Пишу алгоритм FFT на Си для процессора Эльбрус: прямая векторизация

Исходный код лежит здесь.

Структура кода намеренно сделана как можно проще (в смысле «simple», а не «easy»).
Приоритеты в порядке убывания:
 — Скорость выполнения
 — Единообразие
 — Понятность

Компиляция:
./compile.sh */*.c

Проверка корректности:
./check_all.sh 12 1000 x

Измерение скорости:
taskset 1 ./speed_all_stage.sh 12 10000 x
taskset 1 ./speed_all_fft.sh 12 10000 x

taskset 1 нужен для корректного чтения счётчика тактов (привязка к первому ядру).

При компиляции использовались следующие опции lcc:

-Wall -O3 -faligned -ffast-math -march=elbrus-v5

Почему я компилирую для elbrus-v5 написано здесь.

# Версия lcc:
$ lcc --version
lcc:1.29.16:Jan-22-2026:e2k-2c3-linux
gcc (GCC) 11.3.0 compatible

# Версия ОС
$ uname -a
Linux BB8 6.1.0-1.11-e2c3 #1 SMP Mon Mar 30 14:31:34 UTC 2026 e2k E2C3 Elbrus-MCST GNU/Linux

Замеры времени делались с помощью функции clock_gettime():

struct timespec t0, t1;
clock_gettime(CLOCK_REALTIME, &t0);
/***  здесь измеряемый код  ***/
clock_gettime(CLOCK_REALTIME, &t1);
int usec = (t1.tv_sec - t0.tv_sec)*1000000 + (t1.tv_nsec - t0.tv_nsec)/1000;

Также использовалось чтение счётчика тактов процессора:

uint64_t get_clock_count()
{
	uint64_t dst;
	#pragma asm_inline
	asm ("rrd %%clkr, %0" : "=r" (dst));
	return dst;
}

...

uint64_t ticks0 = get_clock_count();
/***  здесь измеряемый код  ***/
uint64_t ticks1 = get_clock_count();
uint64_t ticks = ticks1 - ticks0;

Графики рисовались в Google Sheets.

Данные для графиков собирались с помощью скрипта data_for_diagram.py, который запускает программу измерения скорости с разными параметрами и парсит её вывод.
Пример запуска скрипта:

taskset 1 ./data_for_diagram.py \
./fft_radix2/fft_radix2_speedtest 4 21 1 1000 -1 > out.txt

taskset 1 нужен для корректного чтения счётчика тактов (привязка к первому ядру).

• fft_radix2_vector2

• fft_radix2_vector4

• fft_radix4_vector2

• fft_radix4_vector4

void reverse_radix2_vector2(int bit_count_in, myComplex *data_in, myComplex2 *data_out)
{
	int bit_count_out = bit_count_in - 1;

//	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in  = (__v2di*)data_in;
	__v2di *out = (__v2di*)data_out;

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out; ++i)
	{
		int64_t index = __builtin_e2k_bitrevd(i) >> shift_out;
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		out[index] = __builtin_e2k_qppermb(in[i], in[i], mask);
	}
}

.L4793:
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=1, asz=5, abs=0, disp=0
        }
.L4668:
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          bitrevd,0,sm  %b[11], %b[13]
          qppermb,1,sm  %b[10], %b[10], %r4, %b[12]
          addd,2,sm     %b[11], 0x1, %b[9]
          shrd,3,sm     %b[17], %r0, %b[19]
          shld,4,sm     %b[21], 0x4, %b[20]
          stqp,5        %r2, %b[22], %b[18]
          movaqp,1      area=0, ind=0, am=1, be=0, %b[0]
        }

void reverse_radix2_vector2_x2(int bit_count_in, myComplex *data_in, myComplex2 *data_out)
{
	int bit_count_out = bit_count_in - 1;

//	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;
	int64_t delta = (1LL << shift_out) / 16;

	__v2di *in    = (__v2di*) data_in;
	__v2di *out_0 = (__v2di*)&data_out[0];
	__v2di *out_1 = (__v2di*)&data_out[count_out/2];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0, shifted_i = 0; i < count_out; i += 2, shifted_i += 2*delta)
	{
		int64_t offset = __builtin_e2k_bitrevd(shifted_i);
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		*(__v2du*)((void*)out_0 + offset) = __builtin_e2k_qppermb(in[i + 0], in[i + 0], mask);
		*(__v2du*)((void*)out_1 + offset) = __builtin_e2k_qppermb(in[i + 1], in[i + 1], mask);
	}
}

.L5010:
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=5, abs=0, disp=0
        }
.L4823:
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          bitrevd,0,sm  %b[22], %b[13]
          qppermb,1,sm  %b[10], %b[10], %r5, %b[19]
          stqp,2        %r4, %b[17], %b[21]
          qppermb,3,sm  %b[11], %b[11], %r5, %b[23]
          addd,4,sm     %b[20], %r0, %b[18]
          stqp,5        %r2, %b[17], %b[25]
          movaqp,0      area=0, ind=16, am=1, be=0, %b[0]
          movaqp,1      area=0, ind=0, am=0, be=0, %b[1]
        }

void reverse_radix2_vector2_stream2(int bit_count_in, myComplex *data_in, myComplex2 *data_out)
{
	int bit_count_out = bit_count_in - 1;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;
	int64_t delta = (1LL << shift_out) / 16;

	__v2di *in_0 = (__v2di*)&data_in[0];
	__v2di *in_1 = (__v2di*)&data_in[count_in/2];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0, shifted_i = 0; i < count_out/2; ++i, shifted_i += delta)
	{
		int64_t offset = __builtin_e2k_bitrevd(shifted_i);
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		*(__v2du*)((void*)data_out + offset + 0*16) = __builtin_e2k_qppermb(in_0[i], in_0[i], mask);
		*(__v2du*)((void*)data_out + offset + 1*16) = __builtin_e2k_qppermb(in_1[i], in_1[i], mask);
	}
}

.L5212:
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=2, asz=5, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=1, asz=5, abs=0, disp=0
        }
.L5039:
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          bitrevd,0,sm  %b[22], %b[13]
          qppermb,1,sm  %b[11], %b[11], %r5, %b[23]
          stqp,2        %r2, %b[17], %b[25]
          qppermb,3,sm  %b[10], %b[10], %r5, %b[19]
          addd,4,sm     %b[20], %r4, %b[18]
          stqp,5        %r0, %b[17], %b[21]
          movaqp,1      area=0, ind=0, am=1, be=0, %b[1]
          movaqp,3      area=0, ind=0, am=1, be=0, %b[0]
        }

void reverse_radix2_vector2_stream4(int bit_count_in, myComplex *data_in, myComplex2 *data_out)
{
	int bit_count_out = bit_count_in - 1;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_00 = (__v2di*)&data_in[0 * count_in/4];
	__v2di *in_01 = (__v2di*)&data_in[1 * count_in/4];
	__v2di *in_10 = (__v2di*)&data_in[2 * count_in/4];
	__v2di *in_11 = (__v2di*)&data_in[3 * count_in/4];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/4; ++i)
	{
		int64_t offset = 16 * (__builtin_e2k_bitrevd(i) >> shift_out);
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		*(__v2du*)((void*)data_out + offset + 0*16) = __builtin_e2k_qppermb(in_00[i], in_00[i], mask);
		*(__v2du*)((void*)data_out + offset + 1*16) = __builtin_e2k_qppermb(in_10[i], in_10[i], mask);
		*(__v2du*)((void*)data_out + offset + 2*16) = __builtin_e2k_qppermb(in_01[i], in_01[i], mask);
		*(__v2du*)((void*)data_out + offset + 3*16) = __builtin_e2k_qppermb(in_11[i], in_11[i], mask);
	}
}

.L5516:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=4, asz=4, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=3, asz=4, abs=0, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=2, asz=4, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=1, asz=4, abs=16, disp=0
        }
.L5255:
        {
          loop_mode
          bitrevd,0,sm  %b[4], %b[1]
          qppermb,1,sm  %b[27], %b[27], %r7, %b[9]
          stqp,2        %r2, %b[14], %b[28]
          shld,3,sm     %b[24], 0x4, %b[12]
          qppermb,4,sm  %b[22], %b[22], %r7, %b[5]
          stqp,5        %r4, %b[14], %b[26]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[19], %b[19], %r7, %b[26]
          addd,1,sm     %b[2], 0x1, %b[0]
          stqp,2        %r0, %b[14], %b[11]
          qppermb,3,sm  %b[10], %b[10], %r7, %b[24]
          shrd,4,sm     %b[3], %r6, %b[22]
          stqp,5        %r5, %b[14], %b[7]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[4]
          movaqp,1      area=0, ind=0, am=1, be=0, %b[13]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[16]
          movaqp,3      area=0, ind=0, am=1, be=0, %b[21]
        }

void reverse_radix2_vector2_stream8(int bit_count_in, myComplex *data_in, myComplex2 *data_out)
{
	int bit_count_out = bit_count_in - 1;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_000 = (__v2di*)&data_in[0 * count_in/8];
	__v2di *in_001 = (__v2di*)&data_in[1 * count_in/8];
	__v2di *in_010 = (__v2di*)&data_in[2 * count_in/8];
	__v2di *in_011 = (__v2di*)&data_in[3 * count_in/8];
	__v2di *in_100 = (__v2di*)&data_in[4 * count_in/8];
	__v2di *in_101 = (__v2di*)&data_in[5 * count_in/8];
	__v2di *in_110 = (__v2di*)&data_in[6 * count_in/8];
	__v2di *in_111 = (__v2di*)&data_in[7 * count_in/8];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/8; ++i)
	{
		int64_t offset = 16 * (__builtin_e2k_bitrevd(i) >> shift_out);
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		*(__v2du*)((void*)data_out + offset + 0*16) = __builtin_e2k_qppermb(in_000[i], in_000[i], mask);
		*(__v2du*)((void*)data_out + offset + 1*16) = __builtin_e2k_qppermb(in_100[i], in_100[i], mask);
		*(__v2du*)((void*)data_out + offset + 2*16) = __builtin_e2k_qppermb(in_010[i], in_010[i], mask);
		*(__v2du*)((void*)data_out + offset + 3*16) = __builtin_e2k_qppermb(in_110[i], in_110[i], mask);
		*(__v2du*)((void*)data_out + offset + 4*16) = __builtin_e2k_qppermb(in_001[i], in_001[i], mask);
		*(__v2du*)((void*)data_out + offset + 5*16) = __builtin_e2k_qppermb(in_101[i], in_101[i], mask);
		*(__v2du*)((void*)data_out + offset + 6*16) = __builtin_e2k_qppermb(in_011[i], in_011[i], mask);
		*(__v2du*)((void*)data_out + offset + 7*16) = __builtin_e2k_qppermb(in_111[i], in_111[i], mask);
	}
}

.L6024:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=8, asz=3, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=7, asz=3, abs=0, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=6, asz=3, abs=8, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=5, asz=3, abs=8, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=4, asz=3, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=3, asz=3, abs=16, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=2, asz=3, abs=24, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=1, asz=3, abs=24, disp=0
        }
.L5591:
        {
          loop_mode
          qppermb,1,sm  %b[21], %b[21], %r11, %b[26]
          stqp,2        %r2, %b[18], %b[24]
          qppermb,4,sm  %b[13], %b[13], %r11, %b[25]
          stqp,5        %r4, %b[18], %b[23]
        }
        {
          loop_mode
          qppermb,1,sm  %b[12], %b[12], %r11, %b[24]
          stqp,2        %r0, %b[18], %b[26]
          shrd,3,sm     %b[22], %r12, %b[1]
          qppermb,4,sm  %b[5], %b[5], %r11, %b[23]
          stqp,5        %r5, %b[18], %b[25]
        }
        {
          loop_mode
          qppermb,1,sm  %b[9], %b[9], %r11, %b[27]
          stqp,2        %r6, %b[18], %b[24]
          shld,3,sm     %b[1], 0x4, %b[16]
          qppermb,4,sm  %b[8], %b[8], %r11, %b[25]
          stqp,5        %r9, %b[18], %b[23]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[12]
          movaqp,1      area=0, ind=0, am=1, be=0, %b[13]
          movaqp,2      area=3, ind=0, am=1, be=0, %b[4]
          movaqp,3      area=2, ind=0, am=1, be=0, %b[5]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[15], %b[15], %r11, %b[22]
          addd,1,sm     %b[2], 0x1, %b[0]
          stqp,2        %r7, %b[18], %b[27]
          qppermb,3,sm  %b[14], %b[14], %r11, %b[21]
          bitrevd,4,sm  %b[2], %b[20]
          stqp,5        %r10, %b[18], %b[25]
          movaqp,0      area=3, ind=0, am=1, be=0, %b[1]
          movaqp,1      area=2, ind=0, am=1, be=0, %b[8]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[9]
          movaqp,3      area=0, ind=0, am=1, be=0, %b[17]
        }

void reverse_radix2_vector2_stream16(int bit_count_in, myComplex *data_in, myComplex2 *data_out)
{
	int bit_count_out = bit_count_in - 1;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_0000 = (__v2di*)&data_in[ 0 * count_in/16];
	__v2di *in_0001 = (__v2di*)&data_in[ 1 * count_in/16];
	__v2di *in_0010 = (__v2di*)&data_in[ 2 * count_in/16];
	__v2di *in_0011 = (__v2di*)&data_in[ 3 * count_in/16];
	__v2di *in_0100 = (__v2di*)&data_in[ 4 * count_in/16];
	__v2di *in_0101 = (__v2di*)&data_in[ 5 * count_in/16];
	__v2di *in_0110 = (__v2di*)&data_in[ 6 * count_in/16];
	__v2di *in_0111 = (__v2di*)&data_in[ 7 * count_in/16];
	__v2di *in_1000 = (__v2di*)&data_in[ 8 * count_in/16];
	__v2di *in_1001 = (__v2di*)&data_in[ 9 * count_in/16];
	__v2di *in_1010 = (__v2di*)&data_in[10 * count_in/16];
	__v2di *in_1011 = (__v2di*)&data_in[11 * count_in/16];
	__v2di *in_1100 = (__v2di*)&data_in[12 * count_in/16];
	__v2di *in_1101 = (__v2di*)&data_in[13 * count_in/16];
	__v2di *in_1110 = (__v2di*)&data_in[14 * count_in/16];
	__v2di *in_1111 = (__v2di*)&data_in[15 * count_in/16];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/16; ++i)
	{
		int64_t offset = 16 * (__builtin_e2k_bitrevd(i) >> shift_out);
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		*(__v2du*)((void*)data_out + offset +  0*16) = __builtin_e2k_qppermb(in_0000[i], in_0000[i], mask);
		*(__v2du*)((void*)data_out + offset +  1*16) = __builtin_e2k_qppermb(in_1000[i], in_1000[i], mask);
		*(__v2du*)((void*)data_out + offset +  2*16) = __builtin_e2k_qppermb(in_0100[i], in_0100[i], mask);
		*(__v2du*)((void*)data_out + offset +  3*16) = __builtin_e2k_qppermb(in_1100[i], in_1100[i], mask);
		*(__v2du*)((void*)data_out + offset +  4*16) = __builtin_e2k_qppermb(in_0010[i], in_0010[i], mask);
		*(__v2du*)((void*)data_out + offset +  5*16) = __builtin_e2k_qppermb(in_1010[i], in_1010[i], mask);
		*(__v2du*)((void*)data_out + offset +  6*16) = __builtin_e2k_qppermb(in_0110[i], in_0110[i], mask);
		*(__v2du*)((void*)data_out + offset +  7*16) = __builtin_e2k_qppermb(in_1110[i], in_1110[i], mask);
		*(__v2du*)((void*)data_out + offset +  8*16) = __builtin_e2k_qppermb(in_0001[i], in_0001[i], mask);
		*(__v2du*)((void*)data_out + offset +  9*16) = __builtin_e2k_qppermb(in_1001[i], in_1001[i], mask);
		*(__v2du*)((void*)data_out + offset + 10*16) = __builtin_e2k_qppermb(in_0101[i], in_0101[i], mask);
		*(__v2du*)((void*)data_out + offset + 11*16) = __builtin_e2k_qppermb(in_1101[i], in_1101[i], mask);
		*(__v2du*)((void*)data_out + offset + 12*16) = __builtin_e2k_qppermb(in_0011[i], in_0011[i], mask);
		*(__v2du*)((void*)data_out + offset + 13*16) = __builtin_e2k_qppermb(in_1011[i], in_1011[i], mask);
		*(__v2du*)((void*)data_out + offset + 14*16) = __builtin_e2k_qppermb(in_0111[i], in_0111[i], mask);
		*(__v2du*)((void*)data_out + offset + 15*16) = __builtin_e2k_qppermb(in_1111[i], in_1111[i], mask);
	}
}

.L6935:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=1, incr=0, ind=0, asz=2, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=15, asz=2, abs=0, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=14, asz=2, abs=4, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=13, asz=2, abs=4, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=12, asz=2, abs=8, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=11, asz=2, abs=8, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=10, asz=2, abs=12, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=9, asz=2, abs=12, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=8, asz=2, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=7, asz=2, abs=16, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=6, asz=2, abs=20, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=5, asz=2, abs=20, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=4, asz=2, abs=24, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=3, asz=2, abs=24, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=2, asz=2, abs=28, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=1, asz=2, abs=28, disp=0
        }
.L6163:
        {
          loop_mode
          qppermb,1,sm  %b[24], %b[24], %r1, %b[28]
          stqp,2        %r2, %b[13], %b[9]
          qppermb,4,sm  %b[22], %b[22], %r1, %b[27]
          stqp,5        %r5, %b[13], %b[4]
        }
        {
          loop_mode
          qppermb,1,sm  %b[26], %b[26], %r1, %b[30]
          stqp,2        %r0, %b[13], %b[28]
          qppermb,4,sm  %b[25], %b[25], %r1, %b[29]
          stqp,5        %r6, %b[13], %b[27]
          movaqp,0      area=7, ind=0, am=1, be=0, %b[10]
          movaqp,1      area=6, ind=0, am=1, be=0, %b[4]
          movaqp,2      area=7, ind=0, am=1, be=0, %b[7]
          movaqp,3      area=6, ind=0, am=1, be=0, %b[1]
        }
        {
          loop_mode
          qppermb,1,sm  %b[23], %b[23], %r1, %b[27]
          stqp,2        %r7, %b[13], %b[30]
          qppermb,4,sm  %b[16], %b[16], %r1, %b[26]
          stqp,5        %r10, %b[13], %b[29]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[15]
          movaqp,1      area=0, ind=0, am=1, be=0, %b[17]
          movaqp,2      area=5, ind=0, am=1, be=0, %b[9]
          movaqp,3      area=4, ind=0, am=1, be=0, %b[12]
        }
        {
          loop_mode
          qppermb,1,sm  %b[21], %b[21], %r1, %b[29]
          stqp,2        %r9, %b[13], %b[27]
          qppermb,4,sm  %b[14], %b[14], %r1, %b[28]
          stqp,5        %r11, %b[13], %b[26]
          movaqp,0      area=5, ind=0, am=1, be=0, %b[16]
          movaqp,1      area=4, ind=0, am=1, be=0, %b[19]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[20]
          movaqp,3      area=0, ind=0, am=1, be=0, %b[22]
        }
        {
          loop_mode
          addd,0,sm     %b[2], 0x1, %b[0]
          qppermb,1,sm  %b[18], %b[18], %r1, %b[27]
          stqp,2        %r12, %b[13], %b[29]
          bitrevd,3,sm  %b[2], %b[25]
          qppermb,4,sm  %b[11], %b[11], %r1, %b[26]
          stqp,5        %r13, %b[13], %b[28]
          movaqp,0      area=3, ind=0, am=1, be=0, %b[23]
          movaqp,1      area=2, ind=0, am=1, be=0, %b[24]
          movaqp,2      area=3, ind=0, am=1, be=0, %b[14]
          movaqp,3      area=2, ind=0, am=1, be=0, %b[21]
        }
        {
          loop_mode
          qppermb,1,sm  %b[6], %b[6], %r1, %b[29]
          stqp,2        %r14, %b[13], %b[27]
          shrd,3,sm     %b[25], %r20, %b[2]
          qppermb,4,sm  %b[3], %b[3], %r1, %b[28]
          stqp,5        %r15, %b[13], %b[26]
        }
        {
          loop_mode
          qppermb,1,sm  %b[10], %b[10], %r1, %b[6]
          stqp,2        %r16, %b[13], %b[29]
          shld,3,sm     %b[2], 0x4, %b[11]
          qppermb,4,sm  %b[7], %b[7], %r1, %b[3]
          stqp,5        %r17, %b[13], %b[28]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[17], %b[17], %r1, %b[7]
          stqp,2        %r18, %b[13], %b[8]
          qppermb,3,sm  %b[15], %b[15], %r1, %b[2]
          stqp,5        %r19, %b[13], %b[5]
        }

void reverse_radix2_vector2_stream32(int bit_count_in, myComplex *data_in, myComplex2 *data_out)
{
	int bit_count_out = bit_count_in - 1;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_00000 = (__v2di*)&data_in[ 0 * count_in/32];
	__v2di *in_00001 = (__v2di*)&data_in[ 1 * count_in/32];
	__v2di *in_00010 = (__v2di*)&data_in[ 2 * count_in/32];
	__v2di *in_00011 = (__v2di*)&data_in[ 3 * count_in/32];
	__v2di *in_00100 = (__v2di*)&data_in[ 4 * count_in/32];
	__v2di *in_00101 = (__v2di*)&data_in[ 5 * count_in/32];
	__v2di *in_00110 = (__v2di*)&data_in[ 6 * count_in/32];
	__v2di *in_00111 = (__v2di*)&data_in[ 7 * count_in/32];
	__v2di *in_01000 = (__v2di*)&data_in[ 8 * count_in/32];
	__v2di *in_01001 = (__v2di*)&data_in[ 9 * count_in/32];
	__v2di *in_01010 = (__v2di*)&data_in[10 * count_in/32];
	__v2di *in_01011 = (__v2di*)&data_in[11 * count_in/32];
	__v2di *in_01100 = (__v2di*)&data_in[12 * count_in/32];
	__v2di *in_01101 = (__v2di*)&data_in[13 * count_in/32];
	__v2di *in_01110 = (__v2di*)&data_in[14 * count_in/32];
	__v2di *in_01111 = (__v2di*)&data_in[15 * count_in/32];
	__v2di *in_10000 = (__v2di*)&data_in[16 * count_in/32];
	__v2di *in_10001 = (__v2di*)&data_in[17 * count_in/32];
	__v2di *in_10010 = (__v2di*)&data_in[18 * count_in/32];
	__v2di *in_10011 = (__v2di*)&data_in[19 * count_in/32];
	__v2di *in_10100 = (__v2di*)&data_in[20 * count_in/32];
	__v2di *in_10101 = (__v2di*)&data_in[21 * count_in/32];
	__v2di *in_10110 = (__v2di*)&data_in[22 * count_in/32];
	__v2di *in_10111 = (__v2di*)&data_in[23 * count_in/32];
	__v2di *in_11000 = (__v2di*)&data_in[24 * count_in/32];
	__v2di *in_11001 = (__v2di*)&data_in[25 * count_in/32];
	__v2di *in_11010 = (__v2di*)&data_in[26 * count_in/32];
	__v2di *in_11011 = (__v2di*)&data_in[27 * count_in/32];
	__v2di *in_11100 = (__v2di*)&data_in[28 * count_in/32];
	__v2di *in_11101 = (__v2di*)&data_in[29 * count_in/32];
	__v2di *in_11110 = (__v2di*)&data_in[30 * count_in/32];
	__v2di *in_11111 = (__v2di*)&data_in[31 * count_in/32];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/32; ++i)
	{
		int64_t offset = 16 * (__builtin_e2k_bitrevd(i) >> shift_out);
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		*(__v2du*)((void*)data_out + offset +  0*16) = __builtin_e2k_qppermb(in_00000[i], in_00000[i], mask);
		*(__v2du*)((void*)data_out + offset +  1*16) = __builtin_e2k_qppermb(in_10000[i], in_10000[i], mask);
		*(__v2du*)((void*)data_out + offset +  2*16) = __builtin_e2k_qppermb(in_01000[i], in_01000[i], mask);
		*(__v2du*)((void*)data_out + offset +  3*16) = __builtin_e2k_qppermb(in_11000[i], in_11000[i], mask);
		*(__v2du*)((void*)data_out + offset +  4*16) = __builtin_e2k_qppermb(in_00100[i], in_00100[i], mask);
		*(__v2du*)((void*)data_out + offset +  5*16) = __builtin_e2k_qppermb(in_10100[i], in_10100[i], mask);
		*(__v2du*)((void*)data_out + offset +  6*16) = __builtin_e2k_qppermb(in_01100[i], in_01100[i], mask);
		*(__v2du*)((void*)data_out + offset +  7*16) = __builtin_e2k_qppermb(in_11100[i], in_11100[i], mask);
		*(__v2du*)((void*)data_out + offset +  8*16) = __builtin_e2k_qppermb(in_00010[i], in_00010[i], mask);
		*(__v2du*)((void*)data_out + offset +  9*16) = __builtin_e2k_qppermb(in_10010[i], in_10010[i], mask);
		*(__v2du*)((void*)data_out + offset + 10*16) = __builtin_e2k_qppermb(in_01010[i], in_01010[i], mask);
		*(__v2du*)((void*)data_out + offset + 11*16) = __builtin_e2k_qppermb(in_11010[i], in_11010[i], mask);
		*(__v2du*)((void*)data_out + offset + 12*16) = __builtin_e2k_qppermb(in_00110[i], in_00110[i], mask);
		*(__v2du*)((void*)data_out + offset + 13*16) = __builtin_e2k_qppermb(in_10110[i], in_10110[i], mask);
		*(__v2du*)((void*)data_out + offset + 14*16) = __builtin_e2k_qppermb(in_01110[i], in_01110[i], mask);
		*(__v2du*)((void*)data_out + offset + 15*16) = __builtin_e2k_qppermb(in_11110[i], in_11110[i], mask);
		*(__v2du*)((void*)data_out + offset + 16*16) = __builtin_e2k_qppermb(in_00001[i], in_00001[i], mask);
		*(__v2du*)((void*)data_out + offset + 17*16) = __builtin_e2k_qppermb(in_10001[i], in_10001[i], mask);
		*(__v2du*)((void*)data_out + offset + 18*16) = __builtin_e2k_qppermb(in_01001[i], in_01001[i], mask);
		*(__v2du*)((void*)data_out + offset + 19*16) = __builtin_e2k_qppermb(in_11001[i], in_11001[i], mask);
		*(__v2du*)((void*)data_out + offset + 20*16) = __builtin_e2k_qppermb(in_00101[i], in_00101[i], mask);
		*(__v2du*)((void*)data_out + offset + 21*16) = __builtin_e2k_qppermb(in_10101[i], in_10101[i], mask);
		*(__v2du*)((void*)data_out + offset + 22*16) = __builtin_e2k_qppermb(in_01101[i], in_01101[i], mask);
		*(__v2du*)((void*)data_out + offset + 23*16) = __builtin_e2k_qppermb(in_11101[i], in_11101[i], mask);
		*(__v2du*)((void*)data_out + offset + 24*16) = __builtin_e2k_qppermb(in_00011[i], in_00011[i], mask);
		*(__v2du*)((void*)data_out + offset + 25*16) = __builtin_e2k_qppermb(in_10011[i], in_10011[i], mask);
		*(__v2du*)((void*)data_out + offset + 26*16) = __builtin_e2k_qppermb(in_01011[i], in_01011[i], mask);
		*(__v2du*)((void*)data_out + offset + 27*16) = __builtin_e2k_qppermb(in_11011[i], in_11011[i], mask);
		*(__v2du*)((void*)data_out + offset + 28*16) = __builtin_e2k_qppermb(in_00111[i], in_00111[i], mask);
		*(__v2du*)((void*)data_out + offset + 29*16) = __builtin_e2k_qppermb(in_10111[i], in_10111[i], mask);
		*(__v2du*)((void*)data_out + offset + 30*16) = __builtin_e2k_qppermb(in_01111[i], in_01111[i], mask);
		*(__v2du*)((void*)data_out + offset + 31*16) = __builtin_e2k_qppermb(in_11111[i], in_11111[i], mask);
	}
}

.L8688:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=17, incr=0, ind=0, asz=1, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=16, incr=0, ind=0, asz=1, abs=0, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=15, incr=0, ind=0, asz=1, abs=2, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=14, incr=0, ind=0, asz=1, abs=2, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=13, incr=0, ind=0, asz=1, abs=4, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=12, incr=0, ind=0, asz=1, abs=4, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=11, incr=0, ind=0, asz=1, abs=6, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=10, incr=0, ind=0, asz=1, abs=6, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=9, incr=0, ind=0, asz=1, abs=8, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=8, incr=0, ind=0, asz=1, abs=8, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=7, incr=0, ind=0, asz=1, abs=10, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=6, incr=0, ind=0, asz=1, abs=10, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=5, incr=0, ind=0, asz=1, abs=12, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=4, incr=0, ind=0, asz=1, abs=12, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=3, incr=0, ind=0, asz=1, abs=14, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=2, incr=0, ind=0, asz=1, abs=14, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=1, incr=0, ind=0, asz=1, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=15, asz=1, abs=16, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=14, asz=1, abs=18, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=13, asz=1, abs=18, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=12, asz=1, abs=20, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=11, asz=1, abs=20, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=10, asz=1, abs=22, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=9, asz=1, abs=22, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=8, asz=1, abs=24, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=7, asz=1, abs=24, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=6, asz=1, abs=26, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=5, asz=1, abs=26, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=4, asz=1, abs=28, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=3, asz=1, abs=28, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=2, asz=1, abs=30, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=1, asz=1, abs=30, disp=0
        }
.L7202:
        {
          loop_mode
          qppermb,1,sm  %b[37], %b[37], %r0, %b[21]
          stqp,2        %r2, %b[16], %b[20]
          qppermb,4,sm  %b[35], %b[35], %r0, %b[18]
          stqp,5        %r6, %b[16], %b[18]
        }
        {
          loop_mode
          qppermb,1,sm  %b[39], %b[39], %r0, %b[20]
          stqp,2        %r4, %b[16], %b[21]
          qppermb,4,sm  %b[38], %b[38], %r0, %b[18]
          stqp,5        %r7, %b[16], %b[18]
        }
        {
          loop_mode
          qppermb,1,sm  %b[23], %b[23], %r0, %b[19]
          stqp,2        %r9, %b[16], %b[20]
          qppermb,4,sm  %b[19], %b[19], %r0, %b[18]
          stqp,5        %r11, %b[16], %b[18]
        }
        {
          loop_mode
          qppermb,1,sm  %b[26], %b[26], %r0, %b[19]
          stqp,2        %r10, %b[16], %b[19]
          qppermb,4,sm  %b[33], %b[33], %r0, %b[18]
          stqp,5        %r12, %b[16], %b[18]
        }
        {
          loop_mode
          qppermb,1,sm  %b[25], %b[25], %r0, %b[19]
          stqp,2        %r13, %b[16], %b[19]
          qppermb,4,sm  %b[32], %b[32], %r0, %b[18]
          stqp,5        %r14, %b[16], %b[18]
        }
        {
          loop_mode
          qppermb,1,sm  %b[31], %b[31], %r0, %b[24]
          stqp,2        %r15, %b[16], %b[19]
          qppermb,4,sm  %b[30], %b[30], %r0, %b[21]
          stqp,5        %r16, %b[16], %b[18]
          movaqp,0      area=15, ind=0, am=1, be=0, %b[19]
          movaqp,1      area=14, ind=0, am=1, be=0, %b[22]
          movaqp,2      area=15, ind=0, am=1, be=0, %b[18]
          movaqp,3      area=14, ind=0, am=1, be=0, %b[20]
        }
        {
          loop_mode
          qppermb,1,sm  %b[29], %b[29], %r0, %b[26]
          stqp,2        %r17, %b[16], %b[24]
          qppermb,4,sm  %b[17], %b[17], %r0, %b[25]
          stqp,5        %r18, %b[16], %b[21]
          movaqp,0      area=13, ind=0, am=1, be=0, %b[21]
          movaqp,1      area=12, ind=0, am=1, be=0, %b[24]
          movaqp,2      area=13, ind=0, am=1, be=0, %b[17]
          movaqp,3      area=12, ind=0, am=1, be=0, %b[23]
        }
        {
          loop_mode
          qppermb,1,sm  %b[28], %b[28], %r0, %b[26]
          stqp,2        %r19, %b[16], %b[26]
          qppermb,4,sm  %b[27], %b[27], %r0, %b[25]
          stqp,5        %r20, %b[16], %b[25]
          movaqp,0      area=11, ind=0, am=1, be=0, %b[1]
          movaqp,1      area=10, ind=0, am=1, be=0, %b[13]
          movaqp,2      area=11, ind=0, am=1, be=0, %b[0]
          movaqp,3      area=10, ind=0, am=1, be=0, %b[12]
        }
        {
          loop_mode
          qppermb,1,sm  %g17, %g17, %r0, %b[28]
          stqp,2        %r21, %b[16], %b[26]
          qppermb,4,sm  %g16, %g16, %r0, %b[27]
          stqp,5        %r22, %b[16], %b[25]
          movaqp,0      area=9, ind=0, am=1, be=0, %g17
          movaqp,1      area=8, ind=0, am=1, be=0, %b[26]
          movaqp,2      area=9, ind=0, am=1, be=0, %g16
          movaqp,3      area=8, ind=0, am=1, be=0, %b[25]
        }
        {
          loop_mode
          qppermb,1,sm  %b[15], %b[15], %r0, %b[31]
          stqp,2        %r23, %b[16], %b[28]
          qppermb,4,sm  %b[14], %b[14], %r0, %b[30]
          stqp,5        %r24, %b[16], %b[27]
          movaqp,0      area=7, ind=0, am=1, be=0, %b[27]
          movaqp,1      area=6, ind=0, am=1, be=0, %b[29]
          movaqp,2      area=7, ind=0, am=1, be=0, %b[15]
          movaqp,3      area=6, ind=0, am=1, be=0, %b[28]
        }
        {
          loop_mode
          qppermb,1,sm  %b[3], %b[3], %r0, %b[36]
          stqp,2        %r25, %b[16], %b[31]
          qppermb,4,sm  %b[2], %b[2], %r0, %b[33]
          stqp,5        %r26, %b[16], %b[30]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[32]
          movaqp,1      area=0, ind=0, am=1, be=0, %b[34]
          movaqp,2      area=5, ind=0, am=1, be=0, %b[30]
          movaqp,3      area=4, ind=0, am=1, be=0, %b[31]
        }
        {
          loop_mode
          qppermb,1,sm  %b[24], %b[24], %r0, %b[3]
          stqp,2        %r27, %b[16], %b[36]
          qppermb,4,sm  %b[23], %b[23], %r0, %b[2]
          stqp,5        %r28, %b[16], %b[33]
          movaqp,0      area=5, ind=0, am=1, be=0, %b[23]
          movaqp,1      area=4, ind=0, am=1, be=0, %b[24]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[33]
          movaqp,3      area=0, ind=0, am=1, be=0, %b[35]
        }
        {
          loop_mode
          addd,0,sm     %r5, 0x1, %r5
          qppermb,1,sm  %b[21], %b[21], %r0, %b[5]
          stqp,2        %r29, %b[16], %b[5]
          bitrevd,3,sm  %r5, %b[38]
          qppermb,4,sm  %b[17], %b[17], %r0, %b[4]
          stqp,5        %r30, %b[16], %b[4]
          movaqp,0      area=3, ind=0, am=1, be=0, %b[36]
          movaqp,1      area=2, ind=0, am=1, be=0, %b[37]
          movaqp,2      area=3, ind=0, am=1, be=0, %b[17]
          movaqp,3      area=2, ind=0, am=1, be=0, %b[21]
        }
        {
          loop_mode
          qppermb,1,sm  %b[22], %b[22], %r0, %b[7]
          stqp,2        %r31, %b[16], %b[7]
          shrd,3,sm     %b[38], %r1, %b[20]
          qppermb,4,sm  %b[20], %b[20], %r0, %b[6]
          stqp,5        %r32, %b[16], %b[6]
        }
        {
          loop_mode
          qppermb,1,sm  %b[19], %b[19], %r0, %b[9]
          stqp,2        %r33, %b[16], %b[9]
          shld,3,sm     %b[20], 0x4, %b[14]
          qppermb,4,sm  %b[18], %b[18], %r0, %b[8]
          stqp,5        %r34, %b[16], %b[8]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[34], %b[34], %r0, %b[18]
          stqp,2        %r35, %b[16], %b[11]
          qppermb,3,sm  %b[32], %b[32], %r0, %b[16]
          stqp,5        %r36, %b[16], %b[10]
        }

void reverse_radix2_vector4(int bit_count_in, myComplex *data_in, myComplex4 *data_out)
{
	int bit_count_out = bit_count_in - 2;

//	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;
	int64_t delta = (1LL << shift_out) / 32;

	__v2di *in = (__v2di*)data_in;

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0, shifted_i = 0; i < count_out; ++i, shifted_i += delta)
	{
		int64_t offset = __builtin_e2k_bitrevd(shifted_i);
		__v2di mask_real = {0x0B0A090803020100, 0x1B1A191813121110};
		__v2di mask_imag = {0x0F0E0D0C07060504, 0x1F1E1D1C17161514};
		*(__v2du*)((void*)data_out + offset + 0*16) = __builtin_e2k_qppermb(in[2*i+1], in[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 1*16) = __builtin_e2k_qppermb(in[2*i+1], in[2*i+0], mask_imag);
	}
}

.L6535:
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=5, abs=0, disp=0
        }
.L6346:
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          bitrevd,0,sm  %b[22], %b[13]
          qppermb,1,sm  %b[11], %b[10], %r5, %b[19]
          stqp,2        %r0, %b[17], %b[21]
          qppermb,3,sm  %b[11], %b[10], %r6, %b[23]
          addd,4,sm     %b[20], %r4, %b[18]
          stqp,5        %r2, %b[17], %b[25]
          movaqp,0      area=0, ind=0, am=1, be=0, %b[0]
          movaqp,1      area=0, ind=16, am=0, be=0, %b[1]
        }

void reverse_radix2_vector4_x2(int bit_count_in, myComplex *data_in, myComplex4 *data_out)
{
	int bit_count_out = bit_count_in - 2;

//	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in    = (__v2di*) data_in;
	__v2di *out_0 = (__v2di*)&data_out[0];
	__v2di *out_1 = (__v2di*)&data_out[count_out/2];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out; i += 2)
	{
		int64_t offset = 32 * (__builtin_e2k_bitrevd(i) >> shift_out);
		__v2di mask_real = {0x0B0A090803020100, 0x1B1A191813121110};
		__v2di mask_imag = {0x0F0E0D0C07060504, 0x1F1E1D1C17161514};
		*(__v2du*)((void*)out_0 + offset + 0*16) = __builtin_e2k_qppermb(in[2*(i+0)+1], in[2*(i+0)+0], mask_real);
		*(__v2du*)((void*)out_0 + offset + 1*16) = __builtin_e2k_qppermb(in[2*(i+0)+1], in[2*(i+0)+0], mask_imag);
		*(__v2du*)((void*)out_1 + offset + 0*16) = __builtin_e2k_qppermb(in[2*(i+1)+1], in[2*(i+1)+0], mask_real);
		*(__v2du*)((void*)out_1 + offset + 1*16) = __builtin_e2k_qppermb(in[2*(i+1)+1], in[2*(i+1)+0], mask_imag);
	}
}

.L6884:
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=5, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=5, abs=0, disp=32
        }
.L6561:
        {
          loop_mode
          bitrevd,0,sm  %b[4], %b[1]
          qppermb,1,sm  %b[25], %b[20], %r7, %b[28]
          stqp,2        %r0, %b[7], %b[26]
          shld,3,sm     %b[22], 0x5, %b[5]
          qppermb,4,sm  %b[17], %b[12], %r7, %b[27]
          stqp,5        %r4, %b[7], %b[24]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[23], %b[18], %r9, %b[24]
          addd,1,sm     %b[2], 0x2, %b[0]
          stqp,2        %r2, %b[7], %b[28]
          qppermb,3,sm  %b[15], %b[10], %r9, %b[22]
          shrd,4,sm     %b[3], %r6, %b[20]
          stqp,5        %r5, %b[7], %b[27]
          movaqp,0      area=0, ind=0, am=1, be=0, %b[12]
          movaqp,1      area=0, ind=16, am=0, be=0, %b[17]
          movaqp,2      area=0, ind=0, am=1, be=0, %b[4]
          movaqp,3      area=0, ind=16, am=0, be=0, %b[9]
        }

void reverse_radix2_vector4_stream2(int bit_count_in, myComplex *data_in, myComplex4 *data_out)
{
	int bit_count_out = bit_count_in - 2;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_0 = (__v2di*)&data_in[0];
	__v2di *in_1 = (__v2di*)&data_in[count_in/2];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/2; ++i)
	{
		int64_t offset = 32 * (__builtin_e2k_bitrevd(i) >> shift_out);
		__v2di mask_real = {0x0B0A090803020100, 0x1B1A191813121110};
		__v2di mask_imag = {0x0F0E0D0C07060504, 0x1F1E1D1C17161514};
		*(__v2du*)((void*)data_out + offset + 0*16) = __builtin_e2k_qppermb(in_0[2*i+1], in_0[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 1*16) = __builtin_e2k_qppermb(in_0[2*i+1], in_0[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 2*16) = __builtin_e2k_qppermb(in_1[2*i+1], in_1[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 3*16) = __builtin_e2k_qppermb(in_1[2*i+1], in_1[2*i+0], mask_imag);
	}
}

.L7199:
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=2, asz=5, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=5, abs=0, disp=0
        }
.L6909:
        {
          loop_mode
          bitrevd,0,sm  %b[4], %b[1]
          qppermb,1,sm  %b[25], %b[20], %r9, %b[28]
          stqp,2        %r0, %b[7], %b[26]
          shld,3,sm     %b[22], 0x5, %b[5]
          qppermb,4,sm  %b[17], %b[12], %r9, %b[27]
          stqp,5        %r5, %b[7], %b[24]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[23], %b[18], %r6, %b[24]
          addd,1,sm     %b[2], 0x1, %b[0]
          stqp,2        %r2, %b[7], %b[28]
          qppermb,3,sm  %b[15], %b[10], %r6, %b[22]
          shrd,4,sm     %b[3], %r7, %b[20]
          stqp,5        %r4, %b[7], %b[27]
          movaqp,0      area=0, ind=0, am=1, be=0, %b[12]
          movaqp,1      area=0, ind=16, am=0, be=0, %b[17]
          movaqp,2      area=0, ind=0, am=1, be=0, %b[4]
          movaqp,3      area=0, ind=16, am=0, be=0, %b[9]
        }

void reverse_radix2_vector4_stream4(int bit_count_in, myComplex *data_in, myComplex4 *data_out)
{
	int bit_count_out = bit_count_in - 2;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_00 = (__v2di*)&data_in[0 * count_in/4];
	__v2di *in_01 = (__v2di*)&data_in[1 * count_in/4];
	__v2di *in_10 = (__v2di*)&data_in[2 * count_in/4];
	__v2di *in_11 = (__v2di*)&data_in[3 * count_in/4];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/4; ++i)
	{
		int64_t offset = 32 * (__builtin_e2k_bitrevd(i) >> shift_out);
		__v2di mask_real = {0x0B0A090803020100, 0x1B1A191813121110};
		__v2di mask_imag = {0x0F0E0D0C07060504, 0x1F1E1D1C17161514};
		*(__v2du*)((void*)data_out + offset + 0*16) = __builtin_e2k_qppermb(in_00[2*i+1], in_00[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 1*16) = __builtin_e2k_qppermb(in_00[2*i+1], in_00[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 2*16) = __builtin_e2k_qppermb(in_10[2*i+1], in_10[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 3*16) = __builtin_e2k_qppermb(in_10[2*i+1], in_10[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 4*16) = __builtin_e2k_qppermb(in_01[2*i+1], in_01[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 5*16) = __builtin_e2k_qppermb(in_01[2*i+1], in_01[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 6*16) = __builtin_e2k_qppermb(in_11[2*i+1], in_11[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 7*16) = __builtin_e2k_qppermb(in_11[2*i+1], in_11[2*i+0], mask_imag);
	}
}

.L7728:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=4, asz=4, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=3, asz=4, abs=0, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=2, asz=4, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=4, abs=16, disp=0
        }
.L7242:
        {
          loop_mode
          qppermb,1,sm  %b[20], %b[16], %r13, %b[26]
          stqp,2        %r0, %b[21], %b[25]
          qppermb,4,sm  %b[12], %b[8], %r13, %b[24]
          stqp,5        %r5, %b[21], %b[22]
        }
        {
          loop_mode
          qppermb,1,sm  %b[17], %b[13], %r12, %b[25]
          stqp,2        %r2, %b[21], %b[26]
          shrd,3,sm     %b[19], %r11, %b[1]
          qppermb,4,sm  %b[9], %b[5], %r12, %b[22]
          stqp,5        %r4, %b[21], %b[24]
        }
        {
          loop_mode
          qppermb,1,sm  %b[17], %b[13], %r13, %b[27]
          stqp,2        %r7, %b[21], %b[25]
          shld,3,sm     %b[1], 0x5, %b[19]
          qppermb,4,sm  %b[9], %b[5], %r13, %b[24]
          stqp,5        %r10, %b[21], %b[22]
          movaqp,0      area=0, ind=0, am=1, be=0, %b[12]
          movaqp,1      area=0, ind=16, am=0, be=0, %b[16]
          movaqp,2      area=0, ind=0, am=1, be=0, %b[4]
          movaqp,3      area=0, ind=16, am=0, be=0, %b[8]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[18], %b[14], %r12, %b[23]
          addd,1,sm     %b[2], 0x1, %b[0]
          stqp,2        %r6, %b[21], %b[27]
          qppermb,3,sm  %b[10], %b[6], %r12, %b[20]
          bitrevd,4,sm  %b[2], %b[17]
          stqp,5        %r9, %b[21], %b[24]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[9]
          movaqp,1      area=1, ind=16, am=0, be=0, %b[13]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[1]
          movaqp,3      area=1, ind=16, am=0, be=0, %b[5]
        }

void reverse_radix2_vector4_stream8(int bit_count_in, myComplex *data_in, myComplex4 *data_out)
{
	int bit_count_out = bit_count_in - 2;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_000 = (__v2di*)&data_in[0 * count_in/8];
	__v2di *in_001 = (__v2di*)&data_in[1 * count_in/8];
	__v2di *in_010 = (__v2di*)&data_in[2 * count_in/8];
	__v2di *in_011 = (__v2di*)&data_in[3 * count_in/8];
	__v2di *in_100 = (__v2di*)&data_in[4 * count_in/8];
	__v2di *in_101 = (__v2di*)&data_in[5 * count_in/8];
	__v2di *in_110 = (__v2di*)&data_in[6 * count_in/8];
	__v2di *in_111 = (__v2di*)&data_in[7 * count_in/8];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/8; ++i)
	{
		int64_t offset = 32 * (__builtin_e2k_bitrevd(i) >> shift_out);
		__v2di mask_real = {0x0B0A090803020100, 0x1B1A191813121110};
		__v2di mask_imag = {0x0F0E0D0C07060504, 0x1F1E1D1C17161514};
		*(__v2du*)((void*)data_out + offset +  0*16) = __builtin_e2k_qppermb(in_000[2*i+1], in_000[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  1*16) = __builtin_e2k_qppermb(in_000[2*i+1], in_000[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset +  2*16) = __builtin_e2k_qppermb(in_100[2*i+1], in_100[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  3*16) = __builtin_e2k_qppermb(in_100[2*i+1], in_100[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset +  4*16) = __builtin_e2k_qppermb(in_010[2*i+1], in_010[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  5*16) = __builtin_e2k_qppermb(in_010[2*i+1], in_010[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset +  6*16) = __builtin_e2k_qppermb(in_110[2*i+1], in_110[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  7*16) = __builtin_e2k_qppermb(in_110[2*i+1], in_110[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset +  8*16) = __builtin_e2k_qppermb(in_001[2*i+1], in_001[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  9*16) = __builtin_e2k_qppermb(in_001[2*i+1], in_001[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 10*16) = __builtin_e2k_qppermb(in_101[2*i+1], in_101[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 11*16) = __builtin_e2k_qppermb(in_101[2*i+1], in_101[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 12*16) = __builtin_e2k_qppermb(in_011[2*i+1], in_011[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 13*16) = __builtin_e2k_qppermb(in_011[2*i+1], in_011[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 14*16) = __builtin_e2k_qppermb(in_111[2*i+1], in_111[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 15*16) = __builtin_e2k_qppermb(in_111[2*i+1], in_111[2*i+0], mask_imag);
	}
}

.L8681:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=8, asz=3, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=7, asz=3, abs=0, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=6, asz=3, abs=8, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=5, asz=3, abs=8, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=4, asz=3, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=3, asz=3, abs=16, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=2, asz=3, abs=24, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=3, abs=24, disp=0
        }
.L7803:
        {
          loop_mode
          qppermb,1,sm  %b[16], %b[15], %r20, %b[28]
          stqp,2        %r0, %b[9], %b[5]
          qppermb,4,sm  %b[14], %b[13], %r20, %b[27]
          stqp,5        %r6, %b[9], %b[4]
        }
        {
          loop_mode
          qppermb,1,sm  %b[26], %b[25], %r21, %b[30]
          stqp,2        %r2, %b[9], %b[28]
          qppermb,4,sm  %b[24], %b[23], %r21, %b[29]
          stqp,5        %r5, %b[9], %b[27]
          movaqp,0      area=3, ind=0, am=1, be=0, %b[5]
          movaqp,1      area=3, ind=16, am=0, be=0, %b[8]
          movaqp,2      area=3, ind=0, am=1, be=0, %b[1]
          movaqp,3      area=3, ind=16, am=0, be=0, %b[4]
        }
        {
          loop_mode
          qppermb,1,sm  %b[26], %b[25], %r20, %b[28]
          stqp,2        %r9, %b[9], %b[30]
          qppermb,4,sm  %b[24], %b[23], %r20, %b[27]
          stqp,5        %r11, %b[9], %b[29]
          movaqp,0      area=0, ind=0, am=1, be=0, %b[13]
          movaqp,1      area=0, ind=16, am=0, be=0, %b[14]
          movaqp,2      area=0, ind=0, am=1, be=0, %b[11]
          movaqp,3      area=0, ind=16, am=0, be=0, %b[12]
        }
        {
          loop_mode
          qppermb,1,sm  %b[22], %b[21], %r20, %b[29]
          stqp,2        %r7, %b[9], %b[28]
          qppermb,4,sm  %b[22], %b[21], %r21, %b[26]
          stqp,5        %r10, %b[9], %b[27]
          movaqp,0      area=2, ind=0, am=1, be=0, %b[19]
          movaqp,1      area=2, ind=16, am=0, be=0, %b[20]
          movaqp,2      area=2, ind=0, am=1, be=0, %b[15]
          movaqp,3      area=2, ind=16, am=0, be=0, %b[16]
        }
        {
          loop_mode
          addd,0,sm     %b[2], 0x1, %b[0]
          qppermb,1,sm  %b[18], %b[17], %r20, %b[28]
          stqp,2        %r12, %b[9], %b[29]
          bitrevd,3,sm  %b[2], %b[25]
          qppermb,4,sm  %b[18], %b[17], %r21, %b[27]
          stqp,5        %r13, %b[9], %b[26]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[23]
          movaqp,1      area=1, ind=16, am=0, be=0, %b[24]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[21]
          movaqp,3      area=1, ind=16, am=0, be=0, %b[22]
        }
        {
          loop_mode
          qppermb,1,sm  %b[10], %b[7], %r20, %b[29]
          stqp,2        %r14, %b[9], %b[28]
          shrd,3,sm     %b[25], %r22, %b[2]
          qppermb,4,sm  %b[10], %b[7], %r21, %b[26]
          stqp,5        %r15, %b[9], %b[27]
        }
        {
          loop_mode
          qppermb,1,sm  %b[6], %b[3], %r20, %b[27]
          stqp,2        %r16, %b[9], %b[29]
          shld,3,sm     %b[2], 0x5, %b[7]
          qppermb,4,sm  %b[6], %b[3], %r21, %b[25]
          stqp,5        %r17, %b[9], %b[26]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[14], %b[13], %r21, %b[3]
          stqp,2        %r18, %b[9], %b[27]
          qppermb,3,sm  %b[12], %b[11], %r21, %b[2]
          stqp,5        %r19, %b[9], %b[25]
        }

void reverse_radix2_vector4_stream16(int bit_count_in, myComplex *data_in, myComplex4 *data_out)
{
	int bit_count_out = bit_count_in - 2;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_0000 = (__v2di*)&data_in[ 0 * count_in/16];
	__v2di *in_0001 = (__v2di*)&data_in[ 1 * count_in/16];
	__v2di *in_0010 = (__v2di*)&data_in[ 2 * count_in/16];
	__v2di *in_0011 = (__v2di*)&data_in[ 3 * count_in/16];
	__v2di *in_0100 = (__v2di*)&data_in[ 4 * count_in/16];
	__v2di *in_0101 = (__v2di*)&data_in[ 5 * count_in/16];
	__v2di *in_0110 = (__v2di*)&data_in[ 6 * count_in/16];
	__v2di *in_0111 = (__v2di*)&data_in[ 7 * count_in/16];
	__v2di *in_1000 = (__v2di*)&data_in[ 8 * count_in/16];
	__v2di *in_1001 = (__v2di*)&data_in[ 9 * count_in/16];
	__v2di *in_1010 = (__v2di*)&data_in[10 * count_in/16];
	__v2di *in_1011 = (__v2di*)&data_in[11 * count_in/16];
	__v2di *in_1100 = (__v2di*)&data_in[12 * count_in/16];
	__v2di *in_1101 = (__v2di*)&data_in[13 * count_in/16];
	__v2di *in_1110 = (__v2di*)&data_in[14 * count_in/16];
	__v2di *in_1111 = (__v2di*)&data_in[15 * count_in/16];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/16; ++i)
	{
		int64_t offset = 32 * (__builtin_e2k_bitrevd(i) >> shift_out);
		__v2di mask_real = {0x0B0A090803020100, 0x1B1A191813121110};
		__v2di mask_imag = {0x0F0E0D0C07060504, 0x1F1E1D1C17161514};
		*(__v2du*)((void*)data_out + offset +  0*16) = __builtin_e2k_qppermb(in_0000[2*i+1], in_0000[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  1*16) = __builtin_e2k_qppermb(in_0000[2*i+1], in_0000[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset +  2*16) = __builtin_e2k_qppermb(in_1000[2*i+1], in_1000[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  3*16) = __builtin_e2k_qppermb(in_1000[2*i+1], in_1000[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset +  4*16) = __builtin_e2k_qppermb(in_0100[2*i+1], in_0100[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  5*16) = __builtin_e2k_qppermb(in_0100[2*i+1], in_0100[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset +  6*16) = __builtin_e2k_qppermb(in_1100[2*i+1], in_1100[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  7*16) = __builtin_e2k_qppermb(in_1100[2*i+1], in_1100[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset +  8*16) = __builtin_e2k_qppermb(in_0010[2*i+1], in_0010[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  9*16) = __builtin_e2k_qppermb(in_0010[2*i+1], in_0010[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 10*16) = __builtin_e2k_qppermb(in_1010[2*i+1], in_1010[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 11*16) = __builtin_e2k_qppermb(in_1010[2*i+1], in_1010[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 12*16) = __builtin_e2k_qppermb(in_0110[2*i+1], in_0110[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 13*16) = __builtin_e2k_qppermb(in_0110[2*i+1], in_0110[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 14*16) = __builtin_e2k_qppermb(in_1110[2*i+1], in_1110[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 15*16) = __builtin_e2k_qppermb(in_1110[2*i+1], in_1110[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 16*16) = __builtin_e2k_qppermb(in_0001[2*i+1], in_0001[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 17*16) = __builtin_e2k_qppermb(in_0001[2*i+1], in_0001[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 18*16) = __builtin_e2k_qppermb(in_1001[2*i+1], in_1001[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 19*16) = __builtin_e2k_qppermb(in_1001[2*i+1], in_1001[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 20*16) = __builtin_e2k_qppermb(in_0101[2*i+1], in_0101[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 21*16) = __builtin_e2k_qppermb(in_0101[2*i+1], in_0101[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 22*16) = __builtin_e2k_qppermb(in_1101[2*i+1], in_1101[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 23*16) = __builtin_e2k_qppermb(in_1101[2*i+1], in_1101[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 24*16) = __builtin_e2k_qppermb(in_0011[2*i+1], in_0011[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 25*16) = __builtin_e2k_qppermb(in_0011[2*i+1], in_0011[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 26*16) = __builtin_e2k_qppermb(in_1011[2*i+1], in_1011[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 27*16) = __builtin_e2k_qppermb(in_1011[2*i+1], in_1011[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 28*16) = __builtin_e2k_qppermb(in_0111[2*i+1], in_0111[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 29*16) = __builtin_e2k_qppermb(in_0111[2*i+1], in_0111[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 30*16) = __builtin_e2k_qppermb(in_1111[2*i+1], in_1111[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 31*16) = __builtin_e2k_qppermb(in_1111[2*i+1], in_1111[2*i+0], mask_imag);
	}
}

