Update config and deps of examples

Author: Dvegrod

examples/example-paper-implicitglobalgrid/EXP_test_halo_thr_GPU.jl

@@ -207,39 +207,43 @@ dz = 1.0
                     P  = GPUArray(P);
                     halowidths = (1,1,1)
                     if array_type == "CUDA"
-                        # (dim=3)
-                        dim = 3
-                        P2 = gpuzeros(eltype(P), size(P))
-                        buf = zeros(size(P, 1), size(P, 2), halowidths[dim])
-                        buf .= 0.0
-                        P2 .= 0.0
-                        ranges = [1:size(P, 1), 1:size(P, 2), 1:1]
-                        nthreads = (1, 1, 1)
-                        halosize = [(r[end] - r[1]) + 1 for r = ranges]
-                        nblocks = Tuple(ceil.(Int, halosize ./ nthreads))
-                        custream = stream();
-            	        @define_eff_memory_throughput custom_benchmark=GPUBandwidthCUDA begin
-                	        (nx * ny * 8) * MPI.Comm_size(MPI.COMM_WORLD) / :median_time
-            	        end	
-                        @perftest begin
-                            CUDA.@sync GG.read_h2d_async!(buf, P2, ranges, custream)
+                        @testset "CUDA" begin
+                            # (dim=3)
+                            dim = 3
+                            P2 = gpuzeros(eltype(P), size(P))
+                            buf = zeros(size(P, 1), size(P, 2), halowidths[dim])
+                            buf .= 0.0
+                            P2 .= 0.0
+                            ranges = [1:size(P, 1), 1:size(P, 2), 1:1]
+                            nthreads = (1, 1, 1)
+                            halosize = [(r[end] - r[1]) + 1 for r = ranges]
+                            nblocks = Tuple(ceil.(Int, halosize ./ nthreads))
+                            custream = stream();
+                            @define_eff_memory_throughput custom_benchmark=GPUBandwidthCUDA begin
+                                (nx * ny * 8) * MPI.Comm_size(MPI.COMM_WORLD) / :median_time
+                            end	
+                            @perftest begin
+                                CUDA.@sync GG.read_h2d_async!(buf, P2, ranges, custream)
+                            end
                         end
                     elseif array_type == "AMDGPU"
-                        # (dim=3)
-                        dim = 3
-                        P2 = gpuzeros(eltype(P), size(P))
-                        buf = zeros(size(P, 1), size(P, 2), halowidths[dim])
-                        ranges = [1:size(P, 1), 1:size(P, 2), 1:1]
-                        nthreads = (1, 1, 1)
-                        halosize = [(r[end] - r[1]) + 1 for r = ranges]
-                        nblocks = Tuple(ceil.(Int, halosize ./ nthreads))
-                        rocstream = AMDGPU.HIPStream()
-            	        @define_eff_memory_throughput custom_benchmark=GPUBandwidthROC begin
-                	        (nx * ny * 8) * MPI.Comm_size(MPI.COMM_WORLD) / :median_time
-            	        end	
-                        @perftest begin
-                            GG.read_h2d_async!(buf, P2, ranges, rocstream)
-                            AMDGPU.synchronize()
+                        @testset "AMD" begin
+                            # (dim=3)
+                            dim = 3
+                            P2 = gpuzeros(eltype(P), size(P))
+                            buf = zeros(size(P, 1), size(P, 2), halowidths[dim])
+                            ranges = [1:size(P, 1), 1:size(P, 2), 1:1]
+                            nthreads = (1, 1, 1)
+                            halosize = [(r[end] - r[1]) + 1 for r = ranges]
+                            nblocks = Tuple(ceil.(Int, halosize ./ nthreads))
+                            rocstream = AMDGPU.HIPStream()
+                            @define_eff_memory_throughput custom_benchmark=GPUBandwidthROC begin
+                                (nx * ny * 8) * MPI.Comm_size(MPI.COMM_WORLD) / :median_time
+                            end	
+                            @perftest begin
+                                GG.read_h2d_async!(buf, P2, ranges, rocstream)
+                                AMDGPU.synchronize()
+                            end
                         end
                     end
                     finalize_global_grid(finalize_MPI=false);

examples/example-paper-implicitglobalgrid/Manifest.toml

@@ -188,6 +188,11 @@ git-tree-sha1 = "7fecfb1123b8d0232218e2da0c213004ff15358d"
 uuid = "6e4b80f9-dd63-53aa-95a3-0cdb28fa8baf"
 version = "1.6.3"
 
+[[deps.BitFlags]]
+git-tree-sha1 = "0691e34b3bb8be9307330f88d1a3c3f25466c24d"
+uuid = "d1d4a3ce-64b1-5f1a-9ba4-7e7e69966f35"
+version = "0.1.9"
+
 [[deps.BitTwiddlingConvenienceFunctions]]
 deps = ["Static"]
 git-tree-sha1 = "f21cfd4950cb9f0587d5067e69405ad2acd27b87"
@@ -297,6 +302,12 @@ git-tree-sha1 = "b7231a755812695b8046e8471ddc34c8268cbad5"
 uuid = "da1fd8a2-8d9e-5ec2-8556-3022fb5608a2"
 version = "3.0.0"
 
