diff --git a/.buildkite/pipeline.yml b/.buildkite/pipeline.yml
index b6fc8766..423fcd0c 100644
--- a/.buildkite/pipeline.yml
+++ b/.buildkite/pipeline.yml
@@ -28,10 +28,9 @@ steps:
         matrix:
           setup:
             julia:
-              - "1.6"
-              - "1.7"
               - "1.8"
               - "1.9"
+              - "1.10"
           #     - "nightly"
           # adjustments:
           #   - with:
diff --git a/Manifest.toml b/Manifest.toml
index f933e354..834ccb99 100644
--- a/Manifest.toml
+++ b/Manifest.toml
@@ -1,401 +1,582 @@
 # This file is machine-generated - editing it directly is not advised
 
-[[AbstractFFTs]]
+julia_version = "1.8.5"
+manifest_format = "2.0"
+project_hash = "971c923115a63e4d11061a89aea08517dad66a1f"
+
+[[deps.AbstractFFTs]]
 deps = ["ChainRulesCore", "LinearAlgebra", "Test"]
 git-tree-sha1 = "d92ad398961a3ed262d8bf04a1a2b8340f915fef"
 uuid = "621f4979-c628-5d54-868e-fcf4e3e8185c"
 version = "1.5.0"
 
-[[Adapt]]
+[[deps.Adapt]]
 deps = ["LinearAlgebra", "Requires"]
 git-tree-sha1 = "76289dc51920fdc6e0013c872ba9551d54961c24"
 uuid = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
 version = "3.6.2"
 
-[[ArgTools]]
+[[deps.ArgTools]]
 uuid = "0dad84c5-d112-42e6-8d28-ef12dabb789f"
+version = "1.1.1"
 
-[[Artifacts]]
+[[deps.Artifacts]]
 uuid = "56f22d72-fd6d-98f1-02f0-08ddc0907c33"
 
-[[Atomix]]
+[[deps.Atomix]]
 deps = ["UnsafeAtomics"]
 git-tree-sha1 = "c06a868224ecba914baa6942988e2f2aade419be"
 uuid = "a9b6321e-bd34-4604-b9c9-b65b8de01458"
 version = "0.1.0"
 
-[[BFloat16s]]
+[[deps.BFloat16s]]
 deps = ["LinearAlgebra", "Printf", "Random", "Test"]
 git-tree-sha1 = "dbf84058d0a8cbbadee18d25cf606934b22d7c66"
 uuid = "ab4f0b2a-ad5b-11e8-123f-65d77653426b"
 version = "0.4.2"
 
-[[Base64]]
+[[deps.Base64]]
 uuid = "2a0f44e3-6c83-55bd-87e4-b1978d98bd5f"
 
-[[CEnum]]
+[[deps.CEnum]]
 git-tree-sha1 = "eb4cb44a499229b3b8426dcfb5dd85333951ff90"
 uuid = "fa961155-64e5-5f13-b03f-caf6b980ea82"
 version = "0.4.2"
 
-[[CUDA]]
-deps = ["AbstractFFTs", "Adapt", "BFloat16s", "CEnum", "CUDA_Driver_jll", "CUDA_Runtime_Discovery", "CUDA_Runtime_jll", "ExprTools", "GPUArrays", "GPUCompiler", "KernelAbstractions", "LLVM", "LazyArtifacts", "Libdl", "LinearAlgebra", "Logging", "Preferences", "Printf", "Random", "Random123", "RandomNumbers", "Reexport", "Requires", "SparseArrays", "SpecialFunctions", "UnsafeAtomicsLLVM"]
-git-tree-sha1 = "968c1365e2992824c3e7a794e30907483f8469a9"
+[[deps.CUDA]]
+deps = ["AbstractFFTs", "Adapt", "BFloat16s", "CEnum", "CUDA_Driver_jll", "CUDA_Runtime_Discovery", "CUDA_Runtime_jll", "Crayons", "DataFrames", "ExprTools", "GPUArrays", "GPUCompiler", "KernelAbstractions", "LLVM", "LazyArtifacts", "Libdl", "LinearAlgebra", "Logging", "NVTX", "Preferences", "PrettyTables", "Printf", "Random", "Random123", "RandomNumbers", "Reexport", "Requires", "SparseArrays", "Statistics", "UnsafeAtomicsLLVM"]
+git-tree-sha1 = "f062a48c26ae027f70c44f48f244862aec47bf99"
 uuid = "052768ef-5323-5732-b1bb-66c8b64840ba"
-version = "4.4.1"
+version = "5.0.0"
 
-[[CUDA_Driver_jll]]
+[[deps.CUDA_Driver_jll]]
 deps = ["Artifacts", "JLLWrappers", "LazyArtifacts", "Libdl", "Pkg"]
-git-tree-sha1 = "498f45593f6ddc0adff64a9310bb6710e851781b"
+git-tree-sha1 = "35a37bb72b35964f2895c12c687ae263b4ac170c"
 uuid = "4ee394cb-3365-5eb0-8335-949819d2adfc"
-version = "0.5.0+1"
+version = "0.6.0+3"
 
