The DaCapo Benchmark Suite: A Methodological, Engineering, and Social Journey Steve Blackburn (Australian National University) Abstract The DaCapo research group embarked on building a Java benchmark suite in 2003 after we highlighted the dearth of realistic Java benchmarks to an NSF review panel. The panel suggested that we solve our own problem, but our grant was for dynamic optimizations. NSF did not provide additional funds for benchmark development, but we forged ahead regardless. The result was a suite that became a de facto standard. By 2008 we estimated that our group had spent over 10,000 person-hours on the suite. Since then we’ve made another major release, and are now well on the way to a third major release. In this talk I’ll reflect the journey and some of the many lessons we’ve learned. Bio My research interests are centered on the challenge of making software run faster and more power-efficiently on modern hardware. My primary interests include: microarchitectural support for managed languages, fast and efficient garbage collection, and the design and implementation of virtual machines. As a backdrop to this I have a longstanding interest in role of sound methodology and infrastructure in successful research innovation.