Throughput

  • No Comments

3-D Stacked HBM and Compute Accelerators for LLM: Optimizing Thermal Management and Power Delivery Efficiency

3-D Stacked HBM and Compute Accelerators for LLM: Optimizing Thermal Management and Power Delivery Efficiency 150 150
Author(s): Janak Sharda, Madison Manley, Jungyoun Kwak, Chinsung Park, Muhannad Bakir, Shimeng Yu

Abstract:

Advanced packaging is becoming essential for designing hardware accelerators for large language models (LLMs). Different architectures, such as 2.5-D integration of memory with logic, have been proposed; however, the bandwidth limits the throughput of the complete system. Recent works have proposed memory on logic systems, where high bandwidth memory (HBM) …

Published in: IEEE Journal on Exploratory Solid-State Computational Devices and Circuits
Page(s): 116 – 122
Year of Publication: 2025
Electronic ISSN: 2329-9231
DOI: 10.1109/JXCDC.2025.3617298
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

Energy-Efficient Reconfigurable XGBoost Inference Accelerator With Modular Unit Trees via Selective Node Execution and Data Movement

Energy-Efficient Reconfigurable XGBoost Inference Accelerator With Modular Unit Trees via Selective Node Execution and Data Movement 150 150
Author(s): Chang Eun Song, Yidong Li, Amardeep Ramnani, Pulkit Agrawal, Purvi Agrawal, Sung-Joon Jang, Sang-Seol Lee, Tajana Rosing, Mingu Kang

Abstract:

The extreme gradient boosting (XGBoost) has emerged as a powerful AI algorithm, achieving high accuracy and winning multiple Kaggle competitions in various tasks including medical diagnosis, recommendation systems, and autonomous driving. It has great potential for running on edge devices due to its binary tree-based simple computing kernel, offering unique …

Published in: IEEE Journal of Solid-State Circuits
Page(s): 1 – 13
Year of Publication: 2025
Electronic ISSN: 1558-173X
DOI: 10.1109/JSSC.2025.3607896
Publisher: IEEE

View on IEEE Xplore

  • No Comments

24.86 Gb/s Full-Digital Chaos Random Number 1.53 GSamples/s Noise Generator in 40nm CMOS

24.86 Gb/s Full-Digital Chaos Random Number 1.53 GSamples/s Noise Generator in 40nm CMOS 150 150
Author(s): Cheng-Bin Chen, Tsung Chen, Yuan-Hao Huang

Abstract:

This letter presents a fully digital true random number generator (TRNG) and noise generator (NG) based on a chaos system. We design the chaos random number generator (CRNG) using the proposed Euler-based modified Lorenz system with periodic perturbation and modified modulo unit. The chaos NG (CNG) processor integrates the CRNG …

Published in: IEEE Solid-State Circuits Letters
Page(s): 253 – 256
Year of Publication: 2025
Electronic ISSN: 2573-9603
DOI: 10.1109/LSSC.2025.3605369
Publisher: IEEE

View on IEEE Xplore

  • No Comments

MIX-ACIM: A 28-nm Mixed-Precision Analog Compute-in-Memory With Digital Feature Restoration for Vector-Matrix Multiplication

MIX-ACIM: A 28-nm Mixed-Precision Analog Compute-in-Memory With Digital Feature Restoration for Vector-Matrix Multiplication 150 150
Author(s): Wei-Chun Wang, Shida Zhang, Laith Shamieh, Narasimha Vasishta Kidambi, Isha Chakraborty, Saibal Mukhopadhyay

Abstract:

A mixed-precision analog compute-in-memory (Mix-ACIM) is presented for mixed-precision vector-matrix multiplication (VMM). The design features an all-analog current-domain fixed-point (FxP) VMM with floating-point conversion and feature restoration. A 28 nm CMOS test chip shows 41 TOPS/W and 24 TOPS/mm2 for FxP (8-bit input/weight and 12-bit output) and 24.18 TFLOPS/W and 3.3 …

Published in: IEEE Solid-State Circuits Letters
Page(s): 213 – 216
Year of Publication: 2025
Electronic ISSN: 2573-9603
DOI: 10.1109/LSSC.2025.3590757
Publisher: IEEE

View on IEEE Xplore

Search this website