.L10479:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=1, incr=1, ind=0, asz=2, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=15, asz=2, abs=0, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=14, asz=2, abs=4, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=13, asz=2, abs=4, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=12, asz=2, abs=8, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=11, asz=2, abs=8, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=10, asz=2, abs=12, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=9, asz=2, abs=12, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=8, asz=2, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=7, asz=2, abs=16, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=6, asz=2, abs=20, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=5, asz=2, abs=20, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=4, asz=2, abs=24, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=3, asz=2, abs=24, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=2, asz=2, abs=28, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=2, abs=28, disp=0
        }
.L8820:
        {
          loop_mode
          qppermb,1,sm  %b[34], %b[33], %r36, %b[32]
          stqp,2        %r0, %b[4], %b[44]
          qppermb,4,sm  %b[32], %b[31], %r36, %b[31]
          stqp,5        %r6, %b[4], %b[43]
        }
        {
          loop_mode
          qppermb,1,sm  %b[42], %b[41], %r37, %b[32]
          stqp,2        %r2, %b[4], %b[32]
          qppermb,4,sm  %b[40], %b[39], %r37, %b[31]
          stqp,5        %r1, %b[4], %b[31]
        }
        {
          loop_mode
          qppermb,1,sm  %b[42], %b[41], %r36, %b[32]
          stqp,2        %r9, %b[4], %b[32]
          qppermb,4,sm  %b[40], %b[39], %r36, %b[31]
          stqp,5        %r11, %b[4], %b[31]
        }
        {
          loop_mode
          qppermb,1,sm  %b[38], %b[37], %r36, %b[32]
          stqp,2        %r7, %b[4], %b[32]
          qppermb,4,sm  %b[38], %b[37], %r37, %b[31]
          stqp,5        %r10, %b[4], %b[31]
        }
        {
          loop_mode
          qppermb,1,sm  %b[36], %b[35], %r36, %b[32]
          stqp,2        %r12, %b[4], %b[32]
          qppermb,4,sm  %b[36], %b[35], %r37, %b[31]
          stqp,5        %r13, %b[4], %b[31]
        }
        {
          loop_mode
          qppermb,1,sm  %b[30], %b[29], %r36, %b[30]
          stqp,2        %r14, %b[4], %b[32]
          qppermb,4,sm  %b[30], %b[29], %r37, %b[29]
          stqp,5        %r15, %b[4], %b[31]
          movaqp,0      area=7, ind=0, am=1, be=0, %b[5]
          movaqp,1      area=7, ind=16, am=0, be=0, %b[6]
          movaqp,2      area=7, ind=0, am=1, be=0, %b[0]
          movaqp,3      area=7, ind=16, am=0, be=0, %b[1]
        }
        {
          loop_mode
          qppermb,1,sm  %b[26], %b[25], %r36, %b[26]
          stqp,2        %r16, %b[4], %b[30]
          qppermb,4,sm  %b[26], %b[25], %r37, %b[25]
          stqp,5        %r17, %b[4], %b[29]
          movaqp,0      area=6, ind=0, am=1, be=0, %b[13]
          movaqp,1      area=6, ind=16, am=0, be=0, %b[14]
          movaqp,2      area=6, ind=0, am=1, be=0, %b[9]
          movaqp,3      area=6, ind=16, am=0, be=0, %b[10]
        }
        {
          loop_mode
          qppermb,1,sm  %b[28], %b[27], %r36, %b[26]
          stqp,2        %r18, %b[4], %b[26]
          qppermb,4,sm  %b[28], %b[27], %r37, %b[25]
          stqp,5        %r19, %b[4], %b[25]
          movaqp,0      area=5, ind=0, am=1, be=0, %b[21]
          movaqp,1      area=5, ind=16, am=0, be=0, %b[22]
          movaqp,2      area=5, ind=0, am=1, be=0, %b[17]
          movaqp,3      area=5, ind=16, am=0, be=0, %b[18]
        }
        {
          loop_mode
          qppermb,1,sm  %g16, %g17, %r36, %b[28]
          stqp,2        %r20, %b[4], %b[26]
          qppermb,4,sm  %g16, %g17, %r37, %b[27]
          stqp,5        %r21, %b[4], %b[25]
          movaqp,0      area=4, ind=0, am=1, be=0, %b[25]
          movaqp,1      area=4, ind=16, am=0, be=0, %b[26]
          movaqp,2      area=4, ind=0, am=1, be=0, %g17
          movaqp,3      area=4, ind=16, am=0, be=0, %g16
        }
        {
          loop_mode
          qppermb,1,sm  %b[24], %b[23], %r36, %b[30]
          stqp,2        %r22, %b[4], %b[28]
          qppermb,4,sm  %b[24], %b[23], %r37, %b[29]
          stqp,5        %r23, %b[4], %b[27]
          movaqp,0      area=3, ind=0, am=1, be=0, %b[27]
          movaqp,1      area=3, ind=16, am=0, be=0, %b[28]
          movaqp,2      area=3, ind=0, am=1, be=0, %b[23]
          movaqp,3      area=3, ind=16, am=0, be=0, %b[24]
        }
        {
          loop_mode
          qppermb,1,sm  %b[20], %b[19], %r36, %b[34]
          stqp,2        %r24, %b[4], %b[30]
          qppermb,4,sm  %b[20], %b[19], %r37, %b[33]
          stqp,5        %r25, %b[4], %b[29]
          movaqp,0      area=0, ind=0, am=1, be=0, %b[31]
          movaqp,1      area=0, ind=16, am=0, be=0, %b[32]
          movaqp,2      area=0, ind=0, am=1, be=0, %b[29]
          movaqp,3      area=0, ind=16, am=0, be=0, %b[30]
        }
        {
          loop_mode
          qppermb,1,sm  %b[16], %b[15], %r36, %b[38]
          stqp,2        %r26, %b[4], %b[34]
          qppermb,4,sm  %b[16], %b[15], %r37, %b[37]
          stqp,5        %r27, %b[4], %b[33]
          movaqp,0      area=2, ind=0, am=1, be=0, %b[35]
          movaqp,1      area=2, ind=16, am=0, be=0, %b[36]
          movaqp,2      area=2, ind=0, am=1, be=0, %b[33]
          movaqp,3      area=2, ind=16, am=0, be=0, %b[34]
        }
        {
          loop_mode
          addd,0,sm     %r5, 0x1, %r5
          qppermb,1,sm  %b[12], %b[11], %r36, %b[43]
          stqp,2        %r28, %b[4], %b[38]
          bitrevd,3,sm  %r5, %b[41]
          qppermb,4,sm  %b[12], %b[11], %r37, %b[42]
          stqp,5        %r29, %b[4], %b[37]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[39]
          movaqp,1      area=1, ind=16, am=0, be=0, %b[40]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[37]
          movaqp,3      area=1, ind=16, am=0, be=0, %b[38]
        }
        {
          loop_mode
          qppermb,1,sm  %b[8], %b[7], %r36, %b[43]
          stqp,2        %r30, %b[4], %b[43]
          shrd,3,sm     %b[41], %r38, %b[41]
          qppermb,4,sm  %b[8], %b[7], %r37, %b[42]
          stqp,5        %r31, %b[4], %b[42]
        }
        {
          loop_mode
          qppermb,1,sm  %b[3], %b[2], %r36, %b[42]
          stqp,2        %r32, %b[4], %b[43]
          shld,3,sm     %b[41], 0x5, %b[2]
          qppermb,4,sm  %b[3], %b[2], %r37, %b[41]
          stqp,5        %r33, %b[4], %b[42]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[32], %b[31], %r37, %b[42]
          stqp,2        %r34, %b[4], %b[42]
          qppermb,3,sm  %b[30], %b[29], %r37, %b[41]
          stqp,5        %r35, %b[4], %b[41]
        }

void reverse_radix2_vector4_stream32(int bit_count_in, myComplex *data_in, myComplex4 *data_out)
{
	int bit_count_out = bit_count_in - 2;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_00000 = (__v2di*)&data_in[ 0 * count_in/32];
	__v2di *in_00001 = (__v2di*)&data_in[ 1 * count_in/32];
	__v2di *in_00010 = (__v2di*)&data_in[ 2 * count_in/32];
	__v2di *in_00011 = (__v2di*)&data_in[ 3 * count_in/32];
	__v2di *in_00100 = (__v2di*)&data_in[ 4 * count_in/32];
	__v2di *in_00101 = (__v2di*)&data_in[ 5 * count_in/32];
	__v2di *in_00110 = (__v2di*)&data_in[ 6 * count_in/32];
	__v2di *in_00111 = (__v2di*)&data_in[ 7 * count_in/32];
	__v2di *in_01000 = (__v2di*)&data_in[ 8 * count_in/32];
	__v2di *in_01001 = (__v2di*)&data_in[ 9 * count_in/32];
	__v2di *in_01010 = (__v2di*)&data_in[10 * count_in/32];
	__v2di *in_01011 = (__v2di*)&data_in[11 * count_in/32];
	__v2di *in_01100 = (__v2di*)&data_in[12 * count_in/32];
	__v2di *in_01101 = (__v2di*)&data_in[13 * count_in/32];
	__v2di *in_01110 = (__v2di*)&data_in[14 * count_in/32];
	__v2di *in_01111 = (__v2di*)&data_in[15 * count_in/32];
	__v2di *in_10000 = (__v2di*)&data_in[16 * count_in/32];
	__v2di *in_10001 = (__v2di*)&data_in[17 * count_in/32];
	__v2di *in_10010 = (__v2di*)&data_in[18 * count_in/32];
	__v2di *in_10011 = (__v2di*)&data_in[19 * count_in/32];
	__v2di *in_10100 = (__v2di*)&data_in[20 * count_in/32];
	__v2di *in_10101 = (__v2di*)&data_in[21 * count_in/32];
	__v2di *in_10110 = (__v2di*)&data_in[22 * count_in/32];
	__v2di *in_10111 = (__v2di*)&data_in[23 * count_in/32];
	__v2di *in_11000 = (__v2di*)&data_in[24 * count_in/32];
	__v2di *in_11001 = (__v2di*)&data_in[25 * count_in/32];
	__v2di *in_11010 = (__v2di*)&data_in[26 * count_in/32];
	__v2di *in_11011 = (__v2di*)&data_in[27 * count_in/32];
	__v2di *in_11100 = (__v2di*)&data_in[28 * count_in/32];
	__v2di *in_11101 = (__v2di*)&data_in[29 * count_in/32];
	__v2di *in_11110 = (__v2di*)&data_in[30 * count_in/32];
	__v2di *in_11111 = (__v2di*)&data_in[31 * count_in/32];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/32; ++i)
	{
		int64_t offset = 32 * (__builtin_e2k_bitrevd(i) >> shift_out);
		__v2di mask_real = {0x0B0A090803020100, 0x1B1A191813121110};
		__v2di mask_imag = {0x0F0E0D0C07060504, 0x1F1E1D1C17161514};
		*(__v2du*)((void*)data_out + offset +  0*16) = __builtin_e2k_qppermb(in_00000[2*i+1], in_00000[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  1*16) = __builtin_e2k_qppermb(in_00000[2*i+1], in_00000[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset +  2*16) = __builtin_e2k_qppermb(in_10000[2*i+1], in_10000[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  3*16) = __builtin_e2k_qppermb(in_10000[2*i+1], in_10000[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset +  4*16) = __builtin_e2k_qppermb(in_01000[2*i+1], in_01000[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  5*16) = __builtin_e2k_qppermb(in_01000[2*i+1], in_01000[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset +  6*16) = __builtin_e2k_qppermb(in_11000[2*i+1], in_11000[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  7*16) = __builtin_e2k_qppermb(in_11000[2*i+1], in_11000[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset +  8*16) = __builtin_e2k_qppermb(in_00100[2*i+1], in_00100[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset +  9*16) = __builtin_e2k_qppermb(in_00100[2*i+1], in_00100[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 10*16) = __builtin_e2k_qppermb(in_10100[2*i+1], in_10100[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 11*16) = __builtin_e2k_qppermb(in_10100[2*i+1], in_10100[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 12*16) = __builtin_e2k_qppermb(in_01100[2*i+1], in_01100[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 13*16) = __builtin_e2k_qppermb(in_01100[2*i+1], in_01100[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 14*16) = __builtin_e2k_qppermb(in_11100[2*i+1], in_11100[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 15*16) = __builtin_e2k_qppermb(in_11100[2*i+1], in_11100[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 16*16) = __builtin_e2k_qppermb(in_00010[2*i+1], in_00010[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 17*16) = __builtin_e2k_qppermb(in_00010[2*i+1], in_00010[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 18*16) = __builtin_e2k_qppermb(in_10010[2*i+1], in_10010[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 19*16) = __builtin_e2k_qppermb(in_10010[2*i+1], in_10010[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 20*16) = __builtin_e2k_qppermb(in_01010[2*i+1], in_01010[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 21*16) = __builtin_e2k_qppermb(in_01010[2*i+1], in_01010[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 22*16) = __builtin_e2k_qppermb(in_11010[2*i+1], in_11010[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 23*16) = __builtin_e2k_qppermb(in_11010[2*i+1], in_11010[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 24*16) = __builtin_e2k_qppermb(in_00110[2*i+1], in_00110[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 25*16) = __builtin_e2k_qppermb(in_00110[2*i+1], in_00110[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 26*16) = __builtin_e2k_qppermb(in_10110[2*i+1], in_10110[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 27*16) = __builtin_e2k_qppermb(in_10110[2*i+1], in_10110[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 28*16) = __builtin_e2k_qppermb(in_01110[2*i+1], in_01110[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 29*16) = __builtin_e2k_qppermb(in_01110[2*i+1], in_01110[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 30*16) = __builtin_e2k_qppermb(in_11110[2*i+1], in_11110[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 31*16) = __builtin_e2k_qppermb(in_11110[2*i+1], in_11110[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 32*16) = __builtin_e2k_qppermb(in_00001[2*i+1], in_00001[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 33*16) = __builtin_e2k_qppermb(in_00001[2*i+1], in_00001[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 34*16) = __builtin_e2k_qppermb(in_10001[2*i+1], in_10001[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 35*16) = __builtin_e2k_qppermb(in_10001[2*i+1], in_10001[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 36*16) = __builtin_e2k_qppermb(in_01001[2*i+1], in_01001[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 37*16) = __builtin_e2k_qppermb(in_01001[2*i+1], in_01001[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 38*16) = __builtin_e2k_qppermb(in_11001[2*i+1], in_11001[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 39*16) = __builtin_e2k_qppermb(in_11001[2*i+1], in_11001[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 40*16) = __builtin_e2k_qppermb(in_00101[2*i+1], in_00101[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 41*16) = __builtin_e2k_qppermb(in_00101[2*i+1], in_00101[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 42*16) = __builtin_e2k_qppermb(in_10101[2*i+1], in_10101[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 43*16) = __builtin_e2k_qppermb(in_10101[2*i+1], in_10101[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 44*16) = __builtin_e2k_qppermb(in_01101[2*i+1], in_01101[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 45*16) = __builtin_e2k_qppermb(in_01101[2*i+1], in_01101[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 46*16) = __builtin_e2k_qppermb(in_11101[2*i+1], in_11101[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 47*16) = __builtin_e2k_qppermb(in_11101[2*i+1], in_11101[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 48*16) = __builtin_e2k_qppermb(in_00011[2*i+1], in_00011[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 49*16) = __builtin_e2k_qppermb(in_00011[2*i+1], in_00011[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 50*16) = __builtin_e2k_qppermb(in_10011[2*i+1], in_10011[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 51*16) = __builtin_e2k_qppermb(in_10011[2*i+1], in_10011[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 52*16) = __builtin_e2k_qppermb(in_01011[2*i+1], in_01011[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 53*16) = __builtin_e2k_qppermb(in_01011[2*i+1], in_01011[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 54*16) = __builtin_e2k_qppermb(in_11011[2*i+1], in_11011[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 55*16) = __builtin_e2k_qppermb(in_11011[2*i+1], in_11011[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 56*16) = __builtin_e2k_qppermb(in_00111[2*i+1], in_00111[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 57*16) = __builtin_e2k_qppermb(in_00111[2*i+1], in_00111[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 58*16) = __builtin_e2k_qppermb(in_10111[2*i+1], in_10111[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 59*16) = __builtin_e2k_qppermb(in_10111[2*i+1], in_10111[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 60*16) = __builtin_e2k_qppermb(in_01111[2*i+1], in_01111[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 61*16) = __builtin_e2k_qppermb(in_01111[2*i+1], in_01111[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 62*16) = __builtin_e2k_qppermb(in_11111[2*i+1], in_11111[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 63*16) = __builtin_e2k_qppermb(in_11111[2*i+1], in_11111[2*i+0], mask_imag);
	}
}

