tmbdev · August 12, 2022 23:52
diff --git a/Manifest.toml b/Manifest.toml
 # This file is machine-generated - editing it directly is not advised

 julia_version = "1.7.3"
 manifest_format = "2.0"

 [[deps.AbstractFFTs]]
 deps = ["ChainRulesCore", "LinearAlgebra"]
 git-tree-sha1 = "69f7020bd72f069c219b5e8c236c1fa90d2cb409"
 uuid = "621f4979-c628-5d54-868e-fcf4e3e8185c"
 version = "1.2.1"

 [[deps.Adapt]]
 deps = ["LinearAlgebra"]
 git-tree-sha1 = "195c5505521008abea5aee4f96930717958eac6f"
 uuid = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
 version = "3.4.0"

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

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

 [[deps.Atomix]]
 deps = ["UnsafeAtomics"]
 git-tree-sha1 = "c06a868224ecba914baa6942988e2f2aade419be"
 uuid = "a9b6321e-bd34-4604-b9c9-b65b8de01458"
 version = "0.1.0"

 [[deps.BFloat16s]]
 deps = ["LinearAlgebra", "Printf", "Random", "Test"]
 git-tree-sha1 = "a598ecb0d717092b5539dbbe890c98bac842b072"
 uuid = "ab4f0b2a-ad5b-11e8-123f-65d77653426b"
 version = "0.2.0"

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

 [[deps.CEnum]]
 git-tree-sha1 = "eb4cb44a499229b3b8426dcfb5dd85333951ff90"
 uuid = "fa961155-64e5-5f13-b03f-caf6b980ea82"
 version = "0.4.2"

 [[deps.CUDA]]
 deps = ["AbstractFFTs", "Adapt", "BFloat16s", "CEnum", "CompilerSupportLibraries_jll", "ExprTools", "GPUArrays", "GPUCompiler", "LLVM", "LazyArtifacts", "Libdl", "LinearAlgebra", "Logging", "Printf", "Random", "Random123", "RandomNumbers", "Reexport", "Requires", "SparseArrays", "SpecialFunctions", "TimerOutputs"]
 git-tree-sha1 = "49549e2c28ffb9cc77b3689dc10e46e6271e9452"
 uuid = "052768ef-5323-5732-b1bb-66c8b64840ba"
 version = "3.12.0"

 [[deps.CUDAKernels]]
 deps = ["Adapt", "CUDA", "KernelAbstractions", "StaticArrays", "UnsafeAtomicsLLVM"]
 git-tree-sha1 = "bbab4d1a4001ec322c384dfff0889cec4118da93"
 uuid = "72cfdca4-0801-4ab0-bf6a-d52aa10adc57"
 version = "0.4.3"

 [[deps.ChainRulesCore]]
 deps = ["Compat", "LinearAlgebra", "SparseArrays"]
 git-tree-sha1 = "80ca332f6dcb2508adba68f22f551adb2d00a624"
 uuid = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
 version = "1.15.3"

 [[deps.ChangesOfVariables]]
 deps = ["ChainRulesCore", "LinearAlgebra", "Test"]
 git-tree-sha1 = "38f7a08f19d8810338d4f5085211c7dfa5d5bdd8"
 uuid = "9e997f8a-9a97-42d5-a9f1-ce6bfc15e2c0"
 version = "0.1.4"

 [[deps.Compat]]
 deps = ["Dates", "LinearAlgebra", "UUIDs"]
 git-tree-sha1 = "924cdca592bc16f14d2f7006754a621735280b74"
 uuid = "34da2185-b29b-5c13-b0c7-acf172513d20"
 version = "4.1.0"

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

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

 [[deps.DocStringExtensions]]
 deps = ["LibGit2"]
 git-tree-sha1 = "5158c2b41018c5f7eb1470d558127ac274eca0c9"
 uuid = "ffbed154-4ef7-542d-bbb7-c09d3a79fcae"
 version = "0.9.1"

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

 [[deps.Enzyme]]
 deps = ["Adapt", "CEnum", "Enzyme_jll", "GPUCompiler", "LLVM", "Libdl", "LinearAlgebra", "ObjectFile", "Printf", "Random"]
 git-tree-sha1 = "5f67585de66f933e3b353fd0a6e6191c91380af5"
 repo-rev = "main"
 repo-url = "https://github.com/EnzymeAD/Enzyme.jl.git"
 uuid = "7da242da-08ed-463a-9acd-ee780be4f1d9"
 version = "0.10.4"

 [[deps.Enzyme_jll]]
 deps = ["Artifacts", "JLLWrappers", "LazyArtifacts", "Libdl", "Pkg", "TOML"]
 git-tree-sha1 = "afb3d37467d048e0e139b881ba1193188a9ff207"
 uuid = "7cc45869-7501-5eee-bdea-0790c847d4ef"
 version = "0.0.36+0"

 [[deps.ExprTools]]
 git-tree-sha1 = "56559bbef6ca5ea0c0818fa5c90320398a6fbf8d"
 uuid = "e2ba6199-217a-4e67-a87a-7c52f15ade04"
 version = "0.1.8"

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

 [[deps.GPUArrays]]
 deps = ["Adapt", "GPUArraysCore", "LLVM", "LinearAlgebra", "Printf", "Random", "Reexport", "Serialization", "Statistics"]
 git-tree-sha1 = "73145f1d724b5ee0e90098aec39a65e9697429a6"
 uuid = "0c68f7d7-f131-5f86-a1c3-88cf8149b2d7"
 version = "8.4.2"

 [[deps.GPUArraysCore]]
 deps = ["Adapt"]
 git-tree-sha1 = "d88b17a38322e153c519f5a9ed8d91e9baa03d8f"
 uuid = "46192b85-c4d5-4398-a991-12ede77f4527"
 version = "0.1.1"

 [[deps.GPUCompiler]]
 deps = ["ExprTools", "InteractiveUtils", "LLVM", "Libdl", "Logging", "TimerOutputs", "UUIDs"]
 git-tree-sha1 = "122d7bcc92abf94cf1a86281ad7a4d0e838ab9e0"
 uuid = "61eb1bfa-7361-4325-ad38-22787b887f55"
 version = "0.16.3"

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

 [[deps.InverseFunctions]]
 deps = ["Test"]
 git-tree-sha1 = "b3364212fb5d870f724876ffcd34dd8ec6d98918"
 uuid = "3587e190-3f89-42d0-90ee-14403ec27112"
 version = "0.1.7"

 [[deps.IrrationalConstants]]
 git-tree-sha1 = "7fd44fd4ff43fc60815f8e764c0f352b83c49151"
 uuid = "92d709cd-6900-40b7-9082-c6be49f344b6"
 version = "0.1.1"

 [[deps.JLLWrappers]]
 deps = ["Preferences"]
 git-tree-sha1 = "abc9885a7ca2052a736a600f7fa66209f96506e1"
 uuid = "692b3bcd-3c85-4b1f-b108-f13ce0eb3210"
 version = "1.4.1"

 [[deps.KernelAbstractions]]
 deps = ["Adapt", "Atomix", "InteractiveUtils", "LinearAlgebra", "MacroTools", "SparseArrays", "StaticArrays", "UUIDs", "UnsafeAtomics", "UnsafeAtomicsLLVM"]
 git-tree-sha1 = "02838ecfc5f925ac408ffe6b359ac59ef8865272"
 uuid = "63c18a36-062a-441e-b654-da1e3ab1ce7c"
 version = "0.8.3"

 [[deps.KernelGradients]]
 deps = ["Enzyme", "KernelAbstractions"]
 git-tree-sha1 = "6dbcc9f869625fa50e1c7483f1c4200c65f17f9c"
 uuid = "e5faadeb-7f6c-408e-9747-a7a26e81c66a"
 version = "0.1.2"

 [[deps.LLVM]]
 deps = ["CEnum", "LLVMExtra_jll", "Libdl", "Printf", "Unicode"]
 git-tree-sha1 = "e7e9184b0bf0158ac4e4aa9daf00041b5909bf1a"
 uuid = "929cbde3-209d-540e-8aea-75f648917ca0"
 version = "4.14.0"

