blender
/
blender
134
398
Fork 580
Code Issues 6.3k Pull Requests 757 Projects 19 Wiki Activity

Geometry Nodes: Uniform mode in Shortest Edge Paths node #114733

Closed
Iliya Katushenock wants to merge 9 commits from mod_moder:tmp_speedup_uniform_shortest_edge_paths into main
pull from: mod_moder:tmp_speedup_uniform_shortest_edge_paths
merge into: blender:main

When changing the target branch, be careful to rebase the branch in your fork to match. See documentation.
Conversation 3 Commits 9 Files Changed 1 +21 -19
Iliya Katushenock commented 2023-11-11 11:28:27 +01:00
Member
Copy Link

If Weight input is single, speed of node can be improved due to reduce random-memory reads in hot loop.
Impact is depends on memory bandwidth, my results is 885.95 ms -> 675.35 ms.

If `Weight` input is single, speed of node can be improved due to reduce random-memory reads in hot loop. Impact is depends on memory bandwidth, my results is `885.95 ms` -> `675.35 ms`.
Unifor shortest edge path test.blend
954 KiB
👍 1
Iliya Katushenock added the
Interest
Geometry Nodes
 label 2023-11-11 11:28:27 +01:00
Iliya Katushenock added 1 commit 2023-11-11 11:28:38 +01:00
Iliya Katushenock added 1 commit 2023-11-11 11:29:09 +01:00
Iliya Katushenock added this to the Nodes & Physics project 2023-11-11 11:29:13 +01:00
Iliya Katushenock requested review from Hans Goudey 2023-11-11 11:30:55 +01:00
Iliya Katushenock added 1 commit 2023-11-11 11:40:30 +01:00
Iliya Katushenock added 1 commit 2023-11-11 17:43:43 +01:00
Iliya Katushenock added 1 commit 2023-11-13 16:07:24 +01:00
Iliya Katushenock added 1 commit 2023-11-14 12:58:23 +01:00
Hans Goudey requested changes 2024-01-19 20:04:14 +01:00
Hans Goudey left a comment
Member
Copy Link

It looks like we could move forward with this now, right? I'll just request changes because the branch needs to have main merged in.

It looks like we could move forward with this now, right? I'll just request changes because the branch needs to have main merged in.
👍 1
Iliya Katushenock added 2 commits 2024-01-19 22:03:57 +01:00
Iliya Katushenock requested review from Hans Goudey 2024-01-19 22:04:35 +01:00
Hans Goudey commented 2024-01-20 20:17:10 +01:00
Member
Copy Link

Hmm, unfortunately I can't reproduce the speedup here:

Random value
BEFORE Timer 'shortest_paths': (Average: 29.33 ms, Min: 28.27 ms, Last: 28.59 ms)
AFTER  Timer 'shortest_paths': (Average: 28.39 ms, Min: 27.33 ms, Last: 27.84 ms)
Single value
BEFORE Timer 'shortest_paths': (Average: 26.88 ms, Min: 26.03 ms, Last: 26.55 ms)
AFTER  Timer 'shortest_paths': (Average: 25.92 ms, Min: 25.07 ms, Last: 25.38 ms)
Hmm, unfortunately I can't reproduce the speedup here: ``` Random value BEFORE Timer 'shortest_paths': (Average: 29.33 ms, Min: 28.27 ms, Last: 28.59 ms) AFTER Timer 'shortest_paths': (Average: 28.39 ms, Min: 27.33 ms, Last: 27.84 ms) Single value BEFORE Timer 'shortest_paths': (Average: 26.88 ms, Min: 26.03 ms, Last: 26.55 ms) AFTER Timer 'shortest_paths': (Average: 25.92 ms, Min: 25.07 ms, Last: 25.38 ms) ```
👀 1
Iliya Katushenock commented 2024-01-21 13:52:54 +01:00
Author
Member
Copy Link

Initially i made other version of function (which is works with int-weights and bypass some things (like std::max(0, weight)), result was wrapped in garray-converter). Now, to simplify things, i change implementation to simply use devirtualize_varray. And it seems, now change just 25%. Though it is still a enough.
I think it really depend on memory bandwidth, not sure how to reproduce this results on machine with faster ram.
I also changed test file (10x more mesh) to make results more different.

