Delite: A Compiler Architecture for Performance-Oriented Embedded Domain-Specific Languages

Developing high-performance software is a difficult task that requires the use of low-level, architecture-specific programming models (e.g., OpenMP for CMPs, CUDA for GPUs, MPI for clusters). It is typically not possible to write a single application that can run efficiently in different environments, leading to multiple versions and increased complexity. Domain-Specific Languages (DSLs) are a promising avenue to enable programmers to use high-level abstractions and still achieve good performance on a variety of hardware. This is possible because DSLs have higher-level semantics and restrictions than general-purpose languages, so DSL compilers can perform higher-level optimization and translation. However, the cost of developing performance-oriented DSLs is a substantial roadblock to their development and adoption. In this article, we present an overview of the Delite compiler framework and the DSLs that have been developed with it. Delite simplifies the process of DSL development by providing common components, like parallel patterns, optimizations, and code generators, that can be reused in DSL implementations. Delite DSLs are embedded in Scala, a general-purpose programming language, but use metaprogramming to construct an Intermediate Representation (IR) of user programs and compile to multiple languages (including C++, CUDA, and OpenCL). DSL programs are automatically parallelized and different parts of the application can run simultaneously on CPUs and GPUs. We present Delite DSLs for machine learning, data querying, graph analysis, and scientific computing and show that they all achieve performance competitive to or exceeding C++ code.

Lightweight Modular Staging and Embedded Compilers

Tiark Rompf

Programs expressed in a high-level programming language need to be translated to a low-level machine dialect for execution. This translation is usually accomplished by a compiler, which is able to translate any legal program to equivalent low-level code. But for individual source programs, automatic translation does not always deliver good results: Software engineering practice demands generalization and abstraction, whereas high performance demands specialization and concretization. These goals are at odds, and compilers can only rarely translate expressive high-level programs tomodern hardware platforms in a way that makes best use of the available resources. Explicit program generation is a promising alternative to fully automatic translation. Instead of writing down the program and relying on a compiler for translation, developers write a program generator, which produces a specialized, efficient, low-level program as its output. However, developing high-quality program generators requires a very large effort that is often hard to amortize. In this thesis, we propose a hybrid design: Integrate compilers into programs so that programs can take control of the translation process, but rely on libraries of common compiler functionality for help. We present Lightweight Modular Staging (LMS), a generative programming approach that lowers the development effort significantly. LMS combines program generator logic with the generated code in a single program, using only types to distinguish the two stages of execution. Through extensive use of component technology, LMS makes a reusable and extensible compiler framework available at the library level, allowing programmers to tightly integrate domain-specific abstractions and optimizations into the generation process, with common generic optimizations provided by the framework. Compared to previous work on programgeneration, a key aspect of our design is the use of staging not only as a front-end, but also as a way to implement internal compiler passes and optimizations, many of which can be combined into powerful joint simplification passes. LMS is well suited to develop embedded domain specific languages (DSLs) and has been used to develop powerful performance-oriented DSLs for demanding domains such as machine learning, with code generation for heterogeneous platforms including GPUs. LMS has also been used to generate SQL for embedded database queries and JavaScript for web applications.

EPFL2012

Lightweight Modular Staging: A Pragmatic Approach to Runtime Code Generation and Compiled DSLs

Martin Odersky, Tiark Rompf

Good software engineering practice demands generalization and abstraction, whereas high performance demands specialization and concretization. These goals are at odds, and compilers can only rarely translate expressive high-level programs to modern hardware platforms in a way that makes best use of the available resources. Generative programming is a promising alternative to fully automatic translation. Instead of writing down the target program directly, developers write a program generator, which produces the target program as its output. The generator can be written in a high-level, generic style and still produce efficient, specialized target programs. In practice, however, developing high-quality program generators requires a very large effort that is often hard to amortize. We present Lightweight Modular Staging (LMS), a generative programming approach that lowers this effort significantly. LMS seamlessly combines program generator logic with the generated code in a single program, using only types to distinguish the two stages of execution. Through extensive use of component technology, LMS makes a reusable and extensible compiler framework available at the library level, allowing programmers to tightly integrate domain-specific abstractions and optimizations into the generation process, with common generic optimizations provided by the framework. LMS is well suited to develop embedded domain specific languages (DSLs) and has been used to develop powerful performance-oriented DSLs for demanding domains such as machine learning, with code generation for heterogeneous platforms including GPUs. LMS has also been used to generate SQL for embedded database queries and JavaScript for web applications.

2012

Better Loop Fusion for LMS

Véra Salvisberg

This is my master thesis done at PPL in Stanford under the supervision of Prof. Kunle Olukotun. It improved LMS, a framework for embedding DSLs (domain-specific languages) into Scala which features many general optimizations that can be used by any DSLs for free. I implemented a more powerful and cleaner version of the loop fusion optimization from the compiler world. Loop fusion is an important performance optimization for all languages that feature list comprehensions and translate their high-level operations into loop-based representations. It can decrease runtime, memory footprint and code size through two different fusion cases: The simpler one is called horizontal or side-by-side fusion and fuses adjacent loops iterating over the same range, enabling further optimizations. The second one is vertical or pipeline fusion, where a producer and a consumer of data are fused, removing the need for the intermediate data structure.

2014

Lightweight Modular Staging and Embedded Compilers

Tiark Rompf

EPFL2012