2

MOST: Memory Oversubscription-Aware Scheduling for Tensor Migration on GPU Unified Storage
Deep Neural Network (DNN) training demands large memory capacities that exceed the limits of current GPU onboard memory. Expanding GPU …
PDF Cite Project Project DOI
MOST: Memory Oversubscription-Aware Scheduling for Tensor Migration on GPU Unified Storage
Beyond VABlock: Improving Transformer Workloads through Aggressive Prefetching
The memory capacity constraint of GPUs is a major challenge in running large deep learning workloads with their ever increasing memory …
PDF Cite Project Project DOI
Beyond VABlock: Improving Transformer Workloads through Aggressive Prefetching
SAVector: Vectored Systolic Arrays
Conventional DNN inference accelerators are designed with a few (up to four) large systolic arrays. As such a scale-up architecture …
PDF Cite Project DOI
SAVector: Vectored Systolic Arrays
Conflict-Aware Compiler for Hierarchical Register File on GPUs
Modern graphics processing units (GPUs) leverage a high degree of thread-level parallelism, necessitating large-sized register files …
PDF Cite Project DOI
Conflict-Aware Compiler for Hierarchical Register File on GPUs
Adaptive Kernel Merge and Fusion for Multi-Tenant Inference in Embedded GPUs
This paper proposes a new scheme that improves throughput and reduces queuing delay while running multiple inferences in embedded …
PDF Cite Project DOI
Adaptive Kernel Merge and Fusion for Multi-Tenant Inference in Embedded GPUs
Vizard: Passing over Profiling-Based Detection by Manipulating Performance Counters
Cache side-channel attacks have been serious security threats to server computer systems, thus researchers have proposed software-based …
PDF Cite Project DOI
Vizard: Passing over Profiling-Based Detection by Manipulating Performance Counters
Analyzing GCN Aggregation on GPU
Graph convolutional neural networks (GCNs) are emerging neural networks for graph structures that include large features associated …
PDF Cite Project Project DOI
Analyzing GCN Aggregation on GPU
GhostLeg: Selective Memory Coalescing for Secure GPU Architecture
Architectural considerations for secure executions are getting more critical for GPU since popular security applications and libraries …
PDF Cite Project Project DOI
GhostLeg: Selective Memory Coalescing for Secure GPU Architecture
FLIXR: Embedding Index into Flash Translation Layer in SSDs
Flash memory technologies rely on the flash translation layer (FTL) to manage no in-place update and garbage collection. Current FTL …
PDF Cite Project DOI
FLIXR: Embedding Index into Flash Translation Layer in SSDs
RT-Sniper: A Low-Overhead Defense Mechanism Pinpointing Cache Side-Channel Attacks
Since cache side-channel attacks have been serious security threats to multi-tenant systems, there have been several studies to protect …
PDF Cite Project DOI
RT-Sniper: A Low-Overhead Defense Mechanism Pinpointing Cache Side-Channel Attacks