//========================================================================================================================================================================================================200
//	INFORMATION
//========================================================================================================================================================================================================200

//======================================================================================================================================================150
//	UPDATE
//======================================================================================================================================================150

//	2006.03 Rob Janiczek
//		--creation of prototype version
//	2006.03 Drew Gilliam
//		--rewriting of prototype version into current version
//		--got rid of multiple function calls, all code in a single function (for speed)
//		--code cleanup & commenting
//		--code optimization efforts   
//	2006.04 Drew Gilliam
//		--added diffusion coefficent saturation on [0,1]
//	2009.07 Lukasz G. Szafaryn
//		-- converted from C to CUDA
//	2009.12 Lukasz G. Szafaryn
//		-- reading from image, command line inputs
//	2010.01 Lukasz G. Szafaryn
//		-- arranged, commented
//	2012.05 Lukasz G. Szafaryn
//		-- arranged
//	2012.05 Lukasz G. Szafaryn
//		-- converted from CUDA to OpenCL

//======================================================================================================================================================150
//	DESCRIPTION
//======================================================================================================================================================150

	// The Heart Wall application tracks the movement of a mouse heart over a sequence of 104 609x590 ultrasound images to record response to the stimulus.
	// In its initial stage, the program performs image processing operations on the first image to detect initial, partial shapes of inner and outer heart walls.
	// These operations include: edge detection, SRAD despeckling (also part of Rodinia suite), morphological transformation and dilation. In order to reconstruct
	// approximated full shapes of heart walls, the program generates ellipses that are superimposed over the image and sampled to mark points on the heart walls
	// (Hough Search). In its final stage (Heart Wall Tracking presented here), program tracks movement of surfaces by detecting the movement of image areas under
	// sample points as the shapes of the heart walls change throughout the sequence of images.

	// SRAD is one of the first stages of the Heart Wall application. SRAD (Speckle Reducing Anisotropic Diffusion) is a diffusion method for ultrasonic and radar imaging
	// applications based on partial differential equations (PDEs). It is used to remove locally correlated noise, known as speckles, without destroying important image
	// features. SRAD consists of several pieces of work: image extraction, continuous iterations over the image (preparation, reduction, statistics, computation 1 and
	// computation 2) and image compression. The sequential dependency between all of these stages requires synchronization after each stage (because each stage
	// operates on the entire image).

//======================================================================================================================================================150
//	PAPERS
//======================================================================================================================================================150

	// L. G. Szafaryn, K. Skadron, and J. J. Saucerman. "Experiences Accelerating MATLAB Systems Biology Applications." In Proceedings of the Workshop on Biomedicine
	// in Computing: Systems, Architectures, and Circuits (BiC) 2009, in conjunction with the 36th IEEE/ACM International Symposium on Computer Architecture (ISCA),
	// June 2009. <http://www.cs.virginia.edu/~skadron/Papers/BiC09.pdf>

	// Y. Yu, S. Acton, Speckle reducing anisotropic diffusion, IEEE Transactions on Image Processing 11(11)(2002) 1260-1270.
	// <http://people.virginia.edu/~sc5nf/01097762.pdf>

//======================================================================================================================================================150
//	DOWNLOAD
//======================================================================================================================================================150

	// Rodinia Benchmark Suite page

//======================================================================================================================================================150
//	IMPLEMENTATION-SPECIFIC DESCRIPTION (OpenCL)
//======================================================================================================================================================150

	// This is the OpenCL version of SRAD code.

	// In OpenCL version of this application, each stage is a separate kernel (due to synchronization requirements) that operates on data already residing in GPU memory.
	// In order to improve GPU performance, data was transferred to GPU at the beginning of the code and then transferred back to CPU after all of the computation stages
	// were completed in GPU. Some of the kernels use GPU shared memory for additional improvement in performance. Speedup achievable with OpenCL version depends on
	// the image size (up to the point where GPU saturates).

//======================================================================================================================================================150
//	RUNNING THIS CODE
//======================================================================================================================================================150

	// Input image is generated by expanding the original image (image.pgm) via concatenating its parts. The original image needs to be located in the same folder as source files.

	// The following are the command parameters to the application:

	// 1) Number of iterations. Needs to be integer > 0.
	// 2) Saturation coefficient. Needs to be float > 0.
	// 3) Number of rows in the input image. Needs to be integer > 0.
	// 4) Number of columns in the input image. Needs to be integer > 0.

	// Example:
	// a.out 100 0.5 1000 1000

	// Running a.out without parameters will default to the parameters shown in the line above.

//======================================================================================================================================================150
//	End
//======================================================================================================================================================150

//========================================================================================================================================================================================================200
//	End
//========================================================================================================================================================================================================200