Hechen Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Hechen Wang has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
Fa Foster Dai
8 shared publications- Fa Foster Dai
Department of Electrical and Computer Engineering, Auburn University, Auburn, AL, USA
3 shared publications - Brent R. Carlton
Intel Labs, Intel Corporation, Hillsboro, OR, USA
2 shared publications - Deepak Dasalukunte
Intel Labs, Intel Corporation, Hillsboro, OR, USA
2 shared publications Haoyi Zhao
2 shared publicationsHua Wang
School of Electrical and Computer Engineering, Georgia Tech, Atlanta, GA 30332 USA
2 shared publications
Latest Publications
- 14 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computational Intelligence Magazine
- Vol. 21 (1) , 11-12
Sustaining the AI Revolution With Analog Compute-in-Memory [Industrial and Governmental Activities]
Artificial intelligence (AI), once a mere figment of science fiction, has now entrenched itself deeply into our lives, reshaping everything from adjusting the tone of your email to assisting scientists analyzing deep space images captured by the James Webb space telescope. However, beneath the glorious appearance of the rapid development of AI technology, increasingly serious environmental problems are gradually emerging. To train and operate AI systems, power demand from data centers has skyrocketed, having tripled in just five years and being expected to triple again by 2030 [1]. This staggering increase starkly contrasts with less than 3% of annual global electricity production growth witnessed over the past 40 years, far outpaced by AI's ballooning energy needs [2], as shown in Figure 1 left. If we continue down this path relying on traditional processors, the growth of large language models (LLMs) may soon reach an unsustainable ceiling. This urgency is amplified by the reality that early efficiency gains in AI hardware are plateauing. Data centers nowadays principally utilize GPUs for both training and inferences. While GPU manufacturers often highlight improvements in efficiency—claiming a 40,000x improvement over the past decade—these numbers obscure several underlying concerns [3]. Upon scrutinizing the sources of the improvement, it becomes evident that sustaining such a pace of progress will be fraught with challenges. The main drivers of efficiency enhancement stem from circuit/architecture innovations, semiconductor process advancements, and data format optimizations.
- 14 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computational Intelligence Magazine
- Vol. 21 (1) , 11-12
Sustaining the AI Revolution With Analog Compute-in-Memory [Industrial and Governmental Activities]
Artificial intelligence (AI), once a mere figment of science fiction, has now entrenched itself deeply into our lives, reshaping everything from adjusting the tone of your email to assisting scientists analyzing deep space images captured by the James Webb space telescope. However, beneath the glorious appearance of the rapid development of AI technology, increasingly serious environmental problems are gradually emerging. To train and operate AI systems, power demand from data centers has skyrocketed, having tripled in just five years and being expected to triple again by 2030 [1]. This staggering increase starkly contrasts with less than 3% of annual global electricity production growth witnessed over the past 40 years, far outpaced by AI's ballooning energy needs [2], as shown in Figure 1 left. If we continue down this path relying on traditional processors, the growth of large language models (LLMs) may soon reach an unsustainable ceiling. This urgency is amplified by the reality that early efficiency gains in AI hardware are plateauing. Data centers nowadays principally utilize GPUs for both training and inferences. While GPU manufacturers often highlight improvements in efficiency—claiming a 40,000x improvement over the past decade—these numbers obscure several underlying concerns [3]. Upon scrutinizing the sources of the improvement, it becomes evident that sustaining such a pace of progress will be fraught with challenges. The main drivers of efficiency enhancement stem from circuit/architecture innovations, semiconductor process advancements, and data format optimizations.
- 4 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Solid-State Circuits Letters
- Vol. 8, 9-12
Enhancing AI Acceleration: A Calibration-Free, PVT-Robust Analog Compute-in-Memory Macro With Activation Functions
Most Analog Compute-in-Memory (ACiM) works only focus on the multiple-accumulate (MAC) operation while neglecting the activation function (AF) in the digital domain. The frequent data conversion greatly reduces the benefits obtained by analog computing. This paper proposes an efficient 8-bit inmemory MAC with hybrid capacitor ladders. Then a sparsityaware R-2R DAC and an embedded SAR-ADC that reuses the capacitor ladders in the MAC are introduced to reduce the conversion overhead. Two on-chip AF schemes are included to further improve efficiency. Finally, differential signal path offers 1st order PVT cancellation that improves computing accuracy and reduces the need for calibration.
- 4 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Solid-State Circuits Letters
- Vol. 8, 9-12
Enhancing AI Acceleration: A Calibration-Free, PVT-Robust Analog Compute-in-Memory Macro With Activation Functions
Most Analog Compute-in-Memory (ACiM) works only focus on the multiple-accumulate (MAC) operation while neglecting the activation function (AF) in the digital domain. The frequent data conversion greatly reduces the benefits obtained by analog computing. This paper proposes an efficient 8-bit inmemory MAC with hybrid capacitor ladders. Then a sparsityaware R-2R DAC and an embedded SAR-ADC that reuses the capacitor ladders in the MAC are introduced to reduce the conversion overhead. Two on-chip AF schemes are included to further improve efficiency. Finally, differential signal path offers 1st order PVT cancellation that improves computing accuracy and reduces the need for calibration.
