Make `thrust::transform` use `cub::DeviceTransform`
This PR makes thrust::transform use cub::DeviceTransform for the CUDA backend.
It also:
- Introduces address stability detection and opt-in in libcu++
- Mark lambdas in Thrust BabelStream benchmark address oblivious
Benchmark on H100
['./thrust_transform_before.json', './thrust_transform_after.json']
# base
## [0] NVIDIA H100 PCIe
| T{ct} | Elements | Ref Time | Ref Noise | Cmp Time | Cmp Noise | Diff | %Diff | Status |
|---------|------------|------------|-------------|------------|-------------|------------|---------|----------|
| U32 | 2^16 | 12.429 us | 3.11% | 12.601 us | 5.13% | 0.172 us | 1.38% | PASS |
| U32 | 2^20 | 19.045 us | 1.54% | 19.002 us | 2.01% | -0.044 us | -0.23% | PASS |
| U32 | 2^24 | 117.923 us | 0.36% | 115.669 us | 0.43% | -2.254 us | -1.91% | FAIL |
| U32 | 2^28 | 1.681 ms | 0.20% | 1.635 ms | 0.28% | -46.367 us | -2.76% | FAIL |
| U64 | 2^16 | 13.325 us | 2.58% | 13.367 us | 2.27% | 0.042 us | 0.32% | PASS |
| U64 | 2^20 | 22.654 us | 2.34% | 22.810 us | 2.54% | 0.156 us | 0.69% | PASS |
| U64 | 2^24 | 165.099 us | 0.53% | 164.943 us | 0.54% | -0.156 us | -0.09% | PASS |
| U64 | 2^28 | 2.411 ms | 0.05% | 2.407 ms | 0.05% | -4.272 us | -0.18% | FAIL |
# mul
## [0] NVIDIA H100 PCIe
| T{ct} | Elements | Ref Time | Ref Noise | Cmp Time | Cmp Noise | Diff | %Diff | Status |
|---------|------------|------------|-------------|------------|-------------|------------|---------|----------|
| I8 | 2^25 | 108.473 us | 2.08% | 53.215 us | 7.41% | -55.258 us | -50.94% | FAIL |
| I16 | 2^25 | 115.478 us | 0.25% | 86.300 us | 0.72% | -29.178 us | -25.27% | FAIL |
| F32 | 2^25 | 175.384 us | 0.60% | 160.209 us | 0.44% | -15.175 us | -8.65% | FAIL |
| F64 | 2^25 | 305.885 us | 0.23% | 305.570 us | 0.30% | -0.314 us | -0.10% | PASS |
| I128 | 2^25 | 598.162 us | 0.17% | 596.926 us | 0.18% | -1.236 us | -0.21% | FAIL |
# add
## [0] NVIDIA H100 PCIe
| T{ct} | Elements | Ref Time | Ref Noise | Cmp Time | Cmp Noise | Diff | %Diff | Status |
|---------|------------|------------|-------------|------------|-------------|------------|---------|----------|
| I8 | 2^25 | 119.351 us | 1.41% | 69.760 us | 4.02% | -49.592 us | -41.55% | FAIL |
| I16 | 2^25 | 146.894 us | 0.43% | 123.949 us | 0.59% | -22.945 us | -15.62% | FAIL |
| F32 | 2^25 | 240.612 us | 0.40% | 228.431 us | 0.28% | -12.182 us | -5.06% | FAIL |
| F64 | 2^25 | 439.293 us | 0.24% | 438.821 us | 2.89% | -0.471 us | -0.11% | PASS |
| I128 | 2^25 | 864.237 us | 0.11% | 860.939 us | 0.14% | -3.298 us | -0.38% | FAIL |
# triad
## [0] NVIDIA H100 PCIe
| T{ct} | Elements | Ref Time | Ref Noise | Cmp Time | Cmp Noise | Diff | %Diff | Status |
|---------|------------|------------|-------------|------------|-------------|------------|---------|----------|
| I8 | 2^25 | 118.921 us | 2.13% | 69.948 us | 5.03% | -48.973 us | -41.18% | FAIL |
| I16 | 2^25 | 146.686 us | 0.21% | 123.407 us | 0.68% | -23.279 us | -15.87% | FAIL |
| F32 | 2^25 | 241.016 us | 0.39% | 228.227 us | 0.26% | -12.789 us | -5.31% | FAIL |
| F64 | 2^25 | 439.391 us | 0.21% | 438.366 us | 0.28% | -1.025 us | -0.23% | FAIL |
| I128 | 2^25 | 864.521 us | 0.10% | 860.948 us | 0.14% | -3.574 us | -0.41% | FAIL |
# nstream
## [0] NVIDIA H100 PCIe
| T{ct} | Elements | Ref Time | Ref Noise | Cmp Time | Cmp Noise | Diff | %Diff | Status |
|---------|------------|------------|-------------|------------|-------------|------------|---------|----------|
| I8 | 2^25 | 130.695 us | 2.81% | 87.441 us | 4.90% | -43.255 us | -33.10% | FAIL |
| I16 | 2^25 | 182.814 us | 0.22% | 160.842 us | 0.39% | -21.973 us | -12.02% | FAIL |
| F32 | 2^25 | 307.743 us | 0.33% | 302.920 us | 0.23% | -4.823 us | -1.57% | FAIL |
| F64 | 2^25 | 580.479 us | 0.11% | 587.621 us | 0.14% | 7.142 us | 1.23% | FAIL |
| I128 | 2^25 | 1.136 ms | 0.06% | 1.135 ms | 0.06% | -0.621 us | -0.05% | PASS |
# nstream_stable
## [0] NVIDIA H100 PCIe
| T{ct} | Elements | Ref Time | Ref Noise | Cmp Time | Cmp Noise | Diff | %Diff | Status |
|---------|------------|------------|-------------|------------|-------------|-----------|---------|----------|
| I8 | 2^25 | 131.076 us | 2.62% | 129.962 us | 2.75% | -1.114 us | -0.85% | PASS |
| I16 | 2^25 | 182.595 us | 0.16% | 182.699 us | 0.18% | 0.104 us | 0.06% | PASS |
| F32 | 2^25 | 307.445 us | 0.31% | 307.618 us | 0.30% | 0.174 us | 0.06% | PASS |
| F64 | 2^25 | 580.358 us | 0.16% | 580.528 us | 0.14% | 0.169 us | 0.03% | PASS |
| I128 | 2^25 | 1.135 ms | 0.05% | 1.135 ms | 0.05% | 0.143 us | 0.01% | PASS |
Resolve before:
- [x] #2086
- [ ] #2402
We discussed this PR in the code review hour now and concluded that we are fine with putting the address stability traits into libcu++ and the cuda:: namespace. The functionality is sufficient and we are fine with the naming. The tests can remain in thrust, since we will add more tests in conjunction with thrust callables and thrust types in the future. This mostly relates to automatic detection of whether transformation function arguments can be copied or not.
🟨 CI finished in 7h 41m: Pass: 99%/417 | Total: 7d 07h | Avg: 25m 11s | Max: 2h 03m | Hits: 82%/39381
-
🟨 thrust: Pass: 99%/118 | Total: 2d 11h | Avg: 30m 22s | Max: 1h 12m | Hits: 78%/17872
🔍 cpu: amd64 🔍 🔍 amd64 Pass: 99%/110 | Total: 2d 07h | Avg: 30m 16s | Max: 1h 12m | Hits: 78%/17872 🟩 arm64 Pass: 100%/8 | Total: 4h 14m | Avg: 31m 51s | Max: 40m 45s 🔍 ctk: 11.1 🔍 🔍 11.1 Pass: 93%/15 | Total: 7h 16m | Avg: 29m 05s | Max: 1h 06m 🟩 11.8 Pass: 100%/3 | Total: 2h 01m | Avg: 40m 26s | Max: 47m 25s 🟩 12.5 Pass: 100%/100 | Total: 2d 02h | Avg: 30m 16s | Max: 1h 12m | Hits: 78%/17872 🔍 cudacxx: nvcc11.1 🔍 🟩 ClangCUDA17 Pass: 100%/2 | Total: 57m 22s | Avg: 28m 41s | Max: 29m 18s 🔍 nvcc11.1 Pass: 93%/15 | Total: 7h 16m | Avg: 29m 05s | Max: 1h 06m 🟩 nvcc11.8 Pass: 100%/3 | Total: 2h 01m | Avg: 40m 26s | Max: 47m 25s 🟩 nvcc12.5 Pass: 100%/98 | Total: 2d 01h | Avg: 30m 18s | Max: 1h 12m | Hits: 78%/17872 🔍 cudacxx_family: nvcc 🔍 🟩 ClangCUDA Pass: 100%/2 | Total: 57m 22s | Avg: 28m 41s | Max: 29m 18s 🔍 nvcc Pass: 99%/116 | Total: 2d 10h | Avg: 30m 24s | Max: 1h 12m | Hits: 78%/17872 🚨 cxx: MSVC14.16 🚨 🟩 Clang9 Pass: 100%/6 | Total: 2h 49m | Avg: 28m 10s | Max: 33m 07s 🟩 Clang10 Pass: 100%/3 | Total: 1h 41m | Avg: 33m 47s | Max: 39m 02s 🟩 Clang11 Pass: 100%/4 | Total: 2h 03m | Avg: 30m 54s | Max: 32m 47s 🟩 Clang12 Pass: 100%/4 | Total: 2h 08m | Avg: 32m 05s | Max: 36m 31s 🟩 Clang13 Pass: 100%/4 | Total: 2h 03m | Avg: 30m 58s | Max: 36m 25s 🟩 Clang14 Pass: 100%/4 | Total: 2h 06m | Avg: 31m 43s | Max: 35m 23s 🟩 Clang15 Pass: 100%/4 | Total: 2h 04m | Avg: 31m 09s | Max: 33m 01s 🟩 Clang16 Pass: 100%/4 | Total: 2h 05m | Avg: 31m 28s | Max: 36m 11s 🟩 Clang17 Pass: 100%/18 | Total: 6h 42m | Avg: 22m 20s | Max: 32m 47s 🟩 GCC6 Pass: 100%/2 | Total: 49m 01s | Avg: 24m 30s | Max: 26m 40s 🟩 GCC7 Pass: 100%/6 | Total: 2h 55m | Avg: 29m 11s | Max: 34m 21s 🟩 GCC8 Pass: 100%/6 | Total: 2h 56m | Avg: 29m 21s | Max: 32m 55s 🟩 GCC9 Pass: 100%/6 | Total: 3h 02m | Avg: 30m 23s | Max: 38m 38s 🟩 GCC10 Pass: 100%/4 | Total: 2h 17m | Avg: 34m 24s | Max: 40m 29s 🟩 GCC11 Pass: 100%/7 | Total: 4h 15m | Avg: 36m 26s | Max: 47m 25s 🟩 GCC12 Pass: 100%/4 | Total: 2h 20m | Avg: 35m 12s | Max: 39m 41s 🟩 GCC13 Pass: 100%/20 | Total: 7h 46m | Avg: 23m 18s | Max: 40m 45s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 1h 57m | Avg: 39m 03s | Max: 43m 24s 🔥 MSVC14.16 Pass: 0%/1 | Total: 1h 06m | Avg: 1h 06m | Max: 1h 06m 🟩 MSVC14.29 Pass: 100%/2 | Total: 2h 08m | Avg: 1h 04m | Max: 1h 06m | Hits: 66%/4468 🟩 MSVC14.39 Pass: 100%/6 | Total: 4h 24m | Avg: 44m 03s | Max: 1h 12m | Hits: 82%/13404 🔍 cxx_family: MSVC 🔍 🟩 Clang Pass: 100%/51 | Total: 23h 45m | Avg: 27m 57s | Max: 39m 02s 🟩 GCC Pass: 100%/55 | Total: 1d 02h | Avg: 28m 45s | Max: 47m 25s 🟩 Intel Pass: 100%/3 | Total: 1h 57m | Avg: 39m 03s | Max: 43m 24s 🔍 MSVC Pass: 88%/9 | Total: 7h 39m | Avg: 51m 05s | Max: 1h 12m | Hits: 78%/17872 🔍 jobs: Build 🔍 🔍 Build Pass: 98%/99 | Total: 2d 07h | Avg: 33m 26s | Max: 1h 12m | Hits: 66%/11170 🟩 TestCPU Pass: 100%/11 | Total: 2h 08m | Avg: 11m 40s | Max: 23m 09s | Hits: 99%/6702 🟩 TestGPU Pass: 100%/8 | Total: 2h 26m | Avg: 18m 16s | Max: 35m 45s 🔍 std: 14 🔍 🟩 11 Pass: 100%/30 | Total: 12h 36m | Avg: 25m 12s | Max: 35m 45s 🔍 14 Pass: 97%/34 | Total: 18h 11m | Avg: 32m 06s | Max: 1h 06m | Hits: 77%/6702 🟩 17 Pass: 100%/33 | Total: 17h 58m | Avg: 32m 41s | Max: 1h 06m | Hits: 77%/6702 🟩 20 Pass: 100%/21 | Total: 10h 58m | Avg: 31m 21s | Max: 1h 12m | Hits: 82%/4468 🟨 gpu 🟨 v100 Pass: 99%/118 | Total: 2d 11h | Avg: 30m 22s | Max: 1h 12m | Hits: 78%/17872 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 2h 01m | Avg: 40m 26s | Max: 47m 25s 🟩 90a Pass: 100%/4 | Total: 1h 18m | Avg: 19m 34s | Max: 24m 44s -
🟩 cub: Pass: 100%/132 | Total: 4d 00h | Avg: 44m 01s | Max: 2h 03m | Hits: 62%/4362
🟩 cpu 🟩 amd64 Pass: 100%/124 | Total: 3d 17h | Avg: 43m 22s | Max: 2h 03m | Hits: 62%/4362 🟩 arm64 Pass: 100%/8 | Total: 7h 11m | Avg: 53m 54s | Max: 55m 47s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 11h 24m | Avg: 45m 39s | Max: 57m 01s | Hits: 56%/727 🟩 11.8 Pass: 100%/3 | Total: 3h 19m | Avg: 1h 06m | Max: 1h 08m 🟩 12.5 Pass: 100%/114 | Total: 3d 10h | Avg: 43m 12s | Max: 2h 03m | Hits: 63%/3635 🟩 cudacxx 🟩 ClangCUDA17 Pass: 100%/2 | Total: 46m 54s | Avg: 23m 27s | Max: 24m 53s 🟩 nvcc11.1 Pass: 100%/15 | Total: 11h 24m | Avg: 45m 39s | Max: 57m 01s | Hits: 56%/727 🟩 nvcc11.8 Pass: 100%/3 | Total: 3h 19m | Avg: 1h 06m | Max: 1h 08m 🟩 nvcc12.5 Pass: 100%/112 | Total: 3d 09h | Avg: 43m 33s | Max: 2h 03m | Hits: 63%/3635 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/2 | Total: 46m 54s | Avg: 23m 27s | Max: 24m 53s 🟩 nvcc Pass: 100%/130 | Total: 4d 00h | Avg: 44m 20s | Max: 2h 03m | Hits: 62%/4362 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 4h 55m | Avg: 49m 10s | Max: 58m 56s 🟩 Clang10 Pass: 100%/3 | Total: 2h 30m | Avg: 50m 10s | Max: 51m 06s 🟩 Clang11 Pass: 100%/4 | Total: 3h 31m | Avg: 52m 50s | Max: 54m 43s 🟩 Clang12 Pass: 100%/4 | Total: 3h 31m | Avg: 52m 47s | Max: 55m 44s 🟩 Clang13 Pass: 100%/4 | Total: 3h 29m | Avg: 52m 22s | Max: 56m 10s 🟩 Clang14 Pass: 100%/4 | Total: 3h 33m | Avg: 53m 25s | Max: 55m 46s 🟩 Clang15 Pass: 100%/4 | Total: 3h 27m | Avg: 51m 53s | Max: 55m 29s 🟩 Clang16 Pass: 100%/4 | Total: 3h 40m | Avg: 55m 13s | Max: 58m 31s 🟩 Clang17 Pass: 100%/26 | Total: 12h 43m | Avg: 29m 22s | Max: 53m 00s 🟩 GCC6 Pass: 100%/2 | Total: 1h 31m | Avg: 45m 47s | Max: 48m 30s 🟩 GCC7 Pass: 100%/6 | Total: 4h 52m | Avg: 48m 44s | Max: 56m 47s 🟩 GCC8 Pass: 100%/6 | Total: 4h 46m | Avg: 47m 43s | Max: 50m 43s 🟩 GCC9 Pass: 100%/6 | Total: 4h 49m | Avg: 48m 14s | Max: 54m 59s 🟩 GCC10 Pass: 100%/4 | Total: 3h 37m | Avg: 54m 28s | Max: 57m 47s 🟩 GCC11 Pass: 100%/7 | Total: 6h 53m | Avg: 59m 05s | Max: 1h 08m 🟩 GCC12 Pass: 100%/4 | Total: 3h 33m | Avg: 53m 28s | Max: 57m 11s 🟩 GCC13 Pass: 100%/29 | Total: 16h 05m | Avg: 33m 16s | Max: 2h 03m 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 57m | Avg: 59m 02s | Max: 59m 50s 🟩 MSVC14.16 Pass: 100%/1 | Total: 57m 01s | Avg: 57m 01s | Max: 57m 01s | Hits: 56%/727 🟩 MSVC14.29 Pass: 100%/2 | Total: 2h 14m | Avg: 1h 07m | Max: 1h 08m | Hits: 63%/1454 🟩 MSVC14.39 Pass: 100%/3 | Total: 3h 08m | Avg: 1h 02m | Max: 1h 06m | Hits: 63%/2181 🟩 cxx_family 🟩 Clang Pass: 100%/59 | Total: 1d 17h | Avg: 42m 05s | Max: 58m 56s 🟩 GCC Pass: 100%/64 | Total: 1d 22h | Avg: 43m 17s | Max: 2h 03m 🟩 Intel Pass: 100%/3 | Total: 2h 57m | Avg: 59m 02s | Max: 59m 50s 🟩 MSVC Pass: 100%/6 | Total: 6h 19m | Avg: 1h 03m | Max: 1h 08m | Hits: 62%/4362 🟩 gpu 🟩 v100 Pass: 100%/132 | Total: 4d 00h | Avg: 44m 01s | Max: 2h 03m | Hits: 62%/4362 🟩 jobs 🟩 Build Pass: 100%/99 | Total: 3d 12h | Avg: 51m 13s | Max: 1h 08m | Hits: 62%/4362 🟩 DeviceLaunch Pass: 100%/8 | Total: 2h 41m | Avg: 20m 07s | Max: 28m 59s 🟩 GraphCapture Pass: 100%/8 | Total: 2h 01m | Avg: 15m 10s | Max: 16m 50s 🟩 HostLaunch Pass: 100%/8 | Total: 2h 18m | Avg: 17m 19s | Max: 20m 19s 🟩 SmallGMem Pass: 100%/1 | Total: 2h 03m | Avg: 2h 03m | Max: 2h 03m 🟩 TestGPU Pass: 100%/8 | Total: 3h 15m | Avg: 24m 25s | Max: 27m 32s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 3h 19m | Avg: 1h 06m | Max: 1h 08m 🟩 90a Pass: 100%/4 | Total: 1h 35m | Avg: 23m 58s | Max: 27m 37s 🟩 std 🟩 11 Pass: 100%/34 | Total: 23h 54m | Avg: 42m 11s | Max: 1h 04m 🟩 14 Pass: 100%/37 | Total: 1d 04h | Avg: 45m 24s | Max: 1h 08m | Hits: 60%/2181 🟩 17 Pass: 100%/37 | Total: 1d 04h | Avg: 46m 54s | Max: 2h 03m | Hits: 63%/1454 🟩 20 Pass: 100%/24 | Total: 16h 00m | Avg: 40m 01s | Max: 1h 01m | Hits: 63%/727 -
🟩 libcudacxx: Pass: 100%/112 | Total: 15h 32m | Avg: 8m 19s | Max: 34m 07s | Hits: 91%/16953
🟩 cpu 🟩 amd64 Pass: 100%/104 | Total: 14h 51m | Avg: 8m 34s | Max: 34m 07s | Hits: 91%/16953 🟩 arm64 Pass: 100%/8 | Total: 40m 25s | Avg: 5m 03s | Max: 15m 28s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 1h 27m | Avg: 5m 49s | Max: 18m 19s | Hits: 99%/2633 🟩 11.8 Pass: 100%/3 | Total: 59m 35s | Avg: 19m 51s | Max: 20m 52s 🟩 12.5 Pass: 100%/94 | Total: 13h 05m | Avg: 8m 21s | Max: 34m 07s | Hits: 89%/14320 🟩 cudacxx 🟩 ClangCUDA17 Pass: 100%/2 | Total: 39m 10s | Avg: 19m 35s | Max: 20m 06s 🟩 nvcc11.1 Pass: 100%/15 | Total: 1h 27m | Avg: 5m 49s | Max: 18m 19s | Hits: 99%/2633 🟩 nvcc11.8 Pass: 100%/3 | Total: 59m 35s | Avg: 19m 51s | Max: 20m 52s 🟩 nvcc12.5 Pass: 100%/92 | Total: 12h 26m | Avg: 8m 06s | Max: 34m 07s | Hits: 89%/14320 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/2 | Total: 39m 10s | Avg: 19m 35s | Max: 20m 06s 🟩 nvcc Pass: 100%/110 | Total: 14h 53m | Avg: 8m 07s | Max: 34m 07s | Hits: 91%/16953 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 24m 20s | Avg: 4m 03s | Max: 5m 33s 🟩 Clang10 Pass: 100%/3 | Total: 14m 08s | Avg: 4m 42s | Max: 5m 08s 🟩 Clang11 Pass: 100%/4 | Total: 15m 55s | Avg: 3m 58s | Max: 4m 26s 🟩 Clang12 Pass: 100%/4 | Total: 32m 15s | Avg: 8m 03s | Max: 21m 10s 🟩 Clang13 Pass: 100%/4 | Total: 14m 59s | Avg: 3m 44s | Max: 3m 59s 🟩 Clang14 Pass: 100%/4 | Total: 15m 36s | Avg: 3m 54s | Max: 4m 19s 🟩 Clang15 Pass: 100%/4 | Total: 31m 01s | Avg: 7m 45s | Max: 18m 59s 🟩 Clang16 Pass: 100%/4 | Total: 15m 59s | Avg: 3m 59s | Max: 4m 34s 🟩 Clang17 Pass: 100%/14 | Total: 2h 24m | Avg: 10m 21s | Max: 25m 43s 🟩 GCC6 Pass: 100%/2 | Total: 5m 29s | Avg: 2m 44s | Max: 3m 05s 🟩 GCC7 Pass: 100%/6 | Total: 49m 59s | Avg: 8m 19s | Max: 19m 55s 🟩 GCC8 Pass: 100%/6 | Total: 33m 44s | Avg: 5m 37s | Max: 19m 14s 🟩 GCC9 Pass: 100%/6 | Total: 33m 44s | Avg: 5m 37s | Max: 17m 12s 🟩 GCC10 Pass: 100%/4 | Total: 14m 07s | Avg: 3m 31s | Max: 3m 52s 🟩 GCC11 Pass: 100%/7 | Total: 1h 13m | Avg: 10m 30s | Max: 20m 52s 🟩 GCC12 Pass: 100%/4 | Total: 13m 52s | Avg: 3m 28s | Max: 3m 49s 🟩 GCC13 Pass: 100%/21 | Total: 4h 16m | Avg: 12m 12s | Max: 34m 07s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 42m 34s | Avg: 14m 11s | Max: 19m 33s 🟩 MSVC14.16 Pass: 100%/1 | Total: 17m 35s | Avg: 17m 35s | Max: 17m 35s | Hits: 99%/2633 🟩 MSVC14.29 Pass: 100%/2 | Total: 38m 12s | Avg: 19m 06s | Max: 24m 47s | Hits: 74%/5628 🟩 MSVC14.39 Pass: 100%/3 | Total: 43m 51s | Avg: 14m 37s | Max: 15m 30s | Hits: 99%/8692 🟩 cxx_family 🟩 Clang Pass: 100%/47 | Total: 5h 09m | Avg: 6m 34s | Max: 25m 43s 🟩 GCC Pass: 100%/56 | Total: 8h 00m | Avg: 8m 35s | Max: 34m 07s 🟩 Intel Pass: 100%/3 | Total: 42m 34s | Avg: 14m 11s | Max: 19m 33s 🟩 MSVC Pass: 100%/6 | Total: 1h 39m | Avg: 16m 36s | Max: 24m 47s | Hits: 91%/16953 🟩 gpu 🟩 v100 Pass: 100%/112 | Total: 15h 32m | Avg: 8m 19s | Max: 34m 07s | Hits: 91%/16953 🟩 jobs 🟩 Build Pass: 100%/99 | Total: 11h 13m | Avg: 6m 47s | Max: 24m 47s | Hits: 91%/16953 🟩 NVRTC Pass: 100%/4 | Total: 1h 43m | Avg: 25m 59s | Max: 34m 07s 🟩 Test Pass: 100%/8 | Total: 2h 33m | Avg: 19m 09s | Max: 25m 43s 🟩 VerifyCodegen Pass: 100%/1 | Total: 2m 01s | Avg: 2m 01s | Max: 2m 01s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 59m 35s | Avg: 19m 51s | Max: 20m 52s 🟩 90a Pass: 100%/4 | Total: 16m 33s | Avg: 4m 08s | Max: 5m 10s 🟩 std 🟩 11 Pass: 100%/29 | Total: 3h 45m | Avg: 7m 45s | Max: 20m 52s 🟩 14 Pass: 100%/32 | Total: 3h 47m | Avg: 7m 06s | Max: 24m 47s | Hits: 82%/8101 🟩 17 Pass: 100%/31 | Total: 4h 53m | Avg: 9m 27s | Max: 34m 07s | Hits: 99%/5788 🟩 20 Pass: 100%/19 | Total: 3h 04m | Avg: 9m 41s | Max: 34m 05s | Hits: 99%/3064 -
🟩 cudax: Pass: 100%/54 | Total: 2h 42m | Avg: 3m 00s | Max: 9m 24s | Hits: 90%/194
🟩 cpu 🟩 amd64 Pass: 100%/50 | Total: 2h 32m | Avg: 3m 02s | Max: 9m 24s | Hits: 90%/194 🟩 arm64 Pass: 100%/4 | Total: 10m 13s | Avg: 2m 33s | Max: 3m 00s 🟩 ctk 🟩 12.0 Pass: 100%/23 | Total: 1h 07m | Avg: 2m 55s | Max: 7m 37s | Hits: 89%/97 🟩 12.5 Pass: 100%/31 | Total: 1h 35m | Avg: 3m 04s | Max: 9m 24s | Hits: 90%/97 🟩 cudacxx 🟩 nvcc12.0 Pass: 100%/23 | Total: 1h 07m | Avg: 2m 55s | Max: 7m 37s | Hits: 89%/97 🟩 nvcc12.5 Pass: 100%/31 | Total: 1h 35m | Avg: 3m 04s | Max: 9m 24s | Hits: 90%/97 🟩 cudacxx_family 🟩 nvcc Pass: 100%/54 | Total: 2h 42m | Avg: 3m 00s | Max: 9m 24s | Hits: 90%/194 🟩 cxx 🟩 Clang9 Pass: 100%/2 | Total: 5m 13s | Avg: 2m 36s | Max: 2m 42s 🟩 Clang10 Pass: 100%/2 | Total: 4m 58s | Avg: 2m 29s | Max: 2m 33s 🟩 Clang11 Pass: 100%/4 | Total: 10m 03s | Avg: 2m 30s | Max: 2m 38s 🟩 Clang12 Pass: 100%/4 | Total: 10m 37s | Avg: 2m 39s | Max: 2m 58s 🟩 Clang13 Pass: 100%/4 | Total: 10m 28s | Avg: 2m 37s | Max: 2m 57s 🟩 Clang14 Pass: 100%/6 | Total: 18m 32s | Avg: 3m 05s | Max: 4m 18s 🟩 Clang15 Pass: 100%/2 | Total: 6m 04s | Avg: 3m 02s | Max: 3m 26s 🟩 Clang16 Pass: 100%/6 | Total: 19m 50s | Avg: 3m 18s | Max: 5m 09s 🟩 GCC9 Pass: 100%/2 | Total: 4m 31s | Avg: 2m 15s | Max: 2m 21s 🟩 GCC10 Pass: 100%/4 | Total: 9m 22s | Avg: 2m 20s | Max: 2m 24s 🟩 GCC11 Pass: 100%/4 | Total: 9m 36s | Avg: 2m 24s | Max: 2m 27s 🟩 GCC12 Pass: 100%/12 | Total: 36m 10s | Avg: 3m 00s | Max: 3m 53s 🟩 MSVC14.36 Pass: 100%/1 | Total: 7m 37s | Avg: 7m 37s | Max: 7m 37s | Hits: 89%/97 🟩 MSVC14.39 Pass: 100%/1 | Total: 9m 24s | Avg: 9m 24s | Max: 9m 24s | Hits: 90%/97 🟩 cxx_family 🟩 Clang Pass: 100%/30 | Total: 1h 25m | Avg: 2m 51s | Max: 5m 09s 🟩 GCC Pass: 100%/22 | Total: 59m 39s | Avg: 2m 42s | Max: 3m 53s 🟩 MSVC Pass: 100%/2 | Total: 17m 01s | Avg: 8m 30s | Max: 9m 24s | Hits: 90%/194 🟩 gpu 🟩 v100 Pass: 100%/54 | Total: 2h 42m | Avg: 3m 00s | Max: 9m 24s | Hits: 90%/194 🟩 jobs 🟩 Build Pass: 100%/46 | Total: 2h 09m | Avg: 2m 49s | Max: 9m 24s | Hits: 90%/194 🟩 Test Pass: 100%/8 | Total: 32m 28s | Avg: 4m 03s | Max: 5m 09s 🟩 sm 🟩 90 Pass: 100%/1 | Total: 2m 06s | Avg: 2m 06s | Max: 2m 06s 🟩 90a Pass: 100%/1 | Total: 2m 43s | Avg: 2m 43s | Max: 2m 43s 🟩 std 🟩 17 Pass: 100%/30 | Total: 1h 22m | Avg: 2m 44s | Max: 5m 09s 🟩 20 Pass: 100%/24 | Total: 1h 20m | Avg: 3m 20s | Max: 9m 24s | Hits: 90%/194 -
🟩 pycuda: Pass: 100%/1 | Total: 14m 17s | Avg: 14m 17s | Max: 14m 17s
🟩 cpu 🟩 amd64 Pass: 100%/1 | Total: 14m 17s | Avg: 14m 17s | Max: 14m 17s 🟩 ctk 🟩 12.5 Pass: 100%/1 | Total: 14m 17s | Avg: 14m 17s | Max: 14m 17s 🟩 cudacxx 🟩 nvcc12.5 Pass: 100%/1 | Total: 14m 17s | Avg: 14m 17s | Max: 14m 17s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/1 | Total: 14m 17s | Avg: 14m 17s | Max: 14m 17s 🟩 cxx 🟩 GCC13 Pass: 100%/1 | Total: 14m 17s | Avg: 14m 17s | Max: 14m 17s 🟩 cxx_family 🟩 GCC Pass: 100%/1 | Total: 14m 17s | Avg: 14m 17s | Max: 14m 17s 🟩 gpu 🟩 v100 Pass: 100%/1 | Total: 14m 17s | Avg: 14m 17s | Max: 14m 17s 🟩 jobs 🟩 Test Pass: 100%/1 | Total: 14m 17s | Avg: 14m 17s | Max: 14m 17s
👃 Inspect Changes
Modifications in project?
| Project | |
|---|---|
| CCCL Infrastructure | |
| +/- | libcu++ |
| +/- | CUB |
| +/- | Thrust |
| CUDA Experimental | |
| pycuda | |
| CUDA C Core Library |
Modifications in project or dependencies?
| Project | |
|---|---|
| CCCL Infrastructure | |
| +/- | libcu++ |
| +/- | CUB |
| +/- | Thrust |
| +/- | CUDA Experimental |
| +/- | pycuda |
| +/- | CUDA C Core Library |
🏃 Runner counts (total jobs: 417)
| # | Runner |
|---|---|
| 304 | linux-amd64-cpu16 |
| 62 | linux-amd64-gpu-v100-latest-1 |
| 28 | linux-arm64-cpu16 |
| 23 | windows-amd64-cpu16 |
Benchmark of thrust::transform looks good (see PR description), except this regression:
| F64 | 2^25 | 580.479 us | 0.11% | 587.621 us | 0.14% | 7.142 us | 1.23% | FAIL |
However, 1.23% slowdown seem tolerable given the other improvements.
