Data layout oriented compilation techniques in vectorization for multi-/many-cores Article Swipe

MAKE IMPACT

Shixiong Xu · YOU? · · 2017 · Open Access ·

Single instruction, multiple data (SIMD) architectures are widely adopted in both general-purpose processors and graphic processing units for exploiting data-level parallelism. It is tedious and error-prone for programmers to write high performance code to utilize SIMD execution units on both platforms. Therefore, users often rely on automatic code generation techniques in compilers. However, it is not trivial for compilers to generate high performance code without considering the data layout of the data used in the computation. Data layout determines data access patterns, and in turn have a great impact on the memory performance of the automatically generated code for both CPUs and GPUs.\nIn this thesis, we demonstrate several data layout oriented compilation techniques for efficient vectorization. We put forward semi-automatic data layout transformation to help users to easily change their program, and exploit the best possible data layout in terms of vectorization. Our proposed vectorization based on hyper loop parallelism provides a way to take advantage the relationship between data layout and computation structure. The experimental results demonstrated that this vectorization technique can yield significant performance gain. In addition, we show that this technique is of great use to boost the memory performance on CUDA GPUs.\nWe also present pioneering work that uses loop vectorization techniques to handle nested thread-level parallelism (TLP) on CUDA GPUs. As loop vectorization prioritizes vectorizing loops with contiguous data accesses, it is of great help to achieve an efficient mapping strategy for nested TLP on CUDA GPUs.\nOur new bitslice vector computing for customizable arithmetic precision on general-purpose processors with SIMD extensions not only breaks the limit of hardware arithmetic precision but also achieves great performance. It also shows the great power of logic optimization widely used in hardware synthesis in optimizing C/C++ code with a large amount of logic operations.

Type

dissertation

Language

en

Landing Page

http://hdl.handle.net/2262/81727

PDF

http://hdl.handle.net/2262/81727

OA Status

gold

References

84

Related Works

20

OpenAlex ID

https://openalex.org/W2753037357

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W2753037357

Canonical identifier for this work in OpenAlex

Title

Data layout oriented compilation techniques in vectorization for multi-/many-cores

Work title

Type

dissertation

OpenAlex work type

Language

en

Primary language

Publication year

2017

Year of publication

Publication date

2017-01-01

Full publication date if available

Authors

Shixiong Xu

List of authors in order

Landing page

https://hdl.handle.net/2262/81727

Publisher landing page

PDF URL

https://hdl.handle.net/2262/81727

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

gold

Open access status per OpenAlex

OA URL

https://hdl.handle.net/2262/81727

Direct OA link when available

Concepts

Vectorization (mathematics), Computer science, Parallel computing, Programming language

Top concepts (fields/topics) attached by OpenAlex

Cited by

0

Total citation count in OpenAlex

References (count)

84

Number of works referenced by this work

Related works (count)

20

Other works algorithmically related by OpenAlex

Full payload