|
Hi guys
In C++/CLI what is the difference between using the concept of IJW (It Just Works) and using pragma directive as following:
#pragma managed(push,off)
UnmanagedFunc(){
…native code …
}
#pragma managed(pop)
Does IJW is enabled automatically (so just need to write our native code) or we need to do something to make it works..??
In other mean, what is the advantage of IJW over using pragma directive or the other way around??
|
|
|
|
|
IJW is just a term they used back in 2003/2004 to talk about how the managed-unmanaged transitions and marshaling were smoothly handled for you by the compiler. No one uses the term these days, and instead people just say C++ interop to refer to anything where mixed-mode code comes into play.
#pragma unmanaged is a pre-compiler directive that tells the compiler that any code in that block must be compiled natively (meaning no msil at all). It's mostly used to ensure that frequently used code is compiled for better performance (which usually implies native code generation).
|
|
|
|
|
Thanx Nish
If I use standard C function inside CPP/CLI code .. like for example:
ManagedFunction(){
..... Managed Code .....
..... Managed Code .....
printf("I am standard C function!\n");
..... Managed Code .....
..... Managed Code .....
}
Does MSIL do something with the printf() function! (Notice that i did NOT use #pragma umanaged directive!)
If MSIL will do nothing with printf() so (as i think) printf() will be compiled as native??So why I need to use #pragma umanaged directive.
|
|
|
|
|
The call to printf will be emitted via msil. The printf method itself will execute as native code (there will be a managed to unmanaged jump during execution).
Now instead of printf, assume you were calling your own global function Foo. Now if you did not put Foo's definition in a #pragma unmanaged block, Foo itself will be compiled as msil. That's a scenario where you'd actually want to use #pragma unmanaged, particularly if you think Foo is a time-intensive function.
|
|
|
|
|
Great man... It is more clear now. Thank you.
|
|
|
|
|
What is Difference between Managed C++, C++/CLI and C++.Net?
Also give name of some good books for all of these.
I am MFC/Win32 programmer. In current project we are using WPF and code behind is Managed C++. But I am not sure it is C++.Net or what.
I know C#.Net as well.
Thanks in advance.
|
|
|
|
|
Managed C++ runs under the 'managed' environment which is .NET. C++/CLI and C++.NET are merely different names for the same thing. Take a look at MSDN for more information.
I must get a clever new signature for 2011.
|
|
|
|
|
Richard MacCutchan wrote: Managed C++ runs under the 'managed' environment which is .NET. C++/CLI and C++.NET are merely different names for the same thing. Take a look at MSDN for more information.
Actually it is said that Microsoft has deprecated Managed C++ for C++/CLI. I think there is difference.
Please refer this
http://en.wikipedia.org/wiki/Managed_Extensions_for_C%2B%2B[^]
Thanks for your answer.
|
|
|
|
|
So you knew the answer all along. 
I must get a clever new signature for 2011.
|
|
|
|
|
Actually Richard, I know your answer was also same and correct, but problem was of my understanding. 
|
|
|
|
|
Managed C++ is the older, deprecated syntax for using .NET libraries via C++. It had lots of nasty __ prefixes.
C++/CLI has much nicer keywords for declaring and using managed classes.
The best book I've found is "C++/CLI in Action" by Nishant Sivakumar from Manning Press.
http://www.manning.com/sivakumar/
John
|
|
|
|
|
Thank you very much for your answer.
What I understand is both are .Net via C++. Difference is syntax.
|
|
|
|
|
Exactly. Glad I could help.
John
|
|
|
|
|
<b>Hi
I need help...
