aboutsummaryrefslogtreecommitdiff
path: root/include/libyuv/scale_row.h
AgeCommit message (Collapse)Author
2023-12-08Split convert_test and convert_argb_test to allow building on small systems ↵Frank Barchard
that run out of memory compiling unittests. Update build files to include the new tests and source code. Bug: libyuv:956 Change-Id: I6ec0beb6dc9570f0597d7df1835d616489dbaece Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/5103585 Reviewed-by: Mirko Bonadei <mbonadei@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2023-12-07Add HAS_SCALEARGBROWDOWNEVEN_RVV marco and disable it by defaultBruce Lai
HAS_SCALEARGBROWDOWNEVEN_RVV wasn't defined, so we cannot use ScaleARGBRowDownEven_RVV & ScaleARGBRowDownEvenBox_RVV. - Seperate to two conditional statements when selecting DownEven or DownEvenBox. - Also, add HAS_SCALEARGBROWDOWNEVEN_RVV and disable it by default. Bug: libyuv:965 Signed-off-by: Bruce Lai <bruce.lai@sifive.com> Change-Id: Ic7ec40520b64131a456c6f3eea0639b3620f11ae Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4882441 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2023-08-31Disable NEON if memory sanitizer is enabledFrank Barchard
- MSAN fails on most inline assembly, unaware of what the load and store instructions do. - MSAN is also failing on row_any functions, which memcpy a correct number of pixels into a buffer that is SIMD vector sized, apply SIMD to the full vector, and then memcpy the exact number of resulting pixels to the output buffer. MSAN wants the temporary buffer to be initialized. Which genenerally is done with a memset(buf, 0, sizeof(buf)); to satisify MSAN. - RVV may not require disabling MSAN, since row functions are all 'any' number of elements, and implementation is intrinsics. Bug: b/297979878 Change-Id: Ic21200689c0c7d2c85bb1de3eef38570137d3d8b Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4832740 Reviewed-by: Mirko Bonadei <mbonadei@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Wan-Teh Chang <wtc@google.com>
2023-08-04RVV check __riscv_v_intrinsic versionFrank Barchard
Bug: libyuv:965 Change-Id: I9b02abd13ab3345288655fa7a16383f59cf66bb8 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4750230 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Mirko Bonadei <mbonadei@chromium.org>
2023-07-27[RVV] Enable ScaleRowDown38_RVV & ScaleRowDown38_{2,3}_Box_RVVBruce Lai
* Run on SiFive internal FPGA: Test Case Speedup I420ScaleDownBy3by8_None 4.2 I420ScaleDownBy3by8_Linear 1.7 I420ScaleDownBy3by8_Bilinear 1.7 I420ScaleDownBy3by8_Box 1.7 I444ScaleDownBy3by8_None 4.2 I444ScaleDownBy3by8_Linear 1.8 I444ScaleDownBy3by8_Bilinear 1.8 I444ScaleDownBy3by8_Box 1.8 Change-Id: Ic2e98de2494d9e7b25f5db115a7f21c618eaefed Signed-off-by: Bruce Lai <bruce.lai@sifive.com> Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4711857 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2023-07-26[RVV] Enable ScaleRowUp2_(Bi)linear_RVV/ScaleUVRowUp2_(Bi)linear_RVVDarren Hsieh
