Add assert implementation for device side testing

[pciolkosz]

CCCL is tested in release build and by default assert is compiled out. In CUDAX hierarchy testing device side uses assert for convenient printing and termination, we do #indef NDEBUG to make the asserts stay.
Recently I wanted to remove on extremely long running test from debug builds, but because of the #undef NDEBUG it was difficult to detect a debug build.

I decided to just switch to a custom assert implementation and remove the #undef. This has another benefit that we could do warp aggregate error printing for easier readible logs etc in the future.
This change also renames HOST_DEV_REQUIRE to CUDAX_REQUIRE.

[github-actions]

🟩 CI finished in 1h 45m: Pass: 100%/55 | Total: 2h 42m | Avg: 2m 57s | Max: 9m 52s | Hits: 88%/1308

• 🟩 cudax: Pass: 100%/55 | Total: 2h 42m | Avg: 2m 57s | Max: 9m 52s | Hits: 88%/1308

  🟩 cpu
    🟩 amd64              Pass: 100%/51  | Total:  2h 33m | Avg:  3m 00s | Max:  9m 52s | Hits:  88%/1212  
    🟩 arm64              Pass: 100%/4   | Total:  9m 22s | Avg:  2m 20s | Max:  2m 34s | Hits:  87%/96    
  🟩 ctk
    🟩 12.0               Pass: 100%/23  | Total:  1h 08m | Avg:  2m 59s | Max:  9m 47s | Hits:  87%/546   
    🟩 12.4               Pass: 100%/32  | Total:  1h 34m | Avg:  2m 56s | Max:  9m 52s | Hits:  88%/762   
  🟩 cudacxx
    🟩 nvcc12.0           Pass: 100%/23  | Total:  1h 08m | Avg:  2m 59s | Max:  9m 47s | Hits:  87%/546   
    🟩 nvcc12.4           Pass: 100%/32  | Total:  1h 34m | Avg:  2m 56s | Max:  9m 52s | Hits:  88%/762   
  🟩 cudacxx_family
    🟩 nvcc               Pass: 100%/55  | Total:  2h 42m | Avg:  2m 57s | Max:  9m 52s | Hits:  88%/1308  
  🟩 cxx
    🟩 Clang9             Pass: 100%/2   | Total:  4m 56s | Avg:  2m 28s | Max:  2m 29s | Hits:  91%/48    
    🟩 Clang10            Pass: 100%/2   | Total:  5m 08s | Avg:  2m 34s | Max:  2m 34s | Hits:  91%/48    
    🟩 Clang11            Pass: 100%/4   | Total:  9m 40s | Avg:  2m 25s | Max:  2m 30s | Hits:  91%/96    
    🟩 Clang12            Pass: 100%/4   | Total: 10m 21s | Avg:  2m 35s | Max:  2m 56s | Hits:  91%/96    
    🟩 Clang13            Pass: 100%/4   | Total:  9m 49s | Avg:  2m 27s | Max:  2m 33s | Hits:  91%/96    
    🟩 Clang14            Pass: 100%/6   | Total: 17m 46s | Avg:  2m 57s | Max:  4m 23s | Hits:  94%/144   
    🟩 Clang15            Pass: 100%/2   | Total:  5m 06s | Avg:  2m 33s | Max:  2m 36s | Hits:  91%/48    
    🟩 Clang16            Pass: 100%/6   | Total: 18m 08s | Avg:  3m 01s | Max:  4m 30s | Hits:  94%/144   
    🟩 GCC9               Pass: 100%/2   | Total:  4m 53s | Avg:  2m 26s | Max:  2m 29s | Hits:  83%/48    
    🟩 GCC10              Pass: 100%/4   | Total:  9m 26s | Avg:  2m 21s | Max:  2m 32s | Hits:  83%/96    
    🟩 GCC11              Pass: 100%/4   | Total:  9m 13s | Avg:  2m 18s | Max:  2m 22s | Hits:  83%/96    
    🟩 GCC12              Pass: 100%/12  | Total: 35m 49s | Avg:  2m 59s | Max:  6m 02s | Hits:  86%/288   
    🟩 Intel2023.2.0      Pass: 100%/1   | Total:  3m 00s | Avg:  3m 00s | Max:  3m 00s | Hits:  91%/24    
    🟩 MSVC14.36          Pass: 100%/1   | Total:  9m 47s | Avg:  9m 47s | Max:  9m 47s | Hits:  44%/18    
    🟩 MSVC14.39          Pass: 100%/1   | Total:  9m 52s | Avg:  9m 52s | Max:  9m 52s | Hits:  44%/18    
  🟩 cxx_family
    🟩 Clang              Pass: 100%/30  | Total:  1h 20m | Avg:  2m 41s | Max:  4m 30s | Hits:  92%/720   
    🟩 GCC                Pass: 100%/22  | Total: 59m 21s | Avg:  2m 41s | Max:  6m 02s | Hits:  84%/528   
    🟩 Intel              Pass: 100%/1   | Total:  3m 00s | Avg:  3m 00s | Max:  3m 00s | Hits:  91%/24    
    🟩 MSVC               Pass: 100%/2   | Total: 19m 39s | Avg:  9m 49s | Max:  9m 52s | Hits:  44%/36    
  🟩 gpu
    🟩 v100               Pass: 100%/55  | Total:  2h 42m | Avg:  2m 57s | Max:  9m 52s | Hits:  88%/1308  
  🟩 jobs
    🟩 Build              Pass: 100%/47  | Total:  2h 10m | Avg:  2m 46s | Max:  9m 52s | Hits:  86%/1116  
    🟩 Test               Pass: 100%/8   | Total: 32m 25s | Avg:  4m 03s | Max:  6m 02s | Hits:  95%/192   
  🟩 sm
    🟩 90                 Pass: 100%/1   | Total:  2m 18s | Avg:  2m 18s | Max:  2m 18s | Hits:  83%/24    
    🟩 90a                Pass: 100%/1   | Total:  2m 24s | Avg:  2m 24s | Max:  2m 24s | Hits:  83%/24    
  🟩 std
    🟩 17                 Pass: 100%/31  | Total:  1h 22m | Avg:  2m 39s | Max:  4m 30s | Hits:  89%/744   
    🟩 20                 Pass: 100%/24  | Total:  1h 20m | Avg:  3m 20s | Max:  9m 52s | Hits:  86%/564   
  

