IP Library › Granted Patent US 12,743,570
Granted Patent B2
US 12,743,570 · App. 17/826,881 · Granted Sep 22, 2026

Generative self-supervised learning to transform circuit netlists

Inventors: Siddhartha Nath (San Jose, CA); Haoxing Ren (Austin, TX); Geraldo Pradipta (Minneapolis, MN); Corey Hu (San Diego, CA); Tian Yang (Los Altos, CA)
Assignee: NVIDIA Corp.
G06F30/392G06F18/2185G06F30/394G06N20/00
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 12,743,570
App. No.
17/826,881
Granted
Sep 22, 2026
Kind
B2
Abstract

Self-supervised machine learning is applied to combinational gate sizing based on an input circuit netlist. A transformer neural network architecture is disclosed to select gate sizes along paths of the network between primary inputs/outputs and/or sequential logic elements. The gate size selections may be optimized along dimensions such as path delay, path power consumption, and path circuit area.

Claims (41)

1 . A transformer network for setting characteristics of gates in a circuit, the transformer network trained with gate characteristic distributions from a technology library, the transformer network comprising:

an encoder configured to transform a sequence of gate types for a combinatorial circuit path in the circuit into encoder outputs; and

a decoder configured to transform the encoder outputs, an effort level setting, and the sequence of gate types into a sequence of gate sizes for the combinatorial circuit path,

wherein the effort level setting comprises a ratio of a median signal propagation delay and an actual signal propagation delay for the sequence of gate types.

2 . The transformer network of claim 1 , wherein the median delay is a sum of a median fanout-of-four (FO4) delay of each gate type in the the sequence of gate types.

3 . The transformer network of claim 1 , further comprising:

a weighted cross-entropy loss function employing as a weight value a normalized mean square error (MSE) of FO4 delay values of the gates in the sequence of gate types.

4 . The transformer network of claim 1 , the transformer network further configured to:

select sizes of gates in the sequence of gate types to optimize timing, power, area, or combinations thereof for the sequence of gate types.

5 . The transformer network of claim 1 , wherein the transformer network models the propagation of signals through the sequence of gate types.

6 . The transformer network of claim 1 , wherein the encoder and the decoder each comprise exactly two encoding and decoding stages, respectively.

7 . A method for setting gate sizes in a circuit path, the method comprising:

applying, to an encoder of a transformer network, gate types for each gate in the circuit path;

applying, to a decoder of the transformer network, outputs of the encoder, and a token sequence comprising as a starting token an effort level and a first gate type of the gate type sequence, whereafter the token sequence comprises <predicted k th gate size, (k+1) th gate type> pairs and k is a gate position index in the circuit path; and

the transformer network generating a sequence of the gate sizes from the gate types, effort level, and predicted gate sizes.

8 . The method of claim 7 , wherein the circuit path comprises a combinatorial gate sequence between a start point and an endpoint, and wherein the start point comprises one of a primary input and a first synchronous circuit element, and wherein the endpoint comprises one of a primary output and a second synchronous circuit element.

9 . The method of claim 7 , wherein the effort level setting comprises a ratio of a median delay and an actual delay for the circuit path.

10 . The method of claim 9 , wherein the median delay is a sum of a median fanout-of-four (FO4) delay of each gate type in the circuit path.

11 . The method network of claim 7 , further comprising:

utilizing in the transformer network a loss function weighted by a mean square error (MSE) of FO4 delay values for the gates in the circuit path.

12 . The method of claim 7 , further comprising:

setting the gate sizes to optimize timing, power, area, or combinations thereof for the circuit path.

13 . The method of claim 7 , wherein the encoder comprises a plurality of encoding stages and each encoding stage outputs to a corresponding stage of the decoder.

14 . A system comprising:

at least one processor; and

at least one memory implementing logic to:

operate a transformer network encoder to transform a sequence of gate types for a combinatorial circuit path into encoder outputs;

apply the encoder outputs to a decoder of the transformer network;

further apply to the decoder a token sequence comprising an effort level, the sequence of gate types, and predicted sizes for gates of the combinatorial circuit path; and

operate the decoder to generate a sequence of gate sizes for the combinatorial circuit path from the gate types, effort level, encoder outputs, and predicted gate sizes.

