[CUDAX] Add a global constexpr `cudax::devices` range for all devices in the system by ericniebler · Pull Request #2100 · NVIDIA/cccl

ericniebler · 2024-07-29T22:04:46Z

Description

This PR adds a global constexpr range of cudax::device objects. cudax::devices[0] is the same as cudax::device(0). The number of cuda devices in the system can be obtained with cudax::devices.size().

see [548fc5d] for the changes in only this PR. EDIT: i will rebase when #2084 is merged.

closes #2099

Checklist

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

copy-pr-bot · 2024-07-29T22:04:49Z

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

ericniebler · 2024-07-29T22:07:19Z

pre-commit.ci autofix

ericniebler · 2024-07-29T22:08:16Z

/ok to test

cudax/include/cuda/experimental/__device/device_vector.cuh

ericniebler · 2024-07-30T02:36:38Z

/ok to test

github-actions · 2024-07-30T05:19:10Z

🟩 CI finished in 2h 40m: Pass: 100%/56 | Total: 2h 34m | Avg: 2m 45s | Max: 11m 45s | Hits: 90%/2188

🟩 cudax: Pass: 100%/55 | Total: 2h 22m | Avg: 2m 35s | Max: 7m 57s | Hits: 90%/2188

🟩 cpu
  🟩 amd64              Pass: 100%/51  | Total:  2h 13m | Avg:  2m 37s | Max:  7m 57s | Hits:  90%/2028  
  🟩 arm64              Pass: 100%/4   | Total:  8m 52s | Avg:  2m 13s | Max:  3m 00s | Hits:  90%/160   
🟩 ctk
  🟩 12.0               Pass: 100%/23  | Total:  1h 00m | Avg:  2m 36s | Max:  7m 56s | Hits:  90%/914   
  🟩 12.5               Pass: 100%/32  | Total:  1h 22m | Avg:  2m 34s | Max:  7m 57s | Hits:  90%/1274  
🟩 cudacxx
  🟩 nvcc12.0           Pass: 100%/23  | Total:  1h 00m | Avg:  2m 36s | Max:  7m 56s | Hits:  90%/914   
  🟩 nvcc12.5           Pass: 100%/32  | Total:  1h 22m | Avg:  2m 34s | Max:  7m 57s | Hits:  90%/1274  
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/55  | Total:  2h 22m | Avg:  2m 35s | Max:  7m 57s | Hits:  90%/2188  
🟩 cxx
  🟩 Clang9             Pass: 100%/2   | Total:  4m 20s | Avg:  2m 10s | Max:  2m 18s | Hits:  92%/80    
  🟩 Clang10            Pass: 100%/2   | Total:  3m 59s | Avg:  1m 59s | Max:  2m 01s | Hits:  92%/80    
  🟩 Clang11            Pass: 100%/4   | Total:  8m 41s | Avg:  2m 10s | Max:  2m 20s | Hits:  92%/160   
  🟩 Clang12            Pass: 100%/4   | Total:  8m 37s | Avg:  2m 09s | Max:  2m 15s | Hits:  92%/160   
  🟩 Clang13            Pass: 100%/4   | Total:  7m 59s | Avg:  1m 59s | Max:  2m 02s | Hits:  92%/160   
  🟩 Clang14            Pass: 100%/6   | Total: 16m 10s | Avg:  2m 41s | Max:  3m 59s | Hits:  95%/240   
  🟩 Clang15            Pass: 100%/2   | Total:  4m 28s | Avg:  2m 14s | Max:  2m 21s | Hits:  92%/80    
  🟩 Clang16            Pass: 100%/6   | Total: 16m 43s | Avg:  2m 47s | Max:  4m 12s | Hits:  95%/240   
  🟩 GCC9               Pass: 100%/2   | Total:  4m 12s | Avg:  2m 06s | Max:  2m 07s | Hits:  87%/80    
  🟩 GCC10              Pass: 100%/4   | Total:  7m 55s | Avg:  1m 58s | Max:  2m 10s | Hits:  87%/160   
  🟩 GCC11              Pass: 100%/4   | Total:  7m 46s | Avg:  1m 56s | Max:  2m 10s | Hits:  87%/160   
  🟩 GCC12              Pass: 100%/12  | Total: 33m 01s | Avg:  2m 45s | Max:  4m 01s | Hits:  90%/480   
  🟩 Intel2023.2.0      Pass: 100%/1   | Total:  2m 57s | Avg:  2m 57s | Max:  2m 57s | Hits:  92%/40    
  🟩 MSVC14.36          Pass: 100%/1   | Total:  7m 56s | Avg:  7m 56s | Max:  7m 56s | Hits:  67%/34    
  🟩 MSVC14.39          Pass: 100%/1   | Total:  7m 57s | Avg:  7m 57s | Max:  7m 57s | Hits:  67%/34    
🟩 cxx_family
  🟩 Clang              Pass: 100%/30  | Total:  1h 10m | Avg:  2m 21s | Max:  4m 12s | Hits:  93%/1200  
  🟩 GCC                Pass: 100%/22  | Total: 52m 54s | Avg:  2m 24s | Max:  4m 01s | Hits:  88%/880   
  🟩 Intel              Pass: 100%/1   | Total:  2m 57s | Avg:  2m 57s | Max:  2m 57s | Hits:  92%/40    
  🟩 MSVC               Pass: 100%/2   | Total: 15m 53s | Avg:  7m 56s | Max:  7m 57s | Hits:  67%/68    
🟩 gpu
  🟩 v100               Pass: 100%/55  | Total:  2h 22m | Avg:  2m 35s | Max:  7m 57s | Hits:  90%/2188  
🟩 jobs
  🟩 Build              Pass: 100%/47  | Total:  1h 51m | Avg:  2m 22s | Max:  7m 57s | Hits:  89%/1868  
  🟩 Test               Pass: 100%/8   | Total: 31m 19s | Avg:  3m 54s | Max:  4m 12s | Hits:  97%/320   
🟩 sm
  🟩 90                 Pass: 100%/1   | Total:  1m 54s | Avg:  1m 54s | Max:  1m 54s | Hits:  87%/40    
  🟩 90a                Pass: 100%/1   | Total:  2m 11s | Avg:  2m 11s | Max:  2m 11s | Hits:  87%/40    
🟩 std
  🟩 17                 Pass: 100%/31  | Total:  1h 12m | Avg:  2m 20s | Max:  4m 06s | Hits:  91%/1240  
  🟩 20                 Pass: 100%/24  | Total:  1h 10m | Avg:  2m 55s | Max:  7m 57s | Hits:  90%/948

🟩 pycuda: Pass: 100%/1 | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s

🟩 cpu
  🟩 amd64              Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
🟩 ctk
  🟩 12.5               Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
🟩 cudacxx
  🟩 nvcc12.5           Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
🟩 cxx
  🟩 GCC13              Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
🟩 cxx_family
  🟩 GCC                Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
🟩 gpu
  🟩 v100               Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s
🟩 jobs
  🟩 Test               Pass: 100%/1   | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 56)

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

cudax/include/cuda/experimental/__device/attributes.cuh

cudax/include/cuda/experimental/__device/device_vector.cuh

cudax/test/CMakeLists.txt

the number of cuda devices can be determined by calling `cuda::devices.size()`. `cuda::devices` is a range of `cuda::device` objects.

github-actions · 2024-07-31T00:33:47Z

🟨 CI finished in 5h 06m: Pass: 96%/56 | Total: 3h 13m | Avg: 3m 27s | Max: 10m 52s | Hits: 71%/2279

🟨 cudax: Pass: 96%/55 | Total: 3h 02m | Avg: 3m 19s | Max: 8m 10s | Hits: 71%/2279

🔍 cpu: amd64 🔍
  🔍 amd64              Pass:  96%/51  | Total:  2h 50m | Avg:  3m 20s | Max:  8m 10s | Hits:  71%/2107  
  🟩 arm64              Pass: 100%/4   | Total: 12m 01s | Avg:  3m 00s | Max:  3m 09s | Hits:  62%/172   
🚨 cxx_family: MSVC 🚨
  🟩 Clang              Pass: 100%/30  | Total:  1h 42m | Avg:  3m 24s | Max:  4m 11s | Hits:  67%/1290  
  🟩 GCC                Pass: 100%/22  | Total:  1h 01m | Avg:  2m 48s | Max:  4m 04s | Hits:  76%/946   
  🟩 Intel              Pass: 100%/1   | Total:  3m 35s | Avg:  3m 35s | Max:  3m 35s | Hits:  46%/43    
  🔥 MSVC               Pass:   0%/2   | Total: 14m 57s | Avg:  7m 28s | Max:  8m 10s
🔍 jobs: Build 🔍
  🔍 Build              Pass:  95%/47  | Total:  2h 32m | Avg:  3m 14s | Max:  8m 10s | Hits:  66%/1935  
  🟩 Test               Pass: 100%/8   | Total: 30m 24s | Avg:  3m 48s | Max:  4m 11s | Hits:  97%/344   
🔍 std: 20 🔍
  🟩 17                 Pass: 100%/31  | Total:  1h 39m | Avg:  3m 12s | Max:  4m 11s | Hits:  69%/1333  
  🔍 20                 Pass:  91%/24  | Total:  1h 23m | Avg:  3m 28s | Max:  8m 10s | Hits:  72%/946   
🟨 cxx
  🟩 Clang9             Pass: 100%/2   | Total:  7m 49s | Avg:  3m 54s | Max:  4m 03s | Hits:  59%/86    
  🟩 Clang10            Pass: 100%/2   | Total:  6m 42s | Avg:  3m 21s | Max:  3m 35s | Hits:  55%/86    
  🟩 Clang11            Pass: 100%/4   | Total: 14m 05s | Avg:  3m 31s | Max:  4m 06s | Hits:  57%/172   
  🟩 Clang12            Pass: 100%/4   | Total: 15m 04s | Avg:  3m 46s | Max:  4m 09s | Hits:  57%/172   
  🟩 Clang13            Pass: 100%/4   | Total: 14m 07s | Avg:  3m 31s | Max:  3m 58s | Hits:  57%/172   
  🟩 Clang14            Pass: 100%/6   | Total: 20m 39s | Avg:  3m 26s | Max:  4m 04s | Hits:  86%/258   
  🟩 Clang15            Pass: 100%/2   | Total:  4m 39s | Avg:  2m 19s | Max:  2m 27s | Hits:  65%/86    
  🟩 Clang16            Pass: 100%/6   | Total: 19m 15s | Avg:  3m 12s | Max:  4m 11s | Hits:  76%/258   
  🟩 GCC9               Pass: 100%/2   | Total:  6m 43s | Avg:  3m 21s | Max:  3m 45s | Hits:  74%/86    
  🟩 GCC10              Pass: 100%/4   | Total: 12m 04s | Avg:  3m 01s | Max:  3m 39s | Hits:  74%/172   
  🟩 GCC11              Pass: 100%/4   | Total:  9m 04s | Avg:  2m 16s | Max:  2m 21s | Hits:  74%/172   
  🟩 GCC12              Pass: 100%/12  | Total: 34m 02s | Avg:  2m 50s | Max:  4m 04s | Hits:  79%/516   
  🟩 Intel2023.2.0      Pass: 100%/1   | Total:  3m 35s | Avg:  3m 35s | Max:  3m 35s | Hits:  46%/43    
  🟥 MSVC14.36          Pass:   0%/1   | Total:  6m 47s | Avg:  6m 47s | Max:  6m 47s
  🟥 MSVC14.39          Pass:   0%/1   | Total:  8m 10s | Avg:  8m 10s | Max:  8m 10s
🟨 cudacxx_family
  🟨 nvcc               Pass:  96%/55  | Total:  3h 02m | Avg:  3m 19s | Max:  8m 10s | Hits:  71%/2279  
🟨 gpu
  🟨 v100               Pass:  96%/55  | Total:  3h 02m | Avg:  3m 19s | Max:  8m 10s | Hits:  71%/2279  
🟨 ctk
  🟨 12.0               Pass:  95%/23  | Total:  1h 13m | Avg:  3m 12s | Max:  6m 47s | Hits:  79%/946   
  🟨 12.5               Pass:  96%/32  | Total:  1h 49m | Avg:  3m 24s | Max:  8m 10s | Hits:  65%/1333  
🟨 cudacxx
  🟨 nvcc12.0           Pass:  95%/23  | Total:  1h 13m | Avg:  3m 12s | Max:  6m 47s | Hits:  79%/946   
  🟨 nvcc12.5           Pass:  96%/32  | Total:  1h 49m | Avg:  3m 24s | Max:  8m 10s | Hits:  65%/1333  
🟩 sm
  🟩 90                 Pass: 100%/1   | Total:  1m 48s | Avg:  1m 48s | Max:  1m 48s | Hits:  88%/43    
  🟩 90a                Pass: 100%/1   | Total:  2m 11s | Avg:  2m 11s | Max:  2m 11s | Hits:  60%/43

