/* { dg-require-effective-target vect_int } */
|
/* { dg-require-effective-target vect_int } */
|
|
|
#include <stdarg.h>
|
#include <stdarg.h>
|
#include <stdio.h>
|
#include <stdio.h>
|
#include "tree-vect.h"
|
#include "tree-vect.h"
|
|
|
#define M00 100
|
#define M00 100
|
#define M10 216
|
#define M10 216
|
#define M20 23
|
#define M20 23
|
#define M01 1322
|
#define M01 1322
|
#define M11 13
|
#define M11 13
|
#define M21 27271
|
#define M21 27271
|
#define M02 74
|
#define M02 74
|
#define M12 191
|
#define M12 191
|
#define M22 500
|
#define M22 500
|
|
|
#define K00 405
|
#define K00 405
|
#define K10 112
|
#define K10 112
|
#define K01 4322
|
#define K01 4322
|
#define K11 135
|
#define K11 135
|
|
|
#define N 16
|
#define N 16
|
|
|
/* SLP with load permutation and loop-based vectorization. */
|
/* SLP with load permutation and loop-based vectorization. */
|
void foo (int *__restrict__ pInput, int *__restrict__ pOutput,
|
void foo (int *__restrict__ pInput, int *__restrict__ pOutput,
|
int *__restrict__ pInput2, int *__restrict__ pOutput2)
|
int *__restrict__ pInput2, int *__restrict__ pOutput2)
|
{
|
{
|
int i, a, b, c, d;
|
int i, a, b, c, d;
|
|
|
for (i = 0; i < N / 3; i++)
|
for (i = 0; i < N / 3; i++)
|
{
|
{
|
a = *pInput++;
|
a = *pInput++;
|
b = *pInput++;
|
b = *pInput++;
|
c = *pInput++;
|
c = *pInput++;
|
d = *pInput2++;
|
d = *pInput2++;
|
|
|
*pOutput++ = M00 * a + M01 * b + M02 * c;
|
*pOutput++ = M00 * a + M01 * b + M02 * c;
|
*pOutput++ = M10 * a + M11 * b + M12 * c;
|
*pOutput++ = M10 * a + M11 * b + M12 * c;
|
*pOutput++ = M20 * a + M21 * b + M22 * c;
|
*pOutput++ = M20 * a + M21 * b + M22 * c;
|
|
|
/* Loop-based vectorization. */
|
/* Loop-based vectorization. */
|
*pOutput2++ = K00 * d;
|
*pOutput2++ = K00 * d;
|
}
|
}
|
}
|
}
|
|
|
int main (int argc, const char* argv[])
|
int main (int argc, const char* argv[])
|
{
|
{
|
int input[N], output[N], i;
|
int input[N], output[N], i;
|
int check_results[N] = {1470, 395, 28271, 5958, 1655, 111653, 10446, 2915, 195035, 14934, 4175, 278417, 19422, 5435, 361799, 0};
|
int check_results[N] = {1470, 395, 28271, 5958, 1655, 111653, 10446, 2915, 195035, 14934, 4175, 278417, 19422, 5435, 361799, 0};
|
int input2[N], output2[N];
|
int input2[N], output2[N];
|
int check_results2[N] = {0, 405, 810, 1215, 1620, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
|
int check_results2[N] = {0, 405, 810, 1215, 1620, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
|
|
|
check_vect ();
|
check_vect ();
|
|
|
for (i = 0; i < N; i++)
|
for (i = 0; i < N; i++)
|
{
|
{
|
input[i] = i%256;
|
input[i] = i%256;
|
input2[i] = i%256;
|
input2[i] = i%256;
|
output[i] = 0;
|
output[i] = 0;
|
output2[i] = 0;
|
output2[i] = 0;
|
if (input[i] > 200)
|
if (input[i] > 200)
|
abort ();
|
abort ();
|
}
|
}
|
|
|
foo (input, output, input2, output2);
|
foo (input, output, input2, output2);
|
|
|
for (i = 0; i < N; i++)
|
for (i = 0; i < N; i++)
|
if (output[i] != check_results[i] || output2[i] != check_results2[i])
|
if (output[i] != check_results[i] || output2[i] != check_results2[i])
|
abort ();
|
abort ();
|
|
|
return 0;
|
return 0;
|
}
|
}
|
|
|
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_perm } } } */
|
/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_perm } } } */
|
/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { target vect_perm } } } */
|
/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { target vect_perm } } } */
|
/* { dg-final { cleanup-tree-dump "vect" } } */
|
/* { dg-final { cleanup-tree-dump "vect" } } */
|
|
|
|
|
|
|