aboutsummaryrefslogtreecommitdiff
path: root/source/row_neon64.cc
AgeCommit message (Collapse)Author
2023-06-30Fix warnings for missing prototypesFrank Barchard
- Add static to internal scale and rotate functions - Remove unittest that tested an internal scale function - Remove unused private functions - Include missing scale_argb.h header - Bump version and apply clang format Bug: libyuv:830 Change-Id: I45bab0423b86334f9707f935aedd0c6efc442dd4 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4658956 Reviewed-by: Mirko Bonadei <mbonadei@chromium.org>
2023-06-16ARGBAttenuate use (a + b + 255) >> 8Frank Barchard
- Makes ARM and Intel match and fixes some off by 1 cases - Add ARGBToUV444MatrixRow_NEON - Add ConvertFP16ToFP32Column_NEON - scale_rvv fix intinsic build error - disable row_win version of ARGBAttenuate/Unattenuate Bug: libyuv:936, libyuv:956 Change-Id: Ied99aaad3a11a8eb69212b628c58f86ec0723c38 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4617013 Reviewed-by: Wan-Teh Chang <wtc@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2023-06-07FP16 to FP32 float conversion row functionFrank Barchard
Bug: None Change-Id: I97aab6aafd41c3bf36bfbf33fdcc424e5b3fd6e3 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4590225 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Wan-Teh Chang <wtc@google.com>
2023-06-02Fix tidy warning that uint32_t dither4 should not be constFrank Barchard
- Remove const from uint32_t dither4 parameter to fix clang-tidy warning - Apply clang format - Bump version - Remove unused MMI source; superceded by MSA Bug: None Change-Id: Id49991db25bca4e99590b415312542d917471c62 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4581882 Reviewed-by: Wan-Teh Chang <wtc@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2023-03-24AArch32 YUVTORGB_SETUP use load and dup to avoid modifying pointerFrank Barchard
- Allows code to be optimized with clang 17 -flto-thin - Bump version number to 1864 to allow detection of fix - Apply clang format to standardize formatting; No impact on code generated Bug: chromium:1424089 Change-Id: Ib745836b27915a5e4cb1d7d928ee52659360612b Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4370052 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Justin Green <greenjustin@google.com>
2023-03-24clang 17 -flto-thin bug fix for Neon YUVtoRGB and ARGBToRGB565DitherFrank Barchard
- YUV to RGB AArch32 kRGBCoeffBias rewind pointer - ARGBToRGB565Dither declare width and source pointers as modified Bug: chromium:1424089 Change-Id: I987180652331bab16ce27d8d166399a687ee890e Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4370099 Reviewed-by: Mirko Bonadei <mbonadei@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2023-03-16GCC warning fix for MT2TFrank Barchard
- Fix redundent assignment compile warning in GCC - Apply clang-format - Bump version to 1863 Bug: libyuv:955 Change-Id: If2b6588cd5a7f068a1745fe7763e90caa7277101 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4344729 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Mirko Bonadei <mbonadei@chromium.org>
2023-03-14M2T2 Unpack fixesJustin Green
Fix the algorithm for unpacking the lower 2 bits of M2T2 pixels. Bug: b:258474032 Change-Id: Iea1d63f26e3f127a70ead26bc04ea3d939e793e3 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4337978 Commit-Queue: Justin Green <greenjustin@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2023-02-22MergeUV AVX512BW use assemblyFrank Barchard