ScaleUVRowUp2_(Bi)linear_RVV function is equal to other platforms' ScaleRowUp2_(Bi)linear_Any_XXX. We process entire row in this function. Other platforms only implement non-edge part of image and process edge with scalar. ScaleRowUp2_(Bi)linear_Any_XXX: Combine ScaleRowUp2_(Bi)linear_XXX(non-edge) + ScaleRowUp2_(Bi)linear_C(edge) by SBUH2LANY/SU2BLANY. * Run on SiFive internal FPGA: Test case RVV function Speedup I444ScaleFrom640x360_Bilinear ScaleRowUp2_Bilinear_RVV 8.21 I444ScaleFrom640x360_Linear ScaleRowUp2_Linear_RVV 8.08 UVScaleFrom640x360_Bilinear ScaleUVRowUp2_Bilinear_RVV 7.80 UVScaleFrom640x360_Linear ScaleUVRowUp2_Linear_RVV 7.03 Change-Id: I539245ce51858f077506a78f0e7e82377ac6a95d Signed-off-by: Darren Hsieh <darren.hsieh@sifive.com> Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4666062 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2023-06-14[RVV] Enable ScaleRowDown34_RVV & ScaleRowDown34_{0,1}_Box_RVVDarren Hsieh
Run on SiFive internal FPGA: Test case RVV function Speedup I444ScaleDownBy3by4_None ScaleRowDown34_RVV 5.8 I444ScaleDownBy3by4_Linear ScaleRowDown34_0/1_Box_RVV 6.5 I444ScaleDownBy3by4_Bilinear ScaleRowDown34_0/1_Box_RVV 6.3 Bug: libyuv:956 Change-Id: I8ef221ab14d631e14f1ba1aaa25d2b30d4e710db Signed-off-by: Darren Hsieh <darren.hsieh@sifive.com> Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4607777 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2023-06-13[RVV] Enable Scale{ARGB,UV}RowDown{2,4,EVEN}_RVVDarren Hsieh
Run on SiFive internal FPGA: Test case RVV function Speedup I444ScaleDownBy3_Box ScaleAddRow_RVV+ScaleAddCols(scalar) 2.8 ARGBScaleDownBy2_None ScaleARGBRowDown2_RVV 2.2 ARGBScaleDownBy2_Linear ScaleARGBRowDown2Linear_RVV 5.0 ARGBScaleDownBy2_Box ScaleARGBRowDown2Box_RVV 4.3 ARGBScaleDownBy4_None ScaleARGBRowDownEven_RVV 1.2 ARGBScaleDownBy8_Box ScaleARGBRowDownEvenBox_RVV 3.2 ARGBScaleDownBy4_Box ScaleARGBRowDown2Box_RVV 4.5 I444ScaleDownBy2_None ScaleRowDown2_RVV 5.8 I444ScaleDownBy2_Linear ScaleRowDown2Linear_RVV 6.1 I444ScaleDownBy2_Box ScaleRowDown2Box_RVV 5.0 I444ScaleDownBy4_None ScaleRowDown4_RVV 3.6 I444ScaleDownBy4_Box ScaleRowDown4Box_RVV 3.5 UVScaleDownBy2_None ScaleUVRowDown2_RVV 5.8 UVScaleDownBy2_Linear ScaleUVRowDown2Linear_RVV 5.6 UVScaleDownBy2_Box ScaleUVRowDown2Box_RVV 4.1 UVScaleDownBy4_None ScaleUVRowDown4_RVV 1.7 UVScaleDownBy4_Box ScaleUVRowDown2Box_RVV 4.5 avg-speedup: 4 Note: Specialize ScaleUVRowDown with step_size=4 by ScaleUVRowDown4_RVV. Bug: libyuv:956 Change-Id: If9604a6aadf681193f282507602c57c726332202 Signed-off-by: Darren Hsieh <darren.hsieh@sifive.com> Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4601684 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2023-04-12UVScale down by 2 fix for C and optimize for NEONFrank Barchard
- update cpu_id to use "re" for fopen to avoid leaking handles if a thread is started while the file is open. Bug: libyuv:958 Change-Id: I1af9de68fce12e440e1226fc8070634ccb1bf090 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4417176 Reviewed-by: Wan-Teh Chang <wtc@google.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2023-01-23Add support for odd width and height in I410ToI420Sergio Garcia Murillo
