240
edits
Changes
→Attempt 1:
== Team Members ==
# [mailto:mavillaflor@myseneca.ca?subject=GPU610 Mark Anthony Villaflor] (Leader; Wiki; Maze)# [mailto:hli206@myseneca.ca?subject=GPU610 Huachen Li] (Wiki; Prime Numbers)
# [mailto:ylei11@myseneca.ca?subject=GPU610 Yanhao Lei] (Wiki; Pi)
[mailto:mavillaflor@myseneca.ca;hli206@myseneca.ca;ylei11@myseneca.ca?subject=GPU610 eMail All]
* February 10, 2017 - Completed Phase 1 (Select and Assess)
* March 20, 2017 - Added instructions to compile and execute Maze in Visual Studio
* April 4, 2017 - Updated Phase 2 and 3
== PHASE 1 ==
0.00 3.84 0.00 1 0.00 0.00 _GLOBAL__sub_I__ZN9MazeDebugC2Ejj
0.00 3.84 0.00 1 0.00 0.00 _GLOBAL__sub_I_main
*Profiling with windows environment:
[[File:SDiagram.PNG]]
'''Summary:'''
=== Maze ===
[[File:Out2.png|thumb|Maze 3x3]]
[[File:Out1.png|thumb|Maze 10x10]]
'''Introduction:'''
The Maze program (by corzani@github) generates a maze image (of type PNG).
The following function creates the canvas of the Maze and initialize it by filling all the hexadecimal within each pixel. After the canvas is filled, the function calls the createImage function. Finally, the function write the result from the createImage function in a png file using the "lpng" extension.
void MazePng::toPng(unsigned int scale) {
...
color_type = PNG_COLOR_TYPE_RGB;
bit_depth = 8;
row_pointers = new png_bytep[height];
// This for loop filling all the hexadecimal within each pixel.
for (int i = 0; i < height; ++i) {
row_pointers[i] = new png_byte[width * 3];
// The inner for loop fills all three colours (red, green, blue) to the pixel.
for (int j = 0; j < width * 3; j += 3) {
row_pointers[i][j] = WALL;
row_pointers[i][j + 1] = WALL;
row_pointers[i][j + 2] = WALL;
}
}
createImage(row_pointers, 0);
...
}
The following function carves the path of the Maze by changing the colour of pixels to white.
void MazePng::createImage(png_bytep *row_pointers, unsigned int scale) {
...
//This loops sets the pixels of the row_pointers using the cells pattern
for (unsigned int y = 0; y < height; ++y) {
setPixel(row_pointers, 0, (y * 2) + 1, WALL);
for (unsigned int x = 0; x < width; ++x) {
switch ((cells[(y * width) + x] & 0xC0) >> 6) {
case 2:
temp[0] = PATH;
setPixel(row_pointers, 2 + (x * 2), (y * 2) + 1, temp[0]);
break;
case 1:
temp[1] = PATH;
setPixel(row_pointers, 1 + (x * 2), (y * 2) + 2, temp[1]);
break;
case 0:
setPixel(row_pointers, 2 + (x * 2), (y * 2) + 1, temp[0]);
setPixel(row_pointers, 1 + (x * 2), (y * 2) + 2, temp[1]);
break;
}
setPixel(row_pointers, 1 + (x * 2), (y * 2) + 1, PATH);
}
}
}
'''Testing Environment:'''
* Operating system: Windows 8.1 Enterprise 64-bit (6.3, Build 9600) (9600.winblue_ltsb.160812-0914)
* System memory: 16384MB RAM
== PHASE 3 ==
=== Attempt 1 ===
We tried to optimize the maze program by removing some of the if statements to reduce thread divergence, however the attempt made the program slower than the phase 2 version and only a little bit faster than the serial version.
'''New Kernels:'''
// Initialize all pixels to black (hex 000)
__global__ void k_drawWalls(png_byte* rows, const short* cells, const int width, const int height, const int len, const int size) {
int i = blockIdx.x * blockDim.x + threadIdx.x;
if (i < size) {
rows[i] = WALL;
__syncthreads();
}
}
// Set pixels to white according to the pattern the cell belongs to
__global__ void k_drawPaths(png_byte* rows, const short* cells, const int width, const int height, const int len) {
int i = blockIdx.x * blockDim.x + threadIdx.x;
if (i < width * height) {
int x = i % width;
int y = i / width;
int cas = (cells[i] & 0xC0) >> 6;
int oddY = (2 * y + 1) * len;
int evenY = (2 * y + 2) * len;
int oddX = (2 * x + 1) * 3;
int evenX = (2 * x + 2) * 3;
if (cas == 2) {
rows[oddY + evenX] = rows[oddY + evenX + 1] = rows[oddY + evenX + 2] = PATH;
}
else if (cas == 1) {
rows[evenY + oddX] = rows[evenY + oddX + 1] = rows[evenY + oddX + 2] = PATH;
}
else if (cas == 0) {
rows[oddY + evenX] = rows[oddY + evenX + 1] = rows[oddY + evenX + 2] = PATH;
rows[evenY + oddX] = rows[evenY + oddX + 1] = rows[evenY + oddX + 2] = PATH;
}
rows[oddY + oddX] = rows[oddY + oddX + 1] = rows[oddY + oddX + 2] = PATH;
}
}
'''Analysis:'''
[[File:SPODiagram.PNG]]
For this attempt, the kernel executes for each cell instead of for each byte (in phase 2); it is no longer processing more than 1 pixel in each cell for every thread, which may be the cause to the longer processing time.
=== Attempt 2 ===
We decided to use shared memory in the GPU to improve the speed of the program. However, the maze image does not show correctly: the paths were showing as randomly coloured pixels; the cause is due to the threads setting only a part (1/3, 2/3) of a pixel's values to hexadecimal F.
