IP Library › Granted Patent US 12,418,297
Granted Patent B2
US 12,418,297 · App. 18/208,878 · Granted Sep 16, 2025

Capacitor weighted segmentation buffer

Inventor: Sung-En Hsieh (Hsinchu, TW)
Assignee: MEDIATEK INC.
H03M1/002
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 12,418,297
App. No.
18/208,878
Granted
Sep 16, 2025
Kind
B2
Abstract

A capacitor weighted segmentation buffer includes a push-pull buffer circuit and a plurality of capacitors. The capacitors include a first capacitor having a first terminal coupled to a control terminal of the first transistor and a second terminal arranged to receive a first input signal; a second capacitor having a first terminal coupled to a control terminal of the second transistor and a second terminal arranged to receive the first input signal; a third capacitor having a first terminal coupled to the control terminal of the first transistor and a second terminal arranged to receive a second input signal; and a fourth capacitor having a first terminal coupled to the control terminal of the second transistor and a second terminal arranged to receive the second input signal.

Claims (42)

1. A capacitor weighted segmentation buffer comprising:

a push-pull buffer circuit, comprising:

a first transistor, having a control terminal, a first connection terminal, and a second connection terminal; and

a second transistor, having a control terminal, a first connection terminal, and a second connection terminal, wherein the second connection terminal of the first transistor and the second connection terminal of the second transistor are source terminals coupled to an output node of the capacitor weighted segmentation buffer; and

a plurality of capacitors, comprising:

a first capacitor, having a first terminal coupled to the control terminal of the first transistor, and a second terminal arranged to receive a first input signal of the capacitor weighted segmentation buffer;

a second capacitor, having a first terminal coupled to the control terminal of the second transistor, and a second terminal arranged to receive the first input signal of the capacitor weighted segmentation buffer;

a third capacitor, having a first terminal coupled to the control terminal of the first transistor, and a second terminal arranged to receive a second input signal of the capacitor weighted segmentation buffer; and

a fourth capacitor, having a first terminal coupled to the control terminal of the second transistor, and a second terminal arranged to receive the second input signal of the capacitor weighted segmentation buffer;

wherein each of the first capacitor and the second capacitor has a first capacitance value, and each of the third capacitor and the fourth capacitor has a second capacitance value different from the first capacitance value.

2. The capacitor weighted segmentation buffer of claim 1 , wherein the plurality of capacitors further comprise:

a fifth capacitor, having a first terminal coupled to the control terminal of the first transistor, and a second terminal arranged to receive a third input signal of the capacitor weighted segmentation buffer; and

a sixth capacitor, having a first terminal coupled to the control terminal of the second transistor, and a second terminal arranged to receive the third input signal of the capacitor weighted segmentation buffer;

wherein each of the fifth capacitor and the sixth capacitor has a third capacitance value different from any of the first capacitance value and the second capacitance value.

3. The capacitor weighted segmentation buffer of claim 1 , further comprising:

a switch circuit, arranged to support a first configuration and a second configuration, wherein the push-pull buffer circuit operates in a reset mode when the switch circuit has the first configuration, and operates in a buffer mode when the switch circuit has the second configuration.

4. The capacitor weighted segmentation buffer of claim 3 , further comprising:

a replica bias circuit, arranged to generate and output a first bias voltage to the control terminal of the first transistor and generate and output a second bias voltage to the control terminal of the second transistor when the push-pull buffer circuit operates in the reset mode.

5. The capacitor weighted segmentation buffer of claim 4 , wherein the replica bias circuit is disconnected from the push-pull buffer circuit when the push-pull buffer circuit operates in the buffer mode.

6. The capacitor weighted segmentation buffer of claim 3 , wherein the first input signal is delivered to the second terminal of the first capacitor and the second terminal of the second capacitor when the push-pull buffer circuit operates in the buffer mode; and the second input signal is delivered to the second terminal of the third capacitor and the second terminal of the fourth capacitor when the push-pull buffer circuit operates in the buffer mode.