🟩 CI finished in 11h 59m: Pass: 100%/433 | Total: 8d 02h | Avg: 26m 54s | Max: 1h 12m | Hits: 76%/41615
-
🟩 cub: Pass: 100%/136 | Total: 4d 03h | Avg: 43m 46s | Max: 1h 11m | Hits: 65%/4362
🟩 cpu 🟩 amd64 Pass: 100%/128 | Total: 3d 19h | Avg: 43m 06s | Max: 1h 11m | Hits: 65%/4362 🟩 arm64 Pass: 100%/8 | Total: 7h 15m | Avg: 54m 24s | Max: 57m 31s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 11h 10m | Avg: 44m 40s | Max: 54m 18s | Hits: 65%/727 🟩 11.8 Pass: 100%/3 | Total: 3h 28m | Avg: 1h 09m | Max: 1h 11m 🟩 12.6 Pass: 100%/118 | Total: 3d 12h | Avg: 43m 00s | Max: 1h 07m | Hits: 65%/3635 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/2 | Total: 1h 46m | Avg: 53m 15s | Max: 53m 16s 🟩 nvcc11.1 Pass: 100%/15 | Total: 11h 10m | Avg: 44m 40s | Max: 54m 18s | Hits: 65%/727 🟩 nvcc11.8 Pass: 100%/3 | Total: 3h 28m | Avg: 1h 09m | Max: 1h 11m 🟩 nvcc12.6 Pass: 100%/116 | Total: 3d 10h | Avg: 42m 49s | Max: 1h 07m | Hits: 65%/3635 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/2 | Total: 1h 46m | Avg: 53m 15s | Max: 53m 16s 🟩 nvcc Pass: 100%/134 | Total: 4d 01h | Avg: 43m 37s | Max: 1h 11m | Hits: 65%/4362 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 4h 43m | Avg: 47m 16s | Max: 52m 46s 🟩 Clang10 Pass: 100%/3 | Total: 2h 34m | Avg: 51m 29s | Max: 52m 43s 🟩 Clang11 Pass: 100%/4 | Total: 3h 28m | Avg: 52m 09s | Max: 54m 17s 🟩 Clang12 Pass: 100%/4 | Total: 3h 35m | Avg: 53m 53s | Max: 56m 38s 🟩 Clang13 Pass: 100%/4 | Total: 3h 24m | Avg: 51m 00s | Max: 54m 09s 🟩 Clang14 Pass: 100%/4 | Total: 3h 27m | Avg: 51m 56s | Max: 55m 49s 🟩 Clang15 Pass: 100%/4 | Total: 3h 20m | Avg: 50m 08s | Max: 53m 11s 🟩 Clang16 Pass: 100%/4 | Total: 3h 29m | Avg: 52m 17s | Max: 54m 09s 🟩 Clang17 Pass: 100%/4 | Total: 3h 29m | Avg: 52m 19s | Max: 55m 55s 🟩 Clang18 Pass: 100%/26 | Total: 14h 11m | Avg: 32m 45s | Max: 56m 48s 🟩 GCC6 Pass: 100%/2 | Total: 1h 25m | Avg: 42m 32s | Max: 43m 21s 🟩 GCC7 Pass: 100%/6 | Total: 4h 45m | Avg: 47m 39s | Max: 55m 15s 🟩 GCC8 Pass: 100%/6 | Total: 4h 51m | Avg: 48m 37s | Max: 54m 41s 🟩 GCC9 Pass: 100%/6 | Total: 4h 49m | Avg: 48m 11s | Max: 53m 01s 🟩 GCC10 Pass: 100%/4 | Total: 3h 35m | Avg: 53m 52s | Max: 58m 26s 🟩 GCC11 Pass: 100%/7 | Total: 6h 59m | Avg: 59m 55s | Max: 1h 11m 🟩 GCC12 Pass: 100%/4 | Total: 3h 42m | Avg: 55m 35s | Max: 57m 56s 🟩 GCC13 Pass: 100%/29 | Total: 14h 27m | Avg: 29m 54s | Max: 58m 59s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 57m | Avg: 59m 11s | Max: 1h 01m 🟩 MSVC14.16 Pass: 100%/1 | Total: 54m 18s | Avg: 54m 18s | Max: 54m 18s | Hits: 65%/727 🟩 MSVC14.29 Pass: 100%/2 | Total: 1h 57m | Avg: 58m 37s | Max: 1h 00m | Hits: 65%/1454 🟩 MSVC14.39 Pass: 100%/3 | Total: 3h 02m | Avg: 1h 00m | Max: 1h 07m | Hits: 65%/2181 🟩 cxx_family 🟩 Clang Pass: 100%/63 | Total: 1d 21h | Avg: 43m 34s | Max: 56m 48s 🟩 GCC Pass: 100%/64 | Total: 1d 20h | Avg: 41m 49s | Max: 1h 11m 🟩 Intel Pass: 100%/3 | Total: 2h 57m | Avg: 59m 11s | Max: 1h 01m 🟩 MSVC Pass: 100%/6 | Total: 5h 53m | Avg: 58m 57s | Max: 1h 07m | Hits: 65%/4362 🟩 gpu 🟩 v100 Pass: 100%/136 | Total: 4d 03h | Avg: 43m 46s | Max: 1h 11m | Hits: 65%/4362 🟩 jobs 🟩 Build Pass: 100%/103 | Total: 3d 16h | Avg: 51m 30s | Max: 1h 11m | Hits: 65%/4362 🟩 DeviceLaunch Pass: 100%/8 | Total: 2h 33m | Avg: 19m 09s | Max: 20m 39s 🟩 GraphCapture Pass: 100%/8 | Total: 1h 59m | Avg: 14m 58s | Max: 16m 39s 🟩 HostLaunch Pass: 100%/8 | Total: 2h 25m | Avg: 18m 11s | Max: 21m 39s 🟩 SmallGMem Pass: 100%/1 | Total: 34m 16s | Avg: 34m 16s | Max: 34m 16s 🟩 TestGPU Pass: 100%/8 | Total: 3h 15m | Avg: 24m 22s | Max: 30m 41s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 3h 28m | Avg: 1h 09m | Max: 1h 11m 🟩 90a Pass: 100%/4 | Total: 1h 33m | Avg: 23m 24s | Max: 24m 40s 🟩 std 🟩 11 Pass: 100%/35 | Total: 1d 01h | Avg: 43m 02s | Max: 1h 07m 🟩 14 Pass: 100%/38 | Total: 1d 04h | Avg: 44m 59s | Max: 1h 08m | Hits: 65%/2181 🟩 17 Pass: 100%/38 | Total: 1d 03h | Avg: 44m 09s | Max: 1h 11m | Hits: 65%/1454 🟩 20 Pass: 100%/25 | Total: 17h 38m | Avg: 42m 21s | Max: 1h 07m | Hits: 65%/727 -
🟩 thrust: Pass: 100%/122 | Total: 2d 13h | Avg: 30m 16s | Max: 1h 12m | Hits: 77%/20106
🟩 cpu 🟩 amd64 Pass: 100%/114 | Total: 2d 09h | Avg: 30m 14s | Max: 1h 12m | Hits: 77%/20106 🟩 arm64 Pass: 100%/8 | Total: 4h 05m | Avg: 30m 44s | Max: 36m 08s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 7h 11m | Avg: 28m 47s | Max: 51m 34s | Hits: 66%/2234 🟩 11.8 Pass: 100%/3 | Total: 2h 02m | Avg: 40m 58s | Max: 44m 36s 🟩 12.6 Pass: 100%/104 | Total: 2d 04h | Avg: 30m 11s | Max: 1h 12m | Hits: 78%/17872 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/2 | Total: 58m 02s | Avg: 29m 01s | Max: 30m 15s 🟩 nvcc11.1 Pass: 100%/15 | Total: 7h 11m | Avg: 28m 47s | Max: 51m 34s | Hits: 66%/2234 🟩 nvcc11.8 Pass: 100%/3 | Total: 2h 02m | Avg: 40m 58s | Max: 44m 36s 🟩 nvcc12.6 Pass: 100%/102 | Total: 2d 03h | Avg: 30m 12s | Max: 1h 12m | Hits: 78%/17872 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/2 | Total: 58m 02s | Avg: 29m 01s | Max: 30m 15s 🟩 nvcc Pass: 100%/120 | Total: 2d 12h | Avg: 30m 18s | Max: 1h 12m | Hits: 77%/20106 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 2h 59m | Avg: 29m 54s | Max: 38m 02s 🟩 Clang10 Pass: 100%/3 | Total: 1h 43m | Avg: 34m 23s | Max: 36m 53s 🟩 Clang11 Pass: 100%/4 | Total: 2h 04m | Avg: 31m 01s | Max: 33m 21s 🟩 Clang12 Pass: 100%/4 | Total: 2h 12m | Avg: 33m 06s | Max: 36m 07s 🟩 Clang13 Pass: 100%/4 | Total: 2h 01m | Avg: 30m 24s | Max: 33m 21s 🟩 Clang14 Pass: 100%/4 | Total: 2h 04m | Avg: 31m 01s | Max: 36m 25s 🟩 Clang15 Pass: 100%/4 | Total: 2h 08m | Avg: 32m 10s | Max: 34m 37s 🟩 Clang16 Pass: 100%/4 | Total: 2h 06m | Avg: 31m 33s | Max: 36m 30s 🟩 Clang17 Pass: 100%/4 | Total: 2h 16m | Avg: 34m 05s | Max: 37m 34s 🟩 Clang18 Pass: 100%/18 | Total: 6h 40m | Avg: 22m 13s | Max: 34m 09s 🟩 GCC6 Pass: 100%/2 | Total: 52m 11s | Avg: 26m 05s | Max: 28m 08s 🟩 GCC7 Pass: 100%/6 | Total: 2h 58m | Avg: 29m 44s | Max: 34m 56s 🟩 GCC8 Pass: 100%/6 | Total: 2h 54m | Avg: 29m 02s | Max: 33m 15s 🟩 GCC9 Pass: 100%/6 | Total: 3h 03m | Avg: 30m 37s | Max: 37m 37s 🟩 GCC10 Pass: 100%/4 | Total: 2h 11m | Avg: 32m 52s | Max: 35m 44s 🟩 GCC11 Pass: 100%/7 | Total: 4h 13m | Avg: 36m 16s | Max: 44m 36s 🟩 GCC12 Pass: 100%/4 | Total: 2h 21m | Avg: 35m 15s | Max: 41m 30s 🟩 GCC13 Pass: 100%/20 | Total: 7h 34m | Avg: 22m 44s | Max: 44m 27s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 04m | Avg: 41m 34s | Max: 47m 53s 🟩 MSVC14.16 Pass: 100%/1 | Total: 51m 34s | Avg: 51m 34s | Max: 51m 34s | Hits: 66%/2234 🟩 MSVC14.29 Pass: 100%/2 | Total: 1h 58m | Avg: 59m 03s | Max: 1h 00m | Hits: 66%/4468 🟩 MSVC14.39 Pass: 100%/6 | Total: 4h 13m | Avg: 42m 16s | Max: 1h 12m | Hits: 82%/13404 🟩 cxx_family 🟩 Clang Pass: 100%/55 | Total: 1d 02h | Avg: 28m 39s | Max: 38m 02s 🟩 GCC Pass: 100%/55 | Total: 1d 02h | Avg: 28m 32s | Max: 44m 36s 🟩 Intel Pass: 100%/3 | Total: 2h 04m | Avg: 41m 34s | Max: 47m 53s 🟩 MSVC Pass: 100%/9 | Total: 7h 03m | Avg: 47m 01s | Max: 1h 12m | Hits: 77%/20106 🟩 gpu 🟩 v100 Pass: 100%/122 | Total: 2d 13h | Avg: 30m 16s | Max: 1h 12m | Hits: 77%/20106 🟩 jobs 🟩 Build Pass: 100%/103 | Total: 2d 09h | Avg: 33m 21s | Max: 1h 12m | Hits: 66%/13404 🟩 TestCPU Pass: 100%/11 | Total: 2h 04m | Avg: 11m 20s | Max: 21m 38s | Hits: 99%/6702 🟩 TestGPU Pass: 100%/8 | Total: 2h 12m | Avg: 16m 35s | Max: 20m 58s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 2h 02m | Avg: 40m 58s | Max: 44m 36s 🟩 90a Pass: 100%/4 | Total: 1h 21m | Avg: 20m 24s | Max: 23m 24s 🟩 std 🟩 11 Pass: 100%/31 | Total: 12h 41m | Avg: 24m 33s | Max: 36m 27s 🟩 14 Pass: 100%/35 | Total: 18h 43m | Avg: 32m 06s | Max: 1h 00m | Hits: 74%/8936 🟩 17 Pass: 100%/34 | Total: 18h 45m | Avg: 33m 05s | Max: 58m 34s | Hits: 77%/6702 🟩 20 Pass: 100%/22 | Total: 11h 23m | Avg: 31m 04s | Max: 1h 12m | Hits: 82%/4468 -
🟩 libcudacxx: Pass: 100%/116 | Total: 1d 06h | Avg: 15m 41s | Max: 1h 04m | Hits: 77%/16953
🟩 cpu 🟩 amd64 Pass: 100%/108 | Total: 1d 04h | Avg: 15m 57s | Max: 1h 04m | Hits: 77%/16953 🟩 arm64 Pass: 100%/8 | Total: 1h 37m | Avg: 12m 07s | Max: 18m 32s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 3h 28m | Avg: 13m 55s | Max: 27m 18s | Hits: 46%/2633 🟩 11.8 Pass: 100%/3 | Total: 56m 09s | Avg: 18m 43s | Max: 20m 04s 🟩 12.6 Pass: 100%/98 | Total: 1d 01h | Avg: 15m 51s | Max: 1h 04m | Hits: 83%/14320 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/2 | Total: 37m 25s | Avg: 18m 42s | Max: 18m 53s 🟩 nvcc11.1 Pass: 100%/15 | Total: 3h 28m | Avg: 13m 55s | Max: 27m 18s | Hits: 46%/2633 🟩 nvcc11.8 Pass: 100%/3 | Total: 56m 09s | Avg: 18m 43s | Max: 20m 04s 🟩 nvcc12.6 Pass: 100%/96 | Total: 1d 01h | Avg: 15m 48s | Max: 1h 04m | Hits: 83%/14320 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/2 | Total: 37m 25s | Avg: 18m 42s | Max: 18m 53s 🟩 nvcc Pass: 100%/114 | Total: 1d 05h | Avg: 15m 38s | Max: 1h 04m | Hits: 77%/16953 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 1h 38m | Avg: 16m 21s | Max: 20m 50s 🟩 Clang10 Pass: 100%/3 | Total: 57m 18s | Avg: 19m 06s | Max: 19m 45s 🟩 Clang11 Pass: 100%/4 | Total: 1h 16m | Avg: 19m 06s | Max: 21m 08s 🟩 Clang12 Pass: 100%/4 | Total: 46m 29s | Avg: 11m 37s | Max: 21m 35s 🟩 Clang13 Pass: 100%/4 | Total: 1h 17m | Avg: 19m 15s | Max: 21m 14s 🟩 Clang14 Pass: 100%/4 | Total: 55m 57s | Avg: 13m 59s | Max: 20m 39s 🟩 Clang15 Pass: 100%/4 | Total: 47m 56s | Avg: 11m 59s | Max: 20m 45s 🟩 Clang16 Pass: 100%/4 | Total: 39m 30s | Avg: 9m 52s | Max: 22m 05s 🟩 Clang17 Pass: 100%/4 | Total: 49m 08s | Avg: 12m 17s | Max: 22m 41s 🟩 Clang18 Pass: 100%/14 | Total: 2h 53m | Avg: 12m 25s | Max: 22m 03s 🟩 GCC6 Pass: 100%/2 | Total: 31m 43s | Avg: 15m 51s | Max: 19m 44s 🟩 GCC7 Pass: 100%/6 | Total: 1h 26m | Avg: 14m 21s | Max: 21m 50s 🟩 GCC8 Pass: 100%/6 | Total: 1h 03m | Avg: 10m 32s | Max: 18m 42s 🟩 GCC9 Pass: 100%/6 | Total: 1h 44m | Avg: 17m 22s | Max: 21m 19s 🟩 GCC10 Pass: 100%/4 | Total: 1h 04m | Avg: 16m 13s | Max: 20m 07s 🟩 GCC11 Pass: 100%/7 | Total: 2h 14m | Avg: 19m 10s | Max: 20m 37s 🟩 GCC12 Pass: 100%/4 | Total: 1h 11m | Avg: 17m 45s | Max: 23m 20s 🟩 GCC13 Pass: 100%/21 | Total: 6h 33m | Avg: 18m 45s | Max: 1h 04m 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 35m 06s | Avg: 11m 42s | Max: 18m 14s 🟩 MSVC14.16 Pass: 100%/1 | Total: 27m 18s | Avg: 27m 18s | Max: 27m 18s | Hits: 46%/2633 🟩 MSVC14.29 Pass: 100%/2 | Total: 35m 32s | Avg: 17m 46s | Max: 24m 27s | Hits: 73%/5628 🟩 MSVC14.39 Pass: 100%/3 | Total: 50m 46s | Avg: 16m 55s | Max: 21m 44s | Hits: 90%/8692 🟩 cxx_family 🟩 Clang Pass: 100%/51 | Total: 12h 01m | Avg: 14m 09s | Max: 22m 41s 🟩 GCC Pass: 100%/56 | Total: 15h 49m | Avg: 16m 57s | Max: 1h 04m 🟩 Intel Pass: 100%/3 | Total: 35m 06s | Avg: 11m 42s | Max: 18m 14s 🟩 MSVC Pass: 100%/6 | Total: 1h 53m | Avg: 18m 56s | Max: 27m 18s | Hits: 77%/16953 🟩 gpu 🟩 v100 Pass: 100%/116 | Total: 1d 06h | Avg: 15m 41s | Max: 1h 04m | Hits: 77%/16953 🟩 jobs 🟩 Build Pass: 100%/103 | Total: 1d 00h | Avg: 14m 29s | Max: 27m 18s | Hits: 77%/16953 🟩 NVRTC Pass: 100%/4 | Total: 1h 08m | Avg: 17m 01s | Max: 18m 12s 🟩 Test Pass: 100%/8 | Total: 4h 17m | Avg: 32m 10s | Max: 1h 04m 🟩 VerifyCodegen Pass: 100%/1 | Total: 2m 01s | Avg: 2m 01s | Max: 2m 01s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 56m 09s | Avg: 18m 43s | Max: 20m 04s 🟩 90a Pass: 100%/4 | Total: 26m 36s | Avg: 6m 39s | Max: 7m 32s 🟩 std 🟩 11 Pass: 100%/30 | Total: 7h 02m | Avg: 14m 04s | Max: 24m 37s 🟩 14 Pass: 100%/33 | Total: 8h 03m | Avg: 14m 38s | Max: 44m 23s | Hits: 59%/8101 🟩 17 Pass: 100%/32 | Total: 8h 37m | Avg: 16m 09s | Max: 53m 16s | Hits: 99%/5788 🟩 20 Pass: 100%/20 | Total: 6h 34m | Avg: 19m 44s | Max: 1h 04m | Hits: 84%/3064 -
🟩 cudax: Pass: 100%/58 | Total: 2h 53m | Avg: 2m 59s | Max: 7m 08s | Hits: 89%/194
🟩 cpu 🟩 amd64 Pass: 100%/54 | Total: 2h 44m | Avg: 3m 02s | Max: 7m 08s | Hits: 89%/194 🟩 arm64 Pass: 100%/4 | Total: 9m 16s | Avg: 2m 19s | Max: 2m 23s 🟩 ctk 🟩 12.0 Pass: 100%/23 | Total: 1h 09m | Avg: 3m 01s | Max: 7m 08s | Hits: 89%/97 🟩 12.6 Pass: 100%/35 | Total: 1h 44m | Avg: 2m 58s | Max: 6m 57s | Hits: 89%/97 🟩 cudacxx 🟩 nvcc12.0 Pass: 100%/23 | Total: 1h 09m | Avg: 3m 01s | Max: 7m 08s | Hits: 89%/97 🟩 nvcc12.6 Pass: 100%/35 | Total: 1h 44m | Avg: 2m 58s | Max: 6m 57s | Hits: 89%/97 🟩 cudacxx_family 🟩 nvcc Pass: 100%/58 | Total: 2h 53m | Avg: 2m 59s | Max: 7m 08s | Hits: 89%/194 🟩 cxx 🟩 Clang9 Pass: 100%/2 | Total: 5m 10s | Avg: 2m 35s | Max: 2m 37s 🟩 Clang10 Pass: 100%/2 | Total: 5m 16s | Avg: 2m 38s | Max: 2m 46s 🟩 Clang11 Pass: 100%/4 | Total: 10m 03s | Avg: 2m 30s | Max: 2m 40s 🟩 Clang12 Pass: 100%/4 | Total: 10m 39s | Avg: 2m 39s | Max: 3m 15s 🟩 Clang13 Pass: 100%/4 | Total: 10m 55s | Avg: 2m 43s | Max: 2m 49s 🟩 Clang14 Pass: 100%/6 | Total: 19m 01s | Avg: 3m 10s | Max: 5m 02s 🟩 Clang15 Pass: 100%/2 | Total: 5m 38s | Avg: 2m 49s | Max: 3m 03s 🟩 Clang16 Pass: 100%/4 | Total: 10m 04s | Avg: 2m 31s | Max: 2m 45s 🟩 Clang17 Pass: 100%/2 | Total: 5m 31s | Avg: 2m 45s | Max: 2m 46s 🟩 Clang18 Pass: 100%/4 | Total: 14m 39s | Avg: 3m 39s | Max: 4m 59s 🟩 GCC9 Pass: 100%/2 | Total: 5m 29s | Avg: 2m 44s | Max: 3m 09s 🟩 GCC10 Pass: 100%/4 | Total: 10m 02s | Avg: 2m 30s | Max: 2m 42s 🟩 GCC11 Pass: 100%/4 | Total: 10m 45s | Avg: 2m 41s | Max: 3m 02s 🟩 GCC12 Pass: 100%/9 | Total: 29m 32s | Avg: 3m 16s | Max: 4m 49s 🟩 GCC13 Pass: 100%/3 | Total: 6m 52s | Avg: 2m 17s | Max: 2m 19s 🟩 MSVC14.36 Pass: 100%/1 | Total: 7m 08s | Avg: 7m 08s | Max: 7m 08s | Hits: 89%/97 🟩 MSVC14.39 Pass: 100%/1 | Total: 6m 57s | Avg: 6m 57s | Max: 6m 57s | Hits: 89%/97 🟩 cxx_family 🟩 Clang Pass: 100%/34 | Total: 1h 36m | Avg: 2m 51s | Max: 5m 02s 🟩 GCC Pass: 100%/22 | Total: 1h 02m | Avg: 2m 50s | Max: 4m 49s 🟩 MSVC Pass: 100%/2 | Total: 14m 05s | Avg: 7m 02s | Max: 7m 08s | Hits: 89%/194 🟩 gpu 🟩 v100 Pass: 100%/58 | Total: 2h 53m | Avg: 2m 59s | Max: 7m 08s | Hits: 89%/194 🟩 jobs 🟩 Build Pass: 100%/50 | Total: 2h 19m | Avg: 2m 47s | Max: 7m 08s | Hits: 89%/194 🟩 Test Pass: 100%/8 | Total: 34m 21s | Avg: 4m 17s | Max: 5m 02s 🟩 sm 🟩 90 Pass: 100%/1 | Total: 2m 42s | Avg: 2m 42s | Max: 2m 42s 🟩 90a Pass: 100%/1 | Total: 2m 16s | Avg: 2m 16s | Max: 2m 16s 🟩 std 🟩 17 Pass: 100%/32 | Total: 1h 28m | Avg: 2m 46s | Max: 4m 27s 🟩 20 Pass: 100%/26 | Total: 1h 24m | Avg: 3m 15s | Max: 7m 08s | Hits: 89%/194 -
🟩 pycuda: Pass: 100%/1 | Total: 13m 17s | Avg: 13m 17s | Max: 13m 17s
🟩 cpu 🟩 amd64 Pass: 100%/1 | Total: 13m 17s | Avg: 13m 17s | Max: 13m 17s 🟩 ctk 🟩 12.5 Pass: 100%/1 | Total: 13m 17s | Avg: 13m 17s | Max: 13m 17s 🟩 cudacxx 🟩 nvcc12.5 Pass: 100%/1 | Total: 13m 17s | Avg: 13m 17s | Max: 13m 17s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/1 | Total: 13m 17s | Avg: 13m 17s | Max: 13m 17s 🟩 cxx 🟩 GCC13 Pass: 100%/1 | Total: 13m 17s | Avg: 13m 17s | Max: 13m 17s 🟩 cxx_family 🟩 GCC Pass: 100%/1 | Total: 13m 17s | Avg: 13m 17s | Max: 13m 17s 🟩 gpu 🟩 v100 Pass: 100%/1 | Total: 13m 17s | Avg: 13m 17s | Max: 13m 17s 🟩 jobs 🟩 Test Pass: 100%/1 | Total: 13m 17s | Avg: 13m 17s | Max: 13m 17s
👃 Inspect Changes
Modifications in project?
| Project | |
|---|---|
| CCCL Infrastructure | |
| +/- | libcu++ |
| +/- | CUB |
| +/- | Thrust |
| CUDA Experimental | |
| pycuda | |
| CUDA C Core Library |
Modifications in project or dependencies?
