20 citations · 28 across the 7 of their papers we have counts for
8 papers
The Case for TPU-Accelerated Analytical Query Processing
Yeounoh Chung, Jaehyun Ha, Helena Caminal +4
Large-scale analytical query processing requires computing substrates capable of immense distributed scale-out. Tensor Processing Units (TPUs) perfectly embody this extreme-scale a…
Reducing the GPU Memory Bottleneck with Lossless Compression for ML -- Extended
Aditya K Kamath, Arvind Krishnamurthy, Marco Canini +1
Machine learning (ML) training and inference often process data sets far exceeding GPU memory capacity, forcing them to rely on PCIe for on-demand tensor transfers, causing critica…
LLM-42: Enabling Determinism in LLM Inference with Verified Speculation
Raja Gond, Aditya K Kamath, Ramachandran Ramjee +1
In LLM inference, the same prompt may yield different outputs across different runs. At the system level, this non-determinism arises from floating-point non-associativity combined…
POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference
Aditya K Kamath, Ramya Prabhu, Jayashree Mohan +3
Each request in LLM inference goes through two phases: compute-bound prefill and memory-bandwidth-bound decode. To improve GPU utilization, recent systems use hybrid batching that…
LLeMpower: Understanding Disparities in the Control and Access of Large Language Models
Vishwas Sathish, Hannah Lin, Aditya K Kamath +1
Large Language Models (LLMs) are a powerful technology that augment human skill to create new opportunities, akin to the development of steam engines and the internet. However, LLM…
Herding LLaMaS: Using LLMs as an OS Module
Aditya K Kamath, Sujay Yadalam
Computer systems are becoming increasingly heterogeneous with the emergence of new memory technologies and compute devices. GPUs alongside CPUs have become commonplace and CXL is p…
MaxMem: Colocation and Performance for Big Data Applications on Tiered Main Memory Servers
Amanda Raybuck, Wei Zhang, Kayvan Mansoorshahi +3
We present MaxMem, a tiered main memory management system that aims to maximize Big Data application colocation and performance. MaxMem uses an application-agnostic and lightweight…
Storage Class Memory: Principles, Problems, and Possibilities
Aditya K Kamath, Leslie Monis, A Tarun Karthik +1
Storage Class Memory (SCM) is a class of memory technology which has recently become viable for use. Their namearises from the fact that they exhibit non-volatility of data, simila…