Acceleration Opportunities in Linear Algebra Applications via Idiom Recognition

Autor(es)

de Carvalho, Joao P. L. ; Kuzma, Braedy ; Araujo, Guido ; Assoc Comp Machinery

• Tipo de documento: Artigo Científico
• Fonte: ICPE'20: COMPANION OF THE ACM/SPEC INTERNATIONAL CONFERENCE ON PERFORMANCE ENGINEERING; v. N/A, p. 2-pg., 2020-01-01.

Resumo

General matrix-matrix multiplication (GEMM) is a critical operation in many application domains [1]. It is a central building block of deep learning and computer graphics algorithms and is also a core operation for most scientific applications based on the discretization of systems of differential equations. Due to this, GEMM has been extensively studied and optimized, resulting in libraries of exceptional quality such as BLAS, Eigen, and other platform specific implementations such as MKL (Intel's x86) and ESSL (IBM's PowerPC) [3, 5]. Despite these successes, the GEMM idiom continues to be reimplemented by programmers without consideration for the intricacies already accounted for by the aforementioned libraries. To this end, this project aims to provide transparent adoption of high-performance implementations of GEMM through a novel optimization pass implemented within the LLVM framework using idiom recognition techniques. (AU)

• Processo FAPESP: 13/08293-7 - CECC - Centro de Engenharia e Ciências Computacionais
• Beneficiário: Munir Salomao Skaf
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
• Processo FAPESP: 16/15337-9 - Memória Transacional Distribuída e Modelos Eficientes de Distribuição de Dados para Acelerar Aplicações com Estruturas de Dados Irregulares.
• Beneficiário: João Paulo Labegalini de Carvalho
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 19/01110-0 - Análise de código para identificação de construções afins à primitivas de hardware
• Beneficiário: João Paulo Labegalini de Carvalho
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado