auto vectorizer makes code run slower #28502
Description
| Bugzilla Link | 28128 |
| Version | 3.9 |
| OS | All |
| Reporter | LLVM Bugzilla Contributor |
| CC | @hfinkel,@RKSimon |
Extended Description
#include <stdlib.h>
#include <stdio.h>
#include <time.h>
void tik()
{
static clock_t start, end;
static int flag = 0;
static float elapsed_time;
if (flag == 0) {
start = clock();
} else {
end = clock();
elapsed_time = (float)(end - start) / (float)CLOCKS_PER_SEC;
printf("Elapsed time: %f seconds\n", elapsed_time);
}
flag = 1 - flag;
}
typedef unsigned int uint;
static uint i_max = 64 * 1024 * 1024;
void test()
{
static uint acc[2] = {1, 1};
tik();
for (uint i = 0; i < i_max; ++i) {
acc[0] *= 3;
}
tik();
acc[0] = acc[1] = 1;
tik();
for (uint i = 0; i < i_max; ++i) {
acc[0] *= 3;
acc[1] *= 3;
}
tik();
acc[0] = acc[1] = 1;
tik();
#pragma clang loop vectorize(disable)
for (uint i = 0; i < i_max; ++i) {
acc[0] *= 3;
acc[1] *= 3;
}
tik();
acc[0] = acc[1] = 1;
tik();
for (uint i = 0; i < i_max; ++i) {
acc[0] *= 3;
}
for (uint i = 0; i < i_max; ++i) {
acc[1] *= 3;
}
tik();
}
int main (int argc, char** argv) {
test();
return 0;
}
Output:
$ clang -O vector.c; ./a.out
Elapsed time: 0.003569 seconds
Elapsed time: 0.011365 seconds
Elapsed time: 0.008421 seconds
Elapsed time: 0.005950 seconds
I was expecting the second case run ~2x slower than the first one, for it's doing twice much work. The forth case's runtime is more reasonable.
ENV:
clang: 3.8.1-svn271127-1~exp1 (branches/release_38)
OS: xubuntu 14.04
CPU: Intel(R) Core(TM) i7-4600U CPU @ 2.10GHz