[Mlir-commits] [mlir] [mlir][ArmSME] Update docs (PR #74527)

[Andrzej Warzyński]

https://github.com/banach-space updated https://github.com/llvm/llvm-project/pull/74527

>From 34a84b685074337a9c53481402c4e16952f825a3 Mon Sep 17 00:00:00 2001
From: Andrzej Warzynski <andrzej.warzynski at arm.com>
Date: Tue, 5 Dec 2023 21:30:21 +0000
Subject: [PATCH 1/2] [mlir][sme] Update docs

---
 mlir/docs/Dialects/ArmSME.md | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/mlir/docs/Dialects/ArmSME.md b/mlir/docs/Dialects/ArmSME.md
index 505b52938eacc..4af1594c3933c 100644
--- a/mlir/docs/Dialects/ArmSME.md
+++ b/mlir/docs/Dialects/ArmSME.md
@@ -1,13 +1,28 @@
 # 'ArmSME' Dialect
 
-[TOC]
+Basic dialect to target Arm SME.
+
+This dialect defines custom and LLVM IR intrinsic operations that are used to
+target Arm Scalable Matrix Extension. Through the available lowerings one can,
+for example, lower a [linalg.matmul](https://mlir.llvm.org/docs/Dialects/Linalg/#linalgmatmul-linalgmatmulop)
+opereation to Arm SME
+[FMOPA](https://developer.arm.com/documentation/ddi0602/2023-03/SME-Instructions/FMOPA--widening---Half-precision-floating-point-sum-of-outer-products-and-accumulate-)
+(floating point outer product) operations. See one of the in-tree end-to-end
+integration tests for reference:
+
+* [Linalg/CPU/ArmSME/matmul.mlir](https://github.com/llvm/llvm-project/blob/main/mlir/test/Integration/Dialect/Linalg/CPU/ArmSME/matmul.mlir)
+* [Vector/CPU/ArmSME/test-outerproduct-f64.mlir](https://github.com/llvm/llvm-project/blob/main/mlir/test/Integration/Dialect/Vector/CPU/ArmSME/test-outerproduct-f64.mlir)
 
-Basic dialect to target Arm SME architectures This dialect contains the
-definitions necessary to target Arm SME scalable matrix operations.
+These tests are run "post-commit" by the
+[clang-aarch64-sve-vla](https://lab.llvm.org/buildbot/#/builders/197) LLVM
+BuildBot worker.
 
-## References
-* https://developer.arm.com/documentation/ddi0616
-* https://developer.arm.com/documentation/ddi0602/2023-03/SME-Instructions
+**References:**
+
+* [The Scalable Matrix Extension (SME), for Armv9-A](https://developer.arm.com/documentation/ddi0616)
+* [A64 -- SME Instructions (alphabetic order)](https://developer.arm.com/documentation/ddi0602/2023-03/SME-Instructions)
+
+[TOC]
 
 ## Operations
 

>From 55cc2341783faaaecdb9a1b2ddf91748650713dd Mon Sep 17 00:00:00 2001
From: Andrzej Warzynski <andrzej.warzynski at arm.com>
Date: Wed, 6 Dec 2023 21:17:33 +0000
Subject: [PATCH 2/2] fixup! [mlir][sme] Update docs

Address comments from Ben
---
 mlir/docs/Dialects/ArmSME.md | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/mlir/docs/Dialects/ArmSME.md b/mlir/docs/Dialects/ArmSME.md
index 4af1594c3933c..7326150bcd115 100644
--- a/mlir/docs/Dialects/ArmSME.md
+++ b/mlir/docs/Dialects/ArmSME.md
@@ -3,11 +3,12 @@
 Basic dialect to target Arm SME.
 
 This dialect defines custom and LLVM IR intrinsic operations that are used to
-target Arm Scalable Matrix Extension. Through the available lowerings one can,
-for example, lower a [linalg.matmul](https://mlir.llvm.org/docs/Dialects/Linalg/#linalgmatmul-linalgmatmulop)
+target Arm Scalable Matrix Extension. Through the available conversion and
+ArmSME passes you can, for example, lower a
+[linalg.matmul](https://mlir.llvm.org/docs/Dialects/Linalg/#linalgmatmul-linalgmatmulop)
 opereation to Arm SME
 [FMOPA](https://developer.arm.com/documentation/ddi0602/2023-03/SME-Instructions/FMOPA--widening---Half-precision-floating-point-sum-of-outer-products-and-accumulate-)
-(floating point outer product) operations. See one of the in-tree end-to-end
+(floating-point outer product) operations. See one of the in-tree end-to-end
 integration tests for reference:
 
 * [Linalg/CPU/ArmSME/matmul.mlir](https://github.com/llvm/llvm-project/blob/main/mlir/test/Integration/Dialect/Linalg/CPU/ArmSME/matmul.mlir)