Using Julia v1.6.1 I get several error during testing the CUDA package (v3.1.0). Most of them go back to CUDNNError: CUDNN_STATUS_NOT_INITIALIZED (code 1) - more details below.
The corresponding test runs through without a glitch using Julia v1.5.4 and CUDA v2.4.3.
Am I missing something?
julia> using CUDA
julia> import Pkg
julia> [CUDA.capability(dev) for dev in CUDA.devices()]
1-element Vector{VersionNumber}:
v"7.0.0"
julia> Pkg.test("CUDA")
Testing CUDA
Status `/scratch/local/jl_agg3rz/Project.toml`
[79e6a3ab] Adapt v3.3.0
[ab4f0b2a] BFloat16s v0.1.0
[052768ef] CUDA v3.1.0
[864edb3b] DataStructures v0.18.9
[7a1cc6ca] FFTW v1.4.0
[1a297f60] FillArrays v0.11.7
[0c68f7d7] GPUArrays v6.3.0
[a98d9a8b] Interpolations v0.13.2
[872c559c] NNlib v0.7.19
[ade2ca70] Dates `@stdlib/Dates`
[8ba89e20] Distributed `@stdlib/Distributed`
[37e2e46d] LinearAlgebra `@stdlib/LinearAlgebra`
[de0858da] Printf `@stdlib/Printf`
[3fa0cd96] REPL `@stdlib/REPL`
[9a3f8284] Random `@stdlib/Random`
[2f01184e] SparseArrays `@stdlib/SparseArrays`
[10745b16] Statistics `@stdlib/Statistics`
[8dfed614] Test `@stdlib/Test`
Status `/scratch/local/jl_agg3rz/Manifest.toml`
[621f4979] AbstractFFTs v1.0.1
[79e6a3ab] Adapt v3.3.0
[13072b0f] AxisAlgorithms v1.0.0
[ab4f0b2a] BFloat16s v0.1.0
[fa961155] CEnum v0.4.1
[052768ef] CUDA v3.1.0
[d360d2e6] ChainRulesCore v0.9.40
[34da2185] Compat v3.27.0
[864edb3b] DataStructures v0.18.9
[e2ba6199] ExprTools v0.1.3
[7a1cc6ca] FFTW v1.4.0
[1a297f60] FillArrays v0.11.7
[0c68f7d7] GPUArrays v6.3.0
[61eb1bfa] GPUCompiler v0.11.4
[a98d9a8b] Interpolations v0.13.2
[692b3bcd] JLLWrappers v1.3.0
[929cbde3] LLVM v3.6.0
[1914dd2f] MacroTools v0.5.6
[c03570c3] Memoize v0.4.4
[872c559c] NNlib v0.7.19
[6fe1bfb0] OffsetArrays v1.7.0
[bac558e1] OrderedCollections v1.4.0
[21216c6a] Preferences v1.2.1
[e6cf234a] RandomNumbers v1.4.0
[c84ed2f1] Ratios v0.4.0
[189a3867] Reexport v1.0.0
[ae029012] Requires v1.1.3
[6c6a2e73] Scratch v1.0.3
[276daf66] SpecialFunctions v1.3.0
[90137ffa] StaticArrays v1.1.2
[a759f4b9] TimerOutputs v0.5.8
[efce3f68] WoodburyMatrices v0.5.3
[f5851436] FFTW_jll v3.3.9+7
[1d5cc7b8] IntelOpenMP_jll v2018.0.3+2
[856f044c] MKL_jll v2021.1.1+1
[efe28fd5] OpenSpecFun_jll v0.5.4+0
[0dad84c5] ArgTools `@stdlib/ArgTools`
[56f22d72] Artifacts `@stdlib/Artifacts`
[2a0f44e3] Base64 `@stdlib/Base64`
[ade2ca70] Dates `@stdlib/Dates`