 [[deps.LLVMExtra_jll]]
 deps = ["Artifacts", "JLLWrappers", "LazyArtifacts", "Libdl", "Pkg", "TOML"]
 git-tree-sha1 = "771bfe376249626d3ca12bcd58ba243d3f961576"
 uuid = "dad2f222-ce93-54a1-a47d-0025e8a3acab"
 version = "0.0.16+0"

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

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

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

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

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

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

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

 [[deps.LogExpFunctions]]
 deps = ["ChainRulesCore", "ChangesOfVariables", "DocStringExtensions", "InverseFunctions", "IrrationalConstants", "LinearAlgebra"]
 git-tree-sha1 = "361c2b088575b07946508f135ac556751240091c"
 uuid = "2ab3a3ac-af41-5b50-aa03-7779005ae688"
 version = "0.3.17"

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

 [[deps.MacroTools]]
 deps = ["Markdown", "Random"]
 git-tree-sha1 = "3d3e902b31198a27340d0bf00d6ac452866021cf"
 uuid = "1914dd2f-81c6-5fcd-8719-6d5c9610ff09"
 version = "0.5.9"

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

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

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

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

 [[deps.ObjectFile]]
 deps = ["Reexport", "StructIO"]
 git-tree-sha1 = "55ce61d43409b1fb0279d1781bf3b0f22c83ab3b"
 uuid = "d8793406-e978-5875-9003-1fc021f44a92"
 version = "0.3.7"

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

 [[deps.OpenLibm_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "05823500-19ac-5b8b-9628-191a04bc5112"

 [[deps.OpenSpecFun_jll]]
 deps = ["Artifacts", "CompilerSupportLibraries_jll", "JLLWrappers", "Libdl", "Pkg"]
 git-tree-sha1 = "13652491f6856acfd2db29360e1bbcd4565d04f1"
 uuid = "efe28fd5-8261-553b-a9e1-b2916fc3738e"
 version = "0.5.5+0"

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

 [[deps.Preferences]]
 deps = ["TOML"]
 git-tree-sha1 = "47e5f437cc0e7ef2ce8406ce1e7e24d44915f88d"
 uuid = "21216c6a-2e73-6563-6e65-726566657250"
 version = "1.3.0"

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

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

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

 [[deps.Random123]]
 deps = ["Random", "RandomNumbers"]
 git-tree-sha1 = "7a1a306b72cfa60634f03a911405f4e64d1b718b"
 uuid = "74087812-796a-5b5d-8853-05524746bad3"
 version = "1.6.0"

 [[deps.RandomNumbers]]
 deps = ["Random", "Requires"]
 git-tree-sha1 = "043da614cc7e95c703498a491e2c21f58a2b8111"
 uuid = "e6cf234a-135c-5ec9-84dd-332b85af5143"
 version = "1.5.3"

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

 [[deps.Requires]]
 deps = ["UUIDs"]
 git-tree-sha1 = "838a3a4188e2ded87a4f9f184b4b0d78a1e91cb7"
 uuid = "ae029012-a4dd-5104-9daa-d747884805df"
 version = "1.3.0"

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

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

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

 [[deps.SparseArrays]]
 deps = ["LinearAlgebra", "Random"]
 uuid = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"

 [[deps.SpecialFunctions]]
 deps = ["ChainRulesCore", "IrrationalConstants", "LogExpFunctions", "OpenLibm_jll", "OpenSpecFun_jll"]
 git-tree-sha1 = "d75bda01f8c31ebb72df80a46c88b25d1c79c56d"
 uuid = "276daf66-3868-5448-9aa4-cd146d93841b"
 version = "2.1.7"

 [[deps.StaticArrays]]
 deps = ["LinearAlgebra", "Random", "StaticArraysCore", "Statistics"]
 git-tree-sha1 = "23368a3313d12a2326ad0035f0db0c0966f438ef"
 uuid = "90137ffa-7385-5640-81b9-e52037218182"
 version = "1.5.2"

 [[deps.StaticArraysCore]]
 git-tree-sha1 = "66fe9eb253f910fe8cf161953880cfdaef01cdf0"
 uuid = "1e83bf80-4336-4d27-bf5d-d5a4f845583c"
 version = "1.0.1"

 [[deps.Statistics]]
 deps = ["LinearAlgebra", "SparseArrays"]
 uuid = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"

 [[deps.StructIO]]
 deps = ["Test"]
 git-tree-sha1 = "010dc73c7146869c042b49adcdb6bf528c12e859"
 uuid = "53d494c1-5632-5724-8f4c-31dff12d585f"
 version = "0.3.0"

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

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

 [[deps.Test]]
 deps = ["InteractiveUtils", "Logging", "Random", "Serialization"]
 uuid = "8dfed614-e22c-5e08-85e1-65c5234f0b40"

 [[deps.TimerOutputs]]
 deps = ["ExprTools", "Printf"]
 git-tree-sha1 = "464d64b2510a25e6efe410e7edab14fffdc333df"
 uuid = "a759f4b9-e2f1-59dc-863e-4aeb61b1ea8f"
 version = "0.5.20"

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

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

 [[deps.UnsafeAtomics]]
 git-tree-sha1 = "6331ac3440856ea1988316b46045303bef658278"
 uuid = "013be700-e6cd-48c3-b4a1-df204f14c38f"
 version = "0.2.1"

 [[deps.UnsafeAtomicsLLVM]]
 deps = ["LLVM", "UnsafeAtomics"]
 git-tree-sha1 = "33af9d2031d0dc09e2be9a0d4beefec4466def8e"
 uuid = "d80eeb9a-aca5-4d75-85e5-170c8b632249"
 version = "0.1.0"