Bug: libyuv:950 Change-Id: Ic9a094463af875aefd927023f730b5f35f8551de Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4154630 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2023-01-03Use ScalePlaneDown2_16To8 for avoiding the 2 step processSergio Garcia Murillo
Bug: libyuv:950 Change-Id: I5a77bca9a0230fe00abd810939e217833a14683f Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4134524 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2022-08-04RAWToJ400 require multiple of 16 pixels for NEONFrank Barchard
- fix crash when width is not a multiple of 16 - apply clang format - bump version Bug: libyuv:940, b/240094327 Change-Id: Ic18e5b7b64f78f26e8b7d8440bf490a679bda200 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3812594 Reviewed-by: Wan-Teh Chang <wtc@google.com>
2022-08-02Fix SSE2 version of ScalePlaneUp2_16_BilinearYuan Tong
- Define HAS_SCALEROWUP2_BILINEAR_16_SSE2: it's now fixed. - Correct function name to ScaleRowUp2_Bilinear_16_Any_SSE2: this row function uses only SSE2 instructions. Bug: libyuv:882 Change-Id: Ib1c7ac5b09997cb5b32bc54109d8c566af762433 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3800842 Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2022-08-01Disable bilinear 16 bit scale up for SSE2Frank Barchard
- Undefine HAS_SCALEROWUP2_BILINEAR_16_SSE2 - Save XMM7 in ScaleRowUp2_Bilinear_16_SSE2(). - Rename HAS_SCALEROWUP2LINEAR_xxx to HAS_SCALEROWUP2_LINEAR_xxx - DetileSplitUVRow_C() is implemented using SplitUVRow_C(). - Changes to unit_test/planar_test.cc. Bug: libyuv:882 Change-Id: I0a8e8e5fb43bdf58ded87244e802343eacb789f2 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3795063 Reviewed-by: Wan-Teh Chang <wtc@google.com>
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>
2022-06-07Revert "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>
2022-04-15Change ScaleUVRowUp2_Biinear_16_SSE2 to SSE41Frank Barchard
Bug: libyuv:928 xed -i scale_gcc.o: SYM ScaleUVRowUp2_Linear_16_SSE2: XDIS 0: LOGICAL SSE2 660FEFED pxor xmm5, xmm5 XDIS 4: SSE SSE2 660F76E4 pcmpeqd xmm4, xmm4 XDIS 8: SSE SSE2 660F72D41F psrld xmm4, 0x1f XDIS d: SSE SSE2 660F72F401 pslld xmm4, 0x1 XDIS 12: DATAXFER SSE2 F30F7E07 movq xmm0, qword ptr [rdi] XDIS 16: DATAXFER SSE2 F30F7E4F04 movq xmm1, qword ptr [rdi+0x4] XDIS 1b: SSE SSE2 660F61C5 punpcklwd xmm0, xmm5 XDIS 1f: SSE SSE2 660F61CD punpcklwd xmm1, xmm5 XDIS 23: DATAXFER SSE2 660F6FD0 movdqa xmm2, xmm0 XDIS 27: DATAXFER SSE2 660F6FD9 movdqa xmm3, xmm1 XDIS 2b: SSE SSE2 660F70D24E pshufd xmm2, xmm2, 0x4e XDIS 30: SSE SSE2 660F70DB4E pshufd xmm3, xmm3, 0x4e XDIS 35: SSE SSE2 660FFED4 paddd xmm2, xmm4 XDIS 39: SSE SSE2 660FFEDC paddd xmm3, xmm4 XDIS 3d: SSE SSE2 660FFED0 paddd xmm2, xmm0 XDIS 41: SSE SSE2 660FFED9 paddd xmm3, xmm1 XDIS 45: SSE SSE2 660FFEC0 paddd xmm0, xmm0 XDIS 49: SSE SSE2 660FFEC9 paddd xmm1, xmm1 XDIS 4d: SSE SSE2 660FFEC2 paddd xmm0, xmm2 XDIS 51: SSE SSE2 660FFECB paddd xmm1, xmm3 XDIS 55: SSE SSE2 660F72D002 psrld xmm0, 