Related
I want to implement 2D convolution function in C++ by myself, without using filter2D(). I'm trying to iterate all pixels of input image and kernel, then, assign new value to each pixel of dst.
However, I got this error.
Thread 1: EXC_BAD_ACCESS (code=1, address=0x0)
I found that this error tells I'm accessing nullptr, but I could not solve the problem. Here is my c++ code.
cv::Mat_<float> spatialConvolution(const cv::Mat_<float>& src, const cv::Mat_<float>& kernel)
{
// declare variables
Mat_<float> dst;
Mat_<float> flipped_kernel;
float tmp = 0.0;
// flip kernel
flip(kernel, flipped_kernel, -1);
// multiply and integrate
// input rows
for(int i=0;i<src.rows;i++){
// input columns
for(int j=0;j<src.cols;j++){
// kernel rows
for(int k=0;k<flipped_kernel.rows;k++){
// kernel columns
for(int l=0;l<flipped_kernel.cols;l++){
tmp += src.at<float>(i,j) * flipped_kernel.at<float>(k,l);
}
}
dst.at<float>(i,j) = tmp;
}
}
return dst.clone();
}
To simplify let's suppose you have kernel 3x3
k(0,0) k(0,1) k(0,2)
k(1,0) k(1,1) k(1,2)
k(2,0) k(2,1) k(2,2)
to calculate convolution you are scanning input image (marked as I) from left to fright, from top to bottom
and for every pixel of input image you assign one value calculated from the formula below:
newValue(y,x) = I(y-1,x-1) * k(0,0) + I(y-1,x) * k(0,1) + I(y-1,x+1) * k(0,2)
+ I(y,x-1) * k(1,0) + I(y,x) * k(1,1) + I(y,x+1) * k(1,2) +
+ I(y+1,x-1) * k(2,0) + I(y+1,x) * k(2,1) + I(y+1,x+1) * k(2,2)
------------------x------------>
|
|
| [k(0,0) k(0,1) k(0,2)]
y [k(1,0) k(1,1) k(1,2)]
| [k(2,0) k(2,1) k(2,2)]
|
(y,x) of input Image (I) is anchor point of kernel, to assign new value to I(y,x)
you need to multiply every k coefficient by corresponding point of I - your code doesn't do it.
First you need to create dst matrix with dimenstion as original image, and the same type of pixel.
Then you need to rewrite your loops to reflect formula described above:
cv::Mat_<float> spatialConvolution(const cv::Mat_<float>& src, const cv::Mat_<float>& kernel)
{
Mat dst(src.rows,src.cols,src.type());
Mat_<float> flipped_kernel;
flip(kernel, flipped_kernel, -1);
const int dx = kernel.cols / 2;
const int dy = kernel.rows / 2;
for (int i = 0; i<src.rows; i++)
{
for (int j = 0; j<src.cols; j++)
{
float tmp = 0.0f;
for (int k = 0; k<flipped_kernel.rows; k++)
{
for (int l = 0; l<flipped_kernel.cols; l++)
{
int x = j - dx + l;
int y = i - dy + k;
if (x >= 0 && x < src.cols && y >= 0 && y < src.rows)
tmp += src.at<float>(y, x) * flipped_kernel.at<float>(k, l);
}
}
dst.at<float>(i, j) = saturate_cast<float>(tmp);
}
}
return dst.clone();
}
Your memory access error is presumably happening due to the line:
dst.at<float>(i,j) = tmp;
because dst is not initialized. You can't assign something to that index of the matrix if it has no size/data. Instead, initialize the matrix first, as Mat_<float> is a declaration, not an initialization. Use one of the initializations where you can specify a cv::Size or the rows/columns from the different constructors for Mat (see the docs). For example, you can initialize dst with:
Mat dst{src.size(), src.type()};
I profiled my code and the most expensive part of the code is the loop included in the post. I want to improve the performance of this loop using AVX. I have tried manually unrolling the loop and, while that does improve performance, the improvements are not satisfactory.
int N = 100000000;
int8_t* data = new int8_t[N];
for(int i = 0; i< N; i++) { data[i] = 1 ;}
std::array<float, 10> f = {1,2,3,4,5,6,7,8,9,10};
std::vector<float> output(N, 0);
int k = 0;
for (int i = k; i < N; i = i + 2) {
for (int j = 0; j < 10; j++, k = j + 1) {
output[i] += f[j] * data[i - k];
output[i + 1] += f[j] * data[i - k + 1];
}
}
Could I have some guidance on how to approach this.
