Question

我希望跟踪长时间运行的光线跟踪过程处理的总像素和光线。如果我每次迭代都更新共享变量，由于同步，该过程将明显减慢。我想跟踪进度并最终得到准确的计数结果。有没有办法用OpenMP for循环来做到这一点？

以下是相关循环的一些代码：

void Raytracer::trace(RenderTarget& renderTarget, const Scene& scene, std::atomic<int>& sharedPixelCount, std::atomic<int>& sharedRayCount)
{
    int width = renderTarget.getWidth();
    int height = renderTarget.getHeight();
    int totalPixelCount = width * height;

    #pragma omp parallel for schedule(dynamic, 4096)
    for (int i = 0; i < totalPixelCount; ++i)
    {
        int x = i % width;
        int y = i / width;

        Ray rayToScene = scene.camera.getRay(x, y);
        shootRay(rayToScene, scene, sharedRayCount); // will increment sharedRayCount
        renderTarget.setPixel(x, y, rayToScene.color.clamped());

        ++sharedPixelCount;
    }
}

Answer 1

由于您的动态调度并行for循环的块大小为4096，为什么不将其用作分摊计数器更新的粒度？

例如，以下内容可能有效。我没有测试此代码，您可能需要为totalPixelCount%4096!=0添加一些簿记。

与前面的答案不同，除了循环本身隐含的分支之外，这不会向循环添加分支，许多处理器都有优化指令。它也不需要任何额外的变量或算术。

void Raytracer::trace(RenderTarget& renderTarget, const Scene& scene, std::atomic<int>& sharedPixelCount, std::atomic<int>& sharedRayCount)
{
    int width = renderTarget.getWidth();
    int height = renderTarget.getHeight();
    int totalPixelCount = width * height;

    #pragma omp parallel for schedule(dynamic, 1)
    for (int j = 0; j < totalPixelCount; j+=4096)
    {
      for (int i = j; i < (i+4096); ++i)
      {
        int x = i % width;
        int y = i / width;

        Ray rayToScene = scene.camera.getRay(x, y);
        shootRay(rayToScene, scene, sharedRayCount);
        renderTarget.setPixel(x, y, rayToScene.color.clamped());
      }
      sharedPixelCount += 4096;
    }
}

根本不清楚为什么sharedPixelCount需要在这个循环中更新，因为它在循环体中没有被引用。如果这是正确的，我建议改为以下。

void Raytracer::trace(RenderTarget& renderTarget, const Scene& scene, std::atomic<int>& sharedPixelCount, std::atomic<int>& sharedRayCount)
{
    int width = renderTarget.getWidth();
    int height = renderTarget.getHeight();
    int totalPixelCount = width * height;

    int reducePixelCount = 0;
    #pragma omp parallel for schedule(dynamic, 4096) \
                         reduction(+:reducePixelCount) \
                         shared(reducePixelCount)
    for (int i = 0; i < totalPixelCount; ++i)
    {
        int x = i % width;
        int y = i / width;

        Ray rayToScene = scene.camera.getRay(x, y);
        shootRay(rayToScene, scene, sharedRayCount);
        renderTarget.setPixel(x, y, rayToScene.color.clamped());

        ++reducePixelCount; /* thread-local operation, not atomic */
    }

    /* The interoperability of C++11 atomics and OpenMP is not defined yet,
     * so this should just be avoided until OpenMP 5 at the earliest. 
     * It is sufficient to reduce over a non-atomic type and 
     * do the assignment here. */
    sharedPixelCount = reducePixelCount;
}

Answer 2

以下是如何操作的示例：

void Raytracer::trace(RenderTarget& renderTarget, const Scene& scene, std::atomic<int>& sharedPixelCount, std::atomic<int>& sharedRayCount)
{
    int width = renderTarget.getWidth();
    int height = renderTarget.getHeight();
    int totalPixelCount = width * height;
    int rayCount = 0;
    int previousRayCount = 0;

    #pragma omp parallel for schedule(dynamic, 1000) reduction(+:rayCount) firstprivate(previousRayCount)
    for (int i = 0; i < totalPixelCount; ++i)
    {
        int x = i % width;
        int y = i / width;

        Ray rayToScene = scene.camera.getRay(x, y);
        shootRay(rayToScene, scene, rayCount);
        renderTarget.setPixel(x, y, rayToScene.color.clamped());

        if ((i + 1) % 100 == 0)
        {
            sharedPixelCount += 100;
            sharedRayCount += (rayCount - previousRayCount);
            previousRayCount = rayCount;
        }
    }

    sharedPixelCount = totalPixelCount;
    sharedRayCount = rayCount;
}

循环运行时，它不会100％准确，但错误可以忽略不计。最后会报告确切的值。

在OpenMP中增加共享循环计数器以进行进度报告

2 个答案: