[x265] [PATCH] disable old interface SSE asm code, will be enabled after modification as per new interface
praveen at multicorewareinc.com
praveen at multicorewareinc.com
Tue Oct 28 13:12:44 CET 2014
# HG changeset patch
# User Praveen Tiwari
# Date 1414496512 -19800
# Node ID 1371d3e0f06331e5d01d74201846b66c1f4cc16b
# Parent 91cb96595a4b74addda32d543802cde9e9da6dfd
disable old interface SSE asm code, will be enabled after modification as per new interface
diff -r 91cb96595a4b -r 1371d3e0f063 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp Tue Oct 28 16:48:27 2014 +0530
+++ b/source/common/x86/asm-primitives.cpp Tue Oct 28 17:11:52 2014 +0530
@@ -1336,7 +1336,7 @@
p.sad_x4[LUMA_16x4] = x265_pixel_sad_x4_16x4_sse2;
p.sad_x4[LUMA_12x16] = x265_pixel_sad_x4_12x16_mmx2;
- p.cvt32to16_shr = x265_cvt32to16_shr_sse2;
+// p.cvt32to16_shr = x265_cvt32to16_shr_sse2;
p.cvt32to16_shl[BLOCK_4x4] = x265_cvt32to16_shl_4_sse2;
p.cvt32to16_shl[BLOCK_8x8] = x265_cvt32to16_shl_8_sse2;
p.cvt32to16_shl[BLOCK_16x16] = x265_cvt32to16_shl_16_sse2;
@@ -1374,9 +1374,9 @@
p.calcresidual[BLOCK_16x16] = x265_getResidual16_sse2;
p.calcresidual[BLOCK_32x32] = x265_getResidual32_sse2;
- p.dct[DCT_4x4] = x265_dct4_sse2;
- p.idct[IDCT_4x4] = x265_idct4_sse2;
- p.idct[IDST_4x4] = x265_idst4_sse2;
+// p.dct[DCT_4x4] = x265_dct4_sse2;
+// p.idct[IDCT_4x4] = x265_idct4_sse2;
+// p.idct[IDST_4x4] = x265_idst4_sse2;
LUMA_SS_FILTERS(_sse2);
}
@@ -1387,8 +1387,8 @@
INTRA_ANG_SSSE3(ssse3);
- p.dct[DST_4x4] = x265_dst4_ssse3;
- p.idct[IDCT_8x8] = x265_idct8_ssse3;
+// p.dct[DST_4x4] = x265_dst4_ssse3;
+// p.idct[IDCT_8x8] = x265_idct8_ssse3;
p.count_nonzero = x265_count_nonzero_ssse3;
}
if (cpuMask & X265_CPU_SSE4)
@@ -1403,11 +1403,11 @@
CHROMA_VERT_FILTERS_SSE4_422(_sse4);
CHROMA_HORIZ_FILTERS_444(_sse4);
- p.dct[DCT_8x8] = x265_dct8_sse4;
- p.quant = x265_quant_sse4;
- p.nquant = x265_nquant_sse4;
- p.dequant_normal = x265_dequant_normal_sse4;
- p.cvt16to32_shl = x265_cvt16to32_shl_sse4;
+// p.dct[DCT_8x8] = x265_dct8_sse4;
+// p.quant = x265_quant_sse4;
+// p.nquant = x265_nquant_sse4;
+// p.dequant_normal = x265_dequant_normal_sse4;
+// p.cvt16to32_shl = x265_cvt16to32_shl_sse4;
p.cvt16to32_shr[BLOCK_4x4] = x265_cvt16to32_shr_4_sse4;
p.cvt16to32_shr[BLOCK_8x8] = x265_cvt16to32_shr_8_sse4;
p.cvt16to32_shr[BLOCK_16x16] = x265_cvt16to32_shr_16_sse4;
@@ -1435,20 +1435,20 @@
}
if (cpuMask & X265_CPU_AVX2)
{
- p.dct[DCT_4x4] = x265_dct4_avx2;
- p.quant = x265_quant_avx2;
- p.nquant = x265_nquant_avx2;
- p.dequant_normal = x265_dequant_normal_avx2;
+ // p.dct[DCT_4x4] = x265_dct4_avx2;
+// p.quant = x265_quant_avx2;
+// p.nquant = x265_nquant_avx2;
+// p.dequant_normal = x265_dequant_normal_avx2;
p.scale1D_128to64 = x265_scale1D_128to64_avx2;
#if X86_64
- p.dct[DCT_8x8] = x265_dct8_avx2;
+/* p.dct[DCT_8x8] = x265_dct8_avx2;
p.dct[DCT_16x16] = x265_dct16_avx2;
p.dct[DCT_32x32] = x265_dct32_avx2;
p.idct[IDCT_4x4] = x265_idct4_avx2;
p.idct[IDCT_8x8] = x265_idct8_avx2;
p.idct[IDCT_16x16] = x265_idct16_avx2;
p.idct[IDCT_32x32] = x265_idct32_avx2;
-
+*/
p.transpose[BLOCK_8x8] = x265_transpose8_avx2;
p.transpose[BLOCK_16x16] = x265_transpose16_avx2;
p.transpose[BLOCK_32x32] = x265_transpose32_avx2;
More information about the x265-devel
mailing list