7. The capacitor weighted segmentation buffer of claim 6 , wherein the first input signal is disconnected from the first capacitor and the second capacitor and the second input signal is disconnected from the third capacitor and the fourth capacitor when the push-pull buffer circuit operates in the reset mode.

8. The capacitor weighted segmentation buffer of claim 3 , wherein a common-mode voltage is delivered to the second terminal of the first capacitor, the second terminal of the second capacitor, the second terminal of the third capacitor and the second terminal of the fourth capacitor when the push-pull buffer circuit operates in the reset mode.

9. The capacitor weighted segmentation buffer of claim 1 , wherein the capacitor weighted segmentation buffer is integrated with a digital-to-analog converter (DAC).

10. The capacitor weighted segmentation buffer of claim 9 , wherein the DAC comprises:

a resistor digital-to-analog converter (RDAC), arranged to provide a plurality of reference voltage levels; and

a capacitor digital-to-analog converter (CDAC), wherein the plurality of capacitors are used by the CDAC, and the plurality of reference voltage levels are provided to the CDAC.

11. The capacitor weighted segmentation buffer of claim 10 , wherein the CDAC comprises:

the first capacitor;

the third capacitor;

the second capacitor;

the fourth capacitor;

a first decoder, arranged to select and output one of the plurality of reference voltage levels as the first input signal according to a first segment of a digital code of the DAC; and

a second decoder, arranged to select and output one of the plurality of reference voltage levels as the second input signal according to a second segment of the digital code of the DAC.

12. The capacitor weighted segmentation buffer of claim 11 , wherein the digital code is one input data of a neural network.

13. The capacitor weighted segmentation buffer of claim 9 , wherein the output node of the capacitor weighted segmentation buffer is coupled to an analog compute-in-memory (ACIM) circuit.

14. The capacitor weighted segmentation buffer of claim 1 , wherein the capacitor weighted segmentation buffer is an analog compute-in-memory (ACIM) buffer.

15. The capacitor weighted segmentation buffer of claim 14 , wherein each of the first input signal and the second input signal is generated from an ACIM circuit, and the ACIM circuit comprises:

a plurality of processing circuits, comprising:

a first processing circuit, arranged to generate and output the first input signal according to a plurality of analog inputs and first segments of a plurality of stored data; and

a second processing circuit, arranged to generate and output the second input signal according to the plurality of analog inputs and second segments of the plurality of stored data.

16. The capacitor weighted segmentation buffer of claim 15 , wherein each of the plurality of processing circuits is a multiply-accumulate (MAC) circuit.