🟩 pycuda: Pass: 100%/1 | Total: 10m 52s | Avg: 10m 52s | Max: 10m 52s

🟩 cpu
  🟩 amd64              Pass: 100%/1   | Total: 10m 52s | Avg: 10m 52s | Max: 10m 52s
🟩 ctk
  🟩 12.5               Pass: 100%/1   | Total: 10m 52s | Avg: 10m 52s | Max: 10m 52s
🟩 cudacxx
  🟩 nvcc12.5           Pass: 100%/1   | Total: 10m 52s | Avg: 10m 52s | Max: 10m 52s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/1   | Total: 10m 52s | Avg: 10m 52s | Max: 10m 52s
🟩 cxx
  🟩 GCC13              Pass: 100%/1   | Total: 10m 52s | Avg: 10m 52s | Max: 10m 52s
🟩 cxx_family
  🟩 GCC                Pass: 100%/1   | Total: 10m 52s | Avg: 10m 52s | Max: 10m 52s
🟩 gpu
  🟩 v100               Pass: 100%/1   | Total: 10m 52s | Avg: 10m 52s | Max: 10m 52s
🟩 jobs
  🟩 Test               Pass: 100%/1   | Total: 10m 52s | Avg: 10m 52s | Max: 10m 52s

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 56)

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

cudax/include/cuda/experimental/__device/all_devices.cuh

cudax/include/cuda/experimental/__device/device_vector.cuh

cudax/include/cuda/experimental/__device/all_devices.cuh

ericniebler · 2024-07-31T22:53:22Z

i have updated this pr to make cudax::devices be a range of device objects, instead of a range of device_refs.

github-actions · 2024-08-01T01:16:06Z

🟨 CI finished in 2h 23m: Pass: 98%/56 | Total: 2h 36m | Avg: 2m 48s | Max: 11m 55s | Hits: 90%/2586

🟨 cudax: Pass: 98%/55 | Total: 2h 24m | Avg: 2m 38s | Max: 9m 10s | Hits: 90%/2586

