[x265-commits] [x265] motion: remove NULL checks prior to X265_FREE calls
Steve Borho
steve at borho.org
Sat Oct 5 22:05:06 CEST 2013
details: http://hg.videolan.org/x265/rev/cb6b3038a1e6
branches:
changeset: 4212:cb6b3038a1e6
user: Steve Borho <steve at borho.org>
date: Fri Oct 04 16:01:15 2013 -0500
description:
motion: remove NULL checks prior to X265_FREE calls
Subject: [x265] motion: use new pixelavg_pp primitive for lowres QPEL pixel generation
details: http://hg.videolan.org/x265/rev/7976c35f5b76
branches:
changeset: 4213:7976c35f5b76
user: Steve Borho <steve at borho.org>
date: Fri Oct 04 16:02:01 2013 -0500
description:
motion: use new pixelavg_pp primitive for lowres QPEL pixel generation
Subject: [x265] use x264 pixel average assembly routines for bidir and lowres QPEL
details: http://hg.videolan.org/x265/rev/84d0f4f907f7
branches:
changeset: 4214:84d0f4f907f7
user: Steve Borho <steve at borho.org>
date: Fri Oct 04 17:01:07 2013 -0500
description:
use x264 pixel average assembly routines for bidir and lowres QPEL
This required adding a weight parameter and re-ordering arguments. Bidir might
eventually use the weighting feature so this didn't seem like a bad trade-off.
This commit naively pulls in all of mc-a.asm from x264 for just this one
set of assembly functions.
Subject: [x265] fix bug on SAO initialize
details: http://hg.videolan.org/x265/rev/46a901ac1aff
branches:
changeset: 4215:46a901ac1aff
user: Min Chen <chenm003 at 163.com>
date: Sat Oct 05 14:46:26 2013 +0800
description:
fix bug on SAO initialize
Subject: [x265] pixel: use unaligned loads for reference pixels in sad_24
details: http://hg.videolan.org/x265/rev/bee7275174f1
branches:
changeset: 4216:bee7275174f1
user: Steve Borho <steve at borho.org>
date: Sat Oct 05 15:00:07 2013 -0500
description:
pixel: use unaligned loads for reference pixels in sad_24
Subject: [x265] pixel: fix typo which was copied and pasted 36 times
details: http://hg.videolan.org/x265/rev/fbfa3a5c5ae8
branches:
changeset: 4217:fbfa3a5c5ae8
user: Steve Borho <steve at borho.org>
date: Sat Oct 05 15:04:28 2013 -0500
description:
pixel: fix typo which was copied and pasted 36 times
diffstat:
source/Lib/TLibEncoder/TEncSearch.cpp | 4 +-
source/common/pixel.cpp | 2 +-
source/common/primitives.h | 2 +-
source/common/vec/pixel-sse41.cpp | 153 +-
source/common/x86/CMakeLists.txt | 2 +-
source/common/x86/asm-primitives.cpp | 25 +
source/common/x86/mc-a.asm | 2132 +++++++++++++++++++++++++++++++++
source/encoder/framefilter.cpp | 5 +-
source/encoder/motion.cpp | 15 +-
9 files changed, 2244 insertions(+), 96 deletions(-)
diffs (truncated from 2745 to 300 lines):
diff -r 4ee217cd64cc -r fbfa3a5c5ae8 source/Lib/TLibEncoder/TEncSearch.cpp
--- a/source/Lib/TLibEncoder/TEncSearch.cpp Fri Oct 04 15:30:31 2013 -0500
+++ b/source/Lib/TLibEncoder/TEncSearch.cpp Sat Oct 05 15:04:28 2013 -0500
@@ -2428,7 +2428,7 @@ void TEncSearch::predInterSearch(TComDat
pixel avg[MAX_CU_SIZE * MAX_CU_SIZE];
int partEnum = PartitionFromSizes(roiWidth, roiHeight);