👃 Inspect Changes

Modifications in project?

	Project
	CCCL Infrastructure
	libcu++
	CUB
	Thrust
+/-	CUDA Experimental

Modifications in project or dependencies?

	Project
	CCCL Infrastructure
	libcu++
	CUB
	Thrust
+/-	CUDA Experimental

🏃‍ Runner counts (total jobs: 55)

#	Runner
41	linux-amd64-cpu16
8	linux-amd64-gpu-v100-latest-1
4	linux-arm64-cpu16
2	windows-amd64-cpu16

[github-actions]

🟩 CI finished in 36m 09s: Pass: 100%/55 | Total: 2h 41m | Avg: 2m 56s | Max: 10m 13s | Hits: 88%/1308

• 🟩 cudax: Pass: 100%/55 | Total: 2h 41m | Avg: 2m 56s | Max: 10m 13s | Hits: 88%/1308

  🟩 cpu
    🟩 amd64              Pass: 100%/51  | Total:  2h 32m | Avg:  2m 59s | Max: 10m 13s | Hits:  88%/1212  
    🟩 arm64              Pass: 100%/4   | Total:  9m 14s | Avg:  2m 18s | Max:  2m 33s | Hits:  87%/96    
  🟩 ctk
    🟩 12.0               Pass: 100%/23  | Total:  1h 08m | Avg:  2m 59s | Max: 10m 13s | Hits:  87%/546   
    🟩 12.4               Pass: 100%/32  | Total:  1h 32m | Avg:  2m 53s | Max:  9m 47s | Hits:  88%/762   
  🟩 cudacxx
    🟩 nvcc12.0           Pass: 100%/23  | Total:  1h 08m | Avg:  2m 59s | Max: 10m 13s | Hits:  87%/546   
    🟩 nvcc12.4           Pass: 100%/32  | Total:  1h 32m | Avg:  2m 53s | Max:  9m 47s | Hits:  88%/762   
  🟩 cudacxx_family
    🟩 nvcc               Pass: 100%/55  | Total:  2h 41m | Avg:  2m 56s | Max: 10m 13s | Hits:  88%/1308  
  🟩 cxx
    🟩 Clang9             Pass: 100%/2   | Total:  4m 52s | Avg:  2m 26s | Max:  2m 28s | Hits:  91%/48    
    🟩 Clang10            Pass: 100%/2   | Total:  4m 54s | Avg:  2m 27s | Max:  2m 28s | Hits:  91%/48    
    🟩 Clang11            Pass: 100%/4   | Total:  9m 50s | Avg:  2m 27s | Max:  2m 39s | Hits:  91%/96    
    🟩 Clang12            Pass: 100%/4   | Total: 10m 24s | Avg:  2m 36s | Max:  2m 45s | Hits:  91%/96    
    🟩 Clang13            Pass: 100%/4   | Total:  9m 57s | Avg:  2m 29s | Max:  2m 35s | Hits:  91%/96    
    🟩 Clang14            Pass: 100%/6   | Total: 17m 52s | Avg:  2m 58s | Max:  4m 08s | Hits:  94%/144   
    🟩 Clang15            Pass: 100%/2   | Total:  4m 49s | Avg:  2m 24s | Max:  2m 25s | Hits:  91%/48    
    🟩 Clang16            Pass: 100%/6   | Total: 18m 51s | Avg:  3m 08s | Max:  4m 19s | Hits:  94%/144   
