From 80fa61cf9d0371a67bf1f68064de504cba14730b Mon Sep 17 00:00:00 2001
From: Alexis Montoison <alexis.montoison@polymtl.ca>
Date: Thu, 7 Dec 2023 23:47:19 -0600
Subject: [PATCH] Add comments about using block-GMRES on GPUs

---
 docs/src/block_krylov.md  | 23 +++++++++++++++++++++++
 src/block_krylov_utils.jl | 14 --------------
 2 files changed, 23 insertions(+), 14 deletions(-)

diff --git a/docs/src/block_krylov.md b/docs/src/block_krylov.md
index 2db83c839..428b1ca35 100644
--- a/docs/src/block_krylov.md
+++ b/docs/src/block_krylov.md
@@ -1,5 +1,28 @@
 ## Block-GMRES
 
+!!! note
+    `block_gmres` works on GPUs
+     with Julia 1.11.
+
+If you want to use `block_gmres` on previous Julia versions, you can overload the function `Krylov.copy_triangle` with the following code:
+```julia
+using KernelAbstractions, Krylov
+
+@kernel function copy_triangle_kernel!(dest, src)
+  i, j = @index(Global, NTuple)
+  if j >= i
+    @inbounds dest[i, j] = src[i, j]
+  end
+end
+
+function Krylov.copy_triangle(Q::AbstractMatrix{FC}, R::AbstractMatrix{FC}, k::Int) where FC <: Krylov.FloatOrComplex
+  backend = get_backend(Q)
+  ndrange = (k, k)
+  copy_triangle_kernel!(backend)(R, Q; ndrange=ndrange)
+  KernelAbstractions.synchronize(backend)
+end
+```
+
 ```@docs
 block_gmres
 block_gmres!
diff --git a/src/block_krylov_utils.jl b/src/block_krylov_utils.jl
index c09071fa4..68ba46458 100644
--- a/src/block_krylov_utils.jl
+++ b/src/block_krylov_utils.jl
@@ -156,20 +156,6 @@ function reduced_qr(A::AbstractMatrix{FC}, algo::String) where FC <: FloatOrComp
   return Q, R
 end
 
-# @kernel function copy_triangle_kernel!(dest, src)
-#   i, j = @index(Global, NTuple)
-#   if j >= i
-#     @inbounds dest[i, j] = src[i, j]
-#   end
-# end
-
-# function copy_triangle(Q::AbstractMatrix{FC}, R::AbstractMatrix{FC}, k::Int) where FC <: FloatOrComplex
-#   backend = get_backend(Q)
-#   ndrange = (k, k)
-#   copy_triangle_kernel!(backend)(R, Q; ndrange=ndrange)
-#   KernelAbstractions.synchronize(backend)
-# end
-
 function copy_triangle(Q::AbstractMatrix{FC}, R::AbstractMatrix{FC}, k::Int) where FC <: FloatOrComplex
   if VERSION < v"1.11"
     for i = 1:k