Package evaluation of GemmKernels on Julia 1.13.0-DEV.791 (d5209bd37d*) started at 2025-07-04T15:11:35.232 ################################################################################ # Set-up # Set-up completed after 0.21s ################################################################################ # Installation # Installing GemmKernels... Resolving package versions... Updating `~/.julia/environments/v1.13/Project.toml` [312cec97] + GemmKernels v0.2.0 Updating `~/.julia/environments/v1.13/Manifest.toml` Precompiling packages... 3051.5 ms ✓ CUDA_Driver_jll 1 dependency successfully precompiled in 3 seconds. 28 already precompiled. [621f4979] + AbstractFFTs v1.5.0 [79e6a3ab] + Adapt v4.3.0 [a9b6321e] + Atomix v1.1.1 [ab4f0b2a] + BFloat16s v0.5.1 [fa961155] + CEnum v0.5.0 ⌃ [052768ef] + CUDA v5.4.3 [1af6417a] + CUDA_Runtime_Discovery v0.3.5 [3da002f7] + ColorTypes v0.12.1 [5ae59095] + Colors v0.13.1 [34da2185] + Compat v4.17.0 [a8cc5b0e] + Crayons v4.1.1 [9a962f9c] + DataAPI v1.16.0 [a93c6f00] + DataFrames v1.7.0 [864edb3b] + DataStructures v0.18.22 [e2d170a0] + DataValueInterfaces v1.0.0 [e2ba6199] + ExprTools v0.1.10 [53c48c17] + FixedPointNumbers v0.8.5 ⌅ [0c68f7d7] + GPUArrays v10.3.1 ⌅ [46192b85] + GPUArraysCore v0.1.6 ⌅ [61eb1bfa] + GPUCompiler v0.26.4 [312cec97] + GemmKernels v0.2.0 [842dd82b] + InlineStrings v1.4.4 [41ab1584] + InvertedIndices v1.3.1 [82899510] + IteratorInterfaceExtensions v1.0.0 [692b3bcd] + JLLWrappers v1.7.0 [63c18a36] + KernelAbstractions v0.9.36 ⌅ [929cbde3] + LLVM v6.6.3 [8b046642] + LLVMLoopInfo v1.0.0 [b964fa9f] + LaTeXStrings v1.4.0 [1914dd2f] + MacroTools v0.5.16 [e1d29d7a] + Missings v1.2.0 ⌅ [5da4648a] + NVTX v0.3.5 [bac558e1] + OrderedCollections v1.8.1 [2dfb63ee] + PooledArrays v1.4.3 [aea7be01] + PrecompileTools v1.3.2 [21216c6a] + Preferences v1.4.3 [08abe8d2] + PrettyTables v2.4.0 [74087812] + Random123 v1.7.1 [e6cf234a] + RandomNumbers v1.6.0 [189a3867] + Reexport v1.2.2 [ae029012] + Requires v1.3.1 [6c6a2e73] + Scratch v1.3.0 [91c51154] + SentinelArrays v1.4.8 [a2af1166] + SortingAlgorithms v1.2.1 [90137ffa] + StaticArrays v1.9.13 [1e83bf80] + StaticArraysCore v1.4.3 [10745b16] + Statistics v1.11.1 [892a3eda] + StringManipulation v0.4.1 [3783bdb8] + TableTraits v1.0.1 [bd369af6] + Tables v1.12.1 [a759f4b9] + TimerOutputs v0.5.29 ⌃ [013be700] + UnsafeAtomics v0.2.1 ⌅ [4ee394cb] + CUDA_Driver_jll v0.9.2+0 ⌅ [76a88914] + CUDA_Runtime_jll v0.14.1+0 [9c1d0b0a] + JuliaNVTXCallbacks_jll v0.2.1+0 ⌅ [dad2f222] + LLVMExtra_jll v0.0.29+0 [e98f9f5b] + NVTX_jll v3.2.1+0 [0dad84c5] + ArgTools v1.1.2 [56f22d72] + Artifacts v1.11.0 [2a0f44e3] + Base64 v1.11.0 [ade2ca70] + Dates v1.11.0 [f43a241f] + Downloads v1.7.0 [7b1f6079] + FileWatching v1.11.0 [9fa8497b] + Future v1.11.0 [b77e0a4c] + InteractiveUtils v1.11.0 [ac6e5ff7] + JuliaSyntaxHighlighting v1.12.0 [4af54fe1] + LazyArtifacts v1.11.0 [b27032c2] + LibCURL v0.6.4 [76f85450] + LibGit2 v1.11.0 [8f399da3] + Libdl v1.11.0 [37e2e46d] + LinearAlgebra v1.12.0 [56ddb016] + Logging v1.11.0 [d6f4376e] + Markdown v1.11.0 [ca575930] + NetworkOptions v1.3.0 [44cfe95a] + Pkg v1.13.0 [de0858da] + Printf v1.11.0 [9a3f8284] + Random v1.11.0 [ea8e919c] + SHA v0.7.0 [9e88b42a] + Serialization v1.11.0 [2f01184e] + SparseArrays v1.12.0 [f489334b] + StyledStrings v1.11.0 [fa267f1f] + TOML v1.0.3 [a4e569a6] + Tar v1.10.0 [cf7118a7] + UUIDs v1.11.0 [4ec0a83e] + Unicode v1.11.0 [e66e0078] + CompilerSupportLibraries_jll