| Project | |
|---|---|
| CCCL Infrastructure | |
| +/- | libcu++ |
| +/- | CUB |
| +/- | Thrust |
| +/- | CUDA Experimental |
| +/- | pycuda |
| +/- | CUDA C Core Library |
🏃 Runner counts (total jobs: 433)
| # | Runner |
|---|---|
| 320 | linux-amd64-cpu16 |
| 62 | linux-amd64-gpu-v100-latest-1 |
| 28 | linux-arm64-cpu16 |
| 23 | windows-amd64-cpu16 |
It seems we are blocked on: #2402
🟩 CI finished in 4h 14m: Pass: 100%/394 | Total: 8d 19h | Avg: 32m 10s | Max: 1h 37m | Hits: 55%/25800
-
🟩 libcudacxx: Pass: 100%/118 | Total: 1d 12h | Avg: 18m 43s | Max: 41m 11s | Hits: 30%/9472
🟩 cpu 🟩 amd64 Pass: 100%/110 | Total: 1d 10h | Avg: 18m 48s | Max: 41m 11s | Hits: 30%/9472 🟩 arm64 Pass: 100%/8 | Total: 2h 19m | Avg: 17m 28s | Max: 27m 16s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 4h 54m | Avg: 19m 36s | Max: 39m 07s | Hits: 30%/2175 🟩 11.8 Pass: 100%/3 | Total: 1h 17m | Avg: 25m 46s | Max: 29m 29s 🟩 12.5 Pass: 100%/4 | Total: 2h 19m | Avg: 34m 59s | Max: 40m 09s 🟩 12.6 Pass: 100%/96 | Total: 1d 04h | Avg: 17m 40s | Max: 41m 11s | Hits: 30%/7297 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/12 | Total: 2h 32m | Avg: 12m 40s | Max: 20m 36s 🟩 nvcc11.1 Pass: 100%/15 | Total: 4h 54m | Avg: 19m 36s | Max: 39m 07s | Hits: 30%/2175 🟩 nvcc11.8 Pass: 100%/3 | Total: 1h 17m | Avg: 25m 46s | Max: 29m 29s 🟩 nvcc12.5 Pass: 100%/4 | Total: 2h 19m | Avg: 34m 59s | Max: 40m 09s 🟩 nvcc12.6 Pass: 100%/84 | Total: 1d 01h | Avg: 18m 23s | Max: 41m 11s | Hits: 30%/7297 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/12 | Total: 2h 32m | Avg: 12m 40s | Max: 20m 36s 🟩 nvcc Pass: 100%/106 | Total: 1d 10h | Avg: 19m 24s | Max: 41m 11s | Hits: 30%/9472 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 1h 56m | Avg: 19m 24s | Max: 26m 20s 🟩 Clang10 Pass: 100%/3 | Total: 50m 43s | Avg: 16m 54s | Max: 24m 40s 🟩 Clang11 Pass: 100%/4 | Total: 35m 51s | Avg: 8m 57s | Max: 21m 18s 🟩 Clang12 Pass: 100%/4 | Total: 1h 01m | Avg: 15m 15s | Max: 30m 29s 🟩 Clang13 Pass: 100%/4 | Total: 1h 14m | Avg: 18m 41s | Max: 29m 32s 🟩 Clang14 Pass: 100%/4 | Total: 1h 38m | Avg: 24m 43s | Max: 30m 07s 🟩 Clang15 Pass: 100%/4 | Total: 1h 21m | Avg: 20m 26s | Max: 31m 18s 🟩 Clang16 Pass: 100%/4 | Total: 33m 50s | Avg: 8m 27s | Max: 19m 11s 🟩 Clang17 Pass: 100%/4 | Total: 1h 18m | Avg: 19m 39s | Max: 27m 26s 🟩 Clang18 Pass: 100%/18 | Total: 4h 09m | Avg: 13m 50s | Max: 24m 32s 🟩 GCC6 Pass: 100%/2 | Total: 39m 26s | Avg: 19m 43s | Max: 22m 31s 🟩 GCC7 Pass: 100%/6 | Total: 1h 52m | Avg: 18m 44s | Max: 27m 00s 🟩 GCC8 Pass: 100%/6 | Total: 1h 34m | Avg: 15m 46s | Max: 28m 20s 🟩 GCC9 Pass: 100%/6 | Total: 1h 33m | Avg: 15m 36s | Max: 24m 00s 🟩 GCC10 Pass: 100%/4 | Total: 1h 21m | Avg: 20m 24s | Max: 27m 25s 🟩 GCC11 Pass: 100%/7 | Total: 2h 52m | Avg: 24m 37s | Max: 30m 13s 🟩 GCC12 Pass: 100%/4 | Total: 1h 41m | Avg: 25m 22s | Max: 29m 36s 🟩 GCC13 Pass: 100%/17 | Total: 4h 15m | Avg: 15m 03s | Max: 32m 21s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 1h 24m | Avg: 28m 13s | Max: 35m 53s 🟩 MSVC14.16 Pass: 100%/1 | Total: 39m 07s | Avg: 39m 07s | Max: 39m 07s | Hits: 30%/2175 🟩 MSVC14.29 Pass: 100%/2 | Total: 1h 11m | Avg: 35m 38s | Max: 40m 15s | Hits: 31%/4711 🟩 MSVC14.39 Pass: 100%/1 | Total: 41m 11s | Avg: 41m 11s | Max: 41m 11s | Hits: 29%/2586 🟩 NVHPC24.7 Pass: 100%/4 | Total: 2h 19m | Avg: 34m 59s | Max: 40m 09s 🟩 cxx_family 🟩 Clang Pass: 100%/55 | Total: 14h 41m | Avg: 16m 01s | Max: 31m 18s 🟩 GCC Pass: 100%/52 | Total: 15h 51m | Avg: 18m 17s | Max: 32m 21s 🟩 Intel Pass: 100%/3 | Total: 1h 24m | Avg: 28m 13s | Max: 35m 53s 🟩 MSVC Pass: 100%/4 | Total: 2h 31m | Avg: 37m 53s | Max: 41m 11s | Hits: 30%/9472 🟩 NVHPC Pass: 100%/4 | Total: 2h 19m | Avg: 34m 59s | Max: 40m 09s 🟩 gpu 🟩 v100 Pass: 100%/118 | Total: 1d 12h | Avg: 18m 43s | Max: 41m 11s | Hits: 30%/9472 🟩 jobs 🟩 Build Pass: 100%/110 | Total: 1d 10h | Avg: 18m 47s | Max: 41m 11s | Hits: 30%/9472 🟩 NVRTC Pass: 100%/4 | Total: 1h 33m | Avg: 23m 28s | Max: 28m 10s 🟩 Test Pass: 100%/3 | Total: 46m 12s | Avg: 15m 24s | Max: 16m 47s 🟩 VerifyCodegen Pass: 100%/1 | Total: 2m 11s | Avg: 2m 11s | Max: 2m 11s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 1h 17m | Avg: 25m 46s | Max: 29m 29s 🟩 90 Pass: 100%/4 | Total: 42m 24s | Avg: 10m 36s | Max: 12m 17s 🟩 90a Pass: 100%/8 | Total: 59m 30s | Avg: 7m 26s | Max: 12m 20s 🟩 std 🟩 11 Pass: 100%/32 | Total: 8h 15m | Avg: 15m 28s | Max: 26m 54s 🟩 14 Pass: 100%/32 | Total: 10h 21m | Avg: 19m 24s | Max: 39m 07s | Hits: 31%/4452 🟩 17 Pass: 100%/30 | Total: 10h 00m | Avg: 20m 00s | Max: 40m 15s | Hits: 30%/2434 🟩 20 Pass: 100%/23 | Total: 8h 09m | Avg: 21m 17s | Max: 41m 11s | Hits: 29%/2586 -
🟩 cub: Pass: 100%/110 | Total: 4d 05h | Avg: 55m 37s | Max: 1h 37m | Hits: 60%/2924
🟩 cpu 🟩 amd64 Pass: 100%/102 | Total: 3d 22h | Avg: 55m 45s | Max: 1h 37m | Hits: 60%/2924 🟩 arm64 Pass: 100%/8 | Total: 7h 12m | Avg: 54m 01s | Max: 54m 58s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 12h 02m | Avg: 48m 11s | Max: 51m 08s | Hits: 63%/731 🟩 11.8 Pass: 100%/3 | Total: 3h 49m | Avg: 1h 16m | Max: 1h 20m 🟩 12.5 Pass: 100%/4 | Total: 4h 08m | Avg: 1h 02m | Max: 1h 07m 🟩 12.6 Pass: 100%/88 | Total: 3d 09h | Avg: 55m 53s | Max: 1h 37m | Hits: 59%/2193 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/4 | Total: 3h 56m | Avg: 59m 02s | Max: 1h 01m 🟩 nvcc11.1 Pass: 100%/15 | Total: 12h 02m | Avg: 48m 11s | Max: 51m 08s | Hits: 63%/731 🟩 nvcc11.8 Pass: 100%/3 | Total: 3h 49m | Avg: 1h 16m | Max: 1h 20m 🟩 nvcc12.5 Pass: 100%/4 | Total: 4h 08m | Avg: 1h 02m | Max: 1h 07m 🟩 nvcc12.6 Pass: 100%/84 | Total: 3d 06h | Avg: 55m 44s | Max: 1h 37m | Hits: 59%/2193 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/4 | Total: 3h 56m | Avg: 59m 02s | Max: 1h 01m 🟩 nvcc Pass: 100%/106 | Total: 4d 02h | Avg: 55m 29s | Max: 1h 37m | Hits: 60%/2924 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 5h 13m | Avg: 52m 16s | Max: 57m 48s 🟩 Clang10 Pass: 100%/3 | Total: 2h 47m | Avg: 55m 55s | Max: 59m 47s 🟩 Clang11 Pass: 100%/4 | Total: 3h 45m | Avg: 56m 20s | Max: 57m 49s 🟩 Clang12 Pass: 100%/4 | Total: 3h 46m | Avg: 56m 41s | Max: 59m 02s 🟩 Clang13 Pass: 100%/4 | Total: 3h 35m | Avg: 53m 49s | Max: 57m 12s 🟩 Clang14 Pass: 100%/4 | Total: 3h 38m | Avg: 54m 38s | Max: 56m 55s 🟩 Clang15 Pass: 100%/4 | Total: 3h 41m | Avg: 55m 16s | Max: 59m 31s 🟩 Clang16 Pass: 100%/4 | Total: 3h 31m | Avg: 52m 53s | Max: 54m 43s 🟩 Clang17 Pass: 100%/4 | Total: 3h 45m | Avg: 56m 22s | Max: 1h 02m 🟩 Clang18 Pass: 100%/11 | Total: 9h 45m | Avg: 53m 13s | Max: 1h 01m 🟩 GCC6 Pass: 100%/2 | Total: 1h 33m | Avg: 46m 49s | Max: 49m 54s 🟩 GCC7 Pass: 100%/6 | Total: 5h 11m | Avg: 51m 59s | Max: 1h 02m 🟩 GCC8 Pass: 100%/6 | Total: 5h 00m | Avg: 50m 01s | Max: 52m 53s 🟩 GCC9 Pass: 100%/6 | Total: 5h 23m | Avg: 53m 57s | Max: 1h 00m 🟩 GCC10 Pass: 100%/4 | Total: 3h 46m | Avg: 56m 44s | Max: 1h 00m 🟩 GCC11 Pass: 100%/7 | Total: 7h 31m | Avg: 1h 04m | Max: 1h 20m 🟩 GCC12 Pass: 100%/4 | Total: 3h 43m | Avg: 55m 52s | Max: 59m 02s 🟩 GCC13 Pass: 100%/16 | Total: 15h 11m | Avg: 56m 57s | Max: 1h 37m 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 3h 00m | Avg: 1h 00m | Max: 1h 04m 🟩 MSVC14.16 Pass: 100%/1 | Total: 51m 08s | Avg: 51m 08s | Max: 51m 08s | Hits: 63%/731 🟩 MSVC14.29 Pass: 100%/2 | Total: 1h 59m | Avg: 59m 40s | Max: 1h 02m | Hits: 57%/1462 🟩 MSVC14.39 Pass: 100%/1 | Total: 1h 05m | Avg: 1h 05m | Max: 1h 05m | Hits: 63%/731 🟩 NVHPC24.7 Pass: 100%/4 | Total: 4h 08m | Avg: 1h 02m | Max: 1h 07m 🟩 cxx_family 🟩 Clang Pass: 100%/48 | Total: 1d 19h | Avg: 54m 23s | Max: 1h 02m 🟩 GCC Pass: 100%/51 | Total: 1d 23h | Avg: 55m 44s | Max: 1h 37m 🟩 Intel Pass: 100%/3 | Total: 3h 00m | Avg: 1h 00m | Max: 1h 04m 🟩 MSVC Pass: 100%/4 | Total: 3h 55m | Avg: 58m 57s | Max: 1h 05m | Hits: 60%/2924 🟩 NVHPC Pass: 100%/4 | Total: 4h 08m | Avg: 1h 02m | Max: 1h 07m 🟩 gpu 🟩 v100 Pass: 100%/110 | Total: 4d 05h | Avg: 55m 37s | Max: 1h 37m | Hits: 60%/2924 🟩 jobs 🟩 Build Pass: 100%/102 | Total: 3d 20h | Avg: 54m 27s | Max: 1h 20m | Hits: 60%/2924 🟩 DeviceLaunch Pass: 100%/1 | Total: 1h 37m | Avg: 1h 37m | Max: 1h 37m 🟩 GraphCapture Pass: 100%/1 | Total: 1h 37m | Avg: 1h 37m | Max: 1h 37m 🟩 HostLaunch Pass: 100%/3 | Total: 2h 44m | Avg: 54m 59s | Max: 1h 24m 🟩 TestGPU Pass: 100%/3 | Total: 3h 24m | Avg: 1h 08m | Max: 1h 30m 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 3h 49m | Avg: 1h 16m | Max: 1h 20m 🟩 90a Pass: 100%/4 | Total: 1h 36m | Avg: 24m 10s | Max: 25m 53s 🟩 std 🟩 11 Pass: 100%/30 | Total: 1d 03h | Avg: 55m 00s | Max: 1h 17m 🟩 14 Pass: 100%/29 | Total: 1d 02h | Avg: 54m 32s | Max: 1h 20m | Hits: 58%/1462 🟩 17 Pass: 100%/27 | Total: 1d 00h | Avg: 53m 50s | Max: 1h 12m | Hits: 60%/731 🟩 20 Pass: 100%/24 | Total: 23h 53m | Avg: 59m 43s | Max: 1h 37m | Hits: 63%/731 -
🟩 thrust: Pass: 100%/109 | Total: 2d 19h | Avg: 36m 59s | Max: 1h 26m | Hits: 72%/13180
🟩 cpu 🟩 amd64 Pass: 100%/101 | Total: 2d 14h | Avg: 37m 21s | Max: 1h 26m | Hits: 72%/13180 🟩 arm64 Pass: 100%/8 | Total: 4h 18m | Avg: 32m 17s | Max: 39m 00s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 8h 51m | Avg: 35m 25s | Max: 1h 06m | Hits: 67%/2636 🟩 11.8 Pass: 100%/3 | Total: 2h 11m | Avg: 43m 42s | Max: 48m 05s 🟩 12.5 Pass: 100%/4 | Total: 5h 17m | Avg: 1h 19m | Max: 1h 26m 🟩 12.6 Pass: 100%/87 | Total: 2d 02h | Avg: 35m 04s | Max: 1h 18m | Hits: 73%/10544 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/4 | Total: 1h 47m | Avg: 26m 58s | Max: 29m 40s 🟩 nvcc11.1 Pass: 100%/15 | Total: 8h 51m | Avg: 35m 25s | Max: 1h 06m | Hits: 67%/2636 🟩 nvcc11.8 Pass: 100%/3 | Total: 2h 11m | Avg: 43m 42s | Max: 48m 05s 🟩 nvcc12.5 Pass: 100%/4 | Total: 5h 17m | Avg: 1h 19m | Max: 1h 26m 🟩 nvcc12.6 Pass: 100%/83 | Total: 2d 01h | Avg: 35m 27s | Max: 1h 18m | Hits: 73%/10544 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/4 | Total: 1h 47m | Avg: 26m 58s | Max: 29m 40s 🟩 nvcc Pass: 100%/105 | Total: 2d 17h | Avg: 37m 22s | Max: 1h 26m | Hits: 72%/13180 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 3h 34m | Avg: 35m 45s | Max: 41m 50s 🟩 Clang10 Pass: 100%/3 | Total: 1h 58m | Avg: 39m 23s | Max: 44m 31s 🟩 Clang11 Pass: 100%/4 | Total: 2h 24m | Avg: 36m 05s | Max: 40m 06s 🟩 Clang12 Pass: 100%/4 | Total: 2h 32m | Avg: 38m 09s | Max: 46m 15s 🟩 Clang13 Pass: 100%/4 | Total: 2h 15m | Avg: 33m 59s | Max: 37m 35s 🟩 Clang14 Pass: 100%/4 | Total: 2h 29m | Avg: 37m 16s | Max: 40m 58s 🟩 Clang15 Pass: 100%/4 | Total: 2h 26m | Avg: 36m 41s | Max: 40m 27s 🟩 Clang16 Pass: 100%/4 | Total: 2h 24m | Avg: 36m 00s | Max: 41m 35s 🟩 Clang17 Pass: 100%/4 | Total: 2h 22m | Avg: 35m 36s | Max: 42m 05s 🟩 Clang18 Pass: 100%/11 | Total: 5h 07m | Avg: 27m 59s | Max: 42m 13s 🟩 GCC6 Pass: 100%/2 | Total: 1h 01m | Avg: 30m 32s | Max: 34m 36s 🟩 GCC7 Pass: 100%/6 | Total: 3h 28m | Avg: 34m 45s | Max: 42m 05s 🟩 GCC8 Pass: 100%/6 | Total: 3h 26m | Avg: 34m 27s | Max: 41m 11s 🟩 GCC9 Pass: 100%/6 | Total: 3h 31m | Avg: 35m 10s | Max: 39m 30s 🟩 GCC10 Pass: 100%/4 | Total: 2h 28m | Avg: 37m 12s | Max: 43m 13s 🟩 GCC11 Pass: 100%/7 | Total: 4h 45m | Avg: 40m 49s | Max: 48m 05s 🟩 GCC12 Pass: 100%/4 | Total: 2h 44m | Avg: 41m 10s | Max: 47m 09s 🟩 GCC13 Pass: 100%/14 | Total: 5h 41m | Avg: 24m 23s | Max: 40m 55s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 12m | Avg: 44m 11s | Max: 47m 56s 🟩 MSVC14.16 Pass: 100%/1 | Total: 1h 06m | Avg: 1h 06m | Max: 1h 06m | Hits: 67%/2636 🟩 MSVC14.29 Pass: 100%/2 | Total: 2h 09m | Avg: 1h 04m | Max: 1h 06m | Hits: 63%/5272 🟩 MSVC14.39 Pass: 100%/2 | Total: 1h 41m | Avg: 50m 35s | Max: 1h 18m | Hits: 83%/5272 🟩 NVHPC24.7 Pass: 100%/4 | Total: 5h 17m | Avg: 1h 19m | Max: 1h 26m 🟩 cxx_family 🟩 Clang Pass: 100%/48 | Total: 1d 03h | Avg: 34m 29s | Max: 46m 15s 🟩 GCC Pass: 100%/49 | Total: 1d 03h | Avg: 33m 13s | Max: 48m 05s 🟩 Intel Pass: 100%/3 | Total: 2h 12m | Avg: 44m 11s | Max: 47m 56s 🟩 MSVC Pass: 100%/5 | Total: 4h 57m | Avg: 59m 27s | Max: 1h 18m | Hits: 72%/13180 🟩 NVHPC Pass: 100%/4 | Total: 5h 17m | Avg: 1h 19m | Max: 1h 26m 🟩 gpu 🟩 v100 Pass: 100%/109 | Total: 2d 19h | Avg: 36m 59s | Max: 1h 26m | Hits: 72%/13180 🟩 jobs 🟩 Build Pass: 100%/102 | Total: 2d 17h | Avg: 38m 30s | Max: 1h 26m | Hits: 65%/10544 🟩 TestCPU Pass: 100%/4 | Total: 47m 00s | Avg: 11m 45s | Max: 22m 50s | Hits: 99%/2636 🟩 TestGPU Pass: 100%/3 | Total: 56m 02s | Avg: 18m 40s | Max: 27m 46s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 2h 11m | Avg: 43m 42s | Max: 48m 05s 🟩 90a Pass: 100%/4 | Total: 1h 26m | Avg: 21m 37s | Max: 25m 34s 🟩 std 🟩 11 Pass: 100%/30 | Total: 14h 35m | Avg: 29m 10s | Max: 1h 05m 🟩 14 Pass: 100%/29 | Total: 19h 40m | Avg: 40m 42s | Max: 1h 22m | Hits: 67%/5272 🟩 17 Pass: 100%/27 | Total: 18h 35m | Avg: 41m 19s | Max: 1h 23m | Hits: 58%/2636 🟩 20 Pass: 100%/23 | Total: 14h 20m | Avg: 37m 23s | Max: 1h 26m | Hits: 83%/5272 -
🟩 cudax: Pass: 100%/54 | Total: 4h 48m | Avg: 5m 20s | Max: 19m 27s | Hits: 87%/224
🟩 cpu 🟩 amd64 Pass: 100%/50 | Total: 4h 35m | Avg: 5m 30s | Max: 19m 27s | Hits: 87%/224 🟩 arm64 Pass: 100%/4 | Total: 13m 34s | Avg: 3m 23s | Max: 3m 30s 🟩 ctk 🟩 12.0 Pass: 100%/19 | Total: 1h 43m | Avg: 5m 25s | Max: 19m 04s | Hits: 87%/112 🟩 12.5 Pass: 100%/2 | Total: 11m 50s | Avg: 5m 55s | Max: 6m 09s 🟩 12.6 Pass: 100%/33 | Total: 2h 53m | Avg: 5m 15s | Max: 19m 27s | Hits: 87%/112 🟩 cudacxx 🟩 nvcc12.0 Pass: 100%/19 | Total: 1h 43m | Avg: 5m 25s | Max: 19m 04s | Hits: 87%/112 🟩 nvcc12.5 Pass: 100%/2 | Total: 11m 50s | Avg: 5m 55s | Max: 6m 09s 🟩 nvcc12.6 Pass: 100%/33 | Total: 2h 53m | Avg: 5m 15s | Max: 19m 27s | Hits: 87%/112 🟩 cudacxx_family 🟩 nvcc Pass: 100%/54 | Total: 4h 48m | Avg: 5m 20s | Max: 19m 27s | Hits: 87%/224 🟩 cxx 🟩 Clang9 Pass: 100%/2 | Total: 8m 30s | Avg: 4m 15s | Max: 4m 24s 🟩 Clang10 Pass: 100%/2 | Total: 8m 04s | Avg: 4m 02s | Max: 4m 18s 🟩 Clang11 Pass: 100%/4 | Total: 14m 23s | Avg: 3m 35s | Max: 3m 45s 🟩 Clang12 Pass: 100%/4 | Total: 14m 56s | Avg: 3m 44s | Max: 3m 53s 🟩 Clang13 Pass: 100%/4 | Total: 14m 52s | Avg: 3m 43s | Max: 4m 01s 🟩 Clang14 Pass: 100%/4 | Total: 28m 33s | Avg: 7m 08s | Max: 17m 11s 🟩 Clang15 Pass: 100%/2 | Total: 7m 31s | Avg: 3m 45s | Max: 3m 48s 🟩 Clang16 Pass: 100%/4 | Total: 14m 35s | Avg: 3m 38s | Max: 4m 06s 🟩 Clang17 Pass: 100%/2 | Total: 8m 06s | Avg: 4m 03s | Max: 4m 16s 🟩 Clang18 Pass: 100%/2 | Total: 21m 54s | Avg: 10m 57s | Max: 17m 58s 🟩 GCC9 Pass: 100%/2 | Total: 7m 30s | Avg: 3m 45s | Max: 3m 48s 🟩 GCC10 Pass: 100%/4 | Total: 15m 08s | Avg: 3m 47s | Max: 3m 56s 🟩 GCC11 Pass: 100%/4 | Total: 14m 59s | Avg: 3m 44s | Max: 3m 56s 🟩 GCC12 Pass: 100%/7 | Total: 1h 10m | Avg: 10m 00s | Max: 19m 27s 🟩 GCC13 Pass: 100%/3 | Total: 10m 09s | Avg: 3m 23s | Max: 3m 30s 🟩 MSVC14.36 Pass: 100%/1 | Total: 8m 45s | Avg: 8m 45s | Max: 8m 45s | Hits: 87%/112 🟩 MSVC14.39 Pass: 100%/1 | Total: 9m 01s | Avg: 9m 01s | Max: 9m 01s | Hits: 87%/112 🟩 NVHPC24.7 Pass: 100%/2 | Total: 11m 50s | Avg: 5m 55s | Max: 6m 09s 🟩 cxx_family 🟩 Clang Pass: 100%/30 | Total: 2h 21m | Avg: 4m 42s | Max: 17m 58s 🟩 GCC Pass: 100%/20 | Total: 1h 57m | Avg: 5m 53s | Max: 19m 27s 🟩 MSVC Pass: 100%/2 | Total: 17m 46s | Avg: 8m 53s | Max: 9m 01s | Hits: 87%/224 🟩 NVHPC Pass: 100%/2 | Total: 11m 50s | Avg: 5m 55s | Max: 6m 09s 🟩 gpu 🟩 v100 Pass: 100%/54 | Total: 4h 48m | Avg: 5m 20s | Max: 19m 27s | Hits: 87%/224 🟩 jobs 🟩 Build Pass: 100%/49 | Total: 3h 17m | Avg: 4m 02s | Max: 9m 01s | Hits: 87%/224 🟩 Test Pass: 100%/5 | Total: 1h 30m | Avg: 18m 11s | Max: 19m 27s 🟩 sm 🟩 90 Pass: 100%/1 | Total: 3m 01s | Avg: 3m 01s | Max: 3m 01s 🟩 90a Pass: 100%/1 | Total: 3m 15s | Avg: 3m 15s | Max: 3m 15s 🟩 std 🟩 17 Pass: 100%/29 | Total: 2h 21m | Avg: 4m 52s | Max: 19m 27s 🟩 20 Pass: 100%/25 | Total: 2h 27m | Avg: 5m 54s | Max: 17m 58s | Hits: 87%/224 -
🟩 cccl_c_parallel: Pass: 100%/2 | Total: 11m 33s | Avg: 5m 46s | Max: 9m 17s
🟩 cpu 🟩 amd64 Pass: 100%/2 | Total: 11m 33s | Avg: 5m 46s | Max: 9m 17s 🟩 ctk 🟩 12.6 Pass: 100%/2 | Total: 11m 33s | Avg: 5m 46s | Max: 9m 17s 🟩 cudacxx 🟩 nvcc12.6 Pass: 100%/2 | Total: 11m 33s | Avg: 5m 46s | Max: 9m 17s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/2 | Total: 11m 33s | Avg: 5m 46s | Max: 9m 17s 🟩 cxx 🟩 GCC13 Pass: 100%/2 | Total: 11m 33s | Avg: 5m 46s | Max: 9m 17s 🟩 cxx_family 🟩 GCC Pass: 100%/2 | Total: 11m 33s | Avg: 5m 46s | Max: 9m 17s 🟩 gpu 🟩 v100 Pass: 100%/2 | Total: 11m 33s | Avg: 5m 46s | Max: 9m 17s 🟩 jobs 🟩 Build Pass: 100%/1 | Total: 2m 16s | Avg: 2m 16s | Max: 2m 16s 🟩 Test Pass: 100%/1 | Total: 9m 17s | Avg: 9m 17s | Max: 9m 17s -
🟩 python: Pass: 100%/1 | Total: 16m 38s | Avg: 16m 38s | Max: 16m 38s
🟩 cpu 🟩 amd64 Pass: 100%/1 | Total: 16m 38s | Avg: 16m 38s | Max: 16m 38s 🟩 ctk 🟩 12.6 Pass: 100%/1 | Total: 16m 38s | Avg: 16m 38s | Max: 16m 38s 🟩 cudacxx 🟩 nvcc12.6 Pass: 100%/1 | Total: 16m 38s | Avg: 16m 38s | Max: 16m 38s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/1 | Total: 16m 38s | Avg: 16m 38s | Max: 16m 38s 🟩 cxx 🟩 GCC13 Pass: 100%/1 | Total: 16m 38s | Avg: 16m 38s | Max: 16m 38s 🟩 cxx_family 🟩 GCC Pass: 100%/1 | Total: 16m 38s | Avg: 16m 38s | Max: 16m 38s 🟩 gpu 🟩 v100 Pass: 100%/1 | Total: 16m 38s | Avg: 16m 38s | Max: 16m 38s 🟩 jobs 🟩 Test Pass: 100%/1 | Total: 16m 38s | Avg: 16m 38s | Max: 16m 38s
👃 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: 394)
