Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Re-use pre-converted kernel arguments when launching kernels. #2472

Merged
merged 1 commit into from
Sep 18, 2024
Merged

Re-use pre-converted kernel arguments when launching kernels. #2472

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 22 additions & 11 deletions src/compiler/execution.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,7 +111,7 @@ macro cuda(ex...)
$kernel_tt = Tuple{map(Core.Typeof, $kernel_args)...}
$kernel = $cufunction($kernel_f, $kernel_tt; $(compiler_kwargs...))
if $launch
$kernel($(var_exprs...); $(call_kwargs...))
$kernel($kernel_args...; $(call_kwargs...), convert=Val(false))
end
$kernel
end
Expand Down Expand Up @@ -194,6 +194,13 @@ input object `x` as-is.

Do not add methods to this function, but instead extend the underlying Adapt.jl package and
register methods for the the `CUDA.KernelAdaptor` type.

!!! note

As an optimization, the compiler may choose not to call `cudaconvert` when it can prove
that the argument is already converted, by comparing against the type of the value that
the conversion would return. For semantically important conversions, ensure the type
of the value returned by `cudaconvert` is different from the input type.
"""
cudaconvert(arg) = adapt(KernelAdaptor(), arg)

Expand Down Expand Up @@ -238,15 +245,26 @@ function Base.show(io::IO, ::MIME"text/plain", k::AbstractKernel{F,TT}) where {F
print(io, "CUDA.$(nameof(typeof(k))) for $(k.f)($(join(TT.parameters, ", ")))")
end

@inline @generated function call(kernel::AbstractKernel{F,TT}, args...; call_kwargs...) where {F,TT}
@inline @generated function (kernel::AbstractKernel{F,TT})(args::Vararg{Any,N};
convert=Val(kernel isa HostKernel),
call_kwargs...) where {F,TT,N}
sig = Tuple{F, TT.parameters...} # Base.signature_type with a function type
args = (:(kernel.f), (:( args[$i] ) for i in 1:length(args))...)

# determine argument expressions
argexprs = [:(kernel.f)]
for i in 1:length(args)
if convert.parameters[1]
push!(argexprs, :(cudaconvert(args[$i])))
else
push!(argexprs, :(args[$i]))
end
end

# filter out arguments that shouldn't be passed
predicate = dt -> isghosttype(dt) || Core.Compiler.isconstType(dt)
to_pass = map(!predicate, sig.parameters)
call_t = Type[x[1] for x in zip(sig.parameters, to_pass) if x[2]]
call_args = Union{Expr,Symbol}[x[1] for x in zip(args, to_pass) if x[2]]
call_args = Union{Expr,Symbol}[x[1] for x in zip(argexprs, to_pass) if x[2]]

# replace non-isbits arguments (they should be unused, or compilation would have failed)
# alternatively, make it possible to `launch` with non-isbits arguments.
Expand Down Expand Up @@ -386,10 +404,6 @@ end
# cache of kernel instances
const _kernel_instances = Dict{Any, Any}()

function (kernel::HostKernel)(args::Vararg{Any,N}; threads::CuDim=1, blocks::CuDim=1, kwargs...) where {N}
call(kernel, map(cudaconvert, args)...; threads, blocks, kwargs...)
end

make_seed(::HostKernel) = Random.rand(UInt32)


Expand Down Expand Up @@ -420,9 +434,6 @@ No keyword arguments are supported.
DeviceKernel{F,tt}(f, fun, kernel_state())
end

@inline (kernel::DeviceKernel)(args::Vararg{Any,N}; kwargs...) where {N} =
call(kernel, args...; kwargs...)

# re-use the parent kernel's seed to avoid need for the RNG
make_seed(::DeviceKernel) = kernel_state().random_seed

Expand Down