IEEE Computer Architecture Letters (@IEEECAL) profile picture

IEEE Computer Architecture Letters

@IEEECAL

CAL is a journal for publishing 4-page high impact, high novelty Computer Architecture papers.

Joined July 2019
  • Tweets241
  • Following13
  • Followers1.3K
11Media
Photo by IEEE Computer Architecture Letters (@IEEECAL)Photo by IEEE Computer Architecture Letters (@IEEECAL)Photo by IEEE Computer Architecture Letters (@IEEECAL)Photo by IEEE Computer Architecture Letters (@IEEECAL)Photo by IEEE Computer Architecture Letters (@IEEECAL)Photo by IEEE Computer Architecture Letters (@IEEECAL)Photo by IEEE Computer Architecture Letters (@IEEECAL)Photo by IEEE Computer Architecture Letters (@IEEECAL)Photo by IEEE Computer Architecture Letters (@IEEECAL)Photo by IEEE Computer Architecture Letters (@IEEECAL)
Check out the latest work on "Cost-Effective Extension of DRAM-PIM for Group-Wise LLM Quantization" by Byeori Kim, Changhun Lee, Gwangsun Kim, Eunhyeok Park. computer.org/csdl/journal/ca…

Cost-Effective Extension of DRAM-PIM for Group-Wise LLM Quantization

Processing-in-Memory (PIM) is emerging as a promising next-generation hardware to address memory bottlenecks in large language model (LLM) inference by leveraging internal memory bandwidth, enabling...

computer.org
198
Check out the latest work on "Optically Connected Multi-Stack HBM Modules for Large Language Model Training and Inference" by Yanghui Ou, Hengrui Zhang, Austin Rovinski, David Wentzlaff, Christopher Batten. computer.org/csdl/journal/ca…

Optically Connected Multi-Stack HBM Modules for Large Language Model Training and Inference

Large language models (LLMs) have grown exponentially in size, presenting significant challenges to traditional memory architectures. Current high bandwidth memory (HBM) systems are constrained by...

computer.org
188
Check out the latest work on "Comprehensive Design Space Exploration for Graph Neural Network Aggregation on GPUs" by Hyunwoo Nam, Jay Hwan Lee, Shinhyung Yang, Yeonsoo Kim, Jiun Jeong, Jeonggeun Kim, Bernd Burgstaller. computer.org/csdl/journal/ca…

Comprehensive Design Space Exploration for Graph Neural Network Aggregation on GPUs

Graph neural networks (GNNs) have become the state-of-the-art technology for extracting and predicting data representations on graphs. With increasing demand to accelerate GNN computations, the GPU...

computer.org
282
Check out the latest work on "RoPIM: A Processing-in-Memory Architecture for Accelerating Rotary Positional Embedding in Transformer Models" by Yunhyeong Jeon, Minwoo Jang, Hwanjun Lee, Yeji Jung, Jin Jung, Jonggeon Lee, Jinin So, Daehoon Kim. computer.org/csdl/journal/ca…

RoPIM: A Processing-in-Memory Architecture for Accelerating Rotary Positional Embedding in Transf...

The emergence of attention-based Transformer models, such as GPT, BERT, and LLaMA, has revolutionized Natural Language Processing (NLP) by significantly improving performance across a wide range of...

computer.org
173
Check out the latest work on "Accelerating Page Migrations in Operating Systems With Intel DSA" by Jongho Baik, Jonghyeon Kim, Chang Hyun Park, Jeongseob Ahn. computer.org/csdl/journal/ca…

Accelerating Page Migrations in Operating Systems With Intel DSA

Modern server-class CPUs are introducing special-purpose accelerators on the same chip to improve performance and efficiency for data-intensive applications. This paper presents a case for accelera...

computer.org
135
Check out the latest work on "GPU-Centric Memory Tiering for LLM Serving With NVIDIA Grace Hopper Superchip" by Woohyung Choi, Jinwoo Jeong, Hanhwi Jang, Jeongseob Ahn. computer.org/csdl/journal/ca…

GPU-Centric Memory Tiering for LLM Serving With NVIDIA Grace Hopper Superchip

This study investigates the performance of serving large language models (LLMs) with a focus on the high-bandwidth interconnect between GPU and CPU using a real NVIDIA Grace Hopper Superchip. This...

computer.org
112
Check out the latest work on "Cooperative Memory Deduplication With Intel Data Streaming Accelerator" by Houxiang Ji, Minho Kim, Seonmu Oh, Daehoon Kim, Nam Sung Kim. computer.org/csdl/journal/ca…

Cooperative Memory Deduplication With Intel Data Streaming Accelerator

Memory deduplication plays a critical role in reducing memory consumption and the total cost of ownership (TCO) in hyperscalers, particularly as the advent of large language models imposes unpreced...

computer.org
84
Check out the latest work on "SPAM: Streamlined Prefetcher-Aware Multi-Threaded Cache Covert-Channel Attack" by E. Kritheesh, Biswabandan Panda. computer.org/csdl/journal/ca…

SPAM: Streamlined Prefetcher-Aware Multi-Threaded Cache Covert-Channel Attack

Last-level cache (LLC) covert-channels exploit the cache timing differences to transmit information. In recent works, the attacks rely on a single sender and a single receiver. Streamline is the...

computer.org
57
Check out the latest work on "High-Performance Winograd Based Accelerator Architecture for Convolutional Neural Network" by Vardhana M, Rohan Pinto. computer.org/csdl/journal/ca…

High-Performance Winograd Based Accelerator Architecture for Convolutional Neural Network

Convolutional Neural Networks are deployed mostly on GPUs or CPUs. However, due to the increasing complexity of architecture and growing performance requirements, these platforms may not be suitable...

