TMS320C5505: Hwafft output higher that 32point

Dear Sir,

i get the perfect results for 8point and 16 point fft..

but when i go for 32 bits or higer than that like 64,128,256,512 and 1024 point fft i dont get the exact results. 

i followed ur tutorial.sprabb6b ,sprz281c ,sprz308d and sprz310d too..

my result is going into scratch buffer..

data=&adcOutCh3[0];

hwafft_br(data, data_br, DATA_LEN_1024); /* bit-reverse input data */

data=data_br;

//out_sel = hwafft_wrapper(data,scratch,fft_flag,scale_flag,hwafft_32pts);
out_sel = hwafft_32pts(data, scratch, scratch, data, fft_flag, scale_flag);

if (out_sel == OUT_SEL_DATA)
{
result = data;

result1 = (float *) data;
for(i=0;i<DATA_LEN_1024;i++)
{
Real_Part[i] =data[i] & 0x0000FFFF;
Imaginary_Part[i] = data[i] >> 16;
}
}
if(out_sel==OUT_SEL_SCRATCH)
{
result = scratch;
for(i=0;i<DATA_LEN_1024;i++)
{
Real_Part[i] =scratch[i] & 0x0000FFFF;
Imaginary_Part[i] = scratch[i] >> 16;
}

// .cmd file.

-stack 0x2000 /* Primary stack size */
-sysstack 0x1000 /* Secondary stack size */
-heap 0x2000 /* Heap area size */

-c /* Use C linking conventions: auto-init vars at runtime */
-u _Reset /* Force load of reset interrupt handler */

/* SPECIFY THE SYSTEM MEMORY MAP */

MEMORY
{
PAGE 0: /* ---- Unified Program/Data Address Space ---- */

MMR (RWIX): origin = 0x000000, length = 0x0000c0 /* MMRs */
// DARAM0 (RWIX): origin = 0x0000c0, length = 0x00ff40 /* 64KB - MMRs */
DARAM0 (RWIX) : origin = 00000c0h length = 007f40h /* on-chip DARAM 0 */
//DARAM1 (RWIX) : origin = 0002000h length = 002000h /* on-chip DARAM 1 */
//DARAM2 (RWIX) : origin = 0004000h length = 002000h /* on-chip DARAM 2 */
//DARAM3 (RWIX) : origin = 0006000h length = 002000h /* on-chip DARAM 3 */
DARAM4 (RWIX) : origin = 0008000h length = 002000h /* on-chip DARAM 4 */
DARAM5 (RWIX) : origin = 000a000h length = 002000h /* on-chip DARAM 5 */
DARAM6 (RWIX) : origin = 000c000h length = 002000h /* on-chip DARAM 6 */
DARAM7 (RWIX) : origin = 000e000h length = 002000h /* on-chip DARAM 7 */

SARAM0 (RWIX): origin = 0x010000, length = 0x010000 /* 64KB */
SARAM1 (RWIX): origin = 0x020000, length = 0x020000 /* 128KB */
SARAM2 (RWIX): origin = 0x040000, length = 0x00FE00 /* 64KB */
VECS (RWIX): origin = 0x04FE00, length = 0x000200 /* 512B */
PDROM (RIX): origin = 0xff8000, length = 0x008000 /* 32KB */

PAGE 2: /* -------- 64K-word I/O Address Space -------- */

IOPORT (RWI) : origin = 0x000000, length = 0x020000
}

/* SPECIFY THE SECTIONS ALLOCATION INTO MEMORY */

SECTIONS
{
.text >> SARAM1|SARAM2|SARAM0 /* Code */

/* Both stacks must be on same physical memory page */
.stack > DARAM0 /* Primary system stack */
.sysstack > DARAM0 /* Secondary system stack */

.data >> DARAM0|DARAM4|DARAM5 /* Initialized vars */
.bss >> DARAM0|DARAM6|DARAM7 /* Global & static vars */
.const >> DARAM0|DARAM4|DARAM5 /* Constant data */
.sysmem > DARAM0|DARAM6|DARAM7 /* Dynamic memory (malloc) */
.switch > SARAM2 /* Switch statement tables */
.cinit > SARAM2 /* Auto-initialization tables */
.pinit > SARAM2 /* Initialization fn tables */
.cio > SARAM2 /* C I/O buffers */
.args > SARAM2 /* Arguments to main() */

vectors > VECS /* Interrupt vectors */
.onchip_code : > SARAM2
.ioport > IOPORT PAGE 2 /* Global & static ioport vars */

//data_buf > DARAM4 ALIGN=1024
data_br_buf > SARAM0 ALIGN=1024
scratch_buf > SARAM1 ALIGN=1024
}

plzzz help me out..

i really dont understand whats going wrong