v1.3.0+1 [deac9b47] + LibCURL_jll v8.14.1+1 [e37daf67] + LibGit2_jll v1.9.1+0 [29816b5a] + LibSSH2_jll v1.11.3+1 [14a3606d] + MozillaCACerts_jll v2025.5.20 [4536629a] + OpenBLAS_jll v0.3.29+0 [458c3c95] + OpenSSL_jll v3.5.0+0 [efcefdf7] + PCRE2_jll v10.45.0+0 [bea87d4a] + SuiteSparse_jll v7.10.1+0 [83775a58] + Zlib_jll v1.3.1+2 [8e850b90] + libblastrampoline_jll v5.13.1+0 [8e850ede] + nghttp2_jll v1.65.0+0 [3f19e933] + p7zip_jll v17.5.0+2 Info Packages marked with ⌃ and ⌅ have new versions available. Those with ⌃ may be upgradable, but those with ⌅ are restricted by compatibility constraints from upgrading. To see why use `status --outdated -m` Installation completed after 11.82s ################################################################################ # Precompilation # Precompiling PkgEval dependencies... No packages added to or removed from `~/.julia/environments/pkgeval/Project.toml` No packages added to or removed from `~/.julia/environments/pkgeval/Manifest.toml` Precompiling package dependencies... Precompiling packages... 1069.1 ms ✓ CUDA_Driver_jll 1 dependency successfully precompiled in 1 seconds. 28 already precompiled. Precompiling packages... 1797.5 ms ✓ Atomix 4268.9 ms ✓ NVTX 5932.6 ms ✓ CUDA_Runtime_jll 6504.0 ms ✓ LLVM → BFloat16sExt 10709.1 ms ? GPUCompiler 8830.1 ms ✓ KernelAbstractions 3228.2 ms ✓ KernelAbstractions → SparseArraysExt 2702.3 ms ✓ KernelAbstractions → LinearAlgebraExt 11342.3 ms ? CUDA 12569.3 ms ? Atomix → AtomixCUDAExt 12309.8 ms ? GemmKernels 7 dependencies successfully precompiled in 82 seconds. 88 already precompiled. 4 dependencies failed but may be precompilable after restarting julia 5 dependencies had output during precompilation: ┌ LLVM → BFloat16sExt │ ┌ Error: LLVM extensions library unavailable for your platform: │ │ x86_64-linux-gnu-libgfortran5-cxx11-julia_version+1.13.0-llvm_version+20.asserts │ │ LLVM.jl will not be functional. │ │ │ │ If you are using a custom version of LLVM, try building a │ │ custom version of LLVMExtra_jll using `deps/build_local.jl` │ └ @ LLVM ~/.julia/packages/LLVM/bzSzE/src/LLVM.jl:103 │ WARNING: Constructor for type "ConstantDataArray" was extended in `BFloat16sExt` without explicit qualification or import. │ NOTE: Assumed "ConstantDataArray" refers to `LLVM.ConstantDataArray`. This behavior is deprecated and may differ in future versions. │ NOTE: This behavior may have differed in Julia versions prior to 1.12. │ Hint: If you intended to create a new generic function of the same name, use `function ConstantDataArray end`. │ Hint: To silence the warning, qualify `ConstantDataArray` as `LLVM.ConstantDataArray` in the method signature or explicitly `import LLVM: ConstantDataArray`. └ ┌ GPUCompiler │ ┌ Error: LLVM extensions library unavailable for your platform: │ │ x86_64-linux-gnu-libgfortran5-cxx11-julia_version+1.13.0-llvm_version+20.asserts │ │ LLVM.jl will not be functional. │ │ │ │ If you are using a custom version of LLVM, try building a │ │ custom version of LLVMExtra_jll using `deps/build_local.jl` │ └ @ LLVM ~/.julia/packages/LLVM/bzSzE/src/LLVM.jl:103 │ WARNING: Constructor for type "MethodError" was extended in `GPUCompiler` without explicit qualification or import. │ NOTE: Assumed "MethodError" refers to `Base.MethodError`. This behavior is deprecated and may differ in future versions. │ NOTE: This behavior may have differed in Julia versions prior to 1.12. │ Hint: