# HG changeset patch
# User Me@portablequad
# Date 1319810195 25200
# Node ID 535c119ba09046657913be8b65ce09785c65cfa6
# Parent  e512fcf3748e6fd86e7ae454c64f85ee8b12b20c
rearranged code to fit project patterns

diff -r e512fcf3748e -r 535c119ba090 .hgignore
--- a/.hgignore	Sat Oct 22 19:27:29 2011 -0700
+++ b/.hgignore	Fri Oct 28 06:56:35 2011 -0700
@@ -2,6 +2,8 @@
 
 histograms
 nbproject
+build
+dist
 c-ray-mt
 *.ppm
 *.o
diff -r e512fcf3748e -r 535c119ba090 Makefile
--- a/Makefile	Sat Oct 22 19:27:29 2011 -0700
+++ b/Makefile	Fri Oct 28 06:56:35 2011 -0700
@@ -1,31 +1,33 @@
 obj = 	\
-	VPThread_lib/VMS/Histogram/Histogram.o \
-	VPThread_lib/VMS/Histogram/FloatHist.o \
-	VPThread_lib/VMS/CoreLoop.o \
-	VPThread_lib/VMS/VMS.o \
-	VPThread_lib/VMS/MasterLoop.o \
-	VPThread_lib/VMS/Queue_impl/PrivateQueue.o \
-	VPThread_lib/VMS/Hash_impl/PrivateHash.o \
-	VPThread_lib/VMS/DynArray/DynArray.o \
-	VPThread_lib/VPThread_PluginFns.o \
-	VPThread_lib/VPThread_lib.o \
-	VPThread_lib/VMS/Histogram/DblHist.o \
-	VPThread_lib/VPThread.o \
-	VPThread_lib/VMS/probes.o \
-	VPThread_lib/VMS/ProcrContext.o \
-	VPThread_lib/VPThread_Request_Handlers.o \
-	VPThread_lib/VPThread_helper.o \
-	VPThread_lib/VMS/Hash_impl/MurmurHash2.o \
-	VPThread_lib/VMS/vmalloc.o \
-	VPThread_lib/VMS/contextSwitch.o \
-	VPThread_lib/VMS/Queue_impl/BlockingQueue.o \
-	VPThread_lib/VMS/vutilities.o \
-	c-ray-mt.o
+	src/VPThread_lib/VMS/Histogram/Histogram.o \
+	src/VPThread_lib/VMS/Histogram/FloatHist.o \
+	src/VPThread_lib/VMS/CoreLoop.o \
+	src/VPThread_lib/VMS/VMS.o \
+	src/VPThread_lib/VMS/MasterLoop.o \
+	src/VPThread_lib/VMS/Queue_impl/PrivateQueue.o \
+	src/VPThread_lib/VMS/Hash_impl/PrivateHash.o \
+	src/VPThread_lib/VMS/DynArray/DynArray.o \
+	src/VPThread_lib/VPThread_PluginFns.o \
+	src/VPThread_lib/VPThread_lib.o \
+	src/VPThread_lib/VMS/Histogram/DblHist.o \
+	src/VPThread_lib/VPThread.o \
+	src/VPThread_lib/VMS/probes.o \
+	src/VPThread_lib/VMS/ProcrContext.o \
+	src/VPThread_lib/VPThread_Request_Handlers.o \
+	src/VPThread_lib/VPThread_helper.o \
+	src/VPThread_lib/VMS/Hash_impl/MurmurHash2.o \
+	src/VPThread_lib/VMS/vmalloc.o \
+	src/VPThread_lib/VMS/contextSwitch.o \
+	src/VPThread_lib/VMS/Queue_impl/BlockingQueue.o \
+	src/VPThread_lib/VMS/vutilities.o \
+	src/Application/main.o
 
-bin = c-ray-mt
+bin = task_size_vs_exe_time
+
+NUM_CORES=4
 
 CC = gcc
-CFLAGS = -m64 -ffast-math -fwrapv -fno-omit-frame-pointer -O3 -D VPTHREAD -D APPLICATION=C-RAY -g -Wall
+CFLAGS = -m64 -ffast-math -fwrapv -fno-omit-frame-pointer -O3 -D VPTHREAD -D APPLICATION=C-RAY -D NUM_CORES=$(NUM_CORES) -g -Wall
 
 $(bin): $(obj)
 	$(CC) -o $@ $(obj) -lm -lpthread
diff -r e512fcf3748e -r 535c119ba090 README.txt
--- a/README.txt	Sat Oct 22 19:27:29 2011 -0700
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,27 +0,0 @@
-Kernel: Ray Tracing
-
-This is a kernel-type benchmark of a very simple and brute-force ray tracer.
-
-Installation:
-
-To install the kernel benchmark, navigate to the directory this file is located in, open up a terminal and simply type 'make'. For certain architectures 
-or special compilation options, you might need to change compilation parameters in the makefile.
-
-Usage:
-
-You may execute the benchmark by navigating to this directory after compilation and typing
-
-./c-ray-mt -i FILENAME -s RESOLUTION -o OUTPUT.ppm 
-
-'FILENAME' has to be either "scene" or "sphfract" or another predefined scene description file if there is one.
-'RESOLUTION' specifies the resolution of the produced image and has to be given in the form 1920x1200, for example.
-'OUTPUT' is the name of the file the rendered image will be contained in after the benchmark ran.
-
-The specification of how many threads are used to perform the rendering depends on the parallel programming model.
-
-Benchmark Versions:
-
-Serial
-POSIX Threads
-OpenMP SuperScalar
-
diff -r e512fcf3748e -r 535c119ba090 c-ray-mt.c
--- a/c-ray-mt.c	Sat Oct 22 19:27:29 2011 -0700
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,718 +0,0 @@
-/* c-ray-mt - a simple multithreaded raytracing filter.
