James Zern [Sat, 18 Feb 2017 21:24:32 +0000 (13:24 -0800)]
vp8_fdct4x4_test: align input and output buffers
fixes segfault in 32-bit builds
Change-Id: I5b3cc5a335cb236a6ec4cb11fa8feb54ae0182c7
James Zern [Sat, 18 Feb 2017 00:23:22 +0000 (16:23 -0800)]
datarate_test: disable OnePassCbrSvc2SpatialLayersDenoiserOn
segfaults
BUG=webm:1374
Change-Id: I3790c6cb8a539d13dee6a8225ef09b1575dea26c
Johann Koenig [Fri, 17 Feb 2017 22:11:08 +0000 (22:11 +0000)]
Merge "vp8_short_fdct4x4: verify optimized functions"
James Zern [Fri, 17 Feb 2017 20:29:36 +0000 (20:29 +0000)]
Merge "Add vpx_highbd_idct16x16_10_add_neon()"
Johann [Fri, 23 Sep 2016 23:45:03 +0000 (16:45 -0700)]
vp8_short_fdct4x4: verify optimized functions
Change-Id: I7c7f5dfabde65c09f111fb0ced0e3ad231ee716e
Johann [Tue, 31 Jan 2017 23:58:43 +0000 (15:58 -0800)]
tiny_ssim: clean up on failure
Clears up clang static analysis warnings about memory leaks.
Change-Id: I60d4d0f3794735a8b81d9da4a30d19e7a9cba9cf
Yi Luo [Thu, 16 Feb 2017 21:15:22 +0000 (13:15 -0800)]
Replace idct32x32_1024_add_ssse3 assembly with intrinsics
- Encoding/decoding test, BQTerrace_1920x1080_60.y4m, on
i7-6700, no obvious user-level speed performance downgrade.
- Passed unit tests.
Change-Id: I20688e0dd3731021ec8fb4404734336f1a426bfc
James Zern [Fri, 17 Feb 2017 00:04:42 +0000 (00:04 +0000)]
Merge "cosmetics: Fix spelling mistake in compile flag name."
Johann Koenig [Thu, 16 Feb 2017 23:51:14 +0000 (23:51 +0000)]
Merge "block error avx2: use tran_low_t"
Linfeng Zhang [Tue, 14 Feb 2017 18:24:51 +0000 (10:24 -0800)]
Add vpx_highbd_idct16x16_10_add_neon()
BUG=webm:1301
Change-Id: If686c8144764c4162458f0bc4bb1bbf6555c48ab
James Zern [Thu, 16 Feb 2017 23:02:10 +0000 (23:02 +0000)]
Merge "Fix mips vpx_post_proc_down_and_across_mb_row_msa function"
James Zern [Thu, 16 Feb 2017 22:56:02 +0000 (22:56 +0000)]
Merge "disable VP9MultiThreadedFrameParallel tests"
paulwilkins [Thu, 16 Feb 2017 12:36:56 +0000 (12:36 +0000)]
cosmetics: Fix spelling mistake in compile flag name.
agressive -> aggressive
after:
ce7b38459 Aggressive VBR method.
