46
edits
Changes
→Beginning Information
===== Results =====
You need many billions of points and maybe even trillions to reach a high precision for the final result but using just 2 billion dots causes the program to take over 30 seconds to run. The most intensive part of the program is the loop which is what loops executes 2 billion times in my run of the program while profiling, which can all be parallelized. We can determine from the profiling that 100% of the time executing the program is spent in the loop but of course that is not possible so we will go with 99.9%, using a GTX 1080 as an example GPU which has 20 processors and each having 2048 threads, and using Amdahl's Law we can expect a speedup of 976.191 times
=== Assignment 2 ===
==== Beginning Information ====
Image used for all of the testing
[[File:Duck.JPG||400px]]
==== Enlarge Image====
<pre>
__global__ void enlargeImg(int* a, int* b, int matrixSize, int growthVal, int imgCols, int enlargedCols) {
int idx = blockIdx.x * blockDim.x + threadIdx.x;
int x = idx / enlargedCols;
int y = idx % enlargedCols;
if (idx < matrixSize) {
a[idx] = b[(x / growthVal) * imgCols + (y / growthVal)];
}
}
</pre>
==== Shrink Image ====
<pre>
__global__ void shrinkImg(int* a, int* b, int matrixSize, int shrinkVal, int imgCols, int shrinkCols) {
int idx = blockIdx.x * blockDim.x + threadIdx.x;
int x = idx / shrinkCols;
int y = idx % shrinkCols;
if (idx < matrixSize) {
a[idx] = b[(x / shrinkVal) * imgCols + (y / shrinkVal)];
}
}
</pre>
==== Reflect Image====
<pre>
// Reflect Image Horizontally
__global__ void reflectImgH(int* a, int* b, int rows, int cols) {
int i = blockIdx.x * blockDim.x + threadIdx.x;
int j = blockIdx.y * blockDim.y + threadIdx.y;
//tempImage.pixelVal[rows - (i + 1)][j] = oldImage.pixelVal[i][j];
a[j * cols + (rows - (i + 1))] = b[j * cols + i];
}
//Reflect Image Vertically
__global__ void reflectImgV(int* a, int* b, int rows, int cols) {
int i = blockIdx.x * blockDim.x + threadIdx.x;
int j = blockIdx.y * blockDim.y + threadIdx.y;
//tempImage.pixelVal[i][cols - (j + 1)] = oldImage.pixelVal[i][j];
a[(cols - (j + 1) * cols) + i] = b[j * cols + i];
}
</pre>
==== Translate Image====
<pre>
__global__ void translateImg(int* a, int* b, int cols, int value) {
int i = blockIdx.x * blockDim.x + threadIdx.x;
int j = blockIdx.y * blockDim.y + threadIdx.y;
//tempImage.pixelVal[i + value][j + value] = oldImage.pixelVal[i][j];
a[(j-value) * cols + (i+value)] = b[j * cols + i];
}
</pre>
==== Rotate Image====
<pre>
__global__ void rotateImg(int* a, int* b, int matrixSize, int imgCols, int imgRows, int r0, int c0, float rads) {
int idx = blockIdx.x * blockDim.x + threadIdx.x;
int r = idx / imgCols;
int c = idx % imgCols;
if (idx < matrixSize) {
int r1 = (int)(r0 + ((r - r0) * cos(rads)) - ((c - c0) * sin(rads)));
int c1 = (int)(c0 + ((r - r0) * sin(rads)) + ((c - c0) * cos(rads)));
if (r1 >= imgRows || r1 < 0 || c1 >= imgCols || c1 < 0) {
}
else {
a[c1 * imgCols + r1] = b[c * imgCols + r];
}
}
}
__global__ void rotateImgBlackFix(int* a, int imgCols) {
int idx = blockIdx.x * blockDim.x + threadIdx.x;
int r = idx / imgCols;
int c = idx % imgCols;
if (a[c * imgCols + r] == 0)
a[c * imgCols + r] = a[(c + 1) * imgCols + r];
}
</pre>
==== Negate Image====
<pre>
__global__ void negateImg(int* a, int* b, int matrixSize) {
int matrixCol = blockIdx.x * blockDim.x + threadIdx.x;
if(matrixCol < matrixSize)
</pre>
====Results====
[[File:CHART2GOOD.png]]
=== Assignment 3 ===