If you intended to create a new generic function of the same name, use `function MethodError end`. │ Hint: To silence the warning, qualify `MethodError` as `Base.MethodError` in the method signature or explicitly `import Base: MethodError`. │ WARNING: Method definition (::Type{MethodError})(Any, Any) in module Core at boot.jl:446 overwritten in module GPUCompiler at /home/pkgeval/.julia/packages/GPUCompiler/kqxyC/src/jlgen.jl:38. │ ERROR: Method overwriting is not permitted during Module precompilation. Use `__precompile__(false)` to opt-out of precompilation. └ ┌ Atomix → AtomixCUDAExt │ ┌ Error: LLVM extensions library unavailable for your platform: │ │ x86_64-linux-gnu-libgfortran5-cxx11-julia_version+1.13.0-llvm_version+20.asserts │ │ LLVM.jl will not be functional. │ │ │ │ If you are using a custom version of LLVM, try building a │ │ custom version of LLVMExtra_jll using `deps/build_local.jl` │ └ @ LLVM ~/.julia/packages/LLVM/bzSzE/src/LLVM.jl:103 │ WARNING: Constructor for type "MethodError" was extended in `GPUCompiler` without explicit qualification or import. │ NOTE: Assumed "MethodError" refers to `Base.MethodError`. This behavior is deprecated and may differ in future versions. │ NOTE: This behavior may have differed in Julia versions prior to 1.12. │ Hint: If you intended to create a new generic function of the same name, use `function MethodError end`. │ Hint: To silence the warning, qualify `MethodError` as `Base.MethodError` in the method signature or explicitly `import Base: MethodError`. │ WARNING: Method definition (::Type{MethodError})(Any, Any) in module Core at boot.jl:446 overwritten in module GPUCompiler at /home/pkgeval/.julia/packages/GPUCompiler/kqxyC/src/jlgen.jl:38. │ ERROR: Method overwriting is not permitted during Module precompilation. Use `__precompile__(false)` to opt-out of precompilation. └ ┌ GemmKernels │ ┌ Error: LLVM extensions library unavailable for your platform: │ │ x86_64-linux-gnu-libgfortran5-cxx11-julia_version+1.13.0-llvm_version+20.asserts │ │ LLVM.jl will not be functional. │ │ │ │ If you are using a custom version of LLVM, try building a │ │ custom version of LLVMExtra_jll using `deps/build_local.jl` │ └ @ LLVM ~/.julia/packages/LLVM/bzSzE/src/LLVM.jl:103 │ WARNING: Constructor for type "MethodError" was extended in `GPUCompiler` without explicit qualification or import. │ NOTE: Assumed "MethodError" refers to `Base.MethodError`. This behavior is deprecated and may differ in future versions. │ NOTE: This behavior may have differed in Julia versions prior to 1.12. │ Hint: If you intended to create a new generic function of the same name, use `function MethodError end`. │ Hint: To silence the warning, qualify `MethodError` as `Base.MethodError` in the method signature or explicitly `import Base: MethodError`. │ WARNING: Method definition (::Type{MethodError})(Any, Any) in module Core at boot.jl:446 overwritten in module GPUCompiler at /home/pkgeval/.julia/packages/GPUCompiler/kqxyC/src/jlgen.jl:38. │ ERROR: Method overwriting is not permitted during Module precompilation. Use `__precompile__(false)` to opt-out of precompilation. └ ┌ CUDA │ ┌ Error: LLVM extensions library unavailable for your platform: │ │ x86_64-linux-gnu-libgfortran5-cxx11-julia_version+1.13.0-llvm_version+20.asserts │ │ LLVM.jl will not be functional. │ │ │ │ If you are using a custom version of LLVM, try building a │ │ custom version of LLVMExtra_jll