`Base.FastMath.pow_fast` fails to compile with integer exponent

[Mikolaj-A-Kowalski]

Describe the bug

CUDA.jl fails to properly resolve a call to Base.FastMath.pow_fast(x,y) where y is an integer. The LLVM error Undefined external symbol "__powidf2" is raised instead.

To reproduce

using CUDA

function apply_fast_pow(A,y)
    i = threadIdx().x
    @inbounds @fastmath A[i] = A[i]^y
    nothing
end

A_64 = CUDA.ones(Float64, 10) 
A_32 = CUDA.ones(Float32, 10) 

# Either of the following lines causes the LLVM error
# @cuda threads=length(A_64) apply_f(A_64, 2)
# @cuda threads=length(A_32) apply_f(A_32, 2)
# @cuda threads=length(A_32) apply_f(A_64, Int32(2))
# @cuda threads=length(A_32) apply_f(A_32, Int32(2))

EDIT (01/04/2026): Corrected unwanted promotion as pointed by @giordano 😅

Manifest.toml

# This file is machine-generated - editing it directly is not advised

julia_version = "1.11.4"
manifest_format = "2.0"
project_hash = "4d6f52122ea9741175c8c71d00021be0a921f3ad"

[[deps.AbstractFFTs]]
deps = ["LinearAlgebra"]
git-tree-sha1 = "d92ad398961a3ed262d8bf04a1a2b8340f915fef"
uuid = "621f4979-c628-5d54-868e-fcf4e3e8185c"
version = "1.5.0"

    [deps.AbstractFFTs.extensions]
    AbstractFFTsChainRulesCoreExt = "ChainRulesCore"
    AbstractFFTsTestExt = "Test"

    [deps.AbstractFFTs.weakdeps]
    ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
    Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"

[[deps.Adapt]]
deps = ["LinearAlgebra", "Requires"]
git-tree-sha1 = "35ea197a51ce46fcd01c4a44befce0578a1aaeca"
uuid = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
version = "4.5.0"
weakdeps = ["SparseArrays", "StaticArrays"]

    [deps.Adapt.extensions]
    AdaptSparseArraysExt = "SparseArrays"
    AdaptStaticArraysExt = "StaticArrays"

[[deps.ArgTools]]
uuid = "0dad84c5-d112-42e6-8d28-ef12dabb789f"
version = "1.1.2"

[[deps.Artifacts]]
uuid = "56f22d72-fd6d-98f1-02f0-08ddc0907c33"
version = "1.11.0"

[[deps.Atomix]]
deps = ["UnsafeAtomics"]
git-tree-sha1 = "b8651b2eb5796a386b0398a20b519a6a6150f75c"
uuid = "a9b6321e-bd34-4604-b9c9-b65b8de01458"
version = "1.1.3"

    [deps.Atomix.extensions]
    AtomixCUDAExt = "CUDA"
    AtomixMetalExt = "Metal"
    AtomixOpenCLExt = "OpenCL"
    AtomixoneAPIExt = "oneAPI"

    [deps.Atomix.weakdeps]
    CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
    Metal = "dde4c033-4e86-420c-a63e-0dd931031962"
    OpenCL = "08131aa3-fb12-5dee-8b74-c09406e224a2"
    oneAPI = "8f75cd03-7ff8-4ecb-9b8f-daf728133b1b"

[[deps.BFloat16s]]
deps = ["LinearAlgebra", "Printf", "Random"]
git-tree-sha1 = "e386db8b4753b42caac75ac81d0a4fe161a68a97"
uuid = "ab4f0b2a-ad5b-11e8-123f-65d77653426b"
version = "0.6.1"

[[deps.Base64]]
uuid = "2a0f44e3-6c83-55bd-87e4-b1978d98bd5f"
version = "1.11.0"

[[deps.CEnum]]
git-tree-sha1 = "389ad5c84de1ae7cf0e28e381131c98ea87d54fc"
uuid = "fa961155-64e5-5f13-b03f-caf6b980ea82"
version = "0.5.0"

[[deps.CUDA]]
deps = ["CUDACore", "CUDATools", "Reexport", "cuBLAS", "cuFFT", "cuRAND", "cuSOLVER", "cuSPARSE"]
path = "dev/CUDA"
uuid = "052768ef-5323-5732-b1bb-66c8b64840ba"
version = "6.0.0"

