# US 2019/0171373 A1 · Object memory interfaces across shared links

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0171373 A1
- Document ID: US20190171373A1
- Status: Published application
- Kind: A1
- Application number: 16/266,460
- Filed: 2019-02-04
- Published: 2019-06-06
- Earliest claimed: 2015-12-08
- Assignees: Ultrata, LLC
- Applicants: Ultrata, LLC
- Inventors: Steven J. Frank; Larry Reback
- Web page: https://patentgrep.com/patent/US20190171373A1

## CPC

- G06F 3/0619: {in relation to data integrity, e.g. data losses, bit errors}
- G06F 3/0608: {Saving storage space on storage systems}
- G06F 3/061: {Improving I/O performance}
- G06F 3/0649: {Lifecycle management}
- G06F 3/065: {Replication mechanisms}
- G06F 3/0667: {at data level, e.g. file, record or object virtualisation}
- G06F 3/067: {Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]}
- G06F 11/00: Error detection; Error correction; Monitoring (error detection, correction or monitoring in information storage based on relative movement between record carrier and transducer G11B20/18; monitoring, i.e. supervising the progress of recording or reproducing G11B27/36; in static stores G11C29/00)
- G06F 11/14: Error detection or correction of the data by redundancy in operations (error detection or correction of the data by redundancy in hardware G06F11/16)
- G06F 11/3034: {where the computing system component is a storage system, e.g. DASD based or network based (digital input from or digital output to record carriers G06F3/06; digital recording or reproducing G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097)}
- G06F 11/3037: {where the computing system component is a memory, e.g. virtual memory, cache (accessing, addressing or allocating within memory systems or architectures G06F12/00; checking stores for correct operation G11C29/00)}
- G06F 11/3485: {for I/O devices}
- G06F 12/0223: {User address space allocation, e.g. contiguous or non contiguous base addressing}
- G06F 12/04: Addressing variable-length words or parts of words
- G06F 12/0815: Cache consistency protocols
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

According to one embodiment, a hardware-based processing node of a plurality of hardware-based processing nodes in an object memory fabric can comprise a memory module storing and managing a plurality of memory objects in a hierarchy of the object memory fabric. Each memory object can be created natively within the memory module, accessed using a single memory reference instruction without Input/Output (I/O) instructions, and managed by the memory module at a single memory layer. The object memory fabric can utilize a memory fabric protocol between the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes to distribute and track the memory objects across the object memory fabric. The memory fabric protocol can be utilized across a dedicated link or across a shared link between the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes.

## Claims

### Claim 1

A hardware-based processing node of a plurality of hardware-based processing nodes in an object memory fabric, the hardware-based processing node comprising:
a memory module storing and managing a plurality of memory objects in a hierarchy of the object memory fabric, wherein:
each memory object is created natively within the memory module through a name space of the object memory fabric,
each memory object is accessed by applications executing on the hardware-based processing node using a single memory reference instruction without Input/Output (I/O) instructions by the applications,
each memory object is managed by the memory module through the name space of the object memory fabric at a single memory layer without distinction between memory and storage, and
the object memory fabric utilizes the name space of the object memory fabric and a memory fabric protocol to communication between the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes.

### Claim 2 (depends on 1)

The hardware-based processing node of claim 1, wherein the memory fabric protocol is utilized across a dedicated link the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes.

### Claim 3 (depends on 2)

The hardware processing node of claim 2, wherein the dedicated link comprises an Ethernet link.

### Claim 4 (depends on 1)

The hardware-based processing node of claim 1, wherein the memory fabric protocol is tunneled across a shared link between the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes.

### Claim 5 (depends on 4)

The hardware-based processing node of claim 4, wherein the memory fabric protocol provides a dedicated communication link between the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes and the shared link supports communications other than the memory fabric protocol.

### Claim 6 (depends on 4)

The hardware-based processing node of claim 4, wherein the shared link comprises an Internet Protocol (IP) link.

### Claim 7 (depends on 1)

The hardware-based processing node of claim 1, wherein two or more nodes of the plurality of hardware-based processing nodes are remote from each other in the hierarchy of the object memory fabric and wherein the object memory fabric uses the memory fabric protocol to create neighborhoods of equal-distance nodes in the hierarchy of the object memory fabric.

### Claim 8 (depends on 1)

The hardware-based processing node of claim 1, wherein two or more nodes of the plurality of hardware-based processing nodes are each in different physical locations and wherein the object memory fabric uses the memory fabric protocol to cache and duplicate objects in a plurality of different physical locations.