using `deps/build_local.jl` │ └ @ LLVM ~/.julia/packages/LLVM/bzSzE/src/LLVM.jl:103 │ WARNING: Constructor for type "MethodError" was extended in `GPUCompiler` without explicit qualification or import. │ NOTE: Assumed "MethodError" refers to `Base.MethodError`. This behavior is deprecated and may differ in future versions. │ NOTE: This behavior may have differed in Julia versions prior to 1.12. │ Hint: If you intended to create a new generic function of the same name, use `function MethodError end`. │ Hint: To silence the warning, qualify `MethodError` as `Base.MethodError` in the method signature or explicitly `import Base: MethodError`. │ WARNING: Method definition (::Type{MethodError})(Any, Any) in module Core at boot.jl:446 overwritten in module GPUCompiler at /home/pkgeval/.julia/packages/GPUCompiler/kqxyC/src/jlgen.jl:38. │ ERROR: Method overwriting is not permitted during Module precompilation. Use `__precompile__(false)` to opt-out of precompilation. └ Precompilation completed after 86.58s ################################################################################ # Loading # Loading GemmKernels... Precompiling packages... 10651.6 ms ? GPUCompiler 11013.3 ms ? CUDA 12259.5 ms ? Atomix → AtomixCUDAExt Info Given GemmKernels was explicitly requested, output will be shown live  ┌ Error: LLVM extensions library unavailable for your platform: │ x86_64-linux-gnu-libgfortran5-cxx11-julia_version+1.13.0-llvm_version+20.asserts │ LLVM.jl will not be functional. │ │ If you are using a custom version of LLVM, try building a │ custom version of LLVMExtra_jll using `deps/build_local.jl` └ @ LLVM ~/.julia/packages/LLVM/bzSzE/src/LLVM.jl:103 WARNING: Constructor for type "MethodError" was extended in `GPUCompiler` without explicit qualification or import.  NOTE: Assumed "MethodError" refers to `Base.MethodError`. This behavior is deprecated and may differ in future versions.  NOTE: This behavior may have differed in Julia versions prior to 1.12.  Hint: If you intended to create a new generic function of the same name, use `function MethodError end`.  Hint: To silence the warning, qualify `MethodError` as `Base.MethodError` in the method signature or explicitly `import Base: MethodError`. WARNING: Method definition (::Type{MethodError})(Any, Any) in module Core at boot.jl:446 overwritten in module GPUCompiler at /home/pkgeval/.julia/packages/GPUCompiler/kqxyC/src/jlgen.jl:38. ERROR: Method overwriting is not permitted during Module precompilation. Use `__precompile__(false)` to opt-out of precompilation. 12311.7 ms ? GemmKernels ┌ Error: LLVM extensions library unavailable for your platform: │ x86_64-linux-gnu-libgfortran5-cxx11-julia_version+1.13.0-llvm_version+20.asserts │ LLVM.jl will not be functional. │ │ If you are using a custom version of LLVM, try building a │ custom version of LLVMExtra_jll using `deps/build_local.jl` └ @ LLVM ~/.julia/packages/LLVM/bzSzE/src/LLVM.jl:103 WARNING: Constructor for type "MethodError" was extended in `GPUCompiler` without explicit qualification or import. NOTE: Assumed "MethodError" refers to `Base.MethodError`. This behavior is deprecated and may differ in future versions. NOTE: This behavior may have differed in Julia versions prior to 1.12. Hint: If you intended to create a new generic function of the same name, use `function MethodError end`. Hint: To silence the warning, qualify `MethodError` as `Base.MethodError` in the method signature or explicitly `import Base: MethodError`. WARNING: Method definition (::Type{MethodError})(Any, Any) in module Core at boot.jl:446 overwritten in module GPUCompiler at /home/pkgeval/.julia/packages/GPUCompiler/kqxyC/src/jlgen.jl:38. ERROR: Method overwriting is not permitted during Module precompilation. Use `__precompile__(false)` to opt-out of precompilation. Precompiling packages... 