Very low speed of HPS after Preloader

When you enable the caches, you also have to initialize the MMU.

# include <stdio.h>

# include <stdlib.h>

# include <assert.h>

# include "alt_cache.h"

# include "alt_mmu.h"

int __auto_semihosting;

# define N 256

# define ARRAY_SIZE(array) (sizeof(array) / sizeof(array[0]))

void mul(const double *in_a, const double *in_b, unsigned n, double *out);

/* MMU Page table - 16KB aligned at 16KB boundary */

static uint32_t __attribute__ ((aligned (0x4000))) alt_pt_storage[4096];

static void *alt_pt_alloc(const size_t size, void *context)

{

return context;

}

static void mmu_init(void)

{

uint32_t *ttb1 = NULL;

/* Populate the page table with sections (1 MiB regions). */

ALT_MMU_MEM_REGION_t regions[] = {

/* Memory area: 1 GiB */

{

.va = (void *)0x00000000,

.pa = (void *)0x00000000,

.size = 0x40000000,

.access = ALT_MMU_AP_FULL_ACCESS,

.attributes = ALT_MMU_ATTR_WBA,

.shareable = ALT_MMU_TTB_S_NON_SHAREABLE,

.execute = ALT_MMU_TTB_XN_DISABLE,

.security = ALT_MMU_TTB_NS_SECURE

},

/* Device area: Everything else */

{

.va = (void *)0x40000000,

.pa = (void *)0x40000000,

.size = 0xc0000000,

.access = ALT_MMU_AP_FULL_ACCESS,

.attributes = ALT_MMU_ATTR_DEVICE_NS,

.shareable = ALT_MMU_TTB_S_NON_SHAREABLE,

.execute = ALT_MMU_TTB_XN_ENABLE,

.security = ALT_MMU_TTB_NS_SECURE

}

};

assert(ALT_E_SUCCESS == alt_mmu_init());

assert(alt_mmu_va_space_storage_required(regions, ARRAY_SIZE(regions)) <= sizeof(alt_pt_storage));

assert(ALT_E_SUCCESS == alt_mmu_va_space_create(&ttb1, regions, ARRAY_SIZE(regions), alt_pt_alloc, alt_pt_storage));

assert(ALT_E_SUCCESS == alt_mmu_va_space_enable(ttb1));

}

int main(int argc, char** argv) {

static double a[N], b[N], c[N];

unsigned i, t;

mmu_init();

alt_cache_system_enable();

for (i = 0; i < N; i++) {

a = (double)rand();

b = (double)rand();

}

*(unsigned volatile *)0xFFFEC600 = 0xFFFFFFFF; /* timer reload value */

*(unsigned volatile *)0xFFFEC604 = 0xFFFFFFFF; /* current timer value */

*(unsigned volatile *)0xFFFEC608 = 0x003; /* start timer at 200MHz and automatically reload */

mul(a, b, N, c);

t = *(unsigned volatile *)0xFFFEC604;

printf("used time for %u multiplications = %u ns\n", N, 5 * (0xFFFFFFFF - t));

return 0;

}