do not constexpr cast to enum a value that is outside the enum's range

[ericniebler]

Description

For older CTK's, cudax's device attributes code defines the following:

  static constexpr type fabric = static_cast<::cudaMemAllocationHandleType>(0x8);

the trouble is that that is not actually valid code. 0x8 is outside the range of the cudaMemAllocationHandleType enum before 12.4. I'm not sure why we are skating by in the tests. maybe it's because we use the system_header pragma.

but clangd flags this as broken, which causes most of the cudax headers appear red (as having errors) in vscode when using one of the cuda12.0 devcontainers. and that makes clangd less useful.

i like clangd. i also like conforming code. make the class static an inline const instead of constexpr.

Checklist

• New or existing tests cover these changes.
• The documentation is up to date with these changes.

[github-actions]

🟩 CI finished in 22m 24s: Pass: 100%/30 | Total: 2h 35m | Avg: 5m 11s | Max: 17m 15s | Hits: 97%/15084

• 🟩 cudax: Pass: 100%/26 | Total: 2h 21m | Avg: 5m 26s | Max: 17m 15s | Hits: 97%/15084

  🟩 cpu
    🟩 amd64              Pass: 100%/22  | Total:  2h 08m | Avg:  5m 50s | Max: 17m 15s | Hits:  96%/12672 
    🟩 arm64              Pass: 100%/4   | Total: 13m 00s | Avg:  3m 15s | Max:  3m 31s | Hits:  99%/2412  
  🟩 ctk
    🟩 12.0               Pass: 100%/3   | Total: 27m 32s | Avg:  9m 10s | Max: 17m 15s | Hits:  76%/1514  
    🟩 12.9               Pass: 100%/23  | Total:  1h 53m | Avg:  4m 56s | Max: 11m 24s | Hits:  99%/13570 
  🟩 cudacxx
    🟩 nvcc12.0           Pass: 100%/3   | Total: 27m 32s | Avg:  9m 10s | Max: 17m 15s | Hits:  76%/1514  
    🟩 nvcc12.9           Pass: 100%/23  | Total:  1h 53m | Avg:  4m 56s | Max: 11m 24s | Hits:  99%/13570 
  🟩 cudacxx_family
    🟩 nvcc               Pass: 100%/26  | Total:  2h 21m | Avg:  5m 26s | Max: 17m 15s | Hits:  97%/15084 
  🟩 cxx
    🟩 Clang14            Pass: 100%/2   | Total:  8m 04s | Avg:  4m 02s | Max:  4m 40s | Hits:  90%/1210  
    🟩 Clang15            Pass: 100%/1   | Total:  3m 38s | Avg:  3m 38s | Max:  3m 38s | Hits:  99%/603   
    🟩 Clang16            Pass: 100%/1   | Total:  3m 39s | Avg:  3m 39s | Max:  3m 39s | Hits:  99%/603   
    🟩 Clang17            Pass: 100%/1   | Total:  3m 36s | Avg:  3m 36s | Max:  3m 36s | Hits:  99%/603   
    🟩 Clang18            Pass: 100%/1   | Total:  3m 19s | Avg:  3m 19s | Max:  3m 19s | Hits:  99%/603   
    🟩 Clang19            Pass: 100%/4   | Total: 18m 37s | Avg:  4m 39s | Max:  8m 51s | Hits:  99%/2412  
    🟩 GCC10              Pass: 100%/2   | Total:  9m 29s | Avg:  4m 44s | Max:  5m 37s | Hits:  90%/1210  
    🟩 GCC11              Pass: 100%/1   | Total:  3m 50s | Avg:  3m 50s | Max:  3m 50s | Hits:  99%/603   
    🟩 GCC12              Pass: 100%/1   | Total:  4m 11s | Avg:  4m 11s | Max:  4m 11s | Hits:  99%/603   
    🟩 GCC13              Pass: 100%/8   | Total: 39m 45s | Avg:  4m 58s | Max: 10m 57s | Hits:  99%/4824  
    🟩 MSVC14.39          Pass: 100%/1   | Total: 17m 15s | Avg: 17m 15s | Max: 17m 15s | Hits:  58%/304   
    🟩 MSVC14.43          Pass: 100%/1   | Total: 11m 24s | Avg: 11m 24s | Max: 11m 24s | Hits:  95%/304   
    🟩 NVHPC25.5          Pass: 100%/2   | Total: 14m 34s | Avg:  7m 17s | Max:  7m 24s | Hits:  97%/1202  
  🟩 cxx_family
    🟩 Clang              Pass: 100%/10  | Total: 40m 53s | Avg:  4m 05s | Max:  8m 51s | Hits:  98%/6034  
    🟩 GCC                Pass: 100%/12  | Total: 57m 15s | Avg:  4m 46s | Max: 10m 57s | Hits:  97%/7240  
    🟩 MSVC               Pass: 100%/2   | Total: 28m 39s | Avg: 14m 19s | Max: 17m 15s | Hits:  76%/608   
    🟩 NVHPC              Pass: 100%/2   | Total: 14m 34s | Avg:  7m 17s | Max:  7m 24s | Hits:  97%/1202  
  🟩 gpu
    🟩 h100               Pass: 100%/2   | Total: 11m 12s | Avg:  5m 36s | Max:  7m 56s | Hits:  99%/1206  
    🟩 rtx2080            Pass: 100%/24  | Total:  2h 10m | Avg:  5m 25s | Max: 17m 15s | Hits:  96%/13878 
  🟩 jobs
    🟩 Build              Pass: 100%/23  | Total:  1h 53m | Avg:  4m 56s | Max: 17m 15s | Hits:  96%/13275 
    🟩 Test               Pass: 100%/3   | Total: 27m 44s | Avg:  9m 14s | Max: 10m 57s | Hits:  99%/1809  
  🟩 sm
    🟩 90                 Pass: 100%/3   | Total: 14m 25s | Avg:  4m 48s | Max:  7m 56s | Hits:  99%/1809  
    🟩 90a                Pass: 100%/1   | Total:  3m 14s | Avg:  3m 14s | Max:  3m 14s | Hits:  99%/603   
  🟩 std
    🟩 17                 Pass: 100%/4   | Total: 17m 04s | Avg:  4m 16s | Max:  7m 24s | Hits:  99%/2410  
    🟩 20                 Pass: 100%/22  | Total:  2h 04m | Avg:  5m 38s | Max: 17m 15s | Hits:  96%/12674 
  