0x2 XDIS 5a: SSE SSE2 660F72D102 psrld xmm1, 0x2 XDIS 5f: SSE SSE4 660F382BC1 packusdw xmm0, xmm1 XDIS 64: DATAXFER SSE2 F30F7F06 movdqu xmmword ptr [rsi], xmm0 XDIS 68: MISC BASE 488D7F08 lea rdi, ptr [rdi+0x8] XDIS 6c: MISC BASE 488D7610 lea rsi, ptr [rsi+0x10] XDIS 70: BINARY BASE 83EA04 sub edx, 0x4 XDIS 73: COND_BR BASE 7F9D jnle 0x12 <ScaleUVRowUp2_Linear_16_SSE2+0x12> XDIS 75: RET BASE C3 ret SYM ScaleUVRowUp2_Bilinear_16_SSE2: XDIS 0: LOGICAL SSE2 660FEFFF pxor xmm7, xmm7 XDIS 4: SSE SSE2 660F76F6 pcmpeqd xmm6, xmm6 XDIS 8: SSE SSE2 660F72D61F psrld xmm6, 0x1f XDIS d: SSE SSE2 660F72F603 pslld xmm6, 0x3 XDIS 12: DATAXFER SSE2 F30F7E07 movq xmm0, qword ptr [rdi] XDIS 16: DATAXFER SSE2 F30F7E4F04 movq xmm1, qword ptr [rdi+0x4] XDIS 1b: SSE SSE2 660F61C7 punpcklwd xmm0, xmm7 XDIS 1f: SSE SSE2 660F61CF punpcklwd xmm1, xmm7 XDIS 23: DATAXFER SSE2 660F6FD0 movdqa xmm2, xmm0 XDIS 27: DATAXFER SSE2 660F6FD9 movdqa xmm3, xmm1 XDIS 2b: SSE SSE2 660F70D24E pshufd xmm2, xmm2, 0x4e XDIS 30: SSE SSE2 660F70DB4E pshufd xmm3, xmm3, 0x4e XDIS 35: SSE SSE2 660FFED0 paddd xmm2, xmm0 XDIS 39: SSE SSE2 660FFED9 paddd xmm3, xmm1 XDIS 3d: SSE SSE2 660FFEC0 paddd xmm0, xmm0 XDIS 41: SSE SSE2 660FFEC9 paddd xmm1, xmm1 XDIS 45: SSE SSE2 660FFEC2 paddd xmm0, xmm2 XDIS 49: SSE SSE2 660FFECB paddd xmm1, xmm3 XDIS 4d: DATAXFER SSE2 F30F7E1477 movq xmm2, qword ptr [rdi+rsi*2] XDIS 52: DATAXFER SSE2 F30F7E5C7704 movq xmm3, qword ptr [rdi+rsi*2+0x4] XDIS 58: SSE SSE2 660F61D7 punpcklwd xmm2, xmm7 XDIS 5c: SSE SSE2 660F61DF punpcklwd xmm3, xmm7 XDIS 60: DATAXFER SSE2 660F6FE2 movdqa xmm4, xmm2 XDIS 64: DATAXFER SSE2 660F6FEB movdqa xmm5, xmm3 XDIS 68: SSE SSE2 660F70E44E pshufd xmm4, xmm4, 0x4e XDIS 6d: SSE SSE2 660F70ED4E pshufd xmm5, xmm5, 0x4e XDIS 72: SSE SSE2 660FFEE2 paddd xmm4, xmm2 XDIS 76: SSE SSE2 660FFEEB paddd xmm5, xmm3 XDIS 7a: SSE SSE2 660FFED2 paddd xmm2, xmm2 XDIS 7e: SSE SSE2 660FFEDB paddd xmm3, xmm3 XDIS 82: SSE SSE2 660FFED4 paddd xmm2, xmm4 XDIS 86: SSE SSE2 660FFEDD paddd xmm3, xmm5 XDIS 8a: DATAXFER SSE2 660F6FE0 movdqa xmm4, xmm0 XDIS 8e: DATAXFER SSE2 660F6FEA movdqa xmm5, xmm2 XDIS 92: SSE SSE2 660FFEE0 paddd xmm4, xmm0 XDIS 96: SSE SSE2 660FFEEE paddd xmm5, xmm6 XDIS 9a: SSE SSE2 660FFEE0 paddd xmm4, xmm0 XDIS 9e: SSE SSE2 660FFEE5 paddd xmm4, xmm5 XDIS a2: SSE SSE2 660F72D404 psrld xmm4, 0x4 XDIS a7: DATAXFER SSE2 660F6FEA movdqa xmm5, xmm2 XDIS ab: SSE SSE2 660FFEEA paddd xmm5, xmm2 XDIS af: SSE SSE2 660FFEC6 paddd xmm0, xmm6 XDIS b3: SSE SSE2 660FFEEA paddd xmm5, xmm2 XDIS b7: SSE SSE2 660FFEE8 paddd xmm5, xmm0 XDIS bb: SSE SSE2 660F72D504 psrld xmm5, 0x4 XDIS c0: DATAXFER SSE2 660F6FC1 movdqa xmm0, xmm1 XDIS c4: DATAXFER SSE2 660F6FD3 movdqa xmm2, xmm3 XDIS c8: SSE SSE2 660FFEC1 paddd xmm0, xmm1 XDIS cc: SSE SSE2 660FFED6 paddd xmm2, xmm6 XDIS d0: SSE SSE2 660FFEC1 paddd xmm0, xmm1 XDIS d4: SSE SSE2 660FFEC2 paddd xmm0, xmm2 XDIS d8: SSE SSE2 660F72D004 psrld xmm0, 0x4 XDIS dd: DATAXFER SSE2 660F6FD3 movdqa xmm2, xmm3 XDIS e1: SSE SSE2 660FFED3 paddd xmm2, xmm3 XDIS e5: SSE SSE2 