computer.org
45
Check out the latest work on "PINSim: A Processing In- and Near-Sensor Simulator to Model Intelligent Vision Sensors" by Sepehr Tabrizchi, Mehrdad Morsali, David Pan, Shaahin Angizi, Arman Roohi. computer.org/csdl/journal/ca…

PINSim: A Processing In- and Near-Sensor Simulator to Model Intelligent Vision Sensors

This letter introduces PINSim, a user-friendly and flexible framework for simulating emerging smart vision sensors in the early design stages. PINSim enables the realization of integrated sensing and...

computer.org
69
Check out the latest work on "Characterization and Analysis of the 3D Gaussian Splatting Rendering Pipeline" by Jiwon Lee, Yunjae Lee, Youngeun Kwon, Minsoo Rhu. computer.org/csdl/journal/ca…

Characterization and Analysis of the 3D Gaussian Splatting Rendering Pipeline

Novel view synthesis, a task generating a 2D image frame from a specific viewpoint within a 3D object or scene, plays a crucial role in 3D rendering. Neural Radiance Field (NeRF) emerged as a...

computer.org
138
Check out the latest work on "Electra: Eliminating the Ineffectual Computations on Bitmap Compressed Matrices" by Chaithanya Krishna Vadlamudi, Bahar Asgari. computer.org/csdl/journal/ca…

Electra: Eliminating the Ineffectual Computations on Bitmap Compressed Matrices

The primary computations in several applications, such as deep learning recommendation models, graph neural networks, and scientific computing, involve sparse matrix sparse matrix multiplications...

computer.org
1
105
Check out the latest work on "Straw: A Stress-Aware WL-Based Read Reclaim Technique for High-Density NAND Flash-Based SSDs" by Myoungjun Chun, Jaeyong Lee, Inhyuk Choi, Jisung Park, Myungsuk Kim, Jihong Kim. computer.org/csdl/journal/ca…

Straw: A Stress-Aware WL-Based Read Reclaim Technique for High-Density NAND Flash-Based SSDs

Although read disturbance has emerged as a major reliability concern, managing read disturbance in modern NAND flash memory has not been thoroughly investigated yet. From a device characterization...

computer.org
1
140
Check out the latest work on "IntervalSim++: Enhanced Interval Simulation for Unbalanced Processor Designs" by Haseung Bong, Nahyeon Kang, Youngsok Kim, Joonsung Kim, Hanhwi Jang. computer.org/csdl/journal/ca…

IntervalSim++: Enhanced Interval Simulation for Unbalanced Processor Designs

As processor microarchitecture is getting complicated, an accurate analytic model becomes crucial for exploring large processor design space within limited development time. An interval simulation is...

computer.org
1
98
Check out the latest work on "Quantum Assertion Scheme for Assuring Qudit Robustness" by Navnil Choudhury, Chao Lu, Kanad Basu. computer.org/csdl/journal/ca…

Quantum Assertion Scheme for Assuring Qudit Robustness

Noisy Intermediate-Scale Quantum (NISQ) computers are impeded by constraints such as limited qubit count and susceptibility to noise, hindering the progression towards fault-tolerant quantum comput...

computer.org
87
Check out the latest work on "SCALES: SCALable and Area-Efficient Systolic Accelerator for Ternary Polynomial Multiplication" by Samuel Coulon, Tianyou Bao, Jiafeng Xie. computer.org/csdl/journal/ca…

SCALES: SCALable and Area-Efficient Systolic Accelerator for Ternary Polynomial Multiplication

Polynomial multiplication is a key component in many post-quantum cryptography and homomorphic encryption schemes. One recurring variation, ternary polynomial multiplication over ring - where one...

computer.org
79
Check out the latest work on "ZoneBuffer: An Efficient Buffer Management Scheme for ZNS SSDs" by Hongtao Wang, Peiquan Jin. computer.org/csdl/journal/ca…

ZoneBuffer: An Efficient Buffer Management Scheme for ZNS SSDs

The introduction of Zoned Namespace SSDs (ZNS SSDs) presents new challenges for existing buffer management schemes. In addition to traditional SSD characteristics such as read/write asymmetry and...

computer.org
80
Check out the latest work on "GCStack: A GPU Cycle Accounting Mechanism for Providing Accurate Insight Into GPU Performance" by Hanna Cha, Sungchul Lee, Yeonan Ha, Hanhwi Jang, Joonsung Kim, Youngsok Kim. computer.org/csdl/journal/ca…

GCStack: A GPU Cycle Accounting Mechanism for Providing Accurate Insight Into GPU Performance

Cycles Per Instruction (CPI) stacks help computer architects gain insight into the performance of their target architectures and applications. To bring the benefits of CPI stacks to Graphics Proces...

computer.org
89
Check out the latest work on "A Case for Hardware Memoization in Server CPUs" by Farid Samandi, Natheesan Ratnasegar, Michael Ferdman. computer.org/csdl/journal/ca…

A Case for Hardware Memoization in Server CPUs

Server applications exhibit a high degree of code repetition because they handle many similar requests. In turn, repeated execution of the same code, often with identical inputs, highlights an...

computer.org
62
Check out the latest work on "Characterization and Analysis of Text-to-Image Diffusion Models" by Eunyeong Cho, Jehyeon Bang, Minsoo Rhu. computer.org/csdl/journal/ca…

Characterization and Analysis of Text-to-Image Diffusion Models

Diffusion models have rapidly emerged as a prominent AI model for image generation. Despite its importance, however, little have been understood within the computer architecture community regarding...

computer.org
63
Load more