Move GPU support into Dagger

.buildkite/pipeline.yml

@@ -7,6 +7,9 @@
     arch: x86_64
   command: "julia --project -e 'using Pkg; Pkg.develop(;path=\"lib/TimespanLogging\")'"
 
+.gputest: &gputest
+  if: build.message !~ /\[skip tests\]/
+
 .bench: &bench
   if: build.message =~ /\[run benchmarks\]/
   agents:
@@ -87,6 +90,83 @@ steps:
       - JuliaCI/julia-coverage#v1:
           codecov: true
 
+  - label: Julia 1.11 (CUDA)
+    timeout_in_minutes: 20
+    <<: *gputest
+    plugins:
+      - JuliaCI/julia#v1:
+          version: "1.11"
+      - JuliaCI/julia-test#v1: ~
+      - JuliaCI/julia-coverage#v1:
+          codecov: true
+    agents:
+      queue: "juliagpu"
+      cuda: "*"
+    env:
+      CI_USE_CUDA: "1"
+
+  - label: Julia 1.11 (ROCm)
+    timeout_in_minutes: 20
+    <<: *gputest
+    plugins:
+      - JuliaCI/julia#v1:
+          version: "1.11"
+      - JuliaCI/julia-test#v1: ~
+      - JuliaCI/julia-coverage#v1:
+          codecov: true
+    agents:
+      queue: "juliagpu"
+      rocm: "*"
+    env:
+      CI_USE_ROCM: "1"
+
+  - label: Julia 1.11 (oneAPI)
+    timeout_in_minutes: 20
+    <<: *gputest
+    plugins:
+      - JuliaCI/julia#v1:
+          version: "1.11"
+      - JuliaCI/julia-test#v1: ~
+      - JuliaCI/julia-coverage#v1:
+          codecov: true
+    agents:
+      queue: "juliagpu"
+      intel: "*"
+    env:
+      CI_USE_ONEAPI: "1"
+
+  - label: Julia 1.11 (Metal)
+    timeout_in_minutes: 20
+    <<: *gputest
+    plugins:
+      - JuliaCI/julia#v1:
+          version: "1.11"
+      - JuliaCI/julia-test#v1: ~
+      - JuliaCI/julia-coverage#v1:
+          codecov: true
+    agents:
+      queue: "juliaecosystem"
+      os: "macos"
+      arch: "aarch64"
+    env:
+      CI_USE_METAL: "1"
+
+  - label: Julia 1.11 (OpenCL)
+    timeout_in_minutes: 20
+    <<: *gputest
+    plugins:
+      - JuliaCI/julia#v1:
+          version: "1.11"
+      - JuliaCI/julia-test#v1:
+      - JuliaCI/julia-coverage#v1:
+          codecov: true
+    agents:
+      queue: "juliaecosystem"
+      os: linux
+      arch: x86_64
+    env:
+      CI_USE_OPENCL: "1"
+
   - label: Julia 1 - TimespanLogging
     timeout_in_minutes: 20
     <<: *test

Project.toml

@@ -7,7 +7,9 @@ Adapt = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
 DataStructures = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
 Distributed = "8ba89e20-285c-5b6f-9357-94700520ee1b"
 DistributedNext = "fab6aee4-877b-4bac-a744-3eca44acbb6f"
+FillArrays = "1a297f60-69ca-5386-bcde-b61e274b549b"
 Graphs = "86223c79-3864-5bf0-83f7-82e725a168b6"
+KernelAbstractions = "63c18a36-062a-441e-b654-da1e3ab1ce7c"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 MacroTools = "1914dd2f-81c6-5fcd-8719-6d5c9610ff09"
 MemPool = "f9f48841-c794-520a-933b-121f7ba6ed94"
@@ -28,35 +30,52 @@ TimespanLogging = "a526e669-04d3-4846-9525-c66122c55f63"
 UUIDs = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
 
 [weakdeps]
+AMDGPU = "21141c5a-9bdb-4563-92ae-f87d6854732e"
+CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
 Colors = "5ae59095-9a9b-59fe-a467-6f913c188581"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"
 GraphViz = "f526b714-d49f-11e8-06ff-31ed36ee7ee0"
 JSON3 = "0f8b85d8-7281-11e9-16c2-39a750bddbf1"
+Metal = "dde4c033-4e86-420c-a63e-0dd931031962"
+OpenCL = "08131aa3-fb12-5dee-8b74-c09406e224a2"
+oneAPI = "8f75cd03-7ff8-4ecb-9b8f-daf728133b1b"
 Plots = "91a5bcdd-55d7-5caf-9e0b-520d859cae80"
 PythonCall = "6099a3de-0909-46bc-b1f4-468b9a2dfc0d"
 
 [extensions]
+CUDAExt = "CUDA"
 DistributionsExt = "Distributions"
 GraphVizExt = "GraphViz"
 GraphVizSimpleExt = "Colors"
+IntelExt = "oneAPI"
 JSON3Ext = "JSON3"
+MetalExt = "Metal"
+OpenCLExt = "OpenCL"
 PlotsExt = ["DataFrames", "Plots"]
 PythonExt = "PythonCall"
+ROCExt = "AMDGPU"
 
 [compat]
-Adapt = "4.0.4"
+AMDGPU = "1"
+Adapt = "4"
+CUDA = "3, 4, 5"
 Colors = "0.12, 0.13"
 DataFrames = "1"
 DataStructures = "0.18"
 DistributedNext = "1.0.0"
 Distributions = "0.25"
+FillArrays = "1.13.0"
 GraphViz = "0.2"
 Graphs = "1"
 JSON3 = "1"
+KernelAbstractions = "0.9"
 MacroTools = "0.5"
 MemPool = "0.4.12"
+Metal = "1.1"
 OnlineStats = "1"
+OpenCL = "0.10"
+oneAPI = "1, 2"
 Plots = "1"
 PrecompileTools = "1.2"
 Preferences = "1.4.3"

docs/make.jl

@@ -27,6 +27,7 @@ makedocs(;
         "Processors" => "processors.md",
         "Task Queues" => "task-queues.md",
         "Datadeps" => "datadeps.md",
+        "GPUs" => "gpu.md",
         "Option Propagation" => "propagation.md",
         "Logging and Visualization" => [
             "Logging: Basics" => "logging.md",