公开(公告)号：US12141512B1

公开(公告)日：2024-11-12

申请号：US17490462

申请日：2021-09-30

Applicant: Cadence Design Systems, Inc.

Inventor： Shadi Saba ,  Roque Alejandro Arcudia Hernandez ,  Uyen Huynh Ha Nguyen ,  Pedro Eugênio Rocha Medeiros ,  Claire Liyan Ying

IPC: G06F30/33 ,  G06F30/333 ,  G06N7/01 ,  G06N20/00

Abstract: An approach is disclosed herein to sequence selection in a UVM environment. Generally, this approach includes a training phase for each machine learning model of a plurality of machine learning models. Each model is trained to achieve a particular target state and is rewarded when a selected action or sequence of actions causes movement that might be beneficial to achieving that target state. Once a respective model is trained, the trained model can then be used to determine which one action or sequence of actions (or ordered multiple thereof) to take to achieve the corresponding target state. Thus, by training and using a plurality of machine learning models to achieve a plurality of target states, and stimulating those machine learning models once trained, one or more actions and/or sequences of actions are generated as the selected sequences to be used to verify functionality or operation of a design under test.

公开(公告)号：US12242784B1

公开(公告)日：2025-03-04

申请号：US17490378

申请日：2021-09-30

Applicant: Cadence Design Systems, Inc.

Inventor： Shadi Saba ,  Roque Alejandro Arcudia Hernandez ,  Uyen Huynh Ha Nguyen ,  Pedro Eugênio Rocha Medeiros ,  Claire Liyan Ying

IPC: G06F30/333 ,  G06N5/022

Abstract: An approach is disclosed herein a sequence generation ecosystem using machine learning. The approach disclosed herein is a new approach to sequence generation in the context of validation that relies on machine learning to explore and identify ways to achieve different states. In particular, the approach divides the valid operations into different respective actions and action sequences. These actions are selected by machine learning models as they are being trained using online inference reinforcement learning. This online inference also is likely to result in the discovery of new states. Each state that has been identified is then used as a target to train a respective machine learning model. As part of this process a representation of all the states and actions or sequences of actions executed to reach those states is created. This representation, the respective machine learning models, or a combination thereof can then be used to generate different test sequences.

公开(公告)号：US12099791B1

公开(公告)日：2024-09-24

申请号：US17490496

申请日：2021-09-30

Applicant: Cadence Design Systems, Inc.

Inventor： Shadi Saba ,  Roque Alejandro Arcudia Hernandez ,  Uyen Huynh Ha Nguyen ,  Pedro Eugênio Rocha Medeiros ,  Claire Liyan Ying ,  Ruozhi Zhang ,  Gustavo Emanuel Faria Araujo

IPC: G06F30/333

CPC classification number: G06F30/333

Abstract: An approach is disclosed herein for test sequence processing that is applicable to machine learning model generated test sequences as disclosed herein. The test sequence processing includes classification, grouping, and filtering. The classification is generated based on the execution of the test sequences. The grouping is performed based on information captured during the classification of the test sequences. The filtering is performed on a group by group basis to remove redundant test sequences.

公开(公告)号：US12038477B1

公开(公告)日：2024-07-16

申请号：US17490426

申请日：2021-09-30

Applicant: Cadence Design Systems, Inc.

Inventor： Shadi Saba ,  Roque Alejandro Arcudia Hernandez ,  Uyen Huynh Ha Nguyen ,  Pedro Eugênio Rocha Medeiros ,  Claire Liyan Ying

IPC: G01R31/317 ,  G06N3/045 ,  G06N3/08

CPC classification number: G01R31/31704 ,  G01R31/31718 ,  G06N3/045 ,  G06N3/08

Abstract: The approach disclosed herein is a new approach to sequence generation in the context of validation that relies on machine learning to explore and identify ways to achieve different states. In particular, the approach uses machine learning models to identify different states and ways to transition from one state to another. Actions are selected by machine learning models as they are being trained using reinforcement learning. This online inference also is likely to result in the discovery of not yet discovered states. Each state that has been identified is then used as a target to train a respective machine learning model. As part of this process a representation of all the states and actions or sequences of actions executed to reach those states is created. This representation, the respective machine learning models, or a combination thereof can then be used to generate different test sequences.

公开(公告)号：US11886372B1

公开(公告)日：2024-01-30

申请号：US17375278

申请日：2021-07-14

Applicant: Cadence Design Systems, Inc.

Inventor： Claire Liyan Ying ,  Uyen Huynh Ha Nguyen ,  Shu Wang

IPC: G06F13/36 ,  G06F13/42 ,  G06F13/38 ,  G06F13/40

CPC classification number: G06F13/4221 ,  G06F13/382 ,  G06F13/4027 ,  G06F13/4068

Abstract: The present disclosure relates to packing transaction layer (TL) packets at a link layer of a protocol stack. In some examples, channel type data identify a type of message channel for a first TL packet can be generated. A set of slot formats for a slot for packing the first TL packet can be identified based on the channel type data and a slot format database. A respective slot format of the set of slot formats can be selected for the slot based on a message type of the first TL packet, and a message type of a second TL packet. The first TL packet and the second TL packet can be packed into the slot having the selected respective slot format during generation of a link layer packet.