-
Notifications
You must be signed in to change notification settings - Fork 60
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
Tweaks to the SME2 intrinsics #278
Tweaks to the SME2 intrinsics #278
Conversation
cc: @sdesmalen-arm |
This patch makes a few tweaks to the SME2 intrinsics: * The type suffix of the SME2 svread* intrinsics needs to be explicit (non-optional), since there is no merge input that can be used to infer it. * The zn argument to the svluti* intrinsics is a collection of 2-bit and 4-bit quantities, so it doesn't have a natural element size or signedness. It seems better to keep it as svuint8_t for all variants. * Because of that, there is no argument that implies the return type of the svluti* intrinsics, so the type suffix needs to be explicit. Also, since the instruction performs a bag-of-bits lookup, it makes sense to have floating-point variants too. * The ZA slice forms of svread* and svwrite* are likewise bag-of-bits moves, so we can provide alternatives for all element types. * arm_neon.h shift-by-immediate instructions use an _n suffix to indicate that the shift amount is scalar. arm_sve.h carried this across to the full/non-overloaded forms of SVE immediate shifts. It seems worth doing the same here for consistency, and to protect against vector-vector forms being added in future.
386b81f
to
250b019
Compare
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.
LGTM
uint64_t imm_idx) | ||
// Variants are also available for _zt_u16, _zt_f16, _zt_bf16, _zt_s32, | ||
// _zt_u32 and _zt_f32 | ||
svint16x4_t svluti4_lane_zt_s16_x4(uint64_t zt, svuint16_t zn, |
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.
Hi @rsandifo-arm,
Should the zn argument for the svluti4 x4 also be a svuint8_t?
This patch makes a few tweaks to the SME2 intrinsics: * The type suffix of the SME2 svread* intrinsics needs to be explicit (non-optional), since there is no merge input that can be used to infer it. * The zn argument to the svluti* intrinsics is a collection of 2-bit and 4-bit quantities, so it doesn't have a natural element size or signedness. It seems better to keep it as svuint8_t for all variants. * Because of that, there is no argument that implies the return type of the svluti* intrinsics, so the type suffix needs to be explicit. Also, since the instruction performs a bag-of-bits lookup, it makes sense to have floating-point variants too. * The ZA slice forms of svread* and svwrite* are likewise bag-of-bits moves, so we can provide alternatives for all element types. * arm_neon.h shift-by-immediate instructions use an _n suffix to indicate that the shift amount is scalar. arm_sve.h carried this across to the full/non-overloaded forms of SVE immediate shifts. It seems worth doing the same here for consistency, and to protect against vector-vector forms being added in future.
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.
No changes
This patch makes a few tweaks to the SME2 intrinsics:
The type suffix of the SME2 svread* intrinsics needs to be
explicit (non-optional), since there is no merge input that
can be used to infer it.
The zn argument to the svluti* intrinsics is a collection of
2-bit and 4-bit quantities, so it doesn't have a natural element
size or signedness. It seems better to keep it as svuint8_t for
all variants.
Because of that, there is no argument that implies the return
type of the svluti* intrinsics, so the type suffix needs to be
explicit. Also, since the instruction performs a bag-of-bits
lookup, it makes sense to have floating-point variants too.
The ZA slice forms of svread* and svwrite* are likewise
bag-of-bits moves, so we can provide alternatives for all
element types.
arm_neon.h shift-by-immediate instructions use an _n suffix
to indicate that the shift amount is scalar. arm_sve.h
carried this across to the full/non-overloaded forms of SVE
immediate shifts. It seems worth doing the same here for
consistency, and to protect against vector-vector forms
being added in future.
name: Pull request
about: Technical issues, document format problems, bugs in scripts or feature proposal.
Thank you for submitting a pull request!
If this PR is about a bugfix:
Please use the bugfix label and make sure to go through the checklist below.
If this PR is about a proposal:
We are looking forward to evaluate your proposal, and if possible to
make it part of the Arm C Language Extension (ACLE) specifications.
We would like to encourage you reading through the contribution
guidelines, in particular the section on submitting
a proposal.
Please use the proposal label.
As for any pull request, please make sure to go through the below
checklist.
Checklist: (mark with
X
those which apply)PR (do not bother creating the issue if all you want to do is
fixing the bug yourself).
SPDX-FileCopyrightText
lines on topof any file I have edited. Format is
SPDX-FileCopyrightText: Copyright {year} {entity or name} <{contact informations}>
(Please update existing copyright lines if applicable. You can
specify year ranges with hyphen , as in
2017-2019
, and usecommas to separate gaps, as in
2018-2020, 2022
).Copyright
section of the sources of thespecification I have edited (this will show up in the text
rendered in the PDF and other output format supported). The
format is the same described in the previous item.
tricky to set up on non-*nix machines). The sequence can be
found in the contribution
guidelines. Don't
worry if you cannot run these scripts on your machine, your
patch will be automatically checked in the Actions of the pull
request.
introduced in this PR in the section Changes for next
release of the section Change Control/Document history
of the document. Create Changes for next release if it does
not exist. Notice that changes that are not modifying the
content and rendering of the specifications (both HTML and PDF)
do not need to be listed.
correctness of the result in the PDF output (please refer to the
instructions on how to build the PDFs
locally).
draftversion
is set totrue
in the YAML headerof the sources of the specifications I have modified.
in the README page of the project.