Skip to content
GitLab
Projects Groups Topics Snippets
  • /
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
  • Register
  • Sign in
  • L llm.c - GPT2
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributor statistics
    • Graph
    • Compare revisions
  • Issues 4
    • Issues 4
    • List
    • Boards
    • Service Desk
    • Milestones
  • Merge requests 0
    • Merge requests 0
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Schedules
  • Deployments
    • Deployments
    • Environments
    • Releases
  • Packages and registries
    • Packages and registries
    • Package Registry
    • Container Registry
    • Terraform modules
  • Monitor
    • Monitor
    • Metrics
    • Incidents
  • Analytics
    • Analytics
    • Value stream
    • CI/CD
    • Repository
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
Collapse sidebar
  • tchatela
  • llm.c - GPT2
  • Wiki
  • Runtime and performances

Runtime and performances · Changes

Page history
Update Runtime and performances authored Jul 04, 2024 by tchatela's avatar tchatela
Hide whitespace changes
Inline Side-by-side
Runtime-and-performances.md
View page @ 8ecb0f57
......@@ -64,6 +64,8 @@ However, something else stands out. On another test, which runtime is shown just
## General comparison
### Between versions
This board shows the mean runtime taken for one iteration. The sequential versions are using one thread, the parallels ones are using 2 threads.
| setup \\ version | seq. without -fopenmp | seq with -fopenmp | openMP | openmp/nOS-V |
......@@ -76,4 +78,10 @@ The tests run with numactl can sometimes output the following error :
`ERROR numa_sched_setaffinity_v2_int() failed: Invalid argument` \
`sched_setaffinity: Invalid argument`
However, this error is not occurring systematically.
\ No newline at end of file
However, this error is not occurring systematically.
### With number of threads
![model-perf-base](uploads/9aa5c941abc636bfc7fa05219b2c7488/model-perf-base.png)
Here are the performances of the original given model, compiled with OpenMP. As shown be the graph, the performances of the model stop increasing over 15/20 threads.
\ No newline at end of file
Clone repository

GPT2 Parallelization and Porting

  • Model Description
  • Runtime and Performances
  • Improvements