11 citations · 11 across the 7 of their papers we have counts for
7 papers
DataKernelBench: Can LLMs Optimize Database Queries on GPUs?
Gokul Karthik Kumar, Yotam Perlitz, Corey Lammie +2
GPUs increasingly accelerate database systems, but query-specific peak performance still often relies on hand-written kernels. Existing LLM kernel benchmarks focus on machine learn…
On Design Principles for Efficient Heterogeneous DRAM-PIM-GPU Systems
Corey Lammie, Hadjer Benmeziane, William Andrew Simon +1
Heterogeneous DRAM-based processing-in-memory (PIM)-GPU systems promise significant efficiency gains for decode-phase large language model (LLM) inference, particularly in long-out…
Heterogeneous Mapping for Analog In-Memory Computing Accelerators: A Unified Workflow
Corey Lammie
Analog In-Memory Computing (AIMC) accelerators execute matrix-vector multiplications directly within memory arrays, reducing data movement and improving DNN inference efficiency. T…
Assessing the Performance of Analog Training for Transfer Learning
Omobayode Fagbohungbe, Corey Lammie, Malte J. Rasch +3
Analog in-memory computing is a next-generation computing paradigm that promises fast, parallel, and energy-efficient deep learning training and transfer learning (TL). However, ac…
The Inherent Adversarial Robustness of Analog In-Memory Computing
Corey Lammie, Julian Büchel, Athanasios Vasilopoulos +2
A key challenge for Deep Neural Network (DNN) algorithms is their vulnerability to adversarial attacks. Inherently non-deterministic compute substrates, such as those based on Anal…
Kernel Approximation using Analog In-Memory Computing
Julian Büchel, Giacomo Camposampiero, Athanasios Vasilopoulos +4
Kernel functions are vital ingredients of several machine learning algorithms, but often incur significant memory and computational costs. We introduce an approach to kernel approx…
Efficient transformer adaptation for analog in-memory computing via low-rank adapters
Chen Li, Elena Ferro, Corey Lammie +3
Analog In-Memory Computing (AIMC) offers a promising solution to the von Neumann bottleneck. However, deploying transformer models on AIMC remains challenging due to their inherent…