Hi,
I have now tried to test CUDA on my desktop PC. This uses a GTX 1060 GPU (instead of Quadro P1000) but still CUDA compute capability 6.1
I have made a MWE where I run two basic CUDA tests and pass them. But the third test fails at the same line as before and gives the same code 801 error:
using CUDA
CUDA.versioninfo()
@assert CUDA.functional()
#simple CUDA test (RESULT: TEST PASSED)
using Test
N = 2^20
x_d = CUDA.fill(1.0f0, N) # a vector stored on the GPU filled with 1.0 (Float32)
y_d = CUDA.fill(2.0f0, N) # a vector stored on the GPU filled with 2.0
y_d .+= x_d
@test all(Array(y_d) .== 3.0f0)
#GPU kernel test (RESULT: TEST PASSED)
function gpu_add1!(y, x)
for i = 1:length(y)
@inbounds y[i] += x[i]
end
return nothing
end
fill!(y_d, 2)
@cuda gpu_add1!(y_d, x_d)
@test all(Array(y_d) .== 3.0f0)
#Test WaterLily package in combination with CUDA
using WaterLily
function sphere(n, m; Re=100, U=1, T=Float64, mem=Array)
radius, center = m/8, m/2 - 1
body = AutoBody((x, t) -> √sum(abs2, x .- center) - radius)
Simulation((n, m, m), (U, 0, 0), 2radius; ν=U*2radius/Re, body, T, mem)
end
GPUsim = sphere(3*2^5, 2^6; T=Float32, mem=CuArray) # <-- error thrown here
The error gives the following stacktrace:
ERROR: CUDA error: operation not supported (code 801, ERROR_NOT_SUPPORTED)
Stacktrace:
[1] checked_cuModuleLoadDataEx(_module::Base.RefValue{…}, image::Ptr{…}, numOptions::Int64, options::Vector{…}, optionValues::Vector{…})
@ CUDACore C:\Users\Gebruiker\.julia\packages\CUDACore\NlVPI\lib\cudadrv\module.jl:27
[2] CuModule(data::Vector{UInt8}, options::Dict{CUDACore.CUjit_option_enum, Any})
@ CUDACore C:\Users\Gebruiker\.julia\packages\CUDACore\NlVPI\lib\cudadrv\module.jl:59
[3] CuModule
@ C:\Users\Gebruiker\.julia\packages\CUDACore\NlVPI\lib\cudadrv\module.jl:48 [inlined]
[4] link(job::GPUCompiler.CompilerJob, compiled::@NamedTuple{image::Vector{UInt8}, entry::String})
@ CUDACore C:\Users\Gebruiker\.julia\packages\CUDACore\NlVPI\src\compiler\compilation.jl:504
[5] actual_compilation(cache::Dict{…}, src::Core.MethodInstance, world::UInt64, cfg::GPUCompiler.CompilerConfig{…}, compiler::typeof(CUDACore.compile), linker::typeof(CUDACore.link))
@ GPUCompiler C:\Users\Gebruiker\.julia\packages\GPUCompiler\BSi1T\src\execution.jl:270
[6] cached_compilation(cache::Dict{…}, src::Core.MethodInstance, cfg::GPUCompiler.CompilerConfig{…}, compiler::Function, linker::Function)
@ GPUCompiler C:\Users\Gebruiker\.julia\packages\GPUCompiler\BSi1T\src\execution.jl:159
[7] macro expansion
@ C:\Users\Gebruiker\.julia\packages\CUDACore\NlVPI\src\compiler\execution.jl:456 [inlined]
[8] macro expansion
@ .\lock.jl:376 [inlined]
[9] cufunction(f::WaterLily.var"#gpu_##kern_#546#applyV!##1"{…}, tt::Type{…}; kwargs::@Kwargs{…})
@ CUDACore C:\Users\Gebruiker\.julia\packages\CUDACore\NlVPI\src\compiler\execution.jl:451
[10] cufunction
@ C:\Users\Gebruiker\.julia\packages\CUDACore\NlVPI\src\compiler\execution.jl:448 [inlined]
[11] #kernel_compile#753
@ C:\Users\Gebruiker\.julia\packages\CUDACore\NlVPI\src\compiler\execution.jl:60 [inlined]
[12] macro expansion
@ C:\Users\Gebruiker\.julia\packages\CUDACore\NlVPI\src\compiler\execution.jl:183 [inlined]
[13] (::KernelAbstractions.Kernel{…})(::CuArray{…}, ::Vararg{…}; ndrange::NTuple{…}, workgroupsize::Nothing)
@ CUDACore.CUDAKernels C:\Users\Gebruiker\.julia\packages\CUDACore\NlVPI\src\CUDAKernels.jl:125
[14] (::WaterLily.var"##kern#545#applyV!##4")(c::CuArray{Float32, 4, CUDACore.DeviceMemory})
@ WaterLily C:\Users\Gebruiker\.julia\packages\WaterLily\yOkji\src\core.jl:142
[15] macro expansion
@ C:\Users\Gebruiker\.julia\packages\WaterLily\yOkji\src\core.jl:144 [inlined]
[16] applyV!
