Skip to content

Enable AArch64 arithmetic on LLVM 19. #77

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

Merged
merged 1 commit into from
Aug 14, 2024
Merged

Enable AArch64 arithmetic on LLVM 19. #77

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
4 changes: 3 additions & 1 deletion src/bfloat16.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ import Printf
# However, not all LLVM targets support `bfloat`. If the target can store/load BFloat16s
# (and supports synthesizing constants) we can use the `bfloat` IR type, otherwise we fall
# back to defining a primitive type that will be represented as an `i16`. If, in addition,
# the target supports BFloat16 arithmetic, we can use LLVM intrinsics.
# the target supports BFloat16 arithmetic, we can use LLVM instructions.
# - x86: storage and arithmetic support in LLVM 15
# - aarch64: storage support in LLVM 17
const llvm_storage = if isdefined(Core, :BFloat16)
Expand All @@ -40,6 +40,8 @@ const llvm_arithmetic = if llvm_storage
using Core: BFloat16
if Sys.ARCH in [:x86_64, :i686] && Base.libllvm_version >= v"15"
true
elseif Sys.ARCH == :aarch64 && Base.libllvm_version >= v"19"
true
else
false
end
Expand Down