Change-Id: Ie0f30b1bbc77ed9f32bec047b4a9b3d0cf4853f5
Johann Koenig [Thu, 16 Feb 2017 21:41:27 +0000 (21:41 +0000)]
Merge "correct bitdepth_conversion_sse2.h header guard"
James Zern [Thu, 16 Feb 2017 20:56:04 +0000 (12:56 -0800)]
disable VP9MultiThreadedFrameParallel tests
these are flaky and cause TSan warnings with clang-3.9.1
BUG=webm:1372
Change-Id: I8a7047552ba2ccd2d8c45f8795818c74562e5990
Johann [Thu, 16 Feb 2017 20:43:33 +0000 (12:43 -0800)]
correct bitdepth_conversion_sse2.h header guard
Change-Id: Ic4ffd861608e67fe59bcb3a86010ce3ef11a5519
Yi Luo [Thu, 16 Feb 2017 20:43:28 +0000 (20:43 +0000)]
Merge "Add idct32x32_135_add SSSE3 intrinsics"
Johann [Thu, 16 Feb 2017 19:12:31 +0000 (11:12 -0800)]
block error avx2: use tran_low_t
Change-Id: Ic5f3a1f569d6f82afeaf4fcd7235374bb460db3c
Johann Koenig [Thu, 16 Feb 2017 20:34:48 +0000 (20:34 +0000)]
Merge changes I267050a5,Iebade0ef,Id96a8df3
* changes:
quantize_fp_32x32 highbd ssse3: enable existing function
quantize_fp highbd ssse3: use tran_low_t for coeff
quantize_fp highbd sse2: use tran_low_t for coeff
Yi Luo [Wed, 15 Feb 2017 01:09:59 +0000 (17:09 -0800)]
Add idct32x32_135_add SSSE3 intrinsics
- Replace the corresponding assembly code.
- No user level speed performance degrade.
- Unit tests passed.
Change-Id: Idd0c5a4bad4976f1617c34100cb46e75e3b961e5
Yunqing Wang [Thu, 16 Feb 2017 16:22:54 +0000 (16:22 +0000)]
Merge "Structured the mode ordering code to avoid redundant memcpy"
Johann [Thu, 16 Feb 2017 15:29:32 +0000 (07:29 -0800)]
quantize_fp_32x32 highbd ssse3: enable existing function
This was created as part of the quantize_fp_ssse3 change. Both
functions use the same source file with different macro parameters.
Change-Id: I267050a559426a85955d215aa0aaca270439c5ab
Johann [Thu, 16 Feb 2017 03:01:38 +0000 (19:01 -0800)]
quantize_fp highbd ssse3: use tran_low_t for coeff
Change-Id: Iebade0efc0efbb0a80a0f3adbef4962e3a2f25e8
Johann [Fri, 3 Feb 2017 23:57:28 +0000 (15:57 -0800)]
quantize_fp highbd sse2: use tran_low_t for coeff
Change-Id: Id96a8df33354a7987ce890a3d6798c7375ffa4aa
Johann [Thu, 16 Feb 2017 01:17:45 +0000 (17:17 -0800)]
bitdepth conversion: really use num elements
The previous implementation confused bit/bytes/elements. It was using
'32' as the multiplier but that was mistakenly adopted because a 32x32
transform embedded the stride.
Change-Id: Ieeb867a332416b9a40580b5e7c9b20088e9e691a
Ranjit Kumar Tulabandu [Thu, 16 Feb 2017 14:07:39 +0000 (19:37 +0530)]
Structured the mode ordering code to avoid redundant memcpy
Change-Id: I4f5d6b54018bd1928cd9e5e42619e6f55b334803
Paul Wilkins [Thu, 16 Feb 2017 10:02:09 +0000 (10:02 +0000)]
Merge "Disconnect ARF breakout from frame boost."
Paul Wilkins [Thu, 16 Feb 2017 10:01:57 +0000 (10:01 +0000)]
Merge "Remove unnecessary factor."
Paul Wilkins [Thu, 16 Feb 2017 10:01:45 +0000 (10:01 +0000)]
Merge "Bug in scale_sse_threshold()"
Paul Wilkins [Thu, 16 Feb 2017 09:39:29 +0000 (09:39 +0000)]
Merge "Additional first pass stats."