I would assume that data is a large input array of signed bytes, and f is a small array of floats of length 10, and output is the large output array of floats. Your code goes out of bounds for the first 10 iterations by i, so I will start i from 10 instead. Here is a clean version of the original code:
int s = 10;
for (int i = s; i < N; i += 2) {
for (int j = 0; j < 10; j++) {
output[i] += f[j] * data[i-j-1];
output[i+1] += f[j] * data[i-j];
}
}
As it turns out, processing two iterations by i does not change anything, so we simplify it further to:
for (int i = s; i < N; i++)
for (int j = 0; j < 10; j++)
output[i] += f[j] * data[i-j-1];
This version of code (along with declarations of input/output data) should have been present in the question itself, without others having to clean/simplify the mess.
Now it is obvious that this code applies one-dimensional convolution filter, which is a very common thing in signal processing. For instance, it can by computed in Python using numpy.convolve function. The kernel has very small length 10, so Fast Fourier Transform won't provide any benefits compared to bruteforce approach. Given that the problem is well-known, you can read a lot of articles on vectorizing small-kernel convolution. I will follow the article by hgomersall.
First, let's get rid of reverse indexing. Obviously, we can reverse the kernel before running the main algorithm. After that, we have to compute the so-called cross-correlation instead of convolution. In simple words, we move the kernel array along the input array, and compute the dot product between them for every possible offset.
std::reverse(f.data(), f.data() + 10);
for (int i = s; i < N; i++) {
int b = i-10;
float res = 0.0;
for (int j = 0; j < 10; j++)
res += f[j] * data[b+j];
output[i] = res;
}
In order to vectorize it, let's compute 8 consecutive dot products at once. Recall that we can pack eight 32-bit float numbers into one 256-bit AVX register. We will vectorize the outer loop by i, which means that:
The loop by i will be advanced by 8 every iteration.
Every value inside the outer loop turns into a 8-element pack, such that k-th element of the pack holds this value for (i+k)-th iteration of the outer loop from the scalar version.
Here is the resulting code:
//reverse the kernel
__m256 revKernel[10];
for (size_t i = 0; i < 10; i++)
revKernel[i] = _mm256_set1_ps(f[9-i]); //every component will have same value
//note: you have to compute the last 16 values separately!
for (size_t i = s; i + 16 <= N; i += 8) {
int b = i-10;
__m256 res = _mm256_setzero_ps();
for (size_t j = 0; j < 10; j++) {
//load: data[b+j], data[b+j+1], data[b+j+2], ..., data[b+j+15]
__m128i bytes = _mm_loadu_si128((__m128i*)&data[b+j]);
//convert first 8 bytes of loaded 16-byte pack into 8 floats
__m256 floats = _mm256_cvtepi32_ps(_mm256_cvtepi8_epi32(bytes));
//compute res = res + floats * revKernel[j] elementwise
res = _mm256_fmadd_ps(revKernel[j], floats, res);
}
//store 8 values packed in res into: output[i], output[i+1], ..., output[i+7]
_mm256_storeu_ps(&output[i], res);
}
For 100 millions of elements, this code takes about 120 ms on my machine, while the original scalar implementation took 850 ms. Beware: I have Ryzen 1600 CPU, so results on Intel CPUs may be somewhat different.