[8bb1440f] DelimitedFiles `@stdlib/DelimitedFiles`
[8ba89e20] Distributed `@stdlib/Distributed`
[f43a241f] Downloads `@stdlib/Downloads`
[b77e0a4c] InteractiveUtils `@stdlib/InteractiveUtils`
[4af54fe1] LazyArtifacts `@stdlib/LazyArtifacts`
[b27032c2] LibCURL `@stdlib/LibCURL`
[76f85450] LibGit2 `@stdlib/LibGit2`
[8f399da3] Libdl `@stdlib/Libdl`
[37e2e46d] LinearAlgebra `@stdlib/LinearAlgebra`
[56ddb016] Logging `@stdlib/Logging`
[d6f4376e] Markdown `@stdlib/Markdown`
[a63ad114] Mmap `@stdlib/Mmap`
[ca575930] NetworkOptions `@stdlib/NetworkOptions`
[44cfe95a] Pkg `@stdlib/Pkg`
[de0858da] Printf `@stdlib/Printf`
[3fa0cd96] REPL `@stdlib/REPL`
[9a3f8284] Random `@stdlib/Random`
[ea8e919c] SHA `@stdlib/SHA`
[9e88b42a] Serialization `@stdlib/Serialization`
[1a1011a3] SharedArrays `@stdlib/SharedArrays`
[6462fe0b] Sockets `@stdlib/Sockets`
[2f01184e] SparseArrays `@stdlib/SparseArrays`
[10745b16] Statistics `@stdlib/Statistics`
[fa267f1f] TOML `@stdlib/TOML`
[a4e569a6] Tar `@stdlib/Tar`
[8dfed614] Test `@stdlib/Test`
[cf7118a7] UUIDs `@stdlib/UUIDs`
[4ec0a83e] Unicode `@stdlib/Unicode`
[e66e0078] CompilerSupportLibraries_jll `@stdlib/CompilerSupportLibraries_jll`
[deac9b47] LibCURL_jll `@stdlib/LibCURL_jll`
[29816b5a] LibSSH2_jll `@stdlib/LibSSH2_jll`
[c8ffd9c3] MbedTLS_jll `@stdlib/MbedTLS_jll`
[14a3606d] MozillaCACerts_jll `@stdlib/MozillaCACerts_jll`
[83775a58] Zlib_jll `@stdlib/Zlib_jll`
[8e850ede] nghttp2_jll `@stdlib/nghttp2_jll`
[3f19e933] p7zip_jll `@stdlib/p7zip_jll`
Testing Running tests...
┌ Info: System information:
│ CUDA toolkit 10.2.89, artifact installation
│ CUDA driver 10.2.0
│ NVIDIA driver 440.44.0
│
│ Libraries:
│ - CUBLAS: 10.2.2
│ - CURAND: 10.1.2
│ - CUFFT: 10.1.2
│ - CUSOLVER: 10.3.0
│ - CUSPARSE: 10.3.1
│ - CUPTI: 12.0.0
│ - NVML: 10.0.0+440.44
│ - CUDNN: 8.10.0 (for CUDA 10.2.0)
│ - CUTENSOR: 1.2.1 (for CUDA 10.2.0)
│
│ Toolchain:
│ - Julia: 1.6.1
│ - LLVM: 11.0.1
│ - PTX ISA support: 3.2, 4.0, 4.1, 4.2, 4.3, 5.0, 6.0, 6.1, 6.3, 6.4, 6.5
│ - Device support: sm_30, sm_32, sm_35, sm_37, sm_50, sm_52, sm_53, sm_60, sm_61, sm_62, sm_70, sm_72, sm_75
│
│ 1 device:
└ 0: Tesla V100-PCIE-16GB (sm_70, 14.612 GiB / 15.782 GiB available)
[ Info: Testing using 1 device(s): 1. Tesla V100-PCIE-16GB (UUID df8dbe6c-02af-2641-1396-1f916a568a3b)
| | ---------------- GPU ---------------- | ---------------- CPU ---------------- |