-[[CUDA_Runtime_Discovery]]
+[[deps.CUDA_Runtime_Discovery]]
 deps = ["Libdl"]
 git-tree-sha1 = "bcc4a23cbbd99c8535a5318455dcf0f2546ec536"
 uuid = "1af6417a-86b4-443c-805f-a4643ffb695f"
 version = "0.2.2"
 
-[[CUDA_Runtime_jll]]
+[[deps.CUDA_Runtime_jll]]
 deps = ["Artifacts", "CUDA_Driver_jll", "JLLWrappers", "LazyArtifacts", "Libdl", "TOML"]
-git-tree-sha1 = "5248d9c45712e51e27ba9b30eebec65658c6ce29"
+git-tree-sha1 = "bfe5a693a11522d58392f742243f2b50dc27afd6"
 uuid = "76a88914-d11a-5bdc-97e0-2f5a05c973a2"
-version = "0.6.0+0"
+version = "0.9.2+0"
 
-[[ChainRulesCore]]
+[[deps.ChainRulesCore]]
 deps = ["Compat", "LinearAlgebra", "SparseArrays"]
 git-tree-sha1 = "e30f2f4e20f7f186dc36529910beaedc60cfa644"
 uuid = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
 version = "1.16.0"
 
-[[ChangesOfVariables]]
+[[deps.ChangesOfVariables]]
 deps = ["InverseFunctions", "LinearAlgebra", "Test"]
 git-tree-sha1 = "2fba81a302a7be671aefe194f0525ef231104e7f"
 uuid = "9e997f8a-9a97-42d5-a9f1-ce6bfc15e2c0"
 version = "0.1.8"
 
-[[CommonSubexpressions]]
+[[deps.ColorTypes]]
+deps = ["FixedPointNumbers", "Random"]
+git-tree-sha1 = "eb7f0f8307f71fac7c606984ea5fb2817275d6e4"
+uuid = "3da002f7-5984-5a60-b8a6-cbb66c0b333f"
+version = "0.11.4"
+
+[[deps.Colors]]
+deps = ["ColorTypes", "FixedPointNumbers", "Reexport"]
+git-tree-sha1 = "fc08e5930ee9a4e03f84bfb5211cb54e7769758a"
+uuid = "5ae59095-9a9b-59fe-a467-6f913c188581"
+version = "0.12.10"
+
+[[deps.CommonSubexpressions]]
 deps = ["MacroTools", "Test"]
 git-tree-sha1 = "7b8a93dba8af7e3b42fecabf646260105ac373f7"
 uuid = "bbf7d656-a473-5ed7-a52c-81e309532950"
 version = "0.3.0"
 
-[[Compat]]
+[[deps.Compat]]
 deps = ["Dates", "LinearAlgebra", "UUIDs"]
 git-tree-sha1 = "e460f044ca8b99be31d35fe54fc33a5c33dd8ed7"
 uuid = "34da2185-b29b-5c13-b0c7-acf172513d20"
 version = "4.9.0"
 
-[[CompilerSupportLibraries_jll]]
+[[deps.CompilerSupportLibraries_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "e66e0078-7015-5450-92f7-15fbd957f2ae"
+version = "1.0.1+0"
+
+[[deps.Crayons]]
+git-tree-sha1 = "249fe38abf76d48563e2f4556bebd215aa317e15"
+uuid = "a8cc5b0e-0ffa-5ad4-8c14-923d3ee1735f"
+version = "4.1.1"
+
+[[deps.DataAPI]]
+git-tree-sha1 = "8da84edb865b0b5b0100c0666a9bc9a0b71c553c"
+uuid = "9a962f9c-6df0-11e9-0e5d-c546b8b5ee8a"
+version = "1.15.0"
+
+[[deps.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"
+
+[[deps.DataStructures]]
+deps = ["Compat", "InteractiveUtils", "OrderedCollections"]
+git-tree-sha1 = "3dbd312d370723b6bb43ba9d02fc36abade4518d"
+uuid = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
+version = "0.18.15"
 
-[[Dates]]
+[[deps.DataValueInterfaces]]
+git-tree-sha1 = "bfc1187b79289637fa0ef6d4436ebdfe6905cbd6"
+uuid = "e2d170a0-9d28-54be-80f0-106bbe20a464"
+version = "1.0.0"
+
+[[deps.Dates]]
 deps = ["Printf"]
 uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
 
-[[DiffResults]]
+[[deps.DiffResults]]
 deps = ["StaticArraysCore"]
 git-tree-sha1 = "782dd5f4561f5d267313f23853baaaa4c52ea621"
 uuid = "163ba53b-c6d8-5494-b064-1a9d43ac40c5"
 version = "1.1.0"
 
-[[DiffRules]]
+[[deps.DiffRules]]
 deps = ["IrrationalConstants", "LogExpFunctions", "NaNMath", "Random", "SpecialFunctions"]
 git-tree-sha1 = "23163d55f885173722d1e4cf0f6110cdbaf7e272"
 uuid = "b552c78f-8df3-52c6-915a-8e097449b14b"
 version = "1.15.1"
 
