Age | Commit message (Collapse) | Author |
|
BUG=webm:1301
Change-Id: I56e3bc3aab9214e2debac93796389a7194991084
|
|
BUG=webm:1301
Change-Id: I05f47dca1fddc155c8396e627cfccf6449677307
|
|
relocate the assignment to 'in' outside of the for loop. this quiets a
spurious warning in visual studio builds since:
86e340c enable vpx_idct32x32_1024_add_neon in hbd builds
+ give the variable a more descriptive name
BUG=webm:1294
Change-Id: I5c3da5c7939621477e0fc0ad3a1b2a3045c5bffd
|
|
|
|
Implement vpx_post_proc_down_and_across_mb_row in NEON.
Runs about 6-7x faster than C.
BUG=webm:1320
Change-Id: Ic5c7d3552a88cfcf999ec5bf2bd46fee460642c2
|
|
BUG=webm:1301
Change-Id: I387b7eae716a7df15c691dc6f368b07602df7342
|
|
BUG=webm:1294
Change-Id: Ibdda54e6d1303b0f73bc7bc71417e4041d7618de
|
|
Change-Id: Ie9336a808a3c3592bb4fd5d4ad3839028bfcafba
|
|
Allows for use outside the idcts without pulling in idct_neon.h
Change-Id: I4a94c1af3dac3e1b5bc8296ec9eab0ddcc8cfecf
|
|
after:
2d3d95f enable vpx_idct16x16_256_add_neon in hbd builds
reorder INCLUDEs and fix indent of IF/ENDIFs
remove vpx_config.asm to avoid multiple symbol definitions in windows
builds and shift idct_neon.asm.S to the top to allow use of
CONFIG_VP9_HIGHBITDEPTH in the export list.
Change-Id: I0dacfbae62a6ec8fe4a26940c1a52da2dfad2029
|
|
|
|
|
|
Change-Id: Iae517017217dbacd638d40fcfeeb0f4bba7b8b8b
|
|
BUG=webm:1294
Change-Id: Ib421c150b0d29dee0a81390a612bf01a4a28cff1
|
|
* changes:
enable vpx_idct16x16_10_add_neon in hbd builds
idct16x16,NEON: rm output_stride from pass1 fns
|
|
BUG=webm:1294
Change-Id: Ibad079f25e673d4f5181961896a8a8333a51e825
|
|
vpx_idct16x16_256_add_neon_pass1, vpx_idct16x16_10_add_neon:
this was a constant 8 in all cases meaning the results are stored
contiguously, this allows the number of stores to be reduced.
Change-Id: I7858a0a15a284883ef45c13dfd97c308df9ea09e
|
|
Change-Id: I4ec4ad1928ec2ed87f596f52f097bc52065278dd
|
|
This replaces its C version.
Change-Id: Ie39e9324305fdc0fff610ced608a037e44a85a1a
|
|
* changes:
Add high bitdepth 4x4 idct NEON intrinsics
Update idct x86 intrinsics to not use saturated add and sub
|
|
Change-Id: I4afc130effa05b8be2e9f982967216b1beb2ce4b
|
|
Change-Id: Iaa64d23fdb45ca1f235b0ea57e614516e548eca4
|
|
+ remove unused parameters from vpx_idct16x16_10_add_neon_pass2
Change-Id: Ie5912a4abdd308fab589380bca054a2e7234a2c4
|
|
BUG=webm:1294
Change-Id: Ide6d3994fe01c4320c9d143e6d059b49568048e4
|
|
BUG=webm:1294
Change-Id: I164cfcbe9bc4511d1d04af9206cf351a0ec2957b
|
|
* changes:
Update vpx_idct4x4_16_add_neon() to pass SingleExtremeCoeff test
Refine 8-bit 4x4 idct NEON intrinsics
Add idct speed test.
Update partial_idct_test.cc to support high bitdepth
|
|
BUG=webm:1321
Change-Id: I719023375dc48cf7d8ed72188853f0f1ccc4ad7f
|
|
|
|
Change-Id: Icc4ead05506797d12bf134e8790443676fef5c10
|
|
Change-Id: Ib019964bfcbce7aec57d8c3583127f9354d3c11f
|
|
Change-Id: Ia8fb3ed124f01384e7896e309c9ff22c05b40719
|
|
|
|
|
|
Some cosmetic changes because xmm is an anachronism.
Change-Id: I436a5b78a3c52776c20d6640939311f2a84a9bc7
|
|
Updated idct code to handle single large coefficient (-32768)
Change-Id: Ia13ab1ab434a9a1b9954a5914088977a88841cc7
|
|
|
|
Re-enable the tests to check CvsAssembly.
BUG=webm:1321
Change-Id: Id7f7d74b06c469fb6c8f5d04e91359e9cd9097a6
|
|
BUG=webm:1316
Change-Id: Ib014de06836ac12726f4a2c9f0833ec4eb4d233b
|
|
BUG=webm:1316
Change-Id: I47eeac698a98a31d1af5f72441052302e9fa4f46
|
|
* changes:
fdct8x8_test: add vpx_idct8x8_64_add_neon in hbd
fdct4x4_test: add vpx_idct4x4_16_add_neon in hbd
partial_idct_test,NEON: add missing idct variants
enable vpx_idct32x32_34_add_neon in hbd builds
|
|
BUG=webm:1316
Change-Id: I6a330874348df04df24a6d9efdc06f567e04bf8e
|
|
replace load_and_transpose_s16_8x8() in idct32_6_neon() with a separate
load_tran_low_to_s16() and transpose_s16_8x8(). the combined function is
used in idct32_8_neon() where the input is the correctly sized output
from the earlier stage.
BUG=webm:1294
Change-Id: I4257c4b3a421b2cf5d13651f966eee0680ef98a9
|
|
BUG=webm:1295
Change-Id: I7f80ef4d29813fcb401fc6075babf19e3c195462
|
|
|
|
Also update its trigger threshold from 10 to 12.
Change-Id: Ib8dddd87a5a22a12ca66e7084d342fbb027b0a2f
|
|
|
|
Borrow transition functions from fdct.h nee vpx_quantize_b_sse2
BUG=webm:1304
Change-Id: I9c88c3eec3ff8bb461411d98c26c3c236ea28ef1
|
|
They are identical.
Change-Id: I1ccaf03c81c3cbf88e82d77ffeb8204f5b063c61
|
|
|
|
|