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

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

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

 [[deps.p7zip_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "3f19e933-33d8-53b3-aaab-bd5110c3b7a0"
diff --git a/output.txt b/output.txt
 device = CuDevice(0)
 === cpu
 (size(a), size(b), size(w), size(result)) = ((100, 2000), (100, 2500), (100, 2500), (2000, 2500))
  0.618120 seconds (1.03 M allocations: 55.465 MiB, 1.48% gc time, 30.06% compilation time)
  0.432659 seconds (16 allocations: 896 bytes)
 === cpu deriv
 16.315816 seconds (25.89 M allocations: 1.326 GiB, 3.08% gc time, 44.75% compilation time)
  5.825044 seconds (1.25 M allocations: 19.075 MiB)
 === gpu
 (size(ca), size(cb), size(cw), size(cresult)) = ((100, 2000), (100, 2500), (100, 2500), (2000, 2500))
  9.754175 seconds (21.71 M allocations: 1.146 GiB, 3.04% gc time, 30.37% compilation time)
  0.061197 seconds (62.67 k allocations: 3.375 MiB, 99.17% compilation time)
 === gpu deriv
  5.278094 seconds (8.71 M allocations: 465.265 MiB, 1.80% gc time, 11.96% compilation time)
 error in running finalizer: CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)
 throw_api_error at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
 macro expansion at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
 cuEventDestroy_v2 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
 #33 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/events.jl:30 [inlined]
 #context!#63 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 unknown function (ip: 0x7f18e8dd488b)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 context!##kw at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:161
 unknown function (ip: 0x7f18e8dd43f8)
 unsafe_destroy! at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/events.jl:29
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 run_finalizer at /buildworker/worker/package_linux64/build/src/gc.c:278
 jl_gc_run_finalizers_in_list at /buildworker/worker/package_linux64/build/src/gc.c:365
 run_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:394
 jl_gc_run_pending_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:405
 jl_mutex_unlock at /buildworker/worker/package_linux64/build/src/julia_locks.h:131 [inlined]
 jl_generate_fptr at /buildworker/worker/package_linux64/build/src/jitlayers.cpp:359
 jl_compile_method_internal at /buildworker/worker/package_linux64/build/src/gf.c:1980
 jl_compile_method_internal at /buildworker/worker/package_linux64/build/src/gf.c:2246 [inlined]
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2239 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 jl_f__call_latest at /buildworker/worker/package_linux64/build/src/builtins.c:757
 #invokelatest#2 at ./essentials.jl:716 [inlined]
 invokelatest at ./essentials.jl:714 [inlined]
 exec_options at ./client.jl:294
 _start at ./client.jl:495
 jfptr__start_22567.clone_1 at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/lib/julia/sys.so (unknown line)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 true_main at /buildworker/worker/package_linux64/build/src/jlapi.c:559
 jl_repl_entrypoint at /buildworker/worker/package_linux64/build/src/jlapi.c:701
 main at /buildworker/worker/package_linux64/build/cli/loader_exe.c:42
 unknown function (ip: 0x7f1900394d8f)
 __libc_start_main at /lib/x86_64-linux-gnu/libc.so.6 (unknown line)
 _start at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/bin/julia (unknown line)
 ERROR: LoadError: CUDA error: an illegal memory access was encountered (code 700, ERROR_ILLEGAL_ADDRESS)
 Stacktrace:
 [1] throw_api_error(res::CUDA.cudaError_enum)
   @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
 [2] macro expansion
   @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
 [3] cuEventCreate(phEvent::Base.RefValue{Ptr{Nothing}}, Flags::CUDA.CUevent_flags_enum)
   @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
 [4] CuEvent(flags::CUDA.CUevent_flags_enum)
   @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/events.jl:19
 [5] Event
   @ ~/.julia/packages/CUDAKernels/YWLqR/src/CUDAKernels.jl:109 [inlined]
 [6] Δdist!(x::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, y::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, w::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, result::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, ∂x::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, ∂y::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, ∂w::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, ∂result::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer})
   @ Main ~/proj/mnistjl/wdistances.jl:59
 [7] top-level scope
   @ ./timing.jl:220
 in expression starting at /home/tmb/proj/mnistjl/wdistances.jl:95
 error in running finalizer: CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)
 throw_api_error at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
 macro expansion at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
 cuStreamDestroy_v2 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
 #10 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/stream.jl:86 [inlined]
 #context!#63 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 unknown function (ip: 0x7f18e6516ccb)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 context!##kw at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:161
 unsafe_destroy! at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/stream.jl:85
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 run_finalizer at /buildworker/worker/package_linux64/build/src/gc.c:278
 jl_gc_run_finalizers_in_list at /buildworker/worker/package_linux64/build/src/gc.c:365
 run_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:394 [inlined]
 jl_gc_run_all_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:482
 jl_atexit_hook at /buildworker/worker/package_linux64/build/src/init.c:240
 jl_exit at /buildworker/worker/package_linux64/build/src/jl_uv.c:633
 exit at ./initdefs.jl:28 [inlined]
 exec_options at ./client.jl:296
 _start at ./client.jl:495
 jfptr__start_22567.clone_1 at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/lib/julia/sys.so (unknown line)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 true_main at /buildworker/worker/package_linux64/build/src/jlapi.c:559
 jl_repl_entrypoint at /buildworker/worker/package_linux64/build/src/jlapi.c:701
 main at /buildworker/worker/package_linux64/build/cli/loader_exe.c:42
 unknown function (ip: 0x7f1900394d8f)
 __libc_start_main at /lib/x86_64-linux-gnu/libc.so.6 (unknown line)
 _start at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/bin/julia (unknown line)
 error in running finalizer: CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)
 throw_api_error at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
 macro expansion at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
 cuStreamDestroy_v2 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
 #10 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/stream.jl:86 [inlined]
 #context!#63 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 unknown function (ip: 0x7f18e6516ccb)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 context!##kw at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:161
 unsafe_destroy! at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/stream.jl:85
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 run_finalizer at /buildworker/worker/package_linux64/build/src/gc.c:278
 jl_gc_run_finalizers_in_list at /buildworker/worker/package_linux64/build/src/gc.c:365
 run_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:394 [inlined]
 jl_gc_run_all_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:482
 jl_atexit_hook at /buildworker/worker/package_linux64/build/src/init.c:240
 jl_exit at /buildworker/worker/package_linux64/build/src/jl_uv.c:633
 exit at ./initdefs.jl:28 [inlined]
 exec_options at ./client.jl:296
 _start at ./client.jl:495
 jfptr__start_22567.clone_1 at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/lib/julia/sys.so (unknown line)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 true_main at /buildworker/worker/package_linux64/build/src/jlapi.c:559
 jl_repl_entrypoint at /buildworker/worker/package_linux64/build/src/jlapi.c:701
 main at /buildworker/worker/package_linux64/build/cli/loader_exe.c:42
 unknown function (ip: 0x7f1900394d8f)
 __libc_start_main at /lib/x86_64-linux-gnu/libc.so.6 (unknown line)
 _start at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/bin/julia (unknown line)
 error in running finalizer: CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)
 throw_api_error at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
 macro expansion at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
 cuModuleUnload at /home/tmb/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
 #27 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/module.jl:82 [inlined]
 #context!#63 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 unknown function (ip: 0x7f18e651722b)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 context!##kw at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:161
 unsafe_unload! at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/module.jl:81
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 run_finalizer at /buildworker/worker/package_linux64/build/src/gc.c:278
 jl_gc_run_finalizers_in_list at /buildworker/worker/package_linux64/build/src/gc.c:365
 run_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:394 [inlined]
 jl_gc_run_all_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:482
 jl_atexit_hook at /buildworker/worker/package_linux64/build/src/init.c:240
 jl_exit at /buildworker/worker/package_linux64/build/src/jl_uv.c:633
 exit at ./initdefs.jl:28 [inlined]
 exec_options at ./client.jl:296
 _start at ./client.jl:495
 jfptr__start_22567.clone_1 at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/lib/julia/sys.so (unknown line)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 true_main at /buildworker/worker/package_linux64/build/src/jlapi.c:559
 jl_repl_entrypoint at /buildworker/worker/package_linux64/build/src/jlapi.c:701
 main at /buildworker/worker/package_linux64/build/cli/loader_exe.c:42
 unknown function (ip: 0x7f1900394d8f)
 __libc_start_main at /lib/x86_64-linux-gnu/libc.so.6 (unknown line)
 _start at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/bin/julia (unknown line)
 error in running finalizer: CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)
 throw_api_error at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
 macro expansion at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
 cuEventDestroy_v2 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
 #33 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/events.jl:30 [inlined]
 #context!#63 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 unknown function (ip: 0x7f18e8dd488b)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 context!##kw at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:161
 unknown function (ip: 0x7f18e8dd43f8)
 unsafe_destroy! at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/events.jl:29
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 run_finalizer at /buildworker/worker/package_linux64/build/src/gc.c:278
 jl_gc_run_finalizers_in_list at /buildworker/worker/package_linux64/build/src/gc.c:365
 run_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:394 [inlined]
 jl_gc_run_all_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:482
 jl_atexit_hook at /buildworker/worker/package_linux64/build/src/init.c:240
 jl_exit at /buildworker/worker/package_linux64/build/src/jl_uv.c:633
 exit at ./initdefs.jl:28 [inlined]
 exec_options at ./client.jl:296
 _start at ./client.jl:495
 jfptr__start_22567.clone_1 at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/lib/julia/sys.so (unknown line)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 true_main at /buildworker/worker/package_linux64/build/src/jlapi.c:559
 jl_repl_entrypoint at /buildworker/worker/package_linux64/build/src/jlapi.c:701
 main at /buildworker/worker/package_linux64/build/cli/loader_exe.c:42
 unknown function (ip: 0x7f1900394d8f)
 __libc_start_main at /lib/x86_64-linux-gnu/libc.so.6 (unknown line)
 _start at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/bin/julia (unknown line)
 error in running finalizer: CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)
 throw_api_error at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
 macro expansion at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
 cuStreamDestroy_v2 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
 #10 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/stream.jl:86 [inlined]
 #context!#63 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 unknown function (ip: 0x7f18e6516ccb)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 context!##kw at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:161
 unsafe_destroy! at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/stream.jl:85
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 run_finalizer at /buildworker/worker/package_linux64/build/src/gc.c:278
 jl_gc_run_finalizers_in_list at /buildworker/worker/package_linux64/build/src/gc.c:365
 run_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:394 [inlined]
 jl_gc_run_all_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:482
 jl_atexit_hook at /buildworker/worker/package_linux64/build/src/init.c:240
 jl_exit at /buildworker/worker/package_linux64/build/src/jl_uv.c:633
 exit at ./initdefs.jl:28 [inlined]
 exec_options at ./client.jl:296
 _start at ./client.jl:495
 jfptr__start_22567.clone_1 at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/lib/julia/sys.so (unknown line)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 true_main at /buildworker/worker/package_linux64/build/src/jlapi.c:559
 jl_repl_entrypoint at /buildworker/worker/package_linux64/build/src/jlapi.c:701
 main at /buildworker/worker/package_linux64/build/cli/loader_exe.c:42
 unknown function (ip: 0x7f1900394d8f)
 __libc_start_main at /lib/x86_64-linux-gnu/libc.so.6 (unknown line)
 _start at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/bin/julia (unknown line)
 error in running finalizer: CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)
 throw_api_error at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
 macro expansion at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
 cuStreamDestroy_v2 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
 #10 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/stream.jl:86 [inlined]
 #context!#63 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 unknown function (ip: 0x7f18e6516ccb)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 context!##kw at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:161
 unsafe_destroy! at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/stream.jl:85
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 run_finalizer at /buildworker/worker/package_linux64/build/src/gc.c:278
 jl_gc_run_finalizers_in_list at /buildworker/worker/package_linux64/build/src/gc.c:365
 run_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:394 [inlined]
 jl_gc_run_all_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:482
 jl_atexit_hook at /buildworker/worker/package_linux64/build/src/init.c:240
 jl_exit at /buildworker/worker/package_linux64/build/src/jl_uv.c:633
 exit at ./initdefs.jl:28 [inlined]
 exec_options at ./client.jl:296
 _start at ./client.jl:495
 jfptr__start_22567.clone_1 at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/lib/julia/sys.so (unknown line)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 true_main at /buildworker/worker/package_linux64/build/src/jlapi.c:559
 jl_repl_entrypoint at /buildworker/worker/package_linux64/build/src/jlapi.c:701
 main at /buildworker/worker/package_linux64/build/cli/loader_exe.c:42
 unknown function (ip: 0x7f1900394d8f)
 __libc_start_main at /lib/x86_64-linux-gnu/libc.so.6 (unknown line)
 _start at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/bin/julia (unknown line)
 error in running finalizer: CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)
 throw_api_error at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
 macro expansion at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
 cuStreamDestroy_v2 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
 #10 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/stream.jl:86 [inlined]
 #context!#63 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 unknown function (ip: 0x7f18e6516ccb)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 context!##kw at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:161
 unsafe_destroy! at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/stream.jl:85
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 run_finalizer at /buildworker/worker/package_linux64/build/src/gc.c:278
 jl_gc_run_finalizers_in_list at /buildworker/worker/package_linux64/build/src/gc.c:365
 run_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:394 [inlined]
 jl_gc_run_all_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:482
 jl_atexit_hook at /buildworker/worker/package_linux64/build/src/init.c:240
 jl_exit at /buildworker/worker/package_linux64/build/src/jl_uv.c:633
 exit at ./initdefs.jl:28 [inlined]
 exec_options at ./client.jl:296
 _start at ./client.jl:495
 jfptr__start_22567.clone_1 at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/lib/julia/sys.so (unknown line)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 true_main at /buildworker/worker/package_linux64/build/src/jlapi.c:559
 jl_repl_entrypoint at /buildworker/worker/package_linux64/build/src/jlapi.c:701
 main at /buildworker/worker/package_linux64/build/cli/loader_exe.c:42
 unknown function (ip: 0x7f1900394d8f)
 __libc_start_main at /lib/x86_64-linux-gnu/libc.so.6 (unknown line)
 _start at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/bin/julia (unknown line)
 error in running finalizer: CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)
 throw_api_error at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
 macro expansion at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
 cuModuleUnload at /home/tmb/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
 #27 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/module.jl:82 [inlined]
 #context!#63 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 unknown function (ip: 0x7f18e651722b)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 context!##kw at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:161
 unsafe_unload! at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/module.jl:81
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 run_finalizer at /buildworker/worker/package_linux64/build/src/gc.c:278
 jl_gc_run_finalizers_in_list at /buildworker/worker/package_linux64/build/src/gc.c:365
 run_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:394 [inlined]
 jl_gc_run_all_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:482
 jl_atexit_hook at /buildworker/worker/package_linux64/build/src/init.c:240
 jl_exit at /buildworker/worker/package_linux64/build/src/jl_uv.c:633
 exit at ./initdefs.jl:28 [inlined]
 exec_options at ./client.jl:296
 _start at ./client.jl:495
 jfptr__start_22567.clone_1 at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/lib/julia/sys.so (unknown line)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 true_main at /buildworker/worker/package_linux64/build/src/jlapi.c:559
 jl_repl_entrypoint at /buildworker/worker/package_linux64/build/src/jlapi.c:701
 main at /buildworker/worker/package_linux64/build/cli/loader_exe.c:42
 unknown function (ip: 0x7f1900394d8f)
 __libc_start_main at /lib/x86_64-linux-gnu/libc.so.6 (unknown line)
 _start at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/bin/julia (unknown line)
 error in running finalizer: CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)
 throw_api_error at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
 macro expansion at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
 cuEventDestroy_v2 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
 #33 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/events.jl:30 [inlined]
 #context!#63 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 unknown function (ip: 0x7f18e8dd488b)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 context!##kw at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:161
 unknown function (ip: 0x7f18e8dd43f8)
 unsafe_destroy! at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/events.jl:29
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 run_finalizer at /buildworker/worker/package_linux64/build/src/gc.c:278
 jl_gc_run_finalizers_in_list at /buildworker/worker/package_linux64/build/src/gc.c:365
 run_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:394 [inlined]
 jl_gc_run_all_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:482
 jl_atexit_hook at /buildworker/worker/package_linux64/build/src/init.c:240
 jl_exit at /buildworker/worker/package_linux64/build/src/jl_uv.c:633
 exit at ./initdefs.jl:28 [inlined]
 exec_options at ./client.jl:296
 _start at ./client.jl:495
 jfptr__start_22567.clone_1 at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/lib/julia/sys.so (unknown line)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 true_main at /buildworker/worker/package_linux64/build/src/jlapi.c:559
 jl_repl_entrypoint at /buildworker/worker/package_linux64/build/src/jlapi.c:701
 main at /buildworker/worker/package_linux64/build/cli/loader_exe.c:42
 unknown function (ip: 0x7f1900394d8f)
 __libc_start_main at /lib/x86_64-linux-gnu/libc.so.6 (unknown line)
 _start at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/bin/julia (unknown line)
 WARNING: Error while freeing DeviceBuffer(19.073 MiB at 0x000000030386aa00):
 CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)