- * Copyright (C) 2006 John Tsiombikas <nuclear@siggraph.org>
- *
- * You are free to use, modify and redistribute this program under the
- * terms of the GNU General Public License v2 or (at your option) later.
- * see "http://www.gnu.org/licenses/gpl.txt" for details.
- * ---------------------------------------------------------------------
- * Usage:
- *   compile:  just type make
- *              (add any arch-specific optimizations for your compiler in CFLAGS first)
- *       run:  cat scene | ./c-ray-mt [-t num-threads] >foo.ppm
- *              (on broken systems such as windows try: c-ray-mt -i scene -o foo.ppm)
- *     enjoy:  display foo.ppm
- *              (with imagemagick, or use your favorite image viewer)
- * ---------------------------------------------------------------------
- * Scene file format:
- *   # sphere (many)
- *   s  x y z  rad   r g b   shininess   reflectivity
- *   # light (many)
- *   l  x y z
- *   # camera (one)
- *   c  x y z  fov   tx ty tz
- * ---------------------------------------------------------------------
- */
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <math.h>
-#include <ctype.h>
-#include <errno.h>
-#include <pthread.h>
-#include "VPThread_lib/VPThread.h"
-
-#define VER_MAJOR	1
-#define VER_MINOR	1
-#define VER_STR		"c-ray-mt v%d.%d\n"
-
-#if !defined(unix) && !defined(__unix__)
-#ifdef __MACH__
-#define unix		1
-#define __unix__	1
-#endif	/* __MACH__ */
-#endif	/* unix */
-
-/* find the appropriate way to define explicitly sized types */
-/* for C99 or GNU libc (also mach's libc) we can use stdint.h */
-#if (__STDC_VERSION__ >= 199900) || defined(__GLIBC__) || defined(__MACH__)
-#include <stdint.h>
-#elif defined(unix) || defined(__unix__)	/* some UNIX systems have them in sys/types.h */
-#include <sys/types.h>
-#elif defined(__WIN32__) || defined(WIN32)	/* the nameless one */
-typedef unsigned __int8 uint8_t;
-typedef unsigned __int32 uint32_t;
-#endif	/* sized type detection */
-
-struct vec3 {
-	double x, y, z;
-};
-
-struct ray {
-	struct vec3 orig, dir;
-};
-
-struct material {
-	struct vec3 col;	/* color */
-	double spow;		/* specular power */
-	double refl;		/* reflection intensity */
-};
-
-struct sphere {
-	struct vec3 pos;
-	double rad;
-	struct material mat;
-	struct sphere *next;
-};
-
-struct spoint {
-	struct vec3 pos, normal, vref;	/* position, normal and view reflection */
-	double dist;		/* parametric distance of intersection along the ray */
-};
-
-struct camera {
-	struct vec3 pos, targ;
-	double fov;
-};
-
-struct thread_data {
-	VirtProcr *VP;
-	int sl_start, sl_count;
-	uint32_t *pixels;
-};
-typedef struct thread_data thread_data;
-
-void render_scanline(int xsz, int ysz, int sl, uint32_t *fb, int samples);
-struct vec3 trace(struct ray ray, int depth);
-struct vec3 shade(struct sphere *obj, struct spoint *sp, int depth);
-struct vec3 reflect(struct vec3 v, struct vec3 n);
-struct vec3 cross_product(struct vec3 v1, struct vec3 v2);
-struct ray get_primary_ray(int x, int y, int sample);
-struct vec3 get_sample_pos(int x, int y, int sample);
-struct vec3 jitter(int x, int y, int s);
-int ray_sphere(const struct sphere *sph, struct ray ray, struct spoint *sp);
-void load_scene(FILE *fp);
-unsigned long get_msec(void);
-
-void thread_func(void *tdata, VirtProcr *VProc);
-
-#define MAX_LIGHTS		16				/* maximum number of lights */
-#define RAY_MAG			1000.0			/* trace rays of this magnitude */
-#define MAX_RAY_DEPTH	5				/* raytrace recursion limit */
-#define FOV				0.78539816		/* field of view in rads (pi/4) */
-#define HALF_FOV		(FOV * 0.5)
-#define ERR_MARGIN		1e-6			/* an arbitrary error margin to avoid surface acne */
-
-/* bit-shift ammount for packing each color into a 32bit uint */
-#ifdef LITTLE_ENDIAN
-#define RSHIFT	16
-#define BSHIFT	0
-#else	/* big endian */
-#define RSHIFT	0
-#define BSHIFT	16
-#endif	/* endianess */
-#define GSHIFT	8	/* this is the same in both byte orders */
-
-/* some helpful macros... */
-#define SQ(x)		((x) * (x))
-#define MAX(a, b)	((a) > (b) ? (a) : (b))
-#define MIN(a, b)	((a) < (b) ? (a) : (b))
-#define DOT(a, b)	((a).x * (b).x + (a).y * (b).y + (a).z * (b).z)
-#define NORMALIZE(a)  do {\
-	double len = sqrt(DOT(a, a));\
-	(a).x /= len; (a).y /= len; (a).z /= len;\
-} while(0);
-
-/* global state */
-int xres = 800;
-int yres = 600;
-int rays_per_pixel = 1;
-double aspect = 1.333333;
-struct sphere *obj_list;
-struct vec3 lights[MAX_LIGHTS];
-int lnum = 0;
-struct camera cam;
-
-int thread_num = 1;
-struct thread_data *threads;
-
-volatile int end = 0;
-volatile int start = 0;
