[all-commits] [llvm/llvm-project] d29042: [ARM][MVE] Factor out an IntrinsicMX multiclass.
Simon Tatham via All-commits
all-commits at lists.llvm.org
Wed Dec 11 04:07:47 PST 2019
Branch: refs/heads/master
Home: https://github.com/llvm/llvm-project
Commit: d290424731ede31fd5fd75b929df8fe0adb547c7
https://github.com/llvm/llvm-project/commit/d290424731ede31fd5fd75b929df8fe0adb547c7
Author: Simon Tatham <simon.tatham at arm.com>
Date: 2019-12-11 (Wed, 11 Dec 2019)
Changed paths:
M clang/include/clang/Basic/arm_mve.td
M clang/include/clang/Basic/arm_mve_defs.td
Log Message:
-----------
[ARM][MVE] Factor out an IntrinsicMX multiclass.
Summary:
The ACLE intrinsics for MVE contain a lot of pairs of functions with
`_m` and `_x` in the name, wrapping a predicated MVE instruction which
only partially overwrites its output register. They have the common
pattern that the `_m` variant takes an initial argument called
'inactive', of the same type as the return value, supplying the input
value of the output register, so that lanes disabled by the
predication will be taken from that parameter; the `_x` variant omits
that initial argument, and simply sets it to undef.
That common pattern is simple enough to wrap into a multiclass, which
should save a lot of effort in setting up all the rest of the `_x`
variants. In this commit I introduce `multiclass IntrinsicMX` in
`arm_mve_defs.td`, and convert existing generation of m/x pairs to use
it.
This allows me to remove the `PredicatedImmediateVectorShift`
multiclass (from D71065) completely, because the new multiclass makes
it so much simpler that it's not worth bothering to define it at all.
Reviewers: MarkMurrayARM, miyuki
Reviewed By: MarkMurrayARM, miyuki
Subscribers: kristof.beyls, dmgreen, cfe-commits
Tags: #clang
Differential Revision: https://reviews.llvm.org/D71335
More information about the All-commits
mailing list