rm CUDA page

mcabbott · mcabbott · commit 76fe48412c14 · 2022-11-30T08:26:16.000-05:00
diff --git a/docs/make.jl b/docs/make.jl
@@ -40,7 +40,6 @@ makedocs(
             "MLUtils.jl (`DataLoader`, ...)" => "data/mlutils.md",
             "Functors.jl (`fmap`, ...)" => "models/functors.md",
             "OneHotArrays.jl (`onehot`, ...)" => "data/onehot.md",
-            "CUDA.jl (`cu`, `CuIterator`, ...)" => "reference/CUDA.md",  # do we want this?
          ],
         "Tutorials" => [
         # These walk you through various tasks. It's fine if they overlap quite a lot.
diff --git a/docs/src/gpu.md b/docs/src/gpu.md
@@ -182,3 +182,29 @@ $ export CUDA_VISIBLE_DEVICES='0,1'
 
 
 More information for conditional use of GPUs in CUDA.jl can be found in its [documentation](https://cuda.juliagpu.org/stable/installation/conditional/#Conditional-use), and information about the specific use of the variable is described in the [Nvidia CUDA blog post](https://developer.nvidia.com/blog/cuda-pro-tip-control-gpu-visibility-cuda_visible_devices/).
+
+
+## CUDA Reference
+
+Arrays and iterators:
+
+```@docs
+CUDA.cu
+CUDA.CuIterator
+```
+
+Device settings:
+
+```@docs
+CUDA.allowscalar
+CUDA.functional
+CUDA.device
+CUDA.device!
+```
+
+For benchmarking:
+
+```@docs
+CUDA.@time
+CUDA.@sync
+```
diff --git a/docs/src/reference/CUDA.md b/docs/src/reference/CUDA.md