-int32 end_mutex, end_cond;
-int32 start_cond, start_mutex;
-
-#define NRAN	1024
-#define MASK	(NRAN - 1)
-struct vec3 urand[NRAN];
-int irand[NRAN];
-
-unsigned long rend_time, start_time;
-
-const char *usage = {
-	"Usage: c-ray-mt [options]\n"
-	"  Reads a scene file from stdin, writes the image to stdout, and stats to stderr.\n\n"
-	"Options:\n"
-	"  -t <num>   how many threads to use (default: 1)\n"
-	"  -s WxH     where W is the width and H the height of the image\n"
-	"  -r <rays>  shoot <rays> rays per pixel (antialiasing)\n"
-	"  -i <file>  read from <file> instead of stdin\n"
-	"  -o <file>  write to <file> instead of stdout\n"
-	"  -h         this help screen\n\n"
-};
-
-char __ProgrammName[] = "c-ray";
-char __DataSet[255];
-
-
-void raytrace(void *pixels, VirtProcr *Vprocr);
-
-int main(int argc, char **argv) {
-	int i;
-	uint32_t *pixels;
-	FILE *infile = stdin, *outfile = stdout;
-
-	for(i=1; i<argc; i++) {
-		if(argv[i][0] == '-' && argv[i][2] == 0) {
-			char *sep;
-			switch(argv[i][1]) {
-			case 't':
-				if(!isdigit(argv[++i][0])) {
-					fprintf(stderr, "-t mus be followed by the number of worker threads to spawn\n");
-					return EXIT_FAILURE;
-				}
-				thread_num = atoi(argv[i]);
-				if(!thread_num) {
-					fprintf(stderr, "invalid number of threads specified: %d\n", thread_num);
-					return EXIT_FAILURE;
-				}
-				break;
-					
-			case 's':
-				if(!isdigit(argv[++i][0]) || !(sep = strchr(argv[i], 'x')) || !isdigit(*(sep + 1))) {
-					fputs("-s must be followed by something like \"640x480\"\n", stderr);
-					return EXIT_FAILURE;
-				}
-				xres = atoi(argv[i]);
-				yres = atoi(sep + 1);
-				aspect = (double)xres / (double)yres;
-				break;
-
-			case 'i':
-				if(!(infile = fopen(argv[++i], "rb"))) {
-					fprintf(stderr, "failed to open input file %s: %s\n", argv[i], strerror(errno));
-					return EXIT_FAILURE;
-				}
-				break;
-
-			case 'o':
-				if(!(outfile = fopen(argv[++i], "wb"))) {
-					fprintf(stderr, "failed to open output file %s: %s\n", argv[i], strerror(errno));
-					return EXIT_FAILURE;
-				}
-				break;
-
-			case 'r':
-				if(!isdigit(argv[++i][0])) {
-					fputs("-r must be followed by a number (rays per pixel)\n", stderr);
-					return EXIT_FAILURE;
-				}
-				rays_per_pixel = atoi(argv[i]);
-				break;
-
-			case 'h':
-				fputs(usage, stdout);
-				return 0;
-				
-			default:
-				fprintf(stderr, "unrecognized argument: %s\n", argv[i]);
-				fputs(usage, stderr);
-				return EXIT_FAILURE;
-			}
-		} else {
-			fprintf(stderr, "unrecognized argument: %s\n", argv[i]);
-			fputs(usage, stderr);
-			return EXIT_FAILURE;
-		}
-	}
-        
-        snprintf(__DataSet,255,"file: %s\nsize: %dx%d\nrays per pixel: %d\nthreads: %d\n",
-                        infile, xres, yres, rays_per_pixel, thread_num);
-
-        
-        if(!(pixels = malloc(xres * yres * sizeof *pixels))) {
-		perror("pixel buffer allocation failed");
-		return EXIT_FAILURE;
-	}
-	load_scene(infile);
-        
-        //This is the transition to the VMS runtime
-        VPThread__create_seed_procr_and_do_work(raytrace, (void*)pixels);
-	
-	/* output statistics to stderr */
-	fprintf(stderr, "Rendering took: %lu seconds (%lu milliseconds)\n", rend_time / 1000, rend_time);
-
-	/* output the image */
-	fprintf(outfile, "P6\n%d %d\n255\n", xres, yres);
-	for(i=0; i<xres * yres; i++) {
-		fputc((pixels[i] >> RSHIFT) & 0xff, outfile);
-		fputc((pixels[i] >> GSHIFT) & 0xff, outfile);
-		fputc((pixels[i] >> BSHIFT) & 0xff, outfile);
-	}
-	fflush(outfile);
-
-	if(infile != stdin) fclose(infile);
-	if(outfile != stdout) fclose(outfile);
-
-	struct sphere *walker = obj_list;
-	while(walker) {
-		struct sphere *tmp = walker;
-		walker = walker->next;
-		free(tmp);
-	}
-	free(pixels);
-	return 0;
-}
-
-/* this is run after the VMS is set up*/
-void raytrace(void *pixels, VirtProcr *VProc)
-{
-    int i;
-    double sl, sl_per_thread;
-    
-    /* initialize the random number tables for the jitter */
-    for(i=0; i<NRAN; i++) urand[i].x = (double)rand() / RAND_MAX - 0.5;
-    for(i=0; i<NRAN; i++) urand[i].y = (double)rand() / RAND_MAX - 0.5;
-    for(i=0; i<NRAN; i++) irand[i] = (int)(NRAN * ((double)rand() / RAND_MAX));
-
-    if(thread_num > yres) {
-            fprintf(stderr, "more threads than scanlines specified, reducing number of threads to %d\n", yres);
-            thread_num = yres;
-    }
-
-    
-    if(!(threads = VPThread__malloc(thread_num * sizeof(thread_data), VProc))) {
-            perror("failed to allocate thread table");
