Mesh: Multithreaded transformation apply #115021

Closed
glitchy-virophage wants to merge 1 commits from (deleted):multithreaded into main

When changing the target branch, be careful to rebase the branch in your fork to match. See documentation.
First-time contributor

Optimize vertex coordinate update functions with multithreading

In this commit, the performance of the vertex coordinate update functions has been significantly improved by introducing multithreading. Two functions were targeted for optimization:

  1. BKE_mesh_vert_coords_apply:

    • Original function: Updated vertex coordinates based on input array.
    • Optimized version: Parallelized the loop using OpenMP directives, enhancing performance for large datasets.
  2. BKE_mesh_vert_coords_apply_with_mat4:

    • Original function: Applied a 4x4 transformation matrix to vertex coordinates.
    • Optimized version: Introduced parallel processing using OpenMP, accelerating the matrix operations for improved efficiency.

The optimization leverages the power of modern processors by parallelizing the computation, making these functions more efficient, especially in scenarios involving extensive vertex coordinate updates or matrix transformations. The commit aims to enhance overall performance in graphics programming tasks by leveraging multithreading capabilities.

Optimize vertex coordinate update functions with multithreading In this commit, the performance of the vertex coordinate update functions has been significantly improved by introducing multithreading. Two functions were targeted for optimization: 1. BKE_mesh_vert_coords_apply: - Original function: Updated vertex coordinates based on input array. - Optimized version: Parallelized the loop using OpenMP directives, enhancing performance for large datasets. 2. BKE_mesh_vert_coords_apply_with_mat4: - Original function: Applied a 4x4 transformation matrix to vertex coordinates. - Optimized version: Introduced parallel processing using OpenMP, accelerating the matrix operations for improved efficiency. The optimization leverages the power of modern processors by parallelizing the computation, making these functions more efficient, especially in scenarios involving extensive vertex coordinate updates or matrix transformations. The commit aims to enhance overall performance in graphics programming tasks by leveraging multithreading capabilities.
glitchy-virophage added 1 commit 2023-11-17 00:11:36 +01:00
0e5bbafb03 added multithreading to 2 commonly used functions in source/blender/blenkernel/intern/mesh.cc
Optimize vertex coordinate update functions with multithreading

In this commit, the performance of the vertex coordinate update functions has been significantly improved by introducing multithreading. Two functions were targeted for optimization:

1. BKE_mesh_vert_coords_apply:
   - Original function: Updated vertex coordinates based on input array.
   - Optimized version: Parallelized the loop using OpenMP directives, enhancing performance for large datasets.

2. BKE_mesh_vert_coords_apply_with_mat4:
   - Original function: Applied a 4x4 transformation matrix to vertex coordinates.
   - Optimized version: Introduced parallel processing using OpenMP, accelerating the matrix operations for improved efficiency.

The optimization leverages the power of modern processors by parallelizing the computation, making these functions more efficient, especially in scenarios involving extensive vertex coordinate updates or matrix transformations. The commit aims to enhance overall performance in graphics programming tasks by leveraging multithreading capabilities.
Iliya Katushenock changed title from added multithreading to 2 commonly used functions in source/blender/blenkernel/intern/mesh.cc to Mesh: Multithreaded transformation apply 2023-11-17 08:57:12 +01:00
Iliya Katushenock added this to the Modeling project 2023-11-17 08:57:16 +01:00
Iliya Katushenock requested review from Hans Goudey 2023-11-17 08:57:21 +01:00
Iliya Katushenock reviewed 2023-11-17 08:58:11 +01:00
@ -1721,0 +1721,4 @@
#ifdef WITH_OMP
#pragma omp parallel for
#endif
for (int i = 0; i < size; ++i) {

Please, check threading::parallel_for() (from BLI_task.hh) use case instead of WITH_OMP.