.L13622:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=17, incr=1, ind=0, asz=1, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=16, incr=1, ind=0, asz=1, abs=0, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=15, incr=1, ind=0, asz=1, abs=2, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=14, incr=1, ind=0, asz=1, abs=2, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=13, incr=1, ind=0, asz=1, abs=4, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=12, incr=1, ind=0, asz=1, abs=4, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=11, incr=1, ind=0, asz=1, abs=6, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=10, incr=1, ind=0, asz=1, abs=6, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=9, incr=1, ind=0, asz=1, abs=8, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=8, incr=1, ind=0, asz=1, abs=8, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=7, incr=1, ind=0, asz=1, abs=10, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=6, incr=1, ind=0, asz=1, abs=10, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=5, incr=1, ind=0, asz=1, abs=12, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=4, incr=1, ind=0, asz=1, abs=12, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=3, incr=1, ind=0, asz=1, abs=14, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=2, incr=1, ind=0, asz=1, abs=14, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=1, incr=1, ind=0, asz=1, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=15, asz=1, abs=16, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=14, asz=1, abs=18, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=13, asz=1, abs=18, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=12, asz=1, abs=20, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=11, asz=1, abs=20, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=10, asz=1, abs=22, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=9, asz=1, abs=22, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=8, asz=1, abs=24, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=7, asz=1, abs=24, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=6, asz=1, abs=26, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=5, asz=1, abs=26, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=4, asz=1, abs=28, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=3, asz=1, abs=28, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=2, asz=1, abs=30, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=1, abs=30, disp=0
        }
.L13394:
        {
          loop_mode
          disp  %ctpr1, .L13394
          bitrevd,0     %r1, %g20
          addd,1        %r1, 0x1, %r1
          movaqp,0      area=0, ind=16, am=1, be=0, %g17
          movaqp,1      area=0, ind=0, am=0, be=0, %g16
          movaqp,2      area=0, ind=16, am=1, be=0, %g19
          movaqp,3      area=0, ind=0, am=0, be=0, %g18
        }
        {
          loop_mode
          disp  %ctpr3, .L12302
          shrd,0        %g20, %r6, %g20
          movaqp,0      area=1, ind=16, am=1, be=0, %g22
          movaqp,1      area=1, ind=0, am=0, be=0, %g21
          movaqp,2      area=1, ind=16, am=1, be=0, %g24
          movaqp,3      area=1, ind=0, am=0, be=0, %g23
        }
        {
          loop_mode
          shld,0        %g20, 0x5, %g20
          movaqp,0      area=2, ind=16, am=1, be=0, %g26
          movaqp,1      area=2, ind=0, am=0, be=0, %g25
          movaqp,2      area=2, ind=16, am=1, be=0, %g28
          movaqp,3      area=2, ind=0, am=0, be=0, %g27
        }
        {
          loop_mode
          addd,0        %r2, %g20, %r7
          movaqp,0      area=3, ind=16, am=1, be=0, %g30
          movaqp,1      area=3, ind=0, am=0, be=0, %g29
          movaqp,2      area=3, ind=16, am=1, be=0, %r4
          movaqp,3      area=3, ind=0, am=0, be=0, %g31
        }
        {
          loop_mode
          movaqp,0      area=4, ind=16, am=1, be=0, %r10
          movaqp,1      area=4, ind=0, am=0, be=0, %r9
          movaqp,2      area=4, ind=16, am=1, be=0, %r12
          movaqp,3      area=4, ind=0, am=0, be=0, %r11
        }
        {
          loop_mode
          qppermb,0     %g17, %g16, %r0, %r17
          qppermb,1     %g17, %g16, %r5, %g16
          qppermb,3     %g19, %g18, %r0, %g17
          qppermb,4     %g19, %g18, %r5, %g18
          movaqp,0      area=5, ind=16, am=1, be=0, %r14
          movaqp,1      area=5, ind=0, am=0, be=0, %r13
          movaqp,2      area=5, ind=16, am=1, be=0, %r16
          movaqp,3      area=5, ind=0, am=0, be=0, %r15
        }
        {
          loop_mode
          qppermb,0     %g22, %g21, %r0, %r21
          qppermb,1     %g22, %g21, %r5, %g21
          stqp,2        0x10, %r7, %g16
          qppermb,3     %g24, %g23, %r0, %g22
          qppermb,4     %g24, %g23, %r5, %g23
          stqp,5        %r7, _f16s,_lts0lo 0x30, %g18
          movaqp,0      area=6, ind=16, am=1, be=0, %r18
          movaqp,1      area=6, ind=0, am=0, be=0, %g19
          movaqp,2      area=6, ind=16, am=1, be=0, %r20
          movaqp,3      area=6, ind=0, am=0, be=0, %r19
        }
        {
          loop_mode
          qppermb,0     %g26, %g25, %r0, %g17
          qppermb,1     %g26, %g25, %r5, %g20
          stqp,2        %r2, %g20, %r17
          qppermb,3     %g28, %g27, %r0, %g25
          qppermb,4     %g28, %g27, %r5, %g26
          stqp,5        %r7, _f16s,_lts0lo 0x20, %g17
          movaqp,0      area=7, ind=16, am=1, be=0, %g18
          movaqp,1      area=7, ind=0, am=0, be=0, %g16
          movaqp,2      area=7, ind=16, am=1, be=0, %r22
          movaqp,3      area=7, ind=0, am=0, be=0, %g24
        }
        {
          loop_mode
          qppermb,0     %g30, %g29, %r0, %r24
          qppermb,1     %g30, %g29, %r5, %g29
          stqp,2        %r7, _f16s,_lts0lo 0x50, %g21
          qppermb,3     %r4, %g31, %r0, %g21
          qppermb,4     %r4, %g31, %r5, %g23
          stqp,5        %r7, _f16s,_lts0hi 0x70, %g23
          movaqp,0      area=8, ind=16, am=1, be=0, %g28
          movaqp,1      area=8, ind=0, am=0, be=0, %g27
          movaqp,2      area=8, ind=16, am=1, be=0, %r23
          movaqp,3      area=8, ind=0, am=0, be=0, %r17
        }
        {
          loop_mode
          qppermb,0     %r10, %r9, %r0, %g22
          qppermb,1     %r10, %r9, %r5, %r9
          stqp,2        %r7, _f16s,_lts0lo 0x40, %r21
          qppermb,3     %r12, %r11, %r0, %r10
          qppermb,4     %r12, %r11, %r5, %r11
          stqp,5        %r7, _f16s,_lts0hi 0x60, %g22
          movaqp,0      area=9, ind=16, am=1, be=0, %g31
          movaqp,1      area=9, ind=0, am=0, be=0, %g30
          movaqp,2      area=9, ind=16, am=1, be=0, %r25
          movaqp,3      area=9, ind=0, am=0, be=0, %r4
        }
        {
          loop_mode
          qppermb,0     %r14, %r13, %r0, %g17
          qppermb,1     %r14, %r13, %r5, %g20
          stqp,2        %r7, _f16s,_lts0lo 0x80, %g17
          qppermb,3     %r16, %r15, %r0, %r13
          qppermb,4     %r16, %r15, %r5, %r14
          stqp,5        %r7, _f16s,_lts0hi 0x90, %g20
          movaqp,0      area=10, ind=16, am=1, be=0, %r21
          movaqp,1      area=10, ind=0, am=0, be=0, %r12
          movaqp,2      area=10, ind=16, am=1, be=0, %r27
          movaqp,3      area=10, ind=0, am=0, be=0, %r26
        }
        {
          loop_mode
          qppermb,0     %r18, %g19, %r0, %r28
          qppermb,1     %r18, %g19, %r5, %g19
          stqp,2        %r7, _f16s,_lts0lo 0xa0, %g25
          qppermb,3     %r20, %r19, %r0, %r18
          qppermb,4     %r20, %r19, %r5, %r19
          stqp,5        %r7, _f16s,_lts0hi 0xb0, %g26
          movaqp,0      area=11, ind=16, am=1, be=0, %r16
          movaqp,1      area=11, ind=0, am=0, be=0, %r15
          movaqp,2      area=11, ind=16, am=1, be=0, %g26
          movaqp,3      area=11, ind=0, am=0, be=0, %g25
        }
        {
          loop_mode
          qppermb,0     %g18, %g16, %r0, %r30
          qppermb,1     %g18, %g16, %r5, %g16
          stqp,2        %r7, _f16s,_lts0lo 0xc0, %r24
          qppermb,3     %r22, %g24, %r0, %g18
          qppermb,4     %r22, %g24, %r5, %g24
          stqp,5        %r7, _f16s,_lts0hi 0xd0, %g29
          movaqp,0      area=12, ind=16, am=1, be=0, %r20
          movaqp,1      area=12, ind=0, am=0, be=0, %g29
          movaqp,2      area=12, ind=16, am=1, be=0, %r29
          movaqp,3      area=12, ind=0, am=0, be=0, %r24
        }
        {
          loop_mode
          qppermb,0     %g28, %g27, %r0, %r32
          qppermb,1     %g28, %g27, %r5, %g27
          stqp,2        %r7, _f16s,_lts0lo 0xe0, %g21
          qppermb,3     %r23, %r17, %r0, %g28
          qppermb,4     %r23, %r17, %r5, %r17
          stqp,5        %r7, _f16s,_lts0hi 0xf0, %g23
          movaqp,0      area=13, ind=16, am=1, be=0, %g23
          movaqp,1      area=13, ind=0, am=0, be=0, %g21
          movaqp,2      area=13, ind=16, am=1, be=0, %r31
          movaqp,3      area=13, ind=0, am=0, be=0, %r22
        }
        {
          loop_mode
          qppermb,0     %g31, %g30, %r0, %r34
          qppermb,1     %g31, %g30, %r5, %g30
          stqp,2        %r7, _f16s,_lts0lo 0x100, %g22
          qppermb,3     %r25, %r4, %r0, %g31
          qppermb,4     %r25, %r4, %r5, %r4
          stqp,5        %r7, _f16s,_lts0hi 0x110, %r9
          movaqp,0      area=14, ind=16, am=1, be=0, %r9
          movaqp,1      area=14, ind=0, am=0, be=0, %g22
          movaqp,2      area=14, ind=16, am=1, be=0, %r33
          movaqp,3      area=14, ind=0, am=0, be=0, %r23
        }
        {
          loop_mode
          qppermb,0     %r21, %r12, %r0, %r36
          qppermb,1     %r21, %r12, %r5, %r12
          stqp,2        %r7, _f16s,_lts0lo 0x120, %r10
          qppermb,3     %r27, %r26, %r0, %r21
          qppermb,4     %r27, %r26, %r5, %r26
          stqp,5        %r7, _f16s,_lts0hi 0x130, %r11
          movaqp,0      area=15, ind=16, am=1, be=0, %r11
          movaqp,1      area=15, ind=0, am=0, be=0, %r10
          movaqp,2      area=15, ind=16, am=1, be=0, %r35
          movaqp,3      area=15, ind=0, am=0, be=0, %r25
        }
        {
          loop_mode
          qppermb,0     %r16, %r15, %r0, %g17
          qppermb,1     %r16, %r15, %r5, %g20
          stqp,2        %r7, _f16s,_lts0lo 0x140, %g17
          qppermb,3     %g26, %g25, %r0, %r15
          qppermb,4     %g26, %g25, %r5, %g25
          stqp,5        %r7, _f16s,_lts0hi 0x150, %g20
        }
        {
          loop_mode
          qppermb,0     %r20, %g29, %r0, %g26
          qppermb,1     %r20, %g29, %r5, %g29
          stqp,2        %r7, _f16s,_lts0lo 0x160, %r13
          qppermb,3     %r29, %r24, %r0, %r13
          qppermb,4     %r29, %r24, %r5, %r14
          stqp,5        %r7, _f16s,_lts0hi 0x170, %r14
        }
        {
          loop_mode
          qppermb,0     %g23, %g21, %r0, %g19
          qppermb,1     %g23, %g21, %r5, %g21
          stqp,2        %r7, _f16s,_lts0lo 0x180, %r28
          qppermb,3     %r31, %r22, %r0, %g23
          qppermb,4     %r31, %r22, %r5, %r16
          stqp,5        %r7, _f16s,_lts0hi 0x190, %g19
        }
        {
          loop_mode
          qppermb,0     %r9, %g22, %r0, %r18
          qppermb,1     %r9, %g22, %r5, %g22
          stqp,2        %r7, _f16s,_lts0lo 0x1a0, %r18
          qppermb,3     %r33, %r23, %r0, %r9
          qppermb,4     %r33, %r23, %r5, %r19
          stqp,5        %r7, _f16s,_lts0hi 0x1b0, %r19
        }
        {
          loop_mode
          qppermb,0     %r11, %r10, %r0, %g16
          qppermb,1     %r11, %r10, %r5, %r10
          stqp,2        %r7, _f16s,_lts0lo 0x1c0, %r30
          qppermb,3     %r35, %r25, %r0, %r11
          qppermb,4     %r35, %r25, %r5, %r20
          stqp,5        %r7, _f16s,_lts0hi 0x1d0, %g16
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x1e0, %g18
          stqp,5        %r7, _f16s,_lts0hi 0x1f0, %g24
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x200, %r32
          stqp,5        %r7, _f16s,_lts0hi 0x210, %g27
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x220, %g28
          stqp,5        %r7, _f16s,_lts0hi 0x230, %r17
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x240, %r34
          stqp,5        %r7, _f16s,_lts0hi 0x250, %g30
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x260, %g31
          stqp,5        %r7, _f16s,_lts0hi 0x270, %r4
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x280, %r36
          stqp,5        %r7, _f16s,_lts0hi 0x290, %r12
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x2a0, %r21
          stqp,5        %r7, _f16s,_lts0hi 0x2b0, %r26
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x2c0, %g17
          stqp,5        %r7, _f16s,_lts0hi 0x2d0, %g20
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x2e0, %r15
          stqp,5        %r7, _f16s,_lts0hi 0x2f0, %g25
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x300, %g26
          stqp,5        %r7, _f16s,_lts0hi 0x310, %g29
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x320, %r13
          stqp,5        %r7, _f16s,_lts0hi 0x330, %r14
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x340, %g19
          stqp,5        %r7, _f16s,_lts0hi 0x350, %g21
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x360, %g23
          stqp,5        %r7, _f16s,_lts0hi 0x370, %r16
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x380, %r18
          stqp,5        %r7, _f16s,_lts0hi 0x390, %g22
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x3a0, %r9
          stqp,5        %r7, _f16s,_lts0hi 0x3b0, %r19
        }
        {
          loop_mode
          stqp,2        %r7, _f16s,_lts0lo 0x3c0, %g16
          stqp,5        %r7, _f16s,_lts0hi 0x3d0, %r10
        }
        {
          loop_mode
          ct    %ctpr1 ? %NOT_LOOP_END
          alc   alcf=0, alct=1
          stqp,2        %r7, _f16s,_lts0lo 0x3e0, %r11
          stqp,5        %r7, _f16s,_lts0hi 0x3f0, %r20
        }
        {
          loop_mode
          ct    %ctpr3
          alc   alcf=0, alct=1
        }

void reverse_radix4_vector2(int bit_count_in, myComplex *data_in, myComplex2 *data_out)
{
	int bit_count_out = bit_count_in - 1;

//	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in = (__v2di*)data_in;

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out; ++i)
	{
		uint64_t rev = __builtin_e2k_bitrevd(i);
		int64_t offset = 16 * (((rev>>(shift_out-1)) & 0xAAAAAAAAAAAAAAAA) | ((rev>>(shift_out+1)) & 0x5555555555555555));
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		*(__v2du*)((void*)data_out + offset) = __builtin_e2k_qppermb(in[i], in[i], mask);
	}
}

.L4546:
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=1, asz=5, abs=0, disp=0
        }
.L4397:
        {
          loop_mode
          bitrevd,0,sm  %b[10], %b[1]
          shr_andd,1,sm %b[3], %r5, %r6, %b[9]
          ord,2,sm      %b[11], %b[7], %b[12]
          shld,3,sm     %b[14], 0x4, %b[15]
          qppermb,4,sm  %b[6], %b[6], %r0, %b[13]
          addd,5,sm     %b[10], 0x1, %b[8]
          movaqp,1      area=0, ind=0, am=1, be=0, %b[0]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          shr_andd,1,sm %b[1], %r4, %r7, %b[3]
          stqp,5        %r2, %b[15], %b[13]
        }

void reverse_radix4_vector2_x4(int bit_count_in, myComplex *data_in, myComplex2 *data_out)
{
	int bit_count_out = bit_count_in - 1;

//	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in    = (__v2di*) data_in;
	__v2di *out_0 = (__v2di*)&data_out[0 * count_out/4];
	__v2di *out_1 = (__v2di*)&data_out[1 * count_out/4];
	__v2di *out_2 = (__v2di*)&data_out[2 * count_out/4];
	__v2di *out_3 = (__v2di*)&data_out[3 * count_out/4];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out; i += 4)
	{
		uint64_t rev = __builtin_e2k_bitrevd(i);
		int64_t offset = 16 * (((rev>>(shift_out-1)) & 0xAAAAAAAAAAAAAAAA) | ((rev>>(shift_out+1)) & 0x5555555555555555));
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		*(__v2du*)((void*)out_0 + offset) = __builtin_e2k_qppermb(in[i + 0], in[i + 0], mask);
		*(__v2du*)((void*)out_1 + offset) = __builtin_e2k_qppermb(in[i + 1], in[i + 1], mask);
		*(__v2du*)((void*)out_2 + offset) = __builtin_e2k_qppermb(in[i + 2], in[i + 2], mask);
		*(__v2du*)((void*)out_3 + offset) = __builtin_e2k_qppermb(in[i + 3], in[i + 3], mask);
	}
}