660FFECE paddd xmm1, xmm6 XDIS e9: SSE SSE2 660FFED3 paddd xmm2, xmm3 XDIS ed: SSE SSE2 660FFED1 paddd xmm2, xmm1 XDIS f1: SSE SSE2 660F72D204 psrld xmm2, 0x4 XDIS f6: SSE SSE4 660F382BE0 packusdw xmm4, xmm0 XDIS fb: DATAXFER SSE2 F30F7F22 movdqu xmmword ptr [rdx], xmm4 XDIS ff: SSE SSE4 660F382BEA packusdw xmm5, xmm2 XDIS 104: DATAXFER SSE2 F30F7F2C4A movdqu xmmword ptr [rdx+rcx*2], xmm5 XDIS 109: MISC BASE 488D7F08 lea rdi, ptr [rdi+0x8] XDIS 10d: MISC BASE 488D5210 lea rdx, ptr [rdx+0x10] XDIS 111: BINARY BASE 4183E804 sub r8d, 0x4 XDIS 115: COND_BR BASE 0F8FF7FEFFFF jnle 0x12 <ScaleUVRowUp2_Bilinear_16_SSE2+0x12> XDIS 11b: RET BASE C3 ret Change-Id: Ia20860e9c3c45368822cfd8877167ff0bf973dcc Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3587602 Reviewed-by: richard winterton <rrwinterton@gmail.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
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>
2022-01-21Add optimization functions in scale_lsx.cc file.Hao Chen
Optimize 20 functions in source/scale_lsx.cc file. All test cases passed on loongarch platform. Bug: libyuv:913 Change-Id: I85bcb3b0bfd9461bb6f93202546507352cbd624a Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3351469 Reviewed-by: Frank Barchard <fbarchard@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>
2021-10-14Add LIBYUV_BIT_EXACT macro to force C to match SIMDFrank Barchard
- C code use ARM path, so NEON and C match - C used on Intel platforms, disabling AVX. Bug: libyuv:908, b/202888439 Change-Id: Ie035a150a60d3cf4ee7c849a96819d43640cf020 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3223507 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: richard winterton <rrwinterton@gmail.com>
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>
2021-04-22Switch win32 to row_gcc for clangcl.Frank Barchard
Bug: libyuv:900, libyuv:848, b/178283356, b/185922513 Change-Id: I7697953753391c555a778198db36412c853fb29e Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2844962 Reviewed-by: richard winterton <rrwinterton@gmail.com> Reviewed-by: Dale Curtis <dalecurtis@chromium.org>
2021-04-21Disable win32 SIMDFrank Barchard
Bug: libyuv:900, libyuv:848, b/178283356, b/185922513 Change-Id: Iee7d9970c7991856c8f51158cd12ec72ee9c57eb Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2844779 Reviewed-by: Dale Curtis <dalecurtis@chromium.org>
2021-03-05Add 12 bit YUV to 10 bit RGBFrank Barchard
Bug: libyuv:843 Change-Id: I0104c8fcaeed09e83d2fd654c6a5e7d41bcb74cf Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2727775 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Wan-Teh Chang <wtc@google.com>
2021-03-02Add full 16 bit scaling up by 2x functionYuan Tong
R=fbarchard@chromium.org Change-Id: I4a869aefdc16e34357a615727711594c5d8e3a80 Bug: libyuv:882 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2719842 Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2021-02-12add yuvconvstants utilFrank Barchard