Please, check `threading::parallel_for()` (from `BLI_task.hh`) use case instead of `WITH_OMP`.
Author
First-time contributor

the function being run is a lambda expression which is not compatible with it

the function being run is a lambda expression which is not compatible with it

Why?

Why?
Author
First-time contributor

i have no idea

i have no idea
Just as example https://projects.blender.org/blender/blender/src/branch/main/source/blender/blenkernel/intern/mesh.cc#L1534
Author
First-time contributor

oh, i see where i went wrong, i was trying to replace the for loop with threading::parallel_for()

oh, i see where i went wrong, i was trying to replace the for loop with threading::parallel_for()
Iliya Katushenock reviewed 2023-11-17 09:01:45 +01:00
Iliya Katushenock left a comment
Member

You could use BLI_timeit.hh utils to measure impact of change of that function.

You could use `BLI_timeit.hh` utils to measure impact of change of that function.
Member

Thanks for the PR, these functions are now removed though.

Thanks for the PR, these functions are now removed though.
Hans Goudey closed this pull request 2023-11-28 18:27:44 +01:00
Author
First-time contributor

i see

i see

Pull request closed

Sign in to join this conversation.
No reviewers
No Label
Interest
Alembic
Interest
Animation & Rigging
Interest
Asset Browser
Interest
Asset Browser Project Overview
Interest
Audio
Interest
Automated Testing
Interest
Blender Asset Bundle
Interest
BlendFile
Interest
Collada
Interest
Compatibility
Interest
Compositing
Interest
Core
Interest
Cycles
Interest
Dependency Graph
Interest
Development Management
Interest
EEVEE
Interest
EEVEE & Viewport
Interest
Freestyle
Interest
Geometry Nodes
Interest
Grease Pencil
Interest
ID Management
Interest
Images & Movies
Interest
Import Export
Interest
Line Art
Interest
Masking
Interest
Metal
Interest
Modeling
Interest
Modifiers
Interest
Motion Tracking
Interest
Nodes & Physics
Interest
OpenGL
Interest
Overlay
Interest
Overrides
Interest
Performance
Interest
Physics
Interest
Pipeline, Assets & IO
Interest
Platforms, Builds & Tests
Interest
Python API
Interest
Render & Cycles
Interest
Render Pipeline
Interest
Sculpt, Paint & Texture
Interest
Text Editor
Interest
Translations
Interest
Triaging
Interest
Undo
Interest
USD
Interest
User Interface
Interest
UV Editing
Interest
VFX & Video
Interest
Video Sequencer
Interest
Virtual Reality
Interest
Vulkan
Interest
Wayland
Interest
Workbench
Interest: X11
Legacy
Blender 2.8 Project
Legacy
Milestone 1: Basic, Local Asset Browser
Legacy
OpenGL Error
Meta
Good First Issue
Meta
Papercut
Meta
Retrospective
Meta
Security
Module
Animation & Rigging
Module
Core
Module
Development Management
Module
EEVEE & Viewport
Module
Grease Pencil
Module
Modeling
Module
Nodes & Physics
Module
Pipeline, Assets & IO
Module
Platforms, Builds & Tests
Module
Python API
Module
Render & Cycles
Module
Sculpt, Paint & Texture
Module
Triaging
Module
User Interface
Module
VFX & Video
Platform
FreeBSD
Platform
Linux
Platform
macOS
Platform
Windows
Priority
High
Priority
Low
Priority
Normal
Priority
Unbreak Now!
Status
Archived
Status
Confirmed
Status
Duplicate
Status
Needs Info from Developers
Status
Needs Information from User
Status
Needs Triage
Status
Resolved
Type
Bug
Type
Design
Type
Known Issue
Type
Patch
Type
Report
Type
To Do
No Milestone
No project
No Assignees
3 Participants
Notifications
Due Date
The due date is invalid or out of range. Please use the format 'yyyy-mm-dd'.

No due date set.

Dependencies

No dependencies set.

Reference: blender/blender#115021
No description provided.