• 🟩 packaging: Pass: 100%/4 | Total: 14m 17s | Avg: 3m 34s | Max: 3m 49s

  🟩 cpu
    🟩 amd64              Pass: 100%/4   | Total: 14m 17s | Avg:  3m 34s | Max:  3m 49s
  🟩 ctk
    🟩 12.0               Pass: 100%/2   | Total:  7m 30s | Avg:  3m 45s | Max:  3m 49s
    🟩 12.9               Pass: 100%/2   | Total:  6m 47s | Avg:  3m 23s | Max:  3m 29s
  🟩 cudacxx
    🟩 nvcc12.0           Pass: 100%/2   | Total:  7m 30s | Avg:  3m 45s | Max:  3m 49s
    🟩 nvcc12.9           Pass: 100%/2   | Total:  6m 47s | Avg:  3m 23s | Max:  3m 29s
  🟩 cudacxx_family
    🟩 nvcc               Pass: 100%/4   | Total: 14m 17s | Avg:  3m 34s | Max:  3m 49s
  🟩 cxx
    🟩 Clang14            Pass: 100%/1   | Total:  3m 49s | Avg:  3m 49s | Max:  3m 49s
    🟩 Clang19            Pass: 100%/1   | Total:  3m 29s | Avg:  3m 29s | Max:  3m 29s
    🟩 GCC12              Pass: 100%/1   | Total:  3m 41s | Avg:  3m 41s | Max:  3m 41s
    🟩 GCC13              Pass: 100%/1   | Total:  3m 18s | Avg:  3m 18s | Max:  3m 18s
  🟩 cxx_family
    🟩 Clang              Pass: 100%/2   | Total:  7m 18s | Avg:  3m 39s | Max:  3m 49s
    🟩 GCC                Pass: 100%/2   | Total:  6m 59s | Avg:  3m 29s | Max:  3m 41s
  🟩 gpu
    🟩 rtx2080            Pass: 100%/4   | Total: 14m 17s | Avg:  3m 34s | Max:  3m 49s
  🟩 jobs
    🟩 Test               Pass: 100%/4   | Total: 14m 17s | Avg:  3m 34s | Max:  3m 49s
  

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 30)

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

[miscco]