🔍 cpu: amd64 🔍
  🔍 amd64              Pass:  98%/51  | Total:  2h 15m | Avg:  2m 39s | Max:  9m 10s | Hits:  90%/2394  
  🟩 arm64              Pass: 100%/4   | Total:  8m 59s | Avg:  2m 14s | Max:  2m 39s | Hits:  89%/192   
🔍 ctk: 12.0 🔍
  🔍 12.0               Pass:  95%/23  | Total:  1h 00m | Avg:  2m 39s | Max:  7m 34s | Hits:  91%/1056  
  🟩 12.5               Pass: 100%/32  | Total:  1h 23m | Avg:  2m 37s | Max:  9m 10s | Hits:  90%/1530  
🔍 cudacxx: nvcc12.0 🔍
  🔍 nvcc12.0           Pass:  95%/23  | Total:  1h 00m | Avg:  2m 39s | Max:  7m 34s | Hits:  91%/1056  
  🟩 nvcc12.5           Pass: 100%/32  | Total:  1h 23m | Avg:  2m 37s | Max:  9m 10s | Hits:  90%/1530  
🚨 cxx: MSVC14.36 🚨
  🟩 Clang9             Pass: 100%/2   | Total:  4m 14s | Avg:  2m 07s | Max:  2m 11s | Hits:  91%/96    
  🟩 Clang10            Pass: 100%/2   | Total:  4m 19s | Avg:  2m 09s | Max:  2m 13s | Hits:  91%/96    
  🟩 Clang11            Pass: 100%/4   | Total:  8m 18s | Avg:  2m 04s | Max:  2m 09s | Hits:  91%/192   
  🟩 Clang12            Pass: 100%/4   | Total:  8m 47s | Avg:  2m 11s | Max:  2m 17s | Hits:  91%/192   
  🟩 Clang13            Pass: 100%/4   | Total:  8m 42s | Avg:  2m 10s | Max:  2m 18s | Hits:  91%/192   
  🟩 Clang14            Pass: 100%/6   | Total: 17m 46s | Avg:  2m 57s | Max:  4m 46s | Hits:  94%/288   
  🟩 Clang15            Pass: 100%/2   | Total:  4m 40s | Avg:  2m 20s | Max:  2m 22s | Hits:  91%/96    
  🟩 Clang16            Pass: 100%/6   | Total: 16m 59s | Avg:  2m 49s | Max:  4m 23s | Hits:  94%/288   
  🟩 GCC9               Pass: 100%/2   | Total:  3m 49s | Avg:  1m 54s | Max:  1m 58s | Hits:  87%/96    
  🟩 GCC10              Pass: 100%/4   | Total:  7m 38s | Avg:  1m 54s | Max:  2m 06s | Hits:  87%/192   
  🟩 GCC11              Pass: 100%/4   | Total:  8m 09s | Avg:  2m 02s | Max:  2m 09s | Hits:  86%/192   
  🟩 GCC12              Pass: 100%/12  | Total: 32m 01s | Avg:  2m 40s | Max:  4m 02s | Hits:  90%/576   
  🟩 Intel2023.2.0      Pass: 100%/1   | Total:  2m 52s | Avg:  2m 52s | Max:  2m 52s | Hits:  91%/48    
  🔥 MSVC14.36          Pass:   0%/1   | Total:  7m 34s | Avg:  7m 34s | Max:  7m 34s
  🟩 MSVC14.39          Pass: 100%/1   | Total:  9m 10s | Avg:  9m 10s | Max:  9m 10s | Hits:  71%/42    