Test (Worker) | Time (s) | GC (s) | GC % | Alloc (MB) | RSS (MB) | GC (s) | GC % | Alloc (MB) | RSS (MB) |
initialization (2) | 5.37 | 0.00 | 0.0 | 0.00 | 305.00 | 0.12 | 2.2 | 405.22 | 910.82 |
apiutils (2) | 0.17 | 0.00 | 0.0 | 0.00 | 305.00 | 0.00 | 0.0 | 1.81 | 910.82 |
array (2) | 108.26 | 0.02 | 0.0 | 5.29 | 425.00 | 6.10 | 5.6 | 14619.60 | 1089.48 |
broadcast (2) | 28.90 | 0.00 | 0.0 | 0.00 | 347.00 | 1.38 | 4.8 | 3225.32 | 1169.78 |
codegen (2) | 9.62 | 0.00 | 0.0 | 0.00 | 501.00 | 0.46 | 4.7 | 1263.18 | 1316.51 |
cublas (2) | 106.60 | 0.02 | 0.0 | 14.50 | 501.00 | 5.42 | 5.1 | 14330.21 | 1846.28 |
cufft (2) | 26.37 | 0.01 | 0.0 | 110.15 | 581.00 | 1.04 | 4.0 | 2830.28 | 2170.42 |
curand (2) | 0.15 | 0.00 | 0.0 | 0.00 | 415.00 | 0.04 | 25.6 | 6.94 | 2170.42 |
cusparse (2) | 32.67 | 0.01 | 0.0 | 8.45 | 585.00 | 1.07 | 3.3 | 2871.67 | 2388.04 |
examples (2) | 125.62 | 0.00 | 0.0 | 0.00 | 409.00 | 0.03 | 0.0 | 30.52 | 2388.04 |
exceptions (2) | 76.20 | 0.00 | 0.0 | 0.00 | 409.00 | 0.00 | 0.0 | 38.38 | 2388.04 |
From worker 2: WARNING: Method definition #5674#kernel(Any) in module Main at /home/arndt/.julia/packages/CUDA/k52QH/test/execution.jl:316 overwritten at /home/arndt/.julia/packages/CUDA/k52QH/test/execution.jl:324.
execution (2) | 88.04 | 0.00 | 0.0 | 0.95 | 535.00 | 3.82 | 4.3 | 10200.83 | 2453.33 |
iterator (2) | 2.29 | 0.00 | 0.0 | 1.16 | 411.00 | 0.12 | 5.4 | 367.05 | 2453.33 |
nvml (2) | 0.36 | 0.00 | 0.0 | 0.00 | 409.00 | 0.04 | 11.1 | 26.51 | 2453.33 |
nvtx (2) | 0.22 | 0.00 | 0.0 | 0.00 | 409.00 | 0.00 | 0.0 | 26.91 | 2453.33 |
pointer (2) | 0.23 | 0.00 | 0.2 | 0.00 | 411.00 | 0.00 | 0.0 | 14.08 | 2453.33 |
pool (2) | 4.90 | 0.00 | 0.0 | 0.00 | 409.00 | 0.99 | 20.2 | 787.15 | 2453.33 |
random (2) | 9.84 | 0.13 | 1.3 | 0.02 | 415.00 | 0.42 | 4.3 | 1097.25 | 2453.33 |
sorting (2) | 155.96 | 0.01 | 0.0 | 401.81 | 4201.00 | 5.27 | 3.4 | 20167.87 | 6535.18 |
statistics (2) | 46.98 | 0.00 | 0.0 | 1.21 | 479.00 | 1.96 | 4.2 | 5024.35 | 6535.18 |
texture (2) | 60.13 | 0.00 | 0.0 | 0.09 | 419.00 | 2.46 | 4.1 | 7300.62 | 6535.18 |
threading (2) | 4.96 | 0.00 | 0.1 | 10.94 | 483.00 | 0.19 | 3.8 | 280.41 | 6535.18 |
utils (2) | 0.81 | 0.00 | 0.0 | 0.00 | 479.00 | 0.05 | 5.7 | 60.88 | 6535.18 |
cudadrv/context (2) | 1.11 | 0.00 | 0.0 | 0.00 | 409.00 | 0.00 | 0.0 | 5.80 | 6535.18 |
cudadrv/devices (2) | 0.25 | 0.00 | 0.0 | 0.00 | 409.00 | 0.00 | 0.0 | 27.17 | 6535.18 |
