Continuing on the Device Emulator, make sure to check "DeviceEmulator V2 - how did we get a 40% improvement in performance?", a great post from Barry Bond, Device Emulator's architect:

The DeviceEmulator V2 is significantly faster than the V1 emulator you're used to. Most of the performance wins come from a small set of optimizations in the ARM-to-x86 JIT and the MMU emulator.  These wins improve raw execution of ARM instructions, so all applications and OSes benefit...

Barry goes on describing six "simple optimizations" that provided a "substantial performance win":

  1. Faster Translation Lookaside Buffer (TLB) implementation.
  2. Reduce x86 processor stalls due to mixed code and data
  3. More efficient interrupt polling
  4. Optimized memcpy() and memset()
  5. Optimizing "/Od" Code-Gen from the ARM C/C++ Compiler
  6. Faster Disassembly of ARM Instructions

Enjoy it!