🔍 cxx_family: MSVC 🔍
  🟩 Clang              Pass: 100%/30  | Total:  1h 13m | Avg:  2m 27s | Max:  4m 46s | Hits:  92%/1440  
  🟩 GCC                Pass: 100%/22  | Total: 51m 37s | Avg:  2m 20s | Max:  4m 02s | Hits:  88%/1056  
  🟩 Intel              Pass: 100%/1   | Total:  2m 52s | Avg:  2m 52s | Max:  2m 52s | Hits:  91%/48    
  🔍 MSVC               Pass:  50%/2   | Total: 16m 44s | Avg:  8m 22s | Max:  9m 10s | Hits:  71%/42    
🔍 jobs: Build 🔍
  🔍 Build              Pass:  97%/47  | Total:  1h 52m | Avg:  2m 24s | Max:  9m 10s | Hits:  89%/2202  
  🟩 Test               Pass: 100%/8   | Total: 32m 00s | Avg:  4m 00s | Max:  4m 46s | Hits:  97%/384   
🔍 std: 20 🔍
  🟩 17                 Pass: 100%/31  | Total:  1h 13m | Avg:  2m 21s | Max:  4m 16s | Hits:  90%/1488  
  🔍 20                 Pass:  95%/24  | Total:  1h 11m | Avg:  2m 59s | Max:  9m 10s | Hits:  90%/1098  
🟨 cudacxx_family
  🟨 nvcc               Pass:  98%/55  | Total:  2h 24m | Avg:  2m 38s | Max:  9m 10s | Hits:  90%/2586  
🟨 gpu
  🟨 v100               Pass:  98%/55  | Total:  2h 24m | Avg:  2m 38s | Max:  9m 10s | Hits:  90%/2586  
🟩 sm
  🟩 90                 Pass: 100%/1   | Total:  1m 55s | Avg:  1m 55s | Max:  1m 55s | Hits:  87%/48    
  🟩 90a                Pass: 100%/1   | Total:  2m 09s | Avg:  2m 09s | Max:  2m 09s | Hits:  87%/48

🟩 pycuda: Pass: 100%/1 | Total: 11m 55s | Avg: 11m 55s | Max: 11m 55s

🟩 cpu
  🟩 amd64              Pass: 100%/1   | Total: 11m 55s | Avg: 11m 55s | Max: 11m 55s
🟩 ctk
  🟩 12.5               Pass: 100%/1   | Total: 11m 55s | Avg: 11m 55s | Max: 11m 55s
🟩 cudacxx
  🟩 nvcc12.5           Pass: 100%/1   | Total: 11m 55s | Avg: 11m 55s | Max: 11m 55s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/1   | Total: 11m 55s | Avg: 11m 55s | Max: 11m 55s
🟩 cxx
  🟩 GCC13              Pass: 100%/1   | Total: 11m 55s | Avg: 11m 55s | Max: 11m 55s
🟩 cxx_family
  🟩 GCC                Pass: 100%/1   | Total: 11m 55s | Avg: 11m 55s | Max: 11m 55s
🟩 gpu
  🟩 v100               Pass: 100%/1   | Total: 11m 55s | Avg: 11m 55s | Max: 11m 55s
🟩 jobs
  🟩 Test               Pass: 100%/1   | Total: 11m 55s | Avg: 11m 55s | Max: 11m 55s