- 23 August 2023
- Published by Springer Nature in Nature
- Vol. 620 (7975) , 731-732
Analog chip paves the way for sustainable AI
- 23 August 2023
- Published by Springer Nature in Nature
- Vol. 620 (7975) , 731-732
Analog chip paves the way for sustainable AI
- Top Cited Papers
- 6 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 58 (4) , 1037-1050
A Charge Domain SRAM Compute-in-Memory Macro With C-2C Ladder-Based 8-Bit MAC Unit in 22-nm FinFET Process for Edge Inference
Compute-in-memory (CiM) is one promising solution to address the memory bottleneck existing in traditional computing architectures. However, the tradeoff between energy efficiency and computing precision plagues most CiM implementations, and the low precision imposes a major limitation on CiM’s ability to support practical computational workloads. In this article, a static random access memory (SRAM)-based analog CiM macro is presented with the Intel 22FFL process. By introducing a 1-to-2 ratioed capacitor ladder (C-2C)-based charge domain computing scheme, the proposed CiM prototype chip demonstrates a maximum of 2k multiply-accumulate (MAC) operations in one clock cycle and achieves 32.2-TOPS/W peak power efficiency with 8-bit precision in both input activation and weight while ensuring accurate on-chip matrix–vector multiplications (MVMs) with a computation error less than 0.5%. A 4.0-TOPS/mm $^{2}$ peak area efficiency is attained by adopting a local weight multiplexing scheme with a 9T SRAM cell, which improves the memory density and reduces the need to refresh the weight stored in the SRAM array. A variety of analog impairment factors, including parasitics, mismatch, and noise, were analyzed to guarantee a sufficiently high multibit linearity. The proposed passive analog computing mechanism ensures the computation accuracy over process–voltage–temperature (PVT), with the measured MVM error deviation of less than 1% over PVT variations.
- 6 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 58 (4) , 1037-1050
Top Cited PapersA Charge Domain SRAM Compute-in-Memory Macro With C-2C Ladder-Based 8-Bit MAC Unit in 22-nm FinFET Process for Edge Inference
Compute-in-memory (CiM) is one promising solution to address the memory bottleneck existing in traditional computing architectures. However, the tradeoff between energy efficiency and computing precision plagues most CiM implementations, and the low precision imposes a major limitation on CiM’s ability to support practical computational workloads. In this article, a static random access memory (SRAM)-based analog CiM macro is presented with the Intel 22FFL process. By introducing a 1-to-2 ratioed capacitor ladder (C-2C)-based charge domain computing scheme, the proposed CiM prototype chip demonstrates a maximum of 2k multiply-accumulate (MAC) operations in one clock cycle and achieves 32.2-TOPS/W peak power efficiency with 8-bit precision in both input activation and weight while ensuring accurate on-chip matrix–vector multiplications (MVMs) with a computation error less than 0.5%. A 4.0-TOPS/mm $^{2}$ peak area efficiency is attained by adopting a local weight multiplexing scheme with a 9T SRAM cell, which improves the memory density and reduces the need to refresh the weight stored in the SRAM array. A variety of analog impairment factors, including parasitics, mismatch, and noise, were analyzed to guarantee a sufficiently high multibit linearity. The proposed passive analog computing mechanism ensures the computation accuracy over process–voltage–temperature (PVT), with the measured MVM error deviation of less than 1% over PVT variations.
- Open Access
- 1 January 2021
- Published by INSTICC
- p. 208-213
Risk of CAPM Model Apply in Chinese Concept Stocks based on Python
- 1 January 2021
- Published by INSTICC
- p. 208-213
Open AccessRisk of CAPM Model Apply in Chinese Concept Stocks based on Python
- 1 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 55 (4) , 1064-1076
Sub-Sampling Direct RF-to-Digital Converter With 1024-APSK Modulation for High Throughput Polar Receiver
- 1 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 55 (4) , 1064-1076
Sub-Sampling Direct RF-to-Digital Converter With 1024-APSK Modulation for High Throughput Polar Receiver
- 1 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21581525,p. 1-4
An 8-bit 80-MS/s Fully Self-Timed SAR ADC with 3/2 Interleaved Comparators and High-Order PVT Stabilized HBT Bandgap Reference
This paper presents the design of a fully self-timed 8-bit 80-Ms/s single-core SAR ADC with interleaved comparators and a high order compensated opamp-less bandgap reference. A 3/2 interleaving algorithm was designed for better SFDR performance, where two of the three comparators are orderly chosen for interleaving in each conversion while offset calibration is applied to the idle comparator. Asynchronized SAR logic with a DAC settling timer is designed for fully self-timing of the ADC. The ADC was designed with a PVT stabilized on-chip reference source which promises a stable reference for the ADC at extreme temperature environments such as aerospace exploration or quantum computing. Technique for compensating the temperature coefficient (TC) of a bandgap reference (BGR) using temperature characteristics of transistor's current gain β is proposed. Measured results show 42.8dB SNDR, 56.8 dB SFDR and -53.3dBc THD for the proposed SAR ADC, drawing 1.07mW from a 1.1v supply. Measured average TC of the HBT proposed BGR is 23ppm/°C and 39 ppm/°C over the commercial (0~70°C) and space (-260~125°C) temperature ranges, respectively. The BGR reaches PSRR of -50dB at 1MHz, and -38dB at 1GHz. The entire chip was implemented on 0.13um 8HP SiGe process with an active area of 0.2952 mm 2 .
