Nick’s Lounge

    
    #include 
    #include 

    using namespace Gdiplus;

    GdiplusStartupInput gdiplusStartupInput;
    ULONG_PTR gdiplusToken;
    GdiplusStartup(&gdiplusToken, &gdiplusStartupInput, NULL);
    ...
    IStream* pJpegStream = NULL;  //declare a memory stream
    CreateStreamOnHGlobal(NULL, TRUE, (LPSTREAM*)&pJpegStream);

    GpBitmap* pBitmap = NULL;
    unsigned char* dib = GetDib(); //get DIB or BMP data buffer
    DllExports::GdipCreateBitmapFromGdiDib((LPBITMAPINFO)dib, dib + sizeof(BITMAPINFOHEADER), &pBitmap);

    CLSID imageCLSID;
    GetEncoderClsid(L"image/jpeg", &imageCLSID);

    int jpegQuality = 100;

    EncoderParameters encoderParams; //setup jpeg encoder parameters
    encoderParams.Count = 1;
    encoderParams.Parameter[0].NumberOfValues = 1;
    encoderParams.Parameter[0].Guid = EncoderQuality;
    encoderParams.Parameter[0].Type = EncoderParameterValueTypeLong;
    encoderParams.Parameter[0].Value = &jpegQuality;

    //save jpeg into memory stream
    DllExports::GdipSaveImageToStream(pBitmap, pJpegStream, &imageCLSID, &encoderParams);

    LARGE_INTEGER lnOffset;
    lnOffset.QuadPart = 0;
    ULARGE_INTEGER ulnSize;
    //determine memory stream length
    pJpegStream->Seek(lnOffset, STREAM_SEEK_END, &ulnSize);
    pJpegStream->Seek(lnOffset, STREAM_SEEK_SET, NULL);
    int encodedBytes = ulnSize.QuadPart;
    
    //store jpeg memory stream into jpeg data buffer
    pJpegStream->Read(racBuf_, ulnSize.QuadPart, NULL);
    ...
    GdiplusShutdown(gdiplusToken);

// firewall.cpp : Defines the entry point for the console application.
//

#include "stdafx.h"
/********************************************************************++
Copyright (C) Microsoft. All Rights Reserved.

Abstract:
    This C++ file includes sample code for disabling Windows Firewall 
    per profile using the Microsoft Windows Firewall APIs.

--********************************************************************/
#include 
#include 
#include 

#pragma comment( lib, "ole32.lib" )

// Forward declarations
HRESULT     WFCOMInitialize(INetFwPolicy2** ppNetFwPolicy2);

int __cdecl main()
{
    HRESULT hrComInit = S_OK;
    HRESULT hr = S_OK;

    INetFwPolicy2 *pNetFwPolicy2 = NULL;

    // Initialize COM.
    hrComInit = CoInitializeEx(
                    0,
                    COINIT_APARTMENTTHREADED
                    );

    // Ignore RPC_E_CHANGED_MODE; this just means that COM has already been
    // initialized with a different mode. Since we don't care what the mode is,
    // we'll just use the existing mode.
    if (hrComInit != RPC_E_CHANGED_MODE)
    {
        if (FAILED(hrComInit))
        {
            printf("CoInitializeEx failed: 0x%08lxn", hrComInit);
            goto Cleanup;
        }
    }

    // Retrieve INetFwPolicy2
    hr = WFCOMInitialize(&pNetFwPolicy2);
    if (FAILED(hr))
    {
        goto Cleanup;
    }

    // Disable Windows Firewall for the Domain profile
    hr = pNetFwPolicy2->put_FirewallEnabled(NET_FW_PROFILE2_DOMAIN, FALSE);
    if (FAILED(hr))
    {
        printf("put_FirewallEnabled failed for Domain: 0x%08lxn", hr);
        goto Cleanup;
    }

    // Disable Windows Firewall for the Private profile
    hr = pNetFwPolicy2->put_FirewallEnabled(NET_FW_PROFILE2_PRIVATE, FALSE);
    if (FAILED(hr))
    {
        printf("put_FirewallEnabled failed for Private: 0x%08lxn", hr);
        goto Cleanup;
    }

    // Disable Windows Firewall for the Public profile
    hr = pNetFwPolicy2->put_FirewallEnabled(NET_FW_PROFILE2_PUBLIC, FALSE);
    if (FAILED(hr))
    {
        printf("put_FirewallEnabled failed for Public: 0x%08lxn", hr);
        goto Cleanup;
    }