Now if you really want to unroll something, the inner loop by 10 kernel elements is the perfect place. Here is how it is done:
__m256 revKernel[10];
for (size_t i = 0; i < 10; i++)
revKernel[i] = _mm256_set1_ps(f[9-i]);
for (size_t i = s; i + 16 <= N; i += 8) {
size_t b = i-10;
__m256 res = _mm256_setzero_ps();
#define DOIT(j) {\
__m128i bytes = _mm_loadu_si128((__m128i*)&data[b+j]); \
__m256 floats = _mm256_cvtepi32_ps(_mm256_cvtepi8_epi32(bytes)); \
res = _mm256_fmadd_ps(revKernel[j], floats, res); \
}
DOIT(0);
DOIT(1);
DOIT(2);
DOIT(3);
DOIT(4);
DOIT(5);
DOIT(6);
DOIT(7);
DOIT(8);
DOIT(9);
_mm256_storeu_ps(&output[i], res);
}
It takes 110 ms on my machine (slightly better that the first vectorized version).
The simple copy of all elements (with conversion from bytes to floats) takes 40 ms for me, which means that this code is not memory-bound yet, and there is still some room for improvement left.
My algorithm computes the vertices of a shape in 3-dimensional space by using a 2-dimensional loop iterating over the U and V segments.
for (LONG i=0; i < info.useg + 1; i++) {
// Calculate the u-parameter.
u = info.umin + i * info.udelta;
for (LONG j=0; j < info.vseg + 1; j++) {
// Calculate the v-parameter.
v = info.vmin + j * info.vdelta;
// Compute the point's position.
point = calc_point(op, &info, u, v);
// Set the point to the object and increase the point-index.
points[point_i] = point;
point_i++;
}
}
The array of points is however a one-dimensional array, which is why point_i is incremented in each loop. I know that I could compute the index via point_i = i * info.vseg + j.
I want this loop to be multithreaded. My aim was to create a number of threads that all process a specific range of points. In the thread, I'd do it like:
for (LONG x=start; x <= end; x++) {
LONG i = // ...
LONG j = // ...
Real u = info.umin + i * info.udelta;
Real v = info.vmin + j * info.vdelta;
points[i] = calc_point(op, &info, u, v);
}
The problem is to calculate the i and j indecies from the linear point-index. How can I compute i and j when (well I think):
point_i = i * vsegments + j
I'm unable to solve the math, here..
point_i = i * vsegments + j gives you:
i = point_i / vsegments
j = point_i % vsegments
Of course your loops actually do segments + 1 iterations each (indices 0 to segments), so you would need to use vsegments + 1 instead of vsegments
As a side note: Do you actually need to merge the loops into one for multithreading? I would expect the outer loop to have typically enough iterations to saturate your availible cores anyways.
I am trying to write an android app which needs to calculate gaussian and laplacian pyramids for multiple full resolution images, i wrote this it on C++ with NDK, the most critical part of the code is applying gaussian filter to images abd i am applying this filter with horizontally and vertically.
The filter is (0.0625, 0.25, 0.375, 0.25, 0.0625)
Since i am working on integers i am calculating (1, 4, 6, 4, 1)/16
dst[index] = ( src[index-2] + src[index-1]*4 + src[index]*6+src[index+1]*4+src[index+2])/16;
I have made a few simple optimization however it still is working slow than expected and i was wondering if there are any other optimization options that i am missing.
PS: I should mention that i have tried to write this filter part with inline arm assembly however it give 2x slower results.
//horizontal filter
for(unsigned y = 0; y < height; y++) {
for(unsigned x = 2; x < width-2; x++) {
int index = y*width+x;
dst[index].r = (src[index-2].r+ src[index+2].r + (src[index-1].r + src[index+1].r)*4 + src[index].r*6)>>4;
dst[index].g = (src[index-2].g+ src[index+2].g + (src[index-1].g + src[index+1].g)*4 + src[index].g*6)>>4;
dst[index].b = (src[index-2].b+ src[index+2].b + (src[index-1].b + src[index+1].b)*4 + src[index].b*6)>>4;
}
}
//vertical filter
for(unsigned y = 2; y < height-2; y++) {
for(unsigned x = 0; x < width; x++) {
int index = y*width+x;
dst[index].r = (src[index-2*width].r + src[index+2*width].r + (src[index-width].r + src[index+width].r)*4 + src[index].r*6)>>4;
dst[index].g = (src[index-2*width].g + src[index+2*width].g + (src[index-width].g + src[index+width].g)*4 + src[index].g*6)>>4;
dst[index].b = (src[index-2*width].b + src[index+2*width].b + (src[index-width].b + src[index+width].b)*4 + src[index].b*6)>>4;
}
}
The index multiplication can be factored out of the inner loop since the mulitplicatation only occurs when y is changed:
for (unsigned y ...
