Add a native profiler.

Manifest.toml

@@ -78,6 +78,33 @@ version = "4.8.0"
 deps = ["Artifacts", "Libdl"]
 uuid = "e66e0078-7015-5450-92f7-15fbd957f2ae"
 
+[[Crayons]]
+git-tree-sha1 = "249fe38abf76d48563e2f4556bebd215aa317e15"
+uuid = "a8cc5b0e-0ffa-5ad4-8c14-923d3ee1735f"
+version = "4.1.1"
+
+[[DataAPI]]
+git-tree-sha1 = "8da84edb865b0b5b0100c0666a9bc9a0b71c553c"
+uuid = "9a962f9c-6df0-11e9-0e5d-c546b8b5ee8a"
+version = "1.15.0"
+
+[[DataFrames]]
+deps = ["Compat", "DataAPI", "DataStructures", "Future", "InlineStrings", "InvertedIndices", "IteratorInterfaceExtensions", "LinearAlgebra", "Markdown", "Missings", "PooledArrays", "PrecompileTools", "PrettyTables", "Printf", "REPL", "Random", "Reexport", "SentinelArrays", "SortingAlgorithms", "Statistics", "TableTraits", "Tables", "Unicode"]
+git-tree-sha1 = "04c738083f29f86e62c8afc341f0967d8717bdb8"
+uuid = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
+version = "1.6.1"
+
+[[DataStructures]]
+deps = ["Compat", "InteractiveUtils", "OrderedCollections"]
+git-tree-sha1 = "3dbd312d370723b6bb43ba9d02fc36abade4518d"
+uuid = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
+version = "0.18.15"
+
+[[DataValueInterfaces]]
+git-tree-sha1 = "bfc1187b79289637fa0ef6d4436ebdfe6905cbd6"
+uuid = "e2d170a0-9d28-54be-80f0-106bbe20a464"
+version = "1.0.0"
+
 [[Dates]]
 deps = ["Printf"]
 uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
@@ -97,6 +124,10 @@ git-tree-sha1 = "c1d06d129da9f55715c6c212866f5b1bddc5fa00"
 uuid = "e2ba6199-217a-4e67-a87a-7c52f15ade04"
 version = "0.1.9"
 
+[[Future]]
+deps = ["Random"]
+uuid = "9fa8497b-333b-5362-9e8d-4d0656e87820"
+
 [[GPUArrays]]
 deps = ["Adapt", "GPUArraysCore", "LLVM", "LinearAlgebra", "Printf", "Random", "Reexport", "Serialization", "Statistics"]
 git-tree-sha1 = "2e57b4a4f9cc15e85a24d603256fe08e527f48d1"
@@ -115,6 +146,12 @@ git-tree-sha1 = "72b2e3c2ba583d1a7aa35129e56cf92e07c083e3"
 uuid = "61eb1bfa-7361-4325-ad38-22787b887f55"
 version = "0.21.4"
 
+[[InlineStrings]]
+deps = ["Parsers"]
+git-tree-sha1 = "9cc2baf75c6d09f9da536ddf58eb2f29dedaf461"
+uuid = "842dd82b-1e85-43dc-bf29-5d0ee9dffc48"
+version = "1.4.0"
+
 [[InteractiveUtils]]
 deps = ["Markdown"]
 uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
@@ -125,11 +162,21 @@ git-tree-sha1 = "eabe3125edba5c9c10b60a160b1779a000dc8b29"
 uuid = "3587e190-3f89-42d0-90ee-14403ec27112"
 version = "0.1.11"
 
+[[InvertedIndices]]
+git-tree-sha1 = "0dc7b50b8d436461be01300fd8cd45aa0274b038"
+uuid = "41ab1584-1d38-5bbf-9106-f11c6c58b48f"
+version = "1.3.0"
+
 [[IrrationalConstants]]
 git-tree-sha1 = "630b497eafcc20001bba38a4651b327dcfc491d2"
 uuid = "92d709cd-6900-40b7-9082-c6be49f344b6"
 version = "0.2.2"
 