cudadrv/errors (2) | 0.11 | 0.00 | 0.0 | 0.00 | 409.00 | 0.00 | 0.0 | 10.21 | 6535.18 |
cudadrv/events (2) | 0.08 | 0.00 | 0.0 | 0.00 | 409.00 | 0.00 | 0.0 | 4.13 | 6535.18 |
cudadrv/execution (2) | 0.57 | 0.00 | 0.1 | 0.00 | 411.00 | 0.00 | 0.0 | 48.27 | 6535.18 |
cudadrv/memory (2) | 2.89 | 0.00 | 0.0 | 0.02 | 413.00 | 0.11 | 3.8 | 215.71 | 6535.18 |
cudadrv/module (2) | 0.34 | 0.00 | 0.0 | 0.00 | 411.00 | 0.00 | 0.0 | 27.03 | 6535.18 |
cudadrv/occupancy (2) | 0.11 | 0.00 | 0.0 | 0.00 | 409.00 | 0.00 | 0.0 | 6.48 | 6535.18 |
cudadrv/pool (2) | failed at 2021-05-02T20:07:35.854
cudadrv/profile (3) | 0.27 | 0.00 | 0.0 | 0.00 | 305.00 | 0.01 | 4.3 | 56.65 | 910.82 |
cudadrv/stream (3) | 0.09 | 0.00 | 0.0 | 0.00 | 305.00 | 0.00 | 0.0 | 6.31 | 910.82 |
cudadrv/version (3) | 0.02 | 0.00 | 0.0 | 0.00 | 305.00 | 0.00 | 0.0 | 0.08 | 910.82 |
cudnn/activation (3) | failed at 2021-05-02T20:08:00.603
cudnn/convolution (4) | 0.10 | 0.00 | 0.0 | 0.00 | 305.00 | 0.00 | 0.0 | 7.08 | 910.82 |
cudnn/dropout (4) | failed at 2021-05-02T20:08:17.856
cudnn/inplace (5) | failed at 2021-05-02T20:08:34.127
cudnn/multiheadattn (6) | failed at 2021-05-02T20:09:05.614
cudnn/normalization (7) | failed at 2021-05-02T20:09:50.015
cudnn/optensor (8) | failed at 2021-05-02T20:10:11.980
cudnn/pooling (9) | failed at 2021-05-02T20:10:38.808
cudnn/reduce (10) | failed at 2021-05-02T20:11:04.523
cudnn/rnn (11) | failed at 2021-05-02T20:11:31.604
cudnn/softmax (12) | failed at 2021-05-02T20:11:51.517
cudnn/tensor (13) | 1.84 | 0.46 | 24.9 | 0.00 | 311.00 | 0.17 | 9.3 | 227.36 | 910.82 |
cusolver/dense (13) | 100.96 | 0.06 | 0.1 | 1147.73 | 541.00 | 5.01 | 5.0 | 14323.69 | 1338.73 |
cusolver/multigpu (13) | 7.09 | 0.00 | 0.1 | 403.17 | 1668.00 | 0.30 | 4.3 | 812.35 | 1399.38 |
cusolver/sparse (13) | 8.57 | 0.00 | 0.0 | 0.19 | 531.00 | 0.25 | 2.9 | 737.23 | 1638.07 |
cusparse/interfaces (13) | 15.05 | 0.00 | 0.0 | 0.17 | 449.00 | 0.45 | 3.0 | 1734.17 | 1739.48 |
cutensor/base (13) | 0.13 | 0.00 | 0.2 | 1.11 | 307.00 | 0.00 | 0.0 | 13.01 | 1739.48 |
cutensor/contractions (13) | 46.21 | 0.02 | 0.0 | 32033.88 | 515.00 | 2.58 | 5.6 | 7569.16 | 1877.41 |
cutensor/elementwise_binary (13) | 20.88 | 0.01 | 0.0 | 54.99 | 445.00 | 0.83 | 4.0 | 3101.33 | 1994.87 |
cutensor/elementwise_trinary (13) | 24.05 | 0.00 | 0.0 | 24.44 | 405.00 | 1.11 | 4.6 | 3651.29 | 2290.24 |