miscellaneous cleanup of other code/comments Bug: libyuv:873, libyuv:877 Change-Id: I0d8caf9a65908ff8898b25494f7c724775f84fa3 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2692930 Reviewed-by: Wan-Teh Chang <wtc@google.com> Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2021-02-12Add P010ToP410 and P210ToP410Yuan Tong
These are 16 bit bi-planar convert functions to scale UV plane to Y plane's size using (bi)linear filter. libyuv_unittest --gtest_filter=*ToP41* R=fbarchard@chromium.org Bug: libyuv:872 Change-Id: I3cb4fafe2b2c9eedd0d91cf4c619abb9ee107bc1 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2690102 Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2021-02-09Add NV12ToNV24 and NV16ToNV24Yuan Tong
These are bi-planar convert functions to scale UV plane to Y plane's size using (bi)linear filter. libyuv_unittest --gtest_filter=*ToNV24* R=fbarchard@chromium.org Change-Id: I3d98f833feeef00af3c903ac9ad0e41bdcbcb51f Bug: libyuv:872 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2682152 Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2021-02-03Add special optimization for I420ToI444 and I422ToI444Yuan Tong
These functions use (bi)linear filter, to scale U and V planes to the size of Y plane. This will help enhance the quality of YUV to RGB conversion. Also added 10bit and 12bit version: I010ToI410 I210ToI410 I012ToI412 I212ToI412 libyuv_unittest --gtest_filter=LibYUVConvertTest.I42*ToI444*:LibYUVConvertTest.I*1*ToI41* R=fbarchard@chromium.org Change-Id: Ie4a711a5ba28f2ff1f44c021f7a5c149022264c5 Bug: libyuv:872 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2658097 Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2020-11-03Scale by even factor low level row functionFrank Barchard
Bug: b/171884264 Change-Id: I6a94bde0aa05e681bb4590ea8beec33a61ddbfc9 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2518361 Reviewed-by: richard winterton <rrwinterton@gmail.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2020-10-28PlaneScale, UVScale and ARGBScale test 3x and 4x down sample.Frank Barchard
Intel SkylakeX UVTest3x (1925 ms) UVTest4x (2915 ms) PlaneTest3x (2040 ms) PlaneTest4x (4292 ms) ARGBTest3x (2079 ms) ARGBTest4x (1854 ms) Pixel 2 ARGBTest3x (3602 ms) ARGBTest4x (4064 ms) PlaneTest3x (3331 ms) PlaneTest4x (8977 ms) UVTest3x (3473 ms) UVTest4x (6970 ms) Bug: b/171798872, b/171884264 Change-Id: Iebc70fed907857b6cb71a9baf2aba9861ef1e3f7 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2505601 Reviewed-by: richard winterton <rrwinterton@gmail.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2020-10-14UVScale down use AVX2 and Neon for aarch32Frank Barchard
Intel SkylakeX Was SSSE3 UVScaleDownBy4_Box (2496 ms) Now AVX2 UVScaleDownBy4_Box (1983 ms) Was SSSE3 UVScaleDownBy2_Box (380 ms) Now AVX2 UVScaleDownBy2_Box (360 ms) Pixel 4 aarch32 Was UVScaleDownBy4_Box (4295 ms) Now UVScaleDownBy4_Box (3307 ms) Was UVScaleDownBy2_Box (1022 ms) Now UVScaleDownBy2_Box (778 ms) Bug: libuyv:838 Change-Id: Ic823fa15e5761c1b9a897da27341adbf1ed39883 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2470196 Reviewed-by: richard winterton <rrwinterton@gmail.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2020-10-132x down sample for UV planes ported to SSSE3 / NEONFrank Barchard