- Convert MergeUVRow_AVX512BW to assembly - Enable MergeUVRow_AVX512BW for Windows with clangcl - MergeUVRow_AVX2 use vpmovzxbw and vpsllw - MergeUVRow_16_AVX2 use vpmovzxbw and vpsllw with different shift for U and V AMD Zen 4 640x360 100000 iterations Was AVX512 MergeUVPlane_Opt (884 ms) AVX2 MergeUVPlane_Opt (945 ms) AVX2 MergeUVPlane_16_Opt (2167 ms) Now AVX512 MergeUVPlane_Opt (865 ms) AVX2 MergeUVPlane_Opt (943 ms) SSE2 MergeUVPlane_Opt (973 ms) AVX2 MergeUVPlane_16_Opt (2102 ms) Bug: None Change-Id: I658ada2a75d44c3f93be8bd3ed96f83d5fa2ab8d Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4271230 Reviewed-by: Fritz Koenig <frkoenig@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: richard winterton <rrwinterton@gmail.com>
2023-02-13MergeUV_AVX512BW for I420ToNV12Frank Barchard
On Skylake Xeon 640x360 100000 iterations AVX512 MergeUVPlane_Opt (1196 ms) AVX2 MergeUVPlane_Opt (1565 ms) SSE2 MergeUVPlane_Opt (1780 ms) Pixel 7 MergeUVPlane_Opt (1177 ms) Bug: None Change-Id: If47d4fa957cf27781bba5fd6a2f0bf554101a5c6 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4242247 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: richard winterton <rrwinterton@gmail.com>
2023-01-18Fix for DivideRow_NEON functionsFrank Barchard
- was dup of 8h but mul of 4s. now use umull Bug: libyuv:951 Change-Id: If6cb01f5f006c2235886b81ce120642d7e24a9bb Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4166563 Reviewed-by: Justin Green <greenjustin@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2023-01-17Fix for divide row functions used by P010ToI010Frank Barchard
Bug: libyuv:951 Change-Id: Id323656cb6f99b1be0be7aaa854d3cc15feeba69 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4166562 Reviewed-by: Justin Green <greenjustin@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2022-12-15Casting for scale functionsFrank Barchard
- MT2T support for source strides added, but only works for positive values. - Reduced casting in row_common - one cast per assignment. - scaling functions use intptr_t for intermediate calculations, then cast strides to ptrdiff_t Bug: libyuv:948, b/257266635, b/262468594 Change-Id: I0409a0ce916b777da2a01c0ab0b56dccefed3b33 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4102203 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Wan-Teh Chang <wtc@google.com> Reviewed-by: Justin Green <greenjustin@google.com> Reviewed-by: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Ernest Hua <ernesthua@google.com>
2022-12-06MT2T Warning fixes for fuchsiaFrank Barchard
Bug: b/258474032, b/257266635 Change-Id: Ic5cbbc60e2e1463361e359a2fe3e97976c1ea929 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4081348 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Justin Green <greenjustin@google.com>
2022-11-17Add Detile_16 planar function for 10 bit MT2T formatFrank Barchard
- Neon and SSE2 - Any for odd widths Pixel 2 little core AArch32 build C TestDetilePlane_16 (1275 ms) TestDetilePlane (1203 ms) Neon TestDetilePlane_16 (693 ms) TestDetilePlane (660 ms) Bug: b/258474032 Change-Id: Idbd09c5e9324e4deef5f1d54090d4b63cc7db812 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4031848 Reviewed-by: Wan-Teh Chang <wtc@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2022-09-30YUY2ToNV12 using YUY2ToY and YUY2ToNVUVFrank Barchard
