[FFmpeg-cvslog] avfilter/thumbnail_cuda: add cuda thumbnail filter
ffmpeg | branch: master | Yogender Gupta | Mon Sep 4
18:36:16 2017 +0530| [21e077fcb3d968e3ed6772a0309e31f94cd7a2a5] | committer:
Timo Rothenpieler
avfilter/thumbnail_cuda: add cuda thumbnail filter
Signed-off-by: Timo Rothenpieler
> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=21e077fcb3d968e3ed6772a0309e31f94cd7a2a5
---
Changelog| 2 +
configure| 1 +
libavfilter/Makefile | 1 +
libavfilter/allfilters.c | 1 +
libavfilter/version.h| 2 +-
libavfilter/vf_thumbnail_cuda.c | 444 +++
libavfilter/vf_thumbnail_cuda.cu | 79 +++
7 files changed, 529 insertions(+), 1 deletion(-)
diff --git a/Changelog b/Changelog
index ea48e81efe..38b125be39 100644
--- a/Changelog
+++ b/Changelog
@@ -48,6 +48,8 @@ version :
- convolve video filter
- VP9 tile threading support
- KMS screen grabber
+- CUDA thumbnail filter
+
version 3.3:
- CrystalHD decoder moved to new decode API
diff --git a/configure b/configure
index 2de20a02a4..ff9a64292c 100755
--- a/configure
+++ b/configure
@@ -2759,6 +2759,7 @@ vaapi_encode_deps="vaapi"
hwupload_cuda_filter_deps="cuda"
scale_npp_filter_deps="cuda libnpp"
scale_cuda_filter_deps="cuda_sdk"
+thumbnail_cuda_filter_deps="cuda_sdk"
nvenc_deps="cuda"
nvenc_deps_any="dlopen LoadLibrary"
diff --git a/libavfilter/Makefile b/libavfilter/Makefile
index 8aa974e115..98acb51bcb 100644
--- a/libavfilter/Makefile
+++ b/libavfilter/Makefile
@@ -315,6 +315,7 @@ OBJS-$(CONFIG_TBLEND_FILTER) += vf_blend.o
framesync.o
OBJS-$(CONFIG_TELECINE_FILTER) += vf_telecine.o
OBJS-$(CONFIG_THRESHOLD_FILTER) += vf_threshold.o framesync.o
OBJS-$(CONFIG_THUMBNAIL_FILTER) += vf_thumbnail.o
+OBJS-$(CONFIG_THUMBNAIL_CUDA_FILTER) += vf_thumbnail_cuda.o
vf_thumbnail_cuda.ptx.o
OBJS-$(CONFIG_TILE_FILTER) += vf_tile.o
OBJS-$(CONFIG_TINTERLACE_FILTER) += vf_tinterlace.o
OBJS-$(CONFIG_TLUT2_FILTER) += vf_lut2.o framesync.o
diff --git a/libavfilter/allfilters.c b/libavfilter/allfilters.c
index 63e86721cd..baa84a3e72 100644
--- a/libavfilter/allfilters.c
+++ b/libavfilter/allfilters.c
@@ -326,6 +326,7 @@ static void register_all(void)
REGISTER_FILTER(TELECINE, telecine, vf);
REGISTER_FILTER(THRESHOLD, threshold, vf);
REGISTER_FILTER(THUMBNAIL, thumbnail, vf);
+REGISTER_FILTER(THUMBNAIL_CUDA, thumbnail_cuda, vf);
REGISTER_FILTER(TILE, tile, vf);
REGISTER_FILTER(TINTERLACE, tinterlace, vf);
REGISTER_FILTER(TLUT2, tlut2, vf);
diff --git a/libavfilter/version.h b/libavfilter/version.h
index 5d6aa5fc70..fb382d4e25 100644
--- a/libavfilter/version.h
+++ b/libavfilter/version.h
@@ -30,7 +30,7 @@
#include "libavutil/version.h"
#define LIBAVFILTER_VERSION_MAJOR 6
-#define LIBAVFILTER_VERSION_MINOR 105
+#define LIBAVFILTER_VERSION_MINOR 106
#define LIBAVFILTER_VERSION_MICRO 100
#define LIBAVFILTER_VERSION_INT AV_VERSION_INT(LIBAVFILTER_VERSION_MAJOR, \
diff --git a/libavfilter/vf_thumbnail_cuda.c b/libavfilter/vf_thumbnail_cuda.c
new file mode 100644
index 00..4c08a85121
--- /dev/null
+++ b/libavfilter/vf_thumbnail_cuda.c
@@ -0,0 +1,444 @@
+/*
+* Copyright (c) 2017, NVIDIA CORPORATION. All rights reserved.