-            exit(EXIT_FAILURE);
-    }
-    
-    end_mutex = VPThread__make_mutex(VProc);
-    end_cond  = VPThread__make_cond(end_mutex, VProc);
-    start_mutex = VPThread__make_mutex(VProc);
-    start_cond  = VPThread__make_cond(start_mutex, VProc);    
-    
-    sl = 0.0;
-    sl_per_thread = (double)yres / (double)thread_num;
-    for(i=0; i<thread_num; i++) {
-            threads[i].sl_start = (int)sl;
-            sl += sl_per_thread;
-            threads[i].sl_count = (int)sl - threads[i].sl_start;
-            threads[i].pixels = (uint32_t*)pixels;
-
-            threads[i].VP = 
-                    VPThread__create_thread((VirtProcrFnPtr)thread_func,
-                                   (void*)(&threads[i]), VProc);  
-    }
-    
-    threads[thread_num - 1].sl_count = yres - threads[thread_num - 1].sl_start;
-    
-    fprintf(stderr, VER_STR, VER_MAJOR, VER_MINOR);
-    
-    // start worker threads
-    //printf("start of worker thread (%d)\n", VProc->procrID);      
-    VPThread__mutex_lock(start_mutex, VProc);
-    start_time = get_msec();
-    start = 1;
-    for(i=0; i<thread_num; i++)
-        VPThread__cond_signal(start_cond, VProc);
-    VPThread__mutex_unlock(start_mutex, VProc);
-    
-    //printf("wait for worker (%d)\n", VProc->procrID);      
-    VPThread__mutex_lock(end_mutex, VProc);
-    while(end < thread_num)
-        VPThread__cond_wait(end_cond, VProc);
-    VPThread__mutex_unlock(end_mutex, VProc);
-    
-    rend_time = get_msec() - start_time;
-    
-    VPThread__free(threads,VProc);
-    VPThread__dissipate_thread(VProc);
-}
-
-/* render a frame of xsz/ysz dimensions into the provided framebuffer */
-void render_scanline(int xsz, int ysz, int sl, uint32_t *fb, int samples) {
-	int i, s;
-	double rcp_samples = 1.0 / (double)samples;
-
-	for(i=0; i<xsz; i++) {
-		double r, g, b;
-		r = g = b = 0.0;
-			
-		for(s=0; s<samples; s++) {
-			struct vec3 col = trace(get_primary_ray(i, sl, s), 0);
-			r += col.x;
-			g += col.y;
-			b += col.z;
-		}
-
-		r = r * rcp_samples;
-		g = g * rcp_samples;
-		b = b * rcp_samples;
-			
-		fb[sl * xsz + i] = ((uint32_t)(MIN(r, 1.0) * 255.0) & 0xff) << RSHIFT |
-							((uint32_t)(MIN(g, 1.0) * 255.0) & 0xff) << GSHIFT |
-							((uint32_t)(MIN(b, 1.0) * 255.0) & 0xff) << BSHIFT;
-	}
-}
-
-/* trace a ray throught the scene recursively (the recursion happens through
- * shade() to calculate reflection rays if necessary).
- */
-struct vec3 trace(struct ray ray, int depth) {
-	struct vec3 col;
-	struct spoint sp, nearest_sp;
-	struct sphere *nearest_obj = 0;
-	struct sphere *iter = obj_list->next;
-
-	/* if we reached the recursion limit, bail out */
-	if(depth >= MAX_RAY_DEPTH) {
-		col.x = col.y = col.z = 0.0;
-		return col;
-	}
-	
-	/* find the nearest intersection ... */
-	while(iter) {
-		if(ray_sphere(iter, ray, &sp)) {
-			if(!nearest_obj || sp.dist < nearest_sp.dist) {
-				nearest_obj = iter;
-				nearest_sp = sp;
-			}
-		}
-		iter = iter->next;
-	}
-
-	/* and perform shading calculations as needed by calling shade() */
-	if(nearest_obj) {
-		col = shade(nearest_obj, &nearest_sp, depth);
-	} else {
-		col.x = col.y = col.z = 0.0;
-	}
-
-	return col;
-}
-
-/* Calculates direct illumination with the phong reflectance model.
- * Also handles reflections by calling trace again, if necessary.
- */
-struct vec3 shade(struct sphere *obj, struct spoint *sp, int depth) {
-	int i;
-	struct vec3 col = {0, 0, 0};
-
-	/* for all lights ... */
-	for(i=0; i<lnum; i++) {
-		double ispec, idiff;
-		struct vec3 ldir;
-		struct ray shadow_ray;
-		struct sphere *iter = obj_list->next;
-		int in_shadow = 0;
-
-		ldir.x = lights[i].x - sp->pos.x;
-		ldir.y = lights[i].y - sp->pos.y;
-		ldir.z = lights[i].z - sp->pos.z;
-
-		shadow_ray.orig = sp->pos;
-		shadow_ray.dir = ldir;
-
-		/* shoot shadow rays to determine if we have a line of sight with the light */
-		while(iter) {
-			if(ray_sphere(iter, shadow_ray, 0)) {
-				in_shadow = 1;
-				break;
-			}
-			iter = iter->next;
-		}
-
-		/* and if we're not in shadow, calculate direct illumination with the phong model. */
-		if(!in_shadow) {
-			NORMALIZE(ldir);
-
-			idiff = MAX(DOT(sp->normal, ldir), 0.0);
-			ispec = obj->mat.spow > 0.0 ? pow(MAX(DOT(sp->vref, ldir), 0.0), obj->mat.spow) : 0.0;
-
-			col.x += idiff * obj->mat.col.x + ispec;
-			col.y += idiff * obj->mat.col.y + ispec;
-			col.z += idiff * obj->mat.col.z + ispec;
-		}
-	}
-
-	/* Also, if the object is reflective, spawn a reflection ray, and call trace()
-	 * to calculate the light arriving from the mirror direction.
