東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Dynamically Finding Optimal Kernel L...

Jeshani, Taabish.

Linked to FindBook

Google Book

Amazon

博客來

Dynamically Finding Optimal Kernel Launch Parameters for CUDA Programs.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Dynamically Finding Optimal Kernel Launch Parameters for CUDA Programs./
Author:	Jeshani, Taabish.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
Description:	67 p.
Notes:	Source: Masters Abstracts International, Volume: 85-01.
Contained By:	Masters Abstracts International85-01.
Subject:	Problem solving. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30537966
ISBN:	9798379872571

Dynamically Finding Optimal Kernel Launch Parameters for CUDA Programs.
Jeshani, Taabish.

Dynamically Finding Optimal Kernel Launch Parameters for CUDA Programs. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 67 p.

Source: Masters Abstracts International, Volume: 85-01.

Thesis (M.Sc.)--The University of Western Ontario (Canada), 2023.

This item must not be sold to any third party vendors.

In this thesis, we present KLARAPTOR (Kernel LAunch parameters RAtional Program estimaTOR), a freely available tool to dynamically determine the values of kernel launch parameters of a CUDA kernel. We describe a technique for building a helper program, at the compile-time of a CUDA program, that is used at run-time to determine near-optimal kernel launch parameters for the kernels of that CUDA program. This technique leverages the MWP-CWP performance prediction model, runtime data parameters, and runtime hardware parameters to dynamically determine the launch parameters for each kernel invocation. This technique is implemented within the KLARAPTOR tool, utilizing the LLVM Pass Framework and NVIDIA Nsight Compute CLI profiler. We demonstrate the effectiveness of our approach through experimentation on the PolyBench benchmark suite of CUDA kernels.

ISBN: 9798379872571Subjects--Topical Terms:

516855
Problem solving.

Dynamically Finding Optimal Kernel Launch Parameters for CUDA Programs.
LDR:01931nmm a2200337 4500 001 2395527
005 20240517104614.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798379872571
035 $a (MiAaPQ)AAI30537966
035 $a (MiAaPQ)oaiirlibuwocaetd12031
035 $a AAI30537966
040 $a MiAaPQ $c MiAaPQ
100 1 $a Jeshani, Taabish. $3 3765035
245 1 0 $a Dynamically Finding Optimal Kernel Launch Parameters for CUDA Programs.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 67 p.
500 $a Source: Masters Abstracts International, Volume: 85-01.
500 $a Advisor: Maza, Marc Moreno.
502 $a Thesis (M.Sc.)--The University of Western Ontario (Canada), 2023.
506 $a This item must not be sold to any third party vendors.
520 $a In this thesis, we present KLARAPTOR (Kernel LAunch parameters RAtional Program estimaTOR), a freely available tool to dynamically determine the values of kernel launch parameters of a CUDA kernel. We describe a technique for building a helper program, at the compile-time of a CUDA program, that is used at run-time to determine near-optimal kernel launch parameters for the kernels of that CUDA program. This technique leverages the MWP-CWP performance prediction model, runtime data parameters, and runtime hardware parameters to dynamically determine the launch parameters for each kernel invocation. This technique is implemented within the KLARAPTOR tool, utilizing the LLVM Pass Framework and NVIDIA Nsight Compute CLI profiler. We demonstrate the effectiveness of our approach through experimentation on the PolyBench benchmark suite of CUDA kernels.
590 $a School code: 0784.
650 4 $a Problem solving. $3 516855
650 4 $a Data processing. $3 680224
650 4 $a Transistors. $3 713271
650 4 $a Data exchange. $3 3685752
650 4 $a Programmers. $3 3765036
650 4 $a Statistics. $3 517247
690 $a 0800
690 $a 0463
710 2 $a The University of Western Ontario (Canada). $3 1017622
773 0 $t Masters Abstracts International $g 85-01.
790 $a 0784
791 $a M.Sc.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30537966