Ranges in kernels

using KernelAbstractions
@kernel function f_mwe(dt)
    0.0:dt:1.0
end
version = CUDADevice()
wait(version, f_mwe(version)(0.1;ndrange=10))

InvalidIRError: compiling kernel gpu_f_mwe(Cassette.Context{nametype(CUDACtx),KernelAbstractions.CompilerMetadata{KernelAbstractions.NDIteration.DynamicSize,KernelAbstractions.NDIteration.DynamicCheck,Nothing,CartesianIndices{1,Tuple{Base.OneTo{Int64}}},KernelAbstractions.NDIteration.NDRange{1,KernelAbstractions.NDIteration.DynamicSize,KernelAbstractions.NDIteration.DynamicSize,CartesianIndices{1,Tuple{Base.OneTo{Int64}}},CartesianIndices{1,Tuple{Base.OneTo{Int64}}}}},Nothing,KernelAbstractions.var"##PassType#253",Nothing,Cassette.DisableHooks}, typeof(gpu_f_mwe), Float64) resulted in invalid LLVM IR
Reason: unsupported call through a literal pointer (call to jl_alloc_string)
Stacktrace:
 [1] _string_n at strings/string.jl:60
 [2] StringVector at iobuffer.jl:31
 [3] #IOBuffer#331 at iobuffer.jl:114
 [4] print_to_string at strings/io.jl:133
 [5] string at strings/io.jl:174
 [6] StepRangeLen at range.jl:350
 [7] StepRangeLen at twiceprecision.jl:358
 [8] steprangelen_hp at twiceprecision.jl:344
 [9] overdub at C:\Users\accou\.julia\packages\KernelAbstractions\yw9SF\src\compiler.jl:61
 [10] macro expansion at C:\Users\accou\.julia\dev\DiffEqGPU\test\gpu_ode.jl:113
 [11] gpu_f_mwe at C:\Users\accou\.julia\packages\KernelAbstractions\yw9SF\src\macros.jl:80
 [12] overdub at C:\Users\accou\.julia\packages\Cassette\158rp\src\overdub.jl:0
Reason: unsupported call through a literal pointer (call to jl_string_to_array)
Stacktrace:
 [1] unsafe_wrap at strings/string.jl:71
 [2] StringVector at iobuffer.jl:31
 [3] #IOBuffer#331 at iobuffer.jl:114
 [4] print_to_string at strings/io.jl:133
 [5] string at strings/io.jl:174
 [6] StepRangeLen at range.jl:350
 [7] StepRangeLen at twiceprecision.jl:358
 [8] steprangelen_hp at twiceprecision.jl:344
 [9] overdub at C:\Users\accou\.julia\packages\KernelAbstractions\yw9SF\src\compiler.jl:61
 [10] macro expansion at C:\Users\accou\.julia\dev\DiffEqGPU\test\gpu_ode.jl:113
 [11] gpu_f_mwe at C:\Users\accou\.julia\packages\KernelAbstractions\yw9SF\src\macros.jl:80
 [12] overdub at C:\Users\accou\.julia\packages\Cassette\158rp\src\overdub.jl:0
Reason: unsupported call through a literal pointer (call to memset)
Stacktrace:
 [1] fill! at array.jl:428
 [2] #IOBuffer#331 at iobuffer.jl:121
 [3] print_to_string at strings/io.jl:133
 [4] string at strings/io.jl:174
 [5] StepRangeLen at range.jl:350
 [6] StepRangeLen at twiceprecision.jl:358
 [7] steprangelen_hp at twiceprecision.jl:344
 [8] overdub at C:\Users\accou\.julia\packages\KernelAbstractions\yw9SF\src\compiler.jl:61
 [9] macro expansion at C:\Users\accou\.julia\dev\DiffEqGPU\test\gpu_ode.jl:113
 [10] gpu_f_mwe at C:\Users\accou\.julia\packages\KernelAbstractions\yw9SF\src\macros.jl:80
 [11] overdub at C:\Users\accou\.julia\packages\Cassette\158rp\src\overdub.jl:0
Reason: unsupported dynamic function invocation (call to print)
Stacktrace:
 [1] print_to_string at strings/io.jl:135
 [2] string at strings/io.jl:174
 [3] StepRangeLen at range.jl:350
 [4] StepRangeLen at twiceprecision.jl:358
 [5] steprangelen_hp at twiceprecision.jl:344
 [6] overdub at C:\Users\accou\.julia\packages\KernelAbstractions\yw9SF\src\compiler.jl:61
 [7] macro expansion at C:\Users\accou\.julia\dev\DiffEqGPU\test\gpu_ode.jl:113
 [8] gpu_f_mwe at C:\Users\accou\.julia\packages\KernelAbstractions\yw9SF\src\macros.jl:80
 [9] overdub at C:\Users\accou\.julia\packages\Cassette\158rp\src\overdub.jl:0
Reason: unsupported call through a literal pointer (call to jl_array_grow_end)
Stacktrace:
 [1] _growend! at array.jl:892
 [2] resize! at array.jl:1085
 [3] print_to_string at strings/io.jl:137
 [4] string at strings/io.jl:174
 [5] StepRangeLen at range.jl:350
 [6] StepRangeLen at twiceprecision.jl:358
 [7] steprangelen_hp at twiceprecision.jl:344
 [8] overdub at C:\Users\accou\.julia\packages\KernelAbstractions\yw9SF\src\compiler.jl:61
 [9] macro expansion at C:\Users\accou\.julia\dev\DiffEqGPU\test\gpu_ode.jl:113
 [10] gpu_f_mwe at C:\Users\accou\.julia\packages\KernelAbstractions\yw9SF\src\macros.jl:80
 [11] overdub at C:\Users\accou\.julia\packages\Cassette\158rp\src\overdub.jl:0
Reason: unsupported call through a literal pointer (call to jl_array_del_end)
Stacktrace:
 [1] _deleteend! at array.jl:901
 [2] resize! at array.jl:1090
 [3] print_to_string at strings/io.jl:137
 [4] string at strings/io.jl:174
 [5] StepRangeLen at range.jl:350
 [6] StepRangeLen at twiceprecision.jl:358
 [7] steprangelen_hp at twiceprecision.jl:344
 [8] overdub at C:\Users\accou\.julia\packages\KernelAbstractions\yw9SF\src\compiler.jl:61
 [9] macro expansion at C:\Users\accou\.julia\dev\DiffEqGPU\test\gpu_ode.jl:113
 [10] gpu_f_mwe at C:\Users\accou\.julia\packages\KernelAbstractions\yw9SF\src\macros.jl:80
 [11] overdub at C:\Users\accou\.julia\packages\Cassette\158rp\src\overdub.jl:0
Reason: unsupported call through a literal pointer (call to jl_array_to_string)
Stacktrace:
 [1] String at strings/string.jl:39
 [2] print_to_string at strings/io.jl:137
 [3] string at strings/io.jl:174
 [4] St...

Start by reproducing the range example in test/gpu_ode.jl and trace the InvalidIRError through KernelAbstractions/src/compiler.jl and src/macros.jl, as shown in the stack trace. Done means the kernel can construct and use 0.0:dt:1.0 on CUDA without invalid LLVM IR.