Logic

A Compact XOR Gate Implemented With a Single Straintronic Magnetic Tunnel Junction

A Compact XOR Gate Implemented With a Single Straintronic Magnetic Tunnel Junction 150 150

Abstract:

The XOR Boolean logic gate is widely used in many applications such as encryption (XOR ciphers), binary addition (half- and full-adders), error detection (parity bits), etc. but is challenging to construct because of its demanding conditional dynamics. It typically requires multiple logic switches or other types of gates, which results …

View on IEEE Xplore

Open DRAM Model—Part II: Enabling Processing-in-Memory in 3-D DRAM

Open DRAM Model—Part II: Enabling Processing-in-Memory in 3-D DRAM 150 150

Abstract:

Processing-in-memory (PIM) by implementing Boolean logic functions in dynamic random access memory (DRAM) has been proposed to alleviate the memory wall problem in data-intensive computing. However, quantitatively evaluating DRAM-based logic operations across different DRAM architectures remains challenging due to the lack of publicly available DRAM cell and peripheral transistor models …

View on IEEE Xplore

A3D-MoE: Acceleration of Large Language Models With Mixture of Experts via 3-D Heterogeneous Integration

A3D-MoE: Acceleration of Large Language Models With Mixture of Experts via 3-D Heterogeneous Integration 150 150

Abstract:

Conventional large language models (LLMs) have large parameter sets, making inference costly and energy-intensive; mixture-of-experts (MoEs) mitigates this by activating fewer weights per token, but fine-grained MoE LLMs still face runtime workload variability, inefficient conventional scheduling, and high bandwidth memory (HBM) loading energy/bandwidth demands. A3D-MoE addresses these with 3…

View on IEEE Xplore

A 3-nm FinFET 563-kbit 35.5-Mbit/mm2 Dual-Rail SRAM With 3.89-pJ/Access High Energy Efficient and 27.5-μW/Mbit One-Cycle Latency Low-Leakage Mode

A 3-nm FinFET 563-kbit 35.5-Mbit/mm2 Dual-Rail SRAM With 3.89-pJ/Access High Energy Efficient and 27.5-μW/Mbit One-Cycle Latency Low-Leakage Mode 150 150

Abstract:

This article presents a high-density (HD) 6T SRAM macro designed in 3-nm FinFET technology with an extended dual-rail (XDR) architecture, addressing active energy and leakage for mobile applications. Two key innovations are introduced: the delayed-wordline in write operation (DEWL) technique and a one-cycle latency low-leakage access mode (1-CLM). The XDR …

View on IEEE Xplore

A 12 b 180-MS/s Pipelined-SAR ADC With a Low-Power Calibration-Free RA and Hardware-Efficient SAR Logic

A 12 b 180-MS/s Pipelined-SAR ADC With a Low-Power Calibration-Free RA and Hardware-Efficient SAR Logic 150 150

Abstract:

This letter presents a 12-bit, 180-MS/s pipelined-SAR ADC in 65-nm CMOS. To eliminate the complex interstage gain-error calibration for a fast-response characteristic, a high-gain residue amplifier (RA) featuring a two-stage gain-boosting architecture is proposed. By removing the tail current, the RA significantly alleviates slew-rate and voltage headroom limitations. The …

View on IEEE Xplore

Building Minimum-Power Digital Circuits With Sub-Femtowatt Dynamic Leakage-Suppression Logic Standard Cells

Building Minimum-Power Digital Circuits With Sub-Femtowatt Dynamic Leakage-Suppression Logic Standard Cells 150 150

Abstract:

This article investigates dynamic leakage-suppression (DLS) logic for minimum-power operation in digital circuits. The DLS logic family uses a strong intrinsic subthreshold leakage reduction technique and is an emerging approach for computing applications that prioritize low active power at or beneath the nW-level. We analytically model the key operating characteristics …

View on IEEE Xplore

A 1.1-nJ/Conversion RC-Discharge-Based Resistance Sensor With ±0.65% (3σ) 1 -Point Trimmed Inaccuracy in 0.18-μm CMOS Technology

A 1.1-nJ/Conversion RC-Discharge-Based Resistance Sensor With ±0.65% (3σ) 1 -Point Trimmed Inaccuracy in 0.18-μm CMOS Technology 150 150

Abstract:

This letter presents an energy-efficient RC discharge-based sensor readout circuit for sub-kilo-ohm resistance measurements. An SAR logic is implemented to adjust the DAC capacitor array to equalize the RC time constants of the resistance-sensing and DAC branches, thereby eliminating the high static current required to bias the small sensing resistor. …

View on IEEE Xplore

A 7-Level 18-Wire-State Trio-Signaling Transmitter for MIPI C-PHY 3.0 Interfaces

A 7-Level 18-Wire-State Trio-Signaling Transmitter for MIPI C-PHY 3.0 Interfaces 150 150

Abstract:

This letter presents a MIPI C-PHY v3.0 TX, which adopts trio-signaling using three wires per lane. Each line supports seven-level signaling, enabling 18 wire states to map 32-bit data into nine symbols, achieving 3.56 bits/symbol efficiency. Balanced coding maintains constant driver current, enhancing SSO noise immunity, and embedded clocking is achieved …

View on IEEE Xplore

A 14-nm Nonvolatile-Volatile-Fused Compute-In-Memory Macro Based on Logic-Compatible Flash for Plastic Neural Networks

A 14-nm Nonvolatile-Volatile-Fused Compute-In-Memory Macro Based on Logic-Compatible Flash for Plastic Neural Networks 150 150

Abstract:

Designing computing-in-memory (CIM) chips with synaptic plasticity can potentially support energy-efficient on-chip learning in edge devices for rapid local task adaptation. Its silicon implementation is challenging as it requires hybridizing nonvolatile and volatile memory (VM) and customized computational operations. In this work, we propose a plastic CIM (P-CIM) macro featuring: 1) …

View on IEEE Xplore