IP Library › Granted Patent US 12,724,612
Granted Patent B2
US 12,724,612 · App. 18/506,993 · Granted Sep 1, 2026

Systems and methods for parallel data processing

Inventors: Mohammadreza Soltaniyeh (Sunnyvale, CA); Xuebin Yao (Mountain View, CA); Ramdas Kachare (Pleasanton, CA)
Assignee: Samsung Electronics Co., Ltd.
G06F9/3842G06F9/30043G06F13/4247
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 12,724,612
App. No.
18/506,993
Filed
Nov 10, 2023
Granted
Sep 1, 2026
Kind
B2
Examiner
SUN, SCOTT C
Art Unit
2181
USPC
712/225
Abstract

Systems and methods for parallel data processing. In some embodiments, the system includes: a first processing chain; and a second processing chain, the first processing chain including: a first core; a second core; and a first inter-core bus connecting the second core of the first processing chain to the first core of the first processing chain the system being configured to forward an output of a calculation of the first processing chain to the second processing chain.

Claims (32)

1 . A system, comprising:

a first processing chain; and

a second processing chain,

the first processing chain comprising:

a first core;

a second core; and

a first inter-core bus connecting the second core of the first processing chain to the first core of the first processing chain; and

the system being configured to forward an output of a calculation of the first processing chain to the second processing chain, wherein the first core verifies a speculative operation done by the second core.

2 . The system of claim 1 , wherein the first core of the first processing chain comprises:

a memory; and

a packet processing circuit,

the packet processing circuit being configured:

to receive a packet comprising instructions; and

to store the instructions in the memory.

3 . The system of claim 1 , wherein the first processing chain is configured:

to perform, in the first core of the first processing chain, a first calculation based on a first speculative value;

to perform, in the second core of the first processing chain, a second calculation based on a second speculative value; and

to validate the first speculative value,

wherein the forwarding of the output of the first calculation to the second processing chain is based on the validating.

4 . The system of claim 1 , wherein the system is configured to perform a number of speculative operations using a number of cores based on the number of speculative operations.

5 . The system of claim 1 , further comprising a first inter-chain bus,

wherein an initial core of the first processing chain is connected, through the first inter-chain bus, to an initial core of the second processing chain.

6 . The system of claim 5 , further comprising:

a third processing chain; and

a second inter-chain bus,

wherein an initial core of the first processing chain is connected, through the second inter-chain bus, to an initial core of the third processing chain.

7 . The system of claim 1 , further comprising a packet scheduler connected to the first processing chain and to the second processing chain, the packet scheduler being configured to send, to each of the first processing chain and the second processing chain, packets comprising instructions, parameters, and input data.

8 . The system of claim 1 , further comprising a packet scheduler connected to the first processing chain, the packet scheduler being configured:

to send a first sequence of symbols to the first core of the first processing chain, for testing for a second sequence of symbols; and

to send a third sequence of symbols to a first core of the second processing chain, for testing for the second sequence of symbols,

wherein the first sequence of symbols overlaps with the third sequence of symbols.

9 . The system of claim 8 , wherein the first sequence of symbols overlaps with the third sequence of symbols in an overlapped area having a size greater than the second sequence of symbols.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 19, 2026
From: SOLTANIYEH, MOHAMMADREZA; YAO, XUEBIN; KACHARE, RAMDAS
To: SAMSUNG ELECTRONICS CO., LTD.
Reel/Frame 075710/0819 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 5, 2024
From: SOLTANIYEH, MOHAMMADREZA; YAO, XUEBIN; KACHARE, RAMDAS
To: SAMSUNG ELECTRONICS CO., LTD.
Reel/Frame 066032/0659 →
Continuity (2)
Provisional Application 63521251 · Jun 15, 2023
Related Publication 20240419450A1 · Dec 19, 2024
References Cited (20)
US 8516222B1 · Agarwal et al. · 2013 [cited by applicant]
US 8726251B2 · Kalogeropulos et al. · 2014 [cited by applicant]
US 9092346B2 · McCormick, Jr. · 2015 [cited by applicant]
US 9268596B2 · Rajwar et al. · 2016 [cited by applicant]
US 9940136B2 · Burger et al. · 2018 [cited by applicant]
US 10031756B2 · Burger et al. · 2018 [cited by applicant]
US 10061583B2 · Ould-Ahmed-Vall et al. · 2018 [cited by applicant]
US 10324768B2 · Wang et al. · 2019 [cited by applicant]
US 11531552B2 · Gupta et al. · 2022 [cited by applicant]
US 20080235490A1 · Jones et al. · 2008 [cited by applicant]
US 20090113169A1 · Yang · 2009 [cited by examiner]
US 20120079245A1 · Wang et al. · 2012 [cited by applicant]
US 20160259826A1 · Acar · 2016 [cited by examiner]
US 20160378488A1 · Burger et al. · 2016 [cited by applicant]
US 20210048991A1 · Tanner · 2021 [cited by applicant]
US 20220214885A1 · Foley · 2022 [cited by applicant]
US 20220342673A1 · Wang et al. · 2022 [cited by applicant]
WO WO2015057539A1 · 2015 [cited by applicant]
Mytkowicz, T., et al., “Data-Parallel Finite-State Machines”, ASPLOS '14, Mar. 1-5, 2014, Salt Lake City, Utah, USA, 2014, 13 pages, ACM. [cited by applicant]
U.S. Appl. No. 17/960,033, filed Oct. 4, 2022. [cited by applicant]