[[deps.CUDACore]]
deps = ["Adapt", "BFloat16s", "CEnum", "CUDA_Compiler_jll", "CUDA_Driver_jll", "CUDA_Runtime_Discovery", "CUDA_Runtime_jll", "ExprTools", "GPUArrays", "GPUCompiler", "GPUToolbox", "KernelAbstractions", "LLVM", "LLVMLoopInfo", "LazyArtifacts", "Libdl", "LinearAlgebra", "Logging", "Preferences", "Printf", "Random", "Random123", "RandomNumbers", "StaticArrays"]
path = "dev/CUDA/CUDACore"
uuid = "bd0ed864-bdfe-4181-a5ed-ce625a5fdea2"
version = "6.0.0"

    [deps.CUDACore.extensions]
    ChainRulesCoreExt = "ChainRulesCore"
    EnzymeCoreExt = "EnzymeCore"
    SpecialFunctionsExt = "SpecialFunctions"

    [deps.CUDACore.weakdeps]
    ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
    EnzymeCore = "f151be2c-9106-41f4-ab19-57ee4f262869"
    SpecialFunctions = "276daf66-3868-5448-9aa4-cd146d93841b"

[[deps.CUDATools]]
deps = ["CUDACore", "CUDA_Compiler_jll", "CUPTI", "Crayons", "GPUCompiler", "LLVM", "NVML", "NVTX", "Preferences", "PrettyTables", "Printf", "Statistics", "demumble_jll"]
path = "dev/CUDA/CUDATools"
uuid = "9ec180c6-1c07-47c7-9e6e-ebefa4d1f6d0"
version = "6.0.0"

[[deps.CUDA_Compiler_jll]]
deps = ["Artifacts", "CUDA_Driver_jll", "CUDA_Runtime_jll", "JLLWrappers", "LazyArtifacts", "Libdl", "TOML"]
git-tree-sha1 = "8c19e97de5b7574672e4a7a3abd55714ad66d59a"
uuid = "d1e2174e-dfdc-576e-b43e-73b79eb1aca8"
version = "0.4.2+0"

[[deps.CUDA_Driver_jll]]
deps = ["Artifacts", "JLLWrappers", "Libdl", "TOML"]
git-tree-sha1 = "061f39cc84e99928830aa1005d79f7e99097ba28"
uuid = "4ee394cb-3365-5eb0-8335-949819d2adfc"
version = "13.2.0+0"

[[deps.CUDA_Runtime_Discovery]]
deps = ["Libdl"]
git-tree-sha1 = "f9a521f52d236fe49f1028d69e549e7f2644bb72"
uuid = "1af6417a-86b4-443c-805f-a4643ffb695f"
version = "1.0.0"

[[deps.CUDA_Runtime_jll]]
deps = ["Artifacts", "CUDA_Driver_jll", "JLLWrappers", "LazyArtifacts", "Libdl", "TOML"]
git-tree-sha1 = "af17d37b5b8b4d7525f8902eba1ef6141a9a7d3b"
uuid = "76a88914-d11a-5bdc-97e0-2f5a05c973a2"
version = "0.21.0+0"

[[deps.CUPTI]]
deps = ["CEnum", "CUDACore", "CUDA_Runtime_Discovery", "CUDA_Runtime_jll", "GPUToolbox"]
path = "dev/CUDA/lib/cupti"
uuid = "9e67e8f6-ba02-4b6c-a7db-3b11ae1e7ab7"
version = "6.0.0"

[[deps.CompilerSupportLibraries_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "e66e0078-7015-5450-92f7-15fbd957f2ae"
version = "1.1.1+0"

[[deps.Crayons]]
git-tree-sha1 = "249fe38abf76d48563e2f4556bebd215aa317e15"
uuid = "a8cc5b0e-0ffa-5ad4-8c14-923d3ee1735f"
version = "4.1.1"

[[deps.DataAPI]]
git-tree-sha1 = "abe83f3a2f1b857aac70ef8b269080af17764bbe"
uuid = "9a962f9c-6df0-11e9-0e5d-c546b8b5ee8a"
version = "1.16.0"