-	 */
-	if(obj->mat.refl > 0.0) {
-		struct ray ray;
-		struct vec3 rcol;
-
-		ray.orig = sp->pos;
-		ray.dir = sp->vref;
-		ray.dir.x *= RAY_MAG;
-		ray.dir.y *= RAY_MAG;
-		ray.dir.z *= RAY_MAG;
-
-		rcol = trace(ray, depth + 1);
-		col.x += rcol.x * obj->mat.refl;
-		col.y += rcol.y * obj->mat.refl;
-		col.z += rcol.z * obj->mat.refl;
-	}
-
-	return col;
-}
-
-/* calculate reflection vector */
-struct vec3 reflect(struct vec3 v, struct vec3 n) {
-	struct vec3 res;
-	double dot = v.x * n.x + v.y * n.y + v.z * n.z;
-	res.x = -(2.0 * dot * n.x - v.x);
-	res.y = -(2.0 * dot * n.y - v.y);
-	res.z = -(2.0 * dot * n.z - v.z);
-	return res;
-}
-
-struct vec3 cross_product(struct vec3 v1, struct vec3 v2) {
-	struct vec3 res;
-	res.x = v1.y * v2.z - v1.z * v2.y;
-	res.y = v1.z * v2.x - v1.x * v2.z;
-	res.z = v1.x * v2.y - v1.y * v2.x;
-	return res;
-}
-
-/* determine the primary ray corresponding to the specified pixel (x, y) */
-struct ray get_primary_ray(int x, int y, int sample) {
-	struct ray ray;
-	float m[3][3];
-	struct vec3 i, j = {0, 1, 0}, k, dir, orig, foo;
-
-	k.x = cam.targ.x - cam.pos.x;
-	k.y = cam.targ.y - cam.pos.y;
-	k.z = cam.targ.z - cam.pos.z;
-	NORMALIZE(k);
-
-	i = cross_product(j, k);
-	j = cross_product(k, i);
-	m[0][0] = i.x; m[0][1] = j.x; m[0][2] = k.x;
-	m[1][0] = i.y; m[1][1] = j.y; m[1][2] = k.y;
-	m[2][0] = i.z; m[2][1] = j.z; m[2][2] = k.z;
-	
-	ray.orig.x = ray.orig.y = ray.orig.z = 0.0;
-	ray.dir = get_sample_pos(x, y, sample);
-	ray.dir.z = 1.0 / HALF_FOV;
-	ray.dir.x *= RAY_MAG;
-	ray.dir.y *= RAY_MAG;
-	ray.dir.z *= RAY_MAG;
-	
-	dir.x = ray.dir.x + ray.orig.x;
-	dir.y = ray.dir.y + ray.orig.y;
-	dir.z = ray.dir.z + ray.orig.z;
-	foo.x = dir.x * m[0][0] + dir.y * m[0][1] + dir.z * m[0][2];
-	foo.y = dir.x * m[1][0] + dir.y * m[1][1] + dir.z * m[1][2];
-	foo.z = dir.x * m[2][0] + dir.y * m[2][1] + dir.z * m[2][2];
-
-	orig.x = ray.orig.x * m[0][0] + ray.orig.y * m[0][1] + ray.orig.z * m[0][2] + cam.pos.x;
-	orig.y = ray.orig.x * m[1][0] + ray.orig.y * m[1][1] + ray.orig.z * m[1][2] + cam.pos.y;
-	orig.z = ray.orig.x * m[2][0] + ray.orig.y * m[2][1] + ray.orig.z * m[2][2] + cam.pos.z;
-
-	ray.orig = orig;
-	ray.dir.x = foo.x + orig.x;
-	ray.dir.y = foo.y + orig.y;
-	ray.dir.z = foo.z + orig.z;
-	
-	return ray;
-}
-
-
-struct vec3 get_sample_pos(int x, int y, int sample) {
-	struct vec3 pt;
-	static double sf = 0.0;
-
-	if(sf == 0.0) {
-		sf = 1.5 / (double)xres;
-	}
-
-	pt.x = ((double)x / (double)xres) - 0.5;
-	pt.y = -(((double)y / (double)yres) - 0.65) / aspect;
-
-	if(sample) {
-		struct vec3 jt = jitter(x, y, sample);
-		pt.x += jt.x * sf;
-		pt.y += jt.y * sf / aspect;
-	}
-	return pt;
-}
-
-/* jitter function taken from Graphics Gems I. */
-struct vec3 jitter(int x, int y, int s) {
-	struct vec3 pt;
-	pt.x = urand[(x + (y << 2) + irand[(x + s) & MASK]) & MASK].x;
-	pt.y = urand[(y + (x << 2) + irand[(y + s) & MASK]) & MASK].y;
-	return pt;
-}
-
-/* Calculate ray-sphere intersection, and return {1, 0} to signify hit or no hit.
- * Also the surface point parameters like position, normal, etc are returned through
- * the sp pointer if it is not NULL.
