@@ -2025,11 +2025,17 @@ static int vp4_mc_loop_filter(Vp3DecodeContext *s, int plane, int motion_x, int
plane_width,
plane_height);
+#define safe_loop_filter(name, ptr, stride, bounding_values) \
+ if ((uintptr_t)(ptr) & 7) \
+ s->vp3dsp.name##_unaligned(ptr, stride, bounding_values); \
+ else \
+ s->vp3dsp.name(ptr, stride, bounding_values);
+
if (x_offset)
- s->vp3dsp.h_loop_filter(loop + loop_stride + x_offset + 1, loop_stride, bounding_values);
+ safe_loop_filter(h_loop_filter, loop + loop_stride + x_offset + 1, loop_stride, bounding_values);
if (y_offset)
- s->vp3dsp.v_loop_filter(loop + (y_offset + 1)*loop_stride + 1, loop_stride, bounding_values);
+ safe_loop_filter(v_loop_filter, loop + (y_offset + 1)*loop_stride + 1, loop_stride, bounding_values);
}
for (i = 0; i < 9; i++)
@@ -449,8 +449,8 @@ av_cold void ff_vp3dsp_init(VP3DSPContext *c, int flags)
c->idct_put = vp3_idct_put_c;
c->idct_add = vp3_idct_add_c;
c->idct_dc_add = vp3_idct_dc_add_c;
- c->v_loop_filter = vp3_v_loop_filter_8_c;
- c->h_loop_filter = vp3_h_loop_filter_8_c;
+ c->v_loop_filter = c->v_loop_filter_unaligned = vp3_v_loop_filter_8_c;
+ c->h_loop_filter = c->h_loop_filter_unaligned = vp3_h_loop_filter_8_c;
if (ARCH_ARM)
ff_vp3dsp_init_arm(c, flags);
@@ -43,6 +43,8 @@ typedef struct VP3DSPContext {
void (*idct_dc_add)(uint8_t *dest, ptrdiff_t stride, int16_t *block);
void (*v_loop_filter)(uint8_t *src, ptrdiff_t stride, int *bounding_values);
void (*h_loop_filter)(uint8_t *src, ptrdiff_t stride, int *bounding_values);
+ void (*v_loop_filter_unaligned)(uint8_t *src, ptrdiff_t stride, int *bounding_values);
+ void (*h_loop_filter_unaligned)(uint8_t *src, ptrdiff_t stride, int *bounding_values);
} VP3DSPContext;
void ff_vp3dsp_v_loop_filter_12(uint8_t *first_pixel, ptrdiff_t stride, int *bounding_values);
@@ -59,8 +59,8 @@ av_cold void ff_vp3dsp_init_x86(VP3DSPContext *c, int flags)
c->idct_dc_add = ff_vp3_idct_dc_add_mmxext;
if (!(flags & AV_CODEC_FLAG_BITEXACT)) {
- c->v_loop_filter = ff_vp3_v_loop_filter_mmxext;
- c->h_loop_filter = ff_vp3_h_loop_filter_mmxext;
+ c->v_loop_filter = c->v_loop_filter_unaligned = ff_vp3_v_loop_filter_mmxext;
+ c->h_loop_filter = c->v_loop_filter_unaligned = ff_vp3_h_loop_filter_mmxext;
}
}