[[deps.DataValueInterfaces]]
git-tree-sha1 = "bfc1187b79289637fa0ef6d4436ebdfe6905cbd6"
uuid = "e2d170a0-9d28-54be-80f0-106bbe20a464"
version = "1.0.0"

[[deps.Dates]]
deps = ["Printf"]
uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
version = "1.11.0"

[[deps.Downloads]]
deps = ["ArgTools", "FileWatching", "LibCURL", "NetworkOptions"]
uuid = "f43a241f-c20a-4ad4-852c-f6b1247861c6"
version = "1.6.0"

[[deps.ExprTools]]
git-tree-sha1 = "27415f162e6028e81c72b82ef756bf321213b6ec"
uuid = "e2ba6199-217a-4e67-a87a-7c52f15ade04"
version = "0.1.10"

[[deps.FileWatching]]
uuid = "7b1f6079-737a-58dc-b8bc-7a2ca5c1b5ee"
version = "1.11.0"

[[deps.GPUArrays]]
deps = ["Adapt", "GPUArraysCore", "KernelAbstractions", "LLVM", "LinearAlgebra", "Printf", "Random", "Reexport", "ScopedValues", "Serialization", "SparseArrays", "Statistics"]
git-tree-sha1 = "6487601563e4a1d1dab796e88b4548bf5544209e"
uuid = "0c68f7d7-f131-5f86-a1c3-88cf8149b2d7"
version = "11.4.1"

    [deps.GPUArrays.extensions]
    JLD2Ext = "JLD2"

    [deps.GPUArrays.weakdeps]
    JLD2 = "033835bb-8acc-5ee8-8aae-3f567f8a3819"

[[deps.GPUArraysCore]]
deps = ["Adapt"]
git-tree-sha1 = "83cf05ab16a73219e5f6bd1bdfa9848fa24ac627"
uuid = "46192b85-c4d5-4398-a991-12ede77f4527"
version = "0.2.0"

[[deps.GPUCompiler]]
deps = ["ExprTools", "InteractiveUtils", "LLVM", "Libdl", "Logging", "PrecompileTools", "Preferences", "Scratch", "Serialization", "TOML", "Tracy", "UUIDs"]
git-tree-sha1 = "966946d226e8b676ca6409454718accb18c34c54"
uuid = "61eb1bfa-7361-4325-ad38-22787b887f55"
version = "1.8.2"

[[deps.GPUToolbox]]
deps = ["LLVM"]
git-tree-sha1 = "a589b6c1a0eff953571f5d8b0474f5020831114d"
uuid = "096a3bc2-3ced-46d0-87f4-dd12716f4bfc"
version = "1.1.1"

[[deps.HashArrayMappedTries]]
git-tree-sha1 = "2eaa69a7cab70a52b9687c8bf950a5a93ec895ae"
uuid = "076d061b-32b6-4027-95e0-9a2c6f6d7e74"
version = "0.2.0"

[[deps.InteractiveUtils]]
deps = ["Markdown"]
uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
version = "1.11.0"

[[deps.IteratorInterfaceExtensions]]
git-tree-sha1 = "a3f24677c21f5bbe9d2a714f95dcd58337fb2856"
uuid = "82899510-4779-5014-852e-03e436cf321d"
version = "1.0.0"

[[deps.JLLWrappers]]
deps = ["Artifacts", "Preferences"]
git-tree-sha1 = "0533e564aae234aff59ab625543145446d8b6ec2"
uuid = "692b3bcd-3c85-4b1f-b108-f13ce0eb3210"
version = "1.7.1"

[[deps.JuliaNVTXCallbacks_jll]]
deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
git-tree-sha1 = "af433a10f3942e882d3c671aacb203e006a5808f"
uuid = "9c1d0b0a-7046-5b2e-a33f-ea22f176ac7e"
version = "0.2.1+0"

[[deps.KernelAbstractions]]
deps = ["Adapt", "Atomix", "InteractiveUtils", "MacroTools", "PrecompileTools", "Requires", "StaticArrays", "UUIDs"]
git-tree-sha1 = "f2e76d3ced51a2a9e185abc0b97494c7273f649f"
uuid = "63c18a36-062a-441e-b654-da1e3ab1ce7c"
version = "0.9.41"

