lavc/vp8dsp: add R-V V vp7_idct_dc_add4y

As with idct_dc_add, most of the code is shared with, and replaces, the
previous VP8 function. To improve performance, we break down the 16x4
matrix into 4 rows, rather than 4 squares. Thus strided loads and
stores are avoided, and the 4 DC calculations are vectored.
Unfortunately this requires a vector gather to splat the DC values, but
overall this is still a win for performance:

T-Head C908:
vp7_idct_dc_add4y_c:       7.2
vp7_idct_dc_add4y_rvv_i32: 2.2
vp8_idct_dc_add4y_c:       6.2
vp8_idct_dc_add4y_rvv_i32: 2.2 (before)
vp8_idct_dc_add4y_rvv_i32: 1.7

SpacemiT X60:
vp7_idct_dc_add4y_c:       6.2
vp7_idct_dc_add4y_rvv_i32: 2.0
vp8_idct_dc_add4y_c:       5.5
vp8_idct_dc_add4y_rvv_i32: 2.5 (before)
vp8_idct_dc_add4y_rvv_i32: 1.7

I also tried to provision the DC values using indexed loads. It ends up
slower overall, especially for VP7, as we then have to compute 16 DC's
instead of just 4.

0 files changed, 0 insertions, 0 deletions