Baremetal Application Running Very Slow on Arria 10 ARM

Hello,

I have being trying to run a Baremetal Application on the Arria 10 ARM but it is running very slow. I wrote some test code and ran it on the Arria 10 system and a Xilinx system. The Xilinx system is about 25x faster.

Test Code below:

#include <time.h>
#include <stdio.h>
#include <string.h>
 
unsigned char testBuffer[500];
 
void testFunction1(void);
void testFunction2(int m);
 
int main(void)
{
	clock_t start, end, total;
 
	start = clock();
 
	testFunction1();
 
	end = clock();
 
	total = end - start;
 
	printf("Total = %d\r\n", total);
 
	return 0;
}
 
void testFunction1(void)
{
	int i = 0;
	int j = 0;
 
	for(i = 0; i < 200; i++)
	{
		for(j = 0; j < 200; j++)
		{
			memset(testBuffer, j, 500);
			testFunction2(200);
		}
	}
}
 
void testFunction2(int m)
{
	int i = 0;
 
	for(i = 0; i < m; i++)
	{
		memset(testBuffer, i, 500);
	}
}

The scatter file I am using:

OCRAM 0xFFE00000 0x40000
{
    APP_CODE +0
 
    {
        * (+RO, +RW, +ZI)
    }
 
    ARM_LIB_STACKHEAP  0xFFE20000 EMPTY  0x20000 ; Application heap and stack
    { }
}

I am using the Arm Compiler 5 (DS-5 built-in) and I have followed the steps in this guide: https://fpgawiki.intel.com/wiki/SoCEDSGettingStarted but I can't get any baremetal applications to run at a reasonable speed.

Thank you.