- 1 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21581525,p. 1-4
An 8-bit 80-MS/s Fully Self-Timed SAR ADC with 3/2 Interleaved Comparators and High-Order PVT Stabilized HBT Bandgap Reference
This paper presents the design of a fully self-timed 8-bit 80-Ms/s single-core SAR ADC with interleaved comparators and a high order compensated opamp-less bandgap reference. A 3/2 interleaving algorithm was designed for better SFDR performance, where two of the three comparators are orderly chosen for interleaving in each conversion while offset calibration is applied to the idle comparator. Asynchronized SAR logic with a DAC settling timer is designed for fully self-timing of the ADC. The ADC was designed with a PVT stabilized on-chip reference source which promises a stable reference for the ADC at extreme temperature environments such as aerospace exploration or quantum computing. Technique for compensating the temperature coefficient (TC) of a bandgap reference (BGR) using temperature characteristics of transistor's current gain β is proposed. Measured results show 42.8dB SNDR, 56.8 dB SFDR and -53.3dBc THD for the proposed SAR ADC, drawing 1.07mW from a 1.1v supply. Measured average TC of the HBT proposed BGR is 23ppm/°C and 39 ppm/°C over the commercial (0~70°C) and space (-260~125°C) temperature ranges, respectively. The BGR reaches PSRR of -50dB at 1MHz, and -38dB at 1GHz. The entire chip was implemented on 0.13um 8HP SiGe process with an active area of 0.2952 mm 2 .
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
A bidirectional lens-free digital-bits-in/-out 0.57mm2 terahertz nano-radio in CMOS with 49.3mW Peak power consumption supporting 50cm Internet-of-Things communication
The following topics are dealt with: CMOS integrated circuits; low-power electronics; analogue-digital conversion; calibration; voltage-controlled oscillators; integrated circuit design; delta-sigma modulation; phase noise; oscillators; radio transceivers.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
A bidirectional lens-free digital-bits-in/-out 0.57mm2 terahertz nano-radio in CMOS with 49.3mW Peak power consumption supporting 50cm Internet-of-Things communication
The following topics are dealt with: CMOS integrated circuits; low-power electronics; analogue-digital conversion; calibration; voltage-controlled oscillators; integrated circuit design; delta-sigma modulation; phase noise; oscillators; radio transceivers.
- 18 January 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 53 (3) , 738-749
A Reconfigurable Vernier Time-to-Digital Converter With 2-D Spiral Comparator Array and Second-Order $\Delta \Sigma$ LinearizationThis paper presents an 8-bit 1.25-ps resolution reconfigurable Vernier time-to-digital converter (TDC) with a 2-D spiral comparator array and ΔΣ modulators for linearization. The proposed spiral 2-D comparator array improves both linearity and detection range of the TDC. The quantization errors introduced by digitally tuning delay cells are minimized by using a 2nd-order ΔΣ modulator. The folding point errors commonly seen in 2-D comparator arrays are randomized by using a reconfigurable comparator array controlled by the output of a 2nd-orderΔΣ modulator. The prototype TDC fabricated in a 45-nm silicon on insulator technology consumes 70- to 690-μW power under a 1-V supply at 80-MHz conversion rate. The measured maximum differential nonlinearity/integral nonlinearity across its detectable range are 1.35/1.03 ps without the linearization techniques and 0.31/0.4 ps with the proposed linearization techniques, respectively.
- 18 January 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 53 (3) , 738-749
A Reconfigurable Vernier Time-to-Digital Converter With 2-D Spiral Comparator Array and Second-Order $\Delta \Sigma$ LinearizationThis paper presents an 8-bit 1.25-ps resolution reconfigurable Vernier time-to-digital converter (TDC) with a 2-D spiral comparator array and ΔΣ modulators for linearization. The proposed spiral 2-D comparator array improves both linearity and detection range of the TDC. The quantization errors introduced by digitally tuning delay cells are minimized by using a 2nd-order ΔΣ modulator. The folding point errors commonly seen in 2-D comparator arrays are randomized by using a reconfigurable comparator array controlled by the output of a 2nd-orderΔΣ modulator. The prototype TDC fabricated in a 45-nm silicon on insulator technology consumes 70- to 690-μW power under a 1-V supply at 80-MHz conversion rate. The measured maximum differential nonlinearity/integral nonlinearity across its detectable range are 1.35/1.03 ps without the linearization techniques and 0.31/0.4 ps with the proposed linearization techniques, respectively.