{
int index = y * width;
for (unsigned int x...
You may gain some speed by loading variables before you use them. This would make the processor load them in the cache:
for (unsigned x = ...
{
register YOUR_DATA_TYPE a, b, c, d, e;
a = src[index - 2].r;
b = src[index - 1].r;
c = src[index + 0].r; // The " + 0" is to show a pattern.
d = src[index + 1].r;
e = src[index + 2].r;
dest[index].r = (a + e + (b + d) * 4 + c * 6) >> 4;
// ...
Another trick would be to "cache" the values of the src so that only a new one is added each time because the value in src[index+2] may be used up to 5 times.
So here is a example of the concepts:
//horizontal filter
for(unsigned y = 0; y < height; y++)
{
int index = y*width + 2;
register YOUR_DATA_TYPE a, b, c, d, e;
a = src[index - 2].r;
b = src[index - 1].r;
c = src[index + 0].r; // The " + 0" is to show a pattern.
d = src[index + 1].r;
e = src[index + 2].r;
for(unsigned x = 2; x < width-2; x++)
{
dest[index - 2 + x].r = (a + e + (b + d) * 4 + c * 6) >> 4;
a = b;
b = c;
c = d;
d = e;
e = src[index + x].r;
I'm not sure how your compiler would optimize all this, but I tend to work in pointers. Assuming your struct is 3 bytes... You can start with pointers in the right places (the edge of the filter for source, and the destination for target), and just move them through using constant array offsets. I've also put in an optional OpenMP directive on the outer loop, as this can also improve things.
#pragma omp parallel for
for(unsigned y = 0; y < height; y++) {
const int rowindex = y * width;
char * dpos = (char*)&dest[rowindex+2];
char * spos = (char*)&src[rowindex];
const char *end = (char*)&src[rowindex+width-2];
for( ; spos != end; spos++, dpos++) {
*dpos = (spos[0] + spos[4] + ((spos[1] + src[3])<<2) + spos[2]*6) >> 4;
}
}
Similarly for the vertical loop.
const int scanwidth = width * 3;
const int row1 = scanwidth;
const int row2 = row1+scanwidth;
const int row3 = row2+scanwidth;
const int row4 = row3+scanwidth;
#pragma omp parallel for
for(unsigned y = 2; y < height-2; y++) {
const int rowindex = y * width;
char * dpos = (char*)&dest[rowindex];
char * spos = (char*)&src[rowindex-row2];
const char *end = spos + scanwidth;
for( ; spos != end; spos++, dpos++) {
*dpos = (spos[0] + spos[row4] + ((spos[row1] + src[row3])<<2) + spos[row2]*6) >> 4;
}
}
This is how I do convolutions, anyway. It sacrifices readability a little, and I've never tried measuring the difference. I just tend to write them that way from the outset. See if that gives you a speed-up. The OpenMP definitely will if you have a multicore machine, and the pointer stuff might.
I like the comment about using SSE for these operations.
Some of the more obvious optimizations are exploiting the symmetry of the kernel:
a=*src++; b=*src++; c=*src++; d=*src++; e=*src++; // init
LOOP (n/5) times:
z=(a+e)+(b+d)<<2+c*6; *dst++=z>>4; // then reuse the local variables
a=*src++;
z=(b+a)+(c+e)<<2+d*6; *dst++=z>>4; // registers have been read only once...
b=*src++;
z=(c+b)+(d+a)<<2+e*6; *dst++=z>>4;
e=*src++;
The second thing is that one can perform multiple additions using a single integer. When the values to be filtered are unsigned, one can fit two channels in a single 32-bit integer (or 4 channels in a 64-bit integer); it's the poor mans SIMD.
a= 0x[0011][0034] <-- split to two
b= 0x[0031][008a]
----------------------
sum 0042 00b0
>>4 0004 200b0 <-- mask off
mask 00ff 00ff
-------------------
0004 000b <-- result
(The Simulated SIMD shows one addition followed by a shift by 4)
Here's a kernel that calculates 3 rgb operations in parallel (easy to modify for 6 rgb operations in 64-bit architectures...)