- primitives.pixelavg_pp[partEnum](avg, roiWidth, ref0, ref1, m_predYuv[0].getStride(), m_predYuv[1].getStride());
+ primitives.pixelavg_pp[partEnum](avg, roiWidth, ref0, m_predYuv[0].getStride(), ref1, m_predYuv[1].getStride(), 32);
int satdCost = primitives.satd[partEnum](pu, fenc->getStride(), avg, roiWidth);
bits[2] = bits[0] + bits[1] - mbBits[0] - mbBits[1] + mbBits[2];
@@ -2441,7 +2441,7 @@ void TEncSearch::predInterSearch(TComDat
intptr_t refStride = cu->getSlice()->m_mref[0][refIdx[0]]->lumaStride;
partEnum = PartitionFromSizes(roiWidth, roiHeight);
- primitives.pixelavg_pp[partEnum](avg, roiWidth, ref0, ref1, refStride, refStride);
+ primitives.pixelavg_pp[partEnum](avg, roiWidth, ref0, refStride, ref1, refStride, 32);
satdCost = primitives.satd[partEnum](pu, fenc->getStride(), avg, roiWidth);
diff -r 4ee217cd64cc -r fbfa3a5c5ae8 source/common/pixel.cpp
--- a/source/common/pixel.cpp Fri Oct 04 15:30:31 2013 -0500
+++ b/source/common/pixel.cpp Sat Oct 05 15:04:28 2013 -0500
@@ -580,7 +580,7 @@ void pixeladd_pp_c(int bx, int by, pixel
}
template<int lx, int ly>
-void pixelavg_pp(pixel* dst, intptr_t dstride, pixel* src0, pixel* src1, intptr_t sstride0, intptr_t sstride1)
+void pixelavg_pp(pixel* dst, intptr_t dstride, pixel* src0, intptr_t sstride0, pixel* src1, intptr_t sstride1, int)
{
for (int y = 0; y < ly; y++)
{
diff -r 4ee217cd64cc -r fbfa3a5c5ae8 source/common/primitives.h
--- a/source/common/primitives.h Fri Oct 04 15:30:31 2013 -0500
+++ b/source/common/primitives.h Sat Oct 05 15:04:28 2013 -0500
@@ -196,7 +196,7 @@ typedef void (*blockcpy_sc_t)(int bx, in
typedef void (*pixelsub_sp_t)(int bx, int by, short *dst, intptr_t dstride, pixel *src0, pixel *src1, intptr_t sstride0, intptr_t sstride1);
typedef void (*pixeladd_ss_t)(int bx, int by, short *dst, intptr_t dstride, short *src0, short *src1, intptr_t sstride0, intptr_t sstride1);
typedef void (*pixeladd_pp_t)(int bx, int by, pixel *dst, intptr_t dstride, pixel *src0, pixel *src1, intptr_t sstride0, intptr_t sstride1);
-typedef void (*pixelavg_pp_t)(pixel *dst, intptr_t dstride, pixel *src0, pixel *src1, intptr_t sstride0, intptr_t sstride1);
+typedef void (*pixelavg_pp_t)(pixel *dst, intptr_t dstride, pixel *src0, intptr_t sstride0, pixel *src1, intptr_t sstride1, int weight);
typedef void (*blockfil_s_t)(short *dst, intptr_t dstride, short val);
typedef void (*intra_dc_t)(pixel* above, pixel* left, pixel* dst, intptr_t dstStride, int width, int bFilter);
diff -r 4ee217cd64cc -r fbfa3a5c5ae8 source/common/vec/pixel-sse41.cpp
--- a/source/common/vec/pixel-sse41.cpp Fri Oct 04 15:30:31 2013 -0500
+++ b/source/common/vec/pixel-sse41.cpp Sat Oct 05 15:04:28 2013 -0500
@@ -1406,7 +1406,6 @@ int sad_16(pixel * fenc, intptr_t fencst
template<int ly>
int sad_24(pixel *fenc, intptr_t fencstride, pixel *fref, intptr_t frefstride)
{
- assert((ly % 4) == 0);
__m128i sum0 = _mm_setzero_si128();
__m128i sum1 = _mm_setzero_si128();
@@ -1421,10 +1420,10 @@ int sad_24(pixel *fenc, intptr_t fencstr
T02 = _mm_load_si128((__m128i*)(fenc + (2) * fencstride));