@ C:\Users\Gebruiker\.julia\packages\WaterLily\yOkji\src\Flow.jl:82 [inlined]
[17] apply!(f::Function, c::CuArray{Float32, 4, CUDACore.DeviceMemory})
@ WaterLily C:\Users\Gebruiker\.julia\packages\WaterLily\yOkji\src\Flow.jl:81
[18] Flow(N::Tuple{…}, uBC::Tuple{…}; mem::Type, Δt::Float64, ν::Float64, g::Nothing, u0::Nothing, uλ::Nothing, perdir::Tuple{}, exitBC::Bool, λ::typeof(quick), T::Type)
@ WaterLily C:\Users\Gebruiker\.julia\packages\WaterLily\yOkji\src\Flow.jl:140
[19] Flow
@ C:\Users\Gebruiker\.julia\packages\WaterLily\yOkji\src\Flow.jl:133 [inlined]
[20] #242
@ C:\Users\Gebruiker\.julia\packages\WaterLily\yOkji\src\WaterLily.jl:96 [inlined]
[21] Simulation(dims::Tuple{…}, uBC::Tuple{…}, L::Float64; Δt::Float64, ν::Float64, g::Nothing, U::Nothing, ϵ::Int64, perdir::Tuple{}, u0::Nothing, uλ::Nothing, exitBC::Bool, λ::typeof(quick), body::AutoBody{…}, flow_ctor::WaterLily.var"#240#241"{…}, pois_ctor::WaterLily.var"#244#245"{…}, T::Type, mem::Type)
@ WaterLily C:\Users\Gebruiker\.julia\packages\WaterLily\yOkji\src\WaterLily.jl:103
[22] Simulation
@ C:\Users\Gebruiker\.julia\packages\WaterLily\yOkji\src\WaterLily.jl:93 [inlined]
[23] #sphere#19
@ d:\Julia_VisualStudio\Error801_Reproduce_Folder\Error_801.jl:34 [inlined]
[24] top-level scope
@ d:\Julia_VisualStudio\Error801_Reproduce_Folder\Error_801.jl:37
Some type information was truncated. Use `show(err)` to see complete types.
I have the following info on CUDA and Julia:
CUDA toolchain:
- runtime 12.9.0, artifact installation
- unknown driver for 13.0
- compiler 12.9.41, artifact installation
CUDA libraries:
- cuBLAS: 12.9.1
- cuSPARSE: 12.5.10
- cuSOLVER: 11.7.5
- cuFFT: 11.4.1
- cuRAND: 10.3.10
- CUPTI: 2025.2.1 (API 12.9.1)
- NVML: missing
Julia packages:
- CUDACore: 6.2.1
- GPUArrays: 11.5.8
- GPUCompiler: 1.23.0
- KernelAbstractions: 0.9.42
- CUDA_Driver_jll: 13.3.0+1
- CUDA_Compiler_jll: 0.4.4+1
- CUDA_Runtime_jll: 0.23.0+1
- NVPTX_LLVM_Backend_jll: 22.1.7+1
Toolchain:
- Julia: 1.12.6
- LLVM: 18.1.7
1 device:
0: NVIDIA GeForce GTX 1060 6GB (sm_61, 5.075 GiB / 6.000 GiB available)
compiles to sm_61 / PTX 8.8