Kaustubh Raste [Thu, 16 Feb 2017 06:42:24 +0000 (12:12 +0530)]
Fix mips vpx_post_proc_down_and_across_mb_row_msa function
Added fix to handle non-multiple of 16 cols case for size 16
Change-Id: If3a6d772d112077c5e0a9be9e612e1148f04338c
Johann Koenig [Thu, 16 Feb 2017 02:40:59 +0000 (02:40 +0000)]
Merge "Use 'packssdw' for loading tran_low_t values"
Johann Koenig [Thu, 16 Feb 2017 01:00:44 +0000 (01:00 +0000)]
Merge "vp8_dx_iface: remove unused 'else' condition"
James Zern [Thu, 16 Feb 2017 00:21:19 +0000 (00:21 +0000)]
Merge "vpx_temporal_svc_encoder.sh: remove FUNCNAME bashism"
Marco Paniconi [Wed, 15 Feb 2017 23:03:27 +0000 (23:03 +0000)]
Merge "vp9: Some code cleanup for aq-mode = 3."
Marco [Wed, 15 Feb 2017 21:51:14 +0000 (13:51 -0800)]
vp9: Some code cleanup for aq-mode = 3.
The weight segment needs to only be computed once per frame,
so remove it from the funciton vp9_cyclic_refresh_rc_bits_per_mb(),
which is called within a loop inside vp9_rc_regulate_q.
Change-Id: Ia0e18b89abb97e42c466d4dbc47700d7f76555db
Jerome Jiang [Wed, 15 Feb 2017 03:09:15 +0000 (19:09 -0800)]
vpx_temporal_svc_encoder: Expose error resilient control to cmd line.
Change-Id: Ic74a8690b136ffbc370080f70b2d5a6b1572bf63
Linfeng Zhang [Wed, 15 Feb 2017 20:18:23 +0000 (20:18 +0000)]
Merge "cosmetics,dsp/inv_txfm.c: reorder functions"
Marco Paniconi [Wed, 15 Feb 2017 20:07:19 +0000 (20:07 +0000)]
Merge "vp9. Use same source_sad threshold for all speeds."
Linfeng Zhang [Wed, 15 Feb 2017 00:27:30 +0000 (16:27 -0800)]
cosmetics,dsp/inv_txfm.c: reorder functions
Change-Id: Ie0f7689ebe230c68eadb22a32b14838c1a7543a6
Linfeng Zhang [Wed, 15 Feb 2017 19:34:18 +0000 (19:34 +0000)]
Merge "Add vpx_highbd_idct16x16_38_add_neon()"
Marco [Wed, 15 Feb 2017 19:26:29 +0000 (11:26 -0800)]
vp9. Use same source_sad threshold for all speeds.
Only affects real-time mode.
Change-Id: Iba836f110c4da936f5173cc0f54424d5b6121bff
Marco [Wed, 15 Feb 2017 17:18:34 +0000 (09:18 -0800)]
Vp9: Speed 8 aq-mode=3: Reduce computation in estimating bits per mb.
vp9_compute_qdelta_by_rate has almost 2% overhead in profiling on Nexus 6.
Reduce the calling of that function in speed 8 by estimating the delta-q.
Both rtc and rtc_derf show little/no change in avg psnr/ssim.
Encoding speed is 2~3% faster on Nexus 6.
Change-Id: If25933715783f31104a18a5092ea347b1221b5f5
Linfeng Zhang [Wed, 8 Feb 2017 00:58:12 +0000 (16:58 -0800)]
Add vpx_highbd_idct16x16_38_add_neon()
BUG=webm:1301
Change-Id: Ic6cd8c1e63e1b7a997cbed221e20fff4c599e0fe
Linfeng Zhang [Wed, 15 Feb 2017 17:06:16 +0000 (17:06 +0000)]
Merge "Add vpx_highbd_idct16x16_38_add_c()"
paulwilkins [Wed, 15 Feb 2017 10:33:10 +0000 (10:33 +0000)]
Disconnect ARF breakout from frame boost.
This small change replaces the frame boost check in the arf group
length break out clause with a test against a prediction decay value.
The boost value is in fact partly dependent on the decay value but
this change means that the per frame boost calculation can be adjusted
without influencing the group length calculation.
The value chosen gives a close match on all the test sets with the previous
code (on average) but it was noted that a lower threshold was slightly better
for 1080P and up and a slightly higher value for small image sizes.