    [deps.KernelAbstractions.extensions]
    EnzymeExt = "EnzymeCore"
    LinearAlgebraExt = "LinearAlgebra"
    SparseArraysExt = "SparseArrays"

    [deps.KernelAbstractions.weakdeps]
    EnzymeCore = "f151be2c-9106-41f4-ab19-57ee4f262869"
    LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
    SparseArrays = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"

[[deps.LLVM]]
deps = ["CEnum", "LLVMExtra_jll", "Libdl", "Preferences", "Printf", "Unicode"]
git-tree-sha1 = "69e4739502b7ab5176117e97e1664ed181c35036"
uuid = "929cbde3-209d-540e-8aea-75f648917ca0"
version = "9.4.6"
weakdeps = ["BFloat16s"]

    [deps.LLVM.extensions]
    BFloat16sExt = "BFloat16s"

[[deps.LLVMExtra_jll]]
deps = ["Artifacts", "JLLWrappers", "LazyArtifacts", "Libdl", "TOML"]
git-tree-sha1 = "8e76807afb59ebb833e9b131ebf1a8c006510f33"
uuid = "dad2f222-ce93-54a1-a47d-0025e8a3acab"
version = "0.0.38+0"

[[deps.LLVMLoopInfo]]
git-tree-sha1 = "2e5c102cfc41f48ae4740c7eca7743cc7e7b75ea"
uuid = "8b046642-f1f6-4319-8d3c-209ddc03c586"
version = "1.0.0"

[[deps.LaTeXStrings]]
git-tree-sha1 = "dda21b8cbd6a6c40d9d02a73230f9d70fed6918c"
uuid = "b964fa9f-0449-5b57-a5c2-d3ea65f4040f"
version = "1.4.0"

[[deps.LazyArtifacts]]
deps = ["Artifacts", "Pkg"]
uuid = "4af54fe1-eca0-43a8-85a7-787d91b784e3"
version = "1.11.0"

[[deps.LibCURL]]
deps = ["LibCURL_jll", "MozillaCACerts_jll"]
uuid = "b27032c2-a3e7-50c8-80cd-2d36dbcbfd21"
version = "0.6.4"

[[deps.LibCURL_jll]]
deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll", "Zlib_jll", "nghttp2_jll"]
uuid = "deac9b47-8bc7-5906-a0fe-35ac56dc84c0"
version = "8.6.0+0"

[[deps.LibGit2]]
deps = ["Base64", "LibGit2_jll", "NetworkOptions", "Printf", "SHA"]
uuid = "76f85450-5226-5b5a-8eaa-529ad045b433"
version = "1.11.0"

[[deps.LibGit2_jll]]
deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll"]
uuid = "e37daf67-58a4-590a-8e99-b0245dd2ffc5"
version = "1.7.2+0"

[[deps.LibSSH2_jll]]
deps = ["Artifacts", "Libdl", "MbedTLS_jll"]
uuid = "29816b5a-b9ab-546f-933c-edad1886dfa8"
version = "1.11.0+1"

[[deps.LibTracyClient_jll]]
deps = ["Artifacts", "JLLWrappers", "Libdl"]
git-tree-sha1 = "d4e20500d210247322901841d4eafc7a0c52642d"
uuid = "ad6e5548-8b26-5c9f-8ef3-ef0ad883f3a5"
version = "0.13.1+0"

[[deps.Libdl]]
uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
version = "1.11.0"

[[deps.LinearAlgebra]]
deps = ["Libdl", "OpenBLAS_jll", "libblastrampoline_jll"]
uuid = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
version = "1.11.0"

[[deps.Logging]]
uuid = "56ddb016-857b-54e1-b83d-db4d58db5568"
version = "1.11.0"

[[deps.MacroTools]]
git-tree-sha1 = "1e0228a030642014fe5cfe68c2c0a818f9e3f522"
uuid = "1914dd2f-81c6-5fcd-8719-6d5c9610ff09"
version = "0.5.16"

[[deps.Markdown]]
deps = ["Base64"]
uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
version = "1.11.0"

[[deps.MbedTLS_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1"
version = "2.28.6+0"

