Padding Free Bank Conflict Resolution for CUDA-Based Matrix Transpose Algorithm

The advances of Graphic Processing Units (GPU) technology and the introduction of CUDA programming model facilitates developing new solutions for sparse and dense linear algebra solvers. Matrix Transpose is an important linear algebra procedure that has deep impact in various computational science a...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The International journal of networked and distributed computing (Online) Ročník 2; číslo 3; s. 124 - 134
Hlavní autoři: Khan, Ayaz ul Hassan, Al-Mouhamed, Mayez, Fatayer, Allam, Almousa, Anas, Baqais, Abdulrahman, Assayony, Mohammed
Médium: Journal Article
Jazyk:angličtina
Vydáno: Dordrecht Springer Netherlands 01.01.2014
Springer
Témata:
Bank conflict free
coalesced memory access
CUDA
GPU
linear Algebra solvers
matrix transpose
Research Article
CUDA
solving system of linear equations
Bank conflict free
coalesced memory access
matrix transpose
linear Algebra solvers
GPU
ISSN:2211-7938, 2211-7946, 2211-7946
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The advances of Graphic Processing Units (GPU) technology and the introduction of CUDA programming model facilitates developing new solutions for sparse and dense linear algebra solvers. Matrix Transpose is an important linear algebra procedure that has deep impact in various computational science and engineering applications. Several factors hinder the expected performance of large matrix transpose on GPU devices. The degradation in performance involves the memory access pattern such as coalesced access in the global memory and bank conflict in the shared memory of streaming multiprocessors within the GPU. In this paper, two matrix transpose algorithms are proposed to alleviate the aforementioned issues of ensuring coalesced access and conflict free bank access. The proposed algorithms have comparable execution times with the NVIDIA SDK bank conflict - free matrix transpose implementation. The main advantage of proposed algorithms is that they eliminate bank conflicts while allocating shared memory exactly equal to the tile size (T x T) of the problem space. However, to the best of our knowledge an extra space of Tx(T+1) needs to be allocated in the published research. We have also applied the proposed transpose algorithm to recursive gaussian implementation of NVIDIA SDK and achieved about 6% improvement in performance.
ISSN:2211-7938
2211-7946
2211-7946
DOI:10.2991/ijndc.2014.2.3.2