SPADE: A Flexible and Scalable Accelerator for SpMM and SDDMM
Gerasimos Gerogiannis, Şerif Yeşil, Damitha Lenadora, Dingyuan Cao, Charith Mendis, Josep Torrellas
Abstract
The widespread use of Sparse Matrix Dense Matrix Multiplication (SpMM) and Sampled Dense Matrix Dense Matrix Multiplication (SDDMM) kernels makes them candidates for hardware acceleration. However, accelerator design for these kernels faces two main challenges: (1) the overhead of moving data between CPU and accelerator (often including an address space conversion from the CPU's virtual addresses) and (2) marginal flexibility to leverage the fact that different sparse input matrices benefit from different variations of the SpMM and SDDMM algorithms.
Topics & Concepts
Computer scienceMatrix multiplicationScalabilitySparse matrixLeverage (statistics)AccelerationHardware accelerationParallel computingComputational scienceComputer hardwareOperating systemField-programmable gate arrayArtificial intelligencePhysicsQuantumGaussianQuantum mechanicsClassical mechanicsParallel Computing and Optimization TechniquesAdvanced Data Storage TechnologiesInterconnection Networks and Systems