+[[deps.CodecZlib]]
+deps = ["TranscodingStreams", "Zlib_jll"]
+git-tree-sha1 = "962834c22b66e32aa10f7611c08c8ca4e20749a9"
+uuid = "944b1d66-785c-5afd-91f1-9de20f533193"
+version = "0.7.8"
+
 [[deps.ColorSchemes]]
 deps = ["ColorTypes", "ColorVectorSpace", "Colors", "FixedPointNumbers", "PrecompileTools", "Random"]
 git-tree-sha1 = "b0fd3f56fa442f81e0a47815c92245acfaaa4e34"
@@ -365,6 +376,12 @@ weakdeps = ["InverseFunctions"]
     [deps.CompositionsBase.extensions]
     CompositionsBaseInverseFunctionsExt = "InverseFunctions"
 
+[[deps.ConcurrentUtilities]]
+deps = ["Serialization", "Sockets"]
+git-tree-sha1 = "d9d26935a0bcffc87d2613ce14c527c99fc543fd"
+uuid = "f0e56b4a-5159-44fe-b623-3e5288b988bb"
+version = "2.5.0"
+
 [[deps.Configurations]]
 deps = ["ExproniconLite", "OrderedCollections", "TOML"]
 git-tree-sha1 = "4358750bb58a3caefd5f37a4a0c5bfdbbf075252"
@@ -454,6 +471,12 @@ deps = ["ArgTools", "FileWatching", "LibCURL", "NetworkOptions"]
 uuid = "f43a241f-c20a-4ad4-852c-f6b1247861c6"
 version = "1.6.0"
 
+[[deps.ExceptionUnwrapping]]
+deps = ["Test"]
+git-tree-sha1 = "d36f682e590a83d63d1c7dbd287573764682d12a"
+uuid = "460bff9d-24e4-43bc-9d9f-a8973cb893f4"
+version = "0.1.11"
+
 [[deps.ExprTools]]
 git-tree-sha1 = "27415f162e6028e81c72b82ef756bf321213b6ec"
 uuid = "e2ba6199-217a-4e67-a87a-7c52f15ade04"
@@ -469,13 +492,11 @@ deps = ["Pkg", "Requires", "UUIDs"]
 git-tree-sha1 = "d60eb76f37d7e5a40cc2e7c36974d864b82dc802"
 uuid = "5789e2e9-d7fb-5bc7-8068-2c6fae9b9549"
 version = "1.17.1"
+weakdeps = ["HTTP"]
 
     [deps.FileIO.extensions]
     HTTPExt = "HTTP"
 
-    [deps.FileIO.weakdeps]
-    HTTP = "cd3eb016-35fb-5094-929b-558a96fad6f3"
-
 [[deps.FileWatching]]
 uuid = "7b1f6079-737a-58dc-b8bc-7a2ca5c1b5ee"
 
@@ -517,6 +538,12 @@ git-tree-sha1 = "5bfe837129bf49e2e049b4f1517546055cc16a93"
 uuid = "096a3bc2-3ced-46d0-87f4-dd12716f4bfc"
 version = "0.3.0"
 
+[[deps.HTTP]]
+deps = ["Base64", "CodecZlib", "ConcurrentUtilities", "Dates", "ExceptionUnwrapping", "Logging", "LoggingExtras", "MbedTLS", "NetworkOptions", "OpenSSL", "PrecompileTools", "Random", "SimpleBufferStream", "Sockets", "URIs", "UUIDs"]
+git-tree-sha1 = "5e6fe50ae7f23d171f44e311c2960294aaa0beb5"
+uuid = "cd3eb016-35fb-5094-929b-558a96fad6f3"
+version = "1.10.19"
+
 [[deps.HashArrayMappedTries]]
 git-tree-sha1 = "2eaa69a7cab70a52b9687c8bf950a5a93ec895ae"
 uuid = "076d061b-32b6-4027-95e0-9a2c6f6d7e74"
@@ -775,6 +802,12 @@ version = "0.3.29"
 [[deps.Logging]]
 uuid = "56ddb016-857b-54e1-b83d-db4d58db5568"
 
+[[deps.LoggingExtras]]
+deps = ["Dates", "Logging"]
+git-tree-sha1 = "f00544d95982ea270145636c181ceda21c4e2575"
+uuid = "e6f89c97-d47a-5376-807f-9c37f3926c36"
+version = "1.2.0"
+
 [[deps.LoopVectorization]]
 deps = ["ArrayInterface", "CPUSummary", "CloseOpenIntervals", "DocStringExtensions", "HostCPUFeatures", "IfElse", "LayoutPointers", "LinearAlgebra", "OffsetArrays", "PolyesterWeave", "PrecompileTools", "SIMDTypes", "SLEEFPirates", "Static", "StaticArrayInterface", "ThreadingUtilities", "UnPack", "VectorizationBase"]
 git-tree-sha1 = "a9fc7883eb9b5f04f46efb9a540833d1fad974b3"
@@ -852,6 +885,12 @@ version = "0.1.11"
 deps = ["Base64"]
 uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
 