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 56)

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

…ion of `std::construct_at`

jrhemstad · 2024-08-02T21:47:22Z

cudax/test/device/device_smoke.cu

+    CUDAX_REQUIRE(0 == cudax::devices.end()[-1].get());
+  }
+
+  try


catch2 has some native machinery for verifying an expression throws a specific exception: https://github.com/catchorg/Catch2/blob/devel/docs/assertions.md#exceptions

github-actions · 2024-08-03T00:53:10Z

🟩 CI finished in 3h 49m: Pass: 100%/56 | Total: 2h 35m | Avg: 2m 46s | Max: 11m 11s | Hits: 91%/2738

🟩 cudax: Pass: 100%/55 | Total: 2h 23m | Avg: 2m 36s | Max: 8m 10s | Hits: 91%/2738

🟩 cpu
  🟩 amd64              Pass: 100%/51  | Total:  2h 14m | Avg:  2m 38s | Max:  8m 10s | Hits:  91%/2538  
  🟩 arm64              Pass: 100%/4   | Total:  9m 26s | Avg:  2m 21s | Max:  2m 29s | Hits:  92%/200   
🟩 ctk
  🟩 12.0               Pass: 100%/23  | Total:  1h 00m | Avg:  2m 36s | Max:  8m 10s | Hits:  90%/1144  
  🟩 12.5               Pass: 100%/32  | Total:  1h 23m | Avg:  2m 37s | Max:  7m 20s | Hits:  91%/1594  
🟩 cudacxx
  🟩 nvcc12.0           Pass: 100%/23  | Total:  1h 00m | Avg:  2m 36s | Max:  8m 10s | Hits:  90%/1144  
  🟩 nvcc12.5           Pass: 100%/32  | Total:  1h 23m | Avg:  2m 37s | Max:  7m 20s | Hits:  91%/1594  
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/55  | Total:  2h 23m | Avg:  2m 36s | Max:  8m 10s | Hits:  91%/2738  
🟩 cxx
  🟩 Clang9             Pass: 100%/2   | Total:  4m 12s | Avg:  2m 06s | Max:  2m 10s | Hits:  92%/100   
  🟩 Clang10            Pass: 100%/2   | Total:  4m 20s | Avg:  2m 10s | Max:  2m 17s | Hits:  92%/100   
  🟩 Clang11            Pass: 100%/4   | Total:  8m 27s | Avg:  2m 06s | Max:  2m 12s | Hits:  92%/200   
  🟩 Clang12            Pass: 100%/4   | Total:  8m 29s | Avg:  2m 07s | Max:  2m 14s | Hits:  92%/200   
  🟩 Clang13            Pass: 100%/4   | Total:  8m 32s | Avg:  2m 08s | Max:  2m 18s | Hits:  92%/200   
  🟩 Clang14            Pass: 100%/6   | Total: 16m 25s | Avg:  2m 44s | Max:  4m 15s | Hits:  94%/300   
  🟩 Clang15            Pass: 100%/2   | Total:  4m 21s | Avg:  2m 10s | Max:  2m 14s | Hits:  92%/100   
  🟩 Clang16            Pass: 100%/6   | Total: 18m 53s | Avg:  3m 08s | Max:  5m 16s | Hits:  95%/300   
  🟩 GCC9               Pass: 100%/2   | Total:  4m 13s | Avg:  2m 06s | Max:  2m 07s | Hits:  87%/100   
  🟩 GCC10              Pass: 100%/4   | Total:  7m 52s | Avg:  1m 58s | Max:  2m 16s | Hits:  88%/200   
  🟩 GCC11              Pass: 100%/4   | Total:  8m 17s | Avg:  2m 04s | Max:  2m 15s | Hits:  88%/200   
  🟩 GCC12              Pass: 100%/12  | Total: 31m 37s | Avg:  2m 38s | Max:  3m 39s | Hits:  91%/600   
  🟩 Intel2023.2.0      Pass: 100%/1   | Total:  2m 45s | Avg:  2m 45s | Max:  2m 45s | Hits:  92%/50    
  🟩 MSVC14.36          Pass: 100%/1   | Total:  8m 10s | Avg:  8m 10s | Max:  8m 10s | Hits:  75%/44    
  🟩 MSVC14.39          Pass: 100%/1   | Total:  7m 20s | Avg:  7m 20s | Max:  7m 20s | Hits:  75%/44    
🟩 cxx_family
  🟩 Clang              Pass: 100%/30  | Total:  1h 13m | Avg:  2m 27s | Max:  5m 16s | Hits:  93%/1500  
  🟩 GCC                Pass: 100%/22  | Total: 51m 59s | Avg:  2m 21s | Max:  3m 39s | Hits:  89%/1100  
  🟩 Intel              Pass: 100%/1   | Total:  2m 45s | Avg:  2m 45s | Max:  2m 45s | Hits:  92%/50    
  🟩 MSVC               Pass: 100%/2   | Total: 15m 30s | Avg:  7m 45s | Max:  8m 10s | Hits:  75%/88    
🟩 gpu
  🟩 v100               Pass: 100%/55  | Total:  2h 23m | Avg:  2m 36s | Max:  8m 10s | Hits:  91%/2738  
🟩 jobs
  🟩 Build              Pass: 100%/47  | Total:  1h 52m | Avg:  2m 23s | Max:  8m 10s | Hits:  89%/2338  
  🟩 Test               Pass: 100%/8   | Total: 31m 46s | Avg:  3m 58s | Max:  5m 16s | Hits:  98%/400   
🟩 sm
  🟩 90                 Pass: 100%/1   | Total:  1m 51s | Avg:  1m 51s | Max:  1m 51s | Hits:  88%/50    
  🟩 90a                Pass: 100%/1   | Total:  2m 03s | Avg:  2m 03s | Max:  2m 03s | Hits:  88%/50    
🟩 std
  🟩 17                 Pass: 100%/31  | Total:  1h 13m | Avg:  2m 22s | Max:  5m 16s | Hits:  91%/1550  
  🟩 20                 Pass: 100%/24  | Total:  1h 10m | Avg:  2m 55s | Max:  8m 10s | Hits:  90%/1188

