Tackling the challenges of high-performance graph analytics at compiler level
This talk introduces COMET, a DSL and compiler framework for dense and sparse tensor algebra that employs progressive lowering to generate efficient code for target heterogeneous systems starting from several high-level languages. COMET has been designed to solve some of the challenges in scientific, data analytics, and AI workloads, commonly used at National Laboratories. In addition to common compiler optimizations and code transformations, COMET employs domain-specific and architecture-specific optimizations leveraging the semantics expressed by high-level languages and architectural features. This talk specifically focuses on high-performance data analytics, highlighting challenges and opportunities for domain-specific optimizations at the compiler level and describing the optimizations and code transformation employed by COMET to generate efficient code for graph algorithms.
Sun 18 JunDisplayed time zone: Eastern Time (US & Canada) change
09:00 - 11:00 | |||
09:00 5mDay opening | Introduction CTSTA Fredrik Kjolstad Stanford University | ||
09:05 15mTalk | Software and Hardware for Sparse ML CTSTA Fredrik Kjolstad Stanford University | ||
09:20 15mTalk | Integrating Data Layout into Compilers and Code Generators CTSTA Mary Hall University of Utah | ||
09:35 15mTalk | Tackling the challenges of high-performance graph analytics at compiler level CTSTA Gokcen Kestor Pacific Northwest National Laboratory | ||
09:50 10mPanel | Discussion CTSTA | ||
10:00 5mBreak | BreakSocial CTSTA | ||
10:05 15mTalk | Challenges and Opportunities for Sparse Compilers in LLM CTSTA Zihao Ye University of Washington | ||
10:20 15mTalk | The Sparse Abstract Machine CTSTA Olivia Hsu Stanford University | ||
10:35 15mTalk | TeAAL: A Declarative Framework for Modeling Sparse Tensor Accelerators CTSTA Nandeeka Nayak University of Illinois at Urbana-Champaign | ||
10:50 10mPanel | Discussion CTSTA |