Presentation
MALIWAN: Performance and Energy Efficiency Co-Optimization of GEMM on Versal ACAP Architectures
DescriptionGeneral Matrix Multiplication (GEMM) is a fundamental kernel in scientific computing and deep learning and often dominates both performance and energy consumption, particularly in edge deployments with strict power and resource constraints. AMD's Versal ACAP offers heterogeneous components (AIEs, PL, PS) that can address these challenges, but identifying efficient mappings across these units is challenging, with prior work largely overlooking power-performance trade-offs. We introduce MALIWAN, an automated framework that generates Pareto-optimal GEMM mappings on Versal ACAP devices. MALIWAN combines fast analytical-model–based sampling with data-driven ML, using on-board measurements to train a surrogate that drives large-scale Design Space Exploration. Based on a collection of ≈6,000 on-board experiments, we first provide a comprehensive analysis of how different mapping configurations affect performance and power. We then evaluate MALIWAN on the Versal VCK190, demonstrating geomean improvements of 1.23× (up to 2.5×) in throughput and 1.25× (up to 2.7×) in energy efficiency over state-of-the-art works. Compared to NVIDIA GPUs, MALIWAN achieves up to 2.5× energy efficiency
Event Type
Research Manuscript
TimeMonday, July 271:42pm - 1:55pm PDT
LocationMtg Room 203C
Similar Presentations