| # | Runner |
|---|---|
| 326 | linux-amd64-cpu16 |
| 28 | linux-arm64-cpu16 |
| 25 | linux-amd64-gpu-v100-latest-1 |
| 15 | windows-amd64-cpu16 |
🟨 CI finished in 1h 55m: Pass: 99%/394 | Total: 8d 00h | Avg: 29m 20s | Max: 1h 11m | Hits: 46%/25812
-
🟨 cub: Pass: 99%/110 | Total: 3d 20h | Avg: 50m 34s | Max: 1h 11m | Hits: 63%/2924
🔍 cpu: amd64 🔍 🔍 amd64 Pass: 99%/102 | Total: 3d 13h | Avg: 50m 02s | Max: 1h 11m | Hits: 63%/2924 🟩 arm64 Pass: 100%/8 | Total: 7h 39m | Avg: 57m 23s | Max: 1h 02m 🔍 ctk: 12.6 🔍 🟩 11.1 Pass: 100%/15 | Total: 11h 37m | Avg: 46m 28s | Max: 50m 46s | Hits: 63%/731 🟩 11.8 Pass: 100%/3 | Total: 3h 27m | Avg: 1h 09m | Max: 1h 11m 🟩 12.5 Pass: 100%/4 | Total: 4h 04m | Avg: 1h 01m | Max: 1h 04m 🔍 12.6 Pass: 98%/88 | Total: 3d 01h | Avg: 50m 09s | Max: 1h 02m | Hits: 63%/2193 🔍 cudacxx: nvcc12.6 🔍 🟩 ClangCUDA18 Pass: 100%/4 | Total: 3h 50m | Avg: 57m 42s | Max: 1h 01m 🟩 nvcc11.1 Pass: 100%/15 | Total: 11h 37m | Avg: 46m 28s | Max: 50m 46s | Hits: 63%/731 🟩 nvcc11.8 Pass: 100%/3 | Total: 3h 27m | Avg: 1h 09m | Max: 1h 11m 🟩 nvcc12.5 Pass: 100%/4 | Total: 4h 04m | Avg: 1h 01m | Max: 1h 04m 🔍 nvcc12.6 Pass: 98%/84 | Total: 2d 21h | Avg: 49m 48s | Max: 1h 02m | Hits: 63%/2193 🔍 cudacxx_family: nvcc 🔍 🟩 ClangCUDA Pass: 100%/4 | Total: 3h 50m | Avg: 57m 42s | Max: 1h 01m 🔍 nvcc Pass: 99%/106 | Total: 3d 16h | Avg: 50m 18s | Max: 1h 11m | Hits: 63%/2924 🔍 cxx: GCC13 🔍 🟩 Clang9 Pass: 100%/6 | Total: 4h 56m | Avg: 49m 29s | Max: 57m 33s 🟩 Clang10 Pass: 100%/3 | Total: 2h 33m | Avg: 51m 13s | Max: 51m 51s 🟩 Clang11 Pass: 100%/4 | Total: 3h 30m | Avg: 52m 38s | Max: 55m 01s 🟩 Clang12 Pass: 100%/4 | Total: 3h 41m | Avg: 55m 16s | Max: 59m 01s 🟩 Clang13 Pass: 100%/4 | Total: 3h 29m | Avg: 52m 28s | Max: 55m 38s 🟩 Clang14 Pass: 100%/4 | Total: 3h 33m | Avg: 53m 28s | Max: 57m 49s 🟩 Clang15 Pass: 100%/4 | Total: 3h 41m | Avg: 55m 26s | Max: 58m 04s 🟩 Clang16 Pass: 100%/4 | Total: 3h 22m | Avg: 50m 39s | Max: 52m 37s 🟩 Clang17 Pass: 100%/4 | Total: 3h 28m | Avg: 52m 04s | Max: 56m 25s 🟩 Clang18 Pass: 100%/11 | Total: 9h 39m | Avg: 52m 41s | Max: 1h 01m 🟩 GCC6 Pass: 100%/2 | Total: 1h 33m | Avg: 46m 45s | Max: 49m 35s 🟩 GCC7 Pass: 100%/6 | Total: 5h 09m | Avg: 51m 34s | Max: 56m 37s 🟩 GCC8 Pass: 100%/6 | Total: 4h 50m | Avg: 48m 25s | Max: 55m 14s 🟩 GCC9 Pass: 100%/6 | Total: 4h 52m | Avg: 48m 42s | Max: 52m 36s 🟩 GCC10 Pass: 100%/4 | Total: 3h 34m | Avg: 53m 36s | Max: 55m 57s 🟩 GCC11 Pass: 100%/7 | Total: 7h 07m | Avg: 1h 01m | Max: 1h 11m 🟩 GCC12 Pass: 100%/4 | Total: 3h 27m | Avg: 51m 47s | Max: 54m 06s 🔍 GCC13 Pass: 93%/16 | Total: 9h 26m | Avg: 35m 25s | Max: 1h 02m 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 57m | Avg: 59m 18s | Max: 1h 01m 🟩 MSVC14.16 Pass: 100%/1 | Total: 50m 08s | Avg: 50m 08s | Max: 50m 08s | Hits: 63%/731 🟩 MSVC14.29 Pass: 100%/2 | Total: 1h 53m | Avg: 56m 39s | Max: 57m 28s | Hits: 63%/1462 🟩 MSVC14.39 Pass: 100%/1 | Total: 57m 09s | Avg: 57m 09s | Max: 57m 09s | Hits: 63%/731 🟩 NVHPC24.7 Pass: 100%/4 | Total: 4h 04m | Avg: 1h 01m | Max: 1h 04m 🔍 cxx_family: GCC 🔍 🟩 Clang Pass: 100%/48 | Total: 1d 17h | Avg: 52m 28s | Max: 1h 01m 🔍 GCC Pass: 98%/51 | Total: 1d 16h | Avg: 47m 05s | Max: 1h 11m 🟩 Intel Pass: 100%/3 | Total: 2h 57m | Avg: 59m 18s | Max: 1h 01m 🟩 MSVC Pass: 100%/4 | Total: 3h 40m | Avg: 55m 08s | Max: 57m 28s | Hits: 63%/2924 🟩 NVHPC Pass: 100%/4 | Total: 4h 04m | Avg: 1h 01m | Max: 1h 04m 🔍 jobs: TestGPU 🔍 🟩 Build Pass: 100%/102 | Total: 3d 17h | Avg: 52m 35s | Max: 1h 11m | Hits: 63%/2924 🟩 DeviceLaunch Pass: 100%/1 | Total: 18m 00s | Avg: 18m 00s | Max: 18m 00s 🟩 GraphCapture Pass: 100%/1 | Total: 32m 12s | Avg: 32m 12s | Max: 32m 12s 🟩 HostLaunch Pass: 100%/3 | Total: 1h 17m | Avg: 25m 42s | Max: 37m 08s 🔍 TestGPU Pass: 66%/3 | Total: 1h 11m | Avg: 23m 44s | Max: 32m 45s 🔍 std: 20 🔍 🟩 11 Pass: 100%/30 | Total: 1d 01h | Avg: 50m 16s | Max: 1h 11m 🟩 14 Pass: 100%/29 | Total: 1d 01h | Avg: 52m 08s | Max: 1h 05m | Hits: 63%/1462 🟩 17 Pass: 100%/27 | Total: 23h 47m | Avg: 52m 52s | Max: 1h 10m | Hits: 63%/731 🔍 20 Pass: 95%/24 | Total: 18h 35m | Avg: 46m 27s | Max: 1h 02m | Hits: 63%/731 🟨 gpu 🟨 v100 Pass: 99%/110 | Total: 3d 20h | Avg: 50m 34s | Max: 1h 11m | Hits: 63%/2924 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 3h 27m | Avg: 1h 09m | Max: 1h 11m 🟩 90a Pass: 100%/4 | Total: 1h 31m | Avg: 22m 57s | Max: 24m 40s -
🟩 libcudacxx: Pass: 100%/118 | Total: 1d 00h | Avg: 12m 16s | Max: 50m 29s | Hits: 3%/9484
🟩 cpu 🟩 amd64 Pass: 100%/110 | Total: 22h 46m | Avg: 12m 25s | Max: 50m 29s | Hits: 3%/9484 🟩 arm64 Pass: 100%/8 | Total: 1h 21m | Avg: 10m 11s | Max: 22m 08s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 1h 43m | Avg: 6m 52s | Max: 36m 25s | Hits: 3%/2177 🟩 11.8 Pass: 100%/3 | Total: 54m 24s | Avg: 18m 08s | Max: 31m 04s 🟩 12.5 Pass: 100%/4 | Total: 2h 48m | Avg: 42m 12s | Max: 50m 29s 🟩 12.6 Pass: 100%/96 | Total: 18h 41m | Avg: 11m 40s | Max: 50m 26s | Hits: 3%/7307 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/12 | Total: 2h 31m | Avg: 12m 36s | Max: 19m 30s 🟩 nvcc11.1 Pass: 100%/15 | Total: 1h 43m | Avg: 6m 52s | Max: 36m 25s | Hits: 3%/2177 🟩 nvcc11.8 Pass: 100%/3 | Total: 54m 24s | Avg: 18m 08s | Max: 31m 04s 🟩 nvcc12.5 Pass: 100%/4 | Total: 2h 48m | Avg: 42m 12s | Max: 50m 29s 🟩 nvcc12.6 Pass: 100%/84 | Total: 16h 10m | Avg: 11m 33s | Max: 50m 26s | Hits: 3%/7307 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/12 | Total: 2h 31m | Avg: 12m 36s | Max: 19m 30s 🟩 nvcc Pass: 100%/106 | Total: 21h 36m | Avg: 12m 13s | Max: 50m 29s | Hits: 3%/9484 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 1h 01m | Avg: 10m 15s | Max: 24m 30s 🟩 Clang10 Pass: 100%/3 | Total: 24m 31s | Avg: 8m 10s | Max: 11m 38s 🟩 Clang11 Pass: 100%/4 | Total: 19m 57s | Avg: 4m 59s | Max: 5m 22s 🟩 Clang12 Pass: 100%/4 | Total: 20m 44s | Avg: 5m 11s | Max: 5m 57s 🟩 Clang13 Pass: 100%/4 | Total: 21m 28s | Avg: 5m 22s | Max: 6m 00s 🟩 Clang14 Pass: 100%/4 | Total: 19m 26s | Avg: 4m 51s | Max: 5m 32s 🟩 Clang15 Pass: 100%/4 | Total: 29m 28s | Avg: 7m 22s | Max: 14m 36s 🟩 Clang16 Pass: 100%/4 | Total: 1h 18m | Avg: 19m 42s | Max: 29m 41s 🟩 Clang17 Pass: 100%/4 | Total: 57m 04s | Avg: 14m 16s | Max: 27m 02s 🟩 Clang18 Pass: 100%/18 | Total: 3h 27m | Avg: 11m 31s | Max: 19m 30s 🟩 GCC6 Pass: 100%/2 | Total: 5m 46s | Avg: 2m 53s | Max: 3m 01s 🟩 GCC7 Pass: 100%/6 | Total: 19m 58s | Avg: 3m 19s | Max: 3m 58s 🟩 GCC8 Pass: 100%/6 | Total: 53m 24s | Avg: 8m 54s | Max: 21m 00s 🟩 GCC9 Pass: 100%/6 | Total: 37m 47s | Avg: 6m 17s | Max: 18m 47s 🟩 GCC10 Pass: 100%/4 | Total: 37m 23s | Avg: 9m 20s | Max: 25m 17s 🟩 GCC11 Pass: 100%/7 | Total: 1h 10m | Avg: 10m 00s | Max: 31m 04s 🟩 GCC12 Pass: 100%/4 | Total: 35m 10s | Avg: 8m 47s | Max: 22m 47s 🟩 GCC13 Pass: 100%/17 | Total: 3h 42m | Avg: 13m 05s | Max: 28m 11s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 1h 36m | Avg: 32m 06s | Max: 37m 35s 🟩 MSVC14.16 Pass: 100%/1 | Total: 36m 25s | Avg: 36m 25s | Max: 36m 25s | Hits: 3%/2177 🟩 MSVC14.29 Pass: 100%/2 | Total: 1h 13m | Avg: 36m 35s | Max: 39m 15s | Hits: 3%/4717 🟩 MSVC14.39 Pass: 100%/1 | Total: 50m 26s | Avg: 50m 26s | Max: 50m 26s | Hits: 3%/2590 🟩 NVHPC24.7 Pass: 100%/4 | Total: 2h 48m | Avg: 42m 12s | Max: 50m 29s 🟩 cxx_family 🟩 Clang Pass: 100%/55 | Total: 9h 00m | Avg: 9m 49s | Max: 29m 41s 🟩 GCC Pass: 100%/52 | Total: 8h 02m | Avg: 9m 16s | Max: 31m 04s 🟩 Intel Pass: 100%/3 | Total: 1h 36m | Avg: 32m 06s | Max: 37m 35s 🟩 MSVC Pass: 100%/4 | Total: 2h 40m | Avg: 40m 00s | Max: 50m 26s | Hits: 3%/9484 🟩 NVHPC Pass: 100%/4 | Total: 2h 48m | Avg: 42m 12s | Max: 50m 29s 🟩 gpu 🟩 v100 Pass: 100%/118 | Total: 1d 00h | Avg: 12m 16s | Max: 50m 29s | Hits: 3%/9484 🟩 jobs 🟩 Build Pass: 100%/110 | Total: 21h 39m | Avg: 11m 48s | Max: 50m 29s | Hits: 3%/9484 🟩 NVRTC Pass: 100%/4 | Total: 1h 35m | Avg: 23m 55s | Max: 28m 11s 🟩 Test Pass: 100%/3 | Total: 50m 50s | Avg: 16m 56s | Max: 21m 05s 🟩 VerifyCodegen Pass: 100%/1 | Total: 2m 03s | Avg: 2m 03s | Max: 2m 03s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 54m 24s | Avg: 18m 08s | Max: 31m 04s 🟩 90 Pass: 100%/4 | Total: 43m 08s | Avg: 10m 47s | Max: 14m 14s 🟩 90a Pass: 100%/8 | Total: 59m 17s | Avg: 7m 24s | Max: 12m 48s 🟩 std 🟩 11 Pass: 100%/32 | Total: 4h 39m | Avg: 8m 44s | Max: 29m 56s 🟩 14 Pass: 100%/32 | Total: 6h 32m | Avg: 12m 16s | Max: 40m 35s | Hits: 3%/4457 🟩 17 Pass: 100%/30 | Total: 6h 52m | Avg: 13m 44s | Max: 47m 49s | Hits: 3%/2437 🟩 20 Pass: 100%/23 | Total: 6h 01m | Avg: 15m 41s | Max: 50m 29s | Hits: 3%/2590 -
🟩 thrust: Pass: 100%/109 | Total: 2d 15h | Avg: 34m 54s | Max: 1h 07m | Hits: 74%/13180
🟩 cpu 🟩 amd64 Pass: 100%/101 | Total: 2d 10h | Avg: 34m 59s | Max: 1h 07m | Hits: 74%/13180 🟩 arm64 Pass: 100%/8 | Total: 4h 30m | Avg: 33m 48s | Max: 40m 04s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 8h 09m | Avg: 32m 36s | Max: 55m 33s | Hits: 68%/2636 🟩 11.8 Pass: 100%/3 | Total: 2h 06m | Avg: 42m 14s | Max: 47m 16s 🟩 12.5 Pass: 100%/4 | Total: 3h 51m | Avg: 57m 57s | Max: 1h 03m 🟩 12.6 Pass: 100%/87 | Total: 2d 01h | Avg: 33m 59s | Max: 1h 07m | Hits: 76%/10544 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/4 | Total: 1h 56m | Avg: 29m 00s | Max: 33m 19s 🟩 nvcc11.1 Pass: 100%/15 | Total: 8h 09m | Avg: 32m 36s | Max: 55m 33s | Hits: 68%/2636 🟩 nvcc11.8 Pass: 100%/3 | Total: 2h 06m | Avg: 42m 14s | Max: 47m 16s 🟩 nvcc12.5 Pass: 100%/4 | Total: 3h 51m | Avg: 57m 57s | Max: 1h 03m 🟩 nvcc12.6 Pass: 100%/83 | Total: 1d 23h | Avg: 34m 13s | Max: 1h 07m | Hits: 76%/10544 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/4 | Total: 1h 56m | Avg: 29m 00s | Max: 33m 19s 🟩 nvcc Pass: 100%/105 | Total: 2d 13h | Avg: 35m 07s | Max: 1h 07m | Hits: 74%/13180 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 3h 14m | Avg: 32m 26s | Max: 42m 06s 🟩 Clang10 Pass: 100%/3 | Total: 1h 49m | Avg: 36m 39s | Max: 40m 31s 🟩 Clang11 Pass: 100%/4 | Total: 2h 17m | Avg: 34m 26s | Max: 37m 24s 🟩 Clang12 Pass: 100%/4 | Total: 2h 19m | Avg: 34m 52s | Max: 40m 13s 🟩 Clang13 Pass: 100%/4 | Total: 2h 19m | Avg: 34m 54s | Max: 38m 10s 🟩 Clang14 Pass: 100%/4 | Total: 2h 21m | Avg: 35m 27s | Max: 37m 25s 🟩 Clang15 Pass: 100%/4 | Total: 2h 19m | Avg: 34m 52s | Max: 38m 00s 🟩 Clang16 Pass: 100%/4 | Total: 2h 26m | Avg: 36m 42s | Max: 38m 54s 🟩 Clang17 Pass: 100%/4 | Total: 2h 24m | Avg: 36m 06s | Max: 40m 53s 🟩 Clang18 Pass: 100%/11 | Total: 4h 58m | Avg: 27m 09s | Max: 35m 45s 🟩 GCC6 Pass: 100%/2 | Total: 58m 54s | Avg: 29m 27s | Max: 33m 38s 🟩 GCC7 Pass: 100%/6 | Total: 3h 24m | Avg: 34m 06s | Max: 40m 16s 🟩 GCC8 Pass: 100%/6 | Total: 3h 14m | Avg: 32m 26s | Max: 36m 19s 🟩 GCC9 Pass: 100%/6 | Total: 3h 21m | Avg: 33m 30s | Max: 40m 52s 🟩 GCC10 Pass: 100%/4 | Total: 2h 28m | Avg: 37m 13s | Max: 42m 05s 🟩 GCC11 Pass: 100%/7 | Total: 4h 37m | Avg: 39m 42s | Max: 47m 16s 🟩 GCC12 Pass: 100%/4 | Total: 2h 32m | Avg: 38m 13s | Max: 44m 31s 🟩 GCC13 Pass: 100%/14 | Total: 5h 47m | Avg: 24m 49s | Max: 41m 11s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 11m | Avg: 43m 52s | Max: 49m 17s 🟩 MSVC14.16 Pass: 100%/1 | Total: 55m 33s | Avg: 55m 33s | Max: 55m 33s | Hits: 68%/2636 🟩 MSVC14.29 Pass: 100%/2 | Total: 1h 54m | Avg: 57m 26s | Max: 1h 00m | Hits: 68%/5272 🟩 MSVC14.39 Pass: 100%/2 | Total: 1h 31m | Avg: 45m 49s | Max: 1h 07m | Hits: 84%/5272 🟩 NVHPC24.7 Pass: 100%/4 | Total: 3h 51m | Avg: 57m 57s | Max: 1h 03m 🟩 cxx_family 🟩 Clang Pass: 100%/48 | Total: 1d 02h | Avg: 33m 10s | Max: 42m 06s 🟩 GCC Pass: 100%/49 | Total: 1d 02h | Avg: 32m 22s | Max: 47m 16s 🟩 Intel Pass: 100%/3 | Total: 2h 11m | Avg: 43m 52s | Max: 49m 17s 🟩 MSVC Pass: 100%/5 | Total: 4h 22m | Avg: 52m 24s | Max: 1h 07m | Hits: 74%/13180 🟩 NVHPC Pass: 100%/4 | Total: 3h 51m | Avg: 57m 57s | Max: 1h 03m 🟩 gpu 🟩 v100 Pass: 100%/109 | Total: 2d 15h | Avg: 34m 54s | Max: 1h 07m | Hits: 74%/13180 🟩 jobs 🟩 Build Pass: 100%/102 | Total: 2d 13h | Avg: 36m 25s | Max: 1h 07m | Hits: 68%/10544 🟩 TestCPU Pass: 100%/4 | Total: 47m 37s | Avg: 11m 54s | Max: 23m 44s | Hits: 99%/2636 🟩 TestGPU Pass: 100%/3 | Total: 41m 20s | Avg: 13m 46s | Max: 15m 19s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 2h 06m | Avg: 42m 14s | Max: 47m 16s 🟩 90a Pass: 100%/4 | Total: 1h 22m | Avg: 20m 33s | Max: 22m 58s 🟩 std 🟩 11 Pass: 100%/30 | Total: 14h 09m | Avg: 28m 19s | Max: 47m 00s 🟩 14 Pass: 100%/29 | Total: 18h 12m | Avg: 37m 40s | Max: 1h 02m | Hits: 68%/5272 🟩 17 Pass: 100%/27 | Total: 17h 51m | Avg: 39m 40s | Max: 1h 00m | Hits: 68%/2636 🟩 20 Pass: 100%/23 | Total: 13h 11m | Avg: 34m 23s | Max: 1h 07m | Hits: 84%/5272 -
🟩 cudax: Pass: 100%/54 | Total: 12h 02m | Avg: 13m 22s | Max: 23m 40s | Hits: 2%/224
🟩 cpu 🟩 amd64 Pass: 100%/50 | Total: 11h 06m | Avg: 13m 19s | Max: 23m 40s | Hits: 2%/224 🟩 arm64 Pass: 100%/4 | Total: 56m 08s | Avg: 14m 02s | Max: 14m 45s 🟩 ctk 🟩 12.0 Pass: 100%/19 | Total: 4h 09m | Avg: 13m 08s | Max: 23m 40s | Hits: 2%/112 🟩 12.5 Pass: 100%/2 | Total: 16m 53s | Avg: 8m 26s | Max: 8m 33s 🟩 12.6 Pass: 100%/33 | Total: 7h 35m | Avg: 13m 48s | Max: 21m 21s | Hits: 2%/112 🟩 cudacxx 🟩 nvcc12.0 Pass: 100%/19 | Total: 4h 09m | Avg: 13m 08s | Max: 23m 40s | Hits: 2%/112 🟩 nvcc12.5 Pass: 100%/2 | Total: 16m 53s | Avg: 8m 26s | Max: 8m 33s 🟩 nvcc12.6 Pass: 100%/33 | Total: 7h 35m | Avg: 13m 48s | Max: 21m 21s | Hits: 2%/112 🟩 cudacxx_family 🟩 nvcc Pass: 100%/54 | Total: 12h 02m | Avg: 13m 22s | Max: 23m 40s | Hits: 2%/224 🟩 cxx 🟩 Clang9 Pass: 100%/2 | Total: 27m 51s | Avg: 13m 55s | Max: 13m 56s 🟩 Clang10 Pass: 100%/2 | Total: 28m 47s | Avg: 14m 23s | Max: 16m 00s 🟩 Clang11 Pass: 100%/4 | Total: 57m 27s | Avg: 14m 21s | Max: 15m 54s 🟩 Clang12 Pass: 100%/4 | Total: 56m 25s | Avg: 14m 06s | Max: 15m 37s 🟩 Clang13 Pass: 100%/4 | Total: 53m 23s | Avg: 13m 20s | Max: 14m 14s 🟩 Clang14 Pass: 100%/4 | Total: 50m 22s | Avg: 12m 35s | Max: 18m 17s 🟩 Clang15 Pass: 100%/2 | Total: 30m 02s | Avg: 15m 01s | Max: 16m 19s 🟩 Clang16 Pass: 100%/4 | Total: 1h 00m | Avg: 15m 01s | Max: 16m 37s 🟩 Clang17 Pass: 100%/2 | Total: 30m 03s | Avg: 15m 01s | Max: 16m 31s 🟩 Clang18 Pass: 100%/2 | Total: 21m 38s | Avg: 10m 49s | Max: 17m 58s 🟩 GCC9 Pass: 100%/2 | Total: 27m 50s | Avg: 13m 55s | Max: 14m 51s 🟩 GCC10 Pass: 100%/4 | Total: 56m 46s | Avg: 14m 11s | Max: 14m 44s 🟩 GCC11 Pass: 100%/4 | Total: 58m 48s | Avg: 14m 42s | Max: 15m 20s 🟩 GCC12 Pass: 100%/7 | Total: 1h 27m | Avg: 12m 30s | Max: 23m 40s 🟩 GCC13 Pass: 100%/3 | Total: 39m 34s | Avg: 13m 11s | Max: 14m 45s 🟩 MSVC14.36 Pass: 100%/1 | Total: 9m 16s | Avg: 9m 16s | Max: 9m 16s | Hits: 2%/112 🟩 MSVC14.39 Pass: 100%/1 | Total: 9m 30s | Avg: 9m 30s | Max: 9m 30s | Hits: 2%/112 🟩 NVHPC24.7 Pass: 100%/2 | Total: 16m 53s | Avg: 8m 26s | Max: 8m 33s 🟩 cxx_family 🟩 Clang Pass: 100%/30 | Total: 6h 56m | Avg: 13m 52s | Max: 18m 17s 🟩 GCC Pass: 100%/20 | Total: 4h 30m | Avg: 13m 31s | Max: 23m 40s 🟩 MSVC Pass: 100%/2 | Total: 18m 46s | Avg: 9m 23s | Max: 9m 30s | Hits: 2%/224 🟩 NVHPC Pass: 100%/2 | Total: 16m 53s | Avg: 8m 26s | Max: 8m 33s 🟩 gpu 🟩 v100 Pass: 100%/54 | Total: 12h 02m | Avg: 13m 22s | Max: 23m 40s | Hits: 2%/224 🟩 jobs 🟩 Build Pass: 100%/49 | Total: 10h 20m | Avg: 12m 40s | Max: 16m 37s | Hits: 2%/224 🟩 Test Pass: 100%/5 | Total: 1h 41m | Avg: 20m 18s | Max: 23m 40s 🟩 sm 🟩 90 Pass: 100%/1 | Total: 10m 28s | Avg: 10m 28s | Max: 10m 28s 🟩 90a Pass: 100%/1 | Total: 10m 46s | Avg: 10m 46s | Max: 10m 46s 🟩 std 🟩 17 Pass: 100%/29 | Total: 6h 33m | Avg: 13m 33s | Max: 23m 40s 🟩 20 Pass: 100%/25 | Total: 5h 29m | Avg: 13m 09s | Max: 20m 15s | Hits: 2%/224 -
🟩 cccl_c_parallel: Pass: 100%/2 | Total: 9m 44s | Avg: 4m 52s | Max: 7m 48s
🟩 cpu 🟩 amd64 Pass: 100%/2 | Total: 9m 44s | Avg: 4m 52s | Max: 7m 48s 🟩 ctk 🟩 12.6 Pass: 100%/2 | Total: 9m 44s | Avg: 4m 52s | Max: 7m 48s 🟩 cudacxx 🟩 nvcc12.6 Pass: 100%/2 | Total: 9m 44s | Avg: 4m 52s | Max: 7m 48s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/2 | Total: 9m 44s | Avg: 4m 52s | Max: 7m 48s 🟩 cxx 🟩 GCC13 Pass: 100%/2 | Total: 9m 44s | Avg: 4m 52s | Max: 7m 48s 🟩 cxx_family 🟩 GCC Pass: 100%/2 | Total: 9m 44s | Avg: 4m 52s | Max: 7m 48s 🟩 gpu 🟩 v100 Pass: 100%/2 | Total: 9m 44s | Avg: 4m 52s | Max: 7m 48s 🟩 jobs 🟩 Build Pass: 100%/1 | Total: 1m 56s | Avg: 1m 56s | Max: 1m 56s 🟩 Test Pass: 100%/1 | Total: 7m 48s | Avg: 7m 48s | Max: 7m 48s -
🟩 python: Pass: 100%/1 | Total: 15m 55s | Avg: 15m 55s | Max: 15m 55s
🟩 cpu 🟩 amd64 Pass: 100%/1 | Total: 15m 55s | Avg: 15m 55s | Max: 15m 55s 🟩 ctk 🟩 12.6 Pass: 100%/1 | Total: 15m 55s | Avg: 15m 55s | Max: 15m 55s 🟩 cudacxx 🟩 nvcc12.6 Pass: 100%/1 | Total: 15m 55s | Avg: 15m 55s | Max: 15m 55s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/1 | Total: 15m 55s | Avg: 15m 55s | Max: 15m 55s 🟩 cxx 🟩 GCC13 Pass: 100%/1 | Total: 15m 55s | Avg: 15m 55s | Max: 15m 55s 🟩 cxx_family 🟩 GCC Pass: 100%/1 | Total: 15m 55s | Avg: 15m 55s | Max: 15m 55s 🟩 gpu 🟩 v100 Pass: 100%/1 | Total: 15m 55s | Avg: 15m 55s | Max: 15m 55s 🟩 jobs 🟩 Test Pass: 100%/1 | Total: 15m 55s | Avg: 15m 55s | Max: 15m 55s
👃 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: 394)
| # | Runner |
|---|---|
| 326 | linux-amd64-cpu16 |
| 28 | linux-arm64-cpu16 |
| 25 | linux-amd64-gpu-v100-latest-1 |
| 15 | windows-amd64-cpu16 |
@miscco I applied the feedback you suggested on #2404 to this PR.