 Stacktrace:
  [1] throw_api_error(res::CUDA.cudaError_enum)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
  [2] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
  [3] cuMemFreeAsync(dptr::CUDA.Mem.DeviceBuffer, hStream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
  [4] #free#2
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/memory.jl:97 [inlined]
  [5] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:58 [inlined]
  [6] macro expansion
    @ ./timing.jl:299 [inlined]
  [7] #actual_free#155
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:57 [inlined]
  [8] #_free#173
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:375 [inlined]
  [9] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:348 [inlined]
 [10] macro expansion
    @ ./timing.jl:299 [inlined]
 [11] #free#172
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:347 [inlined]
 [12] #178
    @ ~/.julia/packages/CUDA/DfvRa/src/array.jl:79 [inlined]
 [13] context!(f::CUDA.var"#178#179"{CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CuStream}, ctx::CuContext; skip_destroyed::Bool)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 [14] unsafe_free!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, stream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:78
 [15] unsafe_finalize!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer})
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:99
 [16] exit
    @ ./initdefs.jl:28 [inlined]
 [17] exec_options(opts::Base.JLOptions)
    @ Base ./client.jl:296
 [18] _start()
    @ Base ./client.jl:495
 WARNING: Error while freeing DeviceBuffer(976.562 KiB at 0x0000000303776600):
 CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)

