diff options
| author | Florian Hahn <flo@fhahn.com> | 2020-02-26 16:54:49 +0000 |
|---|---|---|
| committer | Florian Hahn <flo@fhahn.com> | 2020-02-26 16:56:04 +0000 |
| commit | 456e9c2e14bc936100f1d84e7637122b306d8c4c (patch) | |
| tree | 13f21c9a510a745f7e7a824592d9c18d2e46e14f | |
| parent | 48d24465668b268ec0aa39b62cabab5ee50e961d (diff) | |
| download | bcm5719-llvm-456e9c2e14bc936100f1d84e7637122b306d8c4c.tar.gz bcm5719-llvm-456e9c2e14bc936100f1d84e7637122b306d8c4c.zip | |
[ReleaseNotes] Mention new matrix intrinsics.
Reviewers: anemet, Gerolf
Reviewed By: anemet
Differential Revision: https://reviews.llvm.org/D75161
| -rw-r--r-- | llvm/docs/LangRef.rst | 3 | ||||
| -rw-r--r-- | llvm/docs/ReleaseNotes.rst | 6 |
2 files changed, 9 insertions, 0 deletions
diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst index 0ae374de4b6..190c282eacc 100644 --- a/llvm/docs/LangRef.rst +++ b/llvm/docs/LangRef.rst @@ -14553,6 +14553,9 @@ Arguments: """""""""" The argument to this intrinsic must be a vector of floating-point values. + +.. _i_matrixintrinsics: + Matrix Intrinsics ----------------- diff --git a/llvm/docs/ReleaseNotes.rst b/llvm/docs/ReleaseNotes.rst index 60dd07ddb26..6ade99ab174 100644 --- a/llvm/docs/ReleaseNotes.rst +++ b/llvm/docs/ReleaseNotes.rst @@ -106,6 +106,12 @@ Non-comprehensive list of changes in this release still under heavy development and disabled by default, to enable an early run pass ``-mllvm -attributor-disable=false`` to an invocation of clang. +* New matrix math intrinsics have been added to LLVM + (see :ref:`LLVM Language Reference Manual <i_matrixintrinsics>`), together + with the LowerMatrixIntrinsics pass. The pass lowers matrix intrinsics + to a set of efficient vector instructions. The lowering pass is off + by default and can be enabled by passing ``-mllvm -enable-matrix`` to an + invocation of clang. Changes to the LLVM IR |
