[LRS-GL] Support for Align-SSE #12637
Conversation
Arun-Prasad-V
force-pushed
the
lrs_gl_align_sse
branch
from
4e0cc66
to
1b04502
Compare
Arun-Prasad-V
force-pushed
the
lrs_gl_align_sse
branch
from
1b04502
to
7bd1b7d
Compare
src/proc/align.cpp
Outdated
| @@ -11,10 +11,30 @@ | |||
| #include "align.h" | |||
| #include "stream.h" | |||
|
|
|||
| #ifdef RS2_USE_CUDA | |||
There was a problem hiding this comment.
Is it possible a platform will have both CUDA & SSE3 enabled?
Please check because if yes, we will have to choose as this may not compile
There was a problem hiding this comment.
sure @Nir-Az. Will check. But it is the same case for pointcloud implementation as well.
librealsense/src/proc/pointcloud.cpp
Line 394 in d06f21b
There was a problem hiding this comment.
@Nir-Az, the user cannot choose to run with or without "SSE3". If CPU processing is preferred, LRS should automatically detect and use "SSE3" wherever possible.
If "BUILD_WITH_CUDA" flag is enabled, CUDA implementations will be preferred. User cannot dynamically choose between CUDA or SSE3.
There was a problem hiding this comment.
Yes I know, just wanted to make sure that if the user build with Cuda, and gis CPU support SSSE,
He will include both headers.
We need to make sure the headers does not conflict.
There was a problem hiding this comment.
Headers are not conflicting. Anyway, updated them to avoid such confusions.
Tracked on LRS-1007
With LRS-GL library, in case if user chooses CPU acceleration ('SSE3' is enabled during build), create librealsense::align_sse class object instead of librealsense::align.