10963.4 ms ? GPUCompiler Info Given CUDA was explicitly requested, output will be shown live  ┌ Error: LLVM extensions library unavailable for your platform: │ x86_64-linux-gnu-libgfortran5-cxx11-julia_version+1.13.0-llvm_version+20.asserts │ LLVM.jl will not be functional. │ │ If you are using a custom version of LLVM, try building a │ custom version of LLVMExtra_jll using `deps/build_local.jl` └ @ LLVM ~/.julia/packages/LLVM/bzSzE/src/LLVM.jl:103 WARNING: Constructor for type "MethodError" was extended in `GPUCompiler` without explicit qualification or import.  NOTE: Assumed "MethodError" refers to `Base.MethodError`. This behavior is deprecated and may differ in future versions.  NOTE: This behavior may have differed in Julia versions prior to 1.12.  Hint: If you intended to create a new generic function of the same name, use `function MethodError end`.  Hint: To silence the warning, qualify `MethodError` as `Base.MethodError` in the method signature or explicitly `import Base: MethodError`. WARNING: Method definition (::Type{MethodError})(Any, Any) in module Core at boot.jl:446 overwritten in module GPUCompiler at /home/pkgeval/.julia/packages/GPUCompiler/kqxyC/src/jlgen.jl:38. ERROR: Method overwriting is not permitted during Module precompilation. Use `__precompile__(false)` to opt-out of precompilation. 11454.9 ms ? CUDA 12003.8 ms ? Atomix → AtomixCUDAExt ┌ Error: LLVM extensions library unavailable for your platform: │ x86_64-linux-gnu-libgfortran5-cxx11-julia_version+1.13.0-llvm_version+20.asserts │ LLVM.jl will not be functional. │ │ If you are using a custom version of LLVM, try building a │ custom version of LLVMExtra_jll using `deps/build_local.jl` └ @ LLVM ~/.julia/packages/LLVM/bzSzE/src/LLVM.jl:103 WARNING: Constructor for type "MethodError" was extended in `GPUCompiler` without explicit qualification or import. NOTE: Assumed "MethodError" refers to `Base.MethodError`. This behavior is deprecated and may differ in future versions. NOTE: This behavior may have differed in Julia versions prior to 1.12. Hint: If you intended to create a new generic function of the same name, use `function MethodError end`. Hint: To silence the warning, qualify `MethodError` as `Base.MethodError` in the method signature or explicitly `import Base: MethodError`. WARNING: Method definition (::Type{MethodError})(Any, Any) in module Core at boot.jl:446 overwritten in module GPUCompiler at /home/pkgeval/.julia/packages/GPUCompiler/kqxyC/src/jlgen.jl:38. ERROR: Method overwriting is not permitted during Module precompilation. Use `__precompile__(false)` to opt-out of precompilation. Precompiling packages... Info Given GPUCompiler was explicitly requested, output will be shown live  ┌ Error: LLVM extensions library unavailable for your platform: │ x86_64-linux-gnu-libgfortran5-cxx11-julia_version+1.13.0-llvm_version+20.asserts │ LLVM.jl will not be functional. │ │ If you are using a custom version of LLVM, try building a │ custom version of LLVMExtra_jll using `deps/build_local.jl` └ @ LLVM ~/.julia/packages/LLVM/bzSzE/src/LLVM.jl:103 WARNING: Constructor for type "MethodError" was extended in `GPUCompiler` without explicit qualification or import.  