Commit 9b5bd665 authored by James Almer's avatar James Almer

x86/af_afir: fix processing the last element

ff_fcmul_add_sse3() is now identical to the C version.
Reviewed-by: 's avatarPaul B Mahol <onemda@gmail.com>
Signed-off-by: 's avatarJames Almer <jamrial@gmail.com>
parent 3ba5eef2
......@@ -30,7 +30,6 @@ SECTION .text
INIT_XMM sse3
cglobal fcmul_add, 4,4,6, sum, t, c, len
shl lend, 3
add lend, mmsize*2
add tq, lenq
add cq, lenq
add sumq, lenq
......@@ -57,4 +56,8 @@ ALIGN 16
movaps [sumq + lenq+mmsize], m3
add lenq, mmsize*2
jl .loop
REP_RET
movss xm0, [tq + lenq]
mulss xm0, [cq + lenq]
addss xm0, [sumq + lenq]
movss [sumq + lenq], xm0
RET
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment