Slides - jtres 2012
Slides - jtres 2012 Slides - jtres 2012
Higher performance requires just-in-time compilation,which translates bytecode to native code at runtime Both VMs employ adaptive compilation• Interpret initially, when finding hot spot, compiling it DVM’s JIT compilation unit is a hot path called a trace, while JVM’s is a hot method• For lower memory footprint, yet competitive performance• But, the reality is …Virtual Machine & Optimization Lab7
- Page 4: VM for executing Java in Android pl
- Page 12 and 13: Tablet PC with ARM Cortex-A8 and 1G
- Page 14 and 15: 1.210.80.60.40.20Chess kXML Paralle
- Page 16 and 17: 20181614121086420Chess kXML Paralle
- Page 18 and 19: 2.521.510.50Chess kXML Parallel PNG
- Page 20 and 21: How many instructions are generated
- Page 22 and 23: 1.21.151.11.0510.950.90.850.8Chess
- Page 24 and 25: Profile results based on OProfile
- Page 26 and 27: 100%90%80%70%60%50%40%30%20%10%0%In
- Page 28 and 29: Numbers are log scale 1000000100000
- Page 30 and 31: Numbers are log scale 1000000100000
- Page 32 and 33: Apps generate more traces, yet app
- Page 34: We believe Dalvik’s trace-based J
Higher performance requires just-in-time compilation,which translates bytecode to native code at runtime Both VMs employ adaptive compilation• Interpret initially, when finding hot spot, compiling it DVM’s JIT compilation unit is a hot path called a trace, while JVM’s is a hot method• For lower memory footprint, yet competitive performance• But, the reality is …Virtual Machine & Optimization Lab7