-[[DocStringExtensions]]
+[[deps.DocStringExtensions]]
 deps = ["LibGit2"]
 git-tree-sha1 = "2fb1e02f2b635d0845df5d7c167fec4dd739b00d"
 uuid = "ffbed154-4ef7-542d-bbb7-c09d3a79fcae"
 version = "0.9.3"
 
-[[Downloads]]
-deps = ["ArgTools", "LibCURL", "NetworkOptions"]
+[[deps.Downloads]]
+deps = ["ArgTools", "FileWatching", "LibCURL", "NetworkOptions"]
 uuid = "f43a241f-c20a-4ad4-852c-f6b1247861c6"
+version = "1.6.0"
 
-[[ExprTools]]
+[[deps.ExprTools]]
 git-tree-sha1 = "27415f162e6028e81c72b82ef756bf321213b6ec"
 uuid = "e2ba6199-217a-4e67-a87a-7c52f15ade04"
 version = "0.1.10"
 
-[[ForwardDiff]]
+[[deps.FileWatching]]
+uuid = "7b1f6079-737a-58dc-b8bc-7a2ca5c1b5ee"
+
+[[deps.FixedPointNumbers]]
+deps = ["Statistics"]
+git-tree-sha1 = "335bfdceacc84c5cdf16aadc768aa5ddfc5383cc"
+uuid = "53c48c17-4a7d-5ca2-90c5-79b7896eea93"
+version = "0.8.4"
+
+[[deps.ForwardDiff]]
 deps = ["CommonSubexpressions", "DiffResults", "DiffRules", "LinearAlgebra", "LogExpFunctions", "NaNMath", "Preferences", "Printf", "Random", "SpecialFunctions", "StaticArrays"]
 git-tree-sha1 = "cf0fe81336da9fb90944683b8c41984b08793dad"
 uuid = "f6369f11-7733-5829-9624-2563aa707210"
 version = "0.10.36"
 
-[[GPUArrays]]
+[[deps.Future]]
+deps = ["Random"]
+uuid = "9fa8497b-333b-5362-9e8d-4d0656e87820"
+
+[[deps.GPUArrays]]
 deps = ["Adapt", "GPUArraysCore", "LLVM", "LinearAlgebra", "Printf", "Random", "Reexport", "Serialization", "Statistics"]
-git-tree-sha1 = "2e57b4a4f9cc15e85a24d603256fe08e527f48d1"
+git-tree-sha1 = "8ad8f375ae365aa1eb2f42e2565a40b55a4b69a8"
 uuid = "0c68f7d7-f131-5f86-a1c3-88cf8149b2d7"
-version = "8.8.1"
+version = "9.0.0"
 
-[[GPUArraysCore]]
+[[deps.GPUArraysCore]]
 deps = ["Adapt"]
 git-tree-sha1 = "2d6ca471a6c7b536127afccfa7564b5b39227fe0"
 uuid = "46192b85-c4d5-4398-a991-12ede77f4527"
 version = "0.1.5"
 
-[[GPUCompiler]]
+[[deps.GPUCompiler]]
 deps = ["ExprTools", "InteractiveUtils", "LLVM", "Libdl", "Logging", "Scratch", "TimerOutputs", "UUIDs"]
-git-tree-sha1 = "72b2e3c2ba583d1a7aa35129e56cf92e07c083e3"
+git-tree-sha1 = "fa7dcf83344770adde87b256784155b194e05c9a"
 uuid = "61eb1bfa-7361-4325-ad38-22787b887f55"
-version = "0.21.4"
+version = "0.24.4"
 
-[[InteractiveUtils]]
+[[deps.InlineStrings]]
+deps = ["Parsers"]
+git-tree-sha1 = "9cc2baf75c6d09f9da536ddf58eb2f29dedaf461"
+uuid = "842dd82b-1e85-43dc-bf29-5d0ee9dffc48"
+version = "1.4.0"
+
+[[deps.InteractiveUtils]]
 deps = ["Markdown"]
 uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
 
-[[InverseFunctions]]
+[[deps.InverseFunctions]]
 deps = ["Test"]
 git-tree-sha1 = "68772f49f54b479fa88ace904f6127f0a3bb2e46"
 uuid = "3587e190-3f89-42d0-90ee-14403ec27112"
 version = "0.1.12"
 
-[[IrrationalConstants]]
+[[deps.InvertedIndices]]
+git-tree-sha1 = "0dc7b50b8d436461be01300fd8cd45aa0274b038"
+uuid = "41ab1584-1d38-5bbf-9106-f11c6c58b48f"
+version = "1.3.0"
+
+[[deps.IrrationalConstants]]
 git-tree-sha1 = "630b497eafcc20001bba38a4651b327dcfc491d2"
 uuid = "92d709cd-6900-40b7-9082-c6be49f344b6"
 version = "0.2.2"
 