I have an array of string private variable List<String^>^ CalculateGreeks_; having property for get and set List<String^>^ CalculateGreeks() in a class CArgsRequestCredential,
I want to put these variables
PV,Delta,Vega
in my local object
<b>ReqCredObj_ = gcnew Args::CArgsRequestCredential();</b>
first i need to split strings saving each string in a variable and then storing variables in the list..
my code is
List<String^>^ CalculateGreeks1 = gcnew List<String^>();
for(int i = 0 ; i <= LocalArray->GetUpperBound(0);i++)
{
//
//CalculateGreeks1->Add(ii);
String^ Test = Convert::ToString(LocalArray->GetValue(i,0));
array <String ^>^ strings = Test->Split(',');
//ii = gcnew List<String^>^ CalculateGreeks_();
//ii->CalculateGreeks = Convert::ToString(strings);
// CalculateGreeks1->Add(strings);
// ReqCredObj_->CalculateGreeks = Convert::ToString(LocalArray->GetValue(0,1));
}
but my logic is not giving correct values
kindly help
|
|
|
|
|
Hello,
My question seems to be simple, but I stuck with it for long time.
Why it is at all needed more than one project in solution?
How to add multiple projects in one solution?
How to use them?
Thanks in advance.
|
|
|
|
|
Pranit Kothari wrote: Why it is at all needed more than one project in solution?
There are several reasons why you might want to do this, including:
1. You have a static library with rarely-changed code, linked to your app.
2. You have a dll - for example, a shell extension - and an app that presents the gui.
3. You have a dll and several test apps.
Pranit Kothari wrote: How to add multiple projects in one solution?
Right click on the solution in the Solution Explorer, then click on Add > New Project (or Existing Project).
Pranit Kothari wrote: How to use them?
See answer to first question.
|
|
|
|
|
Thanks for your answer.
What I have guessed from your answer is, suppose I have some set of classes that I am creating in one project and I will create another project and use that library. It it correct?
If yes, may I know how to use it? Is it related with assembly or namespace?
|
|
|
|
|
That is correct, look up dynamic and/or static dll use in Google. Having the ability to have all of your dll's in the same workspace is very advantageous for debugging the dlls themselves or interactions between the application and dll.
|
|
|
|
|
Pranit Kothari wrote: Why it is at all needed more than one project in solution?
I create apps in functional blocks, like the database layer. I like to work on that and test it independently. So I have project and a solution as well.
Then I add the projects into the main solution.
|
|
|
|
|
Thanks for your answer.
What I have guessed from your answer is, suppose I have some set of classes that I am creating in one project and I will create another project and use that library. It it correct?
If yes, may I know how to use it? Is it related with assembly or namespace?
|
|
|
|
|
Pranit Kothari wrote: What I have guessed from your answer is, suppose I have some set of classes that I am creating in one project and I will create another project and use that library. It it correct?
Yes and no.
I use the term library to refer to a deliverable. An example is a logging library like log4cpp.
A deliverable has an independent project schedule, has its own requirements and users of the library determine which version to consume by moving the binary (compiled) form into their project.
An application however might have different layers or blocks. Each would likely have their own project. (I usually won't break into layers/blocks if there is only one code file even if there is a conceptual difference.)
On the other hand for something like a windows service I always break the 'service' code into a project that does nothing but provide the basic start/stop and uses another project (called something like 'App') which encompasses the entire functionality of the windows service. So a layout would look like
MyService
App
Service
OtherFunctionality
lib
MyOtherLibrary.dll
In the above the Service project refers to the App project and OtherFunctionality project and references the MyOtherLibrary.dll.
The App project refers to the OtherFunctionality project and references the MyOtherLibrary.dll as well.
Some very common functional blocks for me would be database layers, communication layers and business logic of different types. The App is also a block as it represents the application itself without requiring dependency specifically as a windows service. This makes it trivial to also deliver a stand alone console executable (which I always do as well.)
|
|
|
|
|
Thanks jschell. really nice explanation. Now I got it.
|
|
|
|
|
Usinrg selective instrumentation with Purify needed msvcrt.pdb 7.0.2600.5512,
where can I find it ?
Thanks in advance !!
|
|
|
|
|
Sounds like a question for a Purify forum. Purify install should include all the C-Runtime DLLs it requires. You could try debugging a c++ app built against that version of the runtime and in the debugger use the Microsoft symbol server to download the pdbs by a right-click on the module and download symbols from MS symbol server.
John
|
|
|
|
|
I found msvcrt.pdb under the Platform SDK on my machine.
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
