Transformers

  • No Comments

SparseCol: A 1320 BTOPS/W Precision-Scalable NPU Exploiting Training-Free Structured Bit-Level Sparsity and Dynamic Dataflow

SparseCol: A 1320 BTOPS/W Precision-Scalable NPU Exploiting Training-Free Structured Bit-Level Sparsity and Dynamic Dataflow 150 150
Author(s): Man Shi, Vikram Jain, Weijie Jiang, Chao Fang, Antony Joseph, Wim Dehaene, Marian Verhelst

Abstract:

Bit-serial computation enables sequential processing of data at the bit level, providing several advantages, such as scalable computational precision. This approach has gained significant attention, especially for exploiting bit-level sparsity (BLS) in AI workloads. While current bit-serial processors leverage BLS to eliminate the computation associated with zero bits, they face …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1 – 14
Year of Publication: 2025
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2025.3636451
Publisher: IEEE

View on IEEE Xplore

  • No Comments

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
Author(s): Jaehoon Heo, Adiwena Putra, Sungwoong Yune, Jieon Yoon, Hangyeol Lee, Ji-Hoon Kim, Joo-Young Kim

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 …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1 – 13
Year of Publication: 2025
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2025.3631087
Publisher: IEEE

View on IEEE Xplore

  • No Comments

A Multicore Programmable Variable-Precision Near-Memory Accelerator for CNN and Transformer Models

A Multicore Programmable Variable-Precision Near-Memory Accelerator for CNN and Transformer Models 150 150
Author(s): Yiming Yang, Yiyang Yuan, Xinghua Wang, Xiaoran Li, Hao Wu, Qihao Liu, Weiye Tang, Xiangqu Fu, Feng Zhang

Abstract:

Convolutional neural network (CNN) and transformer are the most popular neural network models in computer vision (CV) and natural language processing (NLP). It is quite common to use both these two models in multimodal scenarios, such as text-to-image generation. However, these two models have very different memory mappings, dataflows and …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1 – 13
Year of Publication: 2025
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2025.3624011
Publisher: IEEE

View on IEEE Xplore

  • No Comments

DPIM: A 2T1C eDRAM Transformer-in-Memory Chip With Sparsity-Aware Quantization and Heterogeneous Dense–Sparse Core

DPIM: A 2T1C eDRAM Transformer-in-Memory Chip With Sparsity-Aware Quantization and Heterogeneous Dense–Sparse Core 150 150
Author(s): Donghyuk Kim, Jae-Young Kim, Hyunjun Cho, Seungjae Yoo, Sukjin Lee, Sungwoong Yune, Sejeong Yang, Hoichang Jeong, Keonhee Park, Ki-Soo Lee, Jongchan Lee, Chanheum Han, Gunmo Koo, Yuli Han, Jaejin Kim, Jaemin Kim, Kyuho Jason Lee, Joo-Hyung Chae, Kunhee Cho, Joo-Young Kim

Abstract:

Transformer models have revolutionized artificial intelligence (AI) applications across various domains, but their increasing complexity poses significant challenges in terms of computational and memory demands. While processing-in-memory (PIM) paradigms have been adopted to address these limitations, existing PIM-based transformer accelerators still face hurdles such as: 1) focusing solely on optimizing attention …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1 – 16
Year of Publication: 2025
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2025.3607826
Publisher: IEEE

View on IEEE Xplore

  • No Comments

A Fully Integrated Galvanic Isolator for Gate Drivers With Asynchronous 100/167 Mb/s ASK/FSK Full-Duplex Communication

A Fully Integrated Galvanic Isolator for Gate Drivers With Asynchronous 100/167 Mb/s ASK/FSK Full-Duplex Communication 150 150
Author(s): Lucrezia Navarin, Karl Norling, Marco Parenzan, Stefano Ruzzu, Andrea Neviani, Andrea Bevilacqua

Abstract:

A fully integrated galvanic isolator for gate drivers that supports high-speed, asynchronous, full-duplex communication is presented. Data transmission from the microcontroller to the power device is achieved using amplitude-shift keying (ASK) at 100 Mb/s, while simultaneous communication in the opposite direction is implemented using frequency-shift keying (FSK) at 167 Mb/s. …