[[deps.MozillaCACerts_jll]]
uuid = "14a3606d-f60d-562e-9121-12d972cd8159"
version = "2023.12.12"

[[deps.NVML]]
deps = ["CEnum", "CUDACore", "GPUToolbox", "Libdl"]
path = "dev/CUDA/lib/nvml"
uuid = "611af6d1-644e-4c5d-bd58-854d7d1254b9"
version = "6.0.0"

[[deps.NVTX]]
deps = ["JuliaNVTXCallbacks_jll", "Libdl", "NVTX_jll"]
git-tree-sha1 = "a9083c3e469e63cca454d1fc3b19472d9d92c14a"
uuid = "5da4648a-3479-48b8-97b9-01cb529c0a1f"
version = "1.0.3"

    [deps.NVTX.extensions]
    NVTXColorsExt = "Colors"

    [deps.NVTX.weakdeps]
    Colors = "5ae59095-9a9b-59fe-a467-6f913c188581"

[[deps.NVTX_jll]]
deps = ["Artifacts", "JLLWrappers", "Libdl"]
git-tree-sha1 = "af2232f69447494514c25742ba1503ec7e9877fe"
uuid = "e98f9f5b-d649-5603-91fd-7774390e6439"
version = "3.2.2+0"

[[deps.NetworkOptions]]
uuid = "ca575930-c2e3-43a9-ace4-1e988b2c1908"
version = "1.2.0"

[[deps.OpenBLAS_jll]]
deps = ["Artifacts", "CompilerSupportLibraries_jll", "Libdl"]
uuid = "4536629a-c528-5b80-bd46-f80d51c5b363"
version = "0.3.27+1"

[[deps.OrderedCollections]]
git-tree-sha1 = "05868e21324cede2207c6f0f466b4bfef6d5e7ee"
uuid = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
version = "1.8.1"

[[deps.Pkg]]
deps = ["Artifacts", "Dates", "Downloads", "FileWatching", "LibGit2", "Libdl", "Logging", "Markdown", "Printf", "Random", "SHA", "TOML", "Tar", "UUIDs", "p7zip_jll"]
uuid = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
version = "1.11.0"
weakdeps = ["REPL"]

    [deps.Pkg.extensions]
    REPLExt = "REPL"

[[deps.PrecompileTools]]
deps = ["Preferences"]
git-tree-sha1 = "5aa36f7049a63a1528fe8f7c3f2113413ffd4e1f"
uuid = "aea7be01-6a6a-4083-8856-8a6e6704d82a"
version = "1.2.1"

[[deps.Preferences]]
deps = ["TOML"]
git-tree-sha1 = "8b770b60760d4451834fe79dd483e318eee709c4"
uuid = "21216c6a-2e73-6563-6e65-726566657250"
version = "1.5.2"

[[deps.PrettyTables]]
deps = ["Crayons", "LaTeXStrings", "Markdown", "PrecompileTools", "Printf", "REPL", "Reexport", "StringManipulation", "Tables"]
git-tree-sha1 = "624de6279ab7d94fc9f672f0068107eb6619732c"
uuid = "08abe8d2-0d0c-5749-adfa-8a2ac140af0d"
version = "3.3.2"

    [deps.PrettyTables.extensions]
    PrettyTablesTypstryExt = "Typstry"

    [deps.PrettyTables.weakdeps]
    Typstry = "f0ed7684-a786-439e-b1e3-3b82803b501e"

[[deps.Printf]]
deps = ["Unicode"]
uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7"
version = "1.11.0"

[[deps.REPL]]
deps = ["InteractiveUtils", "Markdown", "Sockets", "StyledStrings", "Unicode"]
uuid = "3fa0cd96-eef1-5676-8a61-b3b8758bbffb"
version = "1.11.0"

[[deps.Random]]
deps = ["SHA"]
uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
version = "1.11.0"

[[deps.Random123]]
deps = ["Random", "RandomNumbers"]
git-tree-sha1 = "dbe5fd0b334694e905cb9fda73cd8554333c46e2"
uuid = "74087812-796a-5b5d-8853-05524746bad3"
version = "1.7.1"