Added benchmark on H200 (PR description). Looking good except our fibonaccy transformation:
| T{ct} | Elements | Ref Time | Ref Noise | Cmp Time | Cmp Noise | Diff | %Diff | Status |
|---------|------------|------------|-------------|------------|-------------|------------|---------|----------|
| U32 | 2^16 | 9.858 us | 2.82% | 9.025 us | 3.08% | -0.833 us | -8.45% | FAIL |
| U32 | 2^20 | 14.385 us | 2.76% | 16.259 us | 1.84% | 1.875 us | 13.03% | FAIL |
| U32 | 2^24 | 86.839 us | 0.49% | 88.620 us | 0.37% | 1.781 us | 2.05% | FAIL |
| U32 | 2^28 | 1.238 ms | 0.08% | 1.251 ms | 0.09% | 12.555 us | 1.01% | FAIL |
🟩 CI finished in 1h 35m: Pass: 100%/394 | Total: 8d 00h | Avg: 29m 15s | Max: 1h 14m | Hits: 70%/25848
-
🟩 libcudacxx: Pass: 100%/118 | Total: 1d 02h | Avg: 13m 26s | Max: 39m 16s | Hits: 68%/9484
🟩 cpu 🟩 amd64 Pass: 100%/110 | Total: 1d 01h | Avg: 13m 39s | Max: 39m 16s | Hits: 68%/9484 🟩 arm64 Pass: 100%/8 | Total: 1h 24m | Avg: 10m 30s | Max: 23m 35s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 3h 09m | Avg: 12m 36s | Max: 32m 14s | Hits: 35%/2177 🟩 11.8 Pass: 100%/3 | Total: 1h 16m | Avg: 25m 31s | Max: 30m 49s 🟩 12.5 Pass: 100%/4 | Total: 2h 09m | Avg: 32m 17s | Max: 39m 16s 🟩 12.6 Pass: 100%/96 | Total: 19h 52m | Avg: 12m 25s | Max: 33m 11s | Hits: 78%/7307 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/12 | Total: 2h 31m | Avg: 12m 36s | Max: 20m 02s 🟩 nvcc11.1 Pass: 100%/15 | Total: 3h 09m | Avg: 12m 36s | Max: 32m 14s | Hits: 35%/2177 🟩 nvcc11.8 Pass: 100%/3 | Total: 1h 16m | Avg: 25m 31s | Max: 30m 49s 🟩 nvcc12.5 Pass: 100%/4 | Total: 2h 09m | Avg: 32m 17s | Max: 39m 16s 🟩 nvcc12.6 Pass: 100%/84 | Total: 17h 20m | Avg: 12m 23s | Max: 33m 11s | Hits: 78%/7307 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/12 | Total: 2h 31m | Avg: 12m 36s | Max: 20m 02s 🟩 nvcc Pass: 100%/106 | Total: 23h 55m | Avg: 13m 32s | Max: 39m 16s | Hits: 68%/9484 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 2h 03m | Avg: 20m 32s | Max: 29m 21s 🟩 Clang10 Pass: 100%/3 | Total: 43m 47s | Avg: 14m 35s | Max: 23m 10s 🟩 Clang11 Pass: 100%/4 | Total: 33m 35s | Avg: 8m 23s | Max: 20m 07s 🟩 Clang12 Pass: 100%/4 | Total: 58m 50s | Avg: 14m 42s | Max: 25m 23s 🟩 Clang13 Pass: 100%/4 | Total: 43m 26s | Avg: 10m 51s | Max: 29m 58s 🟩 Clang14 Pass: 100%/4 | Total: 19m 14s | Avg: 4m 48s | Max: 5m 09s 🟩 Clang15 Pass: 100%/4 | Total: 51m 30s | Avg: 12m 52s | Max: 23m 52s 🟩 Clang16 Pass: 100%/4 | Total: 31m 21s | Avg: 7m 50s | Max: 17m 33s 🟩 Clang17 Pass: 100%/4 | Total: 1h 01m | Avg: 15m 25s | Max: 26m 47s 🟩 Clang18 Pass: 100%/18 | Total: 3h 52m | Avg: 12m 55s | Max: 27m 27s 🟩 GCC6 Pass: 100%/2 | Total: 26m 12s | Avg: 13m 06s | Max: 22m 57s 🟩 GCC7 Pass: 100%/6 | Total: 38m 30s | Avg: 6m 25s | Max: 21m 31s 🟩 GCC8 Pass: 100%/6 | Total: 1h 20m | Avg: 13m 24s | Max: 26m 54s 🟩 GCC9 Pass: 100%/6 | Total: 54m 39s | Avg: 9m 06s | Max: 22m 44s 🟩 GCC10 Pass: 100%/4 | Total: 52m 06s | Avg: 13m 01s | Max: 26m 25s 🟩 GCC11 Pass: 100%/7 | Total: 1h 59m | Avg: 17m 06s | Max: 30m 49s 🟩 GCC12 Pass: 100%/4 | Total: 34m 33s | Avg: 8m 38s | Max: 20m 28s 🟩 GCC13 Pass: 100%/17 | Total: 3h 30m | Avg: 12m 23s | Max: 27m 44s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 53m 31s | Avg: 17m 50s | Max: 26m 40s 🟩 MSVC14.16 Pass: 100%/1 | Total: 32m 14s | Avg: 32m 14s | Max: 32m 14s | Hits: 35%/2177 🟩 MSVC14.29 Pass: 100%/2 | Total: 43m 54s | Avg: 21m 57s | Max: 33m 11s | Hits: 67%/4717 🟩 MSVC14.39 Pass: 100%/1 | Total: 11m 52s | Avg: 11m 52s | Max: 11m 52s | Hits: 98%/2590 🟩 NVHPC24.7 Pass: 100%/4 | Total: 2h 09m | Avg: 32m 17s | Max: 39m 16s 🟩 cxx_family 🟩 Clang Pass: 100%/55 | Total: 11h 39m | Avg: 12m 42s | Max: 29m 58s 🟩 GCC Pass: 100%/52 | Total: 10h 16m | Avg: 11m 51s | Max: 30m 49s 🟩 Intel Pass: 100%/3 | Total: 53m 31s | Avg: 17m 50s | Max: 26m 40s 🟩 MSVC Pass: 100%/4 | Total: 1h 28m | Avg: 22m 00s | Max: 33m 11s | Hits: 68%/9484 🟩 NVHPC Pass: 100%/4 | Total: 2h 09m | Avg: 32m 17s | Max: 39m 16s 🟩 gpu 🟩 v100 Pass: 100%/118 | Total: 1d 02h | Avg: 13m 26s | Max: 39m 16s | Hits: 68%/9484 🟩 jobs 🟩 Build Pass: 100%/110 | Total: 23h 50m | Avg: 13m 00s | Max: 39m 16s | Hits: 68%/9484 🟩 NVRTC Pass: 100%/4 | Total: 1h 26m | Avg: 21m 39s | Max: 27m 43s 🟩 Test Pass: 100%/3 | Total: 1h 07m | Avg: 22m 34s | Max: 27m 27s 🟩 VerifyCodegen Pass: 100%/1 | Total: 2m 19s | Avg: 2m 19s | Max: 2m 19s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 1h 16m | Avg: 25m 31s | Max: 30m 49s 🟩 90 Pass: 100%/4 | Total: 42m 27s | Avg: 10m 36s | Max: 13m 19s 🟩 90a Pass: 100%/8 | Total: 59m 12s | Avg: 7m 24s | Max: 13m 23s 🟩 std 🟩 11 Pass: 100%/32 | Total: 6h 09m | Avg: 11m 32s | Max: 29m 01s 🟩 14 Pass: 100%/32 | Total: 7h 43m | Avg: 14m 28s | Max: 36m 09s | Hits: 34%/4457 🟩 17 Pass: 100%/30 | Total: 7h 43m | Avg: 15m 27s | Max: 39m 16s | Hits: 99%/2437 🟩 20 Pass: 100%/23 | Total: 4h 48m | Avg: 12m 32s | Max: 27m 44s | Hits: 98%/2590 -
🟩 cub: Pass: 100%/110 | Total: 3d 19h | Avg: 50m 10s | Max: 1h 14m | Hits: 65%/2948
🟩 cpu 🟩 amd64 Pass: 100%/102 | Total: 3d 12h | Avg: 49m 46s | Max: 1h 14m | Hits: 65%/2948 🟩 arm64 Pass: 100%/8 | Total: 7h 21m | Avg: 55m 13s | Max: 1h 02m 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 11h 46m | Avg: 47m 05s | Max: 56m 33s | Hits: 65%/737 🟩 11.8 Pass: 100%/3 | Total: 3h 29m | Avg: 1h 09m | Max: 1h 14m 🟩 12.5 Pass: 100%/4 | Total: 4h 13m | Avg: 1h 03m | Max: 1h 05m 🟩 12.6 Pass: 100%/88 | Total: 3d 00h | Avg: 49m 25s | Max: 1h 02m | Hits: 65%/2211 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/4 | Total: 3h 47m | Avg: 56m 53s | Max: 57m 49s 🟩 nvcc11.1 Pass: 100%/15 | Total: 11h 46m | Avg: 47m 05s | Max: 56m 33s | Hits: 65%/737 🟩 nvcc11.8 Pass: 100%/3 | Total: 3h 29m | Avg: 1h 09m | Max: 1h 14m 🟩 nvcc12.5 Pass: 100%/4 | Total: 4h 13m | Avg: 1h 03m | Max: 1h 05m 🟩 nvcc12.6 Pass: 100%/84 | Total: 2d 20h | Avg: 49m 04s | Max: 1h 02m | Hits: 65%/2211 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/4 | Total: 3h 47m | Avg: 56m 53s | Max: 57m 49s 🟩 nvcc Pass: 100%/106 | Total: 3d 16h | Avg: 49m 55s | Max: 1h 14m | Hits: 65%/2948 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 4h 51m | Avg: 48m 36s | Max: 54m 22s 🟩 Clang10 Pass: 100%/3 | Total: 2h 38m | Avg: 52m 49s | Max: 57m 15s 🟩 Clang11 Pass: 100%/4 | Total: 3h 24m | Avg: 51m 11s | Max: 53m 45s 🟩 Clang12 Pass: 100%/4 | Total: 3h 36m | Avg: 54m 08s | Max: 55m 28s 🟩 Clang13 Pass: 100%/4 | Total: 3h 36m | Avg: 54m 07s | Max: 57m 06s 🟩 Clang14 Pass: 100%/4 | Total: 3h 32m | Avg: 53m 02s | Max: 54m 45s 🟩 Clang15 Pass: 100%/4 | Total: 3h 38m | Avg: 54m 40s | Max: 57m 52s 🟩 Clang16 Pass: 100%/4 | Total: 3h 37m | Avg: 54m 21s | Max: 58m 54s 🟩 Clang17 Pass: 100%/4 | Total: 3h 24m | Avg: 51m 14s | Max: 52m 46s 🟩 Clang18 Pass: 100%/11 | Total: 8h 59m | Avg: 49m 02s | Max: 57m 49s 🟩 GCC6 Pass: 100%/2 | Total: 1h 30m | Avg: 45m 19s | Max: 45m 59s 🟩 GCC7 Pass: 100%/6 | Total: 4h 55m | Avg: 49m 13s | Max: 56m 19s 🟩 GCC8 Pass: 100%/6 | Total: 4h 58m | Avg: 49m 45s | Max: 56m 03s 🟩 GCC9 Pass: 100%/6 | Total: 5h 05m | Avg: 50m 50s | Max: 57m 06s 🟩 GCC10 Pass: 100%/4 | Total: 3h 37m | Avg: 54m 22s | Max: 58m 52s 🟩 GCC11 Pass: 100%/7 | Total: 7h 04m | Avg: 1h 00m | Max: 1h 14m 🟩 GCC12 Pass: 100%/4 | Total: 3h 26m | Avg: 51m 35s | Max: 52m 16s 🟩 GCC13 Pass: 100%/16 | Total: 9h 03m | Avg: 33m 57s | Max: 1h 02m 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 53m | Avg: 57m 41s | Max: 1h 01m 🟩 MSVC14.16 Pass: 100%/1 | Total: 56m 33s | Avg: 56m 33s | Max: 56m 33s | Hits: 65%/737 🟩 MSVC14.29 Pass: 100%/2 | Total: 1h 51m | Avg: 55m 33s | Max: 55m 42s | Hits: 65%/1474 🟩 MSVC14.39 Pass: 100%/1 | Total: 1h 02m | Avg: 1h 02m | Max: 1h 02m | Hits: 65%/737 🟩 NVHPC24.7 Pass: 100%/4 | Total: 4h 13m | Avg: 1h 03m | Max: 1h 05m 🟩 cxx_family 🟩 Clang Pass: 100%/48 | Total: 1d 17h | Avg: 51m 40s | Max: 58m 54s 🟩 GCC Pass: 100%/51 | Total: 1d 15h | Avg: 46m 41s | Max: 1h 14m 🟩 Intel Pass: 100%/3 | Total: 2h 53m | Avg: 57m 41s | Max: 1h 01m 🟩 MSVC Pass: 100%/4 | Total: 3h 50m | Avg: 57m 39s | Max: 1h 02m | Hits: 65%/2948 🟩 NVHPC Pass: 100%/4 | Total: 4h 13m | Avg: 1h 03m | Max: 1h 05m 🟩 gpu 🟩 v100 Pass: 100%/110 | Total: 3d 19h | Avg: 50m 10s | Max: 1h 14m | Hits: 65%/2948 🟩 jobs 🟩 Build Pass: 100%/102 | Total: 3d 17h | Avg: 52m 32s | Max: 1h 14m | Hits: 65%/2948 🟩 DeviceLaunch Pass: 100%/1 | Total: 20m 13s | Avg: 20m 13s | Max: 20m 13s 🟩 GraphCapture Pass: 100%/1 | Total: 17m 11s | Avg: 17m 11s | Max: 17m 11s 🟩 HostLaunch Pass: 100%/3 | Total: 53m 17s | Avg: 17m 45s | Max: 19m 44s 🟩 TestGPU Pass: 100%/3 | Total: 1h 08m | Avg: 22m 53s | Max: 24m 04s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 3h 29m | Avg: 1h 09m | Max: 1h 14m 🟩 90a Pass: 100%/4 | Total: 1h 31m | Avg: 22m 49s | Max: 23m 46s 🟩 std 🟩 11 Pass: 100%/30 | Total: 1d 01h | Avg: 50m 02s | Max: 1h 07m 🟩 14 Pass: 100%/29 | Total: 1d 01h | Avg: 52m 25s | Max: 1h 07m | Hits: 65%/1474 🟩 17 Pass: 100%/27 | Total: 23h 32m | Avg: 52m 18s | Max: 1h 14m | Hits: 65%/737 🟩 20 Pass: 100%/24 | Total: 18h 05m | Avg: 45m 13s | Max: 1h 02m | Hits: 65%/737 -
🟩 thrust: Pass: 100%/109 | Total: 2d 20h | Avg: 37m 49s | Max: 1h 08m | Hits: 73%/13180
🟩 cpu 🟩 amd64 Pass: 100%/101 | Total: 2d 16h | Avg: 38m 01s | Max: 1h 08m | Hits: 73%/13180 🟩 arm64 Pass: 100%/8 | Total: 4h 42m | Avg: 35m 20s | Max: 41m 45s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 9h 14m | Avg: 36m 57s | Max: 55m 42s | Hits: 68%/2636 🟩 11.8 Pass: 100%/3 | Total: 2h 08m | Avg: 42m 49s | Max: 47m 42s 🟩 12.5 Pass: 100%/4 | Total: 3h 56m | Avg: 59m 06s | Max: 1h 08m 🟩 12.6 Pass: 100%/87 | Total: 2d 05h | Avg: 36m 49s | Max: 1h 08m | Hits: 74%/10544 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/4 | Total: 1h 58m | Avg: 29m 41s | Max: 32m 44s 🟩 nvcc11.1 Pass: 100%/15 | Total: 9h 14m | Avg: 36m 57s | Max: 55m 42s | Hits: 68%/2636 🟩 nvcc11.8 Pass: 100%/3 | Total: 2h 08m | Avg: 42m 49s | Max: 47m 42s 🟩 nvcc12.5 Pass: 100%/4 | Total: 3h 56m | Avg: 59m 06s | Max: 1h 08m 🟩 nvcc12.6 Pass: 100%/83 | Total: 2d 03h | Avg: 37m 10s | Max: 1h 08m | Hits: 74%/10544 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/4 | Total: 1h 58m | Avg: 29m 41s | Max: 32m 44s 🟩 nvcc Pass: 100%/105 | Total: 2d 18h | Avg: 38m 08s | Max: 1h 08m | Hits: 73%/13180 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 3h 44m | Avg: 37m 25s | Max: 44m 58s 🟩 Clang10 Pass: 100%/3 | Total: 2h 01m | Avg: 40m 28s | Max: 45m 42s 🟩 Clang11 Pass: 100%/4 | Total: 2h 34m | Avg: 38m 38s | Max: 45m 55s 🟩 Clang12 Pass: 100%/4 | Total: 2h 41m | Avg: 40m 18s | Max: 43m 02s 🟩 Clang13 Pass: 100%/4 | Total: 2h 33m | Avg: 38m 27s | Max: 43m 21s 🟩 Clang14 Pass: 100%/4 | Total: 2h 36m | Avg: 39m 13s | Max: 43m 01s 🟩 Clang15 Pass: 100%/4 | Total: 2h 37m | Avg: 39m 21s | Max: 41m 33s 🟩 Clang16 Pass: 100%/4 | Total: 2h 31m | Avg: 37m 55s | Max: 43m 37s 🟩 Clang17 Pass: 100%/4 | Total: 2h 25m | Avg: 36m 28s | Max: 41m 43s 🟩 Clang18 Pass: 100%/11 | Total: 5h 17m | Avg: 28m 52s | Max: 44m 23s 🟩 GCC6 Pass: 100%/2 | Total: 1h 07m | Avg: 33m 35s | Max: 38m 56s 🟩 GCC7 Pass: 100%/6 | Total: 3h 37m | Avg: 36m 10s | Max: 44m 09s 🟩 GCC8 Pass: 100%/6 | Total: 3h 33m | Avg: 35m 31s | Max: 39m 35s 🟩 GCC9 Pass: 100%/6 | Total: 3h 57m | Avg: 39m 35s | Max: 45m 45s 🟩 GCC10 Pass: 100%/4 | Total: 2h 37m | Avg: 39m 20s | Max: 43m 08s 🟩 GCC11 Pass: 100%/7 | Total: 4h 47m | Avg: 41m 08s | Max: 47m 42s 🟩 GCC12 Pass: 100%/4 | Total: 2h 45m | Avg: 41m 21s | Max: 45m 41s 🟩 GCC13 Pass: 100%/14 | Total: 6h 29m | Avg: 27m 49s | Max: 41m 45s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 18m | Avg: 46m 16s | Max: 50m 32s 🟩 MSVC14.16 Pass: 100%/1 | Total: 55m 42s | Avg: 55m 42s | Max: 55m 42s | Hits: 68%/2636 🟩 MSVC14.29 Pass: 100%/2 | Total: 2h 01m | Avg: 1h 00m | Max: 1h 01m | Hits: 66%/5272 🟩 MSVC14.39 Pass: 100%/2 | Total: 1h 30m | Avg: 45m 03s | Max: 1h 08m | Hits: 82%/5272 🟩 NVHPC24.7 Pass: 100%/4 | Total: 3h 56m | Avg: 59m 06s | Max: 1h 08m 🟩 cxx_family 🟩 Clang Pass: 100%/48 | Total: 1d 05h | Avg: 36m 21s | Max: 45m 55s 🟩 GCC Pass: 100%/49 | Total: 1d 04h | Avg: 35m 24s | Max: 47m 42s 🟩 Intel Pass: 100%/3 | Total: 2h 18m | Avg: 46m 16s | Max: 50m 32s 🟩 MSVC Pass: 100%/5 | Total: 4h 27m | Avg: 53m 32s | Max: 1h 08m | Hits: 73%/13180 🟩 NVHPC Pass: 100%/4 | Total: 3h 56m | Avg: 59m 06s | Max: 1h 08m 🟩 gpu 🟩 v100 Pass: 100%/109 | Total: 2d 20h | Avg: 37m 49s | Max: 1h 08m | Hits: 73%/13180 🟩 jobs 🟩 Build Pass: 100%/102 | Total: 2d 18h | Avg: 39m 22s | Max: 1h 08m | Hits: 66%/10544 🟩 TestCPU Pass: 100%/4 | Total: 46m 41s | Avg: 11m 40s | Max: 21m 26s | Hits: 99%/2636 🟩 TestGPU Pass: 100%/3 | Total: 1h 00m | Avg: 20m 16s | Max: 33m 30s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 2h 08m | Avg: 42m 49s | Max: 47m 42s 🟩 90a Pass: 100%/4 | Total: 1h 40m | Avg: 25m 01s | Max: 29m 10s 🟩 std 🟩 11 Pass: 100%/30 | Total: 15h 45m | Avg: 31m 30s | Max: 50m 32s 🟩 14 Pass: 100%/29 | Total: 19h 55m | Avg: 41m 12s | Max: 1h 00m | Hits: 66%/5272 🟩 17 Pass: 100%/27 | Total: 19h 01m | Avg: 42m 15s | Max: 1h 01m | Hits: 68%/2636 🟩 20 Pass: 100%/23 | Total: 14h 01m | Avg: 36m 36s | Max: 1h 08m | Hits: 82%/5272 -
🟩 cudax: Pass: 100%/54 | Total: 4h 31m | Avg: 5m 01s | Max: 19m 11s | Hits: 88%/236
🟩 cpu 🟩 amd64 Pass: 100%/50 | Total: 4h 17m | Avg: 5m 08s | Max: 19m 11s | Hits: 88%/236 🟩 arm64 Pass: 100%/4 | Total: 14m 47s | Avg: 3m 41s | Max: 4m 21s 🟩 ctk 🟩 12.0 Pass: 100%/19 | Total: 1h 32m | Avg: 4m 50s | Max: 15m 02s | Hits: 88%/118 🟩 12.5 Pass: 100%/2 | Total: 11m 19s | Avg: 5m 39s | Max: 5m 57s 🟩 12.6 Pass: 100%/33 | Total: 2h 48m | Avg: 5m 06s | Max: 19m 11s | Hits: 88%/118 🟩 cudacxx 🟩 nvcc12.0 Pass: 100%/19 | Total: 1h 32m | Avg: 4m 50s | Max: 15m 02s | Hits: 88%/118 🟩 nvcc12.5 Pass: 100%/2 | Total: 11m 19s | Avg: 5m 39s | Max: 5m 57s 🟩 nvcc12.6 Pass: 100%/33 | Total: 2h 48m | Avg: 5m 06s | Max: 19m 11s | Hits: 88%/118 🟩 cudacxx_family 🟩 nvcc Pass: 100%/54 | Total: 4h 31m | Avg: 5m 01s | Max: 19m 11s | Hits: 88%/236 🟩 cxx 🟩 Clang9 Pass: 100%/2 | Total: 7m 50s | Avg: 3m 55s | Max: 4m 11s 🟩 Clang10 Pass: 100%/2 | Total: 8m 18s | Avg: 4m 09s | Max: 4m 47s 🟩 Clang11 Pass: 100%/4 | Total: 14m 20s | Avg: 3m 35s | Max: 3m 51s 🟩 Clang12 Pass: 100%/4 | Total: 14m 29s | Avg: 3m 37s | Max: 3m 50s 🟩 Clang13 Pass: 100%/4 | Total: 14m 52s | Avg: 3m 43s | Max: 3m 58s 🟩 Clang14 Pass: 100%/4 | Total: 26m 12s | Avg: 6m 33s | Max: 15m 02s 🟩 Clang15 Pass: 100%/2 | Total: 7m 53s | Avg: 3m 56s | Max: 4m 17s 🟩 Clang16 Pass: 100%/4 | Total: 15m 39s | Avg: 3m 54s | Max: 4m 21s 🟩 Clang17 Pass: 100%/2 | Total: 7m 33s | Avg: 3m 46s | Max: 3m 50s 🟩 Clang18 Pass: 100%/2 | Total: 22m 47s | Avg: 11m 23s | Max: 19m 11s 🟩 GCC9 Pass: 100%/2 | Total: 6m 42s | Avg: 3m 21s | Max: 3m 23s 🟩 GCC10 Pass: 100%/4 | Total: 13m 45s | Avg: 3m 26s | Max: 3m 45s 🟩 GCC11 Pass: 100%/4 | Total: 14m 01s | Avg: 3m 30s | Max: 3m 37s 🟩 GCC12 Pass: 100%/7 | Total: 1h 01m | Avg: 8m 48s | Max: 16m 28s 🟩 GCC13 Pass: 100%/3 | Total: 10m 06s | Avg: 3m 22s | Max: 3m 35s 🟩 MSVC14.36 Pass: 100%/1 | Total: 7m 04s | Avg: 7m 04s | Max: 7m 04s | Hits: 88%/118 🟩 MSVC14.39 Pass: 100%/1 | Total: 7m 15s | Avg: 7m 15s | Max: 7m 15s | Hits: 88%/118 🟩 NVHPC24.7 Pass: 100%/2 | Total: 11m 19s | Avg: 5m 39s | Max: 5m 57s 🟩 cxx_family 🟩 Clang Pass: 100%/30 | Total: 2h 19m | Avg: 4m 39s | Max: 19m 11s 🟩 GCC Pass: 100%/20 | Total: 1h 46m | Avg: 5m 18s | Max: 16m 28s 🟩 MSVC Pass: 100%/2 | Total: 14m 19s | Avg: 7m 09s | Max: 7m 15s | Hits: 88%/236 🟩 NVHPC Pass: 100%/2 | Total: 11m 19s | Avg: 5m 39s | Max: 5m 57s 🟩 gpu 🟩 v100 Pass: 100%/54 | Total: 4h 31m | Avg: 5m 01s | Max: 19m 11s | Hits: 88%/236 🟩 jobs 🟩 Build Pass: 100%/49 | Total: 3h 10m | Avg: 3m 53s | Max: 7m 15s | Hits: 88%/236 🟩 Test Pass: 100%/5 | Total: 1h 21m | Avg: 16m 17s | Max: 19m 11s 🟩 sm 🟩 90 Pass: 100%/1 | Total: 2m 48s | Avg: 2m 48s | Max: 2m 48s 🟩 90a Pass: 100%/1 | Total: 3m 08s | Avg: 3m 08s | Max: 3m 08s 🟩 std 🟩 17 Pass: 100%/29 | Total: 2h 11m | Avg: 4m 31s | Max: 15m 49s 🟩 20 Pass: 100%/25 | Total: 2h 20m | Avg: 5m 37s | Max: 19m 11s | Hits: 88%/236 -
🟩 cccl_c_parallel: Pass: 100%/2 | Total: 10m 38s | Avg: 5m 19s | Max: 8m 31s
🟩 cpu 🟩 amd64 Pass: 100%/2 | Total: 10m 38s | Avg: 5m 19s | Max: 8m 31s 🟩 ctk 🟩 12.6 Pass: 100%/2 | Total: 10m 38s | Avg: 5m 19s | Max: 8m 31s 🟩 cudacxx 🟩 nvcc12.6 Pass: 100%/2 | Total: 10m 38s | Avg: 5m 19s | Max: 8m 31s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/2 | Total: 10m 38s | Avg: 5m 19s | Max: 8m 31s 🟩 cxx 🟩 GCC13 Pass: 100%/2 | Total: 10m 38s | Avg: 5m 19s | Max: 8m 31s 🟩 cxx_family 🟩 GCC Pass: 100%/2 | Total: 10m 38s | Avg: 5m 19s | Max: 8m 31s 🟩 gpu 🟩 v100 Pass: 100%/2 | Total: 10m 38s | Avg: 5m 19s | Max: 8m 31s 🟩 jobs 🟩 Build Pass: 100%/1 | Total: 2m 07s | Avg: 2m 07s | Max: 2m 07s 🟩 Test Pass: 100%/1 | Total: 8m 31s | Avg: 8m 31s | Max: 8m 31s -
🟩 python: Pass: 100%/1 | Total: 14m 44s | Avg: 14m 44s | Max: 14m 44s
🟩 cpu 🟩 amd64 Pass: 100%/1 | Total: 14m 44s | Avg: 14m 44s | Max: 14m 44s 🟩 ctk 🟩 12.6 Pass: 100%/1 | Total: 14m 44s | Avg: 14m 44s | Max: 14m 44s 🟩 cudacxx 🟩 nvcc12.6 Pass: 100%/1 | Total: 14m 44s | Avg: 14m 44s | Max: 14m 44s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/1 | Total: 14m 44s | Avg: 14m 44s | Max: 14m 44s 🟩 cxx 🟩 GCC13 Pass: 100%/1 | Total: 14m 44s | Avg: 14m 44s | Max: 14m 44s 🟩 cxx_family 🟩 GCC Pass: 100%/1 | Total: 14m 44s | Avg: 14m 44s | Max: 14m 44s 🟩 gpu 🟩 v100 Pass: 100%/1 | Total: 14m 44s | Avg: 14m 44s | Max: 14m 44s 🟩 jobs 🟩 Test Pass: 100%/1 | Total: 14m 44s | Avg: 14m 44s | Max: 14m 44s
👃 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: 394)
| # | Runner |
|---|---|
| 326 | linux-amd64-cpu16 |
| 28 | linux-arm64-cpu16 |
| 25 | linux-amd64-gpu-v100-latest-1 |
| 15 | windows-amd64-cpu16 |
🟩 CI finished in 2h 26m: Pass: 100%/394 | Total: 8d 05h | Avg: 30m 01s | Max: 1h 26m | Hits: 59%/25850
-
🟩 libcudacxx: Pass: 100%/118 | Total: 1d 04h | Avg: 14m 20s | Max: 41m 21s | Hits: 49%/9484
