AFAIK, the Dalvik VM cannot use the existing hardware acceleration in ARM CPUs because
1. It uses bytecodes that the ARM Jazelle accelerator was not designed for. 2. Even if Dalvik bytecodes were compatible, using the ARM Jazelle accelerator would require additional licensing from ARM, which may be (too) costly. >From what I've read, Nokia uses JIT and leaves the ARM Jazelle accelerator unused even while it is present on many of their phones. Regards On Mar 31, 10:06 pm, Stoyan Damov <[email protected]> wrote: > On Tue, Mar 31, 2009 at 10:54 PM, Fred Grott <[email protected]> wrote: > > JIT is not register based I thought and that would be the reason for no JIT > > on chip process as the ANdorid VM is register based not stack based. > > > There was a whole architecture dicsussion by Google when Android was first > > was announced about this.. > > Right, my point is that from what I've read on the next, Dalvik VM was > not needed at all, and its very existence is due to the fact that Sun > wouldn't let Google run java bytecode on Android. Whether the VM is or > isn't registered based is totally irrelevant. What good if Dalvik VM > is registered-based if it interprets code, where this code, if it were > bytecode could run like native code due to the java acceleration? > > Cheers --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "Android Discuss" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/android-discuss?hl=en -~----------~----~----~----~------~----~------~--~---