    🟩 GCC9               Pass: 100%/2   | Total:  4m 43s | Avg:  2m 21s | Max:  2m 24s | Hits:  83%/48    
    🟩 GCC10              Pass: 100%/4   | Total:  9m 31s | Avg:  2m 22s | Max:  2m 30s | Hits:  83%/96    
    🟩 GCC11              Pass: 100%/4   | Total:  9m 33s | Avg:  2m 23s | Max:  2m 34s | Hits:  83%/96    
    🟩 GCC12              Pass: 100%/12  | Total: 33m 11s | Avg:  2m 45s | Max:  3m 43s | Hits:  86%/288   
    🟩 Intel2023.2.0      Pass: 100%/1   | Total:  2m 58s | Avg:  2m 58s | Max:  2m 58s | Hits:  91%/24    
    🟩 MSVC14.36          Pass: 100%/1   | Total: 10m 13s | Avg: 10m 13s | Max: 10m 13s | Hits:  44%/18    
    🟩 MSVC14.39          Pass: 100%/1   | Total:  9m 47s | Avg:  9m 47s | Max:  9m 47s | Hits:  44%/18    
  🟩 cxx_family
    🟩 Clang              Pass: 100%/30  | Total:  1h 21m | Avg:  2m 42s | Max:  4m 19s | Hits:  92%/720   
    🟩 GCC                Pass: 100%/22  | Total: 56m 58s | Avg:  2m 35s | Max:  3m 43s | Hits:  84%/528   
    🟩 Intel              Pass: 100%/1   | Total:  2m 58s | Avg:  2m 58s | Max:  2m 58s | Hits:  91%/24    
    🟩 MSVC               Pass: 100%/2   | Total: 20m 00s | Avg: 10m 00s | Max: 10m 13s | Hits:  44%/36    
  🟩 gpu
    🟩 v100               Pass: 100%/55  | Total:  2h 41m | Avg:  2m 56s | Max: 10m 13s | Hits:  88%/1308  
  🟩 jobs
    🟩 Build              Pass: 100%/47  | Total:  2h 10m | Avg:  2m 46s | Max: 10m 13s | Hits:  86%/1116  
    🟩 Test               Pass: 100%/8   | Total: 30m 44s | Avg:  3m 50s | Max:  4m 19s | Hits:  95%/192   
  🟩 sm
    🟩 90                 Pass: 100%/1   | Total:  2m 14s | Avg:  2m 14s | Max:  2m 14s | Hits:  83%/24    
    🟩 90a                Pass: 100%/1   | Total:  2m 10s | Avg:  2m 10s | Max:  2m 10s | Hits:  83%/24    
  🟩 std
    🟩 17                 Pass: 100%/31  | Total:  1h 20m | Avg:  2m 36s | Max:  3m 59s | Hits:  89%/744   
    🟩 20                 Pass: 100%/24  | Total:  1h 20m | Avg:  3m 21s | Max: 10m 13s | Hits:  86%/564   
  

👃 Inspect Changes

Modifications in project?

	Project
	CCCL Infrastructure
	libcu++
	CUB
	Thrust
+/-	CUDA Experimental

Modifications in project or dependencies?

	Project
	CCCL Infrastructure
	libcu++
	CUB
	Thrust
+/-	CUDA Experimental

🏃‍ Runner counts (total jobs: 55)

#	Runner
41	linux-amd64-cpu16
8	linux-amd64-gpu-v100-latest-1
4	linux-arm64-cpu16
2	windows-amd64-cpu16