-[[JLLWrappers]]
+[[deps.IteratorInterfaceExtensions]]
+git-tree-sha1 = "a3f24677c21f5bbe9d2a714f95dcd58337fb2856"
+uuid = "82899510-4779-5014-852e-03e436cf321d"
+version = "1.0.0"
+
+[[deps.JLLWrappers]]
 deps = ["Artifacts", "Preferences"]
 git-tree-sha1 = "7e5d6779a1e09a36db2a7b6cff50942a0a7d0fca"
 uuid = "692b3bcd-3c85-4b1f-b108-f13ce0eb3210"
 version = "1.5.0"
 
-[[KernelAbstractions]]
+[[deps.JuliaNVTXCallbacks_jll]]
+deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
+git-tree-sha1 = "af433a10f3942e882d3c671aacb203e006a5808f"
+uuid = "9c1d0b0a-7046-5b2e-a33f-ea22f176ac7e"
+version = "0.2.1+0"
+
+[[deps.KernelAbstractions]]
 deps = ["Adapt", "Atomix", "InteractiveUtils", "LinearAlgebra", "MacroTools", "PrecompileTools", "Requires", "SparseArrays", "StaticArrays", "UUIDs", "UnsafeAtomics", "UnsafeAtomicsLLVM"]
 git-tree-sha1 = "4c5875e4c228247e1c2b087669846941fb6e0118"
 uuid = "63c18a36-062a-441e-b654-da1e3ab1ce7c"
 version = "0.9.8"
 
-[[LLVM]]
+[[deps.LLVM]]
 deps = ["CEnum", "LLVMExtra_jll", "Libdl", "Printf", "Unicode"]
-git-tree-sha1 = "8695a49bfe05a2dc0feeefd06b4ca6361a018729"
+git-tree-sha1 = "a9d2ce1d5007b1e8f6c5b89c5a31ff8bd146db5c"
 uuid = "929cbde3-209d-540e-8aea-75f648917ca0"
-version = "6.1.0"
+version = "6.2.1"
 
-[[LLVMExtra_jll]]
+[[deps.LLVMExtra_jll]]
 deps = ["Artifacts", "JLLWrappers", "LazyArtifacts", "Libdl", "TOML"]
-git-tree-sha1 = "c35203c1e1002747da220ffc3c0762ce7754b08c"
+git-tree-sha1 = "7ca6850ae880cc99b59b88517545f91a52020afa"
 uuid = "dad2f222-ce93-54a1-a47d-0025e8a3acab"
-version = "0.0.23+0"
+version = "0.0.25+0"
 
-[[LLVMLoopInfo]]
+[[deps.LLVMLoopInfo]]
 git-tree-sha1 = "2e5c102cfc41f48ae4740c7eca7743cc7e7b75ea"
 uuid = "8b046642-f1f6-4319-8d3c-209ddc03c586"
 version = "1.0.0"
 
-[[LazyArtifacts]]
+[[deps.LaTeXStrings]]
+git-tree-sha1 = "f2355693d6778a178ade15952b7ac47a4ff97996"
+uuid = "b964fa9f-0449-5b57-a5c2-d3ea65f4040f"
+version = "1.3.0"
+
+[[deps.LazyArtifacts]]
 deps = ["Artifacts", "Pkg"]
 uuid = "4af54fe1-eca0-43a8-85a7-787d91b784e3"
 
-[[LibCURL]]
+[[deps.LibCURL]]
 deps = ["LibCURL_jll", "MozillaCACerts_jll"]
 uuid = "b27032c2-a3e7-50c8-80cd-2d36dbcbfd21"
+version = "0.6.3"
 
-[[LibCURL_jll]]
+[[deps.LibCURL_jll]]
 deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll", "Zlib_jll", "nghttp2_jll"]
 uuid = "deac9b47-8bc7-5906-a0fe-35ac56dc84c0"
+version = "7.84.0+0"
 
-[[LibGit2]]
+[[deps.LibGit2]]
 deps = ["Base64", "NetworkOptions", "Printf", "SHA"]
 uuid = "76f85450-5226-5b5a-8eaa-529ad045b433"
 
-[[LibSSH2_jll]]
+[[deps.LibSSH2_jll]]
 deps = ["Artifacts", "Libdl", "MbedTLS_jll"]
 uuid = "29816b5a-b9ab-546f-933c-edad1886dfa8"
+version = "1.10.2+0"
 
-[[Libdl]]
+[[deps.Libdl]]
 uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
 
-[[LinearAlgebra]]
-deps = ["Libdl"]
+[[deps.LinearAlgebra]]
+deps = ["Libdl", "libblastrampoline_jll"]
 uuid = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 
-[[LogExpFunctions]]
+[[deps.LogExpFunctions]]
 deps = ["ChainRulesCore", "ChangesOfVariables", "DocStringExtensions", "InverseFunctions", "IrrationalConstants", "LinearAlgebra"]
 git-tree-sha1 = "7d6dd4e9212aebaeed356de34ccf262a3cd415aa"
 uuid = "2ab3a3ac-af41-5b50-aa03-7779005ae688"
 version = "0.3.26"
 
