Performance optimization for Align post processing block #2040
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
85bd4a4 to
4fe7f05
Compare
ev-mp
approved these changes
Jul 16, 2018
src/proc/align.cpp
Outdated
| byte* other_aligned_to_depth = const_cast<byte*>(aligned_frame.frame->get_frame_data()); | ||
| memset(other_aligned_to_depth, 0, depth_intrinsics.height * depth_intrinsics.width * aligned_bytes_per_pixel); | ||
| #ifdef __SSSE3__ | ||
| auto uid = other_frame->get_stream()->get_unique_id(); |
src/proc/align.cpp
Outdated
| auto data = (int16_t*)depth_frame->get_frame_data(); | ||
|
|
||
| #ifdef __SSSE3__ | ||
| auto uid = other_frame->get_stream()->get_unique_id(); |
| } | ||
| } | ||
|
|
||
| } No newline at end of file |
Contributor
There was a problem hiding this comment.
Indentation + add empty line at the end of file
ev-mp
reviewed
Jul 16, 2018
src/proc/align.cpp
Outdated
| { | ||
| } | ||
|
|
||
| void image_transform::pre_compute_x_y_map(float offset) |
Contributor
There was a problem hiding this comment.
Please add comments what the pre-compute comprise of
ev-mp
reviewed
Jul 16, 2018
| bottom_right = _pixel_bottom_right_int; | ||
| } | ||
|
|
||
| switch (bpp) |
Contributor
There was a problem hiding this comment.
The switch case seem to be redundant
ev-mp
reviewed
Jul 16, 2018
src/proc/align.cpp
Outdated
| template<> | ||
| inline void image_transform::distorte_x_y<RS2_DISTORTION_MODIFIED_BROWN_CONRADY>(const __m128& x, const __m128& y, __m128* distorted_x, __m128* distorted_y, const rs2_intrinsics& to) | ||
| { | ||
| __m128 c[5]; |
Contributor
There was a problem hiding this comment.
Please add comments for the hard-coded values - [5] == distortion coefficients,
for maintainability
ev-mp
reviewed
Jul 16, 2018
src/proc/align.cpp
Outdated
| const rs2_intrinsics& to, | ||
| const rs2_extrinsics& from_to_other) | ||
| { | ||
| //mask for shuffle |
Contributor
There was a problem hiding this comment.
Please add pseudo-code to describe the flow for maintainability
Closed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull-request improves latency and CPU utilization of
alignprocessing block.The solution combines SSE4 optimization for Intel architecture with changes to the algorithm to reduce overhead.
Following-up on: #1189, #1105
OS Microsoft Windows 10 Enterprise
Processor Intel(R) Core(TM) i5-5300U CPU @ 2.30GHz, 2301 Mhz, 2 Core(s), 4 Logical Processor(s)
Align depth to color
Align color to depth
Ubuntu 16.04
Intel® Core™ i7-6700 CPU @ 3.40GHz × 8
Align depth to color
Align color to depth