From 2950adafbaea5ec863d6a55e46d71193613507ed Mon Sep 17 00:00:00 2001 From: "ali.hh.ramadhan@gmail.com" Date: Tue, 20 Apr 2021 18:33:23 -0400 Subject: [PATCH 1/3] Simple exponential growth ODE example --- Manifest.toml | 312 +++++++++++++++++++++++++++++++++++++++++ Project.toml | 8 ++ examples/simple_ode.jl | 46 ++++++ src/EnzymaticOcean.jl | 5 + 4 files changed, 371 insertions(+) create mode 100644 Manifest.toml create mode 100644 Project.toml create mode 100644 examples/simple_ode.jl create mode 100644 src/EnzymaticOcean.jl diff --git a/Manifest.toml b/Manifest.toml new file mode 100644 index 0000000..18858f3 --- /dev/null +++ b/Manifest.toml @@ -0,0 +1,312 @@ +# This file is machine-generated - editing it directly is not advised + +[[AbstractFFTs]] +deps = ["LinearAlgebra"] +git-tree-sha1 = "485ee0867925449198280d4af84bdb46a2a404d0" +uuid = "621f4979-c628-5d54-868e-fcf4e3e8185c" +version = "1.0.1" + +[[Adapt]] +deps = ["LinearAlgebra"] +git-tree-sha1 = "f1b523983a58802c4695851926203b36e28f09db" +uuid = "79e6a3ab-5dfb-504d-930d-738a2a938a0e" +version = "3.3.0" + +[[ArgTools]] +uuid = "0dad84c5-d112-42e6-8d28-ef12dabb789f" + +[[Artifacts]] +uuid = "56f22d72-fd6d-98f1-02f0-08ddc0907c33" + +[[BFloat16s]] +deps = ["LinearAlgebra", "Test"] +git-tree-sha1 = "4af69e205efc343068dc8722b8dfec1ade89254a" +uuid = "ab4f0b2a-ad5b-11e8-123f-65d77653426b" +version = "0.1.0" + +[[Base64]] +uuid = "2a0f44e3-6c83-55bd-87e4-b1978d98bd5f" + +[[CEnum]] +git-tree-sha1 = "215a9aa4a1f23fbd05b92769fdd62559488d70e9" +uuid = "fa961155-64e5-5f13-b03f-caf6b980ea82" +version = "0.4.1" + +[[CUDA]] +deps = ["AbstractFFTs", "Adapt", "BFloat16s", "CEnum", "CompilerSupportLibraries_jll", "DataStructures", "ExprTools", "GPUArrays", "GPUCompiler", "LLVM", "LazyArtifacts", "Libdl", "LinearAlgebra", "Logging", "MacroTools", "Memoize", "NNlib", "Printf", "Random", "Reexport", "Requires", "SparseArrays", "Statistics", "TimerOutputs"] +git-tree-sha1 = "6893a46f357eabd44ce0fc1f9a264120a1a3a732" +uuid = "052768ef-5323-5732-b1bb-66c8b64840ba" +version = "2.6.3" + +[[CUDAKernels]] +deps = ["Adapt", "CUDA", "Cassette", "KernelAbstractions", "SpecialFunctions", "StaticArrays"] +git-tree-sha1 = "0daaee29c30f1ea9e1a8f7c9d92b00d07aba0fa0" +uuid = "72cfdca4-0801-4ab0-bf6a-d52aa10adc57" +version = "0.1.0" + +[[Cassette]] +git-tree-sha1 = "742fbff99a2798f02bd37d25087efb5615b5a207" +uuid = "7057c7e9-c182-5462-911a-8362d720325c" +version = "0.3.5" + +[[ChainRulesCore]] +deps = ["Compat", "LinearAlgebra", "SparseArrays"] +git-tree-sha1 = "42e3c181483fbd2c416087a0a93838803e358358" +uuid = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4" +version = "0.9.38" + +[[Compat]] +deps = ["Base64", "Dates", "DelimitedFiles", "Distributed", "InteractiveUtils", "LibGit2", "Libdl", "LinearAlgebra", "Markdown", "Mmap", "Pkg", "Printf", "REPL", "Random", "SHA", "Serialization", "SharedArrays", "Sockets", "SparseArrays", "Statistics", "Test", "UUIDs", "Unicode"] +git-tree-sha1 = "ac4132ad78082518ec2037ae5770b6e796f7f956" +uuid = "34da2185-b29b-5c13-b0c7-acf172513d20" +version = "3.27.0" + +[[CompilerSupportLibraries_jll]] +deps = ["Artifacts", "Libdl"] +uuid = "e66e0078-7015-5450-92f7-15fbd957f2ae" + +[[DataStructures]] +deps = ["Compat", "InteractiveUtils", "OrderedCollections"] +git-tree-sha1 = "4437b64df1e0adccc3e5d1adbc3ac741095e4677" +uuid = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8" +version = "0.18.9" + +[[Dates]] +deps = ["Printf"] +uuid = "ade2ca70-3891-5945-98fb-dc099432e06a" + +[[DelimitedFiles]] +deps = ["Mmap"] +uuid = "8bb1440f-4735-579b-a4ab-409b98df4dab" + +[[Distributed]] +deps = ["Random", "Serialization", "Sockets"] +uuid = "8ba89e20-285c-5b6f-9357-94700520ee1b" + +[[Downloads]] +deps = ["ArgTools", "LibCURL", "NetworkOptions"] +uuid = "f43a241f-c20a-4ad4-852c-f6b1247861c6" + +[[ExprTools]] +git-tree-sha1 = "10407a39b87f29d47ebaca8edbc75d7c302ff93e" +uuid = "e2ba6199-217a-4e67-a87a-7c52f15ade04" +version = "0.1.3" + +[[GPUArrays]] +deps = ["AbstractFFTs", "Adapt", "LinearAlgebra", "Printf", "Random", "Serialization"] +git-tree-sha1 = "9c95b2fd5c16bc7f97371e9f92f0fef77e0f5957" +uuid = "0c68f7d7-f131-5f86-a1c3-88cf8149b2d7" +version = "6.2.2" + +[[GPUCompiler]] +deps = ["DataStructures", "ExprTools", "InteractiveUtils", "LLVM", "Libdl", "Logging", "Scratch", "Serialization", "TimerOutputs", "UUIDs"] +git-tree-sha1 = "ef2839b063e158672583b9c09d2cf4876a8d3d55" +uuid = "61eb1bfa-7361-4325-ad38-22787b887f55" +version = "0.10.0" + +[[InteractiveUtils]] +deps = ["Markdown"] +uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240" + +[[JLLWrappers]] +deps = ["Preferences"] +git-tree-sha1 = "642a199af8b68253517b80bd3bfd17eb4e84df6e" +uuid = "692b3bcd-3c85-4b1f-b108-f13ce0eb3210" +version = "1.3.0" + +[[KernelAbstractions]] +deps = ["Adapt", "Cassette", "InteractiveUtils", "MacroTools", "SpecialFunctions", "StaticArrays", "UUIDs"] +git-tree-sha1 = "0158a3efe86a7c0a3162ded188172a0ad302353b" +uuid = "63c18a36-062a-441e-b654-da1e3ab1ce7c" +version = "0.6.0" + +[[LLVM]] +deps = ["CEnum", "Libdl", "Printf", "Unicode"] +git-tree-sha1 = "b616937c31337576360cb9fb872ec7633af7b194" +uuid = "929cbde3-209d-540e-8aea-75f648917ca0" +version = "3.6.0" + +[[LazyArtifacts]] +deps = ["Artifacts", "Pkg"] +uuid = "4af54fe1-eca0-43a8-85a7-787d91b784e3" + +[[LibCURL]] +deps = ["LibCURL_jll", "MozillaCACerts_jll"] +uuid = "b27032c2-a3e7-50c8-80cd-2d36dbcbfd21" + +[[LibCURL_jll]] +deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll", "Zlib_jll", "nghttp2_jll"] +uuid = "deac9b47-8bc7-5906-a0fe-35ac56dc84c0" + +[[LibGit2]] +deps = ["Base64", "NetworkOptions", "Printf", "SHA"] +uuid = "76f85450-5226-5b5a-8eaa-529ad045b433" + +[[LibSSH2_jll]] +deps = ["Artifacts", "Libdl", "MbedTLS_jll"] +uuid = "29816b5a-b9ab-546f-933c-edad1886dfa8" + +[[Libdl]] +uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb" + +[[LinearAlgebra]] +deps = ["Libdl"] +uuid = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e" + +[[Logging]] +uuid = "56ddb016-857b-54e1-b83d-db4d58db5568" + +[[MacroTools]] +deps = ["Markdown", "Random"] +git-tree-sha1 = "6a8a2a625ab0dea913aba95c11370589e0239ff0" +uuid = "1914dd2f-81c6-5fcd-8719-6d5c9610ff09" +version = "0.5.6" + +[[Markdown]] +deps = ["Base64"] +uuid = "d6f4376e-aef5-505a-96c1-9c027394607a" + +[[MbedTLS_jll]] +deps = ["Artifacts", "Libdl"] +uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1" + +[[Memoize]] +deps = ["MacroTools"] +git-tree-sha1 = "2b1dfcba103de714d31c033b5dacc2e4a12c7caa" +uuid = "c03570c3-d221-55d1-a50c-7939bbd78826" +version = "0.4.4" + +[[Mmap]] +uuid = "a63ad114-7e13-5084-954f-fe012c677804" + +[[MozillaCACerts_jll]] +uuid = "14a3606d-f60d-562e-9121-12d972cd8159" + +[[NNlib]] +deps = ["Adapt", "ChainRulesCore", "Compat", "LinearAlgebra", "Pkg", "Requires", "Statistics"] +git-tree-sha1 = "723c0d5252bf95808f934b2384519dd325869f40" +uuid = "872c559c-99b0-510c-b3b7-b6c96a88d5cd" +version = "0.7.18" + +[[NetworkOptions]] +uuid = "ca575930-c2e3-43a9-ace4-1e988b2c1908" + +[[OpenSpecFun_jll]] +deps = ["Artifacts", "CompilerSupportLibraries_jll", "JLLWrappers", "Libdl", "Pkg"] +git-tree-sha1 = "9db77584158d0ab52307f8c04f8e7c08ca76b5b3" +uuid = "efe28fd5-8261-553b-a9e1-b2916fc3738e" +version = "0.5.3+4" + +[[OrderedCollections]] +git-tree-sha1 = "4fa2ba51070ec13fcc7517db714445b4ab986bdf" +uuid = "bac558e1-5e72-5ebc-8fee-abe8a469f55d" +version = "1.4.0" + +[[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" + +[[Preferences]] +deps = ["TOML"] +git-tree-sha1 = "ea79e4c9077208cd3bc5d29631a26bc0cff78902" +uuid = "21216c6a-2e73-6563-6e65-726566657250" +version = "1.2.1" + +[[Printf]] +deps = ["Unicode"] +uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7" + +[[REPL]] +deps = ["InteractiveUtils", "Markdown", "Sockets", "Unicode"] +uuid = "3fa0cd96-eef1-5676-8a61-b3b8758bbffb" + +[[Random]] +deps = ["Serialization"] +uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c" + +[[Reexport]] +git-tree-sha1 = "57d8440b0c7d98fc4f889e478e80f268d534c9d5" +uuid = "189a3867-3050-52da-a836-e630ba90ab69" +version = "1.0.0" + +[[Requires]] +deps = ["UUIDs"] +git-tree-sha1 = "4036a3bd08ac7e968e27c203d45f5fff15020621" +uuid = "ae029012-a4dd-5104-9daa-d747884805df" +version = "1.1.3" + +[[SHA]] +uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce" + +[[Scratch]] +deps = ["Dates"] +git-tree-sha1 = "ad4b278adb62d185bbcb6864dc24959ab0627bf6" +uuid = "6c6a2e73-6563-6170-7368-637461726353" +version = "1.0.3" + +[[Serialization]] +uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b" + +[[SharedArrays]] +deps = ["Distributed", "Mmap", "Random", "Serialization"] +uuid = "1a1011a3-84de-559e-8e89-a11a2f7dc383" + +[[Sockets]] +uuid = "6462fe0b-24de-5631-8697-dd941f90decc" + +[[SparseArrays]] +deps = ["LinearAlgebra", "Random"] +uuid = "2f01184e-e22b-5df5-ae63-d93ebab69eaf" + +[[SpecialFunctions]] +deps = ["ChainRulesCore", "OpenSpecFun_jll"] +git-tree-sha1 = "5919936c0e92cff40e57d0ddf0ceb667d42e5902" +uuid = "276daf66-3868-5448-9aa4-cd146d93841b" +version = "1.3.0" + +[[StaticArrays]] +deps = ["LinearAlgebra", "Random", "Statistics"] +git-tree-sha1 = "e8cd1b100d37f5b4cfd2c83f45becf61c762eaf7" +uuid = "90137ffa-7385-5640-81b9-e52037218182" +version = "1.1.1" + +[[Statistics]] +deps = ["LinearAlgebra", "SparseArrays"] +uuid = "10745b16-79ce-11e8-11f9-7d13ad32a3b2" + +[[TOML]] +deps = ["Dates"] +uuid = "fa267f1f-6049-4f14-aa54-33bafae1ed76" + +[[Tar]] +deps = ["ArgTools", "SHA"] +uuid = "a4e569a6-e804-4fa4-b0f3-eef7a1d5b13e" + +[[Test]] +deps = ["InteractiveUtils", "Logging", "Random", "Serialization"] +uuid = "8dfed614-e22c-5e08-85e1-65c5234f0b40" + +[[TimerOutputs]] +deps = ["Printf"] +git-tree-sha1 = "32cdbe6cd2d214c25a0b88f985c9e0092877c236" +uuid = "a759f4b9-e2f1-59dc-863e-4aeb61b1ea8f" +version = "0.5.8" + +[[UUIDs]] +deps = ["Random", "SHA"] +uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4" + +[[Unicode]] +uuid = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5" + +[[Zlib_jll]] +deps = ["Libdl"] +uuid = "83775a58-1f1d-513f-b197-d71354ab007a" + +[[nghttp2_jll]] +deps = ["Artifacts", "Libdl"] +uuid = "8e850ede-7688-5339-a07c-302acd2aaf8d" + +[[p7zip_jll]] +deps = ["Artifacts", "Libdl"] +uuid = "3f19e933-33d8-53b3-aaab-bd5110c3b7a0" diff --git a/Project.toml b/Project.toml new file mode 100644 index 0000000..d9e3886 --- /dev/null +++ b/Project.toml @@ -0,0 +1,8 @@ +name = "EnzymaticOcean" +uuid = "1e308aaf-769c-447f-af17-2df7aeedce0a" +version = "0.1.0" + +[deps] +CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba" +CUDAKernels = "72cfdca4-0801-4ab0-bf6a-d52aa10adc57" +KernelAbstractions = "63c18a36-062a-441e-b654-da1e3ab1ce7c" diff --git a/examples/simple_ode.jl b/examples/simple_ode.jl new file mode 100644 index 0000000..f29402d --- /dev/null +++ b/examples/simple_ode.jl @@ -0,0 +1,46 @@ +using KernelAbstractions +using CUDAKernels +using CUDA + +@kernel function time_step!(x, k, Δt) + I = @index(Global) + @inbounds x[I] = x[I] + Δt * k * x[I] +end + +""" + simulate_exponential_growth(; x₀, k, Δt, N, device) + +Simulates exponential growth according to the ODE + + dx/dt = k * x, x(t = 0) = x₀ + +using forward Euler time stepping with time step `Δt` for `N` iterations. +""" +function simulate_exponential_growth(; x₀, k, Δt, N, device) + + if device isa CPU + x = [x₀] + elseif device isa CUDADevice + x = CuArray([x₀]) + end + + time_step_kernel! = time_step!(device, 1) + + for _ in 1:N + event = time_step_kernel!