15 . The system of claim 14 , wherein the at least one processor comprises a graphics processing unit.

16 . The system of claim 14 , wherein the combinatorial circuit path comprises a start point and an endpoint, and wherein the start point comprises one of a primary input and a first synchronous circuit element, and wherein the endpoint comprises one of a primary output and a second synchronous circuit element.

17 . The system of claim 14 , wherein the effort level setting comprises a ratio of a median delay and an actual delay for the circuit path.

18 . The system of claim 17 , wherein the median delay is a sum of a median fanout-of-four (FO4) delay of each gate type in the circuit path.

19 . The system of claim 14 , the memory further implementing logic to:

implement a loss function weighted by a mean square error (MSE) of FO4 delay values for the gates of the combinatorial circuit path.

20 . A process comprising:

operating a transformer network encoder to transform a sequence of gate types for a combinatorial circuit path into encoder outputs;

applying the encoder outputs to a decoder of the transformer network;

further applying to the decoder a token sequence comprising an effort level, the sequence of gate types, and predicted sizes for gates of the combinatorial circuit path; and

operating the decoder to generate a sequence of gate sizes for the combinatorial circuit path from the gate types, effort level, encoder outputs, and predicted gate sizes.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 28, 2022
From: NATH, SIDDHARTHA; REN, HAOXING; PRADIPTA, GERALDO; HU, COREY; YANG, TIAN
To: NVIDIA CORP.
Reel/Frame 060336/0065 →
Continuity (2)
Provisional Application 63331566 · Apr 15, 2022
Related Publication 20230334215A1 · Oct 19, 2023
References Cited (18)
US 10867091B1 · Oh · 2020 [cited by examiner]
US 10970441B1 · Zhang · 2021 [cited by examiner]
US 11556690B2 · Goldie · 2023 [cited by examiner]
US 20190228126A1 · Oh · 2019 [cited by examiner]
US 20190354796A1 · Meshi · 2019 [cited by examiner]
US 20190385047A1 · Lei · 2019 [cited by examiner]
US 20200274554A1 · Aspuru-Guzik · 2020 [cited by examiner]
US 20210117603A1 · Jiang · 2021 [cited by examiner]
US 20220318684A1 · Allahdadian · 2022 [cited by examiner]
“Pre-Routing Path Delay Estimation Based on Transformer and Residual Framework”, Tai Yang, Guoqing He, Peng Cao, Feb. 21, 2022, IEEE. [cited by examiner]
“Attention is All You Need”, 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA. [cited by examiner]
A. B. Kahng, S. Kang et al., “Learning-based approximation of interconnect delay and slew in signoff timing tools,” in 2013 ACM/IEEE International Workshop on System Level Interconnect Prediction (SLIP). IEEE, 2013, pp.… [cited by applicant]
A. Sharma, D. Chinnery et al., “Fast lagrangian relaxation-based multithreaded gate sizing using simple timing calibrations,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 39, No. 7… [cited by applicant]
A. Vaswani, N. Shazeer et al., “Attention is all you need,” in Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg et al., Eds., vol. 30. Curran Associates, Inc., 2017. [cited by applicant]
C.-P. Chen, C. Chu, and D. Wong, “Fast and exact simultaneous gate and wire sizing by lagrangian relaxation,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 18, No. 7, pp. 1014-1025,… [cited by applicant]
H. Wang, K. Wang et al., “Gcn-rl circuit designer: Transferable transistor sizing with graph neural networks and reinforcement learning,” in 2020 57th ACM/IEEE Design Automation Conference (DAC). IEEE, 2020, pp. 1-6. [cited by applicant]
S. Roy, D. Liu et al., “OSFA: A new paradigm of gate-sizing for power/performance optimizations under multiple operating conditions,” in 2015 52nd ACM/EDAC/IEEEDesign Automation Conference (DAC), 2015, pp. 1-6. [cited by applicant]
Y.-C. Lu, S. Nath et al., “RI-sizer: Vlsi gate sizing for timing optimization using deep reinforcement learning,” in 2021 58th ACM/IEEE Design Automation Conference (DAC). IEEE, 2021, pp. 733-738. [cited by applicant]