Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Rename managed_memory_resource to unified_memory_resource #4103

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

miscco
Copy link
Contributor

@miscco miscco commented Mar 12, 2025

This renames the memory resource and also makes it so that it shows up in our docs

miscco added 2 commits March 12, 2025 11:29
This renames the `managed_memory_resource` to `unified_memory_resource`. While we are at it also add the classes to our documentation.

Fixes NVIDIA#4093
Fixes NVIDIA#4094
Copy link
Contributor

🟩 CI finished in 24m 29s: Pass: 100%/22 | Total: 2h 23m | Avg: 6m 30s | Max: 16m 11s | Hits: 93%/11722
  • 🟩 cudax: Pass: 100%/22 | Total: 2h 23m | Avg: 6m 30s | Max: 16m 11s | Hits: 93%/11722

    🟩 cpu
      🟩 amd64              Pass: 100%/18  | Total:  2h 08m | Avg:  7m 08s | Max: 16m 11s | Hits:  93%/9406  
      🟩 arm64              Pass: 100%/4   | Total: 14m 38s | Avg:  3m 39s | Max:  3m 49s | Hits:  94%/2316  
    🟩 ctk
      🟩 12.0               Pass: 100%/1   | Total: 12m 54s | Avg: 12m 54s | Max: 12m 54s | Hits:  57%/277   
      🟩 12.5               Pass: 100%/2   | Total: 12m 57s | Avg:  6m 28s | Max:  6m 47s | Hits:  88%/742   
      🟩 12.8               Pass: 100%/19  | Total:  1h 57m | Avg:  6m 10s | Max: 16m 11s | Hits:  94%/10703 
    🟩 cudacxx
      🟩 nvcc12.0           Pass: 100%/1   | Total: 12m 54s | Avg: 12m 54s | Max: 12m 54s | Hits:  57%/277   
      🟩 nvcc12.5           Pass: 100%/2   | Total: 12m 57s | Avg:  6m 28s | Max:  6m 47s | Hits:  88%/742   
      🟩 nvcc12.8           Pass: 100%/19  | Total:  1h 57m | Avg:  6m 10s | Max: 16m 11s | Hits:  94%/10703 
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/22  | Total:  2h 23m | Avg:  6m 30s | Max: 16m 11s | Hits:  93%/11722 
    🟩 cxx
      🟩 Clang14            Pass: 100%/1   | Total:  4m 18s | Avg:  4m 18s | Max:  4m 18s | Hits:  95%/581   
      🟩 Clang15            Pass: 100%/1   | Total:  4m 14s | Avg:  4m 14s | Max:  4m 14s | Hits:  95%/579   
      🟩 Clang16            Pass: 100%/1   | Total:  4m 22s | Avg:  4m 22s | Max:  4m 22s | Hits:  95%/579   
      🟩 Clang17            Pass: 100%/1   | Total:  4m 23s | Avg:  4m 23s | Max:  4m 23s | Hits:  95%/579   
      🟩 Clang18            Pass: 100%/4   | Total: 25m 04s | Avg:  6m 16s | Max: 13m 51s | Hits:  96%/2316  
      🟩 GCC10              Pass: 100%/1   | Total:  4m 04s | Avg:  4m 04s | Max:  4m 04s | Hits:  94%/581   
      🟩 GCC11              Pass: 100%/1   | Total:  4m 09s | Avg:  4m 09s | Max:  4m 09s | Hits:  94%/579   
      🟩 GCC12              Pass: 100%/2   | Total: 20m 17s | Avg: 10m 08s | Max: 16m 11s | Hits:  97%/1158  
      🟩 GCC13              Pass: 100%/6   | Total: 32m 39s | Avg:  5m 26s | Max: 14m 00s | Hits:  95%/3474  
      🟩 MSVC14.39          Pass: 100%/1   | Total: 12m 54s | Avg: 12m 54s | Max: 12m 54s | Hits:  57%/277   
      🟩 MSVC14.42          Pass: 100%/1   | Total: 13m 58s | Avg: 13m 58s | Max: 13m 58s | Hits:  57%/277   
      🟩 NVHPC24.7          Pass: 100%/2   | Total: 12m 57s | Avg:  6m 28s | Max:  6m 47s | Hits:  88%/742   
    🟩 cxx_family
      🟩 Clang              Pass: 100%/8   | Total: 42m 21s | Avg:  5m 17s | Max: 13m 51s | Hits:  95%/4634  
      🟩 GCC                Pass: 100%/10  | Total:  1h 01m | Avg:  6m 06s | Max: 16m 11s | Hits:  95%/5792  
      🟩 MSVC               Pass: 100%/2   | Total: 26m 52s | Avg: 13m 26s | Max: 13m 58s | Hits:  57%/554   
      🟩 NVHPC              Pass: 100%/2   | Total: 12m 57s | Avg:  6m 28s | Max:  6m 47s | Hits:  88%/742   
    🟩 gpu
      🟩 h100               Pass: 100%/2   | Total: 17m 47s | Avg:  8m 53s | Max: 14m 00s | Hits:  97%/1158  
      🟩 rtx2080            Pass: 100%/20  | Total:  2h 05m | Avg:  6m 16s | Max: 16m 11s | Hits:  93%/10564 
    🟩 jobs
      🟩 Build              Pass: 100%/19  | Total:  1h 39m | Avg:  5m 13s | Max: 13m 58s | Hits:  92%/9985  
      🟩 Test               Pass: 100%/3   | Total: 44m 02s | Avg: 14m 40s | Max: 16m 11s | Hits:  99%/1737  
    🟩 sm
      🟩 90                 Pass: 100%/3   | Total: 21m 17s | Avg:  7m 05s | Max: 14m 00s | Hits:  96%/1737  
      🟩 90a                Pass: 100%/1   | Total:  3m 47s | Avg:  3m 47s | Max:  3m 47s | Hits:  94%/579   
    🟩 std
      🟩 17                 Pass: 100%/4   | Total: 16m 57s | Avg:  4m 14s | Max:  6m 10s | Hits:  93%/2108  
      🟩 20                 Pass: 100%/18  | Total:  2h 06m | Avg:  7m 01s | Max: 16m 11s | Hits:  93%/9614  
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
libcu++
CUB
Thrust
+/- CUDA Experimental
python
CCCL C Parallel Library
Catch2Helper

Modifications in project or dependencies?

Project
CCCL Infrastructure
libcu++
CUB
Thrust
+/- CUDA Experimental
python
CCCL C Parallel Library
Catch2Helper

🏃‍ Runner counts (total jobs: 22)

# Runner
13 linux-amd64-cpu16
4 linux-arm64-cpu16
2 windows-amd64-cpu16
2 linux-amd64-gpu-rtx2080-latest-1
1 linux-amd64-gpu-h100-latest-1

Copy link
Contributor

@pciolkosz pciolkosz left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I have mixed feelings about this. In the programming guide unified memory is not the same thing as manage memory.
https://docs.nvidia.com/cuda/cuda-c-programming-guide/#unified-memory-introduction
I think if this is always using managed memory we might want to keep that name

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: In Progress
3 participants