#define MASK (255+(255<<10)+(255<<20))
#define KERNEL(a,b,c,d,e) { \
a=((a+e+(c<<1))>>2) & MASK; a=(a+b+c+d)>>2 & MASK; *DATA++ = a; a=DATA[4]; }
void calc_5_rgbs(unsigned int *DATA)
{
register unsigned int a = DATA[0], b=DATA[1], c=DATA[2], d=DATA[3], e=DATA[4];
KERNEL(a,b,c,d,e);
KERNEL(b,c,d,e,a);
KERNEL(c,d,e,a,b);
KERNEL(d,e,a,b,c);
KERNEL(e,a,b,c,d);
}
Works best on ARM and on 64-bit IA with 16 registers... Needs heavy assembler optimizations to overcome register shortage in 32-bit IA (e.g. use ebp as GPR). And just because of that it's an inplace algorithm...
There are just 2 guardian bits between every 8 bits of data, which is just enough to get exactly the same result as in integer calculation.
And BTW: it's faster to just run through the array byte per byte than by r,g,b elements
unsigned char *s=(unsigned char *) source_array;
unsigned char *d=(unsigned char *) dest_array;
for (j=0;j<3*N;j++) d[j]=(s[j]+s[j+16]+s[j+8]*6+s[j+4]*4+s[j+12]*4)>>4;
I'm writing a sparse matrix solver using the Gauss-Seidel method. By profiling, I've determined that about half of my program's time is spent inside the solver. The performance-critical part is as follows:
size_t ic = d_ny + 1, iw = d_ny, ie = d_ny + 2, is = 1, in = 2 * d_ny + 1;
for (size_t y = 1; y < d_ny - 1; ++y) {
for (size_t x = 1; x < d_nx - 1; ++x) {
d_x[ic] = d_b[ic]
- d_w[ic] * d_x[iw] - d_e[ic] * d_x[ie]
- d_s[ic] * d_x[is] - d_n[ic] * d_x[in];
++ic; ++iw; ++ie; ++is; ++in;
}
ic += 2; iw += 2; ie += 2; is += 2; in += 2;
}
All arrays involved are of float type. Actually, they are not arrays but objects with an overloaded [] operator, which (I think) should be optimized away, but is defined as follows:
inline float &operator[](size_t i) { return d_cells[i]; }
inline float const &operator[](size_t i) const { return d_cells[i]; }
For d_nx = d_ny = 128, this can be run about 3500 times per second on an Intel i7 920. This means that the inner loop body runs 3500 * 128 * 128 = 57 million times per second. Since only some simple arithmetic is involved, that strikes me as a low number for a 2.66 GHz processor.
Maybe it's not limited by CPU power, but by memory bandwidth? Well, one 128 * 128 float array eats 65 kB, so all 6 arrays should easily fit into the CPU's L3 cache (which is 8 MB). Assuming that nothing is cached in registers, I count 15 memory accesses in the inner loop body. On a 64-bits system this is 120 bytes per iteration, so 57 million * 120 bytes = 6.8 GB/s. The L3 cache runs at 2.66 GHz, so it's the same order of magnitude. My guess is that memory is indeed the bottleneck.
To speed this up, I've attempted the following:
Compile with g++ -O3. (Well, I'd been doing this from the beginning.)
Parallelizing over 4 cores using OpenMP pragmas. I have to change to the Jacobi algorithm to avoid reads from and writes to the same array. This requires that I do twice as many iterations, leading to a net result of about the same speed.
Fiddling with implementation details of the loop body, such as using pointers instead of indices. No effect.
What's the best approach to speed this guy up? Would it help to rewrite the inner body in assembly (I'd have to learn that first)? Should I run this on the GPU instead (which I know how to do, but it's such a hassle)? Any other bright ideas?
(N.B. I do take "no" for an answer, as in: "it can't be done significantly faster, because...")