+*
+* Permission is hereby granted, free of charge, to any person obtaining a
+* copy of this software and associated documentation files (the "Software"),
+* to deal in the Software without restriction, including without limitation
+* the rights to use, copy, modify, merge, publish, distribute, sublicense,
+* and/or sell copies of the Software, and to permit persons to whom the
+* Software is furnished to do so, subject to the following conditions:
+*
+* The above copyright notice and this permission notice shall be included in
+* all copies or substantial portions of the Software.
+*
+* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+* DEALINGS IN THE SOFTWARE.
+*/
+
+#include
+
+#include "libavutil/hwcontext.h"
+#include "libavutil/hwcontext_cuda_internal.h"
+#include "libavutil/opt.h"
+#include "libavutil/pixdesc.h"
+
+#include "avfilter.h"
+#include "internal.h"
+
+#define HIST_SIZE (3*256)
+#define DIV_UP(a, b) ( ((a) + (b) - 1) / (b) )
+#define BLOCKX 32
+#define BLOCKY 16
+
+static const enum AVPixelFormat supported_formats[] = {
+AV_PIX_FMT_NV12,
+AV_PIX_FMT_YUV420P,
+AV_PIX_FMT_YUV444P,
+AV_PIX_FMT_P010,
+
[FFmpeg-cvslog] avcodec/mips: Remove generic func use in hevc non-uni copy mc msa functions
ffmpeg | branch: master | Kaustubh Raste | Thu Sep
21 13:03:28 2017 +0530| [f160a63badfc6103ce9fdbfeff7c82111ba81ab8] | committer:
Michael Niedermayer
avcodec/mips: Remove generic func use in hevc non-uni copy mc msa functions
Signed-off-by: Kaustubh Raste
Reviewed-by: Manojkumar Bhosale
Signed-off-by: Michael Niedermayer
> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=f160a63badfc6103ce9fdbfeff7c82111ba81ab8
---
libavcodec/mips/hevcdsp_msa.c | 168 --
1 file changed, 160 insertions(+), 8 deletions(-)
diff --git a/libavcodec/mips/hevcdsp_msa.c b/libavcodec/mips/hevcdsp_msa.c
index f2bc748e37..1a854b204f 100644
--- a/libavcodec/mips/hevcdsp_msa.c
+++ b/libavcodec/mips/hevcdsp_msa.c
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2015 Manojkumar Bhosale (manojkumar.bhos...@imgtec.com)
+ * Copyright (c) 2015 - 2017 Manojkumar Bhosale (manojkumar.bhos...@imgtec.com)
*
* This file is part of FFmpeg.