- */
-int ray_sphere(const struct sphere *sph, struct ray ray, struct spoint *sp) {
-	double a, b, c, d, sqrt_d, t1, t2;
-	
-	a = SQ(ray.dir.x) + SQ(ray.dir.y) + SQ(ray.dir.z);
-	b = 2.0 * ray.dir.x * (ray.orig.x - sph->pos.x) +
-				2.0 * ray.dir.y * (ray.orig.y - sph->pos.y) +
-				2.0 * ray.dir.z * (ray.orig.z - sph->pos.z);
-	c = SQ(sph->pos.x) + SQ(sph->pos.y) + SQ(sph->pos.z) +
-				SQ(ray.orig.x) + SQ(ray.orig.y) + SQ(ray.orig.z) +
-				2.0 * (-sph->pos.x * ray.orig.x - sph->pos.y * ray.orig.y - sph->pos.z * ray.orig.z) - SQ(sph->rad);
-	
-	if((d = SQ(b) - 4.0 * a * c) < 0.0) return 0;
-
-	sqrt_d = sqrt(d);
-	t1 = (-b + sqrt_d) / (2.0 * a);
-	t2 = (-b - sqrt_d) / (2.0 * a);
-
-	if((t1 < ERR_MARGIN && t2 < ERR_MARGIN) || (t1 > 1.0 && t2 > 1.0)) return 0;
-
-	if(sp) {
-		if(t1 < ERR_MARGIN) t1 = t2;
-		if(t2 < ERR_MARGIN) t2 = t1;
-		sp->dist = t1 < t2 ? t1 : t2;
-		
-		sp->pos.x = ray.orig.x + ray.dir.x * sp->dist;
-		sp->pos.y = ray.orig.y + ray.dir.y * sp->dist;
-		sp->pos.z = ray.orig.z + ray.dir.z * sp->dist;
-		
-		sp->normal.x = (sp->pos.x - sph->pos.x) / sph->rad;
-		sp->normal.y = (sp->pos.y - sph->pos.y) / sph->rad;
-		sp->normal.z = (sp->pos.z - sph->pos.z) / sph->rad;
-
-		sp->vref = reflect(ray.dir, sp->normal);
-		NORMALIZE(sp->vref);
-	}
-	return 1;
-}
-
-/* Load the scene from an extremely simple scene description file */
-#define DELIM	" \t\n"
-void load_scene(FILE *fp) {
-	char line[256], *ptr, type;
-
-	obj_list = malloc(sizeof(struct sphere));
-	obj_list->next = 0;
-	
-	while((ptr = fgets(line, 256, fp))) {
-		int i;
-		struct vec3 pos, col;
-		double rad, spow, refl;
-		
-		while(*ptr == ' ' || *ptr == '\t') ptr++;
-		if(*ptr == '#' || *ptr == '\n') continue;
-
-		if(!(ptr = strtok(line, DELIM))) continue;
-		type = *ptr;
-		
-		for(i=0; i<3; i++) {
-			if(!(ptr = strtok(0, DELIM))) break;
-			*((double*)&pos.x + i) = atof(ptr);
-		}
-
-		if(type == 'l') {
-			lights[lnum++] = pos;
-			continue;
-		}
-
-		if(!(ptr = strtok(0, DELIM))) continue;
-		rad = atof(ptr);
-
-		for(i=0; i<3; i++) {
-			if(!(ptr = strtok(0, DELIM))) break;
-			*((double*)&col.x + i) = atof(ptr);
-		}
-
-		if(type == 'c') {
-			cam.pos = pos;
-			cam.targ = col;
-			cam.fov = rad;
-			continue;
-		}
-
-		if(!(ptr = strtok(0, DELIM))) continue;
-		spow = atof(ptr);
-
-		if(!(ptr = strtok(0, DELIM))) continue;
-		refl = atof(ptr);
-
-		if(type == 's') {
-			struct sphere *sph = malloc(sizeof *sph);
-			sph->next = obj_list->next;
-			obj_list->next = sph;
-
-			sph->pos = pos;
-			sph->rad = rad;
-			sph->mat.col = col;
-			sph->mat.spow = spow;
-			sph->mat.refl = refl;
-		} else {
-			fprintf(stderr, "unknown type: %c\n", type);
-		}
-	}
-}
-
-
-/* provide a millisecond-resolution timer for each system */
-#if defined(unix) || defined(__unix__)
-#include <time.h>
-#include <sys/time.h>
-unsigned long get_msec(void) {
-	static struct timeval timeval, first_timeval;
-	
-	gettimeofday(&timeval, 0);
-	if(first_timeval.tv_sec == 0) {
-		first_timeval = timeval;
-		return 0;
-	}
-	return (timeval.tv_sec - first_timeval.tv_sec) * 1000 + (timeval.tv_usec - first_timeval.tv_usec) / 1000;
-}
-#elif defined(__WIN32__) || defined(WIN32)
-#include <windows.h>
-unsigned long get_msec(void) {
-	return GetTickCount();
-}
-#else
-#error "I don't know how to measure time on your platform"
-#endif
-
-void thread_func(void *tdata, VirtProcr *VProc) {
-	int i;
-	struct thread_data *td = (struct thread_data*)tdata;
-
-        VPThread__mutex_lock(start_mutex, VProc);
-        while(!start)
-            VPThread__cond_wait(start_cond, VProc);
-        VPThread__mutex_unlock(start_mutex, VProc);        
-        
-	for(i=0; i<td->sl_count; i++) {
-		render_scanline(xres, yres, i + td->sl_start, td->pixels, rays_per_pixel);
-	}
-        
-        VPThread__mutex_lock(end_mutex, VProc);
-        end++;
-        VPThread__cond_signal(end_cond, VProc);
-        VPThread__mutex_unlock(end_mutex, VProc);   
-
-	VPThread__dissipate_thread(VProc);
-}
diff -r e512fcf3748e -r 535c119ba090 scene
--- a/scene	Sat Oct 22 19:27:29 2011 -0700
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,18 +0,0 @@
-# spheres
-#	position		radius	color			shininess	reflectivity
-s	-1.5 -0.3 -1	0.7		1.0 0.2 0.05		50.0	0.3
-s	1.5 -0.4 0		0.6		0.1 0.85 1.0		50.0	0.4
-
-# walls
-s	0 -1000 2		999		0.1 0.2 0.6			80.0	0.5
-
-# bouncing ball
-s	0 0 2			1		0.0 0.0 0.0			60.0	0.7
-
-# lights...
-l	-50 100 -50
-l	40 40 150
-
-# camera (there can be only one!)
