CoolSim: Eliminating Traditional Cache Warming with Fast, Virtualized Profiling
2016 (English)In: 2016 IEEE International Symposium On Performance Analysis Of Systems And Software ISPASS 2016, 2016, 149-150 p.Conference paper (Refereed)
Sampling (e.g., SMARTS and SimPoint) improves simulation performance by an order of magnitude or more through the reduction of large workloads into a small but representative sample. Virtualized fast-forwarding (e.g., FSA) speeds up simulation further by advancing execution at near-native speed between simulation points, making cache warming the critical limiting factor for simulation performance. CoolSim is an efficient simulation framework that eliminates cache warming. It collects sparse memory reuse information (MRI) while advancing between simulation points using virtualized fast-forwarding. During detailed simulation, a statistical cache model uses the previously acquired MRI to estimate the performance of the caches. CoolSim builds upon KVM and gem5 and runs 19x faster than the state-of-the-art sampled simulation. It estimates the CPI of the SPEC CPU2006 bench-marks with 3.62% error on average, across a wide range of cache sizes.
Place, publisher, year, edition, pages
2016. 149-150 p.
, IEEE International Symposium on Performance Analysis of Systems and Software-ISPASS
IdentifiersURN: urn:nbn:se:uu:diva-304691ISI: 000382752200017ISBN: 9781509019533OAI: oai:DiVA.org:uu-304691DiVA: diva2:1033488
17th IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), APR 17-19, 2016, Uppsala, SWEDEN