🟩 cpu 🟩 amd64 Pass: 100%/110 | Total: 1d 03h | Avg: 15m 03s | Max: 41m 21s | Hits: 49%/9484 🟩 arm64 Pass: 100%/8 | Total: 36m 01s | Avg: 4m 30s | Max: 11m 34s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 3h 06m | Avg: 12m 27s | Max: 30m 43s | Hits: 35%/2177 🟩 11.8 Pass: 100%/3 | Total: 47m 23s | Avg: 15m 47s | Max: 22m 21s 🟩 12.5 Pass: 100%/4 | Total: 1h 30m | Avg: 22m 38s | Max: 37m 34s 🟩 12.6 Pass: 100%/96 | Total: 22h 46m | Avg: 14m 14s | Max: 41m 21s | Hits: 53%/7307 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/12 | Total: 2h 28m | Avg: 12m 24s | Max: 21m 47s 🟩 nvcc11.1 Pass: 100%/15 | Total: 3h 06m | Avg: 12m 27s | Max: 30m 43s | Hits: 35%/2177 🟩 nvcc11.8 Pass: 100%/3 | Total: 47m 23s | Avg: 15m 47s | Max: 22m 21s 🟩 nvcc12.5 Pass: 100%/4 | Total: 1h 30m | Avg: 22m 38s | Max: 37m 34s 🟩 nvcc12.6 Pass: 100%/84 | Total: 20h 17m | Avg: 14m 29s | Max: 41m 21s | Hits: 53%/7307 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/12 | Total: 2h 28m | Avg: 12m 24s | Max: 21m 47s 🟩 nvcc Pass: 100%/106 | Total: 1d 01h | Avg: 14m 33s | Max: 41m 21s | Hits: 49%/9484 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 1h 01m | Avg: 10m 18s | Max: 24m 22s 🟩 Clang10 Pass: 100%/3 | Total: 47m 18s | Avg: 15m 46s | Max: 27m 48s 🟩 Clang11 Pass: 100%/4 | Total: 1h 19m | Avg: 19m 59s | Max: 25m 51s 🟩 Clang12 Pass: 100%/4 | Total: 39m 00s | Avg: 9m 45s | Max: 26m 14s 🟩 Clang13 Pass: 100%/4 | Total: 1h 13m | Avg: 18m 26s | Max: 25m 27s 🟩 Clang14 Pass: 100%/4 | Total: 1h 17m | Avg: 19m 17s | Max: 25m 55s 🟩 Clang15 Pass: 100%/4 | Total: 31m 41s | Avg: 7m 55s | Max: 17m 53s 🟩 Clang16 Pass: 100%/4 | Total: 1h 16m | Avg: 19m 05s | Max: 29m 05s 🟩 Clang17 Pass: 100%/4 | Total: 42m 10s | Avg: 10m 32s | Max: 17m 43s 🟩 Clang18 Pass: 100%/18 | Total: 3h 05m | Avg: 10m 17s | Max: 21m 47s 🟩 GCC6 Pass: 100%/2 | Total: 27m 41s | Avg: 13m 50s | Max: 24m 46s 🟩 GCC7 Pass: 100%/6 | Total: 1h 04m | Avg: 10m 40s | Max: 22m 28s 🟩 GCC8 Pass: 100%/6 | Total: 1h 32m | Avg: 15m 25s | Max: 24m 12s 🟩 GCC9 Pass: 100%/6 | Total: 1h 16m | Avg: 12m 44s | Max: 27m 33s 🟩 GCC10 Pass: 100%/4 | Total: 1h 08m | Avg: 17m 02s | Max: 26m 49s 🟩 GCC11 Pass: 100%/7 | Total: 1h 40m | Avg: 14m 21s | Max: 24m 10s 🟩 GCC12 Pass: 100%/4 | Total: 1h 19m | Avg: 19m 53s | Max: 31m 13s 🟩 GCC13 Pass: 100%/17 | Total: 3h 17m | Avg: 11m 35s | Max: 29m 26s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 1h 02m | Avg: 20m 40s | Max: 30m 45s 🟩 MSVC14.16 Pass: 100%/1 | Total: 30m 43s | Avg: 30m 43s | Max: 30m 43s | Hits: 35%/2177 🟩 MSVC14.29 Pass: 100%/2 | Total: 46m 37s | Avg: 23m 18s | Max: 35m 50s | Hits: 64%/4717 🟩 MSVC14.39 Pass: 100%/1 | Total: 41m 21s | Avg: 41m 21s | Max: 41m 21s | Hits: 34%/2590 🟩 NVHPC24.7 Pass: 100%/4 | Total: 1h 30m | Avg: 22m 38s | Max: 37m 34s 🟩 cxx_family 🟩 Clang Pass: 100%/55 | Total: 11h 54m | Avg: 12m 59s | Max: 29m 05s 🟩 GCC Pass: 100%/52 | Total: 11h 45m | Avg: 13m 34s | Max: 31m 13s 🟩 Intel Pass: 100%/3 | Total: 1h 02m | Avg: 20m 40s | Max: 30m 45s 🟩 MSVC Pass: 100%/4 | Total: 1h 58m | Avg: 29m 40s | Max: 41m 21s | Hits: 49%/9484 🟩 NVHPC Pass: 100%/4 | Total: 1h 30m | Avg: 22m 38s | Max: 37m 34s 🟩 gpu 🟩 v100 Pass: 100%/118 | Total: 1d 04h | Avg: 14m 20s | Max: 41m 21s | Hits: 49%/9484 🟩 jobs 🟩 Build Pass: 100%/110 | Total: 1d 01h | Avg: 13m 51s | Max: 41m 21s | Hits: 49%/9484 🟩 NVRTC Pass: 100%/4 | Total: 1h 46m | Avg: 26m 44s | Max: 29m 26s 🟩 Test Pass: 100%/3 | Total: 57m 59s | Avg: 19m 19s | Max: 23m 32s 🟩 VerifyCodegen Pass: 100%/1 | Total: 1m 53s | Avg: 1m 53s | Max: 1m 53s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 47m 23s | Avg: 15m 47s | Max: 22m 21s 🟩 90 Pass: 100%/4 | Total: 40m 10s | Avg: 10m 02s | Max: 12m 45s 🟩 90a Pass: 100%/8 | Total: 57m 10s | Avg: 7m 08s | Max: 12m 09s 🟩 std 🟩 11 Pass: 100%/32 | Total: 6h 09m | Avg: 11m 32s | Max: 28m 29s 🟩 14 Pass: 100%/32 | Total: 7h 18m | Avg: 13m 41s | Max: 30m 43s | Hits: 68%/4457 🟩 17 Pass: 100%/30 | Total: 8h 20m | Avg: 16m 41s | Max: 37m 34s | Hits: 32%/2437 🟩 20 Pass: 100%/23 | Total: 6h 21m | Avg: 16m 35s | Max: 41m 21s | Hits: 34%/2590 -
🟩 cub: Pass: 100%/110 | Total: 3d 19h | Avg: 49m 59s | Max: 1h 13m | Hits: 66%/2948
🟩 cpu 🟩 amd64 Pass: 100%/102 | Total: 3d 12h | Avg: 49m 38s | Max: 1h 13m | Hits: 66%/2948 🟩 arm64 Pass: 100%/8 | Total: 7h 15m | Avg: 54m 28s | Max: 56m 47s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 11h 24m | Avg: 45m 36s | Max: 50m 08s | Hits: 66%/737 🟩 11.8 Pass: 100%/3 | Total: 3h 16m | Avg: 1h 05m | Max: 1h 05m 🟩 12.5 Pass: 100%/4 | Total: 4h 09m | Avg: 1h 02m | Max: 1h 05m 🟩 12.6 Pass: 100%/88 | Total: 3d 00h | Avg: 49m 38s | Max: 1h 13m | Hits: 66%/2211 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/4 | Total: 3h 44m | Avg: 56m 05s | Max: 58m 29s 🟩 nvcc11.1 Pass: 100%/15 | Total: 11h 24m | Avg: 45m 36s | Max: 50m 08s | Hits: 66%/737 🟩 nvcc11.8 Pass: 100%/3 | Total: 3h 16m | Avg: 1h 05m | Max: 1h 05m 🟩 nvcc12.5 Pass: 100%/4 | Total: 4h 09m | Avg: 1h 02m | Max: 1h 05m 🟩 nvcc12.6 Pass: 100%/84 | Total: 2d 21h | Avg: 49m 20s | Max: 1h 13m | Hits: 66%/2211 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/4 | Total: 3h 44m | Avg: 56m 05s | Max: 58m 29s 🟩 nvcc Pass: 100%/106 | Total: 3d 15h | Avg: 49m 45s | Max: 1h 13m | Hits: 66%/2948 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 5h 02m | Avg: 50m 20s | Max: 55m 50s 🟩 Clang10 Pass: 100%/3 | Total: 2h 40m | Avg: 53m 32s | Max: 55m 16s 🟩 Clang11 Pass: 100%/4 | Total: 3h 21m | Avg: 50m 25s | Max: 51m 40s 🟩 Clang12 Pass: 100%/4 | Total: 3h 21m | Avg: 50m 29s | Max: 52m 06s 🟩 Clang13 Pass: 100%/4 | Total: 3h 27m | Avg: 51m 48s | Max: 53m 38s 🟩 Clang14 Pass: 100%/4 | Total: 3h 28m | Avg: 52m 07s | Max: 54m 33s 🟩 Clang15 Pass: 100%/4 | Total: 3h 32m | Avg: 53m 10s | Max: 57m 45s 🟩 Clang16 Pass: 100%/4 | Total: 3h 38m | Avg: 54m 30s | Max: 57m 28s 🟩 Clang17 Pass: 100%/4 | Total: 3h 28m | Avg: 52m 12s | Max: 57m 26s 🟩 Clang18 Pass: 100%/11 | Total: 8h 51m | Avg: 48m 20s | Max: 58m 29s 🟩 GCC6 Pass: 100%/2 | Total: 1h 28m | Avg: 44m 06s | Max: 45m 26s 🟩 GCC7 Pass: 100%/6 | Total: 4h 52m | Avg: 48m 47s | Max: 56m 37s 🟩 GCC8 Pass: 100%/6 | Total: 4h 52m | Avg: 48m 43s | Max: 53m 43s 🟩 GCC9 Pass: 100%/6 | Total: 4h 54m | Avg: 49m 07s | Max: 56m 37s 🟩 GCC10 Pass: 100%/4 | Total: 3h 37m | Avg: 54m 28s | Max: 57m 12s 🟩 GCC11 Pass: 100%/7 | Total: 7h 02m | Avg: 1h 00m | Max: 1h 05m 🟩 GCC12 Pass: 100%/4 | Total: 3h 25m | Avg: 51m 17s | Max: 52m 37s 🟩 GCC13 Pass: 100%/16 | Total: 9h 54m | Avg: 37m 10s | Max: 1h 13m 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 47m | Avg: 55m 48s | Max: 56m 55s 🟩 MSVC14.16 Pass: 100%/1 | Total: 50m 08s | Avg: 50m 08s | Max: 50m 08s | Hits: 66%/737 🟩 MSVC14.29 Pass: 100%/2 | Total: 1h 50m | Avg: 55m 23s | Max: 55m 27s | Hits: 66%/1474 🟩 MSVC14.39 Pass: 100%/1 | Total: 59m 06s | Avg: 59m 06s | Max: 59m 06s | Hits: 66%/737 🟩 NVHPC24.7 Pass: 100%/4 | Total: 4h 09m | Avg: 1h 02m | Max: 1h 05m 🟩 cxx_family 🟩 Clang Pass: 100%/48 | Total: 1d 16h | Avg: 51m 06s | Max: 58m 29s 🟩 GCC Pass: 100%/51 | Total: 1d 16h | Avg: 47m 13s | Max: 1h 13m 🟩 Intel Pass: 100%/3 | Total: 2h 47m | Avg: 55m 48s | Max: 56m 55s 🟩 MSVC Pass: 100%/4 | Total: 3h 40m | Avg: 55m 00s | Max: 59m 06s | Hits: 66%/2948 🟩 NVHPC Pass: 100%/4 | Total: 4h 09m | Avg: 1h 02m | Max: 1h 05m 🟩 gpu 🟩 v100 Pass: 100%/110 | Total: 3d 19h | Avg: 49m 59s | Max: 1h 13m | Hits: 66%/2948 🟩 jobs 🟩 Build Pass: 100%/102 | Total: 3d 16h | Avg: 51m 48s | Max: 1h 05m | Hits: 66%/2948 🟩 DeviceLaunch Pass: 100%/1 | Total: 19m 34s | Avg: 19m 34s | Max: 19m 34s 🟩 GraphCapture Pass: 100%/1 | Total: 13m 58s | Avg: 13m 58s | Max: 13m 58s 🟩 HostLaunch Pass: 100%/3 | Total: 1h 51m | Avg: 37m 06s | Max: 1h 13m 🟩 TestGPU Pass: 100%/3 | Total: 1h 08m | Avg: 22m 49s | Max: 25m 07s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 3h 16m | Avg: 1h 05m | Max: 1h 05m 🟩 90a Pass: 100%/4 | Total: 1h 31m | Avg: 22m 56s | Max: 24m 32s 🟩 std 🟩 11 Pass: 100%/30 | Total: 1d 01h | Avg: 51m 16s | Max: 1h 13m 🟩 14 Pass: 100%/29 | Total: 1d 00h | Avg: 51m 29s | Max: 1h 05m | Hits: 66%/1474 🟩 17 Pass: 100%/27 | Total: 23h 14m | Avg: 51m 39s | Max: 1h 05m | Hits: 66%/737 🟩 20 Pass: 100%/24 | Total: 17h 51m | Avg: 44m 38s | Max: 1h 01m | Hits: 66%/737 -
🟩 thrust: Pass: 100%/109 | Total: 3d 00h | Avg: 39m 44s | Max: 1h 26m | Hits: 64%/13180
🟩 cpu 🟩 amd64 Pass: 100%/101 | Total: 2d 19h | Avg: 39m 54s | Max: 1h 26m | Hits: 64%/13180 🟩 arm64 Pass: 100%/8 | Total: 5h 00m | Avg: 37m 37s | Max: 43m 52s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 9h 21m | Avg: 37m 24s | Max: 1h 06m | Hits: 56%/2636 🟩 11.8 Pass: 100%/3 | Total: 2h 15m | Avg: 45m 05s | Max: 50m 03s 🟩 12.5 Pass: 100%/4 | Total: 5h 13m | Avg: 1h 18m | Max: 1h 26m 🟩 12.6 Pass: 100%/87 | Total: 2d 07h | Avg: 38m 10s | Max: 1h 24m | Hits: 66%/10544 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/4 | Total: 2h 12m | Avg: 33m 01s | Max: 36m 23s 🟩 nvcc11.1 Pass: 100%/15 | Total: 9h 21m | Avg: 37m 24s | Max: 1h 06m | Hits: 56%/2636 🟩 nvcc11.8 Pass: 100%/3 | Total: 2h 15m | Avg: 45m 05s | Max: 50m 03s 🟩 nvcc12.5 Pass: 100%/4 | Total: 5h 13m | Avg: 1h 18m | Max: 1h 26m 🟩 nvcc12.6 Pass: 100%/83 | Total: 2d 05h | Avg: 38m 25s | Max: 1h 24m | Hits: 66%/10544 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/4 | Total: 2h 12m | Avg: 33m 01s | Max: 36m 23s 🟩 nvcc Pass: 100%/105 | Total: 2d 21h | Avg: 39m 59s | Max: 1h 26m | Hits: 64%/13180 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 3h 36m | Avg: 36m 07s | Max: 42m 48s 🟩 Clang10 Pass: 100%/3 | Total: 1h 59m | Avg: 39m 41s | Max: 43m 26s 🟩 Clang11 Pass: 100%/4 | Total: 2h 38m | Avg: 39m 44s | Max: 43m 38s 🟩 Clang12 Pass: 100%/4 | Total: 2h 30m | Avg: 37m 41s | Max: 40m 09s 🟩 Clang13 Pass: 100%/4 | Total: 2h 34m | Avg: 38m 33s | Max: 43m 03s 🟩 Clang14 Pass: 100%/4 | Total: 2h 45m | Avg: 41m 26s | Max: 45m 52s 🟩 Clang15 Pass: 100%/4 | Total: 2h 40m | Avg: 40m 04s | Max: 45m 15s 🟩 Clang16 Pass: 100%/4 | Total: 2h 44m | Avg: 41m 11s | Max: 47m 56s 🟩 Clang17 Pass: 100%/4 | Total: 2h 45m | Avg: 41m 28s | Max: 45m 35s 🟩 Clang18 Pass: 100%/11 | Total: 5h 42m | Avg: 31m 10s | Max: 45m 15s 🟩 GCC6 Pass: 100%/2 | Total: 1h 09m | Avg: 34m 39s | Max: 39m 36s 🟩 GCC7 Pass: 100%/6 | Total: 3h 36m | Avg: 36m 01s | Max: 40m 09s 🟩 GCC8 Pass: 100%/6 | Total: 3h 42m | Avg: 37m 05s | Max: 45m 42s 🟩 GCC9 Pass: 100%/6 | Total: 3h 48m | Avg: 38m 06s | Max: 41m 57s 🟩 GCC10 Pass: 100%/4 | Total: 2h 44m | Avg: 41m 13s | Max: 47m 22s 🟩 GCC11 Pass: 100%/7 | Total: 4h 55m | Avg: 42m 14s | Max: 50m 03s 🟩 GCC12 Pass: 100%/4 | Total: 2h 55m | Avg: 43m 47s | Max: 51m 30s 🟩 GCC13 Pass: 100%/14 | Total: 6h 19m | Avg: 27m 05s | Max: 43m 52s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 39m | Avg: 53m 02s | Max: 59m 07s 🟩 MSVC14.16 Pass: 100%/1 | Total: 1h 06m | Avg: 1h 06m | Max: 1h 06m | Hits: 56%/2636 🟩 MSVC14.29 Pass: 100%/2 | Total: 2h 16m | Avg: 1h 08m | Max: 1h 08m | Hits: 56%/5272 🟩 MSVC14.39 Pass: 100%/2 | Total: 1h 45m | Avg: 52m 34s | Max: 1h 24m | Hits: 76%/5272 🟩 NVHPC24.7 Pass: 100%/4 | Total: 5h 13m | Avg: 1h 18m | Max: 1h 26m 🟩 cxx_family 🟩 Clang Pass: 100%/48 | Total: 1d 05h | Avg: 37m 29s | Max: 47m 56s 🟩 GCC Pass: 100%/49 | Total: 1d 05h | Avg: 35m 44s | Max: 51m 30s 🟩 Intel Pass: 100%/3 | Total: 2h 39m | Avg: 53m 02s | Max: 59m 07s 🟩 MSVC Pass: 100%/5 | Total: 5h 08m | Avg: 1h 01m | Max: 1h 24m | Hits: 64%/13180 🟩 NVHPC Pass: 100%/4 | Total: 5h 13m | Avg: 1h 18m | Max: 1h 26m 🟩 gpu 🟩 v100 Pass: 100%/109 | Total: 3d 00h | Avg: 39m 44s | Max: 1h 26m | Hits: 64%/13180 🟩 jobs 🟩 Build Pass: 100%/102 | Total: 2d 22h | Avg: 41m 37s | Max: 1h 26m | Hits: 55%/10544 🟩 TestCPU Pass: 100%/4 | Total: 46m 55s | Avg: 11m 43s | Max: 21m 03s | Hits: 99%/2636 🟩 TestGPU Pass: 100%/3 | Total: 39m 07s | Avg: 13m 02s | Max: 15m 11s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 2h 15m | Avg: 45m 05s | Max: 50m 03s 🟩 90a Pass: 100%/4 | Total: 1h 46m | Avg: 26m 34s | Max: 32m 01s 🟩 std 🟩 11 Pass: 100%/30 | Total: 16h 18m | Avg: 32m 36s | Max: 1h 05m 🟩 14 Pass: 100%/29 | Total: 20h 34m | Avg: 42m 33s | Max: 1h 20m | Hits: 57%/5272 🟩 17 Pass: 100%/27 | Total: 20h 02m | Avg: 44m 31s | Max: 1h 20m | Hits: 53%/2636 🟩 20 Pass: 100%/23 | Total: 15h 17m | Avg: 39m 52s | Max: 1h 26m | Hits: 76%/5272 -
🟩 cudax: Pass: 100%/54 | Total: 4h 31m | Avg: 5m 01s | Max: 18m 25s | Hits: 87%/238
🟩 cpu 🟩 amd64 Pass: 100%/50 | Total: 4h 17m | Avg: 5m 08s | Max: 18m 25s | Hits: 87%/238 🟩 arm64 Pass: 100%/4 | Total: 13m 54s | Avg: 3m 28s | Max: 3m 42s 🟩 ctk 🟩 12.0 Pass: 100%/19 | Total: 1h 33m | Avg: 4m 53s | Max: 16m 55s | Hits: 87%/119 🟩 12.5 Pass: 100%/2 | Total: 10m 39s | Avg: 5m 19s | Max: 5m 22s 🟩 12.6 Pass: 100%/33 | Total: 2h 47m | Avg: 5m 04s | Max: 18m 25s | Hits: 87%/119 🟩 cudacxx 🟩 nvcc12.0 Pass: 100%/19 | Total: 1h 33m | Avg: 4m 53s | Max: 16m 55s | Hits: 87%/119 🟩 nvcc12.5 Pass: 100%/2 | Total: 10m 39s | Avg: 5m 19s | Max: 5m 22s 🟩 nvcc12.6 Pass: 100%/33 | Total: 2h 47m | Avg: 5m 04s | Max: 18m 25s | Hits: 87%/119 🟩 cudacxx_family 🟩 nvcc Pass: 100%/54 | Total: 4h 31m | Avg: 5m 01s | Max: 18m 25s | Hits: 87%/238 🟩 cxx 🟩 Clang9 Pass: 100%/2 | Total: 8m 04s | Avg: 4m 02s | Max: 4m 19s 🟩 Clang10 Pass: 100%/2 | Total: 7m 35s | Avg: 3m 47s | Max: 4m 03s 🟩 Clang11 Pass: 100%/4 | Total: 14m 17s | Avg: 3m 34s | Max: 3m 54s 🟩 Clang12 Pass: 100%/4 | Total: 13m 46s | Avg: 3m 26s | Max: 3m 46s 🟩 Clang13 Pass: 100%/4 | Total: 13m 47s | Avg: 3m 26s | Max: 3m 40s 🟩 Clang14 Pass: 100%/4 | Total: 26m 22s | Avg: 6m 35s | Max: 15m 18s 🟩 Clang15 Pass: 100%/2 | Total: 7m 17s | Avg: 3m 38s | Max: 3m 40s 🟩 Clang16 Pass: 100%/4 | Total: 14m 52s | Avg: 3m 43s | Max: 3m 59s 🟩 Clang17 Pass: 100%/2 | Total: 7m 19s | Avg: 3m 39s | Max: 3m 41s 🟩 Clang18 Pass: 100%/2 | Total: 21m 29s | Avg: 10m 44s | Max: 17m 38s 🟩 GCC9 Pass: 100%/2 | Total: 6m 46s | Avg: 3m 23s | Max: 3m 33s 🟩 GCC10 Pass: 100%/4 | Total: 13m 46s | Avg: 3m 26s | Max: 3m 28s 🟩 GCC11 Pass: 100%/4 | Total: 13m 55s | Avg: 3m 28s | Max: 3m 48s 🟩 GCC12 Pass: 100%/7 | Total: 1h 06m | Avg: 9m 31s | Max: 18m 25s 🟩 GCC13 Pass: 100%/3 | Total: 9m 52s | Avg: 3m 17s | Max: 3m 21s 🟩 MSVC14.36 Pass: 100%/1 | Total: 6m 58s | Avg: 6m 58s | Max: 6m 58s | Hits: 87%/119 🟩 MSVC14.39 Pass: 100%/1 | Total: 7m 56s | Avg: 7m 56s | Max: 7m 56s | Hits: 87%/119 🟩 NVHPC24.7 Pass: 100%/2 | Total: 10m 39s | Avg: 5m 19s | Max: 5m 22s 🟩 cxx_family 🟩 Clang Pass: 100%/30 | Total: 2h 14m | Avg: 4m 29s | Max: 17m 38s 🟩 GCC Pass: 100%/20 | Total: 1h 50m | Avg: 5m 32s | Max: 18m 25s 🟩 MSVC Pass: 100%/2 | Total: 14m 54s | Avg: 7m 27s | Max: 7m 56s | Hits: 87%/238 🟩 NVHPC Pass: 100%/2 | Total: 10m 39s | Avg: 5m 19s | Max: 5m 22s 🟩 gpu 🟩 v100 Pass: 100%/54 | Total: 4h 31m | Avg: 5m 01s | Max: 18m 25s | Hits: 87%/238 🟩 jobs 🟩 Build Pass: 100%/49 | Total: 3h 05m | Avg: 3m 47s | Max: 7m 56s | Hits: 87%/238 🟩 Test Pass: 100%/5 | Total: 1h 25m | Avg: 17m 03s | Max: 18m 25s 🟩 sm 🟩 90 Pass: 100%/1 | Total: 2m 58s | Avg: 2m 58s | Max: 2m 58s 🟩 90a Pass: 100%/1 | Total: 3m 18s | Avg: 3m 18s | Max: 3m 18s 🟩 std 🟩 17 Pass: 100%/29 | Total: 2h 11m | Avg: 4m 32s | Max: 17m 02s 🟩 20 Pass: 100%/25 | Total: 2h 19m | Avg: 5m 35s | Max: 18m 25s | Hits: 87%/238 -
🟩 cccl_c_parallel: Pass: 100%/2 | Total: 10m 08s | Avg: 5m 04s | Max: 8m 01s
🟩 cpu 🟩 amd64 Pass: 100%/2 | Total: 10m 08s | Avg: 5m 04s | Max: 8m 01s 🟩 ctk 🟩 12.6 Pass: 100%/2 | Total: 10m 08s | Avg: 5m 04s | Max: 8m 01s 🟩 cudacxx 🟩 nvcc12.6 Pass: 100%/2 | Total: 10m 08s | Avg: 5m 04s | Max: 8m 01s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/2 | Total: 10m 08s | Avg: 5m 04s | Max: 8m 01s 🟩 cxx 🟩 GCC13 Pass: 100%/2 | Total: 10m 08s | Avg: 5m 04s | Max: 8m 01s 🟩 cxx_family 🟩 GCC Pass: 100%/2 | Total: 10m 08s | Avg: 5m 04s | Max: 8m 01s 🟩 gpu 🟩 v100 Pass: 100%/2 | Total: 10m 08s | Avg: 5m 04s | Max: 8m 01s 🟩 jobs 🟩 Build Pass: 100%/1 | Total: 2m 07s | Avg: 2m 07s | Max: 2m 07s 🟩 Test Pass: 100%/1 | Total: 8m 01s | Avg: 8m 01s | Max: 8m 01s -
🟩 python: Pass: 100%/1 | Total: 25m 59s | Avg: 25m 59s | Max: 25m 59s
🟩 cpu 🟩 amd64 Pass: 100%/1 | Total: 25m 59s | Avg: 25m 59s | Max: 25m 59s 🟩 ctk 🟩 12.6 Pass: 100%/1 | Total: 25m 59s | Avg: 25m 59s | Max: 25m 59s 🟩 cudacxx 🟩 nvcc12.6 Pass: 100%/1 | Total: 25m 59s | Avg: 25m 59s | Max: 25m 59s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/1 | Total: 25m 59s | Avg: 25m 59s | Max: 25m 59s 🟩 cxx 🟩 GCC13 Pass: 100%/1 | Total: 25m 59s | Avg: 25m 59s | Max: 25m 59s 🟩 cxx_family 🟩 GCC Pass: 100%/1 | Total: 25m 59s | Avg: 25m 59s | Max: 25m 59s 🟩 gpu 🟩 v100 Pass: 100%/1 | Total: 25m 59s | Avg: 25m 59s | Max: 25m 59s 🟩 jobs 🟩 Test Pass: 100%/1 | Total: 25m 59s | Avg: 25m 59s | Max: 25m 59s
👃 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: 394)
| # | Runner |
|---|---|
| 326 | linux-amd64-cpu16 |
| 28 | linux-arm64-cpu16 |
| 25 | linux-amd64-gpu-v100-latest-1 |
| 15 | windows-amd64-cpu16 |
Added benchmark on H200 (PR description). Looking good except our fibonaccy transformation:
For the U32 2^20 fibonacci benchmark, we are launching 2048 blocks before and 683 blocks after. Achieved occupancy decreased by 36% (although theoretical occupancy did not). H200 has 144 SMs, which results in 113.7 (before) and 37.9 (after) warps per SM. The latter is smaller than the maximum number of resident warps per SM (48).
Playing around a bit, I new assume the slowdown could be caused by the work division, especially items per thread and distribution of blocks to SMs.
I made a few attempts at tuning how we compute items per thread. Diff of proposed implementation with new items per thread logic on H200 with 132 SMs:
* at least 2 blocks / 16 warps per SM
| U32 | 2^16 | 11.732 us | 7.70% | 11.660 us | 7.61% | -0.073 us | -0.62% | PASS |
| U32 | 2^20 | 18.633 us | 2.29% | 18.408 us | 2.25% | -0.224 us | -1.20% | PASS |
| U32 | 2^24 | 90.927 us | 0.47% | 90.719 us | 0.45% | -0.208 us | -0.23% | PASS |
| U32 | 2^28 | 1.258 ms | 7.80% | 1.258 ms | 7.85% | -0.314 us | -0.02% | PASS |
* at least 4 blocks / 32 warps per SM
| U32 | 2^16 | 11.732 us | 7.70% | 12.027 us | 7.77% | 0.295 us | 2.51% | PASS |
| U32 | 2^20 | 18.633 us | 2.29% | 18.579 us | 2.20% | -0.054 us | -0.29% | PASS |
| U32 | 2^24 | 90.927 us | 0.47% | 90.959 us | 0.44% | 0.032 us | 0.03% | PASS |
| U32 | 2^28 | 1.258 ms | 7.80% | 1.258 ms | 7.88% | -0.215 us | -0.02% | PASS |
* at least 8 blocks / 64 warps per SM
| U32 | 2^16 | 11.732 us | 7.70% | 11.627 us | 6.16% | -0.105 us | -0.90% | PASS |
| U32 | 2^20 | 18.633 us | 2.29% | 17.322 us | 2.23% | -1.311 us | -7.03% | FAIL |
| U32 | 2^24 | 90.927 us | 0.47% | 90.750 us | 0.41% | -0.177 us | -0.20% | PASS |
| U32 | 2^28 | 1.258 ms | 7.80% | 1.258 ms | 8.89% | 0.600 us | 0.05% | PASS |
* at least 16 blocks / 128 warps per SM:
| U32 | 2^16 | 11.732 us | 7.70% | 11.620 us | 5.30% | -0.112 us | -0.96% | PASS |
| U32 | 2^20 | 18.633 us | 2.29% | 17.461 us | 3.22% | -1.172 us | -6.29% | FAIL |
| U32 | 2^24 | 90.927 us | 0.47% | 91.106 us | 0.46% | 0.179 us | 0.20% | PASS |
| U32 | 2^28 | 1.258 ms | 7.80% | 1.256 ms | 4.94% | -2.113 us | -0.17% | PASS |
Almost no impact in the U64 runs
* Setting minimum elements per thread to 2 via tuning policy:
| U32 | 2^16 | 11.732 us | 7.70% | 11.769 us | 6.23% | 0.037 us | 0.31% | PASS |
| U32 | 2^20 | 18.633 us | 2.29% | 18.305 us | 2.29% | -0.328 us | -1.76% | PASS |
| U32 | 2^24 | 90.927 us | 0.47% | 90.953 us | 0.45% | 0.025 us | 0.03% | PASS |
| U32 | 2^28 | 1.258 ms | 7.80% | 1.253 ms | 0.13% | -4.840 us | -0.38% | FAIL |
| U64 | 2^16 | 11.795 us | 4.14% | 12.554 us | 3.76% | 0.759 us | 6.43% | FAIL |
| U64 | 2^20 | 18.442 us | 2.36% | 18.380 us | 2.22% | -0.062 us | -0.34% | PASS |
| U64 | 2^24 | 102.268 us | 0.55% | 102.100 us | 0.48% | -0.168 us | -0.16% | PASS |
| U64 | 2^28 | 1.445 ms | 0.05% | 1.450 ms | 6.77% | 5.086 us | 0.35% | FAIL |
* Hardcoding elements per thread to 2:
| U32 | 2^16 | 12.215 us | 9.17% | 11.009 us | 10.98% | -1.206 us | -9.87% | FAIL |
| U32 | 2^20 | 16.459 us | 3.12% | 14.886 us | 2.83% | -1.574 us | -9.56% | FAIL |
| U32 | 2^24 | 88.903 us | 0.56% | 92.387 us | 0.58% | 3.484 us | 3.92% | FAIL |
| U32 | 2^28 | 1.240 ms | 0.05% | 1.333 ms | 4.95% | 92.328 us | 7.44% | FAIL |
| U64 | 2^16 | 12.660 us | 4.74% | 10.177 us | 3.65% | -2.483 us | -19.62% | FAIL |
| U64 | 2^20 | 17.940 us | 3.40% | 15.717 us | 2.39% | -2.223 us | -12.39% | FAIL |
| U64 | 2^24 | 105.743 us | 0.46% | 101.769 us | 0.44% | -3.974 us | -3.76% | FAIL |
| U64 | 2^28 | 1.512 ms | 3.87% | 1.481 ms | 0.04% | -31.696 us | -2.10% | FAIL |
The last is also what the previous implementation (based on `cub::DeviceFor`) did, which works good for small problem sizes but is worse for larger ones.
