【发布时间】：2012-07-19 08:00:46
【问题描述】：
我正在做一些有趣的实验计算，这时我遇到了一个有趣的结果：
Completed 1024x1024 pixels with 700 points in...
For Loop (Inline): 19636ms
For Loop: 12612ms
Parallel.For Loop: 3835ms
这不是我所期望的。
系统：Windows 7 64、i3 2120 [双核、4 线程]、Visual Studio 2010。
构建：优化开启，发布模式 [无调试器]，32 位。
其次是令人失望的 64 位性能。虽然它在比率方面更符合我的预期，但它通过全面减慢来实现这一点。
Completed 1024x1024 pixels with 700 points in...
For Loop (Inline): 23409ms
For Loop: 24373ms
Parallel.For Loop: 6839ms
计算很简单：对于索引 x 和 y，找到最接近的 Vector3 并将其存储在二维数组中。
如果你敢的话，这个问题是试图解释为什么内联 for 循环如此缓慢。解释 64 位版本性能不足的加分项。
using System;
using System.Diagnostics;
using System.Threading.Tasks;
namespace TextureFromPoints
{
class Program
{
const int numPoints = 700;
const int textureSize = 1024;
static Random rnd = new Random();
static void Main(string[] args)
{
while (true)
{
Console.WriteLine("Starting");
Console.WriteLine();
var pointCloud = new Vector3[numPoints];
for (int i = 0; i < numPoints; i++)
pointCloud[i] = new Vector3(textureSize);
var result1 = new Vector3[textureSize, textureSize];
var result2 = new Vector3[textureSize, textureSize];
var result3 = new Vector3[textureSize, textureSize];
var sw1 = Stopwatch.StartNew();
for (int x = 0; x < textureSize; x++)
for (int y = 0; y < textureSize; y++)
{
var targetPos = new Vector3(x, y, 0);
var nearestV3 = pointCloud[0];
var nearestV3Distance = nearestV3.DistanceToPoint(targetPos);
for (int i = 1; i < numPoints; i++)
{
var currentV3 = pointCloud[i];
var currentV3Distance = currentV3.DistanceToPoint(targetPos);
if (currentV3Distance < nearestV3Distance)
{
nearestV3 = currentV3;
nearestV3Distance = currentV3Distance;
}
}
result1[x, y] = nearestV3;
}
sw1.Stop();
var sw2 = Stopwatch.StartNew();
for (int x = 0; x < textureSize; x++)
for (int y = 0; y < textureSize; y++)
Computation(pointCloud, result2, x, y);
sw2.Stop();
var sw3 = Stopwatch.StartNew();
Parallel.For(0, textureSize, x =>
{
for (int y = 0; y < textureSize; y++)
Computation(pointCloud, result3, x, y);
});
sw3.Stop();
Console.WriteLine("Completed {0}x{0} pixels with {1} points in...", textureSize, numPoints);
Console.WriteLine("{0}: {1}ms", "For Loop (Inline)", sw1.ElapsedMilliseconds);
Console.WriteLine("{0}: {1}ms", "For Loop", sw2.ElapsedMilliseconds);
Console.WriteLine("{0}: {1}ms", "Parallel.For Loop", sw3.ElapsedMilliseconds);
Console.WriteLine();
Console.Write("Verifying Data: ");
Console.WriteLine(CheckResults(result1, result2) && CheckResults(result1, result3) ? "Valid" : "Error");
Console.WriteLine(); Console.WriteLine();
Console.ReadLine();
}
}
private static bool CheckResults(Vector3[,] lhs, Vector3[,] rhs)
{
for (int x = 0; x < textureSize; x++)
for (int y = 0; y < textureSize; y++)
if (!lhs[x, y].Equals(rhs[x, y]))
return false;
return true;
}
private static void Computation(Vector3[] pointCloud, Vector3[,] result, int x, int y)
{
var targetPos = new Vector3(x, y, 0);
var nearestV3 = pointCloud[0];
var nearestV3Distance = nearestV3.DistanceToPoint(targetPos);
