#include <stdio.h>
#include <sys/mman.h>
#include <string.h>
#include <sys/time.h>
#include <time.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>

// #define VIDEO_MMAP
// #define TEST_UNALIGNED

static void *srcpool;
static void *dstpool;

unsigned int sizes[] = {5,      16,    100,   256,  1000, 16384, 1048576};
unsigned int nums[] =  {100000, 50000, 10000, 5000, 1000, 50,    1};

#define TESTRUNS 10

unsigned int memtest(int size, int num, int srcaligned, int dstaligned)
{
	struct timeval tv0, tv1;
	unsigned char *src=(unsigned char *)srcpool, *dst=(unsigned char *)dstpool;
	unsigned char *sp, *dp;
	unsigned int t,i;
	long int usecs;
	unsigned long int secs;
	
	/* Get src and dst 32-byte aligned */
	src = (unsigned char *)((unsigned int)(src+31) & 0xffffffe0);
	dst = (unsigned char *)((unsigned int)(dst+31) & 0xffffffe0);
	
	/* Now unalign them if desired (some random offset) */
	if(!srcaligned)
		src += 11;
	if(!dstaligned)
		dst += 13;
	
	/* "Train" the system (caches, paging, etc...) */
	sp = src;
	dp = dst;
	for(i=0; i<num; i++) {
		memcpy(dp, sp, size);
		sp += size;
		dp += size;
	}
	
	/* Start measurement */
	gettimeofday(&tv0, NULL);
	for(t=0; t<TESTRUNS; t++) {
		sp = src;
		dp = dst;
		for(i=0; i<num; i++) {
			memcpy(dp, sp, size);
			sp += size;
			dp += size;
		}
	}
	gettimeofday(&tv1, NULL);
	secs = tv1.tv_sec-tv0.tv_sec;
	usecs = tv1.tv_usec-tv0.tv_usec;
	if(usecs<0) {
		usecs += 1000000;
		secs -= 1;
	}
	return usecs+1000000L*secs;
}

unsigned int memverify(int size, int num, int srcaligned, int dstaligned)
{
	unsigned char *src=(unsigned char *)srcpool, *dst=(unsigned char *)dstpool;
	
	/* Get src and dst 32-byte aligned */
	src = (unsigned char *)((unsigned int)(src+31) & 0xffffffe0);
	dst = (unsigned char *)((unsigned int)(dst+31) & 0xffffffe0);
	
	/* Now unalign them if desired (some random offset) */
	if(!srcaligned)
		src += 11;
	if(!dstaligned)
		dst += 13;
	
	return memcmp(dst, src, size*num);
}


void evaluate(char *name, unsigned int totalsize, unsigned int usecs)
{
	double rate;
	
	rate = (double)totalsize*(double)TESTRUNS/((double)usecs/1000000.0);
	rate /= (1024.0*1024.0);
	printf("Memcpy %-30s: %5.3g Mbyte/s (memory throughput: %5.3g Mbytes/s)\n",name, rate, rate*2.0);
}

int main(void)
{
	int t,i;
	unsigned int usecs;
	char buf[50];
	struct timeval tv;
#ifdef VIDEO_MMAP
	unsigned long int *mem;
	int f;
	
	printf("Opening fb0\n");
	f = open("/dev/fb0", O_RDWR);
	if(f<0) {
		perror("opening fb0");
		return 1;
	}
	printf("mmapping fb0\n");
	
	mem = mmap(NULL, 0x00300000, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_LOCKED,f,0);
	
	printf("mmap returned: %08x\n",(unsigned int)mem);
	perror("mmap");
	if(mem==-1)
		return 1;
#else
	unsigned long int mem[786432];
#endif
	
	srcpool = (unsigned char *)mem;
	dstpool = (unsigned char *)mem;
	dstpool += 1572864; /* 1.5 Mbyte offset into 3 Mbyte framebuffer */
	
	gettimeofday(&tv, NULL);
	for(t=0; t<0x000c0000; t++)
		mem[t] = (tv.tv_usec ^ tv.tv_sec) ^ t;

	printf("Fully aligned:\n");	
	for(t=0; t<(sizeof(nums)/sizeof(nums[0])); t++) {
		snprintf(buf, 50, "%d chunks of %d bytes", nums[t], sizes[t]);
		usecs = memtest(sizes[t], nums[t], 1, 1);
		evaluate(buf, nums[t]*sizes[t], usecs);
		if(memverify(sizes[t], nums[t], 1, 1)) {
			printf("Verify faild!\n");
		}
	}
#ifdef TEST_UNALIGNED
	printf("source unaligned:\n");	
	for(t=0; t<(sizeof(nums)/sizeof(nums[0])); t++) {
		snprintf(buf, 50, "%d chunks of %d bytes", nums[t], sizes[t]);
		usecs = memtest(sizes[t], nums[t], 0, 1);
		evaluate(buf, nums[t]*sizes[t], usecs);
	}
	
	printf("destination unaligned:\n");	
	for(t=0; t<(sizeof(nums)/sizeof(nums[0])); t++) {
		snprintf(buf, 50, "%d chunks of %d bytes", nums[t], sizes[t]);
		usecs = memtest(sizes[t], nums[t], 1, 0);
		evaluate(buf, nums[t]*sizes[t], usecs);
	}
	
	printf("both unaligned:\n");	
	for(t=0; t<(sizeof(nums)/sizeof(nums[0])); t++) {
		snprintf(buf, 50, "%d chunks of %d bytes", nums[t], sizes[t]);
		usecs = memtest(sizes[t], nums[t], 0, 0);
		evaluate(buf, nums[t]*sizes[t], usecs);
	}
#endif	
	return 0;
}