Improved documentation
* Documented the use of the compiler directive .inst
* Updated the multi_isa section
* Resolves MLCE-1156
Change-Id: I6a04ac66bc244c3adc010e1f8545f2045992d6db
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10981
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/docs/user_guide/library.dox b/docs/user_guide/library.dox
index 4b54abe..5a337c3 100644
--- a/docs/user_guide/library.dox
+++ b/docs/user_guide/library.dox
@@ -1,5 +1,5 @@
///
-/// Copyright (c) 2017-2021, 2023 Arm Limited.
+/// Copyright (c) 2017-2021, 2023-2024 Arm Limited.
///
/// SPDX-License-Identifier: MIT
///
@@ -568,9 +568,14 @@
Selecting multi_isa when building Compute Library, will create a library that contains all the supported ISA features.
Based on the CPU support, the appropriate kernel will be selected at runtime for execution. Currently this option is
-supported in two configurations: (i) with armv8.2-a as the base architecture where all the supported ISA features are enabled and
-(ii) with armv8-a as the base architecture where only a subset of ISA features (everything except FP16 vector arithmetic)
-are enabled in the build.
+supported in two configurations: (i) with armv8.2-a (ii) with armv8-a. In both cases all the supported ISA features are enabled
+in the build.
+
+The arch option in a multi_isa build sets the minimum architecture required to run the resulting binary.
+For example a multi_isa build for armv8-a will run on any armv8-a or later, when the binary is executed on a armv8.2-a device
+it will use the additional cpu features present in this architecture: FP16 and dot product.
+In order to have a binary like this (multi_isa+armv8-a) the FP16 and dot product kernels in the library are compiled for the
+target armv8.2-a and all other common code for armv8-a.
@subsection architecture_experimental_per_operator_build Per-operator build