Update: as requested, here's a full program:
#include <iostream>
#include <cstdlib>
#include <cstring>
using namespace std;
size_t d_nx = 128, d_ny = 128;
float *d_x, *d_b, *d_w, *d_e, *d_s, *d_n;
void step() {
size_t ic = d_ny + 1, iw = d_ny, ie = d_ny + 2, is = 1, in = 2 * d_ny + 1;
for (size_t y = 1; y < d_ny - 1; ++y) {
for (size_t x = 1; x < d_nx - 1; ++x) {
d_x[ic] = d_b[ic]
- d_w[ic] * d_x[iw] - d_e[ic] * d_x[ie]
- d_s[ic] * d_x[is] - d_n[ic] * d_x[in];
++ic; ++iw; ++ie; ++is; ++in;
}
ic += 2; iw += 2; ie += 2; is += 2; in += 2;
}
}
void solve(size_t iters) {
for (size_t i = 0; i < iters; ++i) {
step();
}
}
void clear(float *a) {
memset(a, 0, d_nx * d_ny * sizeof(float));
}
int main(int argc, char **argv) {
size_t n = d_nx * d_ny;
d_x = new float[n]; clear(d_x);
d_b = new float[n]; clear(d_b);
d_w = new float[n]; clear(d_w);
d_e = new float[n]; clear(d_e);
d_s = new float[n]; clear(d_s);
d_n = new float[n]; clear(d_n);
solve(atoi(argv[1]));
cout << d_x[0] << endl; // prevent the thing from being optimized away
}
I compile and run it as follows:
$ g++ -o gstest -O3 gstest.cpp
$ time ./gstest 8000
0
real 0m1.052s
user 0m1.050s
sys 0m0.010s
(It does 8000 instead of 3500 iterations per second because my "real" program does a lot of other stuff too. But it's representative.)
Update 2: I've been told that unititialized values may not be representative because NaN and Inf values may slow things down. Now clearing the memory in the example code. It makes no difference for me in execution speed, though.
Couple of ideas:
Use SIMD. You could load 4 floats at a time from each array into a SIMD register (e.g. SSE on Intel, VMX on PowerPC). The disadvantage of this is that some of the d_x values will be "stale" so your convergence rate will suffer (but not as bad as a jacobi iteration); it's hard to say whether the speedup offsets it.
Use SOR. It's simple, doesn't add much computation, and can improve your convergence rate quite well, even for a relatively conservative relaxation value (say 1.5).
Use conjugate gradient. If this is for the projection step of a fluid simulation (i.e. enforcing non-compressability), you should be able to apply CG and get a much better convergence rate. A good preconditioner helps even more.
Use a specialized solver. If the linear system arises from the Poisson equation, you can do even better than conjugate gradient using an FFT-based methods.
If you can explain more about what the system you're trying to solve looks like, I can probably give some more advice on #3 and #4.
I think I've managed to optimize it, here's a code, create a new project in VC++, add this code and simply compile under "Release".
#include <iostream>
#include <cstdlib>
#include <cstring>
#define _WIN32_WINNT 0x0400
#define WIN32_LEAN_AND_MEAN
#include <windows.h>
#include <conio.h>
using namespace std;
size_t d_nx = 128, d_ny = 128;
float *d_x, *d_b, *d_w, *d_e, *d_s, *d_n;
void step_original() {
size_t ic = d_ny + 1, iw = d_ny, ie = d_ny + 2, is = 1, in = 2 * d_ny + 1;
for (size_t y = 1; y < d_ny - 1; ++y) {
for (size_t x = 1; x < d_nx - 1; ++x) {
d_x[ic] = d_b[ic]
- d_w[ic] * d_x[iw] - d_e[ic] * d_x[ie]
