# HG changeset patch # User Praveen Tiwari # Date 1383043010 -19800 # Node ID 35bbb8426fe828174d2866154953ef20cea16286 # Parent 3306252fb160dcabe2015a502572e9ad635e48a8 asm code for interp_4tap_vert_pp_24x32
diff -r 3306252fb160 -r 35bbb8426fe8 source/common/x86/ipfilter8.asm --- a/source/common/x86/ipfilter8.asm Tue Oct 29 14:52:06 2013 +0530 +++ b/source/common/x86/ipfilter8.asm Tue Oct 29 16:06:50 2013 +0530 @@ -1003,3 +1003,84 @@ %endmacro FILTER_V4_W6_H4 6, 8 + +;----------------------------------------------------------------------------- +;void interp_4tap_vert_pp_24x32(pixel *src, intptr_t srcStride, pixel *dst, intptr_t dstStride, int coeffIdx) +;----------------------------------------------------------------------------- +%macro FILTER_V4_W24 2 +INIT_XMM sse4 +cglobal interp_4tap_vert_pp_24x32, 4, 6, 8 + +mov r4d, r4m +sub r0, r1 + +%ifdef PIC +lea r5, [tab_ChromaCoeff] +movd m0, [r5 + r4 * 4] +%else +movd m0, [tab_ChromaCoeff + r4 * 4] +%endif + +pshufb m1, m0, [tab_Vm] +pshufb m0, [tab_Vm + 16] + +mova m7, [tab_c_512] + +mov r4d, %2 + +.loop +movu m2, [r0] +movu m3, [r0 + r1] + +punpcklbw m4, m2, m3, +punpckhbw m2, m3, + +pmaddubsw m4, m1 +pmaddubsw m2, m1 + +movu m5, [r0 + 2 * r1] +lea r5, [r0 + 2 * r1] +movu m3, [r5 + r1] + +punpcklbw m6, m5, m3, +punpckhbw m5, m3 + +pmaddubsw m6, m0 +pmaddubsw m5, m0 + +paddw m4, m6 +paddw m2, m5 + +pmulhrsw m4, m7 +pmulhrsw m2, m7 + +packuswb m4, m2 + +movu [r2], m4 + +movq m2, [r0 + 16] +movq m3, [r0 + r1 + 16] +movq m4, [r0 + 2 * r1 + 16] +movq m5, [r5 + r1 + 16] + +punpcklbw m2, m3 +punpcklbw m4, m5 + +pmaddubsw m2, m1 +pmaddubsw m4, m0 + +paddw m2, m4 + +pmulhrsw m2, m7 +packuswb m2, m2 +movh [r2 + 16], m2 + +lea r0, [r0 + r1] +lea r2, [r2 + r3] + +dec r4 +jnz .loop +RET +%endmacro + +FILTER_V4_W24 24, 32 _______________________________________________ x265-devel mailing list [email protected] https://mailman.videolan.org/listinfo/x265-devel