.L4888:
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=5, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=5, abs=0, disp=32
        }
.L4593:
        {
          loop_mode
          qppermb,0,sm  %b[11], %b[11], %r7, %b[20]
          shr_andd,1,sm %b[26], %r9, %r11, %b[16]
          qppermb,3,sm  %b[12], %b[12], %r7, %b[23]
          shr_andd,4,sm %b[26], %r6, %r10, %b[19]
          addd,5,sm     %b[17], 0x4, %b[15]
          movaqp,0      area=0, ind=16, am=1, be=0, %b[7]
          movaqp,1      area=0, ind=0, am=0, be=0, %b[8]
          movaqp,2      area=0, ind=16, am=1, be=0, %b[0]
          movaqp,3      area=0, ind=0, am=0, be=0, %b[1]
        }
        {
          loop_mode
          bitrevd,0,sm  %b[17], %b[24]
          qppermb,1,sm  %b[4], %b[4], %r7, %b[11]
          stqp,2        %r5, %b[6], %b[22]
          ord,3,sm      %b[21], %b[18], %b[27]
          qppermb,4,sm  %b[5], %b[5], %r7, %b[12]
          stqp,5        %r2, %b[6], %b[25]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          stqp,2        %r0, %b[6], %b[13]
          shld,4,sm     %b[27], 0x4, %b[4]
          stqp,5        %r4, %b[6], %b[14]
        }

void reverse_radix4_vector2_stream4(int bit_count_in, myComplex *data_in, myComplex2 *data_out)
{
	int bit_count_out = bit_count_in - 1;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_0 = (__v2di*)&data_in[0 * count_in/4];
	__v2di *in_1 = (__v2di*)&data_in[1 * count_in/4];
	__v2di *in_2 = (__v2di*)&data_in[2 * count_in/4];
	__v2di *in_3 = (__v2di*)&data_in[3 * count_in/4];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/4; ++i)
	{
		uint64_t rev = __builtin_e2k_bitrevd(i);
		int64_t offset = 16 * (((rev>>(shift_out-1)) & 0xAAAAAAAAAAAAAAAA) | ((rev>>(shift_out+1)) & 0x5555555555555555));
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		*(__v2du*)((void*)data_out + offset + 0*16) = __builtin_e2k_qppermb(in_0[i], in_0[i], mask);
		*(__v2du*)((void*)data_out + offset + 1*16) = __builtin_e2k_qppermb(in_1[i], in_1[i], mask);
		*(__v2du*)((void*)data_out + offset + 2*16) = __builtin_e2k_qppermb(in_2[i], in_2[i], mask);
		*(__v2du*)((void*)data_out + offset + 3*16) = __builtin_e2k_qppermb(in_3[i], in_3[i], mask);
	}
}

.L5211:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=4, asz=4, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=3, asz=4, abs=0, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=2, asz=4, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=1, asz=4, abs=16, disp=0
        }
.L4931:
        {
          loop_mode
          qppermb,0,sm  %b[11], %b[11], %r7, %b[20]
          shr_andd,1,sm %b[26], %r9, %r11, %b[16]
          qppermb,3,sm  %b[12], %b[12], %r7, %b[23]
          shr_andd,4,sm %b[26], %r6, %r10, %b[19]
          addd,5,sm     %b[17], 0x1, %b[15]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[1]
          movaqp,1      area=0, ind=0, am=1, be=0, %b[8]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[0]
          movaqp,3      area=0, ind=0, am=1, be=0, %b[7]
        }
        {
          loop_mode
          bitrevd,0,sm  %b[17], %b[24]
          qppermb,1,sm  %b[4], %b[4], %r7, %b[11]
          stqp,2        %r0, %b[6], %b[22]
          ord,3,sm      %b[21], %b[18], %b[27]
          qppermb,4,sm  %b[5], %b[5], %r7, %b[12]
          stqp,5        %r2, %b[6], %b[25]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          stqp,2        %r5, %b[6], %b[13]
          shld,4,sm     %b[27], 0x4, %b[4]
          stqp,5        %r4, %b[6], %b[14]
        }

void reverse_radix4_vector2_stream16(int bit_count_in, myComplex *data_in, myComplex2 *data_out)
{
	int bit_count_out = bit_count_in - 1;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_00 = (__v2di*)&data_in[ 0 * count_in/16];
	__v2di *in_01 = (__v2di*)&data_in[ 1 * count_in/16];
	__v2di *in_02 = (__v2di*)&data_in[ 2 * count_in/16];
	__v2di *in_03 = (__v2di*)&data_in[ 3 * count_in/16];
	__v2di *in_10 = (__v2di*)&data_in[ 4 * count_in/16];
	__v2di *in_11 = (__v2di*)&data_in[ 5 * count_in/16];
	__v2di *in_12 = (__v2di*)&data_in[ 6 * count_in/16];
	__v2di *in_13 = (__v2di*)&data_in[ 7 * count_in/16];
	__v2di *in_20 = (__v2di*)&data_in[ 8 * count_in/16];
	__v2di *in_21 = (__v2di*)&data_in[ 9 * count_in/16];
	__v2di *in_22 = (__v2di*)&data_in[10 * count_in/16];
	__v2di *in_23 = (__v2di*)&data_in[11 * count_in/16];
	__v2di *in_30 = (__v2di*)&data_in[12 * count_in/16];
	__v2di *in_31 = (__v2di*)&data_in[13 * count_in/16];
	__v2di *in_32 = (__v2di*)&data_in[14 * count_in/16];
	__v2di *in_33 = (__v2di*)&data_in[15 * count_in/16];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/16; ++i)
	{
		uint64_t rev = __builtin_e2k_bitrevd(i);
		int64_t offset = 16 * (((rev>>(shift_out-1)) & 0xAAAAAAAAAAAAAAAA) | ((rev>>(shift_out+1)) & 0x5555555555555555));
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		*(__v2du*)((void*)data_out + offset +  0*16) = __builtin_e2k_qppermb(in_00[i], in_00[i], mask);
		*(__v2du*)((void*)data_out + offset +  1*16) = __builtin_e2k_qppermb(in_10[i], in_10[i], mask);
		*(__v2du*)((void*)data_out + offset +  2*16) = __builtin_e2k_qppermb(in_20[i], in_20[i], mask);
		*(__v2du*)((void*)data_out + offset +  3*16) = __builtin_e2k_qppermb(in_30[i], in_30[i], mask);
		*(__v2du*)((void*)data_out + offset +  4*16) = __builtin_e2k_qppermb(in_01[i], in_01[i], mask);
		*(__v2du*)((void*)data_out + offset +  5*16) = __builtin_e2k_qppermb(in_11[i], in_11[i], mask);
		*(__v2du*)((void*)data_out + offset +  6*16) = __builtin_e2k_qppermb(in_21[i], in_21[i], mask);
		*(__v2du*)((void*)data_out + offset +  7*16) = __builtin_e2k_qppermb(in_31[i], in_31[i], mask);
		*(__v2du*)((void*)data_out + offset +  8*16) = __builtin_e2k_qppermb(in_02[i], in_02[i], mask);
		*(__v2du*)((void*)data_out + offset +  9*16) = __builtin_e2k_qppermb(in_12[i], in_12[i], mask);
		*(__v2du*)((void*)data_out + offset + 10*16) = __builtin_e2k_qppermb(in_22[i], in_22[i], mask);
		*(__v2du*)((void*)data_out + offset + 11*16) = __builtin_e2k_qppermb(in_32[i], in_32[i], mask);
		*(__v2du*)((void*)data_out + offset + 12*16) = __builtin_e2k_qppermb(in_03[i], in_03[i], mask);
		*(__v2du*)((void*)data_out + offset + 13*16) = __builtin_e2k_qppermb(in_13[i], in_13[i], mask);
		*(__v2du*)((void*)data_out + offset + 14*16) = __builtin_e2k_qppermb(in_23[i], in_23[i], mask);
		*(__v2du*)((void*)data_out + offset + 15*16) = __builtin_e2k_qppermb(in_33[i], in_33[i], mask);
	}
}

.L6141:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=1, incr=0, ind=0, asz=2, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=15, asz=2, abs=0, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=14, asz=2, abs=4, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=13, asz=2, abs=4, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=12, asz=2, abs=8, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=11, asz=2, abs=8, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=10, asz=2, abs=12, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=9, asz=2, abs=12, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=8, asz=2, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=7, asz=2, abs=16, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=6, asz=2, abs=20, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=5, asz=2, abs=20, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=4, asz=2, abs=24, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=3, asz=2, abs=24, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=2, asz=2, abs=28, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=1, asz=2, abs=28, disp=0
        }
.L5350:
        {
          loop_mode
          qppermb,0,sm  %b[12], %b[12], %r20, %b[46]
          shr_andd,1,sm %b[24], %r21, %r24, %b[1]
          stqp,2        %r0, %b[21], %b[4]
          qppermb,3,sm  %b[17], %b[17], %r20, %b[47]
          shr_andd,4,sm %b[24], %r22, %r23, %b[5]
          stqp,5        %r2, %b[21], %b[16]
        }
        {
          loop_mode
          qppermb,1,sm  %b[41], %b[41], %r20, %b[4]
          stqp,2        %r6, %b[21], %b[46]
          qppermb,4,sm  %b[42], %b[42], %r20, %b[9]
          stqp,5        %r5, %b[21], %b[47]
        }
        {
          loop_mode
          qppermb,1,sm  %b[40], %b[40], %r20, %b[24]
          stqp,2        %r10, %b[21], %b[6]
          qppermb,4,sm  %b[39], %b[39], %r20, %b[23]
          stqp,5        %r7, %b[21], %b[11]
          movaqp,0      area=7, ind=0, am=1, be=0, %b[16]
          movaqp,1      area=6, ind=0, am=1, be=0, %b[20]
          movaqp,2      area=7, ind=0, am=1, be=0, %b[12]
          movaqp,3      area=6, ind=0, am=1, be=0, %b[17]
        }
        {
          loop_mode
          qppermb,1,sm  %b[38], %b[38], %r20, %b[30]
          stqp,2        %r9, %b[21], %b[26]
          qppermb,4,sm  %b[37], %b[37], %r20, %b[29]
          stqp,5        %r11, %b[21], %b[25]
          movaqp,0      area=5, ind=0, am=1, be=0, %b[11]
          movaqp,1      area=4, ind=0, am=1, be=0, %b[36]
          movaqp,2      area=5, ind=0, am=1, be=0, %b[6]
          movaqp,3      area=4, ind=0, am=1, be=0, %b[35]
        }
        {
          loop_mode
          qppermb,1,sm  %b[13], %b[13], %r20, %b[26]
          stqp,2        %r12, %b[21], %b[32]
          qppermb,4,sm  %b[8], %b[8], %r20, %b[25]
          stqp,5        %r13, %b[21], %b[31]
          movaqp,0      area=3, ind=0, am=1, be=0, %b[39]
          movaqp,1      area=2, ind=0, am=1, be=0, %b[40]
          movaqp,2      area=3, ind=0, am=1, be=0, %b[37]
          movaqp,3      area=2, ind=0, am=1, be=0, %b[38]
        }
        {
          loop_mode
          addd,0,sm     %b[2], 0x1, %b[0]
          qppermb,1,sm  %b[22], %b[22], %r20, %b[42]
          stqp,2        %r14, %b[21], %b[28]
          ord,3,sm      %b[5], %b[1], %b[45]
          qppermb,4,sm  %b[19], %b[19], %r20, %b[41]
          stqp,5        %r15, %b[21], %b[27]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[13]
          movaqp,1      area=0, ind=0, am=1, be=0, %b[32]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[8]
          movaqp,3      area=0, ind=0, am=1, be=0, %b[31]
        }
        {
          loop_mode
          bitrevd,0,sm  %b[2], %b[22]
          qppermb,1,sm  %b[18], %b[18], %r20, %b[5]
          stqp,2        %r16, %b[21], %b[44]
          shld,3,sm     %b[45], 0x4, %b[19]
          qppermb,4,sm  %b[14], %b[14], %r20, %b[1]
          stqp,5        %r17, %b[21], %b[43]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[33], %b[33], %r20, %b[2]
          stqp,2        %r18, %b[21], %b[7]
          qppermb,3,sm  %b[34], %b[34], %r20, %b[14]
          stqp,5        %r19, %b[21], %b[3]
        }

void reverse_radix4_vector2_stream32(int bit_count_in, myComplex *data_in, myComplex2 *data_out)
{
	int bit_count_out = bit_count_in - 1;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_000 = (__v2di*)&data_in[ 0 * count_in/64];
	__v2di *in_001 = (__v2di*)&data_in[ 1 * count_in/64];
	__v2di *in_002 = (__v2di*)&data_in[ 2 * count_in/64];
	__v2di *in_003 = (__v2di*)&data_in[ 3 * count_in/64];
	__v2di *in_010 = (__v2di*)&data_in[ 4 * count_in/64];
	__v2di *in_011 = (__v2di*)&data_in[ 5 * count_in/64];
	__v2di *in_012 = (__v2di*)&data_in[ 6 * count_in/64];
	__v2di *in_013 = (__v2di*)&data_in[ 7 * count_in/64];
	__v2di *in_020 = (__v2di*)&data_in[ 8 * count_in/64];
	__v2di *in_021 = (__v2di*)&data_in[ 9 * count_in/64];
	__v2di *in_022 = (__v2di*)&data_in[10 * count_in/64];
	__v2di *in_023 = (__v2di*)&data_in[11 * count_in/64];
	__v2di *in_030 = (__v2di*)&data_in[12 * count_in/64];
	__v2di *in_031 = (__v2di*)&data_in[13 * count_in/64];
	__v2di *in_032 = (__v2di*)&data_in[14 * count_in/64];
	__v2di *in_033 = (__v2di*)&data_in[15 * count_in/64];
	__v2di *in_100 = (__v2di*)&data_in[16 * count_in/64];
	__v2di *in_101 = (__v2di*)&data_in[17 * count_in/64];
	__v2di *in_102 = (__v2di*)&data_in[18 * count_in/64];
	__v2di *in_103 = (__v2di*)&data_in[19 * count_in/64];
	__v2di *in_110 = (__v2di*)&data_in[20 * count_in/64];
	__v2di *in_111 = (__v2di*)&data_in[21 * count_in/64];
	__v2di *in_112 = (__v2di*)&data_in[22 * count_in/64];
	__v2di *in_113 = (__v2di*)&data_in[23 * count_in/64];
	__v2di *in_120 = (__v2di*)&data_in[24 * count_in/64];
	__v2di *in_121 = (__v2di*)&data_in[25 * count_in/64];
	__v2di *in_122 = (__v2di*)&data_in[26 * count_in/64];
	__v2di *in_123 = (__v2di*)&data_in[27 * count_in/64];
	__v2di *in_130 = (__v2di*)&data_in[28 * count_in/64];
	__v2di *in_131 = (__v2di*)&data_in[29 * count_in/64];
	__v2di *in_132 = (__v2di*)&data_in[30 * count_in/64];
	__v2di *in_133 = (__v2di*)&data_in[31 * count_in/64];
	__v2di *in_200 = (__v2di*)&data_in[32 * count_in/64];
	__v2di *in_201 = (__v2di*)&data_in[33 * count_in/64];
	__v2di *in_202 = (__v2di*)&data_in[34 * count_in/64];
	__v2di *in_203 = (__v2di*)&data_in[35 * count_in/64];
	__v2di *in_210 = (__v2di*)&data_in[36 * count_in/64];
	__v2di *in_211 = (__v2di*)&data_in[37 * count_in/64];
	__v2di *in_212 = (__v2di*)&data_in[38 * count_in/64];
	__v2di *in_213 = (__v2di*)&data_in[39 * count_in/64];
	__v2di *in_220 = (__v2di*)&data_in[40 * count_in/64];
	__v2di *in_221 = (__v2di*)&data_in[41 * count_in/64];
	__v2di *in_222 = (__v2di*)&data_in[42 * count_in/64];
	__v2di *in_223 = (__v2di*)&data_in[43 * count_in/64];
	__v2di *in_230 = (__v2di*)&data_in[44 * count_in/64];
	__v2di *in_231 = (__v2di*)&data_in[45 * count_in/64];
	__v2di *in_232 = (__v2di*)&data_in[46 * count_in/64];
	__v2di *in_233 = (__v2di*)&data_in[47 * count_in/64];
	__v2di *in_300 = (__v2di*)&data_in[48 * count_in/64];
	__v2di *in_301 = (__v2di*)&data_in[49 * count_in/64];
	__v2di *in_302 = (__v2di*)&data_in[50 * count_in/64];
	__v2di *in_303 = (__v2di*)&data_in[51 * count_in/64];
	__v2di *in_310 = (__v2di*)&data_in[52 * count_in/64];
	__v2di *in_311 = (__v2di*)&data_in[53 * count_in/64];
	__v2di *in_312 = (__v2di*)&data_in[54 * count_in/64];
	__v2di *in_313 = (__v2di*)&data_in[55 * count_in/64];
	__v2di *in_320 = (__v2di*)&data_in[56 * count_in/64];
	__v2di *in_321 = (__v2di*)&data_in[57 * count_in/64];
	__v2di *in_322 = (__v2di*)&data_in[58 * count_in/64];
	__v2di *in_323 = (__v2di*)&data_in[59 * count_in/64];
	__v2di *in_330 = (__v2di*)&data_in[60 * count_in/64];
	__v2di *in_331 = (__v2di*)&data_in[61 * count_in/64];
	__v2di *in_332 = (__v2di*)&data_in[62 * count_in/64];
	__v2di *in_333 = (__v2di*)&data_in[63 * count_in/64];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/32/2; ++i)
	{
		uint64_t rev = __builtin_e2k_bitrevd(i);
		int64_t offset = 16 * (((rev>>(shift_out-1)) & 0xAAAAAAAAAAAAAAAA) | ((rev>>(shift_out+1)) & 0x5555555555555555));
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		*(__v2du*)((void*)data_out + offset +  0*16) = __builtin_e2k_qppermb(in_000[i], in_000[i], mask);
		*(__v2du*)((void*)data_out + offset +  1*16) = __builtin_e2k_qppermb(in_100[i], in_100[i], mask);
		*(__v2du*)((void*)data_out + offset +  2*16) = __builtin_e2k_qppermb(in_200[i], in_200[i], mask);
		*(__v2du*)((void*)data_out + offset +  3*16) = __builtin_e2k_qppermb(in_300[i], in_300[i], mask);
		*(__v2du*)((void*)data_out + offset +  4*16) = __builtin_e2k_qppermb(in_010[i], in_010[i], mask);
		*(__v2du*)((void*)data_out + offset +  5*16) = __builtin_e2k_qppermb(in_110[i], in_110[i], mask);
		*(__v2du*)((void*)data_out + offset +  6*16) = __builtin_e2k_qppermb(in_210[i], in_210[i], mask);
		*(__v2du*)((void*)data_out + offset +  7*16) = __builtin_e2k_qppermb(in_310[i], in_310[i], mask);
		*(__v2du*)((void*)data_out + offset +  8*16) = __builtin_e2k_qppermb(in_020[i], in_020[i], mask);
		*(__v2du*)((void*)data_out + offset +  9*16) = __builtin_e2k_qppermb(in_120[i], in_120[i], mask);
		*(__v2du*)((void*)data_out + offset + 10*16) = __builtin_e2k_qppermb(in_220[i], in_220[i], mask);
		*(__v2du*)((void*)data_out + offset + 11*16) = __builtin_e2k_qppermb(in_320[i], in_320[i], mask);
		*(__v2du*)((void*)data_out + offset + 12*16) = __builtin_e2k_qppermb(in_030[i], in_030[i], mask);
		*(__v2du*)((void*)data_out + offset + 13*16) = __builtin_e2k_qppermb(in_130[i], in_130[i], mask);
		*(__v2du*)((void*)data_out + offset + 14*16) = __builtin_e2k_qppermb(in_230[i], in_230[i], mask);
		*(__v2du*)((void*)data_out + offset + 15*16) = __builtin_e2k_qppermb(in_330[i], in_330[i], mask);
		*(__v2du*)((void*)data_out + offset + 16*16) = __builtin_e2k_qppermb(in_001[i], in_001[i], mask);
		*(__v2du*)((void*)data_out + offset + 17*16) = __builtin_e2k_qppermb(in_101[i], in_101[i], mask);
		*(__v2du*)((void*)data_out + offset + 18*16) = __builtin_e2k_qppermb(in_201[i], in_201[i], mask);
		*(__v2du*)((void*)data_out + offset + 19*16) = __builtin_e2k_qppermb(in_301[i], in_301[i], mask);
		*(__v2du*)((void*)data_out + offset + 20*16) = __builtin_e2k_qppermb(in_011[i], in_011[i], mask);
		*(__v2du*)((void*)data_out + offset + 21*16) = __builtin_e2k_qppermb(in_111[i], in_111[i], mask);
		*(__v2du*)((void*)data_out + offset + 22*16) = __builtin_e2k_qppermb(in_211[i], in_211[i], mask);
		*(__v2du*)((void*)data_out + offset + 23*16) = __builtin_e2k_qppermb(in_311[i], in_311[i], mask);
		*(__v2du*)((void*)data_out + offset + 24*16) = __builtin_e2k_qppermb(in_021[i], in_021[i], mask);
		*(__v2du*)((void*)data_out + offset + 25*16) = __builtin_e2k_qppermb(in_121[i], in_121[i], mask);
		*(__v2du*)((void*)data_out + offset + 26*16) = __builtin_e2k_qppermb(in_221[i], in_221[i], mask);
		*(__v2du*)((void*)data_out + offset + 27*16) = __builtin_e2k_qppermb(in_321[i], in_321[i], mask);
		*(__v2du*)((void*)data_out + offset + 28*16) = __builtin_e2k_qppermb(in_031[i], in_031[i], mask);
		*(__v2du*)((void*)data_out + offset + 29*16) = __builtin_e2k_qppermb(in_131[i], in_131[i], mask);
		*(__v2du*)((void*)data_out + offset + 30*16) = __builtin_e2k_qppermb(in_231[i], in_231[i], mask);
		*(__v2du*)((void*)data_out + offset + 31*16) = __builtin_e2k_qppermb(in_331[i], in_331[i], mask);
	}