Alright, the fix best fitting into the existing work divison model is:
const int items_per_thread_evenly_spread =
- static_cast<int>(::cuda::std::min(Offset{items_per_thread}, num_items / (config->sm_count * block_dim)));
+ static_cast<int>(::cuda::std::min(Offset{items_per_thread}, num_items / (config->sm_count * block_dim * config->max_occupancy)));
which maximizes occupancy for small problem sizes. That is, if the computed items per thread to sustain peak bytes in flight would lead to insufficient blocks to fill, or evenly fill, all SMs, we rather process less data per block and generate more blocks to max out the device.
ncu is also indicating something like that in the PM Samling:
Before:
After:
We can see that before we launched a lot more blocks, but the SMs were maxed out.
Should this use cuda::ceil_div for that calculation rather than /
Should this use
cuda::ceil_divfor that calculation rather than/
I was actually more leaning towards round(). The division computes the number of items per thread to produce enough blocks to max out the device. If that number is e.g. 3.4 items, running with 4 (ceil_div) would produce too little blocks, running with 3 (integer division) will oversubscribe the device.
I am going to benchmark the new version soon, so I can also include ceil_div. It's a heuristic after all, so I take what works best :)
I am going to benchmark the new version soon, so I can also include
ceil_div. It's a heuristic after all, so I take what works best :)
Well, it's rather inconclusive. Normal division is about 1% faster on H100, and about 1% slower on H200. I will leave the code as is then.
I think I am happy with the result. I only violate the "no regressions of more than 2% compared to previous implementation on 2^24+ problem sizes" rule for the fibonacci benchmark that @gevtushenko gave me a while back. We need 2.5%:
## [0] NVIDIA H100 NVL
| U32 | 2^24 | 96.316 us | 0.49% | 98.619 us | 0.30% | 2.303 us | 2.39% | FAIL |
## [0] NVIDIA H200
| U32 | 2^24 | 88.994 us | 0.57% | 90.992 us | 0.59% | 1.998 us | 2.25% | FAIL |
🟩 CI finished in 2h 22m: Pass: 100%/394 | Total: 8d 06h | Avg: 30m 14s | Max: 1h 26m | Hits: 61%/25850
-
🟩 libcudacxx: Pass: 100%/118 | Total: 1d 02h | Avg: 13m 29s | Max: 49m 23s | Hits: 72%/9484
🟩 cpu 🟩 amd64 Pass: 100%/110 | Total: 1d 01h | Avg: 13m 49s | Max: 49m 23s | Hits: 72%/9484 🟩 arm64 Pass: 100%/8 | Total: 1h 11m | Avg: 8m 55s | Max: 22m 28s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 2h 54m | Avg: 11m 39s | Max: 24m 40s | Hits: 98%/2177 🟩 11.8 Pass: 100%/3 | Total: 1h 12m | Avg: 24m 08s | Max: 30m 42s 🟩 12.5 Pass: 100%/4 | Total: 1h 41m | Avg: 25m 29s | Max: 39m 37s 🟩 12.6 Pass: 100%/96 | Total: 20h 42m | Avg: 12m 56s | Max: 49m 23s | Hits: 65%/7307 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/12 | Total: 2h 30m | Avg: 12m 31s | Max: 22m 37s 🟩 nvcc11.1 Pass: 100%/15 | Total: 2h 54m | Avg: 11m 39s | Max: 24m 40s | Hits: 98%/2177 🟩 nvcc11.8 Pass: 100%/3 | Total: 1h 12m | Avg: 24m 08s | Max: 30m 42s 🟩 nvcc12.5 Pass: 100%/4 | Total: 1h 41m | Avg: 25m 29s | Max: 39m 37s 🟩 nvcc12.6 Pass: 100%/84 | Total: 18h 12m | Avg: 13m 00s | Max: 49m 23s | Hits: 65%/7307 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/12 | Total: 2h 30m | Avg: 12m 31s | Max: 22m 37s 🟩 nvcc Pass: 100%/106 | Total: 1d 00h | Avg: 13m 36s | Max: 49m 23s | Hits: 72%/9484 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 49m 33s | Avg: 8m 15s | Max: 13m 59s 🟩 Clang10 Pass: 100%/3 | Total: 48m 49s | Avg: 16m 16s | Max: 32m 14s 🟩 Clang11 Pass: 100%/4 | Total: 58m 45s | Avg: 14m 41s | Max: 27m 47s 🟩 Clang12 Pass: 100%/4 | Total: 29m 22s | Avg: 7m 20s | Max: 16m 32s 🟩 Clang13 Pass: 100%/4 | Total: 1h 00m | Avg: 15m 04s | Max: 29m 14s 🟩 Clang14 Pass: 100%/4 | Total: 1h 06m | Avg: 16m 40s | Max: 26m 32s 🟩 Clang15 Pass: 100%/4 | Total: 1h 18m | Avg: 19m 37s | Max: 26m 51s 🟩 Clang16 Pass: 100%/4 | Total: 41m 45s | Avg: 10m 26s | Max: 15m 27s 🟩 Clang17 Pass: 100%/4 | Total: 44m 15s | Avg: 11m 03s | Max: 16m 18s 🟩 Clang18 Pass: 100%/18 | Total: 4h 08m | Avg: 13m 49s | Max: 49m 23s 🟩 GCC6 Pass: 100%/2 | Total: 39m 09s | Avg: 19m 34s | Max: 20m 13s 🟩 GCC7 Pass: 100%/6 | Total: 40m 25s | Avg: 6m 44s | Max: 24m 44s 🟩 GCC8 Pass: 100%/6 | Total: 48m 41s | Avg: 8m 06s | Max: 24m 40s 🟩 GCC9 Pass: 100%/6 | Total: 1h 07m | Avg: 11m 10s | Max: 23m 37s 🟩 GCC10 Pass: 100%/4 | Total: 54m 59s | Avg: 13m 44s | Max: 27m 21s 🟩 GCC11 Pass: 100%/7 | Total: 2h 18m | Avg: 19m 51s | Max: 30m 42s 🟩 GCC12 Pass: 100%/4 | Total: 55m 00s | Avg: 13m 45s | Max: 30m 48s 🟩 GCC13 Pass: 100%/17 | Total: 3h 15m | Avg: 11m 30s | Max: 29m 26s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 29m 31s | Avg: 9m 50s | Max: 18m 23s 🟩 MSVC14.16 Pass: 100%/1 | Total: 17m 40s | Avg: 17m 40s | Max: 17m 40s | Hits: 98%/2177 🟩 MSVC14.29 Pass: 100%/2 | Total: 47m 03s | Avg: 23m 31s | Max: 35m 21s | Hits: 63%/4717 🟩 MSVC14.39 Pass: 100%/1 | Total: 29m 07s | Avg: 29m 07s | Max: 29m 07s | Hits: 67%/2590 🟩 NVHPC24.7 Pass: 100%/4 | Total: 1h 41m | Avg: 25m 29s | Max: 39m 37s 🟩 cxx_family 🟩 Clang Pass: 100%/55 | Total: 12h 06m | Avg: 13m 12s | Max: 49m 23s 🟩 GCC Pass: 100%/52 | Total: 10h 39m | Avg: 12m 18s | Max: 30m 48s 🟩 Intel Pass: 100%/3 | Total: 29m 31s | Avg: 9m 50s | Max: 18m 23s 🟩 MSVC Pass: 100%/4 | Total: 1h 33m | Avg: 23m 27s | Max: 35m 21s | Hits: 72%/9484 🟩 NVHPC Pass: 100%/4 | Total: 1h 41m | Avg: 25m 29s | Max: 39m 37s 🟩 gpu 🟩 v100 Pass: 100%/118 | Total: 1d 02h | Avg: 13m 29s | Max: 49m 23s | Hits: 72%/9484 🟩 jobs 🟩 Build Pass: 100%/110 | Total: 23h 27m | Avg: 12m 47s | Max: 39m 37s | Hits: 72%/9484 🟩 NVRTC Pass: 100%/4 | Total: 1h 26m | Avg: 21m 35s | Max: 23m 08s 🟩 Test Pass: 100%/3 | Total: 1h 35m | Avg: 31m 57s | Max: 49m 23s 🟩 VerifyCodegen Pass: 100%/1 | Total: 2m 02s | Avg: 2m 02s | Max: 2m 02s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 1h 12m | Avg: 24m 08s | Max: 30m 42s 🟩 90 Pass: 100%/4 | Total: 40m 38s | Avg: 10m 09s | Max: 12m 10s 🟩 90a Pass: 100%/8 | Total: 56m 38s | Avg: 7m 04s | Max: 11m 39s 🟩 std 🟩 11 Pass: 100%/32 | Total: 5h 21m | Avg: 10m 02s | Max: 29m 26s 🟩 14 Pass: 100%/32 | Total: 5h 57m | Avg: 11m 11s | Max: 31m 45s | Hits: 98%/4457 🟩 17 Pass: 100%/30 | Total: 7h 55m | Avg: 15m 51s | Max: 35m 21s | Hits: 30%/2437 🟩 20 Pass: 100%/23 | Total: 7h 15m | Avg: 18m 56s | Max: 49m 23s | Hits: 67%/2590 -
🟩 cub: Pass: 100%/110 | Total: 3d 21h | Avg: 51m 02s | Max: 1h 14m | Hits: 64%/2948
🟩 cpu 🟩 amd64 Pass: 100%/102 | Total: 3d 14h | Avg: 50m 41s | Max: 1h 14m | Hits: 64%/2948 🟩 arm64 Pass: 100%/8 | Total: 7h 24m | Avg: 55m 33s | Max: 1h 01m 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 11h 42m | Avg: 46m 48s | Max: 50m 21s | Hits: 64%/737 🟩 11.8 Pass: 100%/3 | Total: 3h 30m | Avg: 1h 10m | Max: 1h 14m 🟩 12.5 Pass: 100%/4 | Total: 4h 06m | Avg: 1h 01m | Max: 1h 08m 🟩 12.6 Pass: 100%/88 | Total: 3d 02h | Avg: 50m 37s | Max: 1h 03m | Hits: 64%/2211 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/4 | Total: 3h 58m | Avg: 59m 44s | Max: 1h 01m 🟩 nvcc11.1 Pass: 100%/15 | Total: 11h 42m | Avg: 46m 48s | Max: 50m 21s | Hits: 64%/737 🟩 nvcc11.8 Pass: 100%/3 | Total: 3h 30m | Avg: 1h 10m | Max: 1h 14m 🟩 nvcc12.5 Pass: 100%/4 | Total: 4h 06m | Avg: 1h 01m | Max: 1h 08m 🟩 nvcc12.6 Pass: 100%/84 | Total: 2d 22h | Avg: 50m 11s | Max: 1h 03m | Hits: 64%/2211 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/4 | Total: 3h 58m | Avg: 59m 44s | Max: 1h 01m 🟩 nvcc Pass: 100%/106 | Total: 3d 17h | Avg: 50m 42s | Max: 1h 14m | Hits: 64%/2948 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 4h 47m | Avg: 47m 53s | Max: 53m 10s 🟩 Clang10 Pass: 100%/3 | Total: 2h 43m | Avg: 54m 38s | Max: 56m 55s 🟩 Clang11 Pass: 100%/4 | Total: 3h 32m | Avg: 53m 03s | Max: 57m 33s 🟩 Clang12 Pass: 100%/4 | Total: 3h 34m | Avg: 53m 39s | Max: 55m 55s 🟩 Clang13 Pass: 100%/4 | Total: 3h 25m | Avg: 51m 22s | Max: 53m 41s 🟩 Clang14 Pass: 100%/4 | Total: 3h 32m | Avg: 53m 13s | Max: 55m 08s 🟩 Clang15 Pass: 100%/4 | Total: 3h 42m | Avg: 55m 38s | Max: 57m 47s 🟩 Clang16 Pass: 100%/4 | Total: 3h 29m | Avg: 52m 23s | Max: 54m 42s 🟩 Clang17 Pass: 100%/4 | Total: 3h 31m | Avg: 52m 52s | Max: 57m 08s 🟩 Clang18 Pass: 100%/11 | Total: 9h 43m | Avg: 53m 05s | Max: 1h 01m 🟩 GCC6 Pass: 100%/2 | Total: 1h 37m | Avg: 48m 57s | Max: 49m 15s 🟩 GCC7 Pass: 100%/6 | Total: 4h 51m | Avg: 48m 37s | Max: 56m 06s 🟩 GCC8 Pass: 100%/6 | Total: 4h 59m | Avg: 49m 59s | Max: 53m 25s 🟩 GCC9 Pass: 100%/6 | Total: 5h 06m | Avg: 51m 05s | Max: 53m 46s 🟩 GCC10 Pass: 100%/4 | Total: 3h 46m | Avg: 56m 40s | Max: 58m 10s 🟩 GCC11 Pass: 100%/7 | Total: 7h 08m | Avg: 1h 01m | Max: 1h 14m 🟩 GCC12 Pass: 100%/4 | Total: 3h 31m | Avg: 52m 47s | Max: 55m 33s 🟩 GCC13 Pass: 100%/16 | Total: 9h 34m | Avg: 35m 54s | Max: 57m 17s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 59m | Avg: 59m 46s | Max: 1h 02m 🟩 MSVC14.16 Pass: 100%/1 | Total: 49m 56s | Avg: 49m 56s | Max: 49m 56s | Hits: 64%/737 🟩 MSVC14.29 Pass: 100%/2 | Total: 1h 53m | Avg: 56m 48s | Max: 58m 11s | Hits: 64%/1474 🟩 MSVC14.39 Pass: 100%/1 | Total: 1h 03m | Avg: 1h 03m | Max: 1h 03m | Hits: 64%/737 🟩 NVHPC24.7 Pass: 100%/4 | Total: 4h 06m | Avg: 1h 01m | Max: 1h 08m 🟩 cxx_family 🟩 Clang Pass: 100%/48 | Total: 1d 18h | Avg: 52m 35s | Max: 1h 01m 🟩 GCC Pass: 100%/51 | Total: 1d 16h | Avg: 47m 47s | Max: 1h 14m 🟩 Intel Pass: 100%/3 | Total: 2h 59m | Avg: 59m 46s | Max: 1h 02m 🟩 MSVC Pass: 100%/4 | Total: 3h 46m | Avg: 56m 44s | Max: 1h 03m | Hits: 64%/2948 🟩 NVHPC Pass: 100%/4 | Total: 4h 06m | Avg: 1h 01m | Max: 1h 08m 🟩 gpu 🟩 v100 Pass: 100%/110 | Total: 3d 21h | Avg: 51m 02s | Max: 1h 14m | Hits: 64%/2948 🟩 jobs 🟩 Build Pass: 100%/102 | Total: 3d 17h | Avg: 52m 56s | Max: 1h 14m | Hits: 64%/2948 🟩 DeviceLaunch Pass: 100%/1 | Total: 22m 58s | Avg: 22m 58s | Max: 22m 58s 🟩 GraphCapture Pass: 100%/1 | Total: 21m 35s | Avg: 21m 35s | Max: 21m 35s 🟩 HostLaunch Pass: 100%/3 | Total: 1h 33m | Avg: 31m 15s | Max: 36m 13s 🟩 TestGPU Pass: 100%/3 | Total: 1h 16m | Avg: 25m 37s | Max: 30m 09s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 3h 30m | Avg: 1h 10m | Max: 1h 14m 🟩 90a Pass: 100%/4 | Total: 1h 35m | Avg: 23m 57s | Max: 24m 43s 🟩 std 🟩 11 Pass: 100%/30 | Total: 1d 01h | Avg: 50m 51s | Max: 1h 08m 🟩 14 Pass: 100%/29 | Total: 1d 01h | Avg: 52m 40s | Max: 1h 07m | Hits: 64%/1474 🟩 17 Pass: 100%/27 | Total: 23h 55m | Avg: 53m 09s | Max: 1h 14m | Hits: 64%/737 🟩 20 Pass: 100%/24 | Total: 18h 46m | Avg: 46m 55s | Max: 1h 08m | Hits: 64%/737 -
🟩 thrust: Pass: 100%/109 | Total: 3d 01h | Avg: 40m 24s | Max: 1h 26m | Hits: 51%/13180
🟩 cpu 🟩 amd64 Pass: 100%/101 | Total: 2d 20h | Avg: 40m 36s | Max: 1h 26m | Hits: 51%/13180 🟩 arm64 Pass: 100%/8 | Total: 5h 03m | Avg: 37m 56s | Max: 43m 58s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 9h 25m | Avg: 37m 40s | Max: 1h 15m | Hits: 39%/2636 🟩 11.8 Pass: 100%/3 | Total: 2h 18m | Avg: 46m 08s | Max: 52m 53s 🟩 12.5 Pass: 100%/4 | Total: 5h 02m | Avg: 1h 15m | Max: 1h 26m 🟩 12.6 Pass: 100%/87 | Total: 2d 08h | Avg: 39m 04s | Max: 1h 19m | Hits: 54%/10544 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/4 | Total: 2h 09m | Avg: 32m 24s | Max: 37m 05s 🟩 nvcc11.1 Pass: 100%/15 | Total: 9h 25m | Avg: 37m 40s | Max: 1h 15m | Hits: 39%/2636 🟩 nvcc11.8 Pass: 100%/3 | Total: 2h 18m | Avg: 46m 08s | Max: 52m 53s 🟩 nvcc12.5 Pass: 100%/4 | Total: 5h 02m | Avg: 1h 15m | Max: 1h 26m 🟩 nvcc12.6 Pass: 100%/83 | Total: 2d 06h | Avg: 39m 23s | Max: 1h 19m | Hits: 54%/10544 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/4 | Total: 2h 09m | Avg: 32m 24s | Max: 37m 05s 🟩 nvcc Pass: 100%/105 | Total: 2d 23h | Avg: 40m 43s | Max: 1h 26m | Hits: 51%/13180 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 3h 39m | Avg: 36m 30s | Max: 40m 20s 🟩 Clang10 Pass: 100%/3 | Total: 2h 02m | Avg: 40m 57s | Max: 43m 52s 🟩 Clang11 Pass: 100%/4 | Total: 2h 38m | Avg: 39m 35s | Max: 43m 05s 🟩 Clang12 Pass: 100%/4 | Total: 2h 36m | Avg: 39m 02s | Max: 43m 53s 🟩 Clang13 Pass: 100%/4 | Total: 2h 39m | Avg: 39m 55s | Max: 44m 34s 🟩 Clang14 Pass: 100%/4 | Total: 2h 40m | Avg: 40m 07s | Max: 45m 51s 🟩 Clang15 Pass: 100%/4 | Total: 2h 49m | Avg: 42m 16s | Max: 46m 51s 🟩 Clang16 Pass: 100%/4 | Total: 2h 48m | Avg: 42m 11s | Max: 48m 31s 🟩 Clang17 Pass: 100%/4 | Total: 2h 48m | Avg: 42m 07s | Max: 47m 34s 🟩 Clang18 Pass: 100%/11 | Total: 5h 50m | Avg: 31m 52s | Max: 39m 53s 🟩 GCC6 Pass: 100%/2 | Total: 1h 07m | Avg: 33m 38s | Max: 38m 53s 🟩 GCC7 Pass: 100%/6 | Total: 3h 43m | Avg: 37m 14s | Max: 44m 36s 🟩 GCC8 Pass: 100%/6 | Total: 3h 45m | Avg: 37m 31s | Max: 42m 59s 🟩 GCC9 Pass: 100%/6 | Total: 3h 59m | Avg: 39m 53s | Max: 49m 15s 🟩 GCC10 Pass: 100%/4 | Total: 2h 45m | Avg: 41m 17s | Max: 47m 46s 🟩 GCC11 Pass: 100%/7 | Total: 5h 10m | Avg: 44m 19s | Max: 52m 53s 🟩 GCC12 Pass: 100%/4 | Total: 2h 48m | Avg: 42m 05s | Max: 45m 30s 🟩 GCC13 Pass: 100%/14 | Total: 6h 39m | Avg: 28m 31s | Max: 43m 58s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 34m | Avg: 51m 22s | Max: 59m 24s 🟩 MSVC14.16 Pass: 100%/1 | Total: 1h 15m | Avg: 1h 15m | Max: 1h 15m | Hits: 39%/2636 🟩 MSVC14.29 Pass: 100%/2 | Total: 2h 19m | Avg: 1h 09m | Max: 1h 13m | Hits: 40%/5272 🟩 MSVC14.39 Pass: 100%/2 | Total: 1h 41m | Avg: 50m 48s | Max: 1h 19m | Hits: 69%/5272 🟩 NVHPC24.7 Pass: 100%/4 | Total: 5h 02m | Avg: 1h 15m | Max: 1h 26m 🟩 cxx_family 🟩 Clang Pass: 100%/48 | Total: 1d 06h | Avg: 38m 11s | Max: 48m 31s 🟩 GCC Pass: 100%/49 | Total: 1d 05h | Avg: 36m 41s | Max: 52m 53s 🟩 Intel Pass: 100%/3 | Total: 2h 34m | Avg: 51m 22s | Max: 59m 24s 🟩 MSVC Pass: 100%/5 | Total: 5h 16m | Avg: 1h 03m | Max: 1h 19m | Hits: 51%/13180 🟩 NVHPC Pass: 100%/4 | Total: 5h 02m | Avg: 1h 15m | Max: 1h 26m 🟩 gpu 🟩 v100 Pass: 100%/109 | Total: 3d 01h | Avg: 40m 24s | Max: 1h 26m | Hits: 51%/13180 🟩 jobs 🟩 Build Pass: 100%/102 | Total: 2d 23h | Avg: 42m 02s | Max: 1h 26m | Hits: 39%/10544 🟩 TestCPU Pass: 100%/4 | Total: 46m 26s | Avg: 11m 36s | Max: 22m 00s | Hits: 99%/2636 🟩 TestGPU Pass: 100%/3 | Total: 1h 09m | Avg: 23m 13s | Max: 29m 07s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 2h 18m | Avg: 46m 08s | Max: 52m 53s 🟩 90a Pass: 100%/4 | Total: 1h 48m | Avg: 27m 13s | Max: 31m 54s 🟩 std 🟩 11 Pass: 100%/30 | Total: 16h 20m | Avg: 32m 40s | Max: 1h 04m 🟩 14 Pass: 100%/29 | Total: 21h 03m | Avg: 43m 33s | Max: 1h 15m | Hits: 40%/5272 🟩 17 Pass: 100%/27 | Total: 20h 31m | Avg: 45m 36s | Max: 1h 26m | Hits: 39%/2636 🟩 20 Pass: 100%/23 | Total: 15h 30m | Avg: 40m 27s | Max: 1h 19m | Hits: 69%/5272 -
🟩 cudax: Pass: 100%/54 | Total: 4h 41m | Avg: 5m 13s | Max: 19m 29s | Hits: 87%/238
🟩 cpu 🟩 amd64 Pass: 100%/50 | Total: 4h 27m | Avg: 5m 20s | Max: 19m 29s | Hits: 87%/238 🟩 arm64 Pass: 100%/4 | Total: 14m 15s | Avg: 3m 33s | Max: 3m 55s 🟩 ctk 🟩 12.0 Pass: 100%/19 | Total: 1h 42m | Avg: 5m 22s | Max: 19m 29s | Hits: 87%/119 🟩 12.5 Pass: 100%/2 | Total: 10m 55s | Avg: 5m 27s | Max: 5m 29s 🟩 12.6 Pass: 100%/33 | Total: 2h 48m | Avg: 5m 06s | Max: 18m 46s | Hits: 87%/119 🟩 cudacxx 🟩 nvcc12.0 Pass: 100%/19 | Total: 1h 42m | Avg: 5m 22s | Max: 19m 29s | Hits: 87%/119 🟩 nvcc12.5 Pass: 100%/2 | Total: 10m 55s | Avg: 5m 27s | Max: 5m 29s 🟩 nvcc12.6 Pass: 100%/33 | Total: 2h 48m | Avg: 5m 06s | Max: 18m 46s | Hits: 87%/119 🟩 cudacxx_family 🟩 nvcc Pass: 100%/54 | Total: 4h 41m | Avg: 5m 13s | Max: 19m 29s | Hits: 87%/238 🟩 cxx 🟩 Clang9 Pass: 100%/2 | Total: 7m 50s | Avg: 3m 55s | Max: 3m 58s 🟩 Clang10 Pass: 100%/2 | Total: 7m 47s | Avg: 3m 53s | Max: 4m 13s 🟩 Clang11 Pass: 100%/4 | Total: 14m 25s | Avg: 3m 36s | Max: 3m 55s 🟩 Clang12 Pass: 100%/4 | Total: 13m 57s | Avg: 3m 29s | Max: 3m 33s 🟩 Clang13 Pass: 100%/4 | Total: 13m 49s | Avg: 3m 27s | Max: 3m 38s 🟩 Clang14 Pass: 100%/4 | Total: 28m 47s | Avg: 7m 11s | Max: 17m 45s 🟩 Clang15 Pass: 100%/2 | Total: 7m 50s | Avg: 3m 55s | Max: 3m 59s 🟩 Clang16 Pass: 100%/4 | Total: 14m 53s | Avg: 3m 43s | Max: 3m 55s 🟩 Clang17 Pass: 100%/2 | Total: 8m 01s | Avg: 4m 00s | Max: 4m 07s 🟩 Clang18 Pass: 100%/2 | Total: 20m 35s | Avg: 10m 17s | Max: 16m 30s 🟩 GCC9 Pass: 100%/2 | Total: 7m 31s | Avg: 3m 45s | Max: 3m 55s 🟩 GCC10 Pass: 100%/4 | Total: 14m 20s | Avg: 3m 35s | Max: 3m 47s 🟩 GCC11 Pass: 100%/4 | Total: 14m 55s | Avg: 3m 43s | Max: 3m 59s 🟩 GCC12 Pass: 100%/7 | Total: 1h 09m | Avg: 9m 57s | Max: 19m 29s 🟩 GCC13 Pass: 100%/3 | Total: 10m 05s | Avg: 3m 21s | Max: 3m 29s 🟩 MSVC14.36 Pass: 100%/1 | Total: 8m 50s | Avg: 8m 50s | Max: 8m 50s | Hits: 87%/119 🟩 MSVC14.39 Pass: 100%/1 | Total: 7m 29s | Avg: 7m 29s | Max: 7m 29s | Hits: 87%/119 🟩 NVHPC24.7 Pass: 100%/2 | Total: 10m 55s | Avg: 5m 27s | Max: 5m 29s 🟩 cxx_family 🟩 Clang Pass: 100%/30 | Total: 2h 17m | Avg: 4m 35s | Max: 17m 45s 🟩 GCC Pass: 100%/20 | Total: 1h 56m | Avg: 5m 49s | Max: 19m 29s 🟩 MSVC Pass: 100%/2 | Total: 16m 19s | Avg: 8m 09s | Max: 8m 50s | Hits: 87%/238 🟩 NVHPC Pass: 100%/2 | Total: 10m 55s | Avg: 5m 27s | Max: 5m 29s 🟩 gpu 🟩 v100 Pass: 100%/54 | Total: 4h 41m | Avg: 5m 13s | Max: 19m 29s | Hits: 87%/238 🟩 jobs 🟩 Build Pass: 100%/49 | Total: 3h 12m | Avg: 3m 55s | Max: 8m 50s | Hits: 87%/238 🟩 Test Pass: 100%/5 | Total: 1h 29m | Avg: 17m 53s | Max: 19m 29s 🟩 sm 🟩 90 Pass: 100%/1 | Total: 3m 02s | Avg: 3m 02s | Max: 3m 02s 🟩 90a Pass: 100%/1 | Total: 3m 14s | Avg: 3m 14s | Max: 3m 14s 🟩 std 🟩 17 Pass: 100%/29 | Total: 2h 19m | Avg: 4m 48s | Max: 19m 29s 🟩 20 Pass: 100%/25 | Total: 2h 22m | Avg: 5m 40s | Max: 17m 45s | Hits: 87%/238 -
🟩 cccl_c_parallel: Pass: 100%/2 | Total: 9m 35s | Avg: 4m 47s | Max: 7m 31s
🟩 cpu 🟩 amd64 Pass: 100%/2 | Total: 9m 35s | Avg: 4m 47s | Max: 7m 31s 🟩 ctk 🟩 12.6 Pass: 100%/2 | Total: 9m 35s | Avg: 4m 47s | Max: 7m 31s 🟩 cudacxx 🟩 nvcc12.6 Pass: 100%/2 | Total: 9m 35s | Avg: 4m 47s | Max: 7m 31s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/2 | Total: 9m 35s | Avg: 4m 47s | Max: 7m 31s 🟩 cxx 🟩 GCC13 Pass: 100%/2 | Total: 9m 35s | Avg: 4m 47s | Max: 7m 31s 🟩 cxx_family 🟩 GCC Pass: 100%/2 | Total: 9m 35s | Avg: 4m 47s | Max: 7m 31s 🟩 gpu 🟩 v100 Pass: 100%/2 | Total: 9m 35s | Avg: 4m 47s | Max: 7m 31s 🟩 jobs 🟩 Build Pass: 100%/1 | Total: 2m 04s | Avg: 2m 04s | Max: 2m 04s 🟩 Test Pass: 100%/1 | Total: 7m 31s | Avg: 7m 31s | Max: 7m 31s -
🟩 python: Pass: 100%/1 | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s
🟩 cpu 🟩 amd64 Pass: 100%/1 | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s 🟩 ctk 🟩 12.6 Pass: 100%/1 | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s 🟩 cudacxx 🟩 nvcc12.6 Pass: 100%/1 | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/1 | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s 🟩 cxx 🟩 GCC13 Pass: 100%/1 | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s 🟩 cxx_family 🟩 GCC Pass: 100%/1 | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s 🟩 gpu 🟩 v100 Pass: 100%/1 | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s 🟩 jobs 🟩 Test Pass: 100%/1 | Total: 15m 11s | Avg: 15m 11s | Max: 15m 11s
👃 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: 394)
| # | Runner |
|---|---|
| 326 | linux-amd64-cpu16 |
| 28 | linux-arm64-cpu16 |
| 25 | linux-amd64-gpu-v100-latest-1 |
| 15 | windows-amd64-cpu16 |
I only violate the "no regressions of more than 2% compared to previous implementation on 2^24+ problem sizes" rule for the fibonacci benchmark that @gevtushenko gave me a while back. We need 2.5%:
Talked offline with @gevtushenko who is fine with the results.
