Guanghua Shu
Guanghua Shu has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Pavan Kumar Hanumolu
Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL 61801 USA
3 shared publications- Da Wei
Department of Electrical and Computering Engineering, University of Illinois at Urbana–Champaign, Urbana, IL, USA
2 shared publications - Ahmed Elkholy
Department of Electrical and Computer Engineering, University of Illinois at Urbana–Champaign, Urbana, IL, USA
1 shared publication - Amr Elshazly
Intel Corporation, Hillsboro, OR 97124 USA
1 shared publication - Hamidreza Shahidi
Instacart, Toronto, Canada
1 shared publication Jose E. Schutt-Aine
Department of Electrical and Computer Engineering, University of Illinois at Urbana–Champaign, Urbana, IL, USA
1 shared publication
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4644-4649
A Cascaded Generative Approach for e-Commerce Recommendations
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4644-4649
Open AccessA Cascaded Generative Approach for e-Commerce Recommendations
- 16 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 53 (6) , 1806-1817
Low-Jitter Multi-Output All-Digital Clock Generator Using DTC-Based Open Loop Fractional Dividers
An all-digital reconfigurable multi-output clock generator is presented. A digital phase-locked loop provides a high-frequency clock to multiple independent open loop Δ Σ fractional dividers (FDIVs). A high resolution digital-to-time converter (DTC) whose range is calibrated in background is used to achieve low-jitter performance that is insensitive to process, voltage, and temperature variations. The proposed open loop FDIV operates over a wide frequency range of 20 MHz-1 GHz, and has programmable spread spectrum modulation and instantaneous frequency switching capabilities. Fabricated in a 65-nm process, the prototype FDIV occupies an active area of 0.017 mm². At 1-GHz output frequency, it consumes 3.2 mW from 0.9-V supply and achieves a worst case integrated jitter of 1.44 psrms.
- 16 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 53 (6) , 1806-1817
Low-Jitter Multi-Output All-Digital Clock Generator Using DTC-Based Open Loop Fractional Dividers
An all-digital reconfigurable multi-output clock generator is presented. A digital phase-locked loop provides a high-frequency clock to multiple independent open loop Δ Σ fractional dividers (FDIVs). A high resolution digital-to-time converter (DTC) whose range is calibrated in background is used to achieve low-jitter performance that is insensitive to process, voltage, and temperature variations. The proposed open loop FDIV operates over a wide frequency range of 20 MHz-1 GHz, and has programmable spread spectrum modulation and instantaneous frequency switching capabilities. Fabricated in a 65-nm process, the prototype FDIV occupies an active area of 0.017 mm². At 1-GHz output frequency, it consumes 3.2 mW from 0.9-V supply and achieves a worst case integrated jitter of 1.44 psrms.
- 17 January 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 53 (3) , 884-895
A 0.45–0.7 V 1–6 Gb/s 0.29–0.58 pJ/b Source-Synchronous Transceiver Using Near-Threshold Operation
A low-power source-synchronous multi-Gb/s transceiver is presented. Supply voltage is aggressively scaled to reduce power, and the speed penalty resulting from low-voltage operation is overcome by multiplexing transmitter/receiver synchronized by low-rate multi-phase clocks. Phase spacing errors incurred by device mismatches are corrected using a self-calibration scheme. The proposed phase calibration method uses a single digital DLL to calibrate all the phases, which makes it insensitive to offsets in the calibrating DLL. Fabricated in a 65-nm CMOS process, energy efficiency and data rate of the prototype transceiver vary from 0.29 to 0.58 pJ/bit and 1 to 6 Gb/s, respectively, as the supply voltage changes from 0.45 to 0.7 V.
