Thanks guys for your answers.
I think I will post a question in the ADC group to see if somebody is
taking the risk of submitting an application that uses JNI. In the
mean time I will keep profiling and profiling to see if I can reduce
it a few seconds...
On 11 abr, 01:23, David Given [EMAIL
These performance issues are being a real headache for me! My project
relies very heavily into image processing algorithms, and they take
too long when executing over the emulator.
The set of algorithms executed with a Sun JVM (1.6.0_03) take less
than 20 secs but when I execute them within the
The emulator depends greatly on the performance of your local machine
and does not reflect at all the actual performance on a real device.
On Thu, Apr 10, 2008 at 3:31 PM, qvark
[EMAIL PROTECTED] wrote:
These performance issues are being a real headache for me! My project
relies very
qvark wrote:
[...]
The set of algorithms executed with a Sun JVM (1.6.0_03) take less
than 20 secs but when I execute them within the emulator (in the same
machine), they are taking over 7 minutes! That's more than 20x slower!
AFAIK, the Dalvik VM is currently an *interpreter*... running on an
You are timing your application by running, not by debugging, right?
Debugging the application through Eclipse takes significantly longer
than running it.
Just wanted to make sure :)
On Mar 30, 2:40 pm, mickrobk [EMAIL PROTECTED] wrote:
I feel your pain, when I do a generic flood fill it's
Doing pixel-level processing in within the Dalvik VM will necessarily
incur the overhead of copying the pixel data into the VM heap. As
others have suggested, this needs be done to gain fast access to the
pixel data.
But I doubt that this is the bottleneck, it's certainly the
interpreted nature
saurabh wrote:
[...]
The getPixel
function seems to be taking approx 1/100 of a second. Similarly,
checking whether each pixel satisfies the condition and then copying
it to Bitmap B also takes approx 1/100 second. Therefore, performing
these 2 operations for 547*450 = 246150 pixels takes a
On Mar 30, 7:08 pm, David Given [EMAIL PROTECTED] wrote:
saurabh wrote:
[...]
The getPixel
function seems to be taking approx 1/100 of a second. Similarly,
checking whether each pixel satisfies the condition and then copying
it to Bitmap B also takes approx 1/100 second. Therefore,
I feel your pain, when I do a generic flood fill it's taking 10s of
seconds to walk through the array of pixels. I'm hoping memory access
time will be reduced dramatically on a real device, or if it isn't jni
is supported in some fashion.
On Mar 30, 11:10 am, saurabh [EMAIL PROTECTED] wrote:
On
9 matches
Mail list logo