cutensor/permutations (13) | 3.48 | 0.00 | 0.1 | 12.22 | 385.00 | 0.14 | 4.0 | 502.30 | 2325.46 |
cutensor/reductions (13) | 14.89 | 0.00 | 0.0 | 41.72 | 375.00 | 0.55 | 3.7 | 1636.56 | 2325.85 |
device/array (13) | 4.47 | 0.00 | 0.0 | 0.00 | 347.00 | 0.20 | 4.6 | 591.53 | 2325.85 |
device/intrinsics (13) | 253.97 | 0.00 | 0.0 | 0.01 | 2127.00 | 9.81 | 3.9 | 29907.82 | 2485.50 |
device/ldg (13) | 10.60 | 0.00 | 0.0 | 0.00 | 347.00 | 0.49 | 4.6 | 1504.53 | 2509.30 |
device/random (13) | 45.53 | 0.00 | 0.0 | 0.14 | 351.00 | 1.51 | 3.3 | 4896.64 | 2721.20 |
device/wmma (13) | 66.30 | 0.00 | 0.0 | 0.38 | 349.00 | 2.24 | 3.4 | 7019.36 | 2797.96 |
gpuarrays/math (13) | 5.12 | 0.00 | 0.0 | 0.00 | 347.00 | 0.21 | 4.1 | 669.62 | 2826.11 |
gpuarrays/indexing scalar (13) | 13.25 | 0.00 | 0.0 | 0.00 | 347.00 | 0.50 | 3.8 | 1482.82 | 2841.47 |
gpuarrays/input output (13) | 1.80 | 0.00 | 0.0 | 0.00 | 307.00 | 0.11 | 6.1 | 187.77 | 2841.47 |
gpuarrays/value constructors (13) | 10.37 | 0.00 | 0.0 | 0.00 | 347.00 | 0.33 | 3.2 | 1025.49 | 2841.47 |
gpuarrays/indexing multidimensional (13) | 38.73 | 0.00 | 0.0 | 0.69 | 347.00 | 1.98 | 5.1 | 4448.97 | 2883.22 |
gpuarrays/interface (13) | 7.19 | 0.00 | 0.0 | 0.00 | 347.00 | 0.19 | 2.7 | 814.65 | 2938.44 |
gpuarrays/iterator constructors (13) | 2.53 | 0.00 | 0.0 | 0.02 | 347.00 | 0.16 | 6.1 | 232.22 | 2948.52 |
gpuarrays/uniformscaling (13) | 17.91 | 0.00 | 0.0 | 0.01 | 347.00 | 0.54 | 3.0 | 1413.19 | 2964.54 |
gpuarrays/linear algebra (13) | 141.42 | 0.01 | 0.0 | 1.24 | 417.00 | 6.04 | 4.3 | 19084.92 | 3396.66 |
gpuarrays/conversions (13) | 2.86 | 0.00 | 0.0 | 0.01 | 307.00 | 0.13 | 4.6 | 363.67 | 3419.54 |
gpuarrays/constructors (13) | 1.40 | 0.00 | 0.1 | 0.03 | 307.00 | 0.00 | 0.0 | 89.28 | 3420.58 |
gpuarrays/random (13) | 24.63 | 0.00 | 0.0 | 0.03 | 349.00 | 0.99 | 4.0 | 2743.27 | 3510.09 |
gpuarrays/base (13) | 27.75 | 0.00 | 0.0 | 17.44 | 379.00 | 1.43 | 5.2 | 3955.00 | 3590.78 |
gpuarrays/mapreduce essentials (13) | 170.25 | 0.01 | 0.0 | 3.19 | 351.00 | 6.46 | 3.8 | 19538.75 | 3902.67 |
gpuarrays/broadcasting (13) | 130.10 | 0.00 | 0.0 | 1.19 | 349.00 | 5.63 | 4.3 | 14696.51 | 3947.41 |
gpuarrays/mapreduce derivatives (13) | 330.18 | 0.01 | 0.0 | 3.06 | 353.00 | 10.40 | 3.1 | 29137.73 | 5158.99 |
Worker 2 failed running test cudadrv/pool:
Some tests did not pass: 0 passed, 0 failed, 1 errored, 0 broken.