- Optimized YUY2ToNV12 that reduces it from 3 steps to 2 steps - Was SplitUV, memcpy Y, InterpolateUV - Now YUY2ToY, YUY2ToNVUV - rollback LIBYUV_UNLIMITED_DATA 3840x2160 1000 iterations: Pixel 2 Cortex A73 Was YUY2ToNV12_Opt (6515 ms) Now YUY2ToNV12_Opt (3350 ms) AB7 Mediatek P35 Cortex A53 Was YUY2ToNV12_Opt (6435 ms) Now YUY2ToNV12_Opt (3301 ms) Skylake AVX2 x64 Was YUY2ToNV12_Opt (1872 ms) Now YUY2ToNV12_Opt (1657 ms) SSE2 x64 Was YUY2ToNV12_Opt (2008 ms) Now YUY2ToNV12_Opt (1691 ms) Windows Skylake AVX2 32 bit x86 Was YUY2ToNV12_Opt (2161 ms) Now YUY2ToNV12_Opt (1628 ms) Bug: libyuv:943 Change-Id: I6c2ba2ae765413426baf770b837de114f808f6d0 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3929843 Reviewed-by: Wan-Teh Chang <wtc@google.com> Reviewed-by: richard winterton <rrwinterton@gmail.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2022-09-20I422ToRGB24, I422ToRAW, I422ToRGB24MatrixFilter conversion functions added.Frank Barchard
- YUV to RGB use linear for first and last row. - add assert(yuvconstants) - rename pointers to match row functions. - use macros that match row functions. - use 12 bit upsampler for conversions of 10 and 12 bits Cortex A53 AArch32 I420ToRGB24_Opt (3627 ms) I422ToRGB24_Opt (4099 ms) I444ToRGB24_Opt (4186 ms) I420ToRGB24Filter_Opt (5451 ms) I422ToRGB24Filter_Opt (5430 ms) AVX2 Was I420ToRGB24Filter_Opt (583 ms) Now I420ToRGB24Filter_Opt (560 ms) Neon Cortex A7 Was I420ToRGB24Filter_Opt (5447 ms) Now I420ToRGB24Filter_Opt (5439 ms) Bug: libyuv:938 Change-Id: I1731f2dd591073ae11a756f06574103ba0f803c7 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3906082 Reviewed-by: Justin Green <greenjustin@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2022-09-16I420ToRGB24MatrixFilter function addedFrank Barchard
- Implemented as 3 steps: Upsample UV to 4:4:4, I444ToARGB, ARGBToRGB24 - Fix some build warnings for missing prototypes. Pixel 4 I420ToRGB24_Opt (743 ms) I420ToRGB24Filter_Opt (1331 ms) Windows with skylake xeon: x86 32 bit I420ToRGB24_Opt (387 ms) I420ToRGB24Filter_Opt (571 ms) x64 64 bit I420ToRGB24_Opt (384 ms) I420ToRGB24Filter_Opt (582 ms) Bug: libyuv:938, libyuv:830 Change-Id: Ie27f70816ec084437014f8a1c630ae011ee2348c Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3900298 Reviewed-by: Wan-Teh Chang <wtc@google.com>
2022-08-16MM21ToYUY2 and ABGRToJ420 conversionFrank Barchard
MM21 to YUY2 use zip1 for performance Cortex A510 Was MM21ToYUY2 (612 ms) Now MM21ToYUY2 (573 ms) Prefetches help Cortex A53 Was MM21ToYUY2 (4998 ms) Now MM21ToYUY2 (1900 ms) Pixel 4 Cortex A76 Was MM21ToYUY2 (215 ms) Now MM21ToYUY2 (173 ms) ABGRToJ420 - NEON, SSSE3 and AVX2 row functions - J400, J420 and J422 formats. - Added AVX2 for UV on ARGBToJ420. Was SSSE3 Same code/performance as ARGBToJ420 but with constants re-ordered. Pixel 4 ABGRToJ420_Opt (623 ms) ABGRToJ422_Opt (702 ms) ABGRToJ400_Opt (238 ms) Skylake Xeon With LIBYUV_BIT_EXACT which uses C for UV ABGRToJ420_Opt (988 ms) ABGRToJ422_Opt (1872 ms) ABGRToJ400_Opt (186 ms) Skylake Xeon using AVX2 ABGRToJ420_Opt (251 ms) ABGRToJ422_Opt (245 ms) ABGRToJ400_Opt (184 ms) Skylake Xeon using SSSE3 ABGRToJ420_Opt (328 ms) ABGRToJ422_Opt (362 ms) ABGRToJ400_Opt (185 ms) Bug: b/238137982 Change-Id: I559c3fe3fb80fa2ce5be3d8218736f9cbc627666 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3832111 Reviewed-by: Justin Green <greenjustin@google.com> Reviewed-by: Wan-Teh Chang <wtc@google.com> Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2022-08-04row_neon*: Explicitly initialize pad in RgbConstantsVignesh Venkatasubramanian
Explicitly initialize the 'pad' field of RgbConstants to 0. This prevents the following warning/error in some compilers: error: missing field 'pad' initializer [-Werror,-Wmissing-field-initializers] Bug: b/241008246 Change-Id: Id6a0beb75c5c709404290c75915049f8a3898c83 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3808044 Reviewed-by: Wan-Teh Chang <wtc@google.com>
2022-06-29Merge/SplitRGB fix -mcmodel=large x86 and InterpolateRow_16To8_NEONFrank Barchard