for (int i = 1; i < numPoints; i++)
{
var currentV3 = pointCloud[i];
var currentV3Distance = currentV3.DistanceToPoint(targetPos);
if (currentV3Distance < nearestV3Distance)
{
nearestV3 = currentV3;
nearestV3Distance = currentV3Distance;
}
}
result[x, y] = nearestV3;
}
struct Vector3
{
public float x;
public float y;
public float z;
public Vector3(float x, float y, float z)
{
this.x = x;
this.y = y;
this.z = z;
}
public Vector3(float randomDistance)
{
this.x = (float)rnd.NextDouble() * randomDistance;
this.y = (float)rnd.NextDouble() * randomDistance;
this.z = (float)rnd.NextDouble() * randomDistance;
}
public static Vector3 operator -(Vector3 a, Vector3 b)
{
return new Vector3(a.x - b.x, a.y - b.y, a.z - b.z);
}
public float sqrMagnitude()
{
return x * x + y * y + z * z;
}
public float DistanceToPoint(Vector3 point)
{
return (this - point).sqrMagnitude();
}
}
}
}
更新：感谢 Drew Marsh 的努力，我们现在有了这个超级优化的版本，它内联了所有 V3 操作。
using System;
using System.Diagnostics;
using System.Threading.Tasks;
namespace TextureFromPoints
{
class RevisedProgram
{
const int numPoints = 700;
const int textureSize = 1024;
static Random rnd = new Random();
static void Main(string[] args)
{
while (true)
{
Console.WriteLine("Starting REVISED");
Console.WriteLine();
var pointCloud = new Vector3[numPoints];
for (int i = 0; i < numPoints; i++)
pointCloud[i] = new Vector3(textureSize);
var result1 = new Vector3[textureSize, textureSize];
var result2 = new Vector3[textureSize, textureSize];
var result3 = new Vector3[textureSize, textureSize];
var sw1 = Inline(pointCloud, result1);
var sw2 = NotInline(pointCloud, result2);
var sw3 = Parallelized(pointCloud, result3);
Console.WriteLine("Completed {0}x{0} pixels with {1} points in...", textureSize, numPoints);
Console.WriteLine("{0}: {1}ms", "For Loop (Inline)", sw1.ElapsedMilliseconds);
Console.WriteLine("{0}: {1}ms", "For Loop", sw2.ElapsedMilliseconds);
Console.WriteLine("{0}: {1}ms", "Parallel.For Loop", sw3.ElapsedMilliseconds);
Console.WriteLine();
Console.Write("Verifying Data: ");
Console.WriteLine(CheckResults(result1, result2) && CheckResults(result1, result3) ? "Valid" : "Error");
Console.WriteLine();
Console.WriteLine();
Console.ReadLine();
}
}
private static Stopwatch Parallelized(Vector3[] pointCloud, Vector3[,] result3)
{
var sw3 = Stopwatch.StartNew();
Parallel.For(0, textureSize, x =>
{
for (int y = 0; y < textureSize; y++)
Computation(pointCloud, result3, x, y);
});
sw3.Stop();
return sw3;
}
private static Stopwatch NotInline(Vector3[] pointCloud, Vector3[,] result2)
{
var sw2 = Stopwatch.StartNew();
for (int x = 0; x < textureSize; x++)
for (int y = 0; y < textureSize; y++)
Computation(pointCloud, result2, x, y);
sw2.Stop();
return sw2;
}
private static Stopwatch Inline(Vector3[] pointCloud, Vector3[,] result1)
{
var sw1 = Stopwatch.StartNew();
for (int x = 0; x < textureSize; x++)
for (int y = 0; y < textureSize; y++)
{
var targetPos = new Vector3(x, y, 0);