17. The capacitor weighted segmentation buffer of claim 15 , wherein each of the analog inputs corresponds to one input data of a neural network.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 13, 2023
From: HSIEH, SUNG-EN
To: MEDIATEK INC.
Reel/Frame 063989/0878 →
Continuity (4)
Provisional Application 63376125 · Sep 19, 2022
Provisional Application 63369673 · Jul 28, 2022
Provisional Application 63369674 · Jul 28, 2022
Related Publication 20240039546A1 · Feb 1, 2024
References Cited (31)
US 4644291A · Masuda · 1987 [cited by examiner]
US 6144331A · Jiang · 2000 [cited by examiner]
US 6778009B1 · Lee · 2004 [cited by examiner]
US 7916198B2 · Yeom · 2011 [cited by examiner]
US 8836420B2 · Kimura · 2014 [cited by examiner]
US 9154089B2 · Lee · 2015 [cited by examiner]
US 9455731B1 · Gutta · 2016 [cited by examiner]
US 10833685B1 · Chakraborty · 2020 [cited by examiner]
US 11038512B2 · Yang · 2021 [cited by examiner]
US 11043948B1 · Lekkala · 2021 [cited by examiner]
US 20070054629A1 · Maligeorgos · 2007 [cited by examiner]
US 20090185406A1 · Uno · 2009 [cited by examiner]
US 20120026027A1 · Steensgaard-Madsen · 2012 [cited by examiner]
US 20210295905A1 · Lee · 2021 [cited by applicant]
US 20220012016A1 · Wang · 2022 [cited by applicant]
US 20220013155A1 · Kumar · 2022 [cited by applicant]
US 20220309328A1 · Saxena · 2022 [cited by examiner]
TW 202143067A · 2021 [cited by applicant]
WO 2021158861A1 · 2021 [cited by applicant]
Xie et al., eDRAM-CIM: Compute-In-Memory Design with Reconfigurable Embedded-Dynamic-Memory Array Realizing Adaptive Data Converters and Charge-Domain Computing, ISSCC 2021 / Session 16 / Computation in Memory / 16.2, p… [cited by applicant]
Hongyang Jia et al., Scalable and Programmable Neural Network Inference Accelerator Based on In-Memory Computing, IEEE Journal of Solid-State Circuits, Jan. 2022, pp. 198-211, vol. 57, No. 1, IEEE, XP093051677, Jan. 202… [cited by applicant]
Sung-En Hsieh et al., 7.6 A 70.85-86.27TOPS/W PVT-Insensitive 8b Word-Wise ACIM with Post-Processing Relaxation, ISSCC 2023 / Session 7 / SRAM Compute-In-Memory / 7.6, 2023 IEEE International Solid-State Circuits Confer… [cited by applicant]
Hsieh, the specification, including the claims, and drawings in the U.S. Appl. No. 18/215,175, filed Jun. 28, 2023. [cited by applicant]
Dong et al., A 351TOPS/W and 372.4GOPS Compute-in-Memory SRAM Macro in 7nm FinFET CMOS for Machine-Learning Applications, ISSCC 2020 / Session 15 / SRAM & Compute-In-Memory / 15.3, pp. 242-243 and a page including 15.3.… [cited by applicant]
Wu et al., A 28nm 1Mb Time-Domain Computing-in-Memory 6T-SRAM Macro with a 6.6ns Latency, 1241GOPS and 37.01Tops/W for 8b-MAC Operations for Edge-AI Devices, ISSCC 2022 / Session 11 / Compute-In-Memory and SRAM / 11.8, … [cited by applicant]
Jia et al., A Programmable Neural-Network Inference Accelerator Based on Scalable In-Memory Computing, ISSCC 2021 / Session 15 / Compute-In-Memory Processors for Deep Neural Networks / 15.1, pp. 236-237 and a page inclu… [cited by applicant]
Khwa et al., A 40-nm, 2M-Cell, 8b-Precision, Hybrid SLC-MLC PCM Computing-in-Memory Macro with 20.5-65.0Tops/W for Tiny-AI Edge Devices, ISSCC 2022 / Session 11 / Compute-In-Memory and SRAM / 11.3, pp. 180-181 and a pag… [cited by applicant]
Yan et al., A 1.041-Mb/mm2 27.38-Tops/W Signed-INT8 Dynamic-Logic-Based ADC-less SRAM Compute-In-Memory Macro in 28nm with Reconfigurable Bitwise Operation for AI and Embedded Applications, ISSCC 2022 / Session 11 / Com… [cited by applicant]
Chih et al., An 89Tops/W and 16.3TOPS/mm2 All-Digital SRAM-Based Full-Precision Compute-In Memory Macro in 22nm for Machine-Learning Edge Applications, ISSCC 2021 / Session 16 / Computation in Memory / 16.4, pp. 252-253… [cited by applicant]
Chenyaofo, pytorch-cifar-models. [Online]. Available : https://github.com/chenyaofo/pytorch-cifar-models, 2021. [cited by applicant]
Hershberg et al., A 3.2GS/s 10 ENOB 61mW Ringamp ADC in 16nm with Background Monitoring of Distortion, ISSCC 2019 / Sessuib 3 / Nyquist Rate ADCs / 3.1, pp. 58-59 and a page including Figure 3.1.7, 2019. [cited by applicant]