T03 = _mm_load_si128((__m128i*)(fenc + (3) * fencstride));
- T10 = _mm_load_si128((__m128i*)(fref));
- T11 = _mm_load_si128((__m128i*)(fref + frefstride));
- T12 = _mm_load_si128((__m128i*)(fref + (2) * frefstride));
- T13 = _mm_load_si128((__m128i*)(fref + (3) * frefstride));
+ T10 = _mm_loadu_si128((__m128i*)(fref));
+ T11 = _mm_loadu_si128((__m128i*)(fref + frefstride));
+ T12 = _mm_loadu_si128((__m128i*)(fref + (2) * frefstride));
+ T13 = _mm_loadu_si128((__m128i*)(fref + (3) * frefstride));
T20 = _mm_sad_epu8(T00, T10);
T21 = _mm_sad_epu8(T01, T11);
@@ -1471,10 +1470,10 @@ int sad_24(pixel *fenc, intptr_t fencstr
T02 = _mm_load_si128((__m128i*)(fenc + (2) * fencstride));
T03 = _mm_load_si128((__m128i*)(fenc + (3) * fencstride));
- T10 = _mm_load_si128((__m128i*)(fref));
- T11 = _mm_load_si128((__m128i*)(fref + frefstride));
- T12 = _mm_load_si128((__m128i*)(fref + (2) * frefstride));
- T13 = _mm_load_si128((__m128i*)(fref + (3) * frefstride));
+ T10 = _mm_loadu_si128((__m128i*)(fref));
+ T11 = _mm_loadu_si128((__m128i*)(fref + frefstride));
+ T12 = _mm_loadu_si128((__m128i*)(fref + (2) * frefstride));
+ T13 = _mm_loadu_si128((__m128i*)(fref + (3) * frefstride));
T20 = _mm_sad_epu8(T00, T10);
T21 = _mm_sad_epu8(T01, T11);
@@ -1515,10 +1514,10 @@ int sad_24(pixel *fenc, intptr_t fencstr
T02 = _mm_load_si128((__m128i*)(fenc + (6) * fencstride));
T03 = _mm_load_si128((__m128i*)(fenc + (7) * fencstride));
- T10 = _mm_load_si128((__m128i*)(fref + (4) * frefstride));
- T11 = _mm_load_si128((__m128i*)(fref + (5) * frefstride));
- T12 = _mm_load_si128((__m128i*)(fref + (6) * frefstride));
- T13 = _mm_load_si128((__m128i*)(fref + (7) * frefstride));
+ T10 = _mm_loadu_si128((__m128i*)(fref + (4) * frefstride));
+ T11 = _mm_loadu_si128((__m128i*)(fref + (5) * frefstride));
+ T12 = _mm_loadu_si128((__m128i*)(fref + (6) * frefstride));
+ T13 = _mm_loadu_si128((__m128i*)(fref + (7) * frefstride));
T20 = _mm_sad_epu8(T00, T10);
T21 = _mm_sad_epu8(T01, T11);
@@ -1566,10 +1565,10 @@ int sad_24(pixel *fenc, intptr_t fencstr
T02 = _mm_load_si128((__m128i*)(fenc + (2) * fencstride));
T03 = _mm_load_si128((__m128i*)(fenc + (3) * fencstride));
- T10 = _mm_load_si128((__m128i*)(fref));
- T11 = _mm_load_si128((__m128i*)(fref + frefstride));
- T12 = _mm_load_si128((__m128i*)(fref + (2) * frefstride));
- T13 = _mm_load_si128((__m128i*)(fref + (3) * frefstride));
+ T10 = _mm_loadu_si128((__m128i*)(fref));
+ T11 = _mm_loadu_si128((__m128i*)(fref + frefstride));
+ T12 = _mm_loadu_si128((__m128i*)(fref + (2) * frefstride));
+ T13 = _mm_loadu_si128((__m128i*)(fref + (3) * frefstride));
T20 = _mm_sad_epu8(T00, T10);
T21 = _mm_sad_epu8(T01, T11);
@@ -1610,10 +1609,10 @@ int sad_24(pixel *fenc, intptr_t fencstr
T02 = _mm_load_si128((__m128i*)(fenc + (6) * fencstride));
T03 = _mm_load_si128((__m128i*)(fenc + (7) * fencstride));
- T10 = _mm_load_si128((__m128i*)(fref + (4) * frefstride));
- T11 = _mm_load_si128((__m128i*)(fref + (5) * frefstride));
- T12 = _mm_load_si128((__m128i*)(fref + (6) * frefstride));