[[deps.RandomNumbers]]
deps = ["Random"]
git-tree-sha1 = "c6ec94d2aaba1ab2ff983052cf6a606ca5985902"
uuid = "e6cf234a-135c-5ec9-84dd-332b85af5143"
version = "1.6.0"

[[deps.Reexport]]
git-tree-sha1 = "45e428421666073eab6f2da5c9d310d99bb12f9b"
uuid = "189a3867-3050-52da-a836-e630ba90ab69"
version = "1.2.2"

[[deps.Requires]]
deps = ["UUIDs"]
git-tree-sha1 = "62389eeff14780bfe55195b7204c0d8738436d64"
uuid = "ae029012-a4dd-5104-9daa-d747884805df"
version = "1.3.1"

[[deps.SHA]]
uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
version = "0.7.0"

[[deps.ScopedValues]]
deps = ["HashArrayMappedTries", "Logging"]
git-tree-sha1 = "ac4b837d89a58c848e85e698e2a2514e9d59d8f6"
uuid = "7e506255-f358-4e82-b7e4-beb19740aa63"
version = "1.6.0"

[[deps.Scratch]]
deps = ["Dates"]
git-tree-sha1 = "9b81b8393e50b7d4e6d0a9f14e192294d3b7c109"
uuid = "6c6a2e73-6563-6170-7368-637461726353"
version = "1.3.0"

[[deps.Serialization]]
uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
version = "1.11.0"

[[deps.Sockets]]
uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
version = "1.11.0"

[[deps.SparseArrays]]
deps = ["Libdl", "LinearAlgebra", "Random", "Serialization", "SuiteSparse_jll"]
uuid = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
version = "1.11.0"

[[deps.StaticArrays]]
deps = ["LinearAlgebra", "PrecompileTools", "Random", "StaticArraysCore"]
git-tree-sha1 = "246a8bb2e6667f832eea063c3a56aef96429a3db"
uuid = "90137ffa-7385-5640-81b9-e52037218182"
version = "1.9.18"

    [deps.StaticArrays.extensions]
    StaticArraysChainRulesCoreExt = "ChainRulesCore"
    StaticArraysStatisticsExt = "Statistics"

    [deps.StaticArrays.weakdeps]
    ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
    Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"

[[deps.StaticArraysCore]]
git-tree-sha1 = "6ab403037779dae8c514bad259f32a447262455a"
uuid = "1e83bf80-4336-4d27-bf5d-d5a4f845583c"
version = "1.4.4"

[[deps.Statistics]]
deps = ["LinearAlgebra"]
git-tree-sha1 = "ae3bb1eb3bba077cd276bc5cfc337cc65c3075c0"
uuid = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
version = "1.11.1"
weakdeps = ["SparseArrays"]

    [deps.Statistics.extensions]
    SparseArraysExt = ["SparseArrays"]

[[deps.StringManipulation]]
deps = ["PrecompileTools"]
git-tree-sha1 = "d05693d339e37d6ab134c5ab53c29fce5ee5d7d5"
uuid = "892a3eda-7b42-436c-8928-eab12a02cf0e"
version = "0.4.4"

[[deps.StyledStrings]]
uuid = "f489334b-da3d-4c2e-b8f0-e476e12c162b"
version = "1.11.0"

[[deps.SuiteSparse_jll]]
deps = ["Artifacts", "Libdl", "libblastrampoline_jll"]
uuid = "bea87d4a-7f5b-5778-9afe-8cc45184846c"
version = "7.7.0+0"

[[deps.TOML]]
deps = ["Dates"]
uuid = "fa267f1f-6049-4f14-aa54-33bafae1ed76"
version = "1.0.3"

[[deps.TableTraits]]
deps = ["IteratorInterfaceExtensions"]
git-tree-sha1 = "c06b2f539df1c6efa794486abfb6ed2022561a39"
uuid = "3783bdb8-4a98-5b6b-af9a-565f29a5fe9c"
version = "1.0.1"

[[deps.Tables]]
deps = ["DataAPI", "DataValueInterfaces", "IteratorInterfaceExtensions", "OrderedCollections", "TableTraits"]
git-tree-sha1 = "f2c1efbc8f3a609aadf318094f8fc5204bdaf344"
uuid = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
version = "1.12.1"