Cleanup:

    // Release INetFwPolicy2
    if (pNetFwPolicy2 != NULL)
    {
        pNetFwPolicy2->Release();
    }

    // Uninitialize COM.
    if (SUCCEEDED(hrComInit))
    {
        CoUninitialize();
    }
   
    return 0;
}

// Instantiate INetFwPolicy2
HRESULT WFCOMInitialize(INetFwPolicy2** ppNetFwPolicy2)
{
    HRESULT hr = S_OK;

    hr = CoCreateInstance(
        __uuidof(NetFwPolicy2), 
        NULL, 
        CLSCTX_INPROC_SERVER, 
        __uuidof(INetFwPolicy2), 
        (void**)ppNetFwPolicy2);

    if (FAILED(hr))
    {
        printf("CoCreateInstance for INetFwPolicy2 failed: 0x%08lxn", hr);
        goto Cleanup;        
    }

Cleanup:
    return hr;
}

Recently I am working on UI decoding optimization. I found this program, Full Throttle Override, is very useful, and it can fully release the power of your CPU.

To balance of power consumption and performance, almost all x86 CPUs support either Cool’n’Quiet or SpeedStep or PowerNow! technology, which can dynamically adjust the CPU frequency based on the loading.

I found it’s pretty easy to implement Full Throttle Override and here is the core C++ code

		
void FullThrottle()
{
    OSVERSIONINFO osvi;
    memset(&osvi, 0, sizeof(OSVERSIONINFO));
    osvi.dwOSVersionInfoSize = sizeof(OSVERSIONINFO);
    GetVersionEx(&osvi);
    // For Vista and above
    if (osvi.dwMajorVersion >= 6)
    {
	GUID *scheme;
	PowerGetActiveScheme(NULL, &scheme);
	PowerWriteACValueIndex(NULL
            , scheme
            , &GUID_PROCESSOR_SETTINGS_SUBGROUP
            , &GUID_PROCESSOR_THROTTLE_MINIMUM
            , 100);
	PowerSetActiveScheme(NULL, scheme);
    }
    else
    {
	MessageBox(NULL, L"Not supported by your OS!",L"",0);
    }
}

These two weeks, I am working on our product UI side to improve the performance of animation rendering. Previously, there is only one single thread to decode the animation line by line, and it takes around 50ms for the whole frame.

Now, I change the way of rendering, and let all lines parallel decode to fully take advantage of modern multi-core CPU.

 

Visual Studio natively supports OpenMP, it gives me a easy way to access this powerful tool.

To set this compiler option in the Visual Studio development environment

After some simple code update, surprisingly, I found that my frame decoding performance boosts 950% (almost 10 times faster), from 8 FPS to 76 FPS!

 

Let’s do simple test with the following code:

#define TEST_LENGTH 0x3fffffff

double mptest()
{
    LARGE_INTEGER  large_interger;
    double dff;
    __int64  c1, c2;
    QueryPerformanceFrequency(&large_interger);
    dff = large_interger.QuadPart;
    //
    unsigned char *test = new unsigned char[TEST_LENGTH];
    QueryPerformanceCounter(&large_interger);
    c1 = large_interger.QuadPart;
    #pragma omp parallel for
    for (int i = 0; i<TEST_LENGTH; i++)
    {
        test[i] = rand();
    }
    QueryPerformanceCounter(&large_interger);
    c2 = large_interger.QuadPart;
    delete test;
    return (c2 - c1) * 1000.0f / dff;
}

double test()
{
    LARGE_INTEGER  large_interger;
    double dff;
    __int64  c1, c2;
    QueryPerformanceFrequency(&large_interger);
    dff = large_interger.QuadPart;
    //
    unsigned char *test = new unsigned char[TEST_LENGTH];
    QueryPerformanceCounter(&large_interger);
    c1 = large_interger.QuadPart;
    for (int i = 0; i<TEST_LENGTH; i++)
    {
        test[i] = rand();
    }
    QueryPerformanceCounter(&large_interger);
    c2 = large_interger.QuadPart;
    delete test;
    return (c2 - c1) * 1000.0f / dff;
}

int _tmain(int argc, _TCHAR* argv[])
{
    printf("Random generation cost with MP %lfmsn", mptest());
    printf("Random generation cost without MP %lfmsn", test());
    _getch();
    return 0;
}

Look at the huge difference!