 Stacktrace:
  [1] throw_api_error(res::CUDA.cudaError_enum)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
  [2] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
  [3] cuMemFreeAsync(dptr::CUDA.Mem.DeviceBuffer, hStream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
  [4] #free#2
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/memory.jl:97 [inlined]
  [5] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:58 [inlined]
  [6] macro expansion
    @ ./timing.jl:299 [inlined]
  [7] #actual_free#155
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:57 [inlined]
  [8] #_free#173
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:375 [inlined]
  [9] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:348 [inlined]
 [10] macro expansion
    @ ./timing.jl:299 [inlined]
 [11] #free#172
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:347 [inlined]
 [12] #178
    @ ~/.julia/packages/CUDA/DfvRa/src/array.jl:79 [inlined]
 [13] context!(f::CUDA.var"#178#179"{CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CuStream}, ctx::CuContext; skip_destroyed::Bool)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 [14] unsafe_free!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, stream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:78
 [15] unsafe_finalize!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer})
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:99
 [16] exit
    @ ./initdefs.jl:28 [inlined]
 [17] exec_options(opts::Base.JLOptions)
    @ Base ./client.jl:296
 [18] _start()
    @ Base ./client.jl:495
 WARNING: Error while freeing DeviceBuffer(976.562 KiB at 0x0000000303682200):
 CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)

 Stacktrace:
  [1] throw_api_error(res::CUDA.cudaError_enum)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
  [2] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
  [3] cuMemFreeAsync(dptr::CUDA.Mem.DeviceBuffer, hStream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
  [4] #free#2
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/memory.jl:97 [inlined]
  [5] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:58 [inlined]
  [6] macro expansion
    @ ./timing.jl:299 [inlined]
  [7] #actual_free#155
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:57 [inlined]
  [8] #_free#173
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:375 [inlined]
  [9] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:348 [inlined]
 [10] macro expansion
    @ ./timing.jl:299 [inlined]
 [11] #free#172
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:347 [inlined]
 [12] #178
    @ ~/.julia/packages/CUDA/DfvRa/src/array.jl:79 [inlined]
 [13] context!(f::CUDA.var"#178#179"{CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CuStream}, ctx::CuContext; skip_destroyed::Bool)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 [14] unsafe_free!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, stream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:78
 [15] unsafe_finalize!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer})
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:99
 [16] exit
    @ ./initdefs.jl:28 [inlined]
 [17] exec_options(opts::Base.JLOptions)
    @ Base ./client.jl:296
 [18] _start()
    @ Base ./client.jl:495
 WARNING: Error while freeing DeviceBuffer(781.250 KiB at 0x00000003035bec00):
 CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)

 Stacktrace:
  [1] throw_api_error(res::CUDA.cudaError_enum)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
  [2] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
  [3] cuMemFreeAsync(dptr::CUDA.Mem.DeviceBuffer, hStream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
  [4] #free#2
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/memory.jl:97 [inlined]
  [5] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:58 [inlined]
  [6] macro expansion
    @ ./timing.jl:299 [inlined]
  [7] #actual_free#155
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:57 [inlined]
  [8] #_free#173
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:375 [inlined]
  [9] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:348 [inlined]
 [10] macro expansion
    @ ./timing.jl:299 [inlined]
 [11] #free#172
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:347 [inlined]
 [12] #178
    @ ~/.julia/packages/CUDA/DfvRa/src/array.jl:79 [inlined]
 [13] context!(f::CUDA.var"#178#179"{CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CuStream}, ctx::CuContext; skip_destroyed::Bool)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 [14] unsafe_free!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, stream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:78
 [15] unsafe_finalize!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer})
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:99
 [16] exit
    @ ./initdefs.jl:28 [inlined]
 [17] exec_options(opts::Base.JLOptions)
    @ Base ./client.jl:296
 [18] _start()
    @ Base ./client.jl:495
 WARNING: Error while freeing DeviceBuffer(19.073 MiB at 0x00000003022abe00):
 CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)

 Stacktrace:
  [1] throw_api_error(res::CUDA.cudaError_enum)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
  [2] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
  [3] cuMemFreeAsync(dptr::CUDA.Mem.DeviceBuffer, hStream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
  [4] #free#2
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/memory.jl:97 [inlined]
  [5] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:58 [inlined]
  [6] macro expansion
    @ ./timing.jl:299 [inlined]
  [7] #actual_free#155
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:57 [inlined]
  [8] #_free#173
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:375 [inlined]
  [9] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:348 [inlined]
 [10] macro expansion
    @ ./timing.jl:299 [inlined]
 [11] #free#172
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:347 [inlined]
 [12] #178
    @ ~/.julia/packages/CUDA/DfvRa/src/array.jl:79 [inlined]
 [13] context!(f::CUDA.var"#178#179"{CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CuStream}, ctx::CuContext; skip_destroyed::Bool)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 [14] unsafe_free!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, stream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:78
 [15] unsafe_finalize!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer})
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:99
 [16] exit
    @ ./initdefs.jl:28 [inlined]
 [17] exec_options(opts::Base.JLOptions)
    @ Base ./client.jl:296
 [18] _start()
    @ Base ./client.jl:495
 WARNING: Error while freeing DeviceBuffer(976.562 KiB at 0x00000003021b7a00):
 CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)

 Stacktrace:
  [1] throw_api_error(res::CUDA.cudaError_enum)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
  [2] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
  [3] cuMemFreeAsync(dptr::CUDA.Mem.DeviceBuffer, hStream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
  [4] #free#2
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/memory.jl:97 [inlined]
  [5] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:58 [inlined]
  [6] macro expansion
    @ ./timing.jl:299 [inlined]
  [7] #actual_free#155
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:57 [inlined]
  [8] #_free#173
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:375 [inlined]
  [9] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:348 [inlined]
 [10] macro expansion
    @ ./timing.jl:299 [inlined]
 [11] #free#172
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:347 [inlined]
 [12] #178
    @ ~/.julia/packages/CUDA/DfvRa/src/array.jl:79 [inlined]
 [13] context!(f::CUDA.var"#178#179"{CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CuStream}, ctx::CuContext; skip_destroyed::Bool)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 [14] unsafe_free!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, stream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:78
 [15] unsafe_finalize!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer})
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:99
 [16] exit
    @ ./initdefs.jl:28 [inlined]
 [17] exec_options(opts::Base.JLOptions)
    @ Base ./client.jl:296
 [18] _start()
    @ Base ./client.jl:495
 WARNING: Error while freeing DeviceBuffer(976.562 KiB at 0x00000003020c3600):
 CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)

 Stacktrace:
  [1] throw_api_error(res::CUDA.cudaError_enum)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
  [2] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
  [3] cuMemFreeAsync(dptr::CUDA.Mem.DeviceBuffer, hStream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
  [4] #free#2
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/memory.jl:97 [inlined]
  [5] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:58 [inlined]
  [6] macro expansion
    @ ./timing.jl:299 [inlined]
  [7] #actual_free#155
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:57 [inlined]
  [8] #_free#173
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:375 [inlined]
  [9] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:348 [inlined]
 [10] macro expansion
    @ ./timing.jl:299 [inlined]
 [11] #free#172
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:347 [inlined]
 [12] #178
    @ ~/.julia/packages/CUDA/DfvRa/src/array.jl:79 [inlined]
 [13] context!(f::CUDA.var"#178#179"{CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CuStream}, ctx::CuContext; skip_destroyed::Bool)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 [14] unsafe_free!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, stream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:78
 [15] unsafe_finalize!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer})
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:99
 [16] exit
    @ ./initdefs.jl:28 [inlined]
 [17] exec_options(opts::Base.JLOptions)
    @ Base ./client.jl:296
 [18] _start()
    @ Base ./client.jl:495
 WARNING: Error while freeing DeviceBuffer(781.250 KiB at 0x0000000302000000):
 CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)

 Stacktrace:
  [1] throw_api_error(res::CUDA.cudaError_enum)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
  [2] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
  [3] cuMemFreeAsync(dptr::CUDA.Mem.DeviceBuffer, hStream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
  [4] #free#2
    @ ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/memory.jl:97 [inlined]
  [5] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:58 [inlined]
  [6] macro expansion
    @ ./timing.jl:299 [inlined]
  [7] #actual_free#155
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:57 [inlined]
  [8] #_free#173
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:375 [inlined]
  [9] macro expansion
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:348 [inlined]
 [10] macro expansion
    @ ./timing.jl:299 [inlined]
 [11] #free#172
    @ ~/.julia/packages/CUDA/DfvRa/src/pool.jl:347 [inlined]
 [12] #178
    @ ~/.julia/packages/CUDA/DfvRa/src/array.jl:79 [inlined]
 [13] context!(f::CUDA.var"#178#179"{CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CuStream}, ctx::CuContext; skip_destroyed::Bool)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 [14] unsafe_free!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, stream::CuStream)
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:78
 [15] unsafe_finalize!(xs::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer})
    @ CUDA ~/.julia/packages/CUDA/DfvRa/src/array.jl:99
 [16] exit
    @ ./initdefs.jl:28 [inlined]
 [17] exec_options(opts::Base.JLOptions)
    @ Base ./client.jl:296
 [18] _start()
    @ Base ./client.jl:495
 error in running finalizer: CUDA.CuError(code=CUDA.cudaError_enum(0x000002bc), meta=nothing)
 throw_api_error at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:89
 macro expansion at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/error.jl:97 [inlined]
 cuStreamDestroy_v2 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/utils/call.jl:26
 #10 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/stream.jl:86 [inlined]
 #context!#63 at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:164
 unknown function (ip: 0x7f18e6516ccb)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 context!##kw at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/state.jl:161
 unsafe_destroy! at /home/tmb/.julia/packages/CUDA/DfvRa/lib/cudadrv/stream.jl:85
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 run_finalizer at /buildworker/worker/package_linux64/build/src/gc.c:278
 jl_gc_run_finalizers_in_list at /buildworker/worker/package_linux64/build/src/gc.c:365
 run_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:394 [inlined]
 jl_gc_run_all_finalizers at /buildworker/worker/package_linux64/build/src/gc.c:482
 jl_atexit_hook at /buildworker/worker/package_linux64/build/src/init.c:240
 jl_exit at /buildworker/worker/package_linux64/build/src/jl_uv.c:633
 exit at ./initdefs.jl:28 [inlined]
 exec_options at ./client.jl:296
 _start at ./client.jl:495
 jfptr__start_22567.clone_1 at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/lib/julia/sys.so (unknown line)
 _jl_invoke at /buildworker/worker/package_linux64/build/src/gf.c:2247 [inlined]
 jl_apply_generic at /buildworker/worker/package_linux64/build/src/gf.c:2429
 jl_apply at /buildworker/worker/package_linux64/build/src/julia.h:1788 [inlined]
 true_main at /buildworker/worker/package_linux64/build/src/jlapi.c:559
 jl_repl_entrypoint at /buildworker/worker/package_linux64/build/src/jlapi.c:701
 main at /buildworker/worker/package_linux64/build/cli/loader_exe.c:42
 unknown function (ip: 0x7f1900394d8f)
 __libc_start_main at /lib/x86_64-linux-gnu/libc.so.6 (unknown line)
 _start at /home/tmb/.julia/juliaup/julia-1.7.3+0.x64/bin/julia (unknown line)
diff --git a/Project.toml b/Project.toml
 [deps]
 CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
 CUDAKernels = "72cfdca4-0801-4ab0-bf6a-d52aa10adc57"
 Enzyme = "7da242da-08ed-463a-9acd-ee780be4f1d9"
 KernelAbstractions = "63c18a36-062a-441e-b654-da1e3ab1ce7c"
 KernelGradients = "e5faadeb-7f6c-408e-9747-a7a26e81c66a"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
diff --git a/wdistances.jl b/wdistances.jl
 using Enzyme
 using CUDA
 using CUDAKernels
 using KernelAbstractions
 using KernelGradients
 using Test

 CUDA.allowscalar(false)

 device = CUDA.device()
 @show device

 function kconfig(a::Array)
    return (CPU(), 4)
 end

 function kconfig(a::CuArray)
    return (CUDADevice(), 256)
 end

 function same_device(xs...)
    device = KernelAbstractions.get_device(xs[1])
    for x in xs
        if KernelAbstractions.get_device(x) != device
            return false
        end
    end
    return true
 end

 @kernel function dist_kernel!(@Const(x), @Const(y), @Const(w), result)
    q = 2
    i, j = @index(Global, NTuple)
    result[i, j] = zero(eltype(result))
    for k = 1:size(x, 1)
        result[i, j] += (abs(x[k, i] - y[k, j]) * w[k, j]) ^ q
    end
    result[i, j] = result[i, j] ^ (1 / q)
    nothing
 end

 function dist!(x, y, w, result)
    @assert size(x, 1) == size(y, 1)
    @assert size(x, 2) == size(result, 1)
    @assert size(y, 2) == size(result, 2)
    @assert same_device(x, y, result)
    kernel! = dist_kernel!(kconfig(x)...)
    ev = kernel!(x, y, w, result; ndrange=size(result))
    wait(ev)
 end

 function Δdist!(x, y, w, result, ∂x, ∂y, ∂w, ∂result)
    @assert same_device(x, y, w, result, ∂x, ∂y, ∂w, ∂result)
    @assert size(x) == size(∂x)
    @assert size(y) == size(∂y)
    @assert size(w) == size(∂w)
    @assert size(result) == size(∂result)
    deriv = Enzyme.autodiff(dist_kernel!(kconfig(x)...))
    ev = deriv(Duplicated(x, ∂x), Duplicated(y, ∂y), Duplicated(w, ∂w), Duplicated(result, ∂result); ndrange=size(result))
    wait(ev)
 end

 d = 100
 n = 2000
 m = 2500

 a, b, w, result = rand(Float32, d, n), rand(Float32, d, m), rand(Float32, d, m), zeros(Float32, n, m)
 ∂a, ∂b, ∂w, ∂result = zeros(Float32, d, n), zeros(Float32, d, m), zeros(Float32, d, m), rand(Float32, n, m)

 ca, cb, cw, cresult = CuArray(a), CuArray(b), CuArray(w), CuArray(result)
 c∂a, c∂b, c∂w, c∂result = CuArray(∂a), CuArray(∂b), CuArray(∂w), CuArray(∂result)

 println("=== cpu")

 @show size(a), size(b), size(w), size(result)

 @time dist!(a, b, w, result)
 @time dist!(a, b, w, result)

 println("=== cpu deriv")

 @time Δdist!(a, b, w, result, ∂a, ∂b, ∂w, ∂result)
 @time Δdist!(a, b, w, result, ∂a, ∂b, ∂w, ∂result)

 println("=== gpu")

 @show size(ca), size(cb), size(cw), size(cresult)

 @time dist!(ca, cb, cw, cresult)
 @time dist!(ca, cb, cw, cresult)

 println("=== gpu deriv")

 @time Δdist!(ca, cb, cw, cresult, c∂a, c∂b, c∂w, c∂result)
 @time Δdist!(ca, cb, cw, cresult, c∂a, c∂b, c∂w, c∂result)
	# This file is machine-generated - editing it directly is not advised

	julia_version = "1.7.3"
	manifest_format = "2.0"

	[[deps.AbstractFFTs]]
	deps = ["ChainRulesCore", "LinearAlgebra"]
	git-tree-sha1 = "69f7020bd72f069c219b5e8c236c1fa90d2cb409"
	uuid = "621f4979-c628-5d54-868e-fcf4e3e8185c"
	version = "1.2.1"

	[[deps.Adapt]]
	deps = ["LinearAlgebra"]
	git-tree-sha1 = "195c5505521008abea5aee4f96930717958eac6f"
	uuid = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
	version = "3.4.0"

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

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

	[[deps.Atomix]]
	deps = ["UnsafeAtomics"]
	git-tree-sha1 = "c06a868224ecba914baa6942988e2f2aade419be"
	uuid = "a9b6321e-bd34-4604-b9c9-b65b8de01458"
	version = "0.1.0"

	[[deps.BFloat16s]]
	deps = ["LinearAlgebra", "Printf", "Random", "Test"]
	git-tree-sha1 = "a598ecb0d717092b5539dbbe890c98bac842b072"
	uuid = "ab4f0b2a-ad5b-11e8-123f-65d77653426b"
	version = "0.2.0"