### Claim 9 (depends on 1)

The hardware-based processing node of claim 1, wherein the object memory fabric uses the memory fabric protocol to track the memory objects and blocks within the memory objects that are present on the hardware-based processing node.

### Claim 10 (depends on 1)

The hardware-based processing node of claim 1, wherein the object memory fabric uses the memory fabric protocol to distributes the memory objects across the object memory fabric on a per-object basis.

### Claim 11 (depends on 1)

The hardware-based processing node of claim 1, wherein the object memory fabric uses the memory fabric protocol to propagate changes to the memory objects from the hardware-based processing node to one or more other nodes of the plurality of hardware-based processing nodes.

### Claim 12 (depends on 1)

The hardware-based processing node of claim 1, wherein the object memory fabric uses the memory fabric protocol to propagate changes to the memory objects from the hardware-based processing node to one or more other nodes of the plurality of hardware-based processing nodes by moving only data within the memory objects that has changed and without replicating or copying the memory object

### Claim 13 (depends on 1)

The hardware-based processing node of claim 1, wherein the hardware-based processing node comprises a Dual In-line Memory Module (DIMM) card.

### Claim 14 (depends on 1)

The hardware-based processing node of claim 1, wherein the hardware-based processing node comprises a commodity server and wherein the memory module comprises a Dual In-line Memory Module (DIMM) card installed within the commodity server.

### Claim 15 (depends on 1)

The hardware-based processing node of claim 1, wherein the hardware-based processing node comprises a mobile computing device.

### Claim 16 (depends on 1)

The hardware-based processing node of claim 1, wherein the hardware-based processing node comprises a single chip.

### Claim 17

An object memory fabric comprising:
a plurality of hardware-based processing nodes, each hardware-based processing node comprising:
one or more memory modules storing and managing a plurality of memory objects in a hierarchy of the object memory fabric, wherein each memory object is created natively within the memory module through a name space of the object memory fabric, each memory object is accessed by applications executing on the hardware-based processing node using a single memory reference instruction without Input/Output (I/O) instructions by the applications, each memory object is managed by the one or more memory modules through the name space of the object memory fabric at a single memory layer without distinction between memory and storage, and the object memory fabric utilizes the name space of the object memory fabric and a memory fabric protocol to communicate between the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes, and
a node router communicatively coupled with each of the one or more memory modules of the node and adapted to route memory objects or portions of memory objects between the one or more memory modules of the node using the memory fabric protocol; and
one or more inter-node routers communicatively coupled with each node router, wherein each of the plurality of nodes of the object memory fabric is communicatively coupled with at least one of the inter-node routers and adapted to route memory objects or portions of memory objects between the plurality of nodes using the memory fabric protocol.

### Claim 18 (depends on 17)

The object memory fabric of claim 17, wherein the memory fabric protocol is utilized across a dedicated link the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes.

### Claim 19 (depends on 18)

The object memory fabric of claim 18, wherein the dedicated link comprises an Ethernet link.

### Claim 20 (depends on 17)

The object memory fabric of claim 17, wherein the memory fabric protocol is tunneled across a shared link between the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes.

### Claim 21 (depends on 20)

The object memory fabric of claim 20, wherein the memory fabric protocol provides a dedicated communication link between the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes and the shared link supports communications other than the memory fabric protocol.

### Claim 22 (depends on 20)

The object memory fabric of claim 20, wherein the shared link comprises an Internet Protocol (IP) link.

### Claim 23 (depends on 17)

The object memory fabric of claim 17, further comprising a virtual link between at least one node router and an inter-node router or between two or more inter-node routers and wherein the virtual link comprises an Internet Protocol (IP) network of one or more routers or switches.

### Claim 24 (depends on 17)

The object memory fabric of claim 17, wherein two or more nodes of the plurality of hardware-based processing nodes are remote from each other in the hierarchy of the object memory fabric and wherein distributing and tracking the memory objects across the object memory fabric comprises creating neighborhoods of equal-distance nodes in the hierarchy of the object memory fabric.

### Claim 25 (depends on 17)

The object memory fabric of claim 17, wherein two or more nodes of the plurality of hardware-based processing nodes are each in different physical locations and wherein distributing and tracking the memory objects across the object memory fabric comprises caching and duplicating objects in a plurality of different physical locations.

