國立虎尾科技大學 |

Architectural-Aware Performance Optimization : = From the Foundational Math Library to Cutting-Edge Applications.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Architectural-Aware Performance Optimization :/
Reminder of title:	From the Foundational Math Library to Cutting-Edge Applications.
Author:	Zhai, Yujia.
Description:	1 online resource (170 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-01, Section: B.
Contained By:	Dissertations Abstracts International85-01B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9798379953157

Architectural-Aware Performance Optimization : = From the Foundational Math Library to Cutting-Edge Applications.
Zhai, Yujia.

Architectural-Aware Performance Optimization :From the Foundational Math Library to Cutting-Edge Applications. - 1 online resource (170 pages)

Source: Dissertations Abstracts International, Volume: 85-01, Section: B.

Thesis (Ph.D.)--University of California, Riverside, 2023.

Includes bibliographical references

Efficient performance is essential for deploying a system in the real world. This thesis presents techniques for optimizing performance with an awareness of architecture for applications ranging from foundational math libraries, such as Basic Linear Algebra Subprograms (BLAS), to cutting-edge applications like homomorphic encryption (HE) and deep learning (DL) inference for the transformer model.First, we introduce FT-BLAS, a new implementation of BLAS that offers high reliability and superior performance compared to other libraries, including Intel MKL, OpenBLAS, and BLIS. FT-BLAS is capable of tolerating soft errors on-the-fly, making it more robust than other libraries. The experimental results of FT-BLAS on Intel Skylake, Intel Cascade Lake, and AMD Zen2 processors demonstrate its high performance, being up to 3.50%, 22.14%, and 21.70% faster than Intel MKL, OpenBLAS, and BLIS, respectively.We then present XeHE, a HE library accelerated for Intel GPUs. Our staged optimizations, including low-level optimizations and kernel fusion, accelerate the Number Theoretic Transform (NTT), a fundamental algorithm for HE, by up to 9.93X compared to the naive GPU baseline. Our optimized NTT reaches 79.8% and 85.7% of the peak performance on two GPU devices, and our systematic optimizations improve the performance of encrypted element-wise polynomial matrix multiplication applications by up to 3.11X.Finally, we present ByteTransformer, an industrial transformer framework optimized for variable-length inputs. ByteTransformer has been deployed to serve TikTok and Douyin applications of ByteDance, and part of our proposed optimizations has been integrated into the production code base of NVIDIA. Experimental results on an NVIDIA A100 GPU with variable-length sequence inputs validate that our fused MHA outperforms the standard PyTorch MHA by 6.13x. ByteTransformer's end-to-end performance for a standard BERT Transformer model surpasses state-of-the-art transformer frameworks, such as PyTorch JIT, TensorFlow XLA, Tencent TurboTransformer, Microsoft DeepSpeed-Inference, and NVIDIA FasterTransformer, by 87%, 131%, 138%, 74%, and 55%, respectively. We also demonstrate the general applicability of our optimization methods to other BERT-like models, including ALBERT, DistilBERT, and DeBERTa.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798379953157Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

PerformanceIndex Terms--Genre/Form:

554714
Electronic books.

Architectural-Aware Performance Optimization : = From the Foundational Math Library to Cutting-Edge Applications.
LDR:03724ntm a22003977 4500 001 1146389
005 20240812064603.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379953157
035 $a (MiAaPQ)AAI30489951
035 $a AAI30489951
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Zhai, Yujia. $3 1471773
245 1 0 $a Architectural-Aware Performance Optimization : $b From the Foundational Math Library to Cutting-Edge Applications.
264 0 $c 2023
300 $a 1 online resource (170 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-01, Section: B.
500 $a Advisor: Chen, Zizhong.
502 $a Thesis (Ph.D.)--University of California, Riverside, 2023.
504 $a Includes bibliographical references
520 $a Efficient performance is essential for deploying a system in the real world. This thesis presents techniques for optimizing performance with an awareness of architecture for applications ranging from foundational math libraries, such as Basic Linear Algebra Subprograms (BLAS), to cutting-edge applications like homomorphic encryption (HE) and deep learning (DL) inference for the transformer model.First, we introduce FT-BLAS, a new implementation of BLAS that offers high reliability and superior performance compared to other libraries, including Intel MKL, OpenBLAS, and BLIS. FT-BLAS is capable of tolerating soft errors on-the-fly, making it more robust than other libraries. The experimental results of FT-BLAS on Intel Skylake, Intel Cascade Lake, and AMD Zen2 processors demonstrate its high performance, being up to 3.50%, 22.14%, and 21.70% faster than Intel MKL, OpenBLAS, and BLIS, respectively.We then present XeHE, a HE library accelerated for Intel GPUs. Our staged optimizations, including low-level optimizations and kernel fusion, accelerate the Number Theoretic Transform (NTT), a fundamental algorithm for HE, by up to 9.93X compared to the naive GPU baseline. Our optimized NTT reaches 79.8% and 85.7% of the peak performance on two GPU devices, and our systematic optimizations improve the performance of encrypted element-wise polynomial matrix multiplication applications by up to 3.11X.Finally, we present ByteTransformer, an industrial transformer framework optimized for variable-length inputs. ByteTransformer has been deployed to serve TikTok and Douyin applications of ByteDance, and part of our proposed optimizations has been integrated into the production code base of NVIDIA. Experimental results on an NVIDIA A100 GPU with variable-length sequence inputs validate that our fused MHA outperforms the standard PyTorch MHA by 6.13x. ByteTransformer's end-to-end performance for a standard BERT Transformer model surpasses state-of-the-art transformer frameworks, such as PyTorch JIT, TensorFlow XLA, Tencent TurboTransformer, Microsoft DeepSpeed-Inference, and NVIDIA FasterTransformer, by 87%, 131%, 138%, 74%, and 55%, respectively. We also demonstrate the general applicability of our optimization methods to other BERT-like models, including ALBERT, DistilBERT, and DeBERTa.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Computer engineering. $3 569006
650 4 $a Information technology. $3 559429
653 $a Performance
653 $a Optimizations
653 $a Math library
653 $a Homomorphic encryption
653 $a Deep learning
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0489
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Riverside. $b Computer Science. $3 1195526
773 0 $t Dissertations Abstracts International $g 85-01B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30489951 $z click for full text (PQDT)