Bug: libuyv:838 Change-Id: Id9fb3282a3e86143d76b5e0cb557f0523a88b3c8 Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2465578 Reviewed-by: richard winterton <rrwinterton@gmail.com> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2020-09-29NV12Scale function and ScaleUV for packed UV plane bilinear scalingFrank Barchard
Bug: libyuv:718, libyuv:838, b/168918847 Change-Id: I3300c1e7d51407b9c3201cf52b68e2e11346ff5f Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2427868 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: richard winterton <rrwinterton@gmail.com>
2019-09-11MMI Optimized functions I422ToARGB for 1080p videoFrank Barchard
Improves playback performance for 1080p video on www.youku.com BUG=libyuv:841 Change-Id: Iabe7693fba276162af0290863f46e214ab86fb6c Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/1790959 Reviewed-by: Miguel Casas <mcasas@chromium.org>
2018-10-25Port box filter to NEONFrank Barchard
Bug: libyuv:821 Change-Id: I4a6b9bee2c2fae199c73c9ec7ecb32bde37c1852 Tested: out/Release/libyuv_unittest --gtest_filter=*ScaleFrom1920x1080_Box --libyuv_width=160 --libyuv_height=90 --libyuv_repeat=1000 Reviewed-on: https://chromium-review.googlesource.com/c/1298598 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Miguel Casas <mcasas@chromium.org>
2018-08-11libyuv:loongson Correct the optimization of mmi on loongson3a platform.lixia zhang
When loading or storing the data, the unaligned address will greatly degrade the optimization performance, so non-aligned access instructions are required on the loongson platform. Also delete the optimization function:ScaleARGBFilterCols_MMI, because it degraded the performance. BUG=libyuv:804 R=fbarchard@chromium.org Change-Id: If4c15886a21cdcbac7ae8b336292e4549acf1e47 Reviewed-on: https://chromium-review.googlesource.com/1164627 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2018-08-06Restore the file mode for source filesMartin Storsjö
This was changed in 21be9122aadf7824efe3fc19b2a09ff253a688e1. Change-Id: I6c04dc92f673557e10c231bd090ec8aa88b6bee4 Reviewed-on: https://chromium-review.googlesource.com/1146183 Reviewed-by: Frank Barchard <fbarchard@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2018-07-20libyuv:loongson optimize compare/row/scale/rotate files with mmi.lixia zhang
Currently, libyuv supports MIPS SIMD Arch(MSA), but libyuv does not supports MultiMedia Instruction(MMI)(such as loongson3a platform). In order to improve performance of libyuv on loongson3a platform, this provides optimize 98 functions with mmi. BUG=libyuv:804 Change-Id: I8947626009efad769b3103a867363ece25d79629 Reviewed-on: https://chromium-review.googlesource.com/1122064 Commit-Queue: Frank Barchard <fbarchard@chromium.org> Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2018-02-07tidy applied with readability-inconsistent-declaration-parameter-nameFrank Barchard
