Auto-tuning 3-D FFT library for CUDA GPUs

Existing implementations of FFTs on GPUs are optimized for specific transform sizes like powers of two, and exhibit unstable and peaky performance i.e., do not perform as well in other sizes that appear in practice. Our new auto-tuning 3-D FFT on CUDA generates high performance CUDA kernels for FFTs...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis s. 1 - 10
Hlavní autoři:	Nukada, Akira, Matsuoka, Satoshi
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	New York, NY, USA ACM 14.11.2009
Edice:	ACM Conferences
Témata:	Bandwidth Codes Computing methodologies > Computer graphics > Graphics systems and interfaces > Graphics processors Graphics processing units Hardware Instruction sets Kernel Mathematics of computing > Mathematical analysis > Functional analysis > Approximation Mathematics of computing > Mathematical analysis > Numerical analysis > Computation of transforms Mathematics of computing > Mathematical software Programming Registers Theory of computation > Design and analysis of algorithms > Approximation algorithms analysis Three-dimensional displays Transforms
ISBN:	1605587443, 9781605587448
ISSN:	2167-4329
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!