- T13 = _mm_load_si128((__m128i*)(fref + (7) * frefstride));
+ T10 = _mm_loadu_si128((__m128i*)(fref + (4) * frefstride));
+ T11 = _mm_loadu_si128((__m128i*)(fref + (5) * frefstride));
+ T12 = _mm_loadu_si128((__m128i*)(fref + (6) * frefstride));
+ T13 = _mm_loadu_si128((__m128i*)(fref + (7) * frefstride));
T20 = _mm_sad_epu8(T00, T10);
T21 = _mm_sad_epu8(T01, T11);
@@ -1655,10 +1654,10 @@ int sad_24(pixel *fenc, intptr_t fencstr
T02 = _mm_load_si128((__m128i*)(fenc + (10) * fencstride));
T03 = _mm_load_si128((__m128i*)(fenc + (11) * fencstride));
- T10 = _mm_load_si128((__m128i*)(fref + (8) * frefstride));
- T11 = _mm_load_si128((__m128i*)(fref + (9) * frefstride));
- T12 = _mm_load_si128((__m128i*)(fref + (10) * frefstride));
- T13 = _mm_load_si128((__m128i*)(fref + (11) * frefstride));
+ T10 = _mm_loadu_si128((__m128i*)(fref + (8) * frefstride));
+ T11 = _mm_loadu_si128((__m128i*)(fref + (9) * frefstride));
+ T12 = _mm_loadu_si128((__m128i*)(fref + (10) * frefstride));
+ T13 = _mm_loadu_si128((__m128i*)(fref + (11) * frefstride));
T20 = _mm_sad_epu8(T00, T10);
T21 = _mm_sad_epu8(T01, T11);
@@ -1700,10 +1699,10 @@ int sad_24(pixel *fenc, intptr_t fencstr
T02 = _mm_load_si128((__m128i*)(fenc + (14) * fencstride));
T03 = _mm_load_si128((__m128i*)(fenc + (15) * fencstride));
- T10 = _mm_load_si128((__m128i*)(fref + (12) * frefstride));
- T11 = _mm_load_si128((__m128i*)(fref + (13) * frefstride));
- T12 = _mm_load_si128((__m128i*)(fref + (14) * frefstride));
- T13 = _mm_load_si128((__m128i*)(fref + (15) * frefstride));
+ T10 = _mm_loadu_si128((__m128i*)(fref + (12) * frefstride));
+ T11 = _mm_loadu_si128((__m128i*)(fref + (13) * frefstride));
+ T12 = _mm_loadu_si128((__m128i*)(fref + (14) * frefstride));
+ T13 = _mm_loadu_si128((__m128i*)(fref + (15) * frefstride));
T20 = _mm_sad_epu8(T00, T10);
T21 = _mm_sad_epu8(T01, T11);
@@ -1753,10 +1752,10 @@ int sad_24(pixel *fenc, intptr_t fencstr
T02 = _mm_load_si128((__m128i*)(fenc + (i + 2) * fencstride));
T03 = _mm_load_si128((__m128i*)(fenc + (i + 3) * fencstride));
- T10 = _mm_load_si128((__m128i*)(fref + (i) * frefstride));
- T11 = _mm_load_si128((__m128i*)(fref + (i + 1) * frefstride));
- T12 = _mm_load_si128((__m128i*)(fref + (i + 2) * frefstride));
- T13 = _mm_load_si128((__m128i*)(fref + (i + 3) * frefstride));
+ T10 = _mm_loadu_si128((__m128i*)(fref + (i) * frefstride));
+ T11 = _mm_loadu_si128((__m128i*)(fref + (i + 1) * frefstride));
+ T12 = _mm_loadu_si128((__m128i*)(fref + (i + 2) * frefstride));
+ T13 = _mm_loadu_si128((__m128i*)(fref + (i + 3) * frefstride));
T20 = _mm_sad_epu8(T00, T10);
T21 = _mm_sad_epu8(T01, T11);
@@ -1798,10 +1797,10 @@ int sad_24(pixel *fenc, intptr_t fencstr
T02 = _mm_load_si128((__m128i*)(fenc + (i + 6) * fencstride));
T03 = _mm_load_si128((__m128i*)(fenc + (i + 7) * fencstride));
- T10 = _mm_load_si128((__m128i*)(fref + (i + 4) * frefstride));
- T11 = _mm_load_si128((__m128i*)(fref + (i + 5) * frefstride));
- T12 = _mm_load_si128((__m128i*)(fref + (i + 6) * frefstride));