- d_s[ic] * d_x[is] - d_n[ic] * d_x[in];
++ic; ++iw; ++ie; ++is; ++in;
}
ic += 2; iw += 2; ie += 2; is += 2; in += 2;
}
}
void step_new() {
//size_t ic = d_ny + 1, iw = d_ny, ie = d_ny + 2, is = 1, in = 2 * d_ny + 1;
float
*d_b_ic,
*d_w_ic,
*d_e_ic,
*d_x_ic,
*d_x_iw,
*d_x_ie,
*d_x_is,
*d_x_in,
*d_n_ic,
*d_s_ic;
d_b_ic = d_b;
d_w_ic = d_w;
d_e_ic = d_e;
d_x_ic = d_x;
d_x_iw = d_x;
d_x_ie = d_x;
d_x_is = d_x;
d_x_in = d_x;
d_n_ic = d_n;
d_s_ic = d_s;
for (size_t y = 1; y < d_ny - 1; ++y)
{
for (size_t x = 1; x < d_nx - 1; ++x)
{
/*d_x[ic] = d_b[ic]
- d_w[ic] * d_x[iw] - d_e[ic] * d_x[ie]
- d_s[ic] * d_x[is] - d_n[ic] * d_x[in];*/
*d_x_ic = *d_b_ic
- *d_w_ic * *d_x_iw - *d_e_ic * *d_x_ie
- *d_s_ic * *d_x_is - *d_n_ic * *d_x_in;
//++ic; ++iw; ++ie; ++is; ++in;
d_b_ic++;
d_w_ic++;
d_e_ic++;
d_x_ic++;
d_x_iw++;
d_x_ie++;
d_x_is++;
d_x_in++;
d_n_ic++;
d_s_ic++;
}
//ic += 2; iw += 2; ie += 2; is += 2; in += 2;
d_b_ic += 2;
d_w_ic += 2;
d_e_ic += 2;
d_x_ic += 2;
d_x_iw += 2;
d_x_ie += 2;
d_x_is += 2;
d_x_in += 2;
d_n_ic += 2;
d_s_ic += 2;
}
}
void solve_original(size_t iters) {
for (size_t i = 0; i < iters; ++i) {
step_original();
}
}
void solve_new(size_t iters) {
for (size_t i = 0; i < iters; ++i) {
step_new();
}
}
void clear(float *a) {
memset(a, 0, d_nx * d_ny * sizeof(float));
}
int main(int argc, char **argv) {
size_t n = d_nx * d_ny;
d_x = new float[n]; clear(d_x);
d_b = new float[n]; clear(d_b);
d_w = new float[n]; clear(d_w);
d_e = new float[n]; clear(d_e);
d_s = new float[n]; clear(d_s);
d_n = new float[n]; clear(d_n);
if(argc < 3)
printf("app.exe (x)iters (o/n)algo\n");
bool bOriginalStep = (argv[2][0] == 'o');
size_t iters = atoi(argv[1]);
/*printf("Press any key to start!");
_getch();
printf(" Running speed test..\n");*/
__int64 freq, start, end, diff;
if(!::QueryPerformanceFrequency((LARGE_INTEGER*)&freq))
throw "Not supported!";
freq /= 1000000; // microseconds!
{
::QueryPerformanceCounter((LARGE_INTEGER*)&start);
if(bOriginalStep)
solve_original(iters);
else
solve_new(iters);
::QueryPerformanceCounter((LARGE_INTEGER*)&end);
diff = (end - start) / freq;
}
printf("Speed (%s)\t\t: %u\n", (bOriginalStep ? "original" : "new"), diff);
//_getch();
//cout << d_x[0] << endl; // prevent the thing from being optimized away
}
Run it like this:
app.exe 10000 o
app.exe 10000 n
"o" means old code, yours.
"n" is mine, the new one.
My results:
Speed (original):
1515028
1523171
1495988
Speed (new):
966012
984110
1006045
Improvement of about 30%.
The logic behind:
You've been using index counters to access/manipulate.
I use pointers.
While running, breakpoint at a certain calculation code line in VC++'s debugger, and press F8. You'll get the disassembler window.
The you'll see the produced opcodes (assembly code).
Anyway, look:
int *x = ...;
x[3] = 123;
This tells the PC to put the pointer x at a register (say EAX).
The add it (3 * sizeof(int)).
Only then, set the value to 123.
The pointers approach is much better as you can understand, because we cut the adding process, actually we handle it ourselves, thus able to optimize as needed.
I hope this helps.
Sidenote to stackoverflow.com's staff:
Great website, I hope I've heard of it long ago!