Initially i made other version of function (which is works with int-weights and bypass some things (like `std::max(0, weight)`), result was wrapped in garray-converter). Now, to simplify things, i change implementation to simply use `devirtualize_varray`. And it seems, now change just `25%`. Though it is still a enough. I think it really depend on memory bandwidth, not sure how to reproduce this results on machine with faster ram. I also changed test file (10x more mesh) to make results more different.
Iliya Katushenock added 1 commit 2024-01-21 13:55:07 +01:00
Iliya Katushenock commented 2024-04-06 00:00:52 +02:00
Author
Member
Copy Link

Tried other ways to reduce memory bounds in hot loop and it seems there is no way to make it visibly faster.

  devirtualize_varray(input_cost, [&](auto input_cost) {
    while (!queue.empty()) {
      const float cost_i = queue.top().first;
      const int vert_i = queue.top().second;
      queue.pop();
      if (visited[vert_i]) {
        continue;
      }
      visited[vert_i] = true;
      for (const auto [other_vert, edge] : edge_paths[vert_i]) {
        if (visited[other_vert]) {
          continue;
        }
        const float edge_cost = std::max(0.0f, input_cost[edge]);
        const float new_neighbor_cost = cost_i + edge_cost;
        if (new_neighbor_cost < next_and_cost[other_vert].second) {
          queue.emplace(new_neighbor_cost, other_vert);
        }
      }
      for (const auto [other_vert, edge] : edge_paths[vert_i]) {
        if (visited[other_vert]) {
          continue;
        }
        const float edge_cost = std::max(0.0f, input_cost[edge]);
        const float new_neighbor_cost = cost_i + edge_cost;
        if (new_neighbor_cost < next_and_cost[other_vert].second) {
          next_and_cost[other_vert] = {vert_i, new_neighbor_cost};
        }
      }
    }
  });

Probably, next investigations should be in direction of using multithreaded A*.

Tried other ways to reduce memory bounds in hot loop and it seems there is no way to make it visibly faster. ```Cpp devirtualize_varray(input_cost, [&](auto input_cost) { while (!queue.empty()) { const float cost_i = queue.top().first; const int vert_i = queue.top().second; queue.pop(); if (visited[vert_i]) { continue; } visited[vert_i] = true; for (const auto [other_vert, edge] : edge_paths[vert_i]) { if (visited[other_vert]) { continue; } const float edge_cost = std::max(0.0f, input_cost[edge]); const float new_neighbor_cost = cost_i + edge_cost; if (new_neighbor_cost < next_and_cost[other_vert].second) { queue.emplace(new_neighbor_cost, other_vert); } } for (const auto [other_vert, edge] : edge_paths[vert_i]) { if (visited[other_vert]) { continue; } const float edge_cost = std::max(0.0f, input_cost[edge]); const float new_neighbor_cost = cost_i + edge_cost; if (new_neighbor_cost < next_and_cost[other_vert].second) { next_and_cost[other_vert] = {vert_i, new_neighbor_cost}; } } } }); ``` Probably, next investigations should be in direction of using multithreaded A*.
Iliya Katushenock deleted branch tmp_speedup_uniform_shortest_edge_paths 2024-04-06 00:01:14 +02:00

Pull request closed

This pull request cannot be reopened because the branch was deleted.
Sign in to join this conversation.
Reviewers
No reviewers
Hans Goudey
Labels
Clear labels   
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
This issue affects/is about backward or forward 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
Issues relating to Wayland windowing support.

  
Interest
Workbench

  
Interest: X11

Issues relating to Xorg/X11 support.

  
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
Issues relating to security: https://wiki.blender.org/wiki/Process/Vulnerability_Reports

  
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 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
Milestone
Clear milestone
No items
No Milestone
Projects
Clear projects
No project
Nodes & Physics
Assignees
Clear assignees
No Assignees
2 Participants
Notifications
Due Date
The due date is invalid or out of range. Please use the format 'yyyy-mm-dd'.

No due date set.

Depends on
#114684 Cleanup: Geometry Nodes: Early returns in Shortest Edge Paths node
blender/blender
#114707 Geometry Nodes: Speedup of Shortest Edge Paths node
blender/blender
Reference: blender/blender#114733
No description provided.
Delete Branch "mod_moder:tmp_speedup_uniform_shortest_edge_paths"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?