-#	position	FOV		target
-c	0 6 -17		45		0 -1 0
diff -r e512fcf3748e -r 535c119ba090 sphfract
--- a/sphfract	Sat Oct 22 19:27:29 2011 -0700
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,192 +0,0 @@
-s	0 0 0 	1.0	0.25 0.25 0.25  50.0	0.65
-s	1.4 0 0 	0.4	0.25 0.25 0.25  50.0	0.65
-s	1.96 0 0 	0.16	0.25 0.25 0.25  50.0	0.65
-s	2.184 0 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.96 0.224 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.96 -0.224 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.96 0 0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.96 0 -0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 0.56 0 	0.16	0.25 0.25 0.25  50.0	0.65
-s	1.624 0.56 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.176 0.56 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 0.784 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 0.56 0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 0.56 -0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 -0.56 0 	0.16	0.25 0.25 0.25  50.0	0.65
-s	1.624 -0.56 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.176 -0.56 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 -0.784 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 -0.56 0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 -0.56 -0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 0 0.56 	0.16	0.25 0.25 0.25  50.0	0.65
-s	1.624 0 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.176 0 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 0.224 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 -0.224 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 0 0.784 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 0 -0.56 	0.16	0.25 0.25 0.25  50.0	0.65
-s	1.624 0 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.176 0 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 0.224 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 -0.224 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	1.4 0 -0.784 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 0 0 	0.4	0.25 0.25 0.25  50.0	0.65
-s	-1.96 0 0 	0.16	0.25 0.25 0.25  50.0	0.65
-s	-2.184 0 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.96 0.224 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.96 -0.224 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.96 0 0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.96 0 -0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 0.56 0 	0.16	0.25 0.25 0.25  50.0	0.65
-s	-1.176 0.56 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.624 0.56 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 0.784 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 0.56 0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 0.56 -0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 -0.56 0 	0.16	0.25 0.25 0.25  50.0	0.65
-s	-1.176 -0.56 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.624 -0.56 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 -0.784 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 -0.56 0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 -0.56 -0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 0 0.56 	0.16	0.25 0.25 0.25  50.0	0.65
-s	-1.176 0 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.624 0 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 0.224 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 -0.224 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 0 0.784 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 0 -0.56 	0.16	0.25 0.25 0.25  50.0	0.65
-s	-1.176 0 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.624 0 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 0.224 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 -0.224 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-1.4 0 -0.784 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 1.4 0 	0.4	0.25 0.25 0.25  50.0	0.65
-s	0.56 1.4 0 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.784 1.4 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 1.624 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 1.176 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 1.4 0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 1.4 -0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 1.4 0 	0.16	0.25 0.25 0.25  50.0	0.65
-s	-0.784 1.4 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 1.624 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 1.176 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 1.4 0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 1.4 -0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 1.96 0 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.224 1.96 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.224 1.96 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 2.184 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 1.96 0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 1.96 -0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 1.4 0.56 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.224 1.4 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.224 1.4 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 1.624 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 1.176 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 1.4 0.784 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 1.4 -0.56 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.224 1.4 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.224 1.4 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 1.624 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 1.176 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 1.4 -0.784 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -1.4 0 	0.4	0.25 0.25 0.25  50.0	0.65
-s	0.56 -1.4 0 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.784 -1.4 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 -1.176 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 -1.624 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 -1.4 0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 -1.4 -0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 -1.4 0 	0.16	0.25 0.25 0.25  50.0	0.65
-s	-0.784 -1.4 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 -1.176 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 -1.624 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 -1.4 0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 -1.4 -0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -1.96 0 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.224 -1.96 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.224 -1.96 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -2.184 0 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -1.96 0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -1.96 -0.224 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -1.4 0.56 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.224 -1.4 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.224 -1.4 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -1.176 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -1.624 0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -1.4 0.784 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -1.4 -0.56 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.224 -1.4 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.224 -1.4 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -1.176 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -1.624 -0.56 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -1.4 -0.784 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0 1.4 	0.4	0.25 0.25 0.25  50.0	0.65
-s	0.56 0 1.4 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.784 0 1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 0.224 1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 -0.224 1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 0 1.624 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 0 1.176 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 0 1.4 	0.16	0.25 0.25 0.25  50.0	0.65