Change-Id: I4d5b9f67d5b17b0d99ea3f796d3d6202fd61ee0c
paulwilkins [Tue, 14 Feb 2017 10:35:12 +0000 (10:35 +0000)]
Remove unnecessary factor.
Removed unnecessary scaling factor to simplify.
Change-Id: I3fc9c5975a2597e72f1324e09dd586dea1facfa7
paulwilkins [Thu, 9 Feb 2017 16:30:38 +0000 (16:30 +0000)]
Bug in scale_sse_threshold()
The function scale_sse_threshold() returns a threshold scaled
if necessary for use with 10 and 12 bit from an 8 bit baseline.
SSE error values would be expected to rise for the 10 and 12
bit cases where there are more bits of precision.
Hence the threshold used for the test should also be scaled up.
Change-Id: I4009c98b6eecd1bf64c3c38aaa56598e0136b03d
paulwilkins [Mon, 12 Dec 2016 14:05:19 +0000 (14:05 +0000)]
Additional first pass stats.
Added counts that split the intra coded blocks into low and high variance.
Change-Id: Ic540144b34d5141659081bb22f7ee16fd6861f14
Paul Wilkins [Wed, 15 Feb 2017 10:37:02 +0000 (10:37 +0000)]
Merge "Aggressive VBR method."
James Zern [Wed, 15 Feb 2017 07:44:00 +0000 (23:44 -0800)]
vpx_temporal_svc_encoder.sh: remove FUNCNAME bashism
replace with an explicit output file prefix that matches the function
name
Change-Id: I7f6a4105adb34327b1099a5fbf132aa8d1ad5b90
Johann Koenig [Wed, 15 Feb 2017 01:33:00 +0000 (01:33 +0000)]
Merge "vp9 fdct higbd neon: connect existing highbd calls"
Linfeng Zhang [Tue, 14 Feb 2017 23:39:37 +0000 (15:39 -0800)]
Add vpx_highbd_idct16x16_38_add_c()
When eob is less than or equal to 38 for high-bitdepth 16x16 idct,
call this function.
BUG=webm:1301
Change-Id: I09167f89d29c401f9c36710b0fd2d02644052060
Yunqing Wang [Wed, 15 Feb 2017 00:54:10 +0000 (00:54 +0000)]
Merge "Row based multi-threading of encoding stage"
Ranjit Kumar Tulabandu [Fri, 10 Feb 2017 10:55:50 +0000 (16:25 +0530)]
Row based multi-threading of encoding stage
(Yunqing Wang)
This patch implements the row-based multi-threading within tiles in
the encoding pass, and substantially speeds up the multi-threaded
encoder in VP9.
Speed tests at speed 1 on STDHD(using 4 tiles) set show that the
average speedups of the encoding pass(second pass in the 2-pass
encoding) is 7% while using 2 threads, 16% while using 4 threads,
85% while using 8 threads, and 116% while using 16 threads.
Change-Id: I12e41dbc171951958af9e6d098efd6e2c82827de
Linfeng Zhang [Wed, 15 Feb 2017 00:46:29 +0000 (00:46 +0000)]
Merge "Replace 14 with DCT_CONST_BITS in idct NEON functions' shifts"
Johann [Tue, 31 Jan 2017 23:40:58 +0000 (15:40 -0800)]
vp8_dx_iface: remove unused 'else' condition
Clears up static clang analysis warning regarding a dead store.
Change-Id: If4fe7a9a7f94c6e2001d46136944f90712e543b4
Johann [Tue, 14 Feb 2017 22:26:09 +0000 (14:26 -0800)]
Use 'packssdw' for loading tran_low_t values
This matches bitdepth_conversion_sse2.asm and produces substantially
better assembly. The old way had lots of 'movzwl' and 'shl' and storing
back to memory before loading into an xmm register.
