CCES Unicamp

KernelFaRer: Replacing Native-Code Idioms with High-Performance Library Calls

Well-crafted libraries deliver much higher performance than code generated by sophisticated application programmers using advanced optimizing compilers. When a code pattern for which a well-tuned library implementation exists is found in the source code of an application, the highest performing solution is to replace the pattern with a call to the library. Idiom-recognition solutions in the past either required pattern matching machinery that was outside of the compilation framework or provided a very brittle solution that would fail even for minor variants in the pattern source code. This article introduces Kernel Find & Replacer (KernelFaRer), an idiom recognizer implemented entirely in the existing LLVM compiler framework. The versatility of KernelFaRer is demonstrated by matching and replacing two linear algebra idioms, general matrix-matrix multiplication (GEMM), and symmetric rank-2k update (SYR2K). Both GEMM and SYR2K are used extensively in scientific computation, and GEMM is also a central building block for deep learning and computer graphics algorithms. The idiom recognition in KernelFaRer is much more robust than alternative solutions, has a much lower compilation overhead, and is fully integrated in the broadly used LLVM compilation tools. KernelFaRer replaces existing GEMM and SYR2K idioms with computations performed by BLAS, Eigen, MKL (Intel’s x86), ESSL (IBM’s PowerPC), and BLIS (AMD). Gains in performance that reach 2000× over hand-crafted source code compiled at the highest optimization level demonstrate that replacing application code with library call is a performant solution.

João P. L. De Carvalho, Braedy Kuzma, Ivan Korostelev, José Nelson Amaral, Christopher Barton, José Moreira, and Guido Araujo. 2021. KernelFaRer: Replacing Native-Code Idioms with High-Performance Library Calls. ACM Trans. Archit. Code Optim. 18, 3, Article 38 (June 2021), 22 pages, DOI:



Related posts

Meet the hematene, the “iron graphene”, promising for solar energy generation


CCES stories: Hervé Yviquel

Leandro Martinez

Accelerating Graph Applications Using Phased Transactional Memory

cces cces
WP Twitter Auto Publish Powered By :