[[deps.Tar]]
deps = ["ArgTools", "SHA"]
uuid = "a4e569a6-e804-4fa4-b0f3-eef7a1d5b13e"
version = "1.10.0"

[[deps.Tracy]]
deps = ["ExprTools", "LibTracyClient_jll", "Libdl"]
git-tree-sha1 = "73e3ff50fd3990874c59fef0f35d10644a1487bc"
uuid = "e689c965-62c8-4b79-b2c5-8359227902fd"
version = "0.1.6"

    [deps.Tracy.extensions]
    TracyProfilerExt = "TracyProfiler_jll"

    [deps.Tracy.weakdeps]
    TracyProfiler_jll = "0c351ed6-8a68-550e-8b79-de6f926da83c"

[[deps.UUIDs]]
deps = ["Random", "SHA"]
uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
version = "1.11.0"

[[deps.Unicode]]
uuid = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5"
version = "1.11.0"

[[deps.UnsafeAtomics]]
git-tree-sha1 = "0f30765c32d66d58e41f4cb5624d4fc8a82ec13b"
uuid = "013be700-e6cd-48c3-b4a1-df204f14c38f"
version = "0.3.1"
weakdeps = ["LLVM"]

    [deps.UnsafeAtomics.extensions]
    UnsafeAtomicsLLVM = ["LLVM"]

[[deps.Zlib_jll]]
deps = ["Libdl"]
uuid = "83775a58-1f1d-513f-b197-d71354ab007a"
version = "1.2.13+1"

[[deps.cuBLAS]]
deps = ["Adapt", "BFloat16s", "CEnum", "CUDACore", "CUDA_Runtime_Discovery", "CUDA_Runtime_jll", "GPUArrays", "GPUToolbox", "LLVM", "LinearAlgebra"]
path = "dev/CUDA/lib/cublas"
uuid = "182d3088-87b7-4494-8cad-fc6afaa545bc"
version = "6.0.0"

    [deps.cuBLAS.extensions]
    EnzymeCoreExt = "EnzymeCore"

    [deps.cuBLAS.weakdeps]
    EnzymeCore = "f151be2c-9106-41f4-ab19-57ee4f262869"

[[deps.cuFFT]]
deps = ["AbstractFFTs", "CEnum", "CUDACore", "CUDA_Runtime_Discovery", "CUDA_Runtime_jll", "GPUToolbox", "LinearAlgebra", "Reexport"]
path = "dev/CUDA/lib/cufft"
uuid = "533571aa-0936-420e-b4be-9c66f5f626ca"
version = "6.0.0"

[[deps.cuRAND]]
deps = ["CEnum", "CUDACore", "CUDA_Runtime_Discovery", "CUDA_Runtime_jll", "GPUToolbox", "Random", "Random123", "RandomNumbers"]
path = "dev/CUDA/lib/curand"
uuid = "20fd9a0b-12d5-4c2f-a8af-7c34e9e60431"
version = "6.0.0"

[[deps.cuSOLVER]]
deps = ["CEnum", "CUDACore", "CUDA_Runtime_Discovery", "CUDA_Runtime_jll", "GPUToolbox", "LinearAlgebra", "SparseArrays", "cuBLAS", "cuSPARSE"]
path = "dev/CUDA/lib/cusolver"
uuid = "887afef0-6a32-4de5-add4-7827692ba8fc"
version = "6.0.0"

[[deps.cuSPARSE]]
deps = ["Adapt", "CEnum", "CUDACore", "CUDA_Runtime_Discovery", "CUDA_Runtime_jll", "GPUArrays", "GPUToolbox", "KernelAbstractions", "LinearAlgebra", "SparseArrays"]
path = "dev/CUDA/lib/cusparse"
uuid = "b26da814-b3bc-49ef-b0ee-c816305aa060"
version = "6.0.0"

    [deps.cuSPARSE.extensions]
    SparseMatricesCSRExt = "SparseMatricesCSR"

    [deps.cuSPARSE.weakdeps]
    SparseMatricesCSR = "a0a7dd2c-ebf4-11e9-1f05-cf50bc540ca1"