- T13 = _mm_load_si128((__m128i*)(fref + (i + 7) * frefstride));
+ T10 = _mm_loadu_si128((__m128i*)(fref + (i + 4) * frefstride));
+ T11 = _mm_loadu_si128((__m128i*)(fref + (i + 5) * frefstride));
+ T12 = _mm_loadu_si128((__m128i*)(fref + (i + 6) * frefstride));
+ T13 = _mm_loadu_si128((__m128i*)(fref + (i + 7) * frefstride));
T20 = _mm_sad_epu8(T00, T10);
T21 = _mm_sad_epu8(T01, T11);
@@ -1852,10 +1851,10 @@ int sad_24(pixel *fenc, intptr_t fencstr
T02 = _mm_load_si128((__m128i*)(fenc + (i + 2) * fencstride));
T03 = _mm_load_si128((__m128i*)(fenc + (i + 3) * fencstride));
- T10 = _mm_load_si128((__m128i*)(fref + (i) * frefstride));
- T11 = _mm_load_si128((__m128i*)(fref + (i + 1) * frefstride));
- T12 = _mm_load_si128((__m128i*)(fref + (i + 2) * frefstride));
- T13 = _mm_load_si128((__m128i*)(fref + (i + 3) * frefstride));
+ T10 = _mm_loadu_si128((__m128i*)(fref + (i) * frefstride));
+ T11 = _mm_loadu_si128((__m128i*)(fref + (i + 1) * frefstride));
+ T12 = _mm_loadu_si128((__m128i*)(fref + (i + 2) * frefstride));
+ T13 = _mm_loadu_si128((__m128i*)(fref + (i + 3) * frefstride));
T20 = _mm_sad_epu8(T00, T10);
T21 = _mm_sad_epu8(T01, T11);
@@ -2360,11 +2359,11 @@ int sad_48(pixel * fenc, intptr_t fencst
__m128i T10, T11, T12;
__m128i T20, T21, T22;
- T00 = _mm_load_si128((__m128i*)(fenc)); /*Loding 48 8-bit integer from fenc to local variables*/
+ T00 = _mm_load_si128((__m128i*)(fenc)); /*Loading 48 8-bit integer from fenc to local variables*/
T01 = _mm_load_si128((__m128i*)(fenc + 16));
T02 = _mm_load_si128((__m128i*)(fenc + 32));
- T10 = _mm_loadu_si128((__m128i*)(fref)); /*Loding 48 8-bit integer from fref to local variables*/
+ T10 = _mm_loadu_si128((__m128i*)(fref)); /*Loading 48 8-bit integer from fref to local variables*/
T11 = _mm_loadu_si128((__m128i*)(fref + 16));
T12 = _mm_loadu_si128((__m128i*)(fref + 32));
@@ -3050,12 +3049,12 @@ int sad_64(pixel * fenc, intptr_t fencst
__m128i T10, T11, T12, T13;
__m128i T20, T21, T22, T23;
- T00 = _mm_load_si128((__m128i*)(fenc)); /*Loding 64 8-bit integer from fenc to local variables*/
+ T00 = _mm_load_si128((__m128i*)(fenc)); /*Loading 64 8-bit integer from fenc to local variables*/
T01 = _mm_load_si128((__m128i*)(fenc + 16));
T02 = _mm_load_si128((__m128i*)(fenc + 32));
T03 = _mm_load_si128((__m128i*)(fenc + 48));
- T10 = _mm_loadu_si128((__m128i*)(fref)); /*Loding 64 8-bit integer from fref to local variables*/
+ T10 = _mm_loadu_si128((__m128i*)(fref)); /*Loading 64 8-bit integer from fref to local variables*/
T11 = _mm_loadu_si128((__m128i*)(fref + 16));
T12 = _mm_loadu_si128((__m128i*)(fref + 32));
T13 = _mm_loadu_si128((__m128i*)(fref + 48));
@@ -9687,13 +9686,13 @@ void sad_x3_48(pixel *fenc, pixel *fref1
__m128i T00, T01, T02, T03;
__m128i T10, T11, T12, T13;
__m128i T20, T21, T22, T23;
- /*Loding from offset 0*/
- T00 = _mm_load_si128((__m128i*)(fenc)); /*Loding 48 8-bit integer to Local variable*/
+ /*Loading from offset 0*/
+ T00 = _mm_load_si128((__m128i*)(fenc)); /*Loading 48 8-bit integer to Local variable*/
