Results 71 to 80 of about 62,963 (220)

A Simple Cache Emulator for Evaluating Cache Behavior for SMP Systems

Acta Polytechnica, 2006
Every modern CPU uses a complex memory hierarchy, which consists of multiple cache memory levels. It is very difficult to predict the behavior of this hierarchy for a given program (for details see [1, 2]).
I. Šimeček
doaj  

DeepPicar: A Low-cost Deep Neural Network-based Autonomous Car

, 2018
We present DeepPicar, a low-cost deep neural network based autonomous car platform. DeepPicar is a small scale replication of a real self-driving car called DAVE-2 by NVIDIA.
Bechtel, Michael G., Kim, Minje, McEllhiney, Elise, Yun, Heechul   +3 more
core   +1 more source

Fused Collapsing for Wide BVH Construction

Computer Graphics Forum, EarlyView.
Abstract We propose a novel approach for constructing wide bounding volume hierarchies on the GPU by integrating a simple bottom‐up collapsing procedure within an existing binary bottom‐up BVH builder. Our approach directly constructs a wide BVH without traversing a temporary binary BVH as done by previous approaches and achieves 1.4 – 1.6 × lower ...
Wilhem Barbier, Mathias Paulin
wiley   +1 more source

Forecasting the cost of processing multi-join queries via hashing for main-memory databases (Extended version)

, 2015
Database management systems (DBMSs) carefully optimize complex multi-join queries to avoid expensive disk I/O. As servers today feature tens or hundreds of gigabytes of RAM, a significant fraction of many analytic databases becomes memory-resident.
Ailamaki A., Boncz P. A., Boncz P. A., Chen M.-S., Chen M.-S., DeWitt D. J., Lang H., Li Y., Liu B., Lohman G. M., Lu H., Manegold S., Ono K., Schneider D. A., Shatdal A., Stillger M., Zhang N.   +16 more
core   +1 more source

Encoding Occupancy in Memory Location for Efficient and Compact High‐Resolution Voxel Structures

Computer Graphics Forum, EarlyView.
We encode information about geometric structure into the pointers of a sparse voxel directed acyclic graph (SVDAG). Each pointer carries information about the structure of the node it points to. Our encoding improves ray tracing performance and reduces model size in memory.
Jaina Modisett, Markus Billeter
wiley   +1 more source

GEMM-ArchProfiler: A simulation framework for hardware-level profiling and performance analysis of General Matrix Multiplication in real CNN workloads on heterogeneous CPU architectures

SoftwareX
In this paper, the authors present GEMM-ArchProfiler, a simulation framework for evaluating General Matrix Multiplication performance in convolutional neural networks.
Binu Ayyappan, G. Santhosh Kumar
doaj   +1 more source

Mepylome: A Point‐of‐Care Tumor Diagnostic Toolkit for Tumor DNA Methylation and Copy Number Analysis

Advanced Intelligent Systems, Volume 8, Issue 3, March 2026.
DNA methylation and chromosomal copy number profiling have recently become essential for tumor diagnostics. The open‐source tool Mepylome enables this task in clinical routine. It combines several machine learning strategies and allows users to interactively examine respective data through an intuitive graphical interface. Running up to 65 times faster
Jon Brugger, Claus Hultschig, Daniel Baumhoer, Baptiste Ameline, Benjamin Maciej Freyter, Stephan Frank, Jürgen Hench   +6 more
wiley   +1 more source

Hardware-Accelerated Platforms and Infrastructures for Network Functions: A Survey of Enabling Technologies and Research Studies

IEEE Access, 2020
In order to facilitate flexible network service virtualization and migration, network functions (NFs) are increasingly executed by software modules as so-called “softwarized NFs” on General-Purpose Computing (GPC) platforms and ...
Prateek Shantharama, Akhilesh S. Thyagaturu, Martin Reisslein   +2 more
doaj   +1 more source

CPU and cache efficient management of memory-resident databases [PDF]

2013 IEEE 29th International Conference on Data Engineering (ICDE), 2013
Memory-Resident Database Management Systems (MRDBMS) have to be optimized for two resources: CPU cycles and memory bandwidth. To optimize for bandwidth in mixed OLTP/OLAP scenarios, the hybrid or Partially Decomposed Storage Model (PDSM) has been proposed.
Pirk, H., Funke, F., Grund, M., Neumann, T., Leser, U., Manegold, S., Kemper, A., Kersten, M.L.   +7 more
openaire   +3 more sources

Efficient Scheduling Algorithms for Multicore Cyclic Executives With Precedence and Exclusion Relations

Concurrency and Computation: Practice and Experience, Volume 38, Issue 5, March 2026.
ABSTRACT Cyclic executives (CEs) offer the advantage of ensuring complete determinism with minimal runtime overhead, often making them the preferred choice for safety‐critical real‐time systems. However, generating CEs for multicore processors while addressing task precedence and exclusion relations presents significant challenges.
Bruno Nogueira, Alfredo Lima, Eduardo Tavares, Rodrigo Paes, Francisco Airton Silva   +4 more
wiley   +1 more source