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

	[[deps.CEnum]]
	git-tree-sha1 = "eb4cb44a499229b3b8426dcfb5dd85333951ff90"
	uuid = "fa961155-64e5-5f13-b03f-caf6b980ea82"
	version = "0.4.2"

	[[deps.CUDA]]
	deps = ["AbstractFFTs", "Adapt", "BFloat16s", "CEnum", "CompilerSupportLibraries_jll", "ExprTools", "GPUArrays", "GPUCompiler", "LLVM", "LazyArtifacts", "Libdl", "LinearAlgebra", "Logging", "Printf", "Random", "Random123", "RandomNumbers", "Reexport", "Requires", "SparseArrays", "SpecialFunctions", "TimerOutputs"]
	git-tree-sha1 = "49549e2c28ffb9cc77b3689dc10e46e6271e9452"
	uuid = "052768ef-5323-5732-b1bb-66c8b64840ba"
	version = "3.12.0"

	[[deps.CUDAKernels]]
	deps = ["Adapt", "CUDA", "KernelAbstractions", "StaticArrays", "UnsafeAtomicsLLVM"]
	git-tree-sha1 = "bbab4d1a4001ec322c384dfff0889cec4118da93"
	uuid = "72cfdca4-0801-4ab0-bf6a-d52aa10adc57"
	version = "0.4.3"

	[[deps.ChainRulesCore]]
	deps = ["Compat", "LinearAlgebra", "SparseArrays"]
	git-tree-sha1 = "80ca332f6dcb2508adba68f22f551adb2d00a624"
	uuid = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
	version = "1.15.3"

	[[deps.ChangesOfVariables]]
	deps = ["ChainRulesCore", "LinearAlgebra", "Test"]
	git-tree-sha1 = "38f7a08f19d8810338d4f5085211c7dfa5d5bdd8"
	uuid = "9e997f8a-9a97-42d5-a9f1-ce6bfc15e2c0"
	version = "0.1.4"

	[[deps.Compat]]
	deps = ["Dates", "LinearAlgebra", "UUIDs"]
	git-tree-sha1 = "924cdca592bc16f14d2f7006754a621735280b74"
	uuid = "34da2185-b29b-5c13-b0c7-acf172513d20"
	version = "4.1.0"

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

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

	[[deps.DocStringExtensions]]
	deps = ["LibGit2"]
	git-tree-sha1 = "5158c2b41018c5f7eb1470d558127ac274eca0c9"
	uuid = "ffbed154-4ef7-542d-bbb7-c09d3a79fcae"
	version = "0.9.1"

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

	[[deps.Enzyme]]
	deps = ["Adapt", "CEnum", "Enzyme_jll", "GPUCompiler", "LLVM", "Libdl", "LinearAlgebra", "ObjectFile", "Printf", "Random"]
	git-tree-sha1 = "5f67585de66f933e3b353fd0a6e6191c91380af5"
	repo-rev = "main"
	repo-url = "https://github.com/EnzymeAD/Enzyme.jl.git"
	uuid = "7da242da-08ed-463a-9acd-ee780be4f1d9"
	version = "0.10.4"

	[[deps.Enzyme_jll]]
	deps = ["Artifacts", "JLLWrappers", "LazyArtifacts", "Libdl", "Pkg", "TOML"]
	git-tree-sha1 = "afb3d37467d048e0e139b881ba1193188a9ff207"
	uuid = "7cc45869-7501-5eee-bdea-0790c847d4ef"
	version = "0.0.36+0"

	[[deps.ExprTools]]
	git-tree-sha1 = "56559bbef6ca5ea0c0818fa5c90320398a6fbf8d"
	uuid = "e2ba6199-217a-4e67-a87a-7c52f15ade04"
	version = "0.1.8"

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

	[[deps.GPUArrays]]
	deps = ["Adapt", "GPUArraysCore", "LLVM", "LinearAlgebra", "Printf", "Random", "Reexport", "Serialization", "Statistics"]
	git-tree-sha1 = "73145f1d724b5ee0e90098aec39a65e9697429a6"
	uuid = "0c68f7d7-f131-5f86-a1c3-88cf8149b2d7"
	version = "8.4.2"

	[[deps.GPUArraysCore]]
	deps = ["Adapt"]
	git-tree-sha1 = "d88b17a38322e153c519f5a9ed8d91e9baa03d8f"
	uuid = "46192b85-c4d5-4398-a991-12ede77f4527"
	version = "0.1.1"

	[[deps.GPUCompiler]]
	deps = ["ExprTools", "InteractiveUtils", "LLVM", "Libdl", "Logging", "TimerOutputs", "UUIDs"]
	git-tree-sha1 = "122d7bcc92abf94cf1a86281ad7a4d0e838ab9e0"
	uuid = "61eb1bfa-7361-4325-ad38-22787b887f55"
	version = "0.16.3"

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

	[[deps.InverseFunctions]]
	deps = ["Test"]
	git-tree-sha1 = "b3364212fb5d870f724876ffcd34dd8ec6d98918"
	uuid = "3587e190-3f89-42d0-90ee-14403ec27112"
	version = "0.1.7"

	[[deps.IrrationalConstants]]
	git-tree-sha1 = "7fd44fd4ff43fc60815f8e764c0f352b83c49151"
	uuid = "92d709cd-6900-40b7-9082-c6be49f344b6"
	version = "0.1.1"

	[[deps.JLLWrappers]]
	deps = ["Preferences"]
	git-tree-sha1 = "abc9885a7ca2052a736a600f7fa66209f96506e1"
	uuid = "692b3bcd-3c85-4b1f-b108-f13ce0eb3210"
	version = "1.4.1"

	[[deps.KernelAbstractions]]
	deps = ["Adapt", "Atomix", "InteractiveUtils", "LinearAlgebra", "MacroTools", "SparseArrays", "StaticArrays", "UUIDs", "UnsafeAtomics", "UnsafeAtomicsLLVM"]
	git-tree-sha1 = "02838ecfc5f925ac408ffe6b359ac59ef8865272"
	uuid = "63c18a36-062a-441e-b654-da1e3ab1ce7c"
	version = "0.8.3"

	[[deps.KernelGradients]]
	deps = ["Enzyme", "KernelAbstractions"]
	git-tree-sha1 = "6dbcc9f869625fa50e1c7483f1c4200c65f17f9c"
	uuid = "e5faadeb-7f6c-408e-9747-a7a26e81c66a"
	version = "0.1.2"

	[[deps.LLVM]]
	deps = ["CEnum", "LLVMExtra_jll", "Libdl", "Printf", "Unicode"]
	git-tree-sha1 = "e7e9184b0bf0158ac4e4aa9daf00041b5909bf1a"
	uuid = "929cbde3-209d-540e-8aea-75f648917ca0"
	version = "4.14.0"

	[[deps.LLVMExtra_jll]]
	deps = ["Artifacts", "JLLWrappers", "LazyArtifacts", "Libdl", "Pkg", "TOML"]
	git-tree-sha1 = "771bfe376249626d3ca12bcd58ba243d3f961576"
	uuid = "dad2f222-ce93-54a1-a47d-0025e8a3acab"
	version = "0.0.16+0"

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

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

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

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

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

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

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

	[[deps.LogExpFunctions]]
	deps = ["ChainRulesCore", "ChangesOfVariables", "DocStringExtensions", "InverseFunctions", "IrrationalConstants", "LinearAlgebra"]
	git-tree-sha1 = "361c2b088575b07946508f135ac556751240091c"
	uuid = "2ab3a3ac-af41-5b50-aa03-7779005ae688"
	version = "0.3.17"

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

	[[deps.MacroTools]]
	deps = ["Markdown", "Random"]
	git-tree-sha1 = "3d3e902b31198a27340d0bf00d6ac452866021cf"
	uuid = "1914dd2f-81c6-5fcd-8719-6d5c9610ff09"
	version = "0.5.9"

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

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

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

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

	[[deps.ObjectFile]]
	deps = ["Reexport", "StructIO"]
	git-tree-sha1 = "55ce61d43409b1fb0279d1781bf3b0f22c83ab3b"
	uuid = "d8793406-e978-5875-9003-1fc021f44a92"
	version = "0.3.7"