*
@@ -302,8 +302,34 @@ static void hevc_copy_16w_msa(uint8_t *src, int32_t
src_stride,
ST_SH4(in0_r, in1_r, in2_r, in3_r, dst, dst_stride);
ST_SH4(in0_l, in1_l, in2_l, in3_l, (dst + 8), dst_stride);
} else if (0 == (height % 8)) {
-hevc_copy_16multx8mult_msa(src, src_stride, dst, dst_stride,
- height, 16);
+uint32_t loop_cnt;
+v16i8 src0, src1, src2, src3, src4, src5, src6, src7;
+v8i16 in0_r, in1_r, in2_r, in3_r, in0_l, in1_l, in2_l, in3_l;
+
+for (loop_cnt = (height >> 3); loop_cnt--;) {
+LD_SB8(src, src_stride, src0, src1, src2, src3, src4, src5, src6,
+ src7);
+src += (8 * src_stride);
+ILVR_B4_SH(zero, src0, zero, src1, zero, src2, zero, src3, in0_r,
+ in1_r, in2_r, in3_r);
+ILVL_B4_SH(zero, src0, zero, src1, zero, src2, zero, src3, in0_l,
+ in1_l, in2_l, in3_l);
+SLLI_4V(in0_r, in1_r, in2_r, in3_r, 6);
+SLLI_4V(in0_l, in1_l, in2_l, in3_l, 6);
+ST_SH4(in0_r, in1_r, in2_r, in3_r, dst, dst_stride);
+ST_SH4(in0_l, in1_l, in2_l, in3_l, (dst + 8), dst_stride);
+dst += (4 * dst_stride);
+
+ILVR_B4_SH(zero, src4, zero, src5, zero, src6, zero, src7, in0_r,
+ in1_r, in2_r, in3_r);
+ILVL_B4_SH(zero, src4, zero, src5, zero, src6, zero, src7, in0_l,
+ in1_l, in2_l, in3_l);
+SLLI_4V(in0_r, in1_r, in2_r, in3_r, 6);
+SLLI_4V(in0_l, in1_l, in2_l, in3_l, 6);
+ST_SH4(in0_r, in1_r, in2_r, in3_r, dst, dst_stride);
+ST_SH4(in0_l, in1_l, in2_l, in3_l, (dst + 8), dst_stride);
+dst += (4 * dst_stride);
+}
}
}
@@ -311,29 +337,155 @@ static void hevc_copy_24w_msa(uint8_t *src, int32_t
src_stride,
int16_t *dst, int32_t dst_stride,
int32_t height)
{
-hevc_copy_16multx8mult_msa(src, src_stride, dst, dst_stride, height, 16);
-hevc_copy_8w_msa(src + 16, src_stride, dst + 16, dst_stride, height);
+uint32_t loop_cnt;
+v16i8 zero = { 0 };
+v16i8 src0, src1, src2, src3, src4, src5, src6, src7;
+v8i16 in0_r, in1_r, in2_r, in3_r, in0_l, in1_l, in2_l, in3_l;
+
+for (loop_cnt = (height >> 2); loop_cnt--;) {
+LD_SB4(src, src_stride, src0, src1, src2, src3);
+LD_SB4((src + 16), src_stride, src4, src5, src6, src7);
+src += (4 * src_stride);
+ILVR_B4_SH(zero, src0, zero, src1, zero, src2, zero, src3, in0_r,
in1_r,
+ in2_r, in3_r);
+ILVL_B4_SH(zero, src0, zero, src1, zero, src2, zero, src3, in0_l,
in1_l,
+ in2_l, in3_l);
+SLLI_4V(in0_r, in1_r, in2_r, in3_r, 6);
+SLLI_4V(in0_l, in1_l, in2_l, in3_l, 6);
+ST_SH4(in0_r, in1_r, in2_r, in3_r, dst, dst_stride);
+ST_SH4(in0_l, in1_l, in2_l, in3_l, (dst + 8), dst_stride);
+ILVR_B4_SH(zero, src4, zero, src5, zero, src6, zero, src7, in0_r,
in1_r,
+ in2_r, in3_r);
+SLLI_4V(in0_r, in1_r, in2_r, in3_r, 6);
+ST_SH4(in0_r, in1_r, in2_r, in3_r, (dst + 16), dst_stride);
+dst += (4 * dst_stride);
+}
}
static void hevc_copy_32w_msa(uint8_t *src, int32_t src_stride,
int16_t *dst, int32_t dst_stride,
int32_t height)
{
-hevc_copy_16multx8mult_msa(src, src_stride, dst, dst_stride, height, 32);
+uint32_t loop_cnt;
+v16i8 zero = { 0 };
+v16i8 src0, src1, src2, src3, src4, src5, src6, src7;
+v8i16 in0_r, in1_r, in2_r, in3_r, in0_l, in1_l, in2_l, in3_l;
+
+for (loop_cnt = (height >> 2); loop_cnt--;) {
+LD_SB4(src, src_stride, src0, src2, src4, src6);
