har0ke/FFmpeg
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix scalarproduct_and_madd_int16_altivec() for orders > 16

Browse Source 
the second and third sources were incremented only by half of the needed size
This commit is contained in:
Kostya Shishkov 2013-05-24 19:44:29 +02:00
parent 322e4194dd
commit 0418cbf081
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
libavcodec/ppc/int_altivec.c
View File

@ -129,8 +129,8 @@ static int32_t scalarproduct_and_madd_int16_altivec(int16_t *v1, const int16_t *
pv1[0] = vec_mladd(t0, muls, i0); pv1[0] = vec_mladd(t0, muls, i0);
pv1[1] = vec_mladd(t1, muls, i1); pv1[1] = vec_mladd(t1, muls, i1);
pv1 += 2; pv1 += 2;
v2 += 8; v2 += 16;
v3 += 8; v3 += 16;
} while(--order); } while(--order);
res = vec_splat(vec_sums(res, zero_s32v), 3); res = vec_splat(vec_sums(res, zero_s32v), 3);
vec_ste(res, 0, &ires); vec_ste(res, 0, &ires);