission queue and a chunk-to-stream mapper. A flash translation layer may include a receiver to receive a write command, an LBA mapper to map an LBA to a chunk identifier (ID), stream selection logic to select a stream ID based on the chunk ID, a stream ID adder to add the stream ID to the write command, a queuer to place the chunk ID in the submission queue, and background logic to update the chunk-to-stream mapper after the chunk ID is removed from the submission queue.

Automatic stream detection and assignment algorithm

A system for parallel computing leveraging the use of a key value solid state drive. The system including a modified set of compiler directives that enable the use of parallel compute and data threads. The system may further include a concurrency manager to ensure that the parallel data threads are operated in a thread-safe manner.

Parallel key value based multithread machine learning leveraging KV-SSDS

According to one general aspect, an apparatus may include a storage memory to store a plurality of key-value pairs. The apparatus may include at least one snapshot counter configured to store an operation number associated with a respective snapshot of the plurality of key-value pairs. The apparatus may include a snapshot data structure configured to identify, for at least one key-value pair, which, if any, snapshot(s) the respective key-value pair is associated with.

Implementing snapshot and other functionality in KVSSD through garbage collection and FTL

Embodiments include a multi-stream storage device, a system including a multi-stream storage device, and a method, comprising: receiving an access to a multi-stream storage device; converting at least one parameter of the access into a stream identifier; and accessing the multi-stream storage device using the stream identifier.

Growing community of inventors

Santa Clara, CA, United States of America

Jingpei Yang