NOTE: Assumed "MethodError" refers to `Base.MethodError`. This behavior is deprecated and may differ in future versions.  NOTE: This behavior may have differed in Julia versions prior to 1.12.  Hint: If you intended to create a new generic function of the same name, use `function MethodError end`.  Hint: To silence the warning, qualify `MethodError` as `Base.MethodError` in the method signature or explicitly `import Base: MethodError`. WARNING: Method definition (::Type{MethodError})(Any, Any) in module Core at boot.jl:446 overwritten in module GPUCompiler at /home/pkgeval/.julia/packages/GPUCompiler/kqxyC/src/jlgen.jl:38. ERROR: Method overwriting is not permitted during Module precompilation. Use `__precompile__(false)` to opt-out of precompilation. 10300.7 ms ? GPUCompiler ┌ Error: LLVM extensions library unavailable for your platform: │ x86_64-linux-gnu-libgfortran5-cxx11-julia_version+1.13.0-llvm_version+20.asserts │ LLVM.jl will not be functional. │ │ If you are using a custom version of LLVM, try building a │ custom version of LLVMExtra_jll using `deps/build_local.jl` └ @ LLVM ~/.julia/packages/LLVM/bzSzE/src/LLVM.jl:103 WARNING: Constructor for type "MethodError" was extended in `GPUCompiler` without explicit qualification or import. NOTE: Assumed "MethodError" refers to `Base.MethodError`. This behavior is deprecated and may differ in future versions. NOTE: This behavior may have differed in Julia versions prior to 1.12. Hint: If you intended to create a new generic function of the same name, use `function MethodError end`. Hint: To silence the warning, qualify `MethodError` as `Base.MethodError` in the method signature or explicitly `import Base: MethodError`. WARNING: Method definition (::Type{MethodError})(Any, Any) in module Core at boot.jl:446 overwritten in module GPUCompiler at /home/pkgeval/.julia/packages/GPUCompiler/kqxyC/src/jlgen.jl:38. ERROR: Method overwriting is not permitted during Module precompilation. Use `__precompile__(false)` to opt-out of precompilation. ┌ Error: LLVM extensions library unavailable for your platform: │ x86_64-linux-gnu-libgfortran5-cxx11-julia_version+1.13.0-llvm_version+20.asserts │ LLVM.jl will not be functional. │ │ If you are using a custom version of LLVM, try building a │ custom version of LLVMExtra_jll using `deps/build_local.jl` └ @ LLVM ~/.julia/packages/LLVM/bzSzE/src/LLVM.jl:103 WARNING: Constructor for type "MethodError" was extended in `GPUCompiler` without explicit qualification or import. NOTE: Assumed "MethodError" refers to `Base.MethodError`. This behavior is deprecated and may differ in future versions. NOTE: This behavior may have differed in Julia versions prior to 1.12. Hint: If you intended to create a new generic function of the same name, use `function MethodError end`. Hint: To silence the warning, qualify `MethodError` as `Base.MethodError` in the method signature or explicitly `import Base: MethodError`. ERROR: LoadError: UndefVarError: `verbose_stmt_info` not defined in `Compiler` Suggestion: check for spelling errors or missing imports. Stacktrace: [1] getproperty(x::Module, f::Symbol) @ Base ./Base_compiler.jl:50 [2] top-level scope @ ~/.julia/packages/GPUCompiler/kqxyC/src/jlgen.jl:426 [3] include(mapexpr::Function, mod::Module, _path::String) @ Base ./Base.jl:310 [4] top-level scope @ ~/.julia/packages/GPUCompiler/kqxyC/src/GPUCompiler.jl:35 [5] include(mod::Module, _path::String) @ Base ./Base.jl:309 [6] __require_prelocked(pkg::Base.PkgId, env::String) @ Base ./loading.jl:2691 [7] _require_prelocked(uuidkey::Base.PkgId, env::String) @ Base ./loading.jl:2466 [8] macro expansion @ ./loading.jl:2394 [inlined] [9] macro expansion @ ./lock.jl:376 [inlined] [10] __require(into::Module, mod::Symbol) @ Base ./loading.jl:2359 [11] require @ ./loading.jl:2335 [inlined] [12] eval_import_path @ ./module.jl:36 [inlined] [13] eval_import_path_all(at::Module, path::Expr, keyword::String) @ Base ./module.jl:60 [14] _eval_using(to::Module, path::Expr) @ Base ./module.jl:137 [15] top-level scope @ ~/.julia/packages/CUDA/Tl08O/src/CUDA.jl:3 [16] include(mod::Module, _path::String) @ Base ./Base.jl:309 [17] __require_prelocked(pkg::Base.PkgId, env::String) @ Base ./loading.jl:2691 [18] _require_prelocked(uuidkey::Base.PkgId, env::String) @ Base ./loading.jl:2466 [19] macro expansion @ ./loading.jl:2394 [inlined] [20] macro expansion @ ./lock.jl:376 [inlined] [21] __require(into::Module, mod::Symbol) @ Base ./loading.jl:2359 [22] require @ ./loading.jl:2335 [inlined] [23] eval_import_path @ ./module.jl:36 [inlined] [24] eval_import_path_all(at::Module, path::Expr, keyword::String) @ Base ./module.jl:60 [25] _eval_using(to::Module, path::Expr) @ Base ./module.jl:137 [26] top-level scope @ ~/.julia/packages/GemmKernels/tSDkP/src/GemmKernels.jl:3 [27] include(mod::Module, _path::String) @ Base ./Base.jl:309 [28] __require_prelocked(pkg::Base.PkgId, env::String) @ Base ./loading.jl:2691 [29] _require_prelocked(uuidkey::Base.PkgId, env::String) @ Base ./loading.jl:2466 [30] macro expansion @ ./loading.jl:2394 [inlined] [31] macro expansion @ ./lock.jl:376 [inlined] [32] __require(into::Module, mod::Symbol) @ Base ./loading.jl:2359 [33] require @ ./loading.jl:2335 [inlined] [34] eval_import_path @ ./module.jl:36 [inlined] [35] eval_import_path_all(at::Module, path::Expr, keyword::String) @ Base ./module.jl:60 [36] _eval_using(to::Module, path::Expr) @ Base ./module.jl:137 [37] top-level scope @ none:1 [38] eval(m::Module, e::Any) @ Core ./boot.jl:489 [39] exec_options(opts::Base.JLOptions) @ Base ./client.jl:290 [40] _start() @ Base ./client.jl:557 in expression starting at /home/pkgeval/.julia/packages/GPUCompiler/kqxyC/src/jlgen.jl:426 in expression starting at /home/pkgeval/.julia/packages/GPUCompiler/kqxyC/src/GPUCompiler.jl:1 in expression starting at /home/pkgeval/.julia/packages/CUDA/Tl08O/src/CUDA.jl:1 in expression starting at /home/pkgeval/.julia/packages/GemmKernels/tSDkP/src/GemmKernels.jl:1 Loading failed after 153.99s ERROR: LoadError: failed process: Process(`/opt/julia/bin/julia -C native -J/opt/julia/lib/julia/sys.so -g1 --check-bounds=yes --inline=yes --pkgimages=existing -e 'using GemmKernels'`, ProcessExited(1)) [1] Stacktrace: [1] pipeline_error @ ./process.jl:602 [inlined] [2] run(::Cmd; wait::Bool) @ Base ./process.jl:517 [3] run(::Cmd) @ Base ./process.jl:514 [4] top-level scope @ /PkgEval.jl/scripts/evaluate.jl:193 [5] include(mod::Module, _path::String) @ Base ./Base.jl:309 [6] exec_options(opts::Base.JLOptions) @ Base ./client.jl:324 [7] _start() @ Base ./client.jl:557 in expression starting at /PkgEval.jl/scripts/evaluate.jl:184 PkgEval failed after 280.58s: illegal method overwrites during precompilation