From 2739bfa4bcc229d309eedf6f239328881f91b4cc Mon Sep 17 00:00:00 2001
From: Claudio Bantaloukas <claudio.bantaloukas@arm.com>
Date: Thu, 5 Feb 2026 11:01:10 +0000
Subject: [PATCH 1/8] Update copyright dates

---
 main/acle.md                                  | 2 +-
 neon_intrinsics/advsimd.md                    | 2 +-
 neon_intrinsics/advsimd.template.md           | 2 +-
 tools/intrinsic_db/advsimd.csv                | 2 +-
 tools/intrinsic_db/advsimd_classification.csv | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/main/acle.md b/main/acle.md
index f6d4878f..b8d8d4ca 100644
--- a/main/acle.md
+++ b/main/acle.md
@@ -11,7 +11,7 @@ toc: true
 ---
 
 <!--
-SPDX-FileCopyrightText: Copyright 2011-2025 Arm Limited and/or its affiliates <open-source-office@arm.com>
+SPDX-FileCopyrightText: Copyright 2011-2026 Arm Limited and/or its affiliates <open-source-office@arm.com>
 SPDX-FileCopyrightText: Copyright 2022 Google LLC.
 CC-BY-SA-4.0 AND Apache-Patent-License
 See LICENSE.md file for details
diff --git a/neon_intrinsics/advsimd.md b/neon_intrinsics/advsimd.md
index 630ca2c6..37793135 100644
--- a/neon_intrinsics/advsimd.md
+++ b/neon_intrinsics/advsimd.md
@@ -12,7 +12,7 @@ toc: true
 ---
 
 <!--
-SPDX-FileCopyrightText: Copyright 2014-2025 Arm Limited and/or its affiliates <open-source-office@arm.com>
+SPDX-FileCopyrightText: Copyright 2014-2026 Arm Limited and/or its affiliates <open-source-office@arm.com>
 SPDX-FileCopyrightText: Copyright 2021 Matt P. Dziubinski <matdzb@gmail.com>
 CC-BY-SA-4.0 AND Apache-Patent-License
 See LICENSE.md file for details
diff --git a/neon_intrinsics/advsimd.template.md b/neon_intrinsics/advsimd.template.md
index 336378db..67778062 100644
--- a/neon_intrinsics/advsimd.template.md
+++ b/neon_intrinsics/advsimd.template.md
@@ -12,7 +12,7 @@ toc: true
 ---
 
 <!--
-SPDX-FileCopyrightText: Copyright 2014-2025 Arm Limited and/or its affiliates <open-source-office@arm.com>
+SPDX-FileCopyrightText: Copyright 2014-2026 Arm Limited and/or its affiliates <open-source-office@arm.com>
 SPDX-FileCopyrightText: Copyright 2021 Matt P. Dziubinski <matdzb@gmail.com>
 CC-BY-SA-4.0 AND Apache-Patent-License
 See LICENSE.md file for details
diff --git a/tools/intrinsic_db/advsimd.csv b/tools/intrinsic_db/advsimd.csv
index 5922fcad..0447f568 100644
--- a/tools/intrinsic_db/advsimd.csv
+++ b/tools/intrinsic_db/advsimd.csv
@@ -1,4 +1,4 @@
-<COMMENT>	SPDX-FileCopyrightText: Copyright 2014-2025 Arm Limited <open-source-office@arm.com>
+<COMMENT>	SPDX-FileCopyrightText: Copyright 2014-2026 Arm Limited <open-source-office@arm.com>
 <COMMENT>	SPDX-FileCopyrightText: Copyright 2021 Matt P. Dziubinski <matdzb@gmail.com>
 <COMMENT>	SPDX-License-Identifier: Apache-2.0
 <COMMENT>	
diff --git a/tools/intrinsic_db/advsimd_classification.csv b/tools/intrinsic_db/advsimd_classification.csv
index 1b0f0da8..cf10d904 100644
--- a/tools/intrinsic_db/advsimd_classification.csv
+++ b/tools/intrinsic_db/advsimd_classification.csv
@@ -1,4 +1,4 @@
-<COMMENT>	SPDX-FileCopyrightText: Copyright 2021, 2024 Arm Limited <open-source-office@arm.com>
+<COMMENT>	SPDX-FileCopyrightText: Copyright 2021-2026 Arm Limited <open-source-office@arm.com>
 <COMMENT>	SPDX-License-Identifier: Apache-2.0
 <COMMENT>	
 <COMMENT>	Licensed under the Apache License, Version 2.