🟩 CI finished in 1h 55m: Pass: 100%/394 | Total: 8d 00h | Avg: 29m 17s | Max: 1h 23m | Hits: 61%/25866
-
🟩 libcudacxx: Pass: 100%/118 | Total: 18h 16m | Avg: 9m 17s | Max: 37m 47s | Hits: 82%/9500
🟩 cpu 🟩 amd64 Pass: 100%/110 | Total: 16h 56m | Avg: 9m 14s | Max: 37m 47s | Hits: 82%/9500 🟩 arm64 Pass: 100%/8 | Total: 1h 20m | Avg: 10m 02s | Max: 18m 29s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 1h 34m | Avg: 6m 16s | Max: 24m 04s | Hits: 98%/2181 🟩 11.8 Pass: 100%/3 | Total: 59m 31s | Avg: 19m 50s | Max: 31m 33s 🟩 12.5 Pass: 100%/4 | Total: 35m 35s | Avg: 8m 53s | Max: 9m 18s 🟩 12.6 Pass: 100%/96 | Total: 15h 07m | Avg: 9m 27s | Max: 37m 47s | Hits: 78%/7319 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/12 | Total: 2h 27m | Avg: 12m 17s | Max: 21m 54s 🟩 nvcc11.1 Pass: 100%/15 | Total: 1h 34m | Avg: 6m 16s | Max: 24m 04s | Hits: 98%/2181 🟩 nvcc11.8 Pass: 100%/3 | Total: 59m 31s | Avg: 19m 50s | Max: 31m 33s 🟩 nvcc12.5 Pass: 100%/4 | Total: 35m 35s | Avg: 8m 53s | Max: 9m 18s 🟩 nvcc12.6 Pass: 100%/84 | Total: 12h 39m | Avg: 9m 02s | Max: 37m 47s | Hits: 78%/7319 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/12 | Total: 2h 27m | Avg: 12m 17s | Max: 21m 54s 🟩 nvcc Pass: 100%/106 | Total: 15h 49m | Avg: 8m 57s | Max: 37m 47s | Hits: 82%/9500 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 1h 13m | Avg: 12m 11s | Max: 24m 04s 🟩 Clang10 Pass: 100%/3 | Total: 15m 44s | Avg: 5m 14s | Max: 5m 52s 🟩 Clang11 Pass: 100%/4 | Total: 48m 34s | Avg: 12m 08s | Max: 18m 22s 🟩 Clang12 Pass: 100%/4 | Total: 17m 53s | Avg: 4m 28s | Max: 4m 49s 🟩 Clang13 Pass: 100%/4 | Total: 38m 26s | Avg: 9m 36s | Max: 25m 27s 🟩 Clang14 Pass: 100%/4 | Total: 18m 11s | Avg: 4m 32s | Max: 5m 02s 🟩 Clang15 Pass: 100%/4 | Total: 18m 13s | Avg: 4m 33s | Max: 4m 57s 🟩 Clang16 Pass: 100%/4 | Total: 26m 15s | Avg: 6m 33s | Max: 12m 54s 🟩 Clang17 Pass: 100%/4 | Total: 24m 26s | Avg: 6m 06s | Max: 11m 50s 🟩 Clang18 Pass: 100%/18 | Total: 3h 30m | Avg: 11m 42s | Max: 21m 54s 🟩 GCC6 Pass: 100%/2 | Total: 6m 39s | Avg: 3m 19s | Max: 3m 29s 🟩 GCC7 Pass: 100%/6 | Total: 20m 11s | Avg: 3m 21s | Max: 4m 12s 🟩 GCC8 Pass: 100%/6 | Total: 44m 15s | Avg: 7m 22s | Max: 17m 44s 🟩 GCC9 Pass: 100%/6 | Total: 39m 49s | Avg: 6m 38s | Max: 22m 15s 🟩 GCC10 Pass: 100%/4 | Total: 41m 30s | Avg: 10m 22s | Max: 30m 34s 🟩 GCC11 Pass: 100%/7 | Total: 1h 15m | Avg: 10m 45s | Max: 31m 33s 🟩 GCC12 Pass: 100%/4 | Total: 37m 54s | Avg: 9m 28s | Max: 26m 05s 🟩 GCC13 Pass: 100%/17 | Total: 3h 32m | Avg: 12m 28s | Max: 37m 47s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 16m 57s | Avg: 5m 39s | Max: 6m 17s 🟩 MSVC14.16 Pass: 100%/1 | Total: 18m 32s | Avg: 18m 32s | Max: 18m 32s | Hits: 98%/2181 🟩 MSVC14.29 Pass: 100%/2 | Total: 41m 43s | Avg: 20m 51s | Max: 29m 24s | Hits: 67%/4725 🟩 MSVC14.39 Pass: 100%/1 | Total: 14m 38s | Avg: 14m 38s | Max: 14m 38s | Hits: 97%/2594 🟩 NVHPC24.7 Pass: 100%/4 | Total: 35m 35s | Avg: 8m 53s | Max: 9m 18s 🟩 cxx_family 🟩 Clang Pass: 100%/55 | Total: 8h 11m | Avg: 8m 56s | Max: 25m 27s 🟩 GCC Pass: 100%/52 | Total: 7h 57m | Avg: 9m 11s | Max: 37m 47s 🟩 Intel Pass: 100%/3 | Total: 16m 57s | Avg: 5m 39s | Max: 6m 17s 🟩 MSVC Pass: 100%/4 | Total: 1h 14m | Avg: 18m 43s | Max: 29m 24s | Hits: 82%/9500 🟩 NVHPC Pass: 100%/4 | Total: 35m 35s | Avg: 8m 53s | Max: 9m 18s 🟩 gpu 🟩 v100 Pass: 100%/118 | Total: 18h 16m | Avg: 9m 17s | Max: 37m 47s | Hits: 82%/9500 🟩 jobs 🟩 Build Pass: 100%/110 | Total: 15h 28m | Avg: 8m 26s | Max: 31m 33s | Hits: 82%/9500 🟩 NVRTC Pass: 100%/4 | Total: 1h 55m | Avg: 28m 57s | Max: 37m 47s 🟩 Test Pass: 100%/3 | Total: 49m 55s | Avg: 16m 38s | Max: 17m 55s 🟩 VerifyCodegen Pass: 100%/1 | Total: 1m 48s | Avg: 1m 48s | Max: 1m 48s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 59m 31s | Avg: 19m 50s | Max: 31m 33s 🟩 90 Pass: 100%/4 | Total: 42m 16s | Avg: 10m 34s | Max: 12m 52s 🟩 90a Pass: 100%/8 | Total: 55m 52s | Avg: 6m 59s | Max: 11m 43s 🟩 std 🟩 11 Pass: 100%/32 | Total: 3h 52m | Avg: 7m 16s | Max: 21m 32s 🟩 14 Pass: 100%/32 | Total: 4h 57m | Avg: 9m 17s | Max: 35m 01s | Hits: 66%/4465 🟩 17 Pass: 100%/30 | Total: 5h 09m | Avg: 10m 18s | Max: 31m 33s | Hits: 97%/2441 🟩 20 Pass: 100%/23 | Total: 4h 15m | Avg: 11m 06s | Max: 37m 47s | Hits: 97%/2594 -
🟩 cub: Pass: 100%/110 | Total: 3d 22h | Avg: 51m 37s | Max: 1h 14m | Hits: 45%/2948
🟩 cpu 🟩 amd64 Pass: 100%/102 | Total: 3d 15h | Avg: 51m 23s | Max: 1h 14m | Hits: 45%/2948 🟩 arm64 Pass: 100%/8 | Total: 7h 17m | Avg: 54m 39s | Max: 57m 55s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 11h 56m | Avg: 47m 47s | Max: 52m 56s | Hits: 41%/737 🟩 11.8 Pass: 100%/3 | Total: 3h 36m | Avg: 1h 12m | Max: 1h 14m 🟩 12.5 Pass: 100%/4 | Total: 4h 24m | Avg: 1h 06m | Max: 1h 10m 🟩 12.6 Pass: 100%/88 | Total: 3d 02h | Avg: 50m 55s | Max: 1h 02m | Hits: 46%/2211 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/4 | Total: 3h 51m | Avg: 57m 47s | Max: 1h 01m 🟩 nvcc11.1 Pass: 100%/15 | Total: 11h 56m | Avg: 47m 47s | Max: 52m 56s | Hits: 41%/737 🟩 nvcc11.8 Pass: 100%/3 | Total: 3h 36m | Avg: 1h 12m | Max: 1h 14m 🟩 nvcc12.5 Pass: 100%/4 | Total: 4h 24m | Avg: 1h 06m | Max: 1h 10m 🟩 nvcc12.6 Pass: 100%/84 | Total: 2d 22h | Avg: 50m 35s | Max: 1h 02m | Hits: 46%/2211 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/4 | Total: 3h 51m | Avg: 57m 47s | Max: 1h 01m 🟩 nvcc Pass: 100%/106 | Total: 3d 18h | Avg: 51m 23s | Max: 1h 14m | Hits: 45%/2948 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 5h 01m | Avg: 50m 12s | Max: 1h 00m 🟩 Clang10 Pass: 100%/3 | Total: 2h 51m | Avg: 57m 09s | Max: 1h 01m 🟩 Clang11 Pass: 100%/4 | Total: 3h 30m | Avg: 52m 44s | Max: 53m 34s 🟩 Clang12 Pass: 100%/4 | Total: 3h 31m | Avg: 52m 59s | Max: 56m 49s 🟩 Clang13 Pass: 100%/4 | Total: 3h 36m | Avg: 54m 10s | Max: 57m 13s 🟩 Clang14 Pass: 100%/4 | Total: 3h 40m | Avg: 55m 11s | Max: 57m 12s 🟩 Clang15 Pass: 100%/4 | Total: 3h 37m | Avg: 54m 23s | Max: 58m 49s 🟩 Clang16 Pass: 100%/4 | Total: 3h 34m | Avg: 53m 44s | Max: 57m 59s 🟩 Clang17 Pass: 100%/4 | Total: 3h 43m | Avg: 55m 46s | Max: 58m 18s 🟩 Clang18 Pass: 100%/11 | Total: 9h 09m | Avg: 49m 55s | Max: 1h 01m 🟩 GCC6 Pass: 100%/2 | Total: 1h 35m | Avg: 47m 50s | Max: 48m 38s 🟩 GCC7 Pass: 100%/6 | Total: 5h 14m | Avg: 52m 29s | Max: 58m 11s 🟩 GCC8 Pass: 100%/6 | Total: 5h 06m | Avg: 51m 04s | Max: 58m 13s 🟩 GCC9 Pass: 100%/6 | Total: 5h 13m | Avg: 52m 16s | Max: 58m 09s 🟩 GCC10 Pass: 100%/4 | Total: 3h 37m | Avg: 54m 16s | Max: 58m 22s 🟩 GCC11 Pass: 100%/7 | Total: 7h 26m | Avg: 1h 03m | Max: 1h 14m 🟩 GCC12 Pass: 100%/4 | Total: 3h 43m | Avg: 55m 49s | Max: 58m 39s 🟩 GCC13 Pass: 100%/16 | Total: 9h 06m | Avg: 34m 10s | Max: 1h 00m 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 58m | Avg: 59m 36s | Max: 1h 02m 🟩 MSVC14.16 Pass: 100%/1 | Total: 52m 56s | Avg: 52m 56s | Max: 52m 56s | Hits: 41%/737 🟩 MSVC14.29 Pass: 100%/2 | Total: 2h 00m | Avg: 1h 00m | Max: 1h 00m | Hits: 41%/1474 🟩 MSVC14.39 Pass: 100%/1 | Total: 1h 00m | Avg: 1h 00m | Max: 1h 00m | Hits: 58%/737 🟩 NVHPC24.7 Pass: 100%/4 | Total: 4h 24m | Avg: 1h 06m | Max: 1h 10m 🟩 cxx_family 🟩 Clang Pass: 100%/48 | Total: 1d 18h | Avg: 52m 52s | Max: 1h 01m 🟩 GCC Pass: 100%/51 | Total: 1d 17h | Avg: 48m 18s | Max: 1h 14m 🟩 Intel Pass: 100%/3 | Total: 2h 58m | Avg: 59m 36s | Max: 1h 02m 🟩 MSVC Pass: 100%/4 | Total: 3h 53m | Avg: 58m 28s | Max: 1h 00m | Hits: 45%/2948 🟩 NVHPC Pass: 100%/4 | Total: 4h 24m | Avg: 1h 06m | Max: 1h 10m 🟩 gpu 🟩 v100 Pass: 100%/110 | Total: 3d 22h | Avg: 51m 37s | Max: 1h 14m | Hits: 45%/2948 🟩 jobs 🟩 Build Pass: 100%/102 | Total: 3d 19h | Avg: 54m 02s | Max: 1h 14m | Hits: 45%/2948 🟩 DeviceLaunch Pass: 100%/1 | Total: 18m 27s | Avg: 18m 27s | Max: 18m 27s 🟩 GraphCapture Pass: 100%/1 | Total: 17m 15s | Avg: 17m 15s | Max: 17m 15s 🟩 HostLaunch Pass: 100%/3 | Total: 1h 01m | Avg: 20m 31s | Max: 21m 03s 🟩 TestGPU Pass: 100%/3 | Total: 1h 09m | Avg: 23m 19s | Max: 28m 34s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 3h 36m | Avg: 1h 12m | Max: 1h 14m 🟩 90a Pass: 100%/4 | Total: 1h 33m | Avg: 23m 28s | Max: 24m 19s 🟩 std 🟩 11 Pass: 100%/30 | Total: 1d 01h | Avg: 50m 34s | Max: 1h 08m 🟩 14 Pass: 100%/29 | Total: 1d 02h | Avg: 55m 14s | Max: 1h 14m | Hits: 41%/1474 🟩 17 Pass: 100%/27 | Total: 1d 00h | Avg: 54m 07s | Max: 1h 14m | Hits: 41%/737 🟩 20 Pass: 100%/24 | Total: 18h 18m | Avg: 45m 45s | Max: 1h 07m | Hits: 58%/737 -
🟩 thrust: Pass: 100%/109 | Total: 3d 02h | Avg: 40m 49s | Max: 1h 23m | Hits: 48%/13180
🟩 cpu 🟩 amd64 Pass: 100%/101 | Total: 2d 21h | Avg: 41m 04s | Max: 1h 23m | Hits: 48%/13180 🟩 arm64 Pass: 100%/8 | Total: 5h 02m | Avg: 37m 45s | Max: 45m 17s 🟩 ctk 🟩 11.1 Pass: 100%/15 | Total: 9h 37m | Avg: 38m 30s | Max: 1h 15m | Hits: 36%/2636 🟩 11.8 Pass: 100%/3 | Total: 2h 24m | Avg: 48m 07s | Max: 53m 49s 🟩 12.5 Pass: 100%/4 | Total: 5h 13m | Avg: 1h 18m | Max: 1h 22m 🟩 12.6 Pass: 100%/87 | Total: 2d 08h | Avg: 39m 15s | Max: 1h 23m | Hits: 51%/10544 🟩 cudacxx 🟩 ClangCUDA18 Pass: 100%/4 | Total: 2h 15m | Avg: 33m 54s | Max: 41m 08s 🟩 nvcc11.1 Pass: 100%/15 | Total: 9h 37m | Avg: 38m 30s | Max: 1h 15m | Hits: 36%/2636 🟩 nvcc11.8 Pass: 100%/3 | Total: 2h 24m | Avg: 48m 07s | Max: 53m 49s 🟩 nvcc12.5 Pass: 100%/4 | Total: 5h 13m | Avg: 1h 18m | Max: 1h 22m 🟩 nvcc12.6 Pass: 100%/83 | Total: 2d 06h | Avg: 39m 30s | Max: 1h 23m | Hits: 51%/10544 🟩 cudacxx_family 🟩 ClangCUDA Pass: 100%/4 | Total: 2h 15m | Avg: 33m 54s | Max: 41m 08s 🟩 nvcc Pass: 100%/105 | Total: 2d 23h | Avg: 41m 05s | Max: 1h 23m | Hits: 48%/13180 🟩 cxx 🟩 Clang9 Pass: 100%/6 | Total: 3h 37m | Avg: 36m 19s | Max: 44m 50s 🟩 Clang10 Pass: 100%/3 | Total: 2h 07m | Avg: 42m 35s | Max: 47m 32s 🟩 Clang11 Pass: 100%/4 | Total: 2h 45m | Avg: 41m 26s | Max: 44m 54s 🟩 Clang12 Pass: 100%/4 | Total: 2h 39m | Avg: 39m 55s | Max: 45m 17s 🟩 Clang13 Pass: 100%/4 | Total: 2h 45m | Avg: 41m 27s | Max: 47m 06s 🟩 Clang14 Pass: 100%/4 | Total: 2h 44m | Avg: 41m 09s | Max: 45m 46s 🟩 Clang15 Pass: 100%/4 | Total: 2h 37m | Avg: 39m 17s | Max: 41m 17s 🟩 Clang16 Pass: 100%/4 | Total: 2h 46m | Avg: 41m 42s | Max: 47m 37s 🟩 Clang17 Pass: 100%/4 | Total: 2h 41m | Avg: 40m 16s | Max: 43m 40s 🟩 Clang18 Pass: 100%/11 | Total: 5h 57m | Avg: 32m 28s | Max: 44m 42s 🟩 GCC6 Pass: 100%/2 | Total: 1h 09m | Avg: 34m 37s | Max: 36m 32s 🟩 GCC7 Pass: 100%/6 | Total: 3h 51m | Avg: 38m 36s | Max: 46m 49s 🟩 GCC8 Pass: 100%/6 | Total: 3h 46m | Avg: 37m 46s | Max: 43m 31s 🟩 GCC9 Pass: 100%/6 | Total: 3h 59m | Avg: 39m 58s | Max: 45m 53s 🟩 GCC10 Pass: 100%/4 | Total: 2h 50m | Avg: 42m 40s | Max: 47m 32s 🟩 GCC11 Pass: 100%/7 | Total: 5h 08m | Avg: 44m 07s | Max: 53m 49s 🟩 GCC12 Pass: 100%/4 | Total: 2h 52m | Avg: 43m 11s | Max: 50m 51s 🟩 GCC13 Pass: 100%/14 | Total: 6h 28m | Avg: 27m 44s | Max: 45m 17s 🟩 Intel2023.2.0 Pass: 100%/3 | Total: 2h 40m | Avg: 53m 36s | Max: 1h 03m 🟩 MSVC14.16 Pass: 100%/1 | Total: 1h 15m | Avg: 1h 15m | Max: 1h 15m | Hits: 36%/2636 🟩 MSVC14.29 Pass: 100%/2 | Total: 2h 20m | Avg: 1h 10m | Max: 1h 12m | Hits: 36%/5272 🟩 MSVC14.39 Pass: 100%/2 | Total: 1h 47m | Avg: 53m 49s | Max: 1h 23m | Hits: 67%/5272 🟩 NVHPC24.7 Pass: 100%/4 | Total: 5h 13m | Avg: 1h 18m | Max: 1h 22m 🟩 cxx_family 🟩 Clang Pass: 100%/48 | Total: 1d 06h | Avg: 38m 24s | Max: 47m 37s 🟩 GCC Pass: 100%/49 | Total: 1d 06h | Avg: 36m 54s | Max: 53m 49s 🟩 Intel Pass: 100%/3 | Total: 2h 40m | Avg: 53m 36s | Max: 1h 03m 🟩 MSVC Pass: 100%/5 | Total: 5h 23m | Avg: 1h 04m | Max: 1h 23m | Hits: 48%/13180 🟩 NVHPC Pass: 100%/4 | Total: 5h 13m | Avg: 1h 18m | Max: 1h 22m 🟩 gpu 🟩 v100 Pass: 100%/109 | Total: 3d 02h | Avg: 40m 49s | Max: 1h 23m | Hits: 48%/13180 🟩 jobs 🟩 Build Pass: 100%/102 | Total: 3d 00h | Avg: 42m 37s | Max: 1h 23m | Hits: 36%/10544 🟩 TestCPU Pass: 100%/4 | Total: 47m 52s | Avg: 11m 58s | Max: 24m 08s | Hits: 99%/2636 🟩 TestGPU Pass: 100%/3 | Total: 54m 08s | Avg: 18m 02s | Max: 25m 55s 🟩 sm 🟩 60;70;80;90 Pass: 100%/3 | Total: 2h 24m | Avg: 48m 07s | Max: 53m 49s 🟩 90a Pass: 100%/4 | Total: 1h 52m | Avg: 28m 02s | Max: 32m 28s 🟩 std 🟩 11 Pass: 100%/30 | Total: 16h 39m | Avg: 33m 18s | Max: 1h 11m 🟩 14 Pass: 100%/29 | Total: 21h 30m | Avg: 44m 29s | Max: 1h 21m | Hits: 36%/5272 🟩 17 Pass: 100%/27 | Total: 20h 42m | Avg: 46m 00s | Max: 1h 22m | Hits: 36%/2636 🟩 20 Pass: 100%/23 | Total: 15h 18m | Avg: 39m 55s | Max: 1h 23m | Hits: 67%/5272 -
🟩 cudax: Pass: 100%/54 | Total: 4h 50m | Avg: 5m 23s | Max: 19m 26s | Hits: 78%/238
🟩 cpu 🟩 amd64 Pass: 100%/50 | Total: 4h 36m | Avg: 5m 31s | Max: 19m 26s | Hits: 78%/238 🟩 arm64 Pass: 100%/4 | Total: 14m 35s | Avg: 3m 38s | Max: 4m 01s 🟩 ctk 🟩 12.0 Pass: 100%/19 | Total: 1h 41m | Avg: 5m 19s | Max: 18m 50s | Hits: 78%/119 🟩 12.5 Pass: 100%/2 | Total: 13m 03s | Avg: 6m 31s | Max: 6m 45s 🟩 12.6 Pass: 100%/33 | Total: 2h 56m | Avg: 5m 21s | Max: 19m 26s | Hits: 78%/119 🟩 cudacxx 🟩 nvcc12.0 Pass: 100%/19 | Total: 1h 41m | Avg: 5m 19s | Max: 18m 50s | Hits: 78%/119 🟩 nvcc12.5 Pass: 100%/2 | Total: 13m 03s | Avg: 6m 31s | Max: 6m 45s 🟩 nvcc12.6 Pass: 100%/33 | Total: 2h 56m | Avg: 5m 21s | Max: 19m 26s | Hits: 78%/119 🟩 cudacxx_family 🟩 nvcc Pass: 100%/54 | Total: 4h 50m | Avg: 5m 23s | Max: 19m 26s | Hits: 78%/238 🟩 cxx 🟩 Clang9 Pass: 100%/2 | Total: 9m 03s | Avg: 4m 31s | Max: 4m 34s 🟩 Clang10 Pass: 100%/2 | Total: 8m 20s | Avg: 4m 10s | Max: 4m 27s 🟩 Clang11 Pass: 100%/4 | Total: 14m 45s | Avg: 3m 41s | Max: 3m 51s 🟩 Clang12 Pass: 100%/4 | Total: 15m 12s | Avg: 3m 48s | Max: 4m 00s 🟩 Clang13 Pass: 100%/4 | Total: 14m 01s | Avg: 3m 30s | Max: 3m 45s 🟩 Clang14 Pass: 100%/4 | Total: 28m 48s | Avg: 7m 12s | Max: 17m 48s 🟩 Clang15 Pass: 100%/2 | Total: 7m 18s | Avg: 3m 39s | Max: 3m 41s 🟩 Clang16 Pass: 100%/4 | Total: 14m 36s | Avg: 3m 39s | Max: 3m 59s 🟩 Clang17 Pass: 100%/2 | Total: 7m 44s | Avg: 3m 52s | Max: 4m 07s 🟩 Clang18 Pass: 100%/2 | Total: 23m 13s | Avg: 11m 36s | Max: 19m 13s 🟩 GCC9 Pass: 100%/2 | Total: 7m 31s | Avg: 3m 45s | Max: 3m 54s 🟩 GCC10 Pass: 100%/4 | Total: 14m 01s | Avg: 3m 30s | Max: 3m 52s 🟩 GCC11 Pass: 100%/4 | Total: 14m 54s | Avg: 3m 43s | Max: 4m 16s 🟩 GCC12 Pass: 100%/7 | Total: 1h 11m | Avg: 10m 14s | Max: 19m 26s 🟩 GCC13 Pass: 100%/3 | Total: 10m 54s | Avg: 3m 38s | Max: 4m 01s 🟩 MSVC14.36 Pass: 100%/1 | Total: 7m 52s | Avg: 7m 52s | Max: 7m 52s | Hits: 78%/119 🟩 MSVC14.39 Pass: 100%/1 | Total: 7m 59s | Avg: 7m 59s | Max: 7m 59s | Hits: 78%/119 🟩 NVHPC24.7 Pass: 100%/2 | Total: 13m 03s | Avg: 6m 31s | Max: 6m 45s 🟩 cxx_family 🟩 Clang Pass: 100%/30 | Total: 2h 23m | Avg: 4m 46s | Max: 19m 13s 🟩 GCC Pass: 100%/20 | Total: 1h 58m | Avg: 5m 56s | Max: 19m 26s 🟩 MSVC Pass: 100%/2 | Total: 15m 51s | Avg: 7m 55s | Max: 7m 59s | Hits: 78%/238 🟩 NVHPC Pass: 100%/2 | Total: 13m 03s | Avg: 6m 31s | Max: 6m 45s 🟩 gpu 🟩 v100 Pass: 100%/54 | Total: 4h 50m | Avg: 5m 23s | Max: 19m 26s | Hits: 78%/238 🟩 jobs 🟩 Build Pass: 100%/49 | Total: 3h 16m | Avg: 4m 00s | Max: 7m 59s | Hits: 78%/238 🟩 Test Pass: 100%/5 | Total: 1h 34m | Avg: 18m 55s | Max: 19m 26s 🟩 sm 🟩 90 Pass: 100%/1 | Total: 2m 45s | Avg: 2m 45s | Max: 2m 45s 🟩 90a Pass: 100%/1 | Total: 3m 06s | Avg: 3m 06s | Max: 3m 06s 🟩 std 🟩 17 Pass: 100%/29 | Total: 2h 21m | Avg: 4m 51s | Max: 19m 21s 🟩 20 Pass: 100%/25 | Total: 2h 29m | Avg: 5m 59s | Max: 19m 26s | Hits: 78%/238 -
🟩 cccl_c_parallel: Pass: 100%/2 | Total: 10m 51s | Avg: 5m 25s | Max: 8m 56s
🟩 cpu 🟩 amd64 Pass: 100%/2 | Total: 10m 51s | Avg: 5m 25s | Max: 8m 56s 🟩 ctk 🟩 12.6 Pass: 100%/2 | Total: 10m 51s | Avg: 5m 25s | Max: 8m 56s 🟩 cudacxx 🟩 nvcc12.6 Pass: 100%/2 | Total: 10m 51s | Avg: 5m 25s | Max: 8m 56s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/2 | Total: 10m 51s | Avg: 5m 25s | Max: 8m 56s 🟩 cxx 🟩 GCC13 Pass: 100%/2 | Total: 10m 51s | Avg: 5m 25s | Max: 8m 56s 🟩 cxx_family 🟩 GCC Pass: 100%/2 | Total: 10m 51s | Avg: 5m 25s | Max: 8m 56s 🟩 gpu 🟩 v100 Pass: 100%/2 | Total: 10m 51s | Avg: 5m 25s | Max: 8m 56s 🟩 jobs 🟩 Build Pass: 100%/1 | Total: 1m 55s | Avg: 1m 55s | Max: 1m 55s 🟩 Test Pass: 100%/1 | Total: 8m 56s | Avg: 8m 56s | Max: 8m 56s -
🟩 python: Pass: 100%/1 | Total: 15m 05s | Avg: 15m 05s | Max: 15m 05s
🟩 cpu 🟩 amd64 Pass: 100%/1 | Total: 15m 05s | Avg: 15m 05s | Max: 15m 05s 🟩 ctk 🟩 12.6 Pass: 100%/1 | Total: 15m 05s | Avg: 15m 05s | Max: 15m 05s 🟩 cudacxx 🟩 nvcc12.6 Pass: 100%/1 | Total: 15m 05s | Avg: 15m 05s | Max: 15m 05s 🟩 cudacxx_family 🟩 nvcc Pass: 100%/1 | Total: 15m 05s | Avg: 15m 05s | Max: 15m 05s 🟩 cxx 🟩 GCC13 Pass: 100%/1 | Total: 15m 05s | Avg: 15m 05s | Max: 15m 05s 🟩 cxx_family 🟩 GCC Pass: 100%/1 | Total: 15m 05s | Avg: 15m 05s | Max: 15m 05s 🟩 gpu 🟩 v100 Pass: 100%/1 | Total: 15m 05s | Avg: 15m 05s | Max: 15m 05s 🟩 jobs 🟩 Test Pass: 100%/1 | Total: 15m 05s | Avg: 15m 05s | Max: 15m 05s
👃 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: 394)
| # | Runner |
|---|---|
| 326 | linux-amd64-cpu16 |
| 28 | linux-arm64-cpu16 |
| 25 | linux-amd64-gpu-v100-latest-1 |
| 15 | windows-amd64-cpu16 |