Published in: IEEE Solid-State Circuits Letters
Page(s): 289 – 292
Year of Publication: 2025
Electronic ISSN: 2573-9603
DOI: 10.1109/LSSC.2025.3611018
Publisher: IEEE

View on IEEE Xplore

  • No Comments

SLiMDO: A Single-Link Multi-Domain-Output Isolated DC–DC Converter With Passive Magnetic Flux Sharing for Local Energy Distribution and Rx Behavior Sensing-Based Global Power Modulation

SLiMDO: A Single-Link Multi-Domain-Output Isolated DC–DC Converter With Passive Magnetic Flux Sharing for Local Energy Distribution and Rx Behavior Sensing-Based Global Power Modulation 150 150
Author(s): Jianqiang Jiang, Lei Zhao, Junyao Tang, Cheng Huang

Abstract:

This article introduces a small form-factor single-link multi-domain-output (SLiMDO) isolated dc–dc converter design. The proposed design provides two regulated outputs in separate domains in the receiver (Rx) side with a single micro-transformer. These isolated Rxes achieve local voltage regulation and automatic energy distribution across domains through passive magnetic flux …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1 – 15
Year of Publication: 2025
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2025.3606903
Publisher: IEEE

View on IEEE Xplore

  • No Comments

A Millimeter-Wave Standing-Wave Oscillator With Frequency-Specific Wave-Velocity Control Demonstrating Class-F Effects

A Millimeter-Wave Standing-Wave Oscillator With Frequency-Specific Wave-Velocity Control Demonstrating Class-F Effects 150 150
Author(s): Wei-Yu Lin, Jun-Chau Chien

Abstract:

Implementing dual-resonance class-F oscillators with transformer feedback beyond 60 GHz poses significant challenges due to the limited third-harmonic tank impedance when using small coils with low coupling factors. To address these limitations and leverage the phase noise advantages of class-F operation, this letter introduces a standing-wave oscillator (SWO) topology featuring an …

Published in: IEEE Solid-State Circuits Letters
Page(s): 181 – 184
Year of Publication: 2025
Electronic ISSN: 2573-9603
DOI: 10.1109/LSSC.2025.3578942
Publisher: IEEE

View on IEEE Xplore

  • No Comments

A Simultaneous Dual-Carrier Transformer-Coupled Passive Mixer-First Receiver Front-End Supporting Blocker Suppression

A Simultaneous Dual-Carrier Transformer-Coupled Passive Mixer-First Receiver Front-End Supporting Blocker Suppression 150 150
Author(s): Jamie C. Ye, Alain H. Antón, Sanaz Sadeghi, Russ H. Huang, Alyosha C. Molnar

Abstract:

A high dynamic range N-path passive mixer-first receiver architecture capable of simultaneously down-converting two arbitrary bands through a single RF port is presented. The architecture consists of two passive mixers arranged in a series configuration with a transformer front-end to minimize cross-loading between mixers while still providing impedance transparency and …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1541 – 1553
Year of Publication: 2025
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2025.3546082
Publisher: IEEE

View on IEEE Xplore

  • No Comments

MINOTAUR: A Posit-Based 0.42–0.50-TOPS/W Edge Transformer Inference and Training Accelerator

MINOTAUR: A Posit-Based 0.42–0.50-TOPS/W Edge Transformer Inference and Training Accelerator 150 150
Author(s): Kartik Prabhu, Robert M. Radway, Jeffrey Yu, Kai Bartolone, Massimo Giordano, Fabian Peddinghaus, Yonatan Urman, Win-San Khwa, Yu-Der Chih, Meng-Fan Chang, Subhasish Mitra, Priyanka Raina

Abstract:

Transformer models have revolutionized natural language processing (NLP) and enabled many new applications, but are challenging to deploy on resource-constrained edge devices due to their high computation and memory demands. We present MINOTAUR, an edge system-on-chip (SoC) for inference and fine-tuning of Transformer models with all memory on the chip. …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1311 – 1323
Year of Publication: 2025
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2025.3545731
Publisher: IEEE

View on IEEE Xplore

Search this website