解释 visual studio profiler,这个减法是不是很慢?我能让这一切变得更快吗?
Interpreting visual studio profiler, is this subtraction slow? Can I make all this any faster?
我是第一次使用 Visual Studio 探查器,我正在尝试解释结果。看左边的百分比,我发现这个减法的时间有点耗费st运行ge:
代码的其他部分包含更复杂的表达式,例如:
即使是简单的乘法似乎也比减法快得多:
其他乘法需要更长的时间,我真的不明白为什么,就像这样:
所以,我想我的问题是这里是否发生了什么奇怪的事情。
复杂的表达式比减法花费的时间更长,并且某些表达式比其他类似的表达式花费的时间更长。我 运行 多次分析器,百分比的分布总是这样。我只是解释错了吗?
更新:
我被要求提供整个功能的配置文件,所以就在这里,尽管它有点大。我 运行 for 循环中的函数运行了 1 分钟,得到了 50k 个样本。该函数包含一个双循环。为了方便起见,我首先包含文本,然后是分析图片。请注意,文本中的代码有点更新。
for (int i = 0; i < NUMBER_OF_CONTOUR_POINTS; i++) {
vec4 contourPointV(contour3DPoints[i], 1);
float phi = angles[i];
float xW = pose[0][0] * contourPointV.x + pose[1][0] * contourPointV.y + contourPointV.z * pose[2][0] + pose[3][0];
float yW = pose[0][1] * contourPointV.x + pose[1][1] * contourPointV.y + contourPointV.z * pose[2][1] + pose[3][1];
float zW = pose[0][2] * contourPointV.x + pose[1][2] * contourPointV.y + contourPointV.z * pose[2][2] + pose[3][2];
float x = -G_FU_STRICT * xW / zW;
float y = -G_FV_STRICT * yW / zW;
x = (x + 1) * G_WIDTHo2;
y = (y + 1) * G_HEIGHTo2;
y = G_HEIGHT - y;
phi -= extraTheta;
if (phi < 0)phi += CV_PI2;
int indexForTable = phi * oneKoverPI;
//vec2 ray(cos(phi), sin(phi));
vec2 ray(cos_pre[indexForTable], sin_pre[indexForTable]);
vec2 ray2(-ray.x, -ray.y);
float outerStepX = ray.x * step;
float outerStepY = ray.y * step;
cv::Point2f outerPoint(x + outerStepX, y + outerStepY);
cv::Point2f innerPoint(x - outerStepX, y - outerStepY);
cv::Point2f contourPointCV(x, y);
cv::Point2f contourPointCVcopy(x, y);
bool cut = false;
if (!isInView(outerPoint.x, outerPoint.y) || !isInView(innerPoint.x, innerPoint.y)) {
cut = true;
}
bool outside2 = true; bool outside1 = true;
if (cut) {
outside2 = myClipLine(contourPointCV.x, contourPointCV.y, outerPoint.x, outerPoint.y, G_WIDTH - 1, G_HEIGHT - 1);
outside1 = myClipLine(contourPointCVcopy.x, contourPointCVcopy.y, innerPoint.x, innerPoint.y, G_WIDTH - 1, G_HEIGHT - 1);
}
myIterator innerRayMine(contourPointCVcopy, innerPoint);
myIterator outerRayMine(contourPointCV, outerPoint);
if (!outside1) {
innerRayMine.end = true;
innerRayMine.prob = true;
}
if (!outside2) {
outerRayMine.end = true;
innerRayMine.prob = true;
}
vec2 normal = -ray;
float dfdxTerm = -normal.x;
float dfdyTerm = normal.y;
vec3 point3D = vec3(xW, yW, zW);
cv::Point contourPoint((int)x, (int)y);
float Xc = point3D.x; float Xc2 = Xc * Xc; float Yc = point3D.y; float Yc2 = Yc * Yc; float Zc = point3D.z; float Zc2 = Zc * Zc;
float XcYc = Xc * Yc; float dfdxFu = dfdxTerm * G_FU; float dfdyFv = dfdyTerm * G_FU; float overZc2 = 1 / Zc2; float overZc = 1 / Zc;
pixelJacobi[0] = (dfdyFv * (Yc2 + Zc2) + dfdxFu * XcYc) * overZc2;
pixelJacobi[1] = (-dfdxFu * (Xc2 + Zc2) - dfdyFv * XcYc) * overZc2;
pixelJacobi[2] = (-dfdyFv * Xc + dfdxFu * Yc) * overZc;
