Changes

Three-Star

724 bytes removed, 15:13, 8 April 2018

→‎Assignment 3

=== Assignment 3 ===

~~__global__ void rotateKernel(int* oldImage, int* newImage, int rows, int cols, float rads) {~~

~~'''int c''' = blockIdx.x * blockDim.x + threadIdx.x;~~

~~'''int r''' = blockIdx.y * blockDim.y + threadIdx.y;~~

~~int r0 = rows / 2;~~

~~int c0 = cols / 2;~~

~~float sinRads = sinf(rads);~~

~~float cosRads = cosf(rads);~~

~~if (r < rows && c < cols)~~

{

~~int r1 = (int)(r0 + ((r - r0) * cosRads) - ((c - c0) * sinRads));~~

~~int c1 = (int)(c0 + ((r - r0) * sinRads) + ((c - c0) * cosRads));~~

~~if (inBounds(r1, c1, rows, cols))~~

{

~~newImage[r1 * cols + c1] = oldImage[r * cols + c];~~

}

Using Coalesced Memory (changed matrix access from column to row)

|-

|512x512

|-

|2x enlarged

|-

|3x enlarged

|-

|4x enlarged

|-

|5x enlarged

|-

|}

Changing the way memory is accessed doesn't seem to have any significant improvements/changes to time

122

edits