cudadrv/pool: Error During Test at /home/arndt/.julia/packages/CUDA/k52QH/test/setup.jl:56
Got exception outside of a @test
LoadError: CUDA error: invalid argument (code 1, ERROR_INVALID_VALUE)
Stacktrace:
[1] throw_api_error(res::CUDA.cudaError_enum)
@ CUDA ~/.julia/packages/CUDA/k52QH/lib/cudadrv/error.jl:88
[2] macro expansion
@ ~/.julia/packages/CUDA/k52QH/lib/cudadrv/error.jl:96 [inlined]
[3] cuDeviceGetAttribute
@ ~/.julia/packages/CUDA/k52QH/lib/utils/call.jl:26 [inlined]
[4] attribute(dev::CuDevice, code::CUDA.CUdevice_attribute_enum)
@ CUDA ~/.julia/packages/CUDA/k52QH/lib/cudadrv/devices.jl:83
[5] top-level scope
@ ~/.julia/packages/CUDA/k52QH/test/cudadrv/pool.jl:2
[6] include
@ ./client.jl:444 [inlined]
[7] #9
@ ~/.julia/packages/CUDA/k52QH/test/runtests.jl:79 [inlined]
[8] macro expansion
@ ~/.julia/packages/CUDA/k52QH/test/setup.jl:57 [inlined]
[9] macro expansion
@ /buildworker/worker/package_linux64/build/usr/share/julia/stdlib/v1.6/Test/src/Test.jl:1151 [inlined]
[10] macro expansion
@ ~/.julia/packages/CUDA/k52QH/test/setup.jl:57 [inlined]
[11] macro expansion
@ ~/.julia/packages/CUDA/k52QH/src/utilities.jl:28 [inlined]
[12] macro expansion
@ ~/.julia/packages/CUDA/k52QH/src/pool.jl:572 [inlined]
[13] top-level scope
@ ~/.julia/packages/CUDA/k52QH/test/setup.jl:56
[14] eval
@ ./boot.jl:360 [inlined]
[15] runtests(f::Function, name::String, time_source::Symbol, snoop::Nothing)
@ Main ~/.julia/packages/CUDA/k52QH/test/setup.jl:68
[16] (::Distributed.var"#106#108"{Distributed.CallMsg{:call_fetch}})()
@ Distributed /buildworker/worker/package_linux64/build/usr/share/julia/stdlib/v1.6/Distributed/src/process_messages.jl:278
[17] run_work_thunk(thunk::Distributed.var"#106#108"{Distributed.CallMsg{:call_fetch}}, print_error::Bool)
@ Distributed /buildworker/worker/package_linux64/build/usr/share/julia/stdlib/v1.6/Distributed/src/process_messages.jl:63
[18] macro expansion
@ /buildworker/worker/package_linux64/build/usr/share/julia/stdlib/v1.6/Distributed/src/process_messages.jl:278 [inlined]
[19] (::Distributed.var"#105#107"{Distributed.CallMsg{:call_fetch}, Distributed.MsgHeader, Sockets.TCPSocket})()
@ Distributed ./task.jl:411
in expression starting at /home/arndt/.julia/packages/CUDA/k52QH/test/cudadrv/pool.jl:2
Worker 3 failed running test cudnn/activation:
Some tests did not pass: 3 passed, 0 failed, 40 errored, 0 broken.