- 17 January 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 53 (3) , 884-895
A 0.45–0.7 V 1–6 Gb/s 0.29–0.58 pJ/b Source-Synchronous Transceiver Using Near-Threshold Operation
A low-power source-synchronous multi-Gb/s transceiver is presented. Supply voltage is aggressively scaled to reduce power, and the speed penalty resulting from low-voltage operation is overcome by multiplexing transmitter/receiver synchronized by low-rate multi-phase clocks. Phase spacing errors incurred by device mismatches are corrected using a self-calibration scheme. The proposed phase calibration method uses a single digital DLL to calibrate all the phases, which makes it insensitive to offsets in the calibrating DLL. Fabricated in a 65-nm CMOS process, energy efficiency and data rate of the prototype transceiver vary from 0.29 to 0.58 pJ/bit and 1 to 6 Gb/s, respectively, as the supply voltage changes from 0.45 to 0.7 V.
- 28 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 53 (3) , 873-883
A 10-Gb/s/ch, 0.6-pJ/bit/mm Power Scalable Rapid-ON/OFF Transceiver for On-Chip Energy Proportional Interconnects
Modern multiprocessor system-on-chips employ network-on-chip (NoC) to efficiently connect different components together. NoCs need global and local interconnects to deliver high on-chip bandwidth and low communication latency to avoid being a performance bottleneck. They must also have high throughput density to reduce area occupied by wires. This paper presents techniques to implement power efficient transceivers for on-chip links that can achieve energy proportional operation. Conventional on-chip links optimized for best energy efficiency at peak data rate suffer from degraded energy efficiency under low utilization conditions. Dynamic voltage and frequency scaling and clock gating can partially alleviate this problem, but become ineffective in applications like mobile devices, where the data traffic can be very sporadic. In this paper, architecture and circuit techniques to improve energy efficiency under all utilization levels are presented. The proposed transceiver uses single-ended signaling with only 0.5 μm width and spacing and achieves 5-Gb/μm throughput density. Fast locking signaling and clocking circuits greatly reduce the power-ON time. Fabricated in 65-nm CMOS technology, the proposed 10-Gb/s transceiver achieves wake-up time in less than 17 ns. More than 125× effective data rate scaling (10 Gb/s to 80 Mb/s) is obtained with an energy efficiency degradation of only 1.6× (627 to 997 fJ/b/mm). When the supply voltage is scaled from 1 to 0.7 V, the peak data rate scales from 10 to 6 Gb/s and the power scalable range increases to 208× (10 Gb/s to 48 Mb/s) with the energy efficiency degradation of only 1.2× (627 to 753 fJ/b/mm).
- 28 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 53 (3) , 873-883
A 10-Gb/s/ch, 0.6-pJ/bit/mm Power Scalable Rapid-ON/OFF Transceiver for On-Chip Energy Proportional Interconnects
Modern multiprocessor system-on-chips employ network-on-chip (NoC) to efficiently connect different components together. NoCs need global and local interconnects to deliver high on-chip bandwidth and low communication latency to avoid being a performance bottleneck. They must also have high throughput density to reduce area occupied by wires. This paper presents techniques to implement power efficient transceivers for on-chip links that can achieve energy proportional operation. Conventional on-chip links optimized for best energy efficiency at peak data rate suffer from degraded energy efficiency under low utilization conditions. Dynamic voltage and frequency scaling and clock gating can partially alleviate this problem, but become ineffective in applications like mobile devices, where the data traffic can be very sporadic. In this paper, architecture and circuit techniques to improve energy efficiency under all utilization levels are presented. The proposed transceiver uses single-ended signaling with only 0.5 μm width and spacing and achieves 5-Gb/μm throughput density. Fast locking signaling and clocking circuits greatly reduce the power-ON time. Fabricated in 65-nm CMOS technology, the proposed 10-Gb/s transceiver achieves wake-up time in less than 17 ns. More than 125× effective data rate scaling (10 Gb/s to 80 Mb/s) is obtained with an energy efficiency degradation of only 1.6× (627 to 997 fJ/b/mm). When the supply voltage is scaled from 1 to 0.7 V, the peak data rate scales from 10 to 6 Gb/s and the power scalable range increases to 208× (10 Gb/s to 48 Mb/s) with the energy efficiency degradation of only 1.2× (627 to 753 fJ/b/mm).