-[[Logging]]
+[[deps.Logging]]
 uuid = "56ddb016-857b-54e1-b83d-db4d58db5568"
 
-[[MacroTools]]
+[[deps.MacroTools]]
 deps = ["Markdown", "Random"]
 git-tree-sha1 = "9ee1618cbf5240e6d4e0371d6f24065083f60c48"
 uuid = "1914dd2f-81c6-5fcd-8719-6d5c9610ff09"
 version = "0.5.11"
 
-[[Markdown]]
+[[deps.Markdown]]
 deps = ["Base64"]
 uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
 
-[[MbedTLS_jll]]
+[[deps.MbedTLS_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1"
+version = "2.28.0+0"
+
+[[deps.Missings]]
+deps = ["DataAPI"]
+git-tree-sha1 = "f66bdc5de519e8f8ae43bdc598782d35a25b1272"
+uuid = "e1d29d7a-bbdc-5cf2-9ac0-f12de2c33e28"
+version = "1.1.0"
 
-[[MozillaCACerts_jll]]
+[[deps.MozillaCACerts_jll]]
 uuid = "14a3606d-f60d-562e-9121-12d972cd8159"
+version = "2022.2.1"
+
+[[deps.NVTX]]
+deps = ["Colors", "JuliaNVTXCallbacks_jll", "Libdl", "NVTX_jll"]
+git-tree-sha1 = "8bc9ce4233be3c63f8dcd78ccaf1b63a9c0baa34"
+uuid = "5da4648a-3479-48b8-97b9-01cb529c0a1f"
+version = "0.3.3"
+
+[[deps.NVTX_jll]]
+deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
+git-tree-sha1 = "ce3269ed42816bf18d500c9f63418d4b0d9f5a3b"
+uuid = "e98f9f5b-d649-5603-91fd-7774390e6439"
+version = "3.1.0+2"
 
-[[NaNMath]]
+[[deps.NaNMath]]
 deps = ["OpenLibm_jll"]
 git-tree-sha1 = "0877504529a3e5c3343c6f8b4c0381e57e4387e4"
 uuid = "77ba4419-2d1f-58cd-9bb1-8ffee604a2e3"
 version = "1.0.2"
 
-[[NetworkOptions]]
+[[deps.NetworkOptions]]
 uuid = "ca575930-c2e3-43a9-ace4-1e988b2c1908"
+version = "1.2.0"
+
+[[deps.OpenBLAS_jll]]
+deps = ["Artifacts", "CompilerSupportLibraries_jll", "Libdl"]
+uuid = "4536629a-c528-5b80-bd46-f80d51c5b363"
+version = "0.3.20+0"
 
-[[OpenLibm_jll]]
+[[deps.OpenLibm_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "05823500-19ac-5b8b-9628-191a04bc5112"
+version = "0.8.1+0"
 
-[[OpenSpecFun_jll]]
+[[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"
 
-[[Pkg]]
+[[deps.OrderedCollections]]
+git-tree-sha1 = "2e73fe17cac3c62ad1aebe70d44c963c3cfdc3e3"
+uuid = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
+version = "1.6.2"
+
+[[deps.Parsers]]
+deps = ["Dates", "PrecompileTools", "UUIDs"]
+git-tree-sha1 = "716e24b21538abc91f6205fd1d8363f39b442851"
+uuid = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
+version = "2.7.2"
+
+[[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"
+version = "1.8.0"
+
+[[deps.PooledArrays]]
+deps = ["DataAPI", "Future"]
+git-tree-sha1 = "36d8b4b899628fb92c2749eb488d884a926614d3"
+uuid = "2dfb63ee-cc39-5dd5-95bd-886bf059d720"
+version = "1.4.3"
 
-[[PrecompileTools]]
+[[deps.PrecompileTools]]
 deps = ["Preferences"]
 git-tree-sha1 = "03b4c25b43cb84cee5c90aa9b5ea0a78fd848d2f"
 uuid = "aea7be01-6a6a-4083-8856-8a6e6704d82a"
 version = "1.2.0"
 
-[[Preferences]]
+[[deps.Preferences]]
 deps = ["TOML"]
 git-tree-sha1 = "7eb1686b4f04b82f96ed7a4ea5890a4f0c7a09f1"
 uuid = "21216c6a-2e73-6563-6e65-726566657250"
 version = "1.4.0"
 
-[[Printf]]
+[[deps.PrettyTables]]
+deps = ["Crayons", "LaTeXStrings", "Markdown", "Printf", "Reexport", "StringManipulation", "Tables"]
+git-tree-sha1 = "ee094908d720185ddbdc58dbe0c1cbe35453ec7a"
+uuid = "08abe8d2-0d0c-5749-adfa-8a2ac140af0d"
+version = "2.2.7"
+
+[[deps.Printf]]
 deps = ["Unicode"]
 uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7"
 
