[FFmpeg-cvslog] audiodsp: ppc: Add VSX variant

[Luca Barbato]

ffmpeg | branch: master | Luca Barbato <lu_zero at gentoo.org> | Sat Sep 10 18:12:23 2016 +0200| [caccb3a0cdc7ee32cbed7eab156d35025133eadc] | committer: Diego Biurrun

audiodsp: ppc: Add VSX variant

Signed-off-by: Luca Barbato <lu_zero at gentoo.org>
Signed-off-by: Diego Biurrun <diego at biurrun.de>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=caccb3a0cdc7ee32cbed7eab156d35025133eadc
---

 libavcodec/ppc/audiodsp.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/libavcodec/ppc/audiodsp.c b/libavcodec/ppc/audiodsp.c
index 2a0a6d8..289bb58 100644
--- a/libavcodec/ppc/audiodsp.c
+++ b/libavcodec/ppc/audiodsp.c
@@ -61,6 +61,31 @@ static int32_t scalarproduct_int16_altivec(const int16_t *v1, const int16_t *v2,
 
 #endif /* HAVE_ALTIVEC */
 
+#if HAVE_VSX
+
+static int32_t scalarproduct_int16_vsx(const int16_t *v1, const int16_t *v2, int order)
+{
+    int i;
+    LOAD_ZERO;
+    register vec_s16 vec1;
+    register vec_s32 res = vec_splat_s32(0), t;
+    int32_t ires;
+
+    for (i = 0; i < order; i += 8) {
+        vec1 = vec_vsx_ld(0, v1);
+        t    = vec_msum(vec1, vec_ld(0, v2), zero_s32v);
+        res  = vec_sums(t, res);
+        v1  += 8;
+        v2  += 8;
+    }
+    res = vec_splat(res, 3);
+    vec_ste(res, 0, &ires);
+
+    return ires;
+}
+
+#endif /* HAVE_VSX */
+
 av_cold void ff_audiodsp_init_ppc(AudioDSPContext *c)
 {
 #if HAVE_ALTIVEC && HAVE_BIGENDIAN
@@ -69,4 +94,11 @@ av_cold void ff_audiodsp_init_ppc(AudioDSPContext *c)
 
     c->scalarproduct_int16 = scalarproduct_int16_altivec;
 #endif /* HAVE_ALTIVEC */
+
+#if HAVE_VSX
+    if (!PPC_VSX(av_get_cpu_flags()))
+        return;
+
+    c->scalarproduct_int16 = scalarproduct_int16_vsx;
+#endif /* HAVE_VSX */
 }