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

	[[deps.OpenLibm_jll]]
	deps = ["Artifacts", "Libdl"]
	uuid = "05823500-19ac-5b8b-9628-191a04bc5112"

	[[deps.OpenSpecFun_jll]]
	deps = ["Artifacts", "CompilerSupportLibraries_jll", "JLLWrappers", "Libdl", "Pkg"]
	git-tree-sha1 = "13652491f6856acfd2db29360e1bbcd4565d04f1"
	uuid = "efe28fd5-8261-553b-a9e1-b2916fc3738e"
	version = "0.5.5+0"

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

	[[deps.Preferences]]
	deps = ["TOML"]
	git-tree-sha1 = "47e5f437cc0e7ef2ce8406ce1e7e24d44915f88d"
	uuid = "21216c6a-2e73-6563-6e65-726566657250"
	version = "1.3.0"

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

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

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

	[[deps.Random123]]
	deps = ["Random", "RandomNumbers"]
	git-tree-sha1 = "7a1a306b72cfa60634f03a911405f4e64d1b718b"
	uuid = "74087812-796a-5b5d-8853-05524746bad3"
	version = "1.6.0"

	[[deps.RandomNumbers]]
	deps = ["Random", "Requires"]
	git-tree-sha1 = "043da614cc7e95c703498a491e2c21f58a2b8111"
	uuid = "e6cf234a-135c-5ec9-84dd-332b85af5143"
	version = "1.5.3"

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

	[[deps.Requires]]
	deps = ["UUIDs"]
	git-tree-sha1 = "838a3a4188e2ded87a4f9f184b4b0d78a1e91cb7"
	uuid = "ae029012-a4dd-5104-9daa-d747884805df"
	version = "1.3.0"

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

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

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

	[[deps.SparseArrays]]
	deps = ["LinearAlgebra", "Random"]
	uuid = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"

	[[deps.SpecialFunctions]]
	deps = ["ChainRulesCore", "IrrationalConstants", "LogExpFunctions", "OpenLibm_jll", "OpenSpecFun_jll"]
	git-tree-sha1 = "d75bda01f8c31ebb72df80a46c88b25d1c79c56d"
	uuid = "276daf66-3868-5448-9aa4-cd146d93841b"
	version = "2.1.7"

	[[deps.StaticArrays]]
	deps = ["LinearAlgebra", "Random", "StaticArraysCore", "Statistics"]
	git-tree-sha1 = "23368a3313d12a2326ad0035f0db0c0966f438ef"
	uuid = "90137ffa-7385-5640-81b9-e52037218182"
	version = "1.5.2"

	[[deps.StaticArraysCore]]
	git-tree-sha1 = "66fe9eb253f910fe8cf161953880cfdaef01cdf0"
	uuid = "1e83bf80-4336-4d27-bf5d-d5a4f845583c"
	version = "1.0.1"

	[[deps.Statistics]]
	deps = ["LinearAlgebra", "SparseArrays"]
	uuid = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"

	[[deps.StructIO]]
	deps = ["Test"]
	git-tree-sha1 = "010dc73c7146869c042b49adcdb6bf528c12e859"
	uuid = "53d494c1-5632-5724-8f4c-31dff12d585f"
	version = "0.3.0"

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

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

	[[deps.Test]]
	deps = ["InteractiveUtils", "Logging", "Random", "Serialization"]
	uuid = "8dfed614-e22c-5e08-85e1-65c5234f0b40"

	[[deps.TimerOutputs]]
	deps = ["ExprTools", "Printf"]
	git-tree-sha1 = "464d64b2510a25e6efe410e7edab14fffdc333df"
	uuid = "a759f4b9-e2f1-59dc-863e-4aeb61b1ea8f"
	version = "0.5.20"

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

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

	[[deps.UnsafeAtomics]]
	git-tree-sha1 = "6331ac3440856ea1988316b46045303bef658278"
	uuid = "013be700-e6cd-48c3-b4a1-df204f14c38f"
	version = "0.2.1"

	[[deps.UnsafeAtomicsLLVM]]
	deps = ["LLVM", "UnsafeAtomics"]
	git-tree-sha1 = "33af9d2031d0dc09e2be9a0d4beefec4466def8e"
	uuid = "d80eeb9a-aca5-4d75-85e5-170c8b632249"
	version = "0.1.0"

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

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

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

	[[deps.p7zip_jll]]
	deps = ["Artifacts", "Libdl"]
	uuid = "3f19e933-33d8-53b3-aaab-bd5110c3b7a0"
	[deps]
	CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
	CUDAKernels = "72cfdca4-0801-4ab0-bf6a-d52aa10adc57"
	Enzyme = "7da242da-08ed-463a-9acd-ee780be4f1d9"
	KernelAbstractions = "63c18a36-062a-441e-b654-da1e3ab1ce7c"
	KernelGradients = "e5faadeb-7f6c-408e-9747-a7a26e81c66a"
	Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
	using Enzyme
	using CUDA
	using CUDAKernels
	using KernelAbstractions
	using KernelGradients
	using Test

	CUDA.allowscalar(false)

	device = CUDA.device()
	@show device

	function kconfig(a::Array)
	return (CPU(), 4)
	end

	function kconfig(a::CuArray)
	return (CUDADevice(), 256)
	end

	function same_device(xs...)
	device = KernelAbstractions.get_device(xs[1])
	for x in xs
	if KernelAbstractions.get_device(x) != device
	return false
	end
	end
	return true
	end

	@kernel function dist_kernel!(@Const(x), @Const(y), @Const(w), result)
	q = 2
	i, j = @index(Global, NTuple)
	result[i, j] = zero(eltype(result))
	for k = 1:size(x, 1)
	result[i, j] += (abs(x[k, i] - y[k, j]) * w[k, j]) ^ q
	end
	result[i, j] = result[i, j] ^ (1 / q)
	nothing
	end

	function dist!(x, y, w, result)
	@assert size(x, 1) == size(y, 1)
	@assert size(x, 2) == size(result, 1)
	@assert size(y, 2) == size(result, 2)
	@assert same_device(x, y, result)
	kernel! = dist_kernel!(kconfig(x)...)
	ev = kernel!(x, y, w, result; ndrange=size(result))
	wait(ev)
	end

	function Δdist!(x, y, w, result, ∂x, ∂y, ∂w, ∂result)
	@assert same_device(x, y, w, result, ∂x, ∂y, ∂w, ∂result)
	@assert size(x) == size(∂x)
	@assert size(y) == size(∂y)
	@assert size(w) == size(∂w)
	@assert size(result) == size(∂result)
	deriv = Enzyme.autodiff(dist_kernel!(kconfig(x)...))
	ev = deriv(Duplicated(x, ∂x), Duplicated(y, ∂y), Duplicated(w, ∂w), Duplicated(result, ∂result); ndrange=size(result))
	wait(ev)
	end

	d = 100
	n = 2000
	m = 2500

	a, b, w, result = rand(Float32, d, n), rand(Float32, d, m), rand(Float32, d, m), zeros(Float32, n, m)
	∂a, ∂b, ∂w, ∂result = zeros(Float32, d, n), zeros(Float32, d, m), zeros(Float32, d, m), rand(Float32, n, m)

	ca, cb, cw, cresult = CuArray(a), CuArray(b), CuArray(w), CuArray(result)
	c∂a, c∂b, c∂w, c∂result = CuArray(∂a), CuArray(∂b), CuArray(∂w), CuArray(∂result)

	println("=== cpu")

	@show size(a), size(b), size(w), size(result)

	@time dist!(a, b, w, result)
	@time dist!(a, b, w, result)

	println("=== cpu deriv")

	@time Δdist!(a, b, w, result, ∂a, ∂b, ∂w, ∂result)
	@time Δdist!(a, b, w, result, ∂a, ∂b, ∂w, ∂result)

	println("=== gpu")

	@show size(ca), size(cb), size(cw), size(cresult)

	@time dist!(ca, cb, cw, cresult)
	@time dist!(ca, cb, cw, cresult)

	println("=== gpu deriv")

	@time Δdist!(ca, cb, cw, cresult, c∂a, c∂b, c∂w, c∂result)
	@time Δdist!(ca, cb, cw, cresult, c∂a, c∂b, c∂w, c∂result)