pixelJacobi[3] = -dfdxFu * overZc;
pixelJacobi[4] = -dfdyFv * overZc;
pixelJacobi[5] = (dfdyFv * Yc + dfdxFu * Xc) * overZc2;
float commonFirstTermsSum = 0;
float commonFirstTermsSquaredSum = 0;
int test = 0;
while (!innerRayMine.end) {
test++;
cv::Point xy = innerRayMine.pos(); innerRayMine++;
int x = xy.x;
int y = xy.y;
float dx = x - contourPoint.x;
float dy = y - contourPoint.y;
vec2 dxdy(dx, dy);
float raw = -glm::dot(dxdy, normal);
float heavisideTerm = heaviside_pre[(int)raw * 100 + 1000];
float deltaTerm = delta_pre[(int)raw * 100 + 1000];
const Vec3b rgb = ante[y * 640 + x];
int red = rgb[0]; int green = rgb[1]; int blue = rgb[2];
red = red >> 3; red = red << 10; green = green >> 3; green = green << 5; blue = blue >> 3;
int colorIndex = red + green + blue;
pF = pFPointer[colorIndex];
pB = pBPointer[colorIndex];
float denAsMul = 1 / (pF + pB + 0.000001);
pF = pF * denAsMul;
float pfMinusPb = 2 * pF - 1;
float denominator = heavisideTerm * (pfMinusPb)+pB + 0.000001;
float commonFirstTerm = -pfMinusPb / denominator * deltaTerm;
commonFirstTermsSum += commonFirstTerm;
commonFirstTermsSquaredSum += commonFirstTerm * commonFirstTerm;
}
}
Visual Studio profiles by sampling:经常中断执行,记录指令指针的值;然后它将它映射到源并计算命中该行的频率。
这有一些问题:在优化代码中并不总是能够找出哪一行产生了特定的汇编指令。
我使用的一个技巧是将感兴趣的代码移到一个单独的函数中,并用 __declspec(noinline)
声明它。
在您的示例中,您确定减法执行的次数与乘法执行的次数一样多吗?我会更困惑的是后续乘法的差异(0.39%
和0.53%
)
更新:
我相信以下几行:
float phi = angles[i];
和
phi -= extraTheta;
在组装中一起移动,angles[i]
所花费的时间被添加到该减法线。
我是第一次使用 Visual Studio 探查器,我正在尝试解释结果。看左边的百分比,我发现这个减法的时间有点耗费st运行ge:
代码的其他部分包含更复杂的表达式,例如:
即使是简单的乘法似乎也比减法快得多:
其他乘法需要更长的时间,我真的不明白为什么,就像这样:
所以,我想我的问题是这里是否发生了什么奇怪的事情。
复杂的表达式比减法花费的时间更长,并且某些表达式比其他类似的表达式花费的时间更长。我 运行 多次分析器,百分比的分布总是这样。我只是解释错了吗?
更新:
我被要求提供整个功能的配置文件,所以就在这里,尽管它有点大。我 运行 for 循环中的函数运行了 1 分钟,得到了 50k 个样本。该函数包含一个双循环。为了方便起见,我首先包含文本,然后是分析图片。请注意,文本中的代码有点更新。
for (int i = 0; i < NUMBER_OF_CONTOUR_POINTS; i++) {
vec4 contourPointV(contour3DPoints[i], 1);
float phi = angles[i];
float xW = pose[0][0] * contourPointV.x + pose[1][0] * contourPointV.y + contourPointV.z * pose[2][0] + pose[3][0];
float yW = pose[0][1] * contourPointV.x + pose[1][1] * contourPointV.y + contourPointV.z * pose[2][1] + pose[3][1];
float zW = pose[0][2] * contourPointV.x + pose[1][2] * contourPointV.y + contourPointV.z * pose[2][2] + pose[3][2];
float x = -G_FU_STRICT * xW / zW;
float y = -G_FV_STRICT * yW / zW;
x = (x + 1) * G_WIDTHo2;
y = (y + 1) * G_HEIGHTo2;
y = G_HEIGHT - y;
phi -= extraTheta;
if (phi < 0)phi += CV_PI2;
int indexForTable = phi * oneKoverPI;
//vec2 ray(cos(phi), sin(phi));
vec2 ray(cos_pre[indexForTable], sin_pre[indexForTable]);
vec2 ray2(-ray.x, -ray.y);
float outerStepX = ray.x * step;
float outerStepY = ray.y * step;
cv::Point2f outerPoint(x + outerStepX, y + outerStepY);
cv::Point2f innerPoint(x - outerStepX, y - outerStepY);