For one thing, there seems to be a pipelining issue here. The loop reads from the value in d_x that has just been written to, but apparently it has to wait for that write to complete. Just rearranging the order of the computation, doing something useful while it's waiting, makes it almost twice as fast:
d_x[ic] = d_b[ic]
- d_e[ic] * d_x[ie]
- d_s[ic] * d_x[is] - d_n[ic] * d_x[in]
- d_w[ic] * d_x[iw] /* d_x[iw] has just been written to, process this last */;
It was Eamon Nerbonne who figured this out. Many upvotes to him! I would never have guessed.
Poni's answer looks like the right one to me.
I just want to point out that in this type of problem, you often gain benefits from memory locality. Right now, the b,w,e,s,n arrays are all at separate locations in memory. If you could not fit the problem in L3 cache (mostly in L2), then this would be bad, and a solution of this sort would be helpful:
size_t d_nx = 128, d_ny = 128;
float *d_x;
struct D { float b,w,e,s,n; };
D *d;
void step() {
size_t ic = d_ny + 1, iw = d_ny, ie = d_ny + 2, is = 1, in = 2 * d_ny + 1;
for (size_t y = 1; y < d_ny - 1; ++y) {
for (size_t x = 1; x < d_nx - 1; ++x) {
d_x[ic] = d[ic].b
- d[ic].w * d_x[iw] - d[ic].e * d_x[ie]
- d[ic].s * d_x[is] - d[ic].n * d_x[in];
++ic; ++iw; ++ie; ++is; ++in;
}
ic += 2; iw += 2; ie += 2; is += 2; in += 2;
}
}
void solve(size_t iters) { for (size_t i = 0; i < iters; ++i) step(); }
void clear(float *a) { memset(a, 0, d_nx * d_ny * sizeof(float)); }
int main(int argc, char **argv) {
size_t n = d_nx * d_ny;
d_x = new float[n]; clear(d_x);
d = new D[n]; memset(d,0,n * sizeof(D));
solve(atoi(argv[1]));
cout << d_x[0] << endl; // prevent the thing from being optimized away
}
For example, this solution at 1280x1280 is a little less than 2x faster than Poni's solution (13s vs 23s in my test--your original implementation is then 22s), while at 128x128 it's 30% slower (7s vs. 10s--your original is 10s).
(Iterations were scaled up to 80000 for the base case, and 800 for the 100x larger case of 1280x1280.)
I think you're right about memory being a bottleneck. It's a pretty simple loop with just some simple arithmetic per iteration. the ic, iw, ie, is, and in indices seem to be on opposite sides of the matrix so i'm guessing that there's a bunch of cache misses there.
I'm no expert on the subject, but I've seen that there are several academic papers on improving the cache usage of the Gauss-Seidel method.
Another possible optimization is the use of the red-black variant, where points are updated in two sweeps in a chessboard-like pattern. In this way, all updates in a sweep are independent and can be parallelized.
I suggest putting in some prefetch statements and also researching "data oriented design":
void step_original() {
size_t ic = d_ny + 1, iw = d_ny, ie = d_ny + 2, is = 1, in = 2 * d_ny + 1;
float dw_ic, dx_ic, db_ic, de_ic, dn_ic, ds_ic;
float dx_iw, dx_is, dx_ie, dx_in, de_ic, db_ic;
for (size_t y = 1; y < d_ny - 1; ++y) {
for (size_t x = 1; x < d_nx - 1; ++x) {
// Perform the prefetch
// Sorting these statements by array may increase speed;
// although sorting by index name may increase speed too.
db_ic = d_b[ic];
dw_ic = d_w[ic];
dx_iw = d_x[iw];
de_ic = d_e[ic];
dx_ie = d_x[ie];
ds_ic = d_s[ic];
dx_is = d_x[is];
dn_ic = d_n[ic];
dx_in = d_x[in];
// Calculate
d_x[ic] = db_ic
- dw_ic * dx_iw - de_ic * dx_ie
- ds_ic * dx_is - dn_ic * dx_in;
++ic; ++iw; ++ie; ++is; ++in;
}
ic += 2; iw += 2; ie += 2; is += 2; in += 2;
}
}
This differs from your second method since the values are copied to local temporary variables before the calculation is performed.