+[[IteratorInterfaceExtensions]]
+git-tree-sha1 = "a3f24677c21f5bbe9d2a714f95dcd58337fb2856"
+uuid = "82899510-4779-5014-852e-03e436cf321d"
+version = "1.0.0"
+
 [[JLLWrappers]]
 deps = ["Preferences"]
 git-tree-sha1 = "abc9885a7ca2052a736a600f7fa66209f96506e1"
@@ -154,6 +201,11 @@ git-tree-sha1 = "c35203c1e1002747da220ffc3c0762ce7754b08c"
 uuid = "dad2f222-ce93-54a1-a47d-0025e8a3acab"
 version = "0.0.23+0"
 
+[[LaTeXStrings]]
+git-tree-sha1 = "f2355693d6778a178ade15952b7ac47a4ff97996"
+uuid = "b964fa9f-0449-5b57-a5c2-d3ea65f4040f"
+version = "1.3.0"
+
 [[LazyArtifacts]]
 deps = ["Artifacts", "Pkg"]
 uuid = "4af54fe1-eca0-43a8-85a7-787d91b784e3"
@@ -204,6 +256,12 @@ uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
 deps = ["Artifacts", "Libdl"]
 uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1"
 
+[[Missings]]
+deps = ["DataAPI"]
+git-tree-sha1 = "f66bdc5de519e8f8ae43bdc598782d35a25b1272"
+uuid = "e1d29d7a-bbdc-5cf2-9ac0-f12de2c33e28"
+version = "1.1.0"
+
 [[MozillaCACerts_jll]]
 uuid = "14a3606d-f60d-562e-9121-12d972cd8159"
 
@@ -220,10 +278,27 @@ git-tree-sha1 = "13652491f6856acfd2db29360e1bbcd4565d04f1"
 uuid = "efe28fd5-8261-553b-a9e1-b2916fc3738e"
 version = "0.5.5+0"
 
+[[OrderedCollections]]
+git-tree-sha1 = "2e73fe17cac3c62ad1aebe70d44c963c3cfdc3e3"
+uuid = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
+version = "1.6.2"
+
+[[Parsers]]
+deps = ["Dates", "PrecompileTools", "UUIDs"]
+git-tree-sha1 = "716e24b21538abc91f6205fd1d8363f39b442851"
+uuid = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
+version = "2.7.2"
+
 [[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"
 
+[[PooledArrays]]
+deps = ["DataAPI", "Future"]
+git-tree-sha1 = "a6062fe4063cdafe78f4a0a81cfffb89721b30e7"
+uuid = "2dfb63ee-cc39-5dd5-95bd-886bf059d720"
+version = "1.4.2"
+
 [[PrecompileTools]]
 deps = ["Preferences"]
 git-tree-sha1 = "9673d39decc5feece56ef3940e5dafba15ba0f81"
@@ -236,6 +311,12 @@ git-tree-sha1 = "7eb1686b4f04b82f96ed7a4ea5890a4f0c7a09f1"
 uuid = "21216c6a-2e73-6563-6e65-726566657250"
 version = "1.4.0"
 
+[[PrettyTables]]
+deps = ["Crayons", "LaTeXStrings", "Markdown", "Printf", "Reexport", "StringManipulation", "Tables"]
+git-tree-sha1 = "ee094908d720185ddbdc58dbe0c1cbe35453ec7a"
+uuid = "08abe8d2-0d0c-5749-adfa-8a2ac140af0d"
+version = "2.2.7"
+
 [[Printf]]
 deps = ["Unicode"]
 uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7"
@@ -280,12 +361,24 @@ git-tree-sha1 = "30449ee12237627992a99d5e30ae63e4d78cd24a"
 uuid = "6c6a2e73-6563-6170-7368-637461726353"
 version = "1.2.0"
 
+[[SentinelArrays]]
+deps = ["Dates", "Random"]
+git-tree-sha1 = "04bdff0b09c65ff3e06a05e3eb7b120223da3d39"
+uuid = "91c51154-3ec4-41a3-a24f-3f23e20d615c"
+version = "1.4.0"
+
 [[Serialization]]
 uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
 