Change-Id: Ib33e35354dfd691a4f8b1e39f4dbcbb14cd5302b
Johann [Fri, 3 Feb 2017 23:25:50 +0000 (15:25 -0800)]
vp9 fdct higbd neon: connect existing highbd calls
Change-Id: Ia8f822bd6e70b3911bc433a5a750bfb6f9a3a75c
Johann Koenig [Tue, 14 Feb 2017 21:28:22 +0000 (21:28 +0000)]
Merge "quantize_fp highbd neon: use tran_low_t for coeff"
Linfeng Zhang [Tue, 14 Feb 2017 20:44:57 +0000 (12:44 -0800)]
Replace 14 with DCT_CONST_BITS in idct NEON functions' shifts
Change-Id: I2a39a3bb87516b04d273bc1c0f4a634e3fb6f0f6
clang-format [Tue, 14 Feb 2017 04:06:18 +0000 (20:06 -0800)]
apply clang-format
Change-Id: I75e4a9e0b37bd4586f26c8d6c1fa27f3f6ff1bce
James Zern [Wed, 1 Feb 2017 02:06:43 +0000 (18:06 -0800)]
.clang-format: update to 3.9.1
Change-Id: Ia51f2201df897651067d09122075953382b59139
Yi Luo [Tue, 14 Feb 2017 20:13:26 +0000 (20:13 +0000)]
Merge "Replace idct32x32_34_add_ssse3 assembly with intrinsics"
Yi Luo [Wed, 8 Feb 2017 19:09:03 +0000 (11:09 -0800)]
Replace idct32x32_34_add_ssse3 assembly with intrinsics
- No user-level speed performance change.
- Pass unit tests.
Change-Id: Idfc598e00f354265e41f6b3219f4734216c115c6
Johann [Fri, 3 Feb 2017 22:24:32 +0000 (14:24 -0800)]
quantize_fp highbd neon: use tran_low_t for coeff
Change-Id: I90fd815f15884490ad138f35df575a00d31e8c95
Johann [Tue, 31 Jan 2017 23:51:15 +0000 (15:51 -0800)]
vp8 onyx_if: assert divide by zero
Clears up static clang analysis warning regarding divide by zero.
Trying to explain to the compiler how it's impossible to avoid
incrementing num_blocks at least once is difficult.
Change-Id: Ibaae43be572e5cd7a689b440dcd341c17d33443b
Johann Koenig [Tue, 14 Feb 2017 03:02:50 +0000 (03:02 +0000)]
Merge "Remove UNINITIALIZED_IS_SAFE"
Linfeng Zhang [Tue, 14 Feb 2017 01:15:34 +0000 (01:15 +0000)]
Merge "Add vpx_highbd_idct16x16_256_add_neon()"
Johann [Tue, 31 Jan 2017 23:18:40 +0000 (15:18 -0800)]
Remove UNINITIALIZED_IS_SAFE
Where clang static analysis or gcc -Wmaybe-uninitialized warns of
uninitialized values, assign 0 to ints, MB_MODE_COUNT to
MB_PREDICTION_MODE, and B_MODE_COUNT to B_PREDICTION_MODE.
Assert that the modes have been changed from the invalid value by
the end of the function.
Change-Id: Ib11e1ffb08f0a6fe4b6c6729dc93b83b1c4b6350
Linfeng Zhang [Thu, 2 Feb 2017 00:32:57 +0000 (16:32 -0800)]
Add vpx_highbd_idct16x16_256_add_neon()
BUG=webm:1301
Change-Id: I6bb755552a39bdd26eef3f449601f6a9766c65ec
Johann Koenig [Mon, 13 Feb 2017 23:11:30 +0000 (23:11 +0000)]
Merge "fdct8x8 highbd neon: use tran_low_t for output"
Johann [Fri, 3 Feb 2017 23:14:06 +0000 (15:14 -0800)]
fdct8x8 highbd neon: use tran_low_t for output
Change-Id: I100c4a1955d80bec4d28e82796b3e7f57e84d0ba
Yunqing Wang [Mon, 13 Feb 2017 20:29:31 +0000 (12:29 -0800)]
The bitstream bit match test in multi-threaded encoder
While the new-mt mode is enabled(namely, allowing to use row-based
multi-threading in encoder), several speed features that adaptively
adjust encoding parameters during encoding would cause mismatch
between single-thread encoded bitstream and multi-thread encoded
bitstream. This patch provides a set_control API to disable these
features, so that the bit match bitstream is obtained in the unit
test.
