AFAICT, it is sufficient that the sample buffer has space for half
the source width/height. With the current sample buffer size, this
enables its use for resolutions up to 3840x2176.
Average vertically before horizontally; horizontal averaging is more
worksome. Doing the vertical averaging first reduces the number of
horizontal averages by half.
Use pmaddubsw and pavgw to do the horizontal averaging for a slight
performance improvement.
Minor tweaks.
Improve the SSSE3 dyadic downsample routines and drop the SSE4 routines.
The non-temporal loads used in the SSE4 routines do nothing for cache-
backed memory AFAIK.
Adjust tests because averaging vertically first gives slightly different
output.
~2.39x speedup for the widthx32 routine on Haswell when not memory-bound.
~2.20x speedup for the widthx16 routine on Haswell when not memory-bound.
Note that the widthx16 routine can be unrolled for further speedup.
Assume that data can be written into the padding area following each
line. This enables the use of faster routines for more cases.
Align downsample buffer stride to a multiple of 32.
With this all strides used should be a multiple of 16, which means
that use of narrower downsample routines can be dropped altogether.
Keep track of relative pixel offsets and utilize pshufb to efficiently
extract relevant pixels for horizontal scaling ratios <= 8. Because
pshufb does not cross 128-bit lanes, the overhead of address
calculations and loads is relatively greater as compared with an
SSSE3/SSE4.1 implementation.
Fall back to a generic approach for ratios > 8.
The implementation assumes that data beyond the end of each line,
before the next line begins, can be dirtied; which AFAICT is safe with
the current usage of these routines.
Speedup is ~8.52x/~6.89x (32-bit/64-bit) for horizontal ratios <= 2,
~7.81x/~6.13x for ratios within (2, 4], ~5.81x/~4.52x for ratios
within (4, 8], and ~5.06x/~4.09x for ratios > 8 when not memory-bound
on Haswell as compared with the current SSE2 implementation.
Keep track of relative pixel offsets and utilize pshufb to efficiently
extract relevant pixels for horizontal scaling ratios <= 8. Because
pshufb does not cross 128-bit lanes, the overhead of address
calculations and loads is relatively greater as compared with an
SSSE3 implementation.
Fall back to a generic approach for ratios > 8.
The implementation assumes that data beyond the end of each line,
before the next line begins, can be dirtied; which AFAICT is safe with
the current usage of these routines.
Speedup is ~10.42x/~5.23x (32-bit/64-bit) for horizontal ratios <= 2,
~9.49x/~4.64x for ratios within (2, 4], ~6.43x/~3.18x for ratios
within (4, 8], and ~5.42x/~2.50x for ratios > 8 when not memory-bound
on Haswell as compared with the current SSE2 implementation.
Keep track of relative pixel offsets and utilize pshufb to efficiently
extract relevant pixels for horizontal scaling ratios <= 4.
Fall back to a generic approach for ratios > 4.
The use of blendps makes this require SSE4.1. The pshufb path can be
backported to SSSE3 and the generic path to SSE2 for a minor reduction
in performance by replacing blendps and preceding instructions with an
equivalent sequence.
The implementation assumes that data beyond the end of each line,
before the next line begins, can be dirtied; which AFAICT is safe with
the current usage of these routines.
Speedup is ~5.32x/~4.25x (32-bit/64-bit) for horizontal ratios <= 2,
~5.06x/~3.97x for ratios within (2, 4], and ~3.93x/~3.13x for ratios
> 4 when not memory-bound on Haswell as compared with the current SSE2
implementation.
Keep track of relative pixel offsets and utilize pshufb to efficiently
extract relevant pixels for horizontal scaling ratios <= 4.
Fall back to a generic approach for ratios > 4. Note that the generic
approach can be backported to SSE2.
The implementation assumes that data beyond the end of each line,
before the next line begins, can be dirtied; which AFAICT is safe with
the current usage of these routines.
Speedup is ~6.67x/~3.26x (32-bit/64-bit) for horizontal ratios <= 2,
~6.24x/~3.00x for ratios within (2, 4], and ~4.89x/~2.17x for ratios
> 4 when not memory-bound on Haswell as compared with the current SSE2
implementation.