🟩 pycuda: Pass: 100%/1 | Total: 11m 11s | Avg: 11m 11s | Max: 11m 11s

🟩 cpu
  🟩 amd64              Pass: 100%/1   | Total: 11m 11s | Avg: 11m 11s | Max: 11m 11s
🟩 ctk
  🟩 12.5               Pass: 100%/1   | Total: 11m 11s | Avg: 11m 11s | Max: 11m 11s
🟩 cudacxx
  🟩 nvcc12.5           Pass: 100%/1   | Total: 11m 11s | Avg: 11m 11s | Max: 11m 11s
🟩 cudacxx_family
  🟩 nvcc               Pass: 100%/1   | Total: 11m 11s | Avg: 11m 11s | Max: 11m 11s
🟩 cxx
  🟩 GCC13              Pass: 100%/1   | Total: 11m 11s | Avg: 11m 11s | Max: 11m 11s
🟩 cxx_family
  🟩 GCC                Pass: 100%/1   | Total: 11m 11s | Avg: 11m 11s | Max: 11m 11s
🟩 gpu
  🟩 v100               Pass: 100%/1   | Total: 11m 11s | Avg: 11m 11s | Max: 11m 11s
🟩 jobs
  🟩 Test               Pass: 100%/1   | Total: 11m 11s | Avg: 11m 11s | Max: 11m 11s

👃 Inspect Changes

Modifications in project?

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

Modifications in project or dependencies?

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

🏃‍ Runner counts (total jobs: 56)

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

… in the system (NVIDIA#2100) * add `cuda::devices` vector the number of cuda devices can be determined by calling `cuda::devices.size()`. `cuda::devices` is a range of `cuda::device` objects.

ericniebler requested review from a team as code owners July 29, 2024 22:04

ericniebler requested review from alliepiper and griwes July 29, 2024 22:04

ericniebler changed the title ~~Cudax global devices range~~ [CUDAX] Add a global constexpr cudax::devices range for all devices in the system Jul 29, 2024

pciolkosz reviewed Jul 30, 2024

View reviewed changes

cudax/include/cuda/experimental/__device/device_vector.cuh Outdated Show resolved Hide resolved

pciolkosz reviewed Jul 30, 2024

View reviewed changes

cudax/include/cuda/experimental/__device/device_vector.cuh Outdated Show resolved Hide resolved

miscco requested changes Jul 30, 2024

View reviewed changes

add cuda::devices vector

ac07613

the number of cuda devices can be determined by calling `cuda::devices.size()`. `cuda::devices` is a range of `cuda::device` objects.