Change-Id: Ie9868bafdfe196296d1dd29e0dca517f6a9a4d60
Yunqing Wang [Mon, 13 Feb 2017 21:01:41 +0000 (21:01 +0000)]
Merge "Minor code style refactoring"
James Zern [Mon, 13 Feb 2017 21:01:18 +0000 (21:01 +0000)]
Merge "cosmetics,vp9_ratectrl: apply clang-format"
James Zern [Mon, 13 Feb 2017 21:00:33 +0000 (21:00 +0000)]
Merge "vpx_usec_timer_elapsed: use 64-bit math"
Yunqing Wang [Mon, 13 Feb 2017 20:59:01 +0000 (12:59 -0800)]
Minor code style refactoring
Change-Id: I20107693d0a87e08a10520bfb573ff3dcef69fdb
James Zern [Mon, 13 Feb 2017 19:29:39 +0000 (11:29 -0800)]
cosmetics,vp9_ratectrl: apply clang-format
broken since:
c3f095c8b Merge "Fix to avoid abrupt relaxation of max qindex in recode path"
5f21aba4b Fix to avoid abrupt relaxation of max qindex in recode path
the original change pre-dated the addition of .clang-format
Change-Id: If5e399d9a805bcad9147360b13b36fbc8c560a7c
Linfeng Zhang [Fri, 13 Jan 2017 18:01:51 +0000 (10:01 -0800)]
Add vpx_highbd_idct{16x16,32x32}_1_add_neon()
and update vpx_highbd_idct8x8_1_add_neon()
BUG=webm:1301
Change-Id: I18d1a0cbe98ba822d5194c1b4e13a4c29c5c75f4
paulwilkins [Thu, 5 Jan 2017 12:35:53 +0000 (12:35 +0000)]
Aggressive VBR method.
VBR method that allows a wider Q range for the first normal frame
in each ARF group and then centers the min - max range for the rest of
the arf group on the chosen Q value for that first frame.
This allows for quite rapid adjustment of the active Q range even if the
initial estimate is poor.
In some cases where the ARF frames themselves are tending to
undershoot but the normal frames are overshooting this can still give
net undershoot. This can be corrected by allowing a larger Q delta for
arf frames but is usually is a sign that the allocation to the arfs was to
high.
Change-Id: Icec87758925d8f7aeb2dca29aac0ff9496237469
James Zern [Sat, 11 Feb 2017 03:42:35 +0000 (03:42 +0000)]
Merge "Add vpx_idct16x16_38_add_neon()"
Marco [Tue, 7 Feb 2017 19:46:36 +0000 (11:46 -0800)]
vp9: Non-rd mode: use simple block_yrd for 8 bit high bitdepth builds
Temporary fix until optimization work for block_yrd is completed.
This essentially reverts back to the state before the change:
https://chromium-review.googlesource.com/c/433821/
Compression loss is about ~5-6% on RTC set.
Speed-up (from using this simple/model-based block_yrd) over the low
bitdepth builds (which uses more complex block_yrd) is ~5% on 720p.