 [[Sockets]]
 uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
 
+[[SortingAlgorithms]]
+deps = ["DataStructures"]
+git-tree-sha1 = "c60ec5c62180f27efea3ba2908480f8055e17cee"
+uuid = "a2af1166-a08f-5f64-846c-94a0d3cef48c"
+version = "1.1.1"
+
 [[SparseArrays]]
 deps = ["LinearAlgebra", "Random"]
 uuid = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
@@ -311,10 +404,27 @@ version = "1.4.2"
 deps = ["LinearAlgebra", "SparseArrays"]
 uuid = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 
+[[StringManipulation]]
+git-tree-sha1 = "46da2434b41f41ac3594ee9816ce5541c6096123"
+uuid = "892a3eda-7b42-436c-8928-eab12a02cf0e"
+version = "0.3.0"
+
 [[TOML]]
 deps = ["Dates"]
 uuid = "fa267f1f-6049-4f14-aa54-33bafae1ed76"
 
+[[TableTraits]]
+deps = ["IteratorInterfaceExtensions"]
+git-tree-sha1 = "c06b2f539df1c6efa794486abfb6ed2022561a39"
+uuid = "3783bdb8-4a98-5b6b-af9a-565f29a5fe9c"
+version = "1.0.1"
+
+[[Tables]]
+deps = ["DataAPI", "DataValueInterfaces", "IteratorInterfaceExtensions", "LinearAlgebra", "OrderedCollections", "TableTraits", "Test"]
+git-tree-sha1 = "1544b926975372da01227b382066ab70e574a3ec"
+uuid = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
+version = "1.10.1"
+
 [[Tar]]
 deps = ["ArgTools", "SHA"]
 uuid = "a4e569a6-e804-4fa4-b0f3-eef7a1d5b13e"

Project.toml

@@ -10,6 +10,8 @@ CEnum = "fa961155-64e5-5f13-b03f-caf6b980ea82"
 CUDA_Driver_jll = "4ee394cb-3365-5eb0-8335-949819d2adfc"
 CUDA_Runtime_Discovery = "1af6417a-86b4-443c-805f-a4643ffb695f"
 CUDA_Runtime_jll = "76a88914-d11a-5bdc-97e0-2f5a05c973a2"
+Crayons = "a8cc5b0e-0ffa-5ad4-8c14-923d3ee1735f"
+DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 ExprTools = "e2ba6199-217a-4e67-a87a-7c52f15ade04"
 GPUArrays = "0c68f7d7-f131-5f86-a1c3-88cf8149b2d7"
 GPUCompiler = "61eb1bfa-7361-4325-ad38-22787b887f55"
@@ -20,6 +22,7 @@ Libdl = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 Logging = "56ddb016-857b-54e1-b83d-db4d58db5568"
 Preferences = "21216c6a-2e73-6563-6e65-726566657250"
+PrettyTables = "08abe8d2-0d0c-5749-adfa-8a2ac140af0d"
 Printf = "de0858da-6303-5e67-8744-51eddeeeb8d7"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 Random123 = "74087812-796a-5b5d-8853-05524746bad3"
@@ -28,6 +31,7 @@ Reexport = "189a3867-3050-52da-a836-e630ba90ab69"
 Requires = "ae029012-a4dd-5104-9daa-d747884805df"
 SparseArrays = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
 SpecialFunctions = "276daf66-3868-5448-9aa4-cd146d93841b"
+Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 UnsafeAtomicsLLVM = "d80eeb9a-aca5-4d75-85e5-170c8b632249"
 
 [compat]
@@ -38,12 +42,15 @@ CEnum = "0.2, 0.3, 0.4"
 CUDA_Driver_jll = "0.5"
 CUDA_Runtime_Discovery = "0.2"
 CUDA_Runtime_jll = "0.6"
+Crayons = "4"
+DataFrames = "1"
 ExprTools = "0.1"
 GPUArrays = "8.6"
 GPUCompiler = "0.21"
 KernelAbstractions = "0.9.2"
 LLVM = "6"
 Preferences = "1"
+PrettyTables = "2"
 Random123 = "1.2"
 RandomNumbers = "1.5.3"
 Reexport = "0.2, 1.0"

lib/cudadrv/CUDAdrv.jl

@@ -23,7 +23,6 @@ include("memory.jl")
 include("module.jl")
 include("events.jl")
 include("execution.jl")
-include("profile.jl")
 include("occupancy.jl")
 include("graph.jl")