+LD_SB4((src + 16), src_stride, src1, src3, src5, src7);
+src += (4 * src_stride);
+
+ILVR_B4_SH(zero, src0, zero, src1, zero, src2, zero, src3, in0
[FFmpeg-cvslog] avcodec/svq3: Fix overflow in svq3_add_idct_c()
ffmpeg | branch: master | Michael Niedermayer | Mon Sep 18 17:03:55 2017 +0200| [2c933c51687db958d8045d25ed87848342e869f6] | committer: Michael Niedermayer avcodec/svq3: Fix overflow in svq3_add_idct_c() Fixes: runtime error: signed integer overflow: 2147392585 + 524288 cannot be represented in type 'int' Fixes: 3348/clusterfuzz-testcase-minimized-4809500517203968 Found-by: continuous fuzzing process https://github.com/google/oss-fuzz/tree/master/projects/ffmpeg Signed-off-by: Michael Niedermayer > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=2c933c51687db958d8045d25ed87848342e869f6 --- libavcodec/svq3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/libavcodec/svq3.c b/libavcodec/svq3.c index a766fa49ad..5cb5bd45b7 100644 --- a/libavcodec/svq3.c +++ b/libavcodec/svq3.c @@ -285,7 +285,7 @@ static void svq3_add_idct_c(uint8_t *dst, int16_t *block, const unsigned z1 = 13 * (block[i + 4 * 0] - block[i + 4 * 2]); const unsigned z2 = 7 * block[i + 4 * 1] - 17 * block[i + 4 * 3]; const unsigned z3 = 17 * block[i + 4 * 1] + 7 * block[i + 4 * 3]; -const int rr = (dc + 0x8); +const int rr = (dc + 0x8u); dst[i + stride * 0] = av_clip_uint8(dst[i + stride * 0] + ((int)((z0 + z3) * qmul + rr) >> 20)); dst[i + stride * 1] = av_clip_uint8(dst[i + stride * 1] + ((int)((z1 + z2) * qmul + rr) >> 20)); ___ ffmpeg-cvslog mailing list ffmpeg-cvslog@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-cvslog
[FFmpeg-cvslog] avcodec/mips: preload data in hevc sao edge 90 degree filter msa functions
ffmpeg | branch: master | Kaustubh Raste | Thu Sep
21 12:35:40 2017 +0530| [2b156269974995c42456586f7218ce22a525a1d9] | committer:
Michael Niedermayer
avcodec/mips: preload data in hevc sao edge 90 degree filter msa functions
Signed-off-by: Kaustubh Raste
Reviewed-by: Manojkumar Bhosale
Signed-off-by: Michael Niedermayer
> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=2b156269974995c42456586f7218ce22a525a1d9
---
libavcodec/mips/hevc_lpf_sao_msa.c | 181 +
1 file changed, 122 insertions(+), 59 deletions(-)
diff --git a/libavcodec/mips/hevc_lpf_sao_msa.c
b/libavcodec/mips/hevc_lpf_sao_msa.c
index 3472d32322..39c647ed79 100644
--- a/libavcodec/mips/hevc_lpf_sao_msa.c
+++ b/libavcodec/mips/hevc_lpf_sao_msa.c
@@ -1568,23 +1568,25 @@ static void
hevc_sao_edge_filter_90degree_4width_msa(uint8_t *dst,
int16_t *sao_offset_val,
int32_t height)
{
-int32_t h_cnt;
uint32_t dst_val0, dst_val1;
-v8i16 edge_idx = { 1, 2, 0, 3, 4, 0, 0, 0 };
+v16i8 edge_idx = { 1, 2, 0, 3, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
v16u8 const1 = (v16u8) __msa_ldi_b(1);
v16i8 dst0;
-v16i8 zero = { 0 };
+v16i8 sao_offset = LD_SB(sao_offset_val);
v16u8 cmp_minus10, diff_minus10, cmp_minus11, diff_minus11;
v16u8 src_minus10, src_minus11, src10, src11;
v16i8 src_zero0, src_zero1;
-v8i16 sao_offset, src00, src01, offset_mask0, offset_mask1;
+v16i8 offset;