### Claim 26 (depends on 17)

The object memory fabric of claim 17, wherein the object memory fabric uses the memory fabric protocol to track the memory objects and blocks within the memory objects across the object memory fabric.

### Claim 27 (depends on 17)

The object memory fabric of claim 17, wherein the object memory fabric uses the memory fabric protocol to distribute the memory objects across the object memory fabric on a per-object basis.

### Claim 28 (depends on 17)

The object memory fabric of claim 17, wherein the object memory fabric uses the memory fabric protocol to propagate changes to the memory objects from one of the hardware-based processing node to one or more other nodes of the plurality of hardware-based processing nodes.

### Claim 29 (depends on 17)

The object memory fabric of claim 17, wherein the object memory fabric uses the memory fabric protocol to propagate changes to the memory objects from the hardware-based processing node to one or more other nodes of the plurality of hardware-based processing nodes by moving only data within the memory objects that has changed and without replicating or copying the memory object.

### Claim 30 (depends on 17)

The object memory fabric of claim 17, wherein at least one of the hardware-based processing nodes comprises a Dual In-line Memory Module (DIMM) card.

### Claim 31 (depends on 17)

The object memory fabric of claim 17, wherein at least one of the hardware-based processing nodes comprises a commodity server and wherein the memory module comprises a Dual In-line Memory Module (DIMM) card installed within the commodity server.

### Claim 32 (depends on 17)

The object memory fabric of claim 17, wherein at least one of the hardware-based processing nodes comprises a mobile computing device.

### Claim 33 (depends on 17)

The object memory fabric of claim 17, wherein at least one of the hardware-based processing nodes comprises a single chip.

### Claim 34

A method for providing communication links in an object memory fabric comprising a plurality of hardware-based processing nodes, the method comprising:
creating, by the hardware-based processing nodes of the object memory fabric, each memory object natively within a memory module of a hardware-based processing node through a name space of the object memory fabric;
accessing, by the hardware-based processing nodes, each memory object using a single memory reference instruction without Input/Output (I/O) instructions;
managing, by the hardware-based processing nodes, each memory object within the memory module through the name space of the object memory fabric at a single memory layer without distinction between memory and storage; and
communicating between the hardware-based processing nodes using the name space of the object memory fabric and a memory fabric protocol.

### Claim 35 (depends on 34)

The method of claim 34, wherein the memory fabric protocol is utilized across a dedicated link the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes.

### Claim 36 (depends on 35)

The method of claim 35, wherein the dedicated link comprises an Ethernet link.

### Claim 37 (depends on 34)

The method of claim 34, wherein the memory fabric protocol is tunneled across a shared link between the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes.

### Claim 38 (depends on 37)

The method of claim 37, wherein the memory fabric protocol provides a dedicated communication link between the hardware-based processing node and one or more other nodes of the plurality of hardware-based processing nodes and the shared link supports communications other than the memory fabric protocol.

### Claim 39 (depends on 37)

The method of claim 37, wherein the shared link comprises an Internet Protocol (IP) link.

### Claim 40 (depends on 34)

The method of claim 34, wherein two or more nodes of the plurality of hardware-based processing nodes are remote from each other in the hierarchy of the object memory fabric and wherein distributing and tracking the memory objects across the object memory fabric comprises creating neighborhoods of equal-distance nodes in the hierarchy of the object memory fabric.

### Claim 41 (depends on 34)

The method of claim 34, wherein two or more nodes of the plurality of hardware-based processing nodes are each in different physical locations and wherein distributing and tracking the memory objects across the object memory fabric comprises caching and duplicating objects in a plurality of different physical locations.

### Claim 42 (depends on 34)

The method of claim 34, wherein communicating between the hardware-based processing nodes comprises tracking, by the hardware-based processing node, the memory objects and blocks within the memory objects that are present on the hardware-based processing node.

### Claim 43 (depends on 34)

The method of claim 34, wherein communicating between the hardware-based processing nodes distributing the memory objects across the object memory fabric on a per-object basis.

### Claim 44 (depends on 34)

The method of claim 34, wherein communicating between the hardware-based processing nodes comprises propagating changes to the memory objects from the hardware-based processing node to one or more other nodes of the plurality of hardware-based processing nodes.

### Claim 45 (depends on 34)

The method of claim 34, wherein communicating between the hardware-based processing nodes propagating changes to the memory objects from the hardware-based processing node to one or more other nodes of the plurality of hardware-based processing nodes by moving only data within the memory objects that has changed and without replicating or copying the memory object.
