Hi,
I just format my labtop and install
graphics drivers
CUDA 11.2
julia (1.53)
I added CUDA.jl and downloaded cuDNN111 via artifact and had no errors by here.
I ran Pkg> test CUDA, now I got errors
┌ Error: Exception while generating log record in module Main at C:\Users\jaehp.julia\packages\CUDA\FlHUF\test\runtests.jl:111
│ exception =
│ NVMLError: Unknown Error (code 999)
│ Stacktrace:
│ [1] throw_api_error(::CUDA.NVML.nvmlReturn_enum) at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\error.jl:21│ [2] macro expansion at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\error.jl:39 [inlined]
│ [3] nvmlInit_v2 at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\utils\call.jl:93 [inlined]
│ [4] initialize_api() at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\error.jl:27
│ [5] macro expansion at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\libnvml.jl:25 [inlined]
│ [6] macro expansion at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\error.jl:37 [inlined]
│ [7] nvmlSystemGetDriverVersion(::Ptr{Int8}, ::Int64) at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\utils\call.jl:93
│ [8] driver_version() at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\system.jl:14
│ [9] versioninfo(::Base.GenericIOBuffer{Array{UInt8,1}}) at C:\Users\jaehp.julia\packages\CUDA\FlHUF\src\utilities.jl:46
│ [10] (::var"#20#21")(::Base.GenericIOBuffer{Array{UInt8,1}}) at C:\Users\jaehp.julia\packages\CUDA\FlHUF\test\runtests.jl:111
│ [11] sprint(::Function; context::Nothing, sizehint::Int64) at .\strings\io.jl:105
│ [12] sprint(::Function) at .\strings\io.jl:101
│ [13] top-level scope at logging.jl:331
│ [14] include(::String) at .\client.jl:457
│ [15] top-level scope at none:6
│ [16] eval(::Module, ::Any) at .\boot.jl:331
│ [17] exec_options(::Base.JLOptions) at .\client.jl:272
│ [18] _start() at .\client.jl:506
└ @ Main C:\Users\jaehp.julia\packages\CUDA\FlHUF\test\runtests.jl:111
ERROR: LoadError: NVMLError: Unknown Error (code 999)
Stacktrace:
[1] throw_api_error(::CUDA.NVML.nvmlReturn_enum) at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\error.jl:21
[2] macro expansion at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\error.jl:39 [inlined]
[3] nvmlInit_v2 at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\utils\call.jl:93 [inlined]
[4] initialize_api() at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\error.jl:27
[5] macro expansion at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\libnvml.jl:123 [inlined]
[6] macro expansion at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\error.jl:37 [inlined]
[7] nvmlDeviceGetCount_v2(::Base.RefValue{UInt32}) at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\utils\call.jl:93
[8] length at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\device.jl:41 [inlined]
[9] iterate at C:\Users\jaehp.julia\packages\CUDA\FlHUF\lib\nvml\device.jl:36 [inlined] (repeats 2 times)
[10] iterate at .\iterators.jl:139 [inlined]
[11] iterate at .\iterators.jl:138 [inlined]
[12] iterate at .\generator.jl:44 [inlined]
[13] collect(::Base.Generator{Base.Iterators.Enumerate{CUDA.NVML.DeviceIterator},var"#22#24"}) at .\array.jl:686
[14] top-level scope at C:\Users\jaehp.julia\packages\CUDA\FlHUF\test\runtests.jl:113
[15] include(::String) at .\client.jl:457
[16] top-level scope at none:6
in expression starting at C:\Users\jaehp.julia\packages\CUDA\FlHUF\test\runtests.jl:112
ERROR: Package CUDA errored during testing
The errors are relatively short compared to what I had before I format the computer, but I am not sure whether I can go with CUDA, or I need to solve the error message.
Thanks,