-[[REPL]]
+[[deps.REPL]]
 deps = ["InteractiveUtils", "Markdown", "Sockets", "Unicode"]
 uuid = "3fa0cd96-eef1-5676-8a61-b3b8758bbffb"
 
-[[Random]]
-deps = ["Serialization"]
+[[deps.Random]]
+deps = ["SHA", "Serialization"]
 uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 
-[[Random123]]
+[[deps.Random123]]
 deps = ["Random", "RandomNumbers"]
 git-tree-sha1 = "552f30e847641591ba3f39fd1bed559b9deb0ef3"
 uuid = "74087812-796a-5b5d-8853-05524746bad3"
 version = "1.6.1"
 
-[[RandomNumbers]]
+[[deps.RandomNumbers]]
 deps = ["Random", "Requires"]
 git-tree-sha1 = "043da614cc7e95c703498a491e2c21f58a2b8111"
 uuid = "e6cf234a-135c-5ec9-84dd-332b85af5143"
 version = "1.5.3"
 
-[[Reexport]]
+[[deps.Reexport]]
 git-tree-sha1 = "45e428421666073eab6f2da5c9d310d99bb12f9b"
 uuid = "189a3867-3050-52da-a836-e630ba90ab69"
 version = "1.2.2"
 
-[[Requires]]
+[[deps.Requires]]
 deps = ["UUIDs"]
 git-tree-sha1 = "838a3a4188e2ded87a4f9f184b4b0d78a1e91cb7"
 uuid = "ae029012-a4dd-5104-9daa-d747884805df"
 version = "1.3.0"
 
-[[SHA]]
+[[deps.SHA]]
 uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
+version = "0.7.0"
 
-[[Scratch]]
+[[deps.Scratch]]
 deps = ["Dates"]
 git-tree-sha1 = "30449ee12237627992a99d5e30ae63e4d78cd24a"
 uuid = "6c6a2e73-6563-6170-7368-637461726353"
 version = "1.2.0"
 
-[[Serialization]]
+[[deps.SentinelArrays]]
+deps = ["Dates", "Random"]
+git-tree-sha1 = "04bdff0b09c65ff3e06a05e3eb7b120223da3d39"
+uuid = "91c51154-3ec4-41a3-a24f-3f23e20d615c"
+version = "1.4.0"
+
+[[deps.Serialization]]
 uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
 
-[[Sockets]]
+[[deps.Sockets]]
 uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
 
-[[SparseArrays]]
+[[deps.SortingAlgorithms]]
+deps = ["DataStructures"]
+git-tree-sha1 = "c60ec5c62180f27efea3ba2908480f8055e17cee"
+uuid = "a2af1166-a08f-5f64-846c-94a0d3cef48c"
+version = "1.1.1"
+
+[[deps.SparseArrays]]
 deps = ["LinearAlgebra", "Random"]
 uuid = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
 
-[[SpecialFunctions]]
+[[deps.SpecialFunctions]]
 deps = ["ChainRulesCore", "IrrationalConstants", "LogExpFunctions", "OpenLibm_jll", "OpenSpecFun_jll"]
 git-tree-sha1 = "e2cfc4012a19088254b3950b85c3c1d8882d864d"
 uuid = "276daf66-3868-5448-9aa4-cd146d93841b"
 version = "2.3.1"
 
-[[StaticArrays]]
+[[deps.StaticArrays]]
 deps = ["LinearAlgebra", "Random", "StaticArraysCore", "Statistics"]
 git-tree-sha1 = "51621cca8651d9e334a659443a74ce50a3b6dfab"
 uuid = "90137ffa-7385-5640-81b9-e52037218182"
 version = "1.6.3"
 
-[[StaticArraysCore]]
+[[deps.StaticArraysCore]]
 git-tree-sha1 = "36b3d696ce6366023a0ea192b4cd442268995a0d"
 uuid = "1e83bf80-4336-4d27-bf5d-d5a4f845583c"
 version = "1.4.2"
 
-[[Statistics]]
+[[deps.Statistics]]
 deps = ["LinearAlgebra", "SparseArrays"]
 uuid = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 
-[[TOML]]
+[[deps.StringManipulation]]
+deps = ["PrecompileTools"]
+git-tree-sha1 = "a04cabe79c5f01f4d723cc6704070ada0b9d46d5"
+uuid = "892a3eda-7b42-436c-8928-eab12a02cf0e"
+version = "0.3.4"
+
+[[deps.TOML]]
 deps = ["Dates"]
 uuid = "fa267f1f-6049-4f14-aa54-33bafae1ed76"
+version = "1.0.0"
+
+[[deps.TableTraits]]
+deps = ["IteratorInterfaceExtensions"]
+git-tree-sha1 = "c06b2f539df1c6efa794486abfb6ed2022561a39"
+uuid = "3783bdb8-4a98-5b6b-af9a-565f29a5fe9c"
+version = "1.0.1"
 
