jit

问题 I am referring to the below document by Oracle: http://docs.oracle.com/cd/E13150_01/jrockit_jvm/jrockit/geninfo/diagnos/underst_jit.html#wp1080014 It is mentioned in the "1. The JRockit JVM Runs JIT Compilation " section that the JIT JVM has more startup time and less execution time and vice-versa for JVMs without JIT. I am confused because as per my knowledge, JIT compiles the code as per the execution of program therefore making the compilation fast. And the code will be optimized so

问题 I have a code and i wonder can JIT be prevented from optimising method clearArraySafely ? Is it possible to selectively disabling the JIT for some part of code? Or how can I be sure that this code will not be optimized? private static char[] password; public static void clearArraySafely() { // Overwritting array for (int i = 0 ; i <= password.length; i++) { password[i] = 0; //System.out.print(i); // <- I don't want to do this trick to be sure } password = null; } Is there any good class to

问题 A method could get inlined; there is an attribute to prevent that ("there's an att for that"). However, apparently a method may also not get its own stack frame on x64 due to tail-call optimization by the JITter (http://www.hanselman.com/blog/ReleaseISNOTDebug64bitOptimizationsAndCMethodInliningInReleaseBuildCallStacks.aspx). Would this affect the behavior of MethodBase.GetCurrentMethod ? The discussions that I can find are mostly about inlining (When is a method eligible to be inlined by the

问题 I wrote a small static JNI function which is only 5 instructions long. Is it possible for the JVM to inline this code into the body of a method which calls it frequently or will it always generate a call instruction in the JITed method? For example: public class SomeClass { private static native long func(); public void doLoop() { for(int i = 0; i < 0xFFFFFF; i++) { func(); } } public static void main(String[] args) { for(int i = 0; i < 0xFFFFFF; i++) { doLoop(); } } } Is it possible for the

问题 So I'm trying to understand exactly when .NET Assemblies are loaded into a .NET process. I read this blog entry which did a great job of explaining things and confirmed a lot of what I thought I already knew, but it also brought up a point in which I think I slightly misunderstood. Dependent Assemblies are just in time loaded when first referenced in code I took this to mean that when and furthermore if the first time a call to an assembly was made then the assembly was loaded into the

问题 I am developing a tool for some numerical analysis of user-defined functions. The idea is to make a convenient UI in Python, where user can enter C function, then press a button - and receive some output data. Computations can take minutes or hours, so Numpy-only performance is not acceptable. I have tried the following approach: the Python-based UI calls gcc, compiles dll from user functions that is than used by my core C-based algorithms in Cython wrappings. It works, but since there is no

问题 I have understanding how heap and garbage collector works: garbage collection happens in generations, memory allocation happens sequentially, during garbage collection free/unused space compacted by shifting data and forming continues block, etc. Is there any headers for allocated memory chunks are present and how big are they (I heard it’s 8-16 bytes for .NET CLR) and if byte, word or quad-word alignment present? I’m interested in any information for JIT (Java) and CLR (.NET Framework or

问题 I'd like to know what scope and sequence the CLR applies to JIT compilation. For example, if my application calls only a single method of a given class, do the unused methods of that class get JIT compiled needlessly? And if yes, are they all JIT compiled before executing the one method I needed, or are they lazily compiled after the fact? And what about branches in a method? Does the CLR allow half of the code in a method to be compiled, while allowing a separate branch in the same method to

问题 We would like to extend Mono's VM to generate information that can be consumed by DTrace and instruments. I am looking at making changes to the Mono runtime to have it register or notify the code that it has dynamically generated so DTrace can produce useful information for those blocks of code. 回答1: What kind of information do you want to include? The main example of doing this is ustack helpers, which convey from a VM to DTrace how to translate stack frames into human-readable frames. These

问题 I understand the gist of how JIT compilation works (after reading such resources as this SO question). However, I am still wondering how does it actually execute the machine code at runtime? I don't have a deep background in operating systems or compiler optimizations, and haven't done anything with machine code directly, but am starting to explore it. I have started playing around in assembly, and see how something like NASM can take your assembly code and compile it to machine code (the