var nearestV3 = pointCloud[0];
Vector3 temp1 = new Vector3(nearestV3.x - targetPos.x, nearestV3.y - targetPos.y, nearestV3.z - targetPos.z);
var nearestV3Distance = temp1.x * temp1.x + temp1.y * temp1.y + temp1.z * temp1.z;
for (int i = 1; i < numPoints; i++)
{
var currentV3 = pointCloud[i];
Vector3 temp2 = new Vector3(currentV3.x - targetPos.x, currentV3.y - targetPos.y, currentV3.z - targetPos.z);
var currentV3Distance = temp2.x * temp2.x + temp2.y * temp2.y + temp2.z * temp2.z;
if (currentV3Distance < nearestV3Distance)
{
nearestV3 = currentV3;
nearestV3Distance = currentV3Distance;
}
}
result1[x, y] = nearestV3;
}
sw1.Stop();
return sw1;
}
private static bool CheckResults(Vector3[,] lhs, Vector3[,] rhs)
{
for (int x = 0; x < textureSize; x++)
for (int y = 0; y < textureSize; y++)
if (!lhs[x, y].Equals(rhs[x, y]))
return false;
return true;
}
private static void Computation(Vector3[] pointCloud, Vector3[,] result, int x, int y)
{
var targetPos = new Vector3(x, y, 0);
var nearestV3 = pointCloud[0];
Vector3 temp1 = new Vector3(nearestV3.x - targetPos.x, nearestV3.y - targetPos.y, nearestV3.z - targetPos.z);
var nearestV3Distance = temp1.x * temp1.x + temp1.y * temp1.y + temp1.z * temp1.z;
for (int i = 1; i < numPoints; i++)
{
var currentV3 = pointCloud[i];
Vector3 temp2 = new Vector3(currentV3.x - targetPos.x, currentV3.y - targetPos.y, currentV3.z - targetPos.z);
var currentV3Distance = temp2.x * temp2.x + temp2.y * temp2.y + temp2.z * temp2.z;
if (currentV3Distance < nearestV3Distance)
{
nearestV3 = currentV3;
nearestV3Distance = currentV3Distance;
}
}
result[x, y] = nearestV3;
}
struct Vector3
{
public float x;
public float y;
public float z;
public Vector3(float x, float y, float z)
{
this.x = x;
this.y = y;
this.z = z;
}
public Vector3(float randomDistance)
{
this.x = (float)rnd.NextDouble() * randomDistance;
this.y = (float)rnd.NextDouble() * randomDistance;
this.z = (float)rnd.NextDouble() * randomDistance;
}
}
}
}
它给出了以下结果：
x86
Completed 1024x1024 pixels with 700 points in...
For Loop (Inline): 3820ms
For Loop: 3962ms
Parallel.For Loop: 1681ms
x64
Completed 1024x1024 pixels with 700 points in...
For Loop (Inline): 10978ms
For Loop: 10924ms
Parallel.For Loop: 3073ms
所以好消息是，我们可以大幅提高此代码的性能 - 并使单线程版本的运行速度与并行表亲保持一致。
坏消息是，这意味着完全放弃 x64 并手动内联所有数学。
在这个阶段，我对编译器的性能非常失望 - 我希望它们会更好。
结论
这很令人沮丧和悲伤......虽然我们真的不知道为什么我们可以对它是由愚蠢的编译器引起的做出有根据的猜测。只需将编译器从 x64 更改为 x86 并进行一些手动内联，24 秒到 3.8 秒并不是我所期望的。然而，我已经完成了我正在编写的概念证明，并且由于一个简单的空间散列，我可以在 0.7 秒内计算出一个 1024 x 1024 的图像，其中包含 70,000 个“点”——比我原来的 x64 场景快约 340000%，并且没有螺纹或内衬。因此，我已经接受了一个答案——当前的需求已经消失，尽管我仍在调查这个问题。
【问题讨论】：
-
你的双核更像是 4 核，或者至少是 2+2。
-
@Henk Holterman，不，它有点像最新测试中的双 :P 一旦你把愚蠢的编译器排除在外，性能只有单核的 226% - 更多的是多亏了超线程，我对双核的预期 + 约 20-40% 的提升。
-
如果不说明测试等，单个数字有点毫无意义。我见过 2+2 达到 350% 以上的基准
-
@Henk Holterman - 我不仅说明了测试，还提供了代码。我感兴趣的是为什么我通常认为的默认快速高效代码非常缓慢且效率低下。这并不是要证明单线程很慢，而是要问为什么在为现实世界应用程序开发的代码上它IS很慢！
标签： c# multithreading optimization task-parallel-library