+[[deps.MbedTLS]]
+deps = ["Dates", "MbedTLS_jll", "MozillaCACerts_jll", "NetworkOptions", "Random", "Sockets"]
+git-tree-sha1 = "c067a280ddc25f196b5e7df3877c6b226d390aaf"
+uuid = "739be429-bea8-5141-9913-cc70e7f3736d"
+version = "1.1.9"
+
 [[deps.MbedTLS_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1"
@@ -937,6 +976,18 @@ git-tree-sha1 = "ab6596a9d8236041dcd59b5b69316f28a8753592"
 uuid = "fe0851c0-eecd-5654-98d4-656369965a5c"
 version = "5.0.9+0"
 
+[[deps.OpenSSL]]
+deps = ["BitFlags", "Dates", "MozillaCACerts_jll", "NetworkOptions", "OpenSSL_jll", "Sockets"]
+git-tree-sha1 = "1d1aaa7d449b58415f97d2839c318b70ffb525a0"
+uuid = "4d8831e6-92b7-49fb-bdf8-b643e874388c"
+version = "1.6.1"
+
+[[deps.OpenSSL_jll]]
+deps = ["Artifacts", "JLLWrappers", "Libdl"]
+git-tree-sha1 = "c9cbeda6aceffc52d8a0017e71db27c7a7c0beaf"
+uuid = "458c3c95-2e84-50aa-8efc-19380b2a3a95"
+version = "3.5.5+0"
+
 [[deps.OpenSpecFun_jll]]
 deps = ["Artifacts", "CompilerSupportLibraries_jll", "JLLWrappers", "Libdl"]
 git-tree-sha1 = "1346c9208249809840c91b26703912dff463d335"
@@ -955,12 +1006,10 @@ uuid = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
 version = "2.8.3"
 
 [[deps.PerfTest]]
-deps = ["BenchmarkTools", "Configurations", "CountFlops", "CpuId", "Dates", "JLD2", "JSON", "LinearAlgebra", "MLStyle", "MacroTools", "Pkg", "Printf", "Revise", "STREAMBenchmark", "Suppressor", "TOML", "Test", "UnicodePlots"]
-git-tree-sha1 = "ec6629197969f11c533089ea6b58fa27de24e2f2"
-repo-rev = "master"
-repo-url = "https://github.com/JuliaPerf/PerfTest.jl.git"
+deps = ["BenchmarkTools", "Configurations", "CountFlops", "CpuId", "Dates", "HTTP", "JLD2", "JSON", "LibGit2", "LinearAlgebra", "MLStyle", "MacroTools", "Pkg", "Printf", "Revise", "STREAMBenchmark", "Suppressor", "TOML", "Test", "UnicodePlots"]
+path = "../.."
 uuid = "1dca261b-fc56-4a8c-a7e2-9798d8a75978"
-version = "0.1.0"
+version = "0.1.5"
 weakdeps = ["MPI"]
 
     [deps.PerfTest.extensions]
@@ -1120,6 +1169,11 @@ version = "1.4.9"
 [[deps.Serialization]]
 uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
 
+[[deps.SimpleBufferStream]]
+git-tree-sha1 = "f305871d2f381d21527c770d4788c06c097c9bc1"
+uuid = "777ac1f9-54b0-4bf8-805c-2214025038e7"
+version = "1.2.0"
+
 [[deps.Sockets]]
 uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
 
@@ -1319,6 +1373,16 @@ version = "0.1.6"
     [deps.Tracy.weakdeps]
     TracyProfiler_jll = "0c351ed6-8a68-550e-8b79-de6f926da83c"
 
+[[deps.TranscodingStreams]]
+git-tree-sha1 = "0c45878dcfdcfa8480052b6ab162cdd138781742"
+uuid = "3bb67fe8-82b1-5028-8e26-92a6c54297fa"
+version = "0.11.3"
+
+[[deps.URIs]]
+git-tree-sha1 = "bef26fb046d031353ef97a82e3fdb6afe7f21b1a"
+uuid = "5c2747f8-b7ea-4ff2-ba2e-563bfd36b1d4"
+version = "1.6.1"
+
 [[deps.UUIDs]]
 deps = ["Random", "SHA"]
 uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"

examples/example-paper-implicitglobalgrid/perftest_config.toml

@@ -8,17 +8,17 @@ enabled = false
 [general]
 recursive = true
 save_results = true
-autoflops = true
+autoflops = false
 suppress_output = true
 plotting = true
 save_folder = ".perftests"
 max_saved_results = 20
-verbose = false
+verbose = true
 logs_enabled = true
 safe_formulas = false
 
 [regression]
-enabled = true
+enabled = false
 default_threshold = 0.9
 use_bencher = false
 custom_file = ""

src/transform/configuration.jl

@@ -243,7 +243,7 @@ PRECOMPILATION_CONFIG = Dict(
         "safe_formulas" => false,
     ),
     "regression" => Dict(
-        "enabled" => true,
+        "enabled" => false,
         "custom_file" => "",
         "default_threshold" => 0.9,
         "use_bencher" => false,