cv::Point2f contourPointCV(x, y);
cv::Point2f contourPointCVcopy(x, y);
bool cut = false;
if (!isInView(outerPoint.x, outerPoint.y) || !isInView(innerPoint.x, innerPoint.y)) {
cut = true;
}
bool outside2 = true; bool outside1 = true;
if (cut) {
outside2 = myClipLine(contourPointCV.x, contourPointCV.y, outerPoint.x, outerPoint.y, G_WIDTH - 1, G_HEIGHT - 1);
outside1 = myClipLine(contourPointCVcopy.x, contourPointCVcopy.y, innerPoint.x, innerPoint.y, G_WIDTH - 1, G_HEIGHT - 1);
}
myIterator innerRayMine(contourPointCVcopy, innerPoint);
myIterator outerRayMine(contourPointCV, outerPoint);
if (!outside1) {
innerRayMine.end = true;
innerRayMine.prob = true;
}
if (!outside2) {
outerRayMine.end = true;
innerRayMine.prob = true;
}
vec2 normal = -ray;
float dfdxTerm = -normal.x;
float dfdyTerm = normal.y;
vec3 point3D = vec3(xW, yW, zW);
cv::Point contourPoint((int)x, (int)y);
float Xc = point3D.x; float Xc2 = Xc * Xc; float Yc = point3D.y; float Yc2 = Yc * Yc; float Zc = point3D.z; float Zc2 = Zc * Zc;
float XcYc = Xc * Yc; float dfdxFu = dfdxTerm * G_FU; float dfdyFv = dfdyTerm * G_FU; float overZc2 = 1 / Zc2; float overZc = 1 / Zc;
pixelJacobi[0] = (dfdyFv * (Yc2 + Zc2) + dfdxFu * XcYc) * overZc2;
pixelJacobi[1] = (-dfdxFu * (Xc2 + Zc2) - dfdyFv * XcYc) * overZc2;
pixelJacobi[2] = (-dfdyFv * Xc + dfdxFu * Yc) * overZc;
pixelJacobi[3] = -dfdxFu * overZc;
pixelJacobi[4] = -dfdyFv * overZc;
pixelJacobi[5] = (dfdyFv * Yc + dfdxFu * Xc) * overZc2;
float commonFirstTermsSum = 0;
float commonFirstTermsSquaredSum = 0;
int test = 0;
while (!innerRayMine.end) {
test++;
cv::Point xy = innerRayMine.pos(); innerRayMine++;
int x = xy.x;
int y = xy.y;
float dx = x - contourPoint.x;
float dy = y - contourPoint.y;
vec2 dxdy(dx, dy);
float raw = -glm::dot(dxdy, normal);
float heavisideTerm = heaviside_pre[(int)raw * 100 + 1000];
float deltaTerm = delta_pre[(int)raw * 100 + 1000];
const Vec3b rgb = ante[y * 640 + x];
int red = rgb[0]; int green = rgb[1]; int blue = rgb[2];
red = red >> 3; red = red << 10; green = green >> 3; green = green << 5; blue = blue >> 3;
int colorIndex = red + green + blue;
pF = pFPointer[colorIndex];
pB = pBPointer[colorIndex];
float denAsMul = 1 / (pF + pB + 0.000001);
pF = pF * denAsMul;
float pfMinusPb = 2 * pF - 1;
float denominator = heavisideTerm * (pfMinusPb)+pB + 0.000001;
float commonFirstTerm = -pfMinusPb / denominator * deltaTerm;
commonFirstTermsSum += commonFirstTerm;
commonFirstTermsSquaredSum += commonFirstTerm * commonFirstTerm;
}
}
Visual Studio profiles by sampling:经常中断执行,记录指令指针的值;然后它将它映射到源并计算命中该行的频率。
这有一些问题:在优化代码中并不总是能够找出哪一行产生了特定的汇编指令。
我使用的一个技巧是将感兴趣的代码移到一个单独的函数中,并用 __declspec(noinline)
声明它。
在您的示例中,您确定减法执行的次数与乘法执行的次数一样多吗?我会更困惑的是后续乘法的差异(0.39%
和0.53%
)
更新:
我相信以下几行:
float phi = angles[i];
和
phi -= extraTheta;
在组装中一起移动,angles[i]
所花费的时间被添加到该减法线。