-s	-0.784 0 1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 0.224 1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 -0.224 1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 0 1.624 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 0 1.176 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0.56 1.4 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.224 0.56 1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.224 0.56 1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0.784 1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0.56 1.624 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0.56 1.176 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -0.56 1.4 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.224 -0.56 1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.224 -0.56 1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -0.784 1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -0.56 1.624 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -0.56 1.176 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0 1.96 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.224 0 1.96 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.224 0 1.96 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0.224 1.96 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -0.224 1.96 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0 2.184 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0 -1.4 	0.4	0.25 0.25 0.25  50.0	0.65
-s	0.56 0 -1.4 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.784 0 -1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 0.224 -1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 -0.224 -1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 0 -1.176 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0.56 0 -1.624 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 0 -1.4 	0.16	0.25 0.25 0.25  50.0	0.65
-s	-0.784 0 -1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 0.224 -1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 -0.224 -1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 0 -1.176 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.56 0 -1.624 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0.56 -1.4 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.224 0.56 -1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.224 0.56 -1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0.784 -1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0.56 -1.176 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0.56 -1.624 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -0.56 -1.4 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.224 -0.56 -1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.224 -0.56 -1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -0.784 -1.4 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -0.56 -1.176 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -0.56 -1.624 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0 -1.96 	0.16	0.25 0.25 0.25  50.0	0.65
-s	0.224 0 -1.96 	0.064	0.25 0.25 0.25  50.0	0.65
-s	-0.224 0 -1.96 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0.224 -1.96 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 -0.224 -1.96 	0.064	0.25 0.25 0.25  50.0	0.65
-s	0 0 -2.184 	0.064	0.25 0.25 0.25  50.0	0.65
-s  0 -10002.25 0  10000  0.2 0.35 0.5  80.0  0.4
-s  0  10100.00 0  10000  0.5 0.2 0.1  40.0  0.0
-l	-50 68 -50
-l	40 40 150
-c	-7 6 -12 45  0 -0.65 0
diff -r e512fcf3748e -r 535c119ba090 src/Application/main.c
--- a/src/Application/main.c	Sat Oct 22 19:27:29 2011 -0700
+++ b/src/Application/main.c	Fri Oct 28 06:56:35 2011 -0700
@@ -102,14 +102,17 @@
 
 
 
-union workload{
+union timeStamp{
     uint32 highLow[2];
     uint64 total;
 };
 
 struct input_t{
     struct barrier_t* barrier;
-    uint64   workcycles;
+    uint64  totalWorkCycles;
+    uint64  workPlusMutexCycles;
+    union timeStamp startTime;
+    union timeStamp endTime;
 };
 
 
@@ -126,39 +129,43 @@
  * Workload
  */
 void work(void* input, VirtProcr* animatingPr)
-{
-    int n,m;
-    struct input_t* in = (struct input_t*)input;
-    unsigned int totalCycles = 0;
-    unsigned int workspace1;
-    double workspace2;
-    int32 privateMutex = VPThread__make_mutex(animatingPr);
+ {
+   int n,m;
+   struct input_t* in = (struct input_t*)input;
+   unsigned int totalWorkCycles = 0;
+   unsigned int workspace1;
+   double workspace2;
+   int32 privateMutex = VPThread__make_mutex(animatingPr);
 
-    for(m=0; m<repetitions; m++)
+   saveTimeStampCountInto(in->startTime.highLow[0], in->startTime.highLow[1]);
+   for(m=0; m<repetitions; m++)
     {
-        int32 stamp_startWorkload, stamp_endWorkload;
-        saveLowTimeStampCountInto( stamp_startWorkload );
-        for(n=0; n<workload_size; n++)
-        {
-            workspace1 += (workspace1 + 32)/2;
-            workspace2 += (workspace2 + 23.2)/1.4;
-        }
-        saveLowTimeStampCountInto( stamp_endWorkload );
-        int32 numCycles = stamp_endWorkload-stamp_startWorkload;
-        if( numCycles < 100000000 ) totalCycles += numCycles; //sanity check
-        
-        VPThread__mutex_lock(privateMutex, animatingPr);
-        //access queue
-        VPThread__mutex_unlock(privateMutex, animatingPr);
+      int32 stamp_startWorkload, stamp_endWorkload;
+      saveLowTimeStampCountInto( stamp_startWorkload );
+      for(n=0; n<workload_size; n++)
+       {
+         workspace1 += (workspace1 + 32)/2;
+         workspace2 += (workspace2 + 23.2)/1.4;
+       }
+      saveLowTimeStampCountInto( stamp_endWorkload );
+      int32 numCycles = stamp_endWorkload-stamp_startWorkload;
+      if( numCycles < 100000000 ) totalWorkCycles += numCycles;//sanity check
+
+      VPThread__mutex_lock(privateMutex, animatingPr);
+      //access queue
+      VPThread__mutex_unlock(privateMutex, animatingPr);
     }
-    
-    in->workcycles = totalCycles;
-    barrier_wait(in->barrier,animatingPr);
-    //Shutdown worker
-    VPThread__dissipate_thread(animatingPr);
-    printf("%d", workspace1);
-    printf("%f", workspace2);
-}
+
+   saveTimeStampCountInto( in->endTime.highLow[0], in->endTime.highLow[1] );
+   in->totalWorkCycles = totalWorkCycles;
+   in->workPlusMutexCycles = in->endTime.total - in->startTime.total;
+   barrier_wait(in->barrier, animatingPr);
+   
+   //Shutdown worker
+   VPThread__dissipate_thread(animatingPr);
+//   printf("%d", workspace1);  //Should never execute!  VMS bug if does
+//   printf("%f", workspace2);
+ }
 
 /* this is run after the VMS is set up*/
 void benchmark(void *in, VirtProcr *animatingPr)
@@ -172,19 +179,24 @@
     { input[i].barrier = &barr;
     }
 
-   union workload stamp_startThread, stamp_endThread;
-   saveTimeStampCountInto(stamp_startThread.highLow[0], stamp_startThread.highLow[1]);
+   union timeStamp startBenchTime, endBenchTime;
+   uint64 lastThreadFinishTime = 0L;
+   saveTimeStampCountInto(startBenchTime.highLow[0], startBenchTime.highLow[1]);
    for(i=0; i<num_threads; i++)
     { VPThread__create_thread((VirtProcrFnPtr)work, (void*)&input[i], animatingPr);
     }
    barrier_wait(&barr, animatingPr);
-   saveTimeStampCountInto(stamp_endThread.highLow[0], stamp_endThread.highLow[1]);
+   saveTimeStampCountInto(endBenchTime.highLow[0], endBenchTime.highLow[1]);
 
 
    for(i=0; i<num_threads; i++)
-    { printf("Workcycles: %d\n",input[i].workcycles);
+    { printf("WorkCycles: %d\n",input[i].totalWorkCycles);
+      printf("Work + Sync Cycles: %lu\n", input[i].workPlusMutexCycles);
+      if(input[i].endTime.total > lastThreadFinishTime)
+         lastThreadFinishTime = input[i].endTime.total;
     }
-   printf("Total cycles %lu\n", stamp_endThread.total-stamp_startThread.total);
+   printf("Time inside Barrier: %lu\n", endBenchTime.total-startBenchTime.total);
+   printf("Longest Span: %lu\n", lastThreadFinishTime-startBenchTime.total);
 
    //======================================================