[x265] [PATCH 255 of 307] x86: AVX512 luma_hvpp

[mythreyi at multicorewareinc.com]

# HG changeset patch
# User Vignesh Vijayakumar<vignesh at multicorewareinc.com>
# Date 1513072665 -19800
#      Tue Dec 12 15:27:45 2017 +0530
# Node ID 9ca6f6a66eabf5bfdecc3a8472c1137d16b1c722
# Parent  b858f80e3ff03118abb1ef3e4ea56059f9ec5af4
x86: AVX512 luma_hvpp

Calling interp_8tap_hv_pp_cpu C function(which calls luma_hps and luma_vsp asm functions individually)
Including ALL_LUMA_PU_T for luma_hvpp which calls interp_8tap_hv_pp_cpu C function.

diff -r b858f80e3ff0 -r 9ca6f6a66eab source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Tue Dec 12 15:44:55 2017 +0530
+++ b/source/common/x86/asm-primitives.cpp	Tue Dec 12 15:27:45 2017 +0530
@@ -3056,6 +3056,23 @@
         p.chroma[X265_CSP_I422].pu[CHROMA_422_32x16].satd = PFX(pixel_satd_32x16_avx512);
         p.cu[BLOCK_32x32].intra_pred[DC_IDX] = PFX(intra_pred_dc32_avx512);
 
+        p.pu[LUMA_64x64].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_64x64>;
+        p.pu[LUMA_64x48].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_64x48>;
+        p.pu[LUMA_64x32].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_64x32>;
+        p.pu[LUMA_64x16].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_64x16>;
+        p.pu[LUMA_32x8].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_32x8>;
+        p.pu[LUMA_32x16].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_32x16>;
+        p.pu[LUMA_32x32].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_32x32>;
+        p.pu[LUMA_32x24].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_32x24>;
+        p.pu[LUMA_32x64].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_32x64>;
+        p.pu[LUMA_16x4].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_16x4>;
+        p.pu[LUMA_16x8].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_16x8>;
+        p.pu[LUMA_16x12].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_16x12>;
+        p.pu[LUMA_16x16].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_16x16>;
+        p.pu[LUMA_16x32].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_16x32>;
+        p.pu[LUMA_16x64].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_16x64>;
+        p.pu[LUMA_48x64].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_48x64>;
+
     }
 #endif
 }
@@ -5220,6 +5237,24 @@
         p.pu[LUMA_16x16].luma_vps = PFX(interp_8tap_vert_ps_16x16_avx512);
         p.pu[LUMA_16x32].luma_vps = PFX(interp_8tap_vert_ps_16x32_avx512);
         //p.pu[LUMA_16x64].luma_vps = PFX(interp_8tap_vert_ps_16x64_avx512);
+
+        p.pu[LUMA_64x64].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_64x64>;
+        p.pu[LUMA_64x48].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_64x48>;
+        p.pu[LUMA_64x32].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_64x32>;
+        p.pu[LUMA_64x16].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_64x16>;
+        p.pu[LUMA_32x8].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_32x8>;
+        p.pu[LUMA_32x16].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_32x16>;
+        p.pu[LUMA_32x32].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_32x32>;
+        p.pu[LUMA_32x24].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_32x24>;
+        p.pu[LUMA_32x64].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_32x64>;
+        p.pu[LUMA_16x4].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_16x4>;
+        p.pu[LUMA_16x8].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_16x8>;
+        p.pu[LUMA_16x12].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_16x12>;
+        p.pu[LUMA_16x16].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_16x16>;
+        p.pu[LUMA_16x32].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_16x32>;
+        p.pu[LUMA_16x64].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_16x64>;
+        p.pu[LUMA_48x64].luma_hvpp = interp_8tap_hv_pp_cpu<LUMA_48x64>;
+
     }
 #endif
 }