Layout-oblivious compiler optimization for matrix computations
ACM Transactions on Architecture and Code Optimization (TACO) - Special Issue on High-Performance Embedded Architectures and Compilers
On the determination of inlining vectors for program optimization
CC'13 Proceedings of the 22nd international conference on Compiler Construction
The Cetus Source-to-Source Compiler Infrastructure: Overview and Evaluation
International Journal of Parallel Programming
Hi-index | 0.00 |
The emergence of multi-core architectures makes it essential for optimizing compilers to automatically extract parallelism for large scienti脙"脗篓脙聟c applications composed of many subroutines residing in different 脙"脗篓脙聟les. In lining is a well-known technique which can be used to erase procedural boundaries and enable more aggressive loop parallelization. However, conventional in lining cannot be applied to external libraries where the source code is not available, and when overly applied, it can degrade the effectiveness of compiler optimizations due to excessive code complexity. This paper highlights some obstacles we encountered while applying conventional in lining combined with automatic loop parallelization using the Polaris optimizing compiler and presents a new approach, annotation-based in lining, to effectively overcome these obstacles. Our experimental results show that the annotation-based in lining approach can eliminate negative impact of conventional in lining while enhancing the effectiveness of interprocedural parallelization for a majority of applications from the PERFECT benchmark suite.