cudnn/activation: Error During Test at /home/arndt/.julia/packages/CUDA/k52QH/test/cudnn/activation.jl:47
Test threw exception
Expression: y0 ≈ cudnnActivationForward(cx; mode, nanOpt, coef, alpha) |> Array
CUDNNError: CUDNN_STATUS_NOT_INITIALIZED (code 1)
Stacktrace:
[1] throw_api_error(res::CUDA.CUDNN.cudnnStatus_t)
@ CUDA.CUDNN ~/.julia/packages/CUDA/k52QH/lib/cudnn/error.jl:22
[2] macro expansion
@ ~/.julia/packages/CUDA/k52QH/lib/cudnn/error.jl:39 [inlined]
[3] cudnnCreate()
@ CUDA.CUDNN ~/.julia/packages/CUDA/k52QH/lib/cudnn/base.jl:3
[4] #686
@ ~/.julia/packages/CUDA/k52QH/lib/cudnn/CUDNN.jl:68 [inlined]
[5] (::CUDA.APIUtils.var"#2#5"{CUDA.CUDNN.var"#686#690", CUDA.APIUtils.HandleCache{CuContext, Ptr{Nothing}}, CuContext})()
@ CUDA.APIUtils ~/.julia/packages/CUDA/k52QH/lib/utils/cache.jl:22
[6] lock(f::CUDA.APIUtils.var"#2#5"{CUDA.CUDNN.var"#686#690", CUDA.APIUtils.HandleCache{CuContext, Ptr{Nothing}}, CuContext}, l::ReentrantLock)
@ Base ./lock.jl:187
[7] check_cache
@ ~/.julia/packages/CUDA/k52QH/lib/utils/cache.jl:20 [inlined]
[8] pop!
@ ~/.julia/packages/CUDA/k52QH/lib/utils/cache.jl:41 [inlined]
[9] (::CUDA.CUDNN.var"#685#689"{NamedTuple{(:device, :context, :stream, :math_mode, :math_precision), Tuple{CuDevice, CuContext, CuStream, CUDA.MathMode, Symbol}}})()
@ CUDA.CUDNN ~/.julia/packages/CUDA/k52QH/lib/cudnn/CUDNN.jl:67
[10] get!
@ ./iddict.jl:163 [inlined]
[11] handle()
@ CUDA.CUDNN ~/.julia/packages/CUDA/k52QH/lib/cudnn/CUDNN.jl:66
[12] #cudnnActivationForwardAD#645
@ ~/.julia/packages/CUDA/k52QH/lib/cudnn/activation.jl:48 [inlined]
[13] #cudnnActivationForwardWithDefaults#644
@ ~/.julia/packages/CUDA/k52QH/lib/cudnn/activation.jl:42 [inlined]
[14] #cudnnActivationForward#640
@ ~/.julia/packages/CUDA/k52QH/lib/cudnn/activation.jl:21 [inlined]
[15] (::var"#activationtest#10"{var"#activationtest#8#11"{CuArray{Float64, 1}, CuArray{Float64, 1}, Vector{Float64}, Vector{Float64}}})(; mode::cudnnActivationMode_t, nanOpt::cudnnNanPropagation_t, coef::Int64, alpha::Int64, beta::Int64)
@ Main ~/.julia/packages/CUDA/k52QH/test/cudnn/activation.jl:47
[16] macro expansion
@ ~/.julia/packages/CUDA/k52QH/test/cudnn/activation.jl:53 [inlined]
[17] macro expansion
@ /buildworker/worker/package_linux64/build/usr/share/julia/stdlib/v1.6/Test/src/Test.jl:1151 [inlined]
[18] top-level scope
@ ~/.julia/packages/CUDA/k52QH/test/cudnn/activation.jl:24
.... (more errors of the same kind) ....