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/32/2; ++i)
	{
		uint64_t rev = __builtin_e2k_bitrevd(i);
		int64_t offset = 16 * (((rev>>(shift_out-1)) & 0xAAAAAAAAAAAAAAAA) | ((rev>>(shift_out+1)) & 0x5555555555555555));
		__v2di mask = {0x0B0A090803020100, 0x0F0E0D0C07060504};
		*(__v2du*)((void*)data_out + offset + 32*16) = __builtin_e2k_qppermb(in_002[i], in_002[i], mask);
		*(__v2du*)((void*)data_out + offset + 33*16) = __builtin_e2k_qppermb(in_102[i], in_102[i], mask);
		*(__v2du*)((void*)data_out + offset + 34*16) = __builtin_e2k_qppermb(in_202[i], in_202[i], mask);
		*(__v2du*)((void*)data_out + offset + 35*16) = __builtin_e2k_qppermb(in_302[i], in_302[i], mask);
		*(__v2du*)((void*)data_out + offset + 36*16) = __builtin_e2k_qppermb(in_012[i], in_012[i], mask);
		*(__v2du*)((void*)data_out + offset + 37*16) = __builtin_e2k_qppermb(in_112[i], in_112[i], mask);
		*(__v2du*)((void*)data_out + offset + 38*16) = __builtin_e2k_qppermb(in_212[i], in_212[i], mask);
		*(__v2du*)((void*)data_out + offset + 39*16) = __builtin_e2k_qppermb(in_312[i], in_312[i], mask);
		*(__v2du*)((void*)data_out + offset + 40*16) = __builtin_e2k_qppermb(in_022[i], in_022[i], mask);
		*(__v2du*)((void*)data_out + offset + 41*16) = __builtin_e2k_qppermb(in_122[i], in_122[i], mask);
		*(__v2du*)((void*)data_out + offset + 42*16) = __builtin_e2k_qppermb(in_222[i], in_222[i], mask);
		*(__v2du*)((void*)data_out + offset + 43*16) = __builtin_e2k_qppermb(in_322[i], in_322[i], mask);
		*(__v2du*)((void*)data_out + offset + 44*16) = __builtin_e2k_qppermb(in_032[i], in_032[i], mask);
		*(__v2du*)((void*)data_out + offset + 45*16) = __builtin_e2k_qppermb(in_132[i], in_132[i], mask);
		*(__v2du*)((void*)data_out + offset + 46*16) = __builtin_e2k_qppermb(in_232[i], in_232[i], mask);
		*(__v2du*)((void*)data_out + offset + 47*16) = __builtin_e2k_qppermb(in_332[i], in_332[i], mask);
		*(__v2du*)((void*)data_out + offset + 48*16) = __builtin_e2k_qppermb(in_003[i], in_003[i], mask);
		*(__v2du*)((void*)data_out + offset + 49*16) = __builtin_e2k_qppermb(in_103[i], in_103[i], mask);
		*(__v2du*)((void*)data_out + offset + 50*16) = __builtin_e2k_qppermb(in_203[i], in_203[i], mask);
		*(__v2du*)((void*)data_out + offset + 51*16) = __builtin_e2k_qppermb(in_303[i], in_303[i], mask);
		*(__v2du*)((void*)data_out + offset + 52*16) = __builtin_e2k_qppermb(in_013[i], in_013[i], mask);
		*(__v2du*)((void*)data_out + offset + 53*16) = __builtin_e2k_qppermb(in_113[i], in_113[i], mask);
		*(__v2du*)((void*)data_out + offset + 54*16) = __builtin_e2k_qppermb(in_213[i], in_213[i], mask);
		*(__v2du*)((void*)data_out + offset + 55*16) = __builtin_e2k_qppermb(in_313[i], in_313[i], mask);
		*(__v2du*)((void*)data_out + offset + 56*16) = __builtin_e2k_qppermb(in_023[i], in_023[i], mask);
		*(__v2du*)((void*)data_out + offset + 57*16) = __builtin_e2k_qppermb(in_123[i], in_123[i], mask);
		*(__v2du*)((void*)data_out + offset + 58*16) = __builtin_e2k_qppermb(in_223[i], in_223[i], mask);
		*(__v2du*)((void*)data_out + offset + 59*16) = __builtin_e2k_qppermb(in_323[i], in_323[i], mask);
		*(__v2du*)((void*)data_out + offset + 60*16) = __builtin_e2k_qppermb(in_033[i], in_033[i], mask);
		*(__v2du*)((void*)data_out + offset + 61*16) = __builtin_e2k_qppermb(in_133[i], in_133[i], mask);
		*(__v2du*)((void*)data_out + offset + 62*16) = __builtin_e2k_qppermb(in_233[i], in_233[i], mask);
		*(__v2du*)((void*)data_out + offset + 63*16) = __builtin_e2k_qppermb(in_333[i], in_333[i], mask);
	}
}

.L9991:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=17, incr=0, ind=0, asz=1, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=16, incr=0, ind=0, asz=1, abs=0, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=15, incr=0, ind=0, asz=1, abs=2, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=14, incr=0, ind=0, asz=1, abs=2, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=13, incr=0, ind=0, asz=1, abs=4, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=12, incr=0, ind=0, asz=1, abs=4, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=11, incr=0, ind=0, asz=1, abs=6, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=10, incr=0, ind=0, asz=1, abs=6, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=9, incr=0, ind=0, asz=1, abs=8, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=8, incr=0, ind=0, asz=1, abs=8, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=7, incr=0, ind=0, asz=1, abs=10, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=6, incr=0, ind=0, asz=1, abs=10, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=5, incr=0, ind=0, asz=1, abs=12, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=4, incr=0, ind=0, asz=1, abs=12, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=3, incr=0, ind=0, asz=1, abs=14, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=2, incr=0, ind=0, asz=1, abs=14, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=1, incr=0, ind=0, asz=1, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=15, asz=1, abs=16, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=14, asz=1, abs=18, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=13, asz=1, abs=18, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=12, asz=1, abs=20, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=11, asz=1, abs=20, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=10, asz=1, abs=22, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=9, asz=1, abs=22, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=8, asz=1, abs=24, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=7, asz=1, abs=24, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=6, asz=1, abs=26, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=5, asz=1, abs=26, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=4, asz=1, abs=28, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=3, asz=1, abs=28, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=2, asz=1, abs=30, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=1, asz=1, abs=30, disp=0
        }
.L6665:
        {
          loop_mode
          qppermb,0,sm  %b[41], %b[41], %r0, %b[58]
          shr_andd,1,sm %b[56], %r1, %r38, %b[54]
          stqp,2        %r5, %b[34], %b[54]
          qppermb,3,sm  %b[46], %b[46], %r0, %b[60]
          shr_andd,4,sm %b[56], %r4, %r37, %b[56]
          stqp,5        %r2, %b[34], %b[58]
        }
        {
          loop_mode
          qppermb,1,sm  %b[76], %b[76], %r0, %b[1]
          stqp,2        %r7, %b[34], %b[58]
          qppermb,4,sm  %b[77], %b[77], %r0, %b[8]
          stqp,5        %r6, %b[34], %b[60]
        }
        {
          loop_mode
          qppermb,1,sm  %b[65], %b[65], %r0, %b[10]
          stqp,2        %r11, %b[34], %b[3]
          qppermb,4,sm  %b[63], %b[63], %r0, %b[3]
          stqp,5        %r9, %b[34], %b[10]
        }
        {
          loop_mode
          qppermb,1,sm  %b[75], %b[75], %r0, %b[12]
          stqp,2        %r10, %b[34], %b[12]
          qppermb,4,sm  %b[74], %b[74], %r0, %b[5]
          stqp,5        %r12, %b[34], %b[5]
        }
        {
          loop_mode
          qppermb,1,sm  %b[73], %b[73], %r0, %b[14]
          stqp,2        %r13, %b[34], %b[14]
          qppermb,4,sm  %b[72], %b[72], %r0, %b[7]
          stqp,5        %r14, %b[34], %b[7]
        }
        {
          loop_mode
          qppermb,1,sm  %b[71], %b[71], %r0, %b[16]
          stqp,2        %r15, %b[34], %b[16]
          qppermb,4,sm  %b[70], %b[70], %r0, %b[9]
          stqp,5        %r16, %b[34], %b[9]
        }
        {
          loop_mode
          qppermb,1,sm  %b[69], %b[69], %r0, %b[18]
          stqp,2        %r17, %b[34], %b[18]
          qppermb,4,sm  %b[67], %b[67], %r0, %b[11]
          stqp,5        %r18, %b[34], %b[11]
          movaqp,0      area=15, ind=0, am=1, be=0, %b[60]
          movaqp,1      area=14, ind=0, am=1, be=0, %b[64]
          movaqp,2      area=15, ind=0, am=1, be=0, %b[58]
          movaqp,3      area=14, ind=0, am=1, be=0, %b[62]
        }
        {
          loop_mode
          qppermb,1,sm  %b[68], %b[68], %r0, %b[36]
          stqp,2        %r19, %b[34], %b[20]
          qppermb,4,sm  %b[61], %b[61], %r0, %b[31]
          stqp,5        %r20, %b[34], %b[13]
          movaqp,0      area=13, ind=0, am=1, be=0, %b[63]
          movaqp,1      area=12, ind=0, am=1, be=0, %b[20]
          movaqp,2      area=13, ind=0, am=1, be=0, %b[61]
          movaqp,3      area=12, ind=0, am=1, be=0, %b[13]
        }
        {
          loop_mode
          qppermb,1,sm  %b[59], %b[59], %r0, %b[53]
          stqp,2        %r21, %b[34], %b[38]
          qppermb,4,sm  %b[57], %b[57], %r0, %b[49]
          stqp,5        %r22, %b[34], %b[33]
          movaqp,0      area=11, ind=0, am=1, be=0, %b[38]
          movaqp,1      area=10, ind=0, am=1, be=0, %b[46]
          movaqp,2      area=11, ind=0, am=1, be=0, %b[33]
          movaqp,3      area=10, ind=0, am=1, be=0, %b[41]
        }
        {
          loop_mode
          qppermb,1,sm  %b[48], %b[48], %r0, %b[48]
          stqp,2        %r23, %b[34], %b[55]
          qppermb,4,sm  %b[43], %b[43], %r0, %b[43]
          stqp,5        %r24, %b[34], %b[51]
          movaqp,0      area=9, ind=0, am=1, be=0, %b[57]
          movaqp,1      area=8, ind=0, am=1, be=0, %b[66]
          movaqp,2      area=9, ind=0, am=1, be=0, %b[55]
          movaqp,3      area=8, ind=0, am=1, be=0, %b[59]
        }
        {
          loop_mode
          qppermb,1,sm  %b[40], %b[40], %r0, %b[40]
          stqp,2        %r25, %b[34], %b[50]
          qppermb,4,sm  %b[35], %b[35], %r0, %b[35]
          stqp,5        %r26, %b[34], %b[45]
          movaqp,0      area=7, ind=0, am=1, be=0, %b[67]
          movaqp,1      area=6, ind=0, am=1, be=0, %b[69]
          movaqp,2      area=7, ind=0, am=1, be=0, %b[65]
          movaqp,3      area=6, ind=0, am=1, be=0, %b[68]
        }
        {
          loop_mode
          qppermb,1,sm  %b[22], %b[22], %r0, %b[22]
          stqp,2        %r27, %b[34], %b[42]
          qppermb,4,sm  %b[15], %b[15], %r0, %b[15]
          stqp,5        %r28, %b[34], %b[37]
          movaqp,0      area=5, ind=0, am=1, be=0, %b[71]
          movaqp,1      area=4, ind=0, am=1, be=0, %b[73]
          movaqp,2      area=5, ind=0, am=1, be=0, %b[70]
          movaqp,3      area=4, ind=0, am=1, be=0, %b[72]
        }
        {
          loop_mode
          qppermb,1,sm  %b[63], %b[63], %r0, %b[24]
          stqp,2        %r29, %b[34], %b[24]
          qppermb,4,sm  %b[61], %b[61], %r0, %b[17]
          stqp,5        %r30, %b[34], %b[17]
          movaqp,0      area=3, ind=0, am=1, be=0, %b[74]
          movaqp,1      area=2, ind=0, am=1, be=0, %b[75]
          movaqp,2      area=3, ind=0, am=1, be=0, %b[61]
          movaqp,3      area=2, ind=0, am=1, be=0, %b[63]
        }
        {
          loop_mode
          addd,0,sm     %b[2], 0x1, %b[0]
          qppermb,1,sm  %b[64], %b[64], %r0, %b[28]
          stqp,2        %r31, %b[34], %b[28]
          ord,3,sm      %b[56], %b[54], %b[54]
          qppermb,4,sm  %b[62], %b[62], %r0, %b[21]
          stqp,5        %r32, %b[34], %b[21]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[42]
          movaqp,1      area=0, ind=0, am=1, be=0, %b[50]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[37]
          movaqp,3      area=0, ind=0, am=1, be=0, %b[45]
        }
        {
          loop_mode
          bitrevd,0,sm  %b[2], %b[54]
          qppermb,1,sm  %b[60], %b[60], %r0, %b[25]
          stqp,2        %r33, %b[34], %b[32]
          shld,3,sm     %b[54], 0x4, %b[32]
          qppermb,4,sm  %b[58], %b[58], %r0, %b[2]
          stqp,5        %r34, %b[34], %b[25]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[47], %b[47], %r0, %b[52]
          stqp,2        %r35, %b[34], %b[29]
          qppermb,3,sm  %b[52], %b[52], %r0, %b[56]
          stqp,5        %r36, %b[34], %b[6]
        }

        ...