Bug: libyuv:750 Test: builds and runs and passes more tidy tests Change-Id: I023699a7aa61ea3f5e4a21647112691ea5739281 Reviewed-on: https://chromium-review.googlesource.com/902170 Reviewed-by: Weiyong Yao <braveyao@chromium.org>
2018-01-24Lint cleanup after C99 change CLFrank Barchard
TBR=braveyao@chromium.org Bug: libyuv:774 Test: git cl lint Change-Id: I51cf8107a8db17fbc9952d610f3e4d7aac5aa743 Reviewed-on: https://chromium-review.googlesource.com/882217 Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2018-01-23Switch to C99 typesFrank Barchard
Append _t to all sized types. uint64 becomes uint64_t etc Bug: libyuv:774 Test: try bots build on all platforms Change-Id: Ide273d7f8012313d6610415d514a956d6f3a8cac Reviewed-on: https://chromium-review.googlesource.com/879922 Reviewed-by: Miguel Casas <mcasas@chromium.org>
2018-01-10Remove x64 native_client macros.Frank Barchard
Bug: libyuv:702 Test: try bots pass Change-Id: I76d74b5f02fe9843418108b84742e2f714d1ab0a Reviewed-on: https://chromium-review.googlesource.com/855656 Reviewed-by: Frank Barchard <fbarchard@chromium.org>
2017-12-14Remove Mips DSPR2 codeFrank Barchard
Bug: libyuv:765 Test: build for mips still passes Change-Id: I99105ad3951d2210c0793e3b9241c178442fdc37 Reviewed-on: https://chromium-review.googlesource.com/826404 Reviewed-by: Weiyong Yao <braveyao@chromium.org> Commit-Queue: Frank Barchard <fbarchard@chromium.org>
2017-11-09Re-enable x86 assembly without requiring -msse2Frank Barchard
clang does not require -msse2 or -msse for inline, except the "x" parameter. So change this to "m" for 32 bit. 64 bit requires sse2 so use "x" for 64 bit. gcc requires -msse for xmm registers in clobber list. Reduce compiler requirement from -msse2 to -msse for enabling assembly. Bug: libyuv:754, libyuv:757 Test: CC=clang CXX=clang++ CFLAGS="-m32" CXXFLAGS="-m32 -mno-sse -O2" make -f linux.mk Change-Id: I86df72cfee80b7d349561c1fd7c97ad360767255 Reviewed-on: https://chromium-review.googlesource.com/759303 Reviewed-by: richard winterton <rrwinterton@gmail.com> Reviewed-by: Frank Barchard <fbarchard@google.com> Commit-Queue: Frank Barchard <fbarchard@google.com>
2017-11-08Remove DISABLE_CLANG_MSAFrank Barchard
cleanup to remove ifdefs around functions affected by a clang bug. gn gen out/Release "--args=is_debug=false target_os=\"android\" target_cpu=\"mips64el\" mips_arch_variant=\"r6\" mips_use_msa=true is_component_build=true is_clang=true" ninja -v -C out/Release libyuv_unittest Bug: libyuv:634 Test: build for mips with clang Change-Id: I278b368dbb2fe89082240e280267d0a27a214c78 Reviewed-on: https://chromium-review.googlesource.com/757980 Reviewed-by: Frank Barchard <fbarchard@google.com> Commit-Queue: Frank Barchard <fbarchard@google.com>
2017-11-08Revert "Enable SSE2 code without -msse"Frank Barchard
This reverts commit 01e994d74e4e3937ee1a3efdc048320a1e51f818. Change-Id: Ie76710d0f4e641e071889c5125fd3be23cdcdb59 Reviewed-on: https://chromium-review.googlesource.com/758499 Reviewed-by: Frank Barchard <fbarchard@google.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-08 07:15:05 +0000