(x, k, Δt, ndrange=1) + wait(event) + end + + return x[1] +end + +# 1 CPU kernel launch +@show simulate_exponential_growth(x₀=1.0, k=2.5, Δt=0.01, N=1, device=CPU()) +# @show simulate_exponential_growth(x₀=1, k=2.5, Δt=0.01, N=1, device=CUDADevice()) + +# iterative kernel launches +@show simulate_exponential_growth(x₀=1.0, k=2.5, Δt=0.01, N=100, device=CPU()) +# @show simulate_exponential_growth(x₀=1.0, k=2.5, Δt=0.01, N=100, device=CUDADevice()) + +# Optimization problem: +# If x₀=1, Δt = 0.01, N = 100, and x(t = 1) = π then what is k? diff --git a/src/EnzymaticOcean.jl b/src/EnzymaticOcean.jl new file mode 100644 index 0000000..5aba2b3 --- /dev/null +++ b/src/EnzymaticOcean.jl @@ -0,0 +1,5 @@ +module EnzymaticOcean + +greet() = print("Hello World!") + +end # module From 5b30bf0d2dfd59c796753345c5ab7ffd128e20b0 Mon Sep 17 00:00:00 2001 From: "ali.hh.ramadhan@gmail.com" Date: Tue, 20 Apr 2021 18:42:32 -0400 Subject: [PATCH 2/3] Fix GPU case --- examples/simple_ode.jl | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/examples/simple_ode.jl b/examples/simple_ode.jl index f29402d..6848c4b 100644 --- a/examples/simple_ode.jl +++ b/examples/simple_ode.jl @@ -31,16 +31,16 @@ function simulate_exponential_growth(; x₀, k, Δt, N, device) wait(event) end - return x[1] + return CUDA.@allowscalar x[1] end # 1 CPU kernel launch @show simulate_exponential_growth(x₀=1.0, k=2.5, Δt=0.01, N=1, device=CPU()) -# @show simulate_exponential_growth(x₀=1, k=2.5, Δt=0.01, N=1, device=CUDADevice()) +@show simulate_exponential_growth(x₀=1.0, k=2.5, Δt=0.01, N=1, device=CUDADevice()) # iterative kernel launches @show simulate_exponential_growth(x₀=1.0, k=2.5, Δt=0.01, N=100, device=CPU()) -# @show simulate_exponential_growth(x₀=1.0, k=2.5, Δt=0.01, N=100, device=CUDADevice()) +@show simulate_exponential_growth(x₀=1.0, k=2.5, Δt=0.01, N=100, device=CUDADevice()) # Optimization problem: # If x₀=1, Δt = 0.01, N = 100, and x(t = 1) = π then what is k? From 1740f862d0e9a68f5627932fa5c85696ad2d8bcf Mon Sep 17 00:00:00 2001 From: "ali.hh.ramadhan@gmail.com" Date: Tue, 20 Apr 2021 19:57:57 -0400 Subject: [PATCH 3/3] Move iteration loop inside kernel --- examples/simple_ode.jl | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/examples/simple_ode.jl b/examples/simple_ode.jl index 6848c4b..f1f2a5e 100644 --- a/examples/simple_ode.jl +++ b/examples/simple_ode.jl @@ -2,9 +2,11 @@ using KernelAbstractions using CUDAKernels using CUDA -@kernel function time_step!(x, k, Δt) +@kernel function time_step!(x, k, Δt, N) I = @index(Global) - @inbounds x[I] = x[I] + Δt * k * x[I] + for _ in 1:N + @inbounds x[I] = x[I] + Δt * k * x[I] + end end """ @@ -25,16 +27,13 @@ function simulate_exponential_growth(; x₀, k, Δt, N, device) end time_step_kernel! = time_step!(device, 1) - - for _ in 1:N - event = time_step_kernel!(x, k, Δt, ndrange=1) - wait(event) - end + event = time_step_kernel!(x, k, Δt, N, ndrange=1) + wait(event) return CUDA.@allowscalar x[1] end -# 1 CPU kernel launch +# 1 kernel launch @show simulate_exponential_growth(x₀=1.0, k=2.5, Δt=0.01, N=1, device=CPU()) @show simulate_exponential_growth(x₀=1.0, k=2.5, Δt=0.01, N=1, device=CUDADevice())