IP Library Granted Patent US 11,196,713
Granted Patent B2
US 11,196,713 · App. 16/162,632 · Granted Dec 7, 2021

Classical implementation of quantum entanglement in datacenter network design

Inventor: Paul L. Borrill (Palo Alto, CA)
Assignee: Eric Litak
H04L63/0414H04L9/0852H04L63/0428
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,196,713
App. No.
16/162,632
Granted
Dec 7, 2021
Kind
B2
Abstract

Quantum mechanics provides several features useful for datacenter networking. The no cloning theorem, which states that it is impossible to mate a duplicate of an arbitrary, unknown quantum state, can be used to detect eavesdroppers. Entanglement allows two parties to have common knowledge of a shared state. These properties are being used today for quantum key exchange and quantum computing, but they are currently too expensive for general use. Fortunately, we can use classical mechanisms to get a close enough approximation of these quantum properties to solve some important problems in distributed computing. Nothing we describe here is quantum mechanical. Rather, we show that it is possible to use classical mechanisms to emulate some properties of quantum mechanics, which enable us to address interesting problems in distributed computing. The engineering insight, is that we can get closer to achieving these properties than might be expected through conventional thinking. The key to obtaining the properties we desire is to make the inherently asynchronous system temporarily locally synchronous for the operations we need. In this patent, we describe how to classically emulate the parts of the no cloning theorem and entanglement that we need for datacenter networking. We then demonstrate how those approximations to quantum behavior can be used to solve important problems in distributed computing, such as ‘exactly-once’ semantics in an environment where failures occur and can be healed without applications needing to know.

Claims (5)

1. A method of a mechanism on a dedicated link between two servers, comprising:

taking an arrival of a packet of information containing an Element of Shared Information (ESI), wherein ESI has two complementary halves distributed across two or more components of a distributed system, such that one complementary half of ESI is on one side of the dedicated link and the other complementary half of the ESI is on other side of the dedicated link;

establishing liveness through a perpetual exchange of ESI in the dedicated link;

combining and swapping the packet of information, wherein the two complementary halves of the ESI are combined such that complementary halves are merged and atomically swapped with the other using a swap instruction in a processor or other logic on each side; and

sending the swapped information back down the link, such that if both sides of the dedicated link follow the mechanism a symmetric time link is formed that guarantees an observer can only see a complementary state on the two sides.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 3, 2021
From: BORRILL, PAUL LINDSEY
To: LITAK, ERIC
Reel/Frame 055482/0641 →
Continuity (2)
Provisional Application 62573196 · Oct 17, 2017
Related Publication 20190141016A1 · May 9, 2019
Cited By (1)
US 12,639,288