-[[Tar]]
+[[deps.Tables]]
+deps = ["DataAPI", "DataValueInterfaces", "IteratorInterfaceExtensions", "LinearAlgebra", "OrderedCollections", "TableTraits"]
+git-tree-sha1 = "a1f34829d5ac0ef499f6d84428bd6b4c71f02ead"
+uuid = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
+version = "1.11.0"
+
+[[deps.Tar]]
 deps = ["ArgTools", "SHA"]
 uuid = "a4e569a6-e804-4fa4-b0f3-eef7a1d5b13e"
+version = "1.10.1"
 
-[[Test]]
+[[deps.Test]]
 deps = ["InteractiveUtils", "Logging", "Random", "Serialization"]
 uuid = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
-[[TimerOutputs]]
+[[deps.TimerOutputs]]
 deps = ["ExprTools", "Printf"]
 git-tree-sha1 = "f548a9e9c490030e545f72074a41edfd0e5bcdd7"
 uuid = "a759f4b9-e2f1-59dc-863e-4aeb61b1ea8f"
 version = "0.5.23"
 
-[[UUIDs]]
+[[deps.UUIDs]]
 deps = ["Random", "SHA"]
 uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
 
-[[Unicode]]
+[[deps.Unicode]]
 uuid = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5"
 
-[[UnsafeAtomics]]
+[[deps.UnsafeAtomics]]
 git-tree-sha1 = "6331ac3440856ea1988316b46045303bef658278"
 uuid = "013be700-e6cd-48c3-b4a1-df204f14c38f"
 version = "0.2.1"
 
-[[UnsafeAtomicsLLVM]]
+[[deps.UnsafeAtomicsLLVM]]
 deps = ["LLVM", "UnsafeAtomics"]
 git-tree-sha1 = "323e3d0acf5e78a56dfae7bd8928c989b4f3083e"
 uuid = "d80eeb9a-aca5-4d75-85e5-170c8b632249"
 version = "0.1.3"
 
-[[Zlib_jll]]
+[[deps.Zlib_jll]]
 deps = ["Libdl"]
 uuid = "83775a58-1f1d-513f-b197-d71354ab007a"
+version = "1.2.12+3"
+
+[[deps.libblastrampoline_jll]]
+deps = ["Artifacts", "Libdl", "OpenBLAS_jll"]
+uuid = "8e850b90-86db-534c-a0d3-1478176c7d93"
+version = "5.1.1+0"
 
-[[nghttp2_jll]]
+[[deps.nghttp2_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "8e850ede-7688-5339-a07c-302acd2aaf8d"
+version = "1.48.0+0"
 
-[[p7zip_jll]]
+[[deps.p7zip_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "3f19e933-33d8-53b3-aaab-bd5110c3b7a0"
+version = "17.4.0+0"
diff --git a/Project.toml b/Project.toml
index fbf9e023..38540b9a 100644
--- a/Project.toml
+++ b/Project.toml
@@ -11,8 +11,8 @@ LLVMLoopInfo = "8b046642-f1f6-4319-8d3c-209ddc03c586"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 
 [compat]
-CUDA = "3.5, 4"
+CUDA = "3.5, 4, 5"
 ForwardDiff = "0.10"
 LLVM = "3, 4, 5, 6"
 LLVMLoopInfo = "1"
-julia = "1.6"
+julia = "1.8"
diff --git a/benchmarks/blas.jl b/benchmarks/blas.jl
index 01fa53e1..e71f77af 100644
--- a/benchmarks/blas.jl
+++ b/benchmarks/blas.jl
@@ -45,15 +45,10 @@ function blas_benchmark(group, a_type, b_type, cd_type, N, M=N, K=N; alpha=true,
 
     # NOTE: we use `cuStreamSynchronize` instead of `synchronize` to avoid
     #       influence from the Julia scheduler
-    group[name] = @benchmarkable(
-        begin
-            GemmKernels.matmatmul!(c, $a_layout, $b_layout, a, b, $alpha, $beta; $(kwargs)...)
-            CUDA.cuStreamSynchronize(stream())
-        end,
-        setup=(a=CuArray($a_h); b=CuArray($b_h); c=CuArray($c_h);
-               CUDA.cuStreamSynchronize(stream())),
-        teardown=(CUDA.unsafe_free!(a); CUDA.unsafe_free!(b); CUDA.unsafe_free!(c))
-    )
+    group[name] = @benchmarkable begin
+        GemmKernels.matmatmul!($c, $a_layout, $b_layout, $a, $b, $alpha, $beta; $(kwargs)...)
+        CUDA.cuStreamSynchronize(stream())
+    end
 end
 
 let group = addgroup!(group, "WMMA")
diff --git a/benchmarks/runbenchmarks.jl b/benchmarks/runbenchmarks.jl
index d54f4d08..f5fe2570 100644
--- a/benchmarks/runbenchmarks.jl
+++ b/benchmarks/runbenchmarks.jl
@@ -14,42 +14,55 @@ using StableRNGs
 # the effects of using newly-allocated memory.
 BenchmarkTools.DEFAULT_PARAMETERS.evals = 5
 