ericniebler force-pushed the cudax-global-devices-range branch from c9cac6e to ac07613 Compare July 30, 2024 19:25

ericniebler requested a review from miscco July 30, 2024 19:25

ericniebler mentioned this pull request Jul 30, 2024

[CUDAX] rename device to device_ref, add immovable device as a place to cache properties #2110

Merged

pciolkosz approved these changes Jul 30, 2024

View reviewed changes

miscco reviewed Jul 31, 2024

View reviewed changes

cudax/include/cuda/experimental/__device/all_devices.cuh Outdated Show resolved Hide resolved

miscco reviewed Jul 31, 2024

View reviewed changes

cudax/include/cuda/experimental/__device/all_devices.cuh Show resolved Hide resolved

miscco reviewed Jul 31, 2024

View reviewed changes

cudax/include/cuda/experimental/__device/all_devices.cuh Show resolved Hide resolved

miscco reviewed Jul 31, 2024

View reviewed changes

cudax/include/cuda/experimental/__device/all_devices.cuh Outdated Show resolved Hide resolved

bernhardmgruber reviewed Jul 31, 2024

View reviewed changes

ericniebler added 2 commits July 31, 2024 15:29

review feedback

fcb65c5

merge from origin/main

ee6ee91

ericniebler requested a review from miscco July 31, 2024 23:42

miscco approved these changes Aug 2, 2024

View reviewed changes

ericniebler added 2 commits August 2, 2024 18:37

Merge branch 'main' into cudax-global-devices-range

4e3f743

work around a work around for the EDG front end in MSVC's implementat…

5fbe8e2

…ion of `std::construct_at`

ericniebler requested a review from a team as a code owner August 2, 2024 20:46

add cudax::devices.at(n) that throws on out-of-range

785dda8

ericniebler enabled auto-merge (squash) August 2, 2024 21:26

jrhemstad reviewed Aug 2, 2024

View reviewed changes

ericniebler merged commit a8ca75c into NVIDIA:main Aug 3, 2024

Conversation

ericniebler commented Jul 29, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Checklist

Uh oh!

copy-pr-bot bot commented Jul 29, 2024

Uh oh!

ericniebler commented Jul 29, 2024

Uh oh!

ericniebler commented Jul 29, 2024

Uh oh!

Uh oh!

Uh oh!

ericniebler commented Jul 30, 2024

Uh oh!

github-actions bot commented Jul 30, 2024

🟩 cudax: Pass: 100%/55 | Total: 2h 22m | Avg: 2m 35s | Max: 7m 57s | Hits: 90%/2188

🟩 pycuda: Pass: 100%/1 | Total: 11m 45s | Avg: 11m 45s | Max: 11m 45s

👃 Inspect Changes

Modifications in project?

Modifications in project or dependencies?

🏃‍ Runner counts (total jobs: 56)

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

github-actions bot commented Jul 31, 2024

🟨 cudax: Pass: 96%/55 | Total: 3h 02m | Avg: 3m 19s | Max: 8m 10s | Hits: 71%/2279

🟩 pycuda: Pass: 100%/1 | Total: 10m 52s | Avg: 10m 52s | Max: 10m 52s

👃 Inspect Changes

Modifications in project?

Modifications in project or dependencies?

🏃‍ Runner counts (total jobs: 56)

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

ericniebler commented Jul 31, 2024

Uh oh!

github-actions bot commented Aug 1, 2024

🟨 cudax: Pass: 98%/55 | Total: 2h 24m | Avg: 2m 38s | Max: 9m 10s | Hits: 90%/2586

🟩 pycuda: Pass: 100%/1 | Total: 11m 55s | Avg: 11m 55s | Max: 11m 55s

👃 Inspect Changes

Modifications in project?

Modifications in project or dependencies?

🏃‍ Runner counts (total jobs: 56)

Uh oh!

jrhemstad Aug 2, 2024

Choose a reason for hiding this comment

Uh oh!

github-actions bot commented Aug 3, 2024

🟩 cudax: Pass: 100%/55 | Total: 2h 23m | Avg: 2m 36s | Max: 8m 10s | Hits: 91%/2738

🟩 pycuda: Pass: 100%/1 | Total: 11m 11s | Avg: 11m 11s | Max: 11m 11s

👃 Inspect Changes

Modifications in project?

Modifications in project or dependencies?

🏃‍ Runner counts (total jobs: 56)

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

ericniebler commented Jul 29, 2024 •

edited

Loading