.L9337:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=17, incr=0, ind=0, asz=1, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=16, incr=0, ind=0, asz=1, abs=0, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=15, incr=0, ind=0, asz=1, abs=2, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=14, incr=0, ind=0, asz=1, abs=2, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=13, incr=0, ind=0, asz=1, abs=4, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=12, incr=0, ind=0, asz=1, abs=4, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=11, incr=0, ind=0, asz=1, abs=6, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=10, incr=0, ind=0, asz=1, abs=6, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=9, incr=0, ind=0, asz=1, abs=8, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=8, incr=0, ind=0, asz=1, abs=8, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=7, incr=0, ind=0, asz=1, abs=10, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=6, incr=0, ind=0, asz=1, abs=10, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=5, incr=0, ind=0, asz=1, abs=12, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=4, incr=0, ind=0, asz=1, abs=12, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=3, incr=0, ind=0, asz=1, abs=14, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=2, incr=0, ind=0, asz=1, abs=14, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=1, incr=0, ind=0, asz=1, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=15, asz=1, abs=16, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=14, asz=1, abs=18, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=13, asz=1, abs=18, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=12, asz=1, abs=20, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=11, asz=1, abs=20, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=10, asz=1, abs=22, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=9, asz=1, abs=22, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=8, asz=1, abs=24, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=7, asz=1, abs=24, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=6, asz=1, abs=26, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=5, asz=1, abs=26, disp=0
        }
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=4, asz=1, abs=28, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=3, asz=1, abs=28, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=2, asz=1, abs=30, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=16, d=0, incr=0, ind=1, asz=1, abs=30, disp=0
        }
.L7373:
        {
          loop_mode
          qppermb,0,sm  %b[41], %b[41], %r0, %b[58]
          shr_andd,1,sm %b[56], %r1, %r38, %b[54]
          stqp,2        %r5, %b[34], %b[54]
          qppermb,3,sm  %b[46], %b[46], %r0, %b[60]
          shr_andd,4,sm %b[56], %r4, %r37, %b[56]
          stqp,5        %r2, %b[34], %b[58]
        }
        {
          loop_mode
          qppermb,1,sm  %b[76], %b[76], %r0, %b[1]
          stqp,2        %r7, %b[34], %b[58]
          qppermb,4,sm  %b[77], %b[77], %r0, %b[8]
          stqp,5        %r6, %b[34], %b[60]
        }
        {
          loop_mode
          qppermb,1,sm  %b[65], %b[65], %r0, %b[10]
          stqp,2        %r11, %b[34], %b[3]
          qppermb,4,sm  %b[63], %b[63], %r0, %b[3]
          stqp,5        %r9, %b[34], %b[10]
        }
        {
          loop_mode
          qppermb,1,sm  %b[75], %b[75], %r0, %b[12]
          stqp,2        %r10, %b[34], %b[12]
          qppermb,4,sm  %b[74], %b[74], %r0, %b[5]
          stqp,5        %r12, %b[34], %b[5]
        }
        {
          loop_mode
          qppermb,1,sm  %b[73], %b[73], %r0, %b[14]
          stqp,2        %r13, %b[34], %b[14]
          qppermb,4,sm  %b[72], %b[72], %r0, %b[7]
          stqp,5        %r14, %b[34], %b[7]
        }
        {
          loop_mode
          qppermb,1,sm  %b[71], %b[71], %r0, %b[16]
          stqp,2        %r15, %b[34], %b[16]
          qppermb,4,sm  %b[70], %b[70], %r0, %b[9]
          stqp,5        %r16, %b[34], %b[9]
        }
        {
          loop_mode
          qppermb,1,sm  %b[69], %b[69], %r0, %b[18]
          stqp,2        %r17, %b[34], %b[18]
          qppermb,4,sm  %b[67], %b[67], %r0, %b[11]
          stqp,5        %r18, %b[34], %b[11]
          movaqp,0      area=15, ind=0, am=1, be=0, %b[60]
          movaqp,1      area=14, ind=0, am=1, be=0, %b[64]
          movaqp,2      area=15, ind=0, am=1, be=0, %b[58]
          movaqp,3      area=14, ind=0, am=1, be=0, %b[62]
        }
        {
          loop_mode
          qppermb,1,sm  %b[68], %b[68], %r0, %b[36]
          stqp,2        %r19, %b[34], %b[20]
          qppermb,4,sm  %b[61], %b[61], %r0, %b[31]
          stqp,5        %r20, %b[34], %b[13]
          movaqp,0      area=13, ind=0, am=1, be=0, %b[63]
          movaqp,1      area=12, ind=0, am=1, be=0, %b[20]
          movaqp,2      area=13, ind=0, am=1, be=0, %b[61]
          movaqp,3      area=12, ind=0, am=1, be=0, %b[13]
        }
        {
          loop_mode
          qppermb,1,sm  %b[59], %b[59], %r0, %b[53]
          stqp,2        %r21, %b[34], %b[38]
          qppermb,4,sm  %b[57], %b[57], %r0, %b[49]
          stqp,5        %r22, %b[34], %b[33]
          movaqp,0      area=11, ind=0, am=1, be=0, %b[38]
          movaqp,1      area=10, ind=0, am=1, be=0, %b[46]
          movaqp,2      area=11, ind=0, am=1, be=0, %b[33]
          movaqp,3      area=10, ind=0, am=1, be=0, %b[41]
        }
        {
          loop_mode
          qppermb,1,sm  %b[48], %b[48], %r0, %b[48]
          stqp,2        %r23, %b[34], %b[55]
          qppermb,4,sm  %b[43], %b[43], %r0, %b[43]
          stqp,5        %r24, %b[34], %b[51]
          movaqp,0      area=9, ind=0, am=1, be=0, %b[57]
          movaqp,1      area=8, ind=0, am=1, be=0, %b[66]
          movaqp,2      area=9, ind=0, am=1, be=0, %b[55]
          movaqp,3      area=8, ind=0, am=1, be=0, %b[59]
        }
        {
          loop_mode
          qppermb,1,sm  %b[40], %b[40], %r0, %b[40]
          stqp,2        %r25, %b[34], %b[50]
          qppermb,4,sm  %b[35], %b[35], %r0, %b[35]
          stqp,5        %r26, %b[34], %b[45]
          movaqp,0      area=7, ind=0, am=1, be=0, %b[67]
          movaqp,1      area=6, ind=0, am=1, be=0, %b[69]
          movaqp,2      area=7, ind=0, am=1, be=0, %b[65]
          movaqp,3      area=6, ind=0, am=1, be=0, %b[68]
        }
        {
          loop_mode
          qppermb,1,sm  %b[22], %b[22], %r0, %b[22]
          stqp,2        %r27, %b[34], %b[42]
          qppermb,4,sm  %b[15], %b[15], %r0, %b[15]
          stqp,5        %r28, %b[34], %b[37]
          movaqp,0      area=5, ind=0, am=1, be=0, %b[71]
          movaqp,1      area=4, ind=0, am=1, be=0, %b[73]
          movaqp,2      area=5, ind=0, am=1, be=0, %b[70]
          movaqp,3      area=4, ind=0, am=1, be=0, %b[72]
        }
        {
          loop_mode
          qppermb,1,sm  %b[63], %b[63], %r0, %b[24]
          stqp,2        %r29, %b[34], %b[24]
          qppermb,4,sm  %b[61], %b[61], %r0, %b[17]
          stqp,5        %r30, %b[34], %b[17]
          movaqp,0      area=3, ind=0, am=1, be=0, %b[74]
          movaqp,1      area=2, ind=0, am=1, be=0, %b[75]
          movaqp,2      area=3, ind=0, am=1, be=0, %b[61]
          movaqp,3      area=2, ind=0, am=1, be=0, %b[63]
        }
        {
          loop_mode
          addd,0,sm     %b[2], 0x1, %b[0]
          qppermb,1,sm  %b[64], %b[64], %r0, %b[28]
          stqp,2        %r31, %b[34], %b[28]
          ord,3,sm      %b[56], %b[54], %b[54]
          qppermb,4,sm  %b[62], %b[62], %r0, %b[21]
          stqp,5        %r32, %b[34], %b[21]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[42]
          movaqp,1      area=0, ind=0, am=1, be=0, %b[50]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[37]
          movaqp,3      area=0, ind=0, am=1, be=0, %b[45]
        }
        {
          loop_mode
          bitrevd,0,sm  %b[2], %b[54]
          qppermb,1,sm  %b[60], %b[60], %r0, %b[25]
          stqp,2        %r33, %b[34], %b[32]
          shld,3,sm     %b[54], 0x4, %b[32]
          qppermb,4,sm  %b[58], %b[58], %r0, %b[2]
          stqp,5        %r34, %b[34], %b[25]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[47], %b[47], %r0, %b[52]
          stqp,2        %r35, %b[34], %b[29]
          qppermb,3,sm  %b[52], %b[52], %r0, %b[56]
          stqp,5        %r36, %b[34], %b[6]
        }

void reverse_radix4_vector4(int bit_count_in, myComplex *data_in, myComplex4 *data_out)
{
	int bit_count_out = bit_count_in - 2;

//	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in = (__v2di*)data_in;

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out; ++i)
	{
		uint64_t rev = __builtin_e2k_bitrevd(i);
		int64_t offset = 32 * (((rev>>(shift_out-1)) & 0xAAAAAAAAAAAAAAAA) | ((rev>>(shift_out+1)) & 0x5555555555555555));
		__v2di mask_real = {0x0B0A090803020100, 0x1B1A191813121110};
		__v2di mask_imag = {0x0F0E0D0C07060504, 0x1F1E1D1C17161514};
		*(__v2du*)((void*)data_out + offset + 0*16) = __builtin_e2k_qppermb(in[2*i+1], in[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 1*16) = __builtin_e2k_qppermb(in[2*i+1], in[2*i+0], mask_imag);
	}
}

.L6561:
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=5, abs=0, disp=0
        }
.L6351:
        {
          loop_mode
          qppermb,0,sm  %b[15], %b[12], %r4, %b[19]
          shr_andd,1,sm %b[14], %r6, %r10, %b[0]
          qppermb,3,sm  %b[15], %b[12], %r5, %b[20]
          shr_andd,4,sm %b[16], %r7, %r9, %b[5]
          ord,5,sm      %b[7], %b[4], %b[18]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          bitrevd,0,sm  %b[3], %b[12]
          stqp,2        %r0, %b[17], %b[19]
          addd,3,sm     %b[3], 0x1, %b[1]
          shld,4,sm     %b[18], 0x5, %b[15]
          stqp,5        %r2, %b[17], %b[20]
          movaqp,0      area=0, ind=0, am=1, be=0, %b[4]
          movaqp,1      area=0, ind=16, am=0, be=0, %b[7]
        }

void reverse_radix4_vector4_x4(int bit_count_in, myComplex *data_in, myComplex4 *data_out)
{
	int bit_count_out = bit_count_in - 2;

//	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in    = (__v2di*) data_in;
	__v2di *out_0 = (__v2di*)&data_out[0 * count_out/4];
	__v2di *out_1 = (__v2di*)&data_out[1 * count_out/4];
	__v2di *out_2 = (__v2di*)&data_out[2 * count_out/4];
	__v2di *out_3 = (__v2di*)&data_out[3 * count_out/4];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out; i += 4)
	{
		uint64_t rev = __builtin_e2k_bitrevd(i);
		int64_t offset = 32 * (((rev>>(shift_out-1)) & 0xAAAAAAAAAAAAAAAA) | ((rev>>(shift_out+1)) & 0x5555555555555555));
		__v2di mask_real = {0x0B0A090803020100, 0x1B1A191813121110};
		__v2di mask_imag = {0x0F0E0D0C07060504, 0x1F1E1D1C17161514};
		*(__v2du*)((void*)out_0 + offset + 0*16) = __builtin_e2k_qppermb(in[2*(i+0)+1], in[2*(i+0)+0], mask_real);
		*(__v2du*)((void*)out_0 + offset + 1*16) = __builtin_e2k_qppermb(in[2*(i+0)+1], in[2*(i+0)+0], mask_imag);
		*(__v2du*)((void*)out_1 + offset + 0*16) = __builtin_e2k_qppermb(in[2*(i+1)+1], in[2*(i+1)+0], mask_real);
		*(__v2du*)((void*)out_1 + offset + 1*16) = __builtin_e2k_qppermb(in[2*(i+1)+1], in[2*(i+1)+0], mask_imag);
		*(__v2du*)((void*)out_2 + offset + 0*16) = __builtin_e2k_qppermb(in[2*(i+2)+1], in[2*(i+2)+0], mask_real);
		*(__v2du*)((void*)out_2 + offset + 1*16) = __builtin_e2k_qppermb(in[2*(i+2)+1], in[2*(i+2)+0], mask_imag);
		*(__v2du*)((void*)out_3 + offset + 0*16) = __builtin_e2k_qppermb(in[2*(i+3)+1], in[2*(i+3)+0], mask_real);
		*(__v2du*)((void*)out_3 + offset + 1*16) = __builtin_e2k_qppermb(in[2*(i+3)+1], in[2*(i+3)+0], mask_imag);
	}
}

.L7192:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=4, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=4, abs=0, disp=32
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=4, abs=16, disp=64
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=4, abs=16, disp=96
        }
.L6608:
        {
          loop_mode
          qppermb,0,sm  %b[23], %b[9], %r11, %b[35]
          stqp,2        %r0, %b[33], %b[22]
          qppermb,3,sm  %b[23], %b[9], %r13, %b[36]
          shr_andd,4,sm %b[12], %r14, %r16, %b[1]
          stqp,5        %r2, %b[33], %b[25]
        }
        {
          loop_mode
          ord,0,sm      %b[17], %b[3], %b[23]
          qppermb,1,sm  %b[15], %b[10], %r11, %b[37]
          stqp,2        %r4, %b[33], %b[35]
          qppermb,4,sm  %b[28], %b[20], %r13, %b[38]
          stqp,5        %r10, %b[33], %b[36]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[14]
          movaqp,1      area=1, ind=16, am=0, be=0, %b[22]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[4]
          movaqp,3      area=1, ind=16, am=0, be=0, %b[9]
        }
        {
          loop_mode
          shld,0,sm     %b[23], 0x5, %b[31]
          qppermb,1,sm  %b[28], %b[20], %r11, %b[36]
          stqp,2        %r6, %b[33], %b[37]
          addd,3,sm     %b[2], 0x4, %b[0]
          qppermb,4,sm  %b[15], %b[10], %r13, %b[35]
          stqp,5        %r9, %b[33], %b[38]
          movaqp,0      area=0, ind=0, am=1, be=0, %b[25]
          movaqp,1      area=0, ind=16, am=0, be=0, %b[30]
          movaqp,2      area=0, ind=0, am=1, be=0, %b[3]
          movaqp,3      area=0, ind=16, am=0, be=0, %b[17]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[34], %b[29], %r11, %b[20]
          shr_andd,1,sm %b[12], %r12, %r15, %b[15]
          stqp,2        %r5, %b[33], %b[36]
          qppermb,3,sm  %b[34], %b[29], %r13, %b[23]
          bitrevd,4,sm  %b[2], %b[10]
          stqp,5        %r7, %b[33], %b[35]
        }

void reverse_radix4_vector4_stream4(int bit_count_in, myComplex *data_in, myComplex4 *data_out)
{
	int bit_count_out = bit_count_in - 2;

	int count_in  = 1 << bit_count_in;
	int count_out = 1 << bit_count_out;
	int shift_out = 64 - bit_count_out;

	__v2di *in_0 = (__v2di*)&data_in[0 * count_in/4];
	__v2di *in_1 = (__v2di*)&data_in[1 * count_in/4];
	__v2di *in_2 = (__v2di*)&data_in[2 * count_in/4];
	__v2di *in_3 = (__v2di*)&data_in[3 * count_in/4];

	#pragma ivdep
	#pragma unroll(1)
	#pragma prefetch
	for(int64_t i = 0; i < count_out/4; ++i)
	{
		uint64_t rev = __builtin_e2k_bitrevd(i);
		int64_t offset = 32 * (((rev>>(shift_out-1)) & 0xAAAAAAAAAAAAAAAA) | ((rev>>(shift_out+1)) & 0x5555555555555555));
		__v2di mask_real = {0x0B0A090803020100, 0x1B1A191813121110};
		__v2di mask_imag = {0x0F0E0D0C07060504, 0x1F1E1D1C17161514};
		*(__v2du*)((void*)data_out + offset + 0*16) = __builtin_e2k_qppermb(in_0[2*i+1], in_0[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 1*16) = __builtin_e2k_qppermb(in_0[2*i+1], in_0[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 2*16) = __builtin_e2k_qppermb(in_1[2*i+1], in_1[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 3*16) = __builtin_e2k_qppermb(in_1[2*i+1], in_1[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 4*16) = __builtin_e2k_qppermb(in_2[2*i+1], in_2[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 5*16) = __builtin_e2k_qppermb(in_2[2*i+1], in_2[2*i+0], mask_imag);
		*(__v2du*)((void*)data_out + offset + 6*16) = __builtin_e2k_qppermb(in_3[2*i+1], in_3[2*i+0], mask_real);
		*(__v2du*)((void*)data_out + offset + 7*16) = __builtin_e2k_qppermb(in_3[2*i+1], in_3[2*i+0], mask_imag);
	}
}

.L7740:
        {
          fapb  ct=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=4, asz=4, abs=0, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=3, asz=4, abs=0, disp=0
        }
        {
          fapb  ct=1, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=2, asz=4, abs=16, disp=0
          fapb  dpl=0, dcd=0, fmt=5, mrng=0, d=0, incr=1, ind=1, asz=4, abs=16, disp=0
        }
.L7235:
        {
          loop_mode
          qppermb,0,sm  %b[23], %b[9], %r11, %b[35]
          stqp,2        %r0, %b[33], %b[22]
          qppermb,3,sm  %b[23], %b[9], %r13, %b[36]
          shr_andd,4,sm %b[12], %r14, %r16, %b[1]
          stqp,5        %r2, %b[33], %b[25]
        }
        {
          loop_mode
          ord,0,sm      %b[17], %b[3], %b[23]
          qppermb,1,sm  %b[15], %b[10], %r11, %b[37]
          stqp,2        %r5, %b[33], %b[35]
          qppermb,4,sm  %b[28], %b[20], %r13, %b[38]
          stqp,5        %r4, %b[33], %b[36]
          movaqp,0      area=1, ind=0, am=1, be=0, %b[14]
          movaqp,1      area=1, ind=16, am=0, be=0, %b[22]
          movaqp,2      area=1, ind=0, am=1, be=0, %b[4]
          movaqp,3      area=1, ind=16, am=0, be=0, %b[9]
        }
        {
          loop_mode
          shld,0,sm     %b[23], 0x5, %b[31]
          qppermb,1,sm  %b[28], %b[20], %r11, %b[36]
          stqp,2        %r10, %b[33], %b[37]
          addd,3,sm     %b[2], 0x1, %b[0]
          qppermb,4,sm  %b[15], %b[10], %r13, %b[35]
          stqp,5        %r6, %b[33], %b[38]
          movaqp,0      area=0, ind=0, am=1, be=0, %b[25]
          movaqp,1      area=0, ind=16, am=0, be=0, %b[30]
          movaqp,2      area=0, ind=0, am=1, be=0, %b[3]
          movaqp,3      area=0, ind=16, am=0, be=0, %b[17]
        }
        {
          loop_mode
          alc   alcf=1, alct=1
          abn   abnf=1, abnt=1
          ct    %ctpr1 ? %NOT_LOOP_END
          qppermb,0,sm  %b[34], %b[29], %r11, %b[20]
          shr_andd,1,sm %b[12], %r12, %r15, %b[15]
          stqp,2        %r7, %b[33], %b[36]
          qppermb,3,sm  %b[34], %b[29], %r13, %b[23]
          bitrevd,4,sm  %b[2], %b[10]
          stqp,5        %r9, %b[33], %b[35]
        }