-@info "Loading previous benchmark results"
-github_token = get(ENV, "GITHUB_TOKEN", nothing)
-benchmark_results = mktempdir()
-if github_token === nothing
-    run(`$(git()) clone -q https://github.com/JuliaGPU/GemmKernels.jl -b benchmark-results $benchmark_results`)
-else
-    run(`$(git()) clone -q https://$github_token:x-oauth-basic@github.com/JuliaGPU/GemmKernels.jl -b benchmark-results $benchmark_results`)
+if haskey(ENV, "BUILDKITE_BRANCH")
+    @info "Loading previous benchmark results"
+    github_token = get(ENV, "GITHUB_TOKEN", nothing)
+    benchmark_results = mktempdir()
+    if github_token === nothing
+        run(`$(git()) clone -q https://github.com/JuliaGPU/GemmKernels.jl -b benchmark-results $benchmark_results`)
+    else
+        run(`$(git()) clone -q https://$github_token:x-oauth-basic@github.com/JuliaGPU/GemmKernels.jl -b benchmark-results $benchmark_results`)
+    end
+    run(`$(git()) -C $benchmark_results config --local user.name "JuliaGPU BenchmarkBot"`)
+    run(`$(git()) -C $benchmark_results config --local user.email "nobody@juliagpu.org"`)
 end
-run(`$(git()) -C $benchmark_results config --local user.name "JuliaGPU BenchmarkBot"`)
-run(`$(git()) -C $benchmark_results config --local user.email "nobody@juliagpu.org"`)
 
 # load timings
 function load_results()
-    proc = open(`$(git()) -C $benchmark_results log --first-parent --pretty=format:"%H" origin/master`)
-    while !eof(proc)
-        commit = readline(proc)
+    results_file = joinpath(@__DIR__, "reference-results.json")
+    details_file = joinpath(@__DIR__, "reference-details.json")
+    commit = "local"
 
-        details_file = joinpath(benchmark_results, "details-$commit.json")
-        details = if isfile(details_file)
-            json = JSON.parsefile(details_file)
-            # the named tuples got stored as dicts; convert them back to named tuples
-            reconstruct_details(d::Dict) = (; Dict(Symbol(k)=>v for (k,v) in d)...)
-            # the id arrays got stored as a string; parse them back
-            reconstruct_ids(d::Dict, f=identity) = Dict(eval(Meta.parse(k))=>f(v) for (k,v) in json)
-            reconstruct_ids(json, reconstruct_details)
-        else
-            nothing
-        end
+    if haskey(ENV, "BUILDKITE_BRANCH")
+        proc = open(`$(git()) -C $benchmark_results log --first-parent --pretty=format:"%H" origin/master`)
+        while !eof(proc)
+            commit = readline(proc)
 
-        results_file = joinpath(benchmark_results, "results-$commit.json")
-        if isfile(results_file)
-            timings = BenchmarkTools.load(results_file)[1]
-            close(proc)
-            return (; commit, timings, details)
+            details_file = joinpath(benchmark_results, "details-$commit.json")
+            results_file = joinpath(benchmark_results, "results-$commit.json")
+            if isfile(results_file)
+                break
+            end
         end
+        close(proc)
+    end
+
+    details = if isfile(details_file)
+        json = JSON.parsefile(details_file)
+        # the named tuples got stored as dicts; convert them back to named tuples
+        reconstruct_details(d::Dict) = (; Dict(Symbol(k)=>v for (k,v) in d)...)
+        # the id arrays got stored as a string; parse them back
+        reconstruct_ids(d::Dict, f=identity) = Dict(eval(Meta.parse(k))=>f(v) for (k,v) in json)
+        reconstruct_ids(json, reconstruct_details)
+    else
+        nothing
     end
+
+    if isfile(results_file)
+        timings = BenchmarkTools.load(results_file)[1]
+        return (; commit, timings, details)
+    end
+
     return nothing
 end
 previous_results = load_results()
@@ -103,6 +116,14 @@ if get(ENV, "BUILDKITE_BRANCH", nothing) == "master"
     run(`$(git()) -C $benchmark_results add $details_file`)
     run(`$(git()) -C $benchmark_results commit -q -m "Results for $commit."`)
     run(`$(git()) -C $benchmark_results push -q`)
+else
+    results_file = joinpath(@__DIR__, "results.json")
+    BenchmarkTools.save(results_file, timings)
+
+    details_file = joinpath(@__DIR__, "details.json")
+    open(details_file, "w") do io
+        JSON.print(io, details)
+    end
 end
 
 # result rendering functions
@@ -231,7 +252,7 @@ if previous_results !== nothing
     println(body)
 
     # comment on PR
-    if github_token !== nothing && get(ENV, "BUILDKITE_PULL_REQUEST", "false") !== "false"
+    if get(ENV, "BUILDKITE_PULL_REQUEST", "false") !== "false" && github_token !== nothing
         auth = GitHub.authenticate(github_token)
         repo = GitHub.repo("JuliaGPU/GemmKernels.jl"; auth)
         pr = parse(Int, ENV["BUILDKITE_PULL_REQUEST"])