comparison x86/vp8dsp.asm @ 12194:80b142c2e9f7 libavcodec

Change function prototypes for width=8 inner and mbedge loopfilter functions so that it does both U and V planes at the same time. This will have speed advantages when using SSE2 (or higher) optimizations, since we can do both the U and V rows together in a single xmm register. This also renames filter16 to filter16y and filter8 to filter8uv so that it's more obvious what each function is used for.

12193:0a63bed2a00e

; void vp8_h/v_loop_filter<size>_inner_<opt>(uint8_t *dst, int stride,
;                                            int flimE, int flimI, int hev_thr);
;-----------------------------------------------------------------------------

%macro INNER_LOOPFILTER 4
cglobal vp8_%2_loop_filter16_inner_%1, 5, %3, %4
%define dst_reg     r0
%define mstride_reg r1
%define E_reg       r2
%define I_reg       r3
%define hev_thr_reg r4

12194:80b142c2e9f7

; void vp8_h/v_loop_filter<size>_inner_<opt>(uint8_t *dst, int stride,
;                                            int flimE, int flimI, int hev_thr);
;-----------------------------------------------------------------------------

%macro INNER_LOOPFILTER 4
cglobal vp8_%2_loop_filter16y_inner_%1, 5, %3, %4
%define dst_reg     r0
%define mstride_reg r1
%define E_reg       r2
%define I_reg       r3
%define hev_thr_reg r4