aboutsummaryrefslogtreecommitdiffstats
path: root/tests/checkasm/float_dsp.c
diff options
context:
space:
mode:
authorRémi Denis-Courmont <remi@remlab.net>2023-10-29 13:26:30 +0200
committerRémi Denis-Courmont <remi@remlab.net>2023-11-06 19:42:49 +0200
commit02594c8c011ca2cdc20334e9bb812ec8f6f37cf3 (patch)
tree4f6d5d2f123d653ce4abb4c0fb40035155c34865 /tests/checkasm/float_dsp.c
parentf68ad5d2de40e42b57b9f44ec69d9cbc0f709460 (diff)
downloadffmpeg-02594c8c011ca2cdc20334e9bb812ec8f6f37cf3.tar.gz
lavc/pixblockdsp: rework R-V V get_pixels_unaligned
As in the aligned case, we can use VLSE64.V, though the way of doing so gets more convoluted, so the performance gains are more modest: get_pixels_unaligned_c: 126.7 get_pixels_unaligned_rvv_i32: 145.5 (before) get_pixels_unaligned_rvv_i64: 62.2 (after) For the reference, those are the aligned benchmarks (unchanged) on the same T-Head C908 hardware: get_pixels_c: 126.7 get_pixels_rvi: 85.7 get_pixels_rvv_i64: 33.2
Diffstat (limited to 'tests/checkasm/float_dsp.c')
0 files changed, 0 insertions, 0 deletions