gdi - 为什么windows上的skia效率很差

Question

我将skia 与Windows 上的gdi 绘画进行了比较。两者都绘制 98000 条随机线。令我惊讶的是skia的效率远低于gdi(skia绘画花费了1600ms，而gdi花费了0ms)。我的测试代码粘贴在下面。有什么建议吗？

bool PaintCompare() {
    //generate ramdon points
    std::default_random_engine e(std::chrono::high_resolution_clock::now().time_since_epoch().count());
    std::uniform_real_distribution<float> u(10, 500);
    SkPoint pts[100];
    for (int i = 0; i<100; i++)
        pts[i].set(u(e), u(e));
    SkPaint paint;
    paint.setColor(SkColorSetRGB(255, 0, 0));

    //create skia canvas
    sk_sp<SkSurface> rasterSurface(
        SkSurface::MakeRasterN32Premul(600, 600));
    SkCanvas* canvas = rasterSurface->getCanvas();

    //draw lines with skia
    auto start = std::chrono::high_resolution_clock::now();
    for (int i = 0; i<1000; i++)
    {
        for (int j = 1; j<99; j++)
        {
            canvas->drawLine(pts[j].fX, pts[j].fY, pts[j + 1].fX, pts[j + 1].fY, paint);
        }
    }
    auto cost = std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::high_resolution_clock::now() - start);
    sk_sp<SkImage> img(rasterSurface->makeImageSnapshot());
    if (!img) { return false; }
    SkBitmap skBmp;
    if (!img->asLegacyBitmap(&skBmp, SkImage::kRO_LegacyBitmapMode)) {
        return false;
    }

    //show bitmap on hdc
    BITMAPINFO bmi;
    memset(&bmi, 0, sizeof(bmi));
    bmi.bmiHeader.biSize = sizeof(BITMAPINFOHEADER);
    bmi.bmiHeader.biWidth = 600;
    bmi.bmiHeader.biHeight = -600; // top-down image 
    bmi.bmiHeader.biPlanes = 1;
    bmi.bmiHeader.biBitCount = 32;
    bmi.bmiHeader.biCompression = BI_RGB;
    bmi.bmiHeader.biSizeImage = 0;

    HDC hdc = GetDC();
    LPVOID pBits = NULL;
    HBITMAP hBmp = CreateDIBSection(hdc, &bmi, DIB_RGB_COLORS, &pBits, 0, 0);
    skBmp.copyPixelsTo(pBits, skBmp.getSize());
    CDC memdc;
    memdc.CreateCompatibleDC(hdc);
    memdc.SelectBitmap(hBmp);
    BitBlt(hdc, 0, 0, 600, 600, memdc, 0, 0, SRCCOPY);
    memdc.DeleteDC();


    //draw with gdi
    CPen pen;
    pen.CreatePen(PS_SOLID, 1, RGB(0, 255, 0));
    RECT rc{ 0,0,600,600 };
    CBitmap bmp;
    bmp.CreateCompatibleBitmap(hdc, 600, 600);
    memdc.CreateCompatibleDC(hdc);
    memdc.SelectBitmap(bmp);
    memdc.FillSolidRect(&rc, RGB(0, 0, 0));
    memdc.SelectPen(pen);
    start = std::chrono::high_resolution_clock::now();
    for (int i = 0; i<1000; i++)
    {
        for (int j = 1; j<99; j++)
        {
            memdc.MoveTo(pts[j].fX, pts[j].fY);
            memdc.LineTo(pts[j + 1].fX, pts[j + 1].fY);
        }
    }
    auto cost2 = std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::high_resolution_clock::now() - start);

    //copy bitmap to window
    BitBlt(hdc, 700, 0, 600, 600, memdc, 0, 0, SRCCOPY);
    ReleaseDC(hdc);
    memdc.DeleteDC();

    //wchar_t buf[256];
    //wsprintf(buf, L"left cost=%I64d, right cost=%I64d", cost.count(), cost2.count());
    //GetParent().SetWindowText(buf);

    //cost == 1596615 microseconds
    //cost2 == 107253 microseconds
}

Answer 1

终于找到问题了。我在 Debug模式下给出结果!

在 Debug模式下，带有光栅后端的skia比gdi慢20倍。 然而，在 Release模式下，带有光栅后端的skia比gdi慢4-5倍。

我进行了另一个测试，skia 使用 opengl 作为后端。结果显示skia 和gdi 花费的时间几乎相同。 Skia 比 GDI 慢约 15%。