-
Notifications
You must be signed in to change notification settings - Fork 738
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.
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
[SYCL][COMPAT] Added 33 bit extend operations with and without saturation #13006
Conversation
|
||
#ifdef SYCL_EXT_ONEAPI_BFLOAT16_MATH_FUNCTIONS | ||
template <> | ||
inline sycl::ext::oneapi::bfloat16 clamp(sycl::ext::oneapi::bfloat16 val, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why not add these directly to the existing bfloat16 extension? So users don't need to mix and max namespaces?
https://github.com/intel/llvm/blob/sycl/sycl/doc/extensions/experimental/sycl_ext_oneapi_bfloat16_math_functions.asciidoc
This comment was marked as duplicate.
This comment was marked as duplicate.
Sorry, something went wrong.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I've added a TODO regarding this. If SYCL users need this type for clamp
, they should not go through the syclcompat version. If it gets added to the bfloat extension, it is sensible to remove this from syclcompat.
@intel/llvm-gatekeepers this is ready for merging, thanks |
Adds support for addition, substraction, min, and max operations extended from 32 to 33 bit.
Adds an extra API for each operation where a transform binaryop can be applied to the result of the defined
extend
operation.