| commit | 7e42d5f0ab2aeac811fd01e122627c9198b13f01 | |
| author | Martin Storsjö <martin@martin.st> | |
| Thu, 31 Jan 2019 22:12:46 +0000 (1 00:12 +0200) | ||
| committer | Martin Storsjö <martin@martin.st> | |
| Tue, 19 Feb 2019 09:46:28 +0000 (19 11:46 +0200) | ||
| tree | 7a04b33369318adf05a6a859f80519abff58b71d | treesnapshot (tar.gz zip) |
| parent | 49f9c4272c4029b57ff300d908ba03c6332fc9c4 | commitdiff |
aarch64: vp8: Optimize vp8_idct_add_neon for aarch64
The previous version was a pretty exact translation of the arm
version. This version does do some unnecessary arithemetic (it does
more operations on vectors that are only half filled; it does 4
uaddw and 4 sqxtun instead of 2 of each), but it reduces the overhead
of packing data together (which could be done for free in the arm
version).
This gives a decent speedup on Cortex A53, a minor speedup on
A72 and a very minor slowdown on Cortex A73.
Before: Cortex A53 A72 A73
vp8_idct_add_neon: 79.7 67.5 65.0
After:
vp8_idct_add_neon: 67.7 64.8 66.7
Signed-off-by: Martin Storsjö <martin@martin.st>
The previous version was a pretty exact translation of the arm
version. This version does do some unnecessary arithemetic (it does
more operations on vectors that are only half filled; it does 4
uaddw and 4 sqxtun instead of 2 of each), but it reduces the overhead
of packing data together (which could be done for free in the arm
version).
This gives a decent speedup on Cortex A53, a minor speedup on
A72 and a very minor slowdown on Cortex A73.
Before: Cortex A53 A72 A73
vp8_idct_add_neon: 79.7 67.5 65.0
After:
vp8_idct_add_neon: 67.7 64.8 66.7
Signed-off-by: Martin Storsjö <martin@martin.st>
| libavcodec/aarch64/vp8dsp_neon.S | diffblobblamehistory |