701 citations · 794 across the 17 of their papers we have counts for
18 papers
REACH: Controller-Managed Long-Span ECC for HBM AI Inference
Rui Xie, Yunhua Fang, Asad Ul Haq +5
High-Bandwidth Memory (HBM) cost motivates stronger controller protection that can support a wider range of device error rates. Long-span error-correcting codes provide stronger pr…
Is Finer Better? The Limits of Microscaling Formats in Large Language Models
Andrea Fasoli, Monodeep Kar, Chi-Chun Liu +4
Microscaling data formats leverage per-block tensor quantization to enable aggressive model compression with limited loss in accuracy. Unlocking their potential for efficient train…
Making Strong Error-Correcting Codes Work Effectively for HBM in AI Inference
Rui Xie, Yunhua Fang, Asad Ul Haq +5
LLM inference is increasingly memory bound, and HBM cost per GB dominates system cost. Current HBM stacks include short on-die ECC that tightens binning, raises price, and fixes re…
Breaking the HBM Bit Cost Barrier: Domain-Specific ECC for AI Inference Infrastructure
Rui Xie, Asad Ul Haq, Yunhua Fang +5
High-Bandwidth Memory (HBM) delivers exceptional bandwidth and energy efficiency for AI workloads, but its high cost per bit, driven in part by stringent on-die reliability require…
SmartQuant: CXL-based AI Model Store in Support of Runtime Configurable Weight Quantization
Rui Xie, Asad Ul Haq, Linsen Ma +5
Recent studies have revealed that, during the inference on generative AI models such as transformer, the importance of different weights exhibits substantial context-dependent vari…
Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons
Zhenyu Liu, Garrett Gagnon, Swagath Venkataramani +1
Deep Neural Networks (DNNs) have revolutionized a wide range of industries, from healthcare and finance to automotive, by offering unparalleled capabilities in data analysis and de…
Approximate Computing and the Efficient Machine Learning Expedition
Jörg Henkel, Hai Li, Anand Raghunathan +4
Approximate computing (AxC) has been long accepted as a design alternative for efficient system implementation at the cost of relaxed accuracy requirements. Despite the AxC researc…
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization
Andrea Fasoli, Chia-Yu Chen, Mauricio Serrano +5
We report on aggressive quantization strategies that greatly accelerate inference of Recurrent Neural Network Transducers (RNN-T). We use a 4 bit integer representation for both we…
4-bit Quantization of LSTM-based Speech Recognition Models
Andrea Fasoli, Chia-Yu Chen, Mauricio Serrano +9
We investigate the impact of aggressive low-precision representations of weights and activations in two families of large LSTM-based architectures for Automatic Speech Recognition…
ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training
Chia-Yu Chen, Jiamin Ni, Songtao Lu +8
Large-scale distributed training of Deep Neural Networks (DNNs) on state-of-the-art platforms is expected to be severely communication constrained. To overcome this limitation, num…
Workload-aware Automatic Parallelization for Multi-GPU DNN Training
Sungho Shin, Youngmin Jo, Jungwook Choi +3
Deep neural networks (DNNs) have emerged as successful solutions for variety of artificial intelligence applications, but their very large and deep models impose high computational…
Bridging the Accuracy Gap for 2-bit Quantized Neural Networks (QNN)
Jungwook Choi, Pierce I-Jen Chuang, Zhuo Wang +3
Deep learning algorithms achieve high classification accuracy at the expense of significant computation cost. In order to reduce this cost, several quantization schemes have gained…
PACT: Parameterized Clipping Activation for Quantized Neural Networks
Jungwook Choi, Zhuo Wang, Swagath Venkataramani +3
Deep learning algorithms achieve high classification accuracy at the expense of significant computation cost. To address this cost, a number of quantization schemes have been propo…
SparCE: Sparsity aware General Purpose Core Extensions to Accelerate Deep Neural Networks
Sanchari Sen, Shubham Jain, Swagath Venkataramani +1
Deep Neural Networks (DNNs) have emerged as the method of choice for solving a wide range of machine learning tasks. The enormous computational demands posed by DNNs have most comm…
DyVEDeep: Dynamic Variable Effort Deep Neural Networks
Sanjay Ganapathy, Swagath Venkataramani, Balaraman Ravindran +1
Deep Neural Networks (DNNs) have advanced the state-of-the-art in a variety of machine learning tasks and are deployed in increasing numbers of products and services. However, the…
Multiplier-less Artificial Neurons Exploiting Error Resiliency for Energy-Efficient Neural Computing
Syed Shakib Sarwar, Swagath Venkataramani, Anand Raghunathan +1
Large-scale artificial neural networks have shown significant promise in addressing a wide range of classification and recognition applications. However, their large computational…
Energy-Efficient Object Detection using Semantic Decomposition
Priyadarshini Panda, Swagath Venkataramani, Abhronil Sengupta +2
Machine-learning algorithms offer immense possibilities in the development of several cognitive applications. In fact, large scale machine-learning classifiers now represent the st…
Exploring Spin-Transfer-Torque Devices for Logic Applications
Zoha Pajouhi, Swagath Venkataramani, Karthik Yogendra +2
As CMOS nears the end of the projected scaling roadmap, significant effort has been devoted to the search for new materials and devices that can realize memory and logic. Spintroni…