MergeRGB and SplitRGB use a register to point to 9 shuffle tables. - fixes an out of registers error with -mcmodel=large InterpolateRow_16To8_NEON improves performance for I210ToI420: On Pixel 4 for 720p x1000 images Was I210ToI420_Opt (608 ms) Now I210ToI420_Opt (336 ms) On Skylake Xeon Was I210ToI420_Opt (259 ms) Now I210ToI420_Opt (209 ms) Bug: libyuv:931, libyuv:930 Change-Id: I20f8244803f06da511299bf1a2ffc7945eb35221 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3717054 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Justin Green <greenjustin@google.com>
2022-06-22Bilinear scale up msan fixFrank Barchard
- Avoid stepping to height + 1 for bilinear filter 2nd row for last row of source - Box filter ubsan fix for 3/4 and 3/8 scaling for 16 bit planar - Height 1 asan fixes Bug: libyuv:935, b/206716399 Change-Id: I56088520f2a884a37b987ee5265def175047673e Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3717263 Reviewed-by: Wan-Teh Chang <wtc@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2022-06-09Add I210ToI420Frank Barchard
Bug: libyuv:931, b/228605787, b/233233302, b/233634772, b/234558395, b/234340482 Change-Id: Ib135d0b4ff17665f6a4ab60edb782a7b314219a4 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3696042 Reviewed-by: Mirko Bonadei <mbonadei@chromium.org>
2022-06-08Convert16To8Row_NEON use shift without roundingFrank Barchard
Fixes chromium PaintCanvasVideoRendererTest.HighBitDepth sqdmulh was creating a 9 bit value with rounding, and then shifted it right 1 with no rounding. The rounding had an off by 1 impact in some tests. Pixel 3 C I010ToI420_Opt (749 ms) Was sqdmulh I010ToI420_Opt (370 ms) Now ushl I010ToI420_Opt (324 ms) Pixel 4 C I010ToI420_Opt (581 ms) Was sqdmulh I010ToI420_Opt (240 ms) Now ushl I010ToI420_Opt (231 ms) Bug: b/216321733, b/233233302 Change-Id: I26f673bb411401d1e4a8126bf22d61c649223e9b Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3694143 Reviewed-by: Justin Green <greenjustin@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2022-06-07Revert "I210ToI420, InterpolatePlane_16, and ScalePlane Vertical-only asan fix"Frank Barchard
This reverts commit 60254a1d846a93a4d7559009004cdd91bcc04d82. Reason for revert: breaks PaintCanvasVideoRendererTest.HighBitDepth Original change's description: > I210ToI420, InterpolatePlane_16, and ScalePlane Vertical-only asan fix > > - Add I210ToI420 to convert 10 bit 4:2:2 YUV to 4:2:0 8 bit > - Add NEON InterpolateRow_16 for fast 10 bit scaling > - When scaling up, set step to interpolate toward height - 1 to avoid buffer overread > - When scaling down, center the 2 rows used for source to achieve filtering. > - CopyPlane check for 0 size and return > > Bug: libyuv:931, b/228605787, b/233233302, b/233634772, b/234558395, b/234340482 > Change-Id: I63e8580710a57812b683c2fe40583ac5a179c4f1 > Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3687552 > Reviewed-by: Mirko Bonadei <mbonadei@chromium.org> > Reviewed-by: richard winterton <rrwinterton@gmail.com> Bug: libyuv:931, b/228605787, b/233233302, b/233634772, b/234558395, b/234340482 Change-Id: Icc05bb340db0e7fe864061fb501d0a861c764116 No-Presubmit: true No-Tree-Checks: true No-Try: true Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3692886 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Commit-Queue: Mirko Bonadei <mbonadei@chromium.org> Reviewed-by: Mirko Bonadei <mbonadei@chromium.org>
2022-06-07I210ToI420, InterpolatePlane_16, and ScalePlane Vertical-only asan fixFrank Barchard
