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

Bump toolchain. #438

Merged
merged 3 commits into from
May 16, 2024
Merged

Bump toolchain. #438

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a241418
Bump toolchain.
maleadt May 15, 2024
9dd8cdf
Work around NEO not reporting MAX_GROUP_SIZE.
maleadt May 15, 2024
72bfd4e
Disable ZE_extension_kernel_max_group_size_properties under validation.
maleadt May 16, 2024
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
2 changes: 1 addition & 1 deletion Project.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ GPUArrays = "10"
GPUCompiler = "0.23, 0.24, 0.25, 0.26"
KernelAbstractions = "0.9.1"
LLVM = "6"
NEO_jll = "=24.09.28717"
NEO_jll = "=24.13.29138"
Preferences = "1"
SPIRV_LLVM_Translator_unified_jll = "0.4"
SpecialFunctions = "1.3, 2"
Expand Down
5 changes: 4 additions & 1 deletion lib/level-zero/module.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,7 +237,10 @@ function properties(kernel::ZeKernel)
preferred_group_size_props_ref = Ref(ze_kernel_preferred_group_size_properties_t())
link_extensions(props_ref, preferred_group_size_props_ref)
if haskey(oneL0.extension_properties(kernel.mod.context.driver),
"ZE_extension_kernel_max_group_size_properties")
"ZE_extension_kernel_max_group_size_properties") ||
(!validation_layer[] && # intel/compute-runtime#733
properties(kernel.mod.device).vendorId == 0x8086 &&
properties(kernel.mod.context.driver).driverVersion >= v"1.3.29138")
# TODO: memoize
max_group_size_props_ref = Ref(ze_kernel_max_group_size_properties_ext_t())
link_extensions(preferred_group_size_props_ref, max_group_size_props_ref)
Expand Down
6 changes: 6 additions & 0 deletions lib/level-zero/oneL0.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,6 +101,9 @@ include("residency.jl")

const functional = Ref{Bool}(false)

const validation_layer = Ref{Bool}()
const parameter_validation = Ref{Bool}()

function __init__()
precompiling = ccall(:jl_generating_output, Cint, ()) != 0
precompiling && return
Expand Down Expand Up @@ -132,6 +135,9 @@ function __init__()
functional[] = false
return
end

validation_layer[] = parse(Bool, get(ENV, "ZE_ENABLE_VALIDATION_LAYER", "false"))
parameter_validation[] = parse(Bool, get(ENV, "ZE_ENABLE_PARAMETER_VALIDATION", "false"))
end

end
2 changes: 1 addition & 1 deletion src/compiler/execution.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,11 +167,11 @@ function launch_configuration(kernel::HostKernel{F,TT}) where {F,TT}
# configurations, so roll our own version that behaves like CUDA's
# occupancy API and assumes the kernel still does bounds checking.

# once the MAX_GROUP_SIZE extension is implemented, we can use it here
kernel_props = oneL0.properties(kernel.fun)
group_size = if kernel_props.maxGroupSize !== missing
kernel_props.maxGroupSize
else
# without the MAX_GROUP_SIZE extension, we need to be conservative
dev = kernel.fun.mod.device
compute_props = oneL0.compute_properties(dev)
max_size = compute_props.maxTotalGroupSize
Expand Down