+v8i16 offset_mask0, offset_mask1;
-sao_offset = LD_SH(sao_offset_val);
+sao_offset = __msa_pckev_b(sao_offset, sao_offset);
+/* load in advance */
LD_UB2(src - src_stride, src_stride, src_minus10, src_minus11);
+LD_UB2(src + src_stride, src_stride, src10, src11);
-for (h_cnt = (height >> 1); h_cnt--;) {
-LD_UB2(src + src_stride, src_stride, src10, src11);
+for (height -= 2; height; height -= 2) {
+src += (src_stride << 1);
src_minus10 = (v16u8) __msa_ilvr_b((v16i8) src10, (v16i8) src_minus10);
src_zero0 = __msa_ilvr_b((v16i8) src_minus11, (v16i8) src_minus11);
@@ -1604,19 +1606,22 @@ static void
hevc_sao_edge_filter_90degree_4width_msa(uint8_t *dst,
offset_mask0 = (v8i16) (__msa_hadd_u_h(diff_minus10, diff_minus10) +
2);
offset_mask1 = (v8i16) (__msa_hadd_u_h(diff_minus11, diff_minus11) +
2);
-VSHF_H2_SH(edge_idx, edge_idx, sao_offset, sao_offset, offset_mask0,
- offset_mask0, offset_mask0, offset_mask0);
-VSHF_H2_SH(edge_idx, edge_idx, sao_offset, sao_offset, offset_mask1,
- offset_mask1, offset_mask1, offset_mask1);
-ILVEV_B2_SH(src_zero0, zero, src_zero1, zero, src00, src01);
-ADD2(offset_mask0, src00, offset_mask1, src01, offset_mask0,
- offset_mask1);
-CLIP_SH2_0_255(offset_mask0, offset_mask1);
-dst0 = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0);
+offset = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0);
+dst0 = __msa_pckev_b((v16i8) src_zero1, (v16i8) src_zero0);
+
+VSHF_B2_SB(edge_idx, edge_idx, sao_offset, sao_offset, offset, offset,
+ offset, offset);
+
+dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128);
+dst0 = __msa_adds_s_b(dst0, offset);
+dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128);
src_minus10 = src10;
src_minus11 = src11;
+/* load in advance */
+LD_UB2(src + src_stride, src_stride, src10, src11);
+
dst_val0 = __msa_copy_u_w((v4i32) dst0, 0);
dst_val1 = __msa_copy_u_w((v4i32) dst0, 2);
SW(dst_val0, dst);
@@ -1624,8 +1629,41 @@ static void
hevc_sao_edge_filter_90degree_4width_msa(uint8_t *dst,
SW(dst_val1, dst);
dst += dst_stride;
-src += (src_stride << 1);
}
+
+src_minus10 = (v16u8) __msa_ilvr_b((v16i8) src10, (v16i8) src_minus10);
+src_zero0 = __msa_ilvr_b((v16i8) src_minus11, (v16i8) src_minus11);
+src_minus11 = (v16u8) __msa_ilvr_b((v16i8) src11, (v16i8) src_minus11);
+src_zero1 = __msa_ilvr_b((v16i8) src10, (v16i8) src10);
+
+cmp_minus10 = ((v16u8) src_zero0 == src_minus10);
+diff_minus10 = __msa_nor_v(cmp_minus10, cmp_minus10);
+cmp_minus10 = (src_minus10 < (v16u8) src_zero0);
+diff_minus10 = __msa_bmnz_v(diff_minus10, const1, cmp_minus10);
+
+cmp_minus11 = ((v16u8) src_zero1 == src_minus11);
+diff_minus11 = __msa_nor_v(cmp_minus11, cmp_minus11);
+cmp_minus11 = (src_minus11 < (v16u8) src_zero1);
+diff_minus11 = __msa_bmnz_v(diff_minus11, const1, cmp_minus11);
+
+offset_mask0 = (v8i16) (__msa_hadd_u_h(diff_minus10, diff_minus10) + 2);
+offset_mask1 = (v8i16) (__msa_hadd_u_h(diff_minus11, diff_minus11) + 2);
+
+offset = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0);
+dst0 = __msa_pckev_b((v16i8) src_zero1
[FFmpeg-cvslog] avcodec/ffv1dec: Fix integer overflow in read_quant_table()