Change-Id: Ie0af9eb0d111e5595f587870c44f08317403b8d8
James Zern [Fri, 10 Feb 2017 03:28:59 +0000 (19:28 -0800)]
vpx_usec_timer_elapsed: use 64-bit math
this prevents a rollover when tv_sec is a long:
signed integer overflow: 2776 * 1000000 cannot be represented in type
'long'
Change-Id: I03dc4476ee122b02e2856dad28358a20cf16a9f8
Paul Wilkins [Thu, 9 Feb 2017 17:17:55 +0000 (17:17 +0000)]
Merge "Fix to avoid abrupt relaxation of max qindex in recode path"
Paul Wilkins [Thu, 9 Feb 2017 17:17:44 +0000 (17:17 +0000)]
Merge "Fix for max qindex calculation of a gf interval"
Linfeng Zhang [Tue, 7 Feb 2017 18:06:21 +0000 (10:06 -0800)]
Add vpx_idct16x16_38_add_neon()
The RunQuantCheck() test on it exposes 16-bit overflow in stage 7 of
pass 2. Change to use saturating add/sub for both
vpx_idct16x16_38_add_neon() and vpx_idct16x16_256_add_neon() for high
bitdepth.
Change-Id: Ibf4c107a887553a52852cc582e28d38a5a5a2712
Yi Luo [Wed, 8 Feb 2017 00:40:10 +0000 (16:40 -0800)]
Replace idct8x8_12_add_ssse3 assembly code with intrinsics
- Performance achieves the same as assembly.
- Unit tests pass.
Change-Id: I6eacfbbd826b3946c724d78fbef7948af6406ccd
Linfeng Zhang [Wed, 8 Feb 2017 17:20:19 +0000 (17:20 +0000)]
Merge "Add vpx_idct16x16_38_add_c()"
Johann Koenig [Tue, 7 Feb 2017 23:26:09 +0000 (23:26 +0000)]
Merge "block_error_fp highbd sse2: use tran_low_t for coeff"
Marco Paniconi [Tue, 7 Feb 2017 22:24:59 +0000 (22:24 +0000)]
Merge "vp9: Denoiser speed-up: increase partition and ac skip thresholds."
Yunqing Wang [Tue, 7 Feb 2017 19:55:40 +0000 (19:55 +0000)]
Merge "Row based multi-threading of ARNR filtering stage"
Marco Paniconi [Tue, 7 Feb 2017 19:25:47 +0000 (19:25 +0000)]
Merge "vp9: Adjust rate_err threshold for setting active_worst factor."
Marco [Tue, 7 Feb 2017 01:02:28 +0000 (17:02 -0800)]
vp9: Denoiser speed-up: increase partition and ac skip thresholds.
Add factor to increase varianace partition and ac skip thresholds,
under certain conditions (noise level and sum_diff), to increase
denoiser speed.
Change-Id: I7671140ef3598bf5f114a72623d68792bcd7b77b
Linfeng Zhang [Wed, 11 Jan 2017 20:22:37 +0000 (12:22 -0800)]
Add vpx_idct16x16_38_add_c()
When eob is less than or equal to 38 for 16x16 idct, call this function.
Change-Id: Ief6f3fb16a49ace3c92cebf4e220bf5bf52a6087
Marco [Tue, 7 Feb 2017 17:35:56 +0000 (09:35 -0800)]
vp9: Adjust rate_err threshold for setting active_worst factor.
Only affects 1 pass vbr.
Small improvement on ytlive set.
Change-Id: I09a7456fe658fbea82ece1035cf683bd8bd8bd14
Linfeng Zhang [Tue, 7 Feb 2017 16:52:39 +0000 (16:52 +0000)]
Merge "Update 16x16 8-bit idct NEON intrinsics"
Johann [Thu, 2 Feb 2017 23:28:16 +0000 (15:28 -0800)]
block_error_fp highbd sse2: use tran_low_t for coeff
BUG=webm:1365
Change-Id: Id2ed3ebaaaa6a4b68628c23e08b64ea5f1341761
Ranjit Kumar Tulabandu [Mon, 6 Feb 2017 13:44:16 +0000 (19:14 +0530)]
Row based multi-threading of ARNR filtering stage
Change-Id: Ic238d32c7e10b730342224ab56712a89a6026a8f
Johann Koenig [Tue, 7 Feb 2017 02:49:58 +0000 (02:49 +0000)]
Merge "highbd x86: consolidate tran_low_t conversions"