T01 = _mm_load_si128((__m128i*)(fenc + FENC_STRIDE));
T02 = _mm_load_si128((__m128i*)(fenc + (2) * FENC_STRIDE));
T03 = _mm_load_si128((__m128i*)(fenc + (3) * FENC_STRIDE));
- T10 = _mm_loadu_si128((__m128i*)(fref1)); /*Loding reference frame 1 to Local variable*/
+ T10 = _mm_loadu_si128((__m128i*)(fref1)); /*Loading reference frame 1 to Local variable*/
T11 = _mm_loadu_si128((__m128i*)(fref1 + frefstride));
T12 = _mm_loadu_si128((__m128i*)(fref1 + (2) * frefstride));
T13 = _mm_loadu_si128((__m128i*)(fref1 + (3) * frefstride));
@@ -9707,7 +9706,7 @@ void sad_x3_48(pixel *fenc, pixel *fref1
T22 = _mm_add_epi16(T22, T23);
sum0 = _mm_add_epi16(T20, T22);
- T10 = _mm_loadu_si128((__m128i*)(fref2)); /*Loding reference frame 2 to Local variable*/
+ T10 = _mm_loadu_si128((__m128i*)(fref2)); /*Loading reference frame 2 to Local variable*/
T11 = _mm_loadu_si128((__m128i*)(fref2 + frefstride));
T12 = _mm_loadu_si128((__m128i*)(fref2 + (2) * frefstride));
T13 = _mm_loadu_si128((__m128i*)(fref2 + (3) * frefstride));
@@ -9721,7 +9720,7 @@ void sad_x3_48(pixel *fenc, pixel *fref1
T22 = _mm_add_epi16(T22, T23);
sum1 = _mm_add_epi16(T20, T22);
- T10 = _mm_loadu_si128((__m128i*)(fref3)); /*Loding reference frame 3 to Local variable*/
+ T10 = _mm_loadu_si128((__m128i*)(fref3)); /*Loading reference frame 3 to Local variable*/
T11 = _mm_loadu_si128((__m128i*)(fref3 + frefstride));
T12 = _mm_loadu_si128((__m128i*)(fref3 + (2) * frefstride));
T13 = _mm_loadu_si128((__m128i*)(fref3 + (3) * frefstride));
@@ -9735,7 +9734,7 @@ void sad_x3_48(pixel *fenc, pixel *fref1
T22 = _mm_add_epi16(T22, T23);
sum2 = _mm_add_epi16(T20, T22);
- T00 = _mm_load_si128((__m128i*)(fenc + 16)); /*Loding from offset 16*/
+ T00 = _mm_load_si128((__m128i*)(fenc + 16)); /*Loading from offset 16*/
T01 = _mm_load_si128((__m128i*)(fenc + 16 + FENC_STRIDE));
T02 = _mm_load_si128((__m128i*)(fenc + 16 + (2) * FENC_STRIDE));
T03 = _mm_load_si128((__m128i*)(fenc + 16 + (3) * FENC_STRIDE));
@@ -9785,7 +9784,7 @@ void sad_x3_48(pixel *fenc, pixel *fref1
T22 = _mm_add_epi16(T20, T22);
sum2 = _mm_add_epi32(sum2, T22);
- T00 = _mm_load_si128((__m128i*)(fenc + 32)); /*Loding from offset 32*/
+ T00 = _mm_load_si128((__m128i*)(fenc + 32)); /*Loading from offset 32*/
T01 = _mm_load_si128((__m128i*)(fenc + 32 + FENC_STRIDE));
T02 = _mm_load_si128((__m128i*)(fenc + 32 + (2) * FENC_STRIDE));
T03 = _mm_load_si128((__m128i*)(fenc + 32 + (3) * FENC_STRIDE));
@@ -11237,13 +11236,13 @@ void sad_x3_64(pixel *fenc, pixel *fref1
__m128i T00, T01, T02, T03;
__m128i T10, T11, T12, T13;
__m128i T20, T21, T22, T23;
- /*Loding for offset 0*/
- T00 = _mm_load_si128((__m128i*)(fenc)); /*Loding 64 8-bit integer to Local variable*/
+ /*Loading for offset 0*/
+ T00 = _mm_load_si128((__m128i*)(fenc)); /*Loading 64 8-bit integer to Local variable*/
T01 = _mm_load_si128((__m128i*)(fenc + FENC_STRIDE));
T02 = _mm_load_si128((__m128i*)(fenc + (2) * FENC_STRIDE));
T03 = _mm_load_si128((__m128i*)(fenc + (3) * FENC_STRIDE));
More information about the x265-commits
mailing list