ffmpeg | branch: master | Michael Niedermayer | Mon
Sep 18 17:26:09 2017 +0200| [d00fc952b6c261dd8eb0f7552b9ccf985dbc2b20] |
committer: Michael Niedermayer
avcodec/ffv1dec: Fix integer overflow in read_quant_table()
Fixes: runtime error: signed integer overflow: 2147483647 + 1 cannot be
represented in type 'int'
Fixes: 3361/clusterfuzz-testcase-minimized-5065842955911168
Found-by: continuous fuzzing process
https://github.com/google/oss-fuzz/tree/master/projects/ffmpeg
Signed-off-by: Michael Niedermayer
> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=d00fc952b6c261dd8eb0f7552b9ccf985dbc2b20
---
libavcodec/ffv1dec.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/libavcodec/ffv1dec.c b/libavcodec/ffv1dec.c
index b13ecd3eab..d2bfee784f 100644
--- a/libavcodec/ffv1dec.c
+++ b/libavcodec/ffv1dec.c
@@ -372,7 +372,7 @@ static int read_quant_table(RangeCoder *c, int16_t
*quant_table, int scale)
memset(state, 128, sizeof(state));
for (v = 0; i < 128; v++) {
-unsigned len = get_symbol(c, state, 0) + 1;
+unsigned len = get_symbol(c, state, 0) + 1U;
if (len > 128 - i || !len)
return AVERROR_INVALIDDATA;
___
ffmpeg-cvslog mailing list
ffmpeg-cvslog@ffmpeg.org
http://ffmpeg.org/mailman/listinfo/ffmpeg-cvslog
[FFmpeg-cvslog] avcodec/dirac_dwt: Fix integer overflow in COMPOSE_FIDELITYi*()
ffmpeg | branch: master | Michael Niedermayer | Mon Sep 18 02:53:25 2017 +0200| [67da2685e03805230207daab83ab43a390fbb887] | committer: Michael Niedermayer avcodec/dirac_dwt: Fix integer overflow in COMPOSE_FIDELITYi*() Fixes: runtime error: signed integer overflow: 161 * 13872281 cannot be represented in type 'int' Fixes: 3295/clusterfuzz-testcase-minimized-4738998142500864 Found-by: continuous fuzzing process https://github.com/google/oss-fuzz/tree/master/projects/ffmpeg Signed-off-by: Michael Niedermayer > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=67da2685e03805230207daab83ab43a390fbb887 --- libavcodec/dirac_dwt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/libavcodec/dirac_dwt.h b/libavcodec/dirac_dwt.h index adf5178714..755d5e5d2d 100644 --- a/libavcodec/dirac_dwt.h +++ b/libavcodec/dirac_dwt.h @@ -111,10 +111,10 @@ void ff_spatial_idwt_slice2(DWTContext *d, int y); (b0 + b1) #define COMPOSE_FIDELITYiL0(b0, b1, b2, b3, b4, b5, b6, b7, b8)\ -(b4 - ((-8*(b0+b8) + 21*(b1+b7) - 46*(b2+b6) + 161*(b3+b5) + 128) >> 8)) +(b4 - ((int)(-8*(b0+(unsigned)b8) + 21*(b1+(unsigned)b7) - 46*(b2+(unsigned)b6) + 161*(b3+(unsigned)b5) + 128) >> 8)) #define COMPOSE_FIDELITYiH0(b0, b1, b2, b3, b4, b5, b6, b7, b8)\ -(b4 + ((-2*(b0+b8) + 10*(b1+b7) - 25*(b2+b6) + 81*(b3+b5) + 128) >> 8)) +(b4 + ((int)(-2*(b0+(unsigned)b8) + 10*(b1+(unsigned)b7) - 25*(b2+(unsigned)b6) + 81*(b3+(unsigned)b5) + 128) >> 8)) #define COMPOSE_DAUB97iL1(b0, b1, b2)\ (b1 - ((int)(1817*(b0 + (unsigned)b2) + 2048) >> 12)) ___ ffmpeg-cvslog mailing list ffmpeg-cvslog@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-cvslog
[FFmpeg-cvslog] avformat/gif: use av_packet_alloc()
ffmpeg | branch: master | James Almer | Sat Sep 23 02:18:47