[[deps.demumble_jll]]
deps = ["Artifacts", "JLLWrappers", "Libdl"]
git-tree-sha1 = "6498e3581023f8e530f34760d18f75a69e3a4ea8"
uuid = "1e29f10c-031c-5a83-9565-69cddfc27673"
version = "1.3.0+0"

[[deps.libblastrampoline_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "8e850b90-86db-534c-a0d3-1478176c7d93"
version = "5.11.0+0"

[[deps.nghttp2_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "8e850ede-7688-5339-a07c-302acd2aaf8d"
version = "1.59.0+0"

[[deps.p7zip_jll]]
deps = ["Artifacts", "Libdl"]
uuid = "3f19e933-33d8-53b3-aaab-bd5110c3b7a0"
version = "17.4.0+2"

Expected behavior

The example kernel should execute. Either fallback to the orginary Base.:^ or have extra overloads to handle the case with integer exponent

Version info

Details on Julia:

Julia Version 1.11.4
Commit 8561cc3d68d (2025-03-10 11:36 UTC)
Build Info:
  Official https://julialang.org/ release
Platform Info:
  OS: Linux (x86_64-linux-gnu)
  CPU: 64 × Intel(R) Xeon(R) Platinum 8362 CPU @ 2.80GHz
  WORD_SIZE: 64
  LLVM: libLLVM-16.0.6 (ORCJIT, icelake-server)
Threads: 1 default, 0 interactive, 1 GC (on 64 virtual cores)

Details on CUDA:

CUDA toolchain: 
- runtime 13.2, artifact installation
- driver 570.211.1 for 13.2
- compiler 13.2

CUDA libraries: 
- cuBLAS: 13.3.0
- cuSPARSE: 12.7.9
- cuSOLVER: 12.1.0
- cuFFT: 12.2.0
- cuRAND: 10.4.2
- CUPTI: 2026.1.0 (API 13.2.0)
- NVML: 12.0.0+570.211.1

Julia packages: 
- CUDACore: 6.0.0
- GPUArrays: 11.4.1
- GPUCompiler: 1.8.2
- KernelAbstractions: 0.9.41
- CUDA_Driver_jll: 13.2.0+0
- CUDA_Compiler_jll: 0.4.2+0
- CUDA_Runtime_jll: 0.21.0+0

Toolchain:
- Julia: 1.11.4
- LLVM: 16.0.6

4 devices:
  0: NVIDIA L40 (sm_89, 43.806 GiB / 44.988 GiB available)
  1: NVIDIA L40 (sm_89, 44.258 GiB / 44.988 GiB available)
  2: NVIDIA L40 (sm_89, 44.258 GiB / 44.988 GiB available)
  3: NVIDIA L40 (sm_89, 44.258 GiB / 44.988 GiB available)

Additional context

I think this is just a case of a missing overload. Trying it out locally adding a fall-back:

@device_override FastMath.pow_fast(x, y) = Base.:(^)(x, y)

fixes the problem.

I imagine though that the proper solution would include some "fast" fallback when possible e.g.:

@device_override FastMath.pow_fast(x, y) = Base.:(^)(x, y)
@device_override @inline function FastMath.pow_fast(x::Float32, y::Integer)
    y == -1 && return inv(x)
    y == 0 && return one(x)
    y == 1 && return x
    y == 2 && return x*x
    y == 3 && return x*x*x
    Base.FastMath.pow_fast(x, Float32(y))
end

[giordano]

A_32 = CUDA.ones(Float32, 10) .+ 0.3

Nitpick, note that 0.3 is a literal Float64, so that adding it to an array of Float32 produces an array of Float64. To reproduce the bug, .+ 0.3 is unnecessary,

[giordano]

I believe this is an upstream LLVM bug, I can reproduce the same error simply with https://godbolt.org/z/jbvcna33P

; ModuleID = 'start'
source_filename = "start"
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
target triple = "nvptx64-nvidia-cuda"

declare double @llvm.powi.f64.i32(double, i32) #0

define double @kernel(double %0, i32 %1) {
conversion:
  %2 = call double @llvm.powi.f64.i32(double %0, i32 %1)
  ret double %2
}

Are these llvm.powi.* intrinsics not supported by the NVPTX backend?

As suggested above, I believe the solution is to make CUDA.jl emit some different LLVM IR which doesn't error our badly.