Noise

HUTAO: A Reconfigurable Homomorphic Processing UniT With Cache-Aware Operation Scheduling

HUTAO: A Reconfigurable Homomorphic Processing UniT With Cache-Aware Operation Scheduling 150 150

Abstract:

Fully homomorphic encryption (FHE) enables privacy-preserving machine learning (PPML) at the cost of intensive computational overhead, which necessitates the use of domain-specific accelerators. To achieve comprehensive support for leveled FHE, this article presents a reconfigurable multi-scheme FHE processor that supports both client-side encryption/decryption and server-side evaluation. First, a reconfigurable …

View on IEEE Xplore

A 77-fJ/bit 8-Gbps Adaptive-Voltage-Compatible Self-Timed Die-to-Die Link for 2.5-D and 3-D Interconnect in 3 nm

A 77-fJ/bit 8-Gbps Adaptive-Voltage-Compatible Self-Timed Die-to-Die Link for 2.5-D and 3-D Interconnect in 3 nm 150 150

Abstract:

This work presents a self-timed die-to-die link that serializes four data bits per pin for 2.5-D, or 3-D interconnects using a standard adaptive digital clock and voltage supply. The link achieves 8 Gbps of per-pin bandwidth with a latency of one cycle, energy efficiency of 77 fJ/b, and bandwidth density of 44…

View on IEEE Xplore

A 19.4-fsRMS Jitter 0.1-to-44-GHz Cryo-CMOS Fractional-N CP-PLL Featuring Automatic Bleed Calibration for Quantum Computing

A 19.4-fsRMS Jitter 0.1-to-44-GHz Cryo-CMOS Fractional-N CP-PLL Featuring Automatic Bleed Calibration for Quantum Computing 150 150

Abstract:

Cryogenic fractional- $N$ phase-locked loops (PLLs) are essential for large-scale superconducting quantum computing, and serve as integrated pump sources for Josephson parametric amplifiers. These PLLs enable high-fidelity qubit readout while reducing the thermal load and wiring complexity associated with room-temperature generators. However, the cryogenic pump sources developed thus far were …

View on IEEE Xplore

0.13 K NETD D-Band CMOS Passive Imager With Noise Suppression Analysis

0.13 K NETD D-Band CMOS Passive Imager With Noise Suppression Analysis 150 150

Abstract:

This article presents a new system design and in-depth analysis of a wideband, low-power passive imaging receiver based on a Dicke-switch architecture, implemented in 28 nm CMOS technology. The proposed structure employs a three-coil gm-boosting technique for the low-noise amplifier (LNA). This approach reduces the LNA’s noise figure (NF) and …

View on IEEE Xplore

A 39.4-mW 300 MHz-BW 70.9 dB-SNDR Hybrid ADC With Resistive Input and 200 fs, rms-Jitter Tolerance

A 39.4-mW 300 MHz-BW 70.9 dB-SNDR Hybrid ADC With Resistive Input and 200 fs, rms-Jitter Tolerance 150 150

Abstract:

This letter presents a power-efficient hybrid ADC architecture: a low-resolution continuous-time (CT) delta-sigma modulator (DSM) followed by a time-interleaved pipeline stage which further quantizes the quantization noise of the DSM. In the frontend CT DSM, the resistive input makes the ADC easy-to-drive, and the direct-charge-dump feedback (DCD FB) provides a …

View on IEEE Xplore

A Bidirectional Neuromodulation Chipset With Algorithm-Aware AFE Optimization and High-Voltage-Compliant Stimulation

A Bidirectional Neuromodulation Chipset With Algorithm-Aware AFE Optimization and High-Voltage-Compliant Stimulation 150 150

Abstract:

This work presents a bidirectional neuromodulation chipset with 64-channel neural analog front-end (AFE), and a four-channel current stimulator. The chipset employs a heterogeneous architecture, combining a 28-nm low-voltage (LV) CMOS process for the AFE and the digital backend (DBE) to improve area and power efficiency, with a 180-nm high-voltage (HV) …

View on IEEE Xplore

An 11.95-ENOB 560-MS/s Amplifier-Switching Subranging Analog-to-Digital Converter With Multi-Threshold Comparators

An 11.95-ENOB 560-MS/s Amplifier-Switching Subranging Analog-to-Digital Converter With Multi-Threshold Comparators 150 150

Abstract:

This article proposes a 14-bit, 560-MS/s subranging analog-to-digital converter (ADC) that employs an amplifier-switching architecture with multi-threshold comparators. The proposed amplifier-switching architecture reuses a flash quantizer multiple times during subranging conversion by amplifying the residue voltage with an appropriate gain at each quantization step. This approach reduces the required …

View on IEEE Xplore

A 4 × 224 Gb/s Single-Ended PAM-4 Transceiver Front-End With Noise Suppression Technique and Cascaded Equalizers in 130-nm SiGe BiCMOS

A 4 × 224 Gb/s Single-Ended PAM-4 Transceiver Front-End With Noise Suppression Technique and Cascaded Equalizers in 130-nm SiGe BiCMOS 150 150

Abstract:

A dc-coupled analog single-ended (SE) transceiver (TRX) front-end supporting 224 Gb/s/lane is presented. It features SE-to-differential (S2D) and differential-to-SE (D2S) conversion, power-efficient broadband analog equalization, and noise suppression. Both the transmitter and receiver front-ends adopt pseudodifferential structures with dual-loop regulators to achieve a high power supply rejection …

View on IEEE Xplore

A 57.3-fps 12.8 TFLOPS/W Text-to-Motion Processor With Inter-Iteration Output Sparsity and Inter-Frame Joint Similarity

A 57.3-fps 12.8 TFLOPS/W Text-to-Motion Processor With Inter-Iteration Output Sparsity and Inter-Frame Joint Similarity 150 150

Abstract:

Recently, 3-D human motion generation has become essential in media applications such as film production and augmented reality (AR)/virtual reality (VR) devices, requiring the generation of human joint movements and detailed 3-D meshes for each joint. Traditionally, joint creation required hours or even days, making it impractical for real-time …

View on IEEE Xplore