- Add I210ToI420 to convert 10 bit 4:2:2 YUV to 4:2:0 8 bit - Add NEON InterpolateRow_16 for fast 10 bit scaling - When scaling up, set step to interpolate toward height - 1 to avoid buffer overread - When scaling down, center the 2 rows used for source to achieve filtering. - CopyPlane check for 0 size and return Bug: libyuv:931, b/228605787, b/233233302, b/233634772, b/234558395, b/234340482 Change-Id: I63e8580710a57812b683c2fe40583ac5a179c4f1 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3687552 Reviewed-by: Mirko Bonadei <mbonadei@chromium.org> Reviewed-by: richard winterton <rrwinterton@gmail.com>
2022-05-24Convert16To8 NEONFrank Barchard
Pixel 3 Was C I010ToI420_Opt (749 ms) Now NEON I010ToI420_Opt (356 ms) Pixel 4 Was C I010ToI420_Opt (581 ms) Now NEON I010ToI420_Opt (163 ms) Bug: b/233233302, b/233634772 Change-Id: I60a84648a66f77d97c0a7822b29bd18b8e3a3355 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3661401 Reviewed-by: Justin Green <greenjustin@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2022-03-25Declare RgbConstants structs as static constWan-Teh Chang
These RgbConstants structs were added in https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3534023. They should be declared as static const. These four symbols were detected by Chrome's android-binary-size trybot as "Mutable Constants". Change-Id: I3b4d4ff4b32e261ba528c07647b9d69ac368ab5b Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3553035 Reviewed-by: Mirko Bonadei <mbonadei@chromium.org> Commit-Queue: Wan-Teh Chang <wtc@google.com>
2022-03-18RAWToJ400 faster version for ARMFrank Barchard
- Unrolled to 16 pixels - Take constants via structure, allowing different colorspace and channel order - Use ADDHN to add 16.5 and take upper 8 bits of 16 bit values, narrowing to 8 bits - clang-format applied, affecting mips code On Cortex A510 Was RAWToJ400_Opt (1623 ms) Now RAWToJ400_Opt (862 ms) C RAWToJ400_Opt (1627 ms) Bug: b/220171611 Change-Id: I06a9baf9650ebe2802fb6ff6dfbd524e2c06ada0 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3534023 Reviewed-by: Wan-Teh Chang <wtc@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2022-02-23Fix RotatePlane by 90 on Neon when source width is not a multiple of 8Frank Barchard
Bug: b/220888716, b/218875554, b/220205245 Change-Id: I17e118ac9b9a7013386a5f0ad27a2dd249474ae5 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3483576 Reviewed-by: Mirko Bonadei <mbonadei@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2022-02-03Add support for MM21.Justin Green
Add support for MM21 to NV12 and I420 conversion, and add SIMD optimizations for arm, aarch64, SSE2, and SSSE3 machines. Bug: libyuv:915, b/215425056 Change-Id: Iecb0c33287f35766a6169d4adf3b7397f1ba8b5d Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3433269 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Commit-Queue: Justin Green <greenjustin@google.com>
2022-01-31DetilePlane and unittest for NEONFrank Barchard
Bug: libyuv:915, b/215425056 Change-Id: Iccab1ed3f6d385f02895d44faa94d198ad79d693 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3424820 Reviewed-by: Justin Green <greenjustin@google.com> Reviewed-by: Frank Barchard <fbarchard@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2022-01-26Remove MMI supportFrank Barchard
Bug: libyuv:916 Change-Id: I345b7e271ceb4b32fe91e292915e66be40812810 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3415817 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Wan-Teh Chang <wtc@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2022-01-14I420ToARGB for AVX512Frank Barchard
On Skylake Xeon AVX512 I420ToARGB_Opt (2050 ms) AVX2 I420ToARGB_Opt (2533 ms) SSSE3 I420ToARGB_Opt (3688 ms) Bug: libyuv:911 Change-Id: I2214cc15dec24b06541895ca59d88990edbb2216 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3382100 Reviewed-by: richard winterton <rrwinterton@gmail.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2021-12-10J400ToARGB optimized for Exynos using ZIP+ST1Frank Barchard
Bug: 204562143 Change-Id: I56c98198c02bd0dd1283f1c14837730c92832c39 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3328702 Reviewed-by: richard winterton <rrwinterton@gmail.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2021-11-24NV21ToYUV24 replace ST3 with ST1. ARGBToAR64 replace ST2 with ST1Frank Barchard
On Samsung S8 Exynos M2 Was ST3 NV21ToYUV24_Opt (769 ms) Now ST1 NV21ToYUV24_Opt (473 ms) Was ST2 ARGBToAR64_Opt (1759 ms) Now ST1 ARGBToAR64_Opt (987 ms) Skylake Xeon, AVX2 version: Was NV21ToYUV24_Opt (885 ms) Now NV21ToYUV24_Opt (194 ms) Bug: b/204562143, b/124413599 Change-Id: Icc9cb64d822cd11937789a4e04fbb773b3e33aa3 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3290664 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: richard winterton <rrwinterton@gmail.com>
2021-10-28Android420ToI420Rotate function to convert with rotationFrank Barchard
- adapted from Android420ToI420, adding a rotation parameter - SplitRotateUV added to rotate and split the UV channel of NV12 or NV21 - rename RotateUV functions to SplitRotateUV Bug: b/203549508 Change-Id: I6774da5fb5908fdf1fc12393f0001f41bbda9851 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3251282 Reviewed-by: richard winterton <rrwinterton@gmail.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2021-10-19Enable SIMD for exact RGB to Y conversionsFrank Barchard
Bug: libyuv:908, b/202888439 Change-Id: Icc5470b85d91b441ded9958ee04b4f32246646f0 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3230489 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Mirko Bonadei <mbonadei@chromium.org>
2021-10-15BIT_EXACT for unattenuate and attenuate.Frank Barchard
- reenable Intel SIMD unaffected by BIT_EXACT - add bit exact version of ARGBAttenuate, which uses ARM version of formula. - add bit exact version of ARGBUnatenuate, which mimics the AVX code. Apply clang format to cleanup code. Bug: libyuv:908, b/202888439 Change-Id: Ie842b1b3956b48f4190858e61c02998caedc2897 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3224702 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: richard winterton <rrwinterton@gmail.com>
2021-10-12Fix for failed compile with armv-7a neon gccFrank Barchard
Bug: libyuv:907 Change-Id: I955e83c72b57ce5ba45730030b32f337be610a21 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3216739 Reviewed-by: Mirko Bonadei <mbonadei@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2021-09-09change ld1 to ldr for memory references to allow GCC to use an offsetFrank Barchard
Bug: chromium:819294, libyuv:903 Change-Id: I1cd19cc5a068c421d1112c9ea6090e18fb002a4c Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3152821 Reviewed-by: Wan-Teh Chang <wtc@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2021-09-09GCC: force memory address without offset on aarch64Stephan Hartmann
With "m" GCC generates a memory address with offset which is not allowed with ld1 on aarch64. Change constraint to "Q" to force address without offset. Bug: chromium:819294, libyuv:903 Change-Id: Iaae24bc6882cdef823259040a37fdbfc31f91185 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2922146 Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2021-04-30Make 2 step transitive tests measure 2 step time.Frank Barchard
Add tests of all macros used by libyuv public headers When a 1 step conversion is added, a 2 step test can compare the old 2 step method to the 1 step. A 1 step unittest is also added which compares C to SIMD. Making the 2 step conversions measure performance of the 2 steps allows the old 2 step performance to be compared to 1 step. All macros used in public headers are added to an ifdef test. Showing them in a unittest allows some diagnostics when a test is failing. Bug: libyuv:901 Change-Id: I7ffa6ed0cb3b506fa1b7fd4b7b1b729658c3c266 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2857916 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Mirko Bonadei <mbonadei@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2021-04-19Unlimited data for IntelYuan Tong
Use unsigned coefficients on Intel. Make C, NEON and AVX2 match under LIBYUV_UNLIMITED_DATA. Bug: libyuv:862, libyuv:863 Change-Id: I6c02147ea3c1875c4fc23863435aea86dcf5880a Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2830180 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Reviewed-by: richard winterton <rrwinterton@gmail.com>
2021-04-15Refactor NEON YUVToRGB, Remove subsamplingYuan Tong
Refactor NEON YUVToRGB Assembly to support HBD data as input and output. Work on YUV444 internally, remove subsampling in I444ToARGB. libyuv_unittest --gtest_filter=*.NV??ToARGB_Opt:*UYVYToARGB_Opt:*YUY2ToARGB_Opt:*I4*ToARGB_Opt Bug: libyuv:895, libyuv:862, libyuv:863 Change-Id: I05b56ea8ea56d9e523720b842fa6e4b122ed4115 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2810060 Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2021-04-09use width + 1 for odd width testsFrank Barchard
Bug: libyuv:894, libyuv:898, libyuv:899 Change-Id: Ieba8eaeb8b06f0323824967776673e339b263220 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2809701 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Mirko Bonadei <mbonadei@chromium.org>
2021-04-01clang-tidy appliedFrank Barchard
Bug: libyuv:886, libyuv:889 Change-Id: I2d14d03c19402381256d3c6d988e0b7307bdffd8 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2800147 Reviewed-by: richard winterton <rrwinterton@gmail.com>
2021-03-31Add MergeAR30Plane, MergeAR64Plane, MergeARGB16To8PlaneYuan Tong
These functions merge high bit depth planar RGB pixels into packed format. Change-Id: I506935a164b069e6b2fed8bf152cb874310c0916 Bug: libyuv:886, libyuv:889 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2780468 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2021-03-24Fixes for SplitUVPlane_16 and MergeUVPlane_16Frank Barchard
Planar functions pass depth instead of scale factor. Row functions pass shift instead of depth. Add assert to C. AVX shift instruction expects a single shift value in XMM. Neon pass shift as input (not output). Split Neon reimplemented as left shift on shorts by negative to achieve right shift. Add planar unitests Bug: libyuv:888 Change-Id: I8fe62d3d777effc5321c361cd595c58b7f93807e Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2782086 Reviewed-by: richard winterton <rrwinterton@gmail.com> Reviewed-by: Mirko Bonadei <mbonadei@chromium.org>
2021-03-23Add RAWToJ420Frank Barchard
Add J420 output from RAW. Optimize RGB24 and RAW To J420 on ARM by using NEON for the 2 step conversion. Also fix sign-compare warning that was breaking Windows build Bug: libyuv:887, b/183534734 Change-Id: I8c39334552dc0b28414e638708db413d6adf8d6e Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2783382 Reviewed-by: Wan-Teh Chang <wtc@google.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-08 07:07:39 +0000