The diagnostic message is not clear when compiling this code from FFmpeg with
gcc-4.5 -c vsad_intra.c -O3 -ffast-math -ftree-vectorizer-verbose=7 -msse2
[...]
ac3_downmix.c:10: note: cost model: vector iteration cost = 2060 is divisible
by scalar iteration cost = 7 by a factor greater than or equal to the
vectorization factor = 4 .
ac3_downmix.c:10: note: not vectorized: vectorization not profitable.
[...]
ac3_downmix.c:20: note: cost model: vector iteration cost = 2056 is divisible
by scalar iteration cost = 4 by a factor greater than or equal to the
vectorization factor = 4 .
ac3_downmix.c:20: note: not vectorized: vectorization not profitable.
What does this message mean?
"vector iteration cost = 2056 is divisible by scalar iteration cost = 4 by a
factor greater than or equal to the vectorization factor = 4 ."
Is the vectorization not profitable?
Why?
typedef long int intptr_t;
void ff_ac3_downmix_c(float (*samples)[256], float (*matrix)[2], int out_ch,
int in_ch, int len)
{
int i, j;
float v0, v1;
if(out_ch == 2) {
for(i=0; i<len; i++) {
v0 = v1 = 0.0f;
for(j=0; j<in_ch; j++) {
v0 += samples[j][i] * matrix[j][0];
v1 += samples[j][i] * matrix[j][1];
}
samples[0][i] = v0;
samples[1][i] = v1;
}
} else if(out_ch == 1) {
for(i=0; i<len; i++) {
v0 = 0.0f;
for(j=0; j<in_ch; j++)
v0 += samples[j][i] * matrix[j][0];
samples[0][i] = v0;
}
}
}
--
Summary: Diagnostic message is not clear for vectorization
profitability analysis
Product: gcc
Version: 4.5.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
AssignedTo: unassigned at gcc dot gnu dot org
ReportedBy: spop at gcc dot gnu dot org
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=43431