2017 -0300| [afe674734bbe71ef6c32f96a98f5f84d007eea1c] | committer: James Almer
avformat/gif: use av_packet_alloc()
Signed-off-by: James Almer
> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=afe674734bbe71ef6c32f96a98f5f84d007eea1c
---
libavformat/gif.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/libavformat/gif.c b/libavformat/gif.c
index 91cd40db5c..d6113dbc85 100644
--- a/libavformat/gif.c
+++ b/libavformat/gif.c
@@ -186,7 +186,7 @@ static int gif_write_packet(AVFormatContext *s, AVPacket
*pkt)
AVStream *video_st = s->streams[0];
if (!gif->prev_pkt) {
-gif->prev_pkt = av_malloc(sizeof(*gif->prev_pkt));
+gif->prev_pkt = av_packet_alloc();
if (!gif->prev_pkt)
return AVERROR(ENOMEM);
___
ffmpeg-cvslog mailing list
ffmpeg-cvslog@ffmpeg.org
http://ffmpeg.org/mailman/listinfo/ffmpeg-cvslog
[FFmpeg-cvslog] avformat/apngenc: use av_packet_alloc()
ffmpeg | branch: master | James Almer | Sat Sep 23 02:15:16
2017 -0300| [bb4b7624d9dd17dcda44703d5d69292a85fe2d4d] | committer: James Almer
avformat/apngenc: use av_packet_alloc()
Signed-off-by: James Almer
> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=bb4b7624d9dd17dcda44703d5d69292a85fe2d4d
---
libavformat/apngenc.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/libavformat/apngenc.c b/libavformat/apngenc.c
index 378a9b3b36..d4191c02cc 100644
--- a/libavformat/apngenc.c
+++ b/libavformat/apngenc.c
@@ -228,7 +228,7 @@ static int apng_write_packet(AVFormatContext
*format_context, AVPacket *packet)
int ret;
if (!apng->prev_packet) {
-apng->prev_packet = av_malloc(sizeof(*apng->prev_packet));
+apng->prev_packet = av_packet_alloc();
if (!apng->prev_packet)
return AVERROR(ENOMEM);
___
ffmpeg-cvslog mailing list
ffmpeg-cvslog@ffmpeg.org
http://ffmpeg.org/mailman/listinfo/ffmpeg-cvslog
[FFmpeg-cvslog] libavcodec: v4l2: add support for v4l2 mem2mem codecs
ffmpeg | branch: master | Jorge Ramirez-Ortiz | Wed Sep 20 18:55:40 2017 -0700| [1ef7752d64cbe9af2f27cc65aba3a2ca3831c128] | committer: wm4 libavcodec: v4l2: add support for v4l2 mem2mem codecs This patchset enhances Alexis Ballier's original patch and validates it using Qualcomm's Venus hardware (driver recently landed upstream [1]). This has been tested on Qualcomm's DragonBoard 410c and 820c Configure/make scripts have been validated on Ubuntu 10.04 and 16.04. Tested decoders: - h264 - h263 - mpeg4 - vp8 - vp9 - hevc Tested encoders: - h264 - h263 - mpeg4 Tested transcoding (concurrent encoding/decoding) Some of the changes introduced: - v4l2: code cleanup and abstractions added - v4l2: follow the new encode/decode api. - v4l2: fix display size for NV12 output pool. - v4l2: handle EOS (EPIPE and draining) - v4l2: vp8 and mpeg4 decoding and encoding. - v4l2: hevc and vp9 support. - v4l2: generate EOF on dequeue errors. - v4l2: h264_mp4toannexb filtering. - v4l2: fixed make install and fate issues. - v4l2: codecs enabled/disabled depending on pixfmt defined - v4l2: pass timebase/framerate to the context - v4l2: runtime decoder reconfiguration. - v4l2: add more frame information - v4l2: free hardware resources on last reference being released - v4l2: encoding: disable b-frames for upstreaming (patch required) [1] https://lwn.net/Articles/697956/ System Level view: v42l_m2m_enc/dec --> v4l2_m2m --> v4l2_context --> v4l2_buffers Reviewed-by: Jorge Ramirez Reviewed-by: Alexis Ballier Tested-by: Jorge Ramirez Signed-off-by: wm4 > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=1ef7752d64cbe9af2f27cc65aba3a2ca3831c128 --- Changelog | 1 + configure | 28 ++ libavcodec/Makefile | 15 ++ libavcodec/allcodecs.c| 9 + libavcodec/v4l2_buffers.c | 453 +++ libavcodec/v4l2_buffers.h | 121 + libavcodec/v4l2_context.c | 667 ++ libavcodec/v4l2_context.h | 181 + libavcodec/v4l2_fmt.c | 182 + libavcodec/v4l2_fmt.h | 34 +++ libavcodec/v4l2_m2m.c | 383 ++ libavcodec/v4l2_m2m.h | 103 +++ libavcodec/v4l2_m2m_dec.c | 228 libavcodec/v4l2_m2m_enc.c | 352 14 files changed, 2757 insertions(+) diff --git a/Changelog b/Changelog index 38b125be39..678dcdadc7 100644 --- a/Changelog +++ b/Changelog @@ -49,6 +49,7 @@ version : - VP9 tile threading support - KMS screen grabber - CUDA thumbnail filter +- V4L2 mem2mem HW assisted codecs version 3.3: diff --git a/configure b/configure index ff9a64292c..16fc2bd074 100755 --- a/configure +++ b/configure @@ -185,6 +185,7 @@ Individual component options: --enable-filter=NAME enable filter NAME --disable-filter=NAMEdisable filter NAME --disable-filtersdisable all filters + --disable-v4l2_m2m disable V4L2 mem2mem code [autodetect] External library support: @@ -1628,6 +1629,7 @@ HWACCEL_AUTODETECT_LIBRARY_LIST=" vda vdpau videotoolbox +v4l2_m2m xvmc " @@ -2755,6 +2757,7 @@ omx_rpi_select="omx" qsvdec_select="qsv" qsvenc_select="qsv" vaapi_encode_deps="vaapi" +v4l2_m2m_deps_any="linux_videodev2_h" hwupload_cuda_filter_deps="cuda" scale_npp_filter_deps="cuda libnpp" @@ -2765,6 +2768,8 @@ nvenc_deps="cuda" nvenc_deps_any="dlopen LoadLibrary" nvenc_encoder_deps="nvenc" +h263_v4l2m2m_decoder_deps="v4l2_m2m h263_v4l2_m2m" +h263_v4l2m2m_encoder_deps="v4l2_m2m h263_v4l2_m2m" h264_crystalhd_decoder_select="crystalhd h264_mp4toannexb_bsf h264_parser" h264_cuvid_decoder_deps="cuda cuvid" h264_cuvid_decoder_select="h264_mp4toannexb_bsf" @@ -2783,6 +2788,8 @@ h264_vda_decoder_deps="vda" h264_vda_decoder_select="h264_decoder" h264_vdpau_decoder_deps="vdpau" h264_vdpau_decoder_select="h264_decoder" +h264_v4l2m2m_decoder_deps="v4l2_m2m h264_v4l2_m2m" +h264_v4l2m2m_encoder_deps="v4l2_m2m h264_v4l2_m2m" hevc_cuvid_decoder_deps="cuda cuvid" hevc_cuvid_decoder_select="hevc_mp4toannexb_bsf" hevc_mediacodec_decoder_deps="mediacodec" @@ -2794,12 +2801,15 @@ hevc_qsv_encoder_deps="libmfx" hevc_qsv_encoder_select="hevcparse qsvenc" hevc_vaapi_encoder_deps="VAEncPictureParameterBufferHEVC" hevc_vaapi_encoder_select="vaapi_encode golomb" +hevc_v4l2m2m_decoder_deps="v4l2_m2m hevc_v4l2_m2m" +hevc_v4l2m2m_encoder_deps="v4l2_m2m hevc_v4l2_m2m" mjpeg_cuvid_decoder_deps="cuda cuvid" mjpeg_vaapi_encoder_deps="VAEncPictureParameterBufferJPEG" mjpeg_vaapi_encoder_select="vaapi_encode jpegtables" mpeg1_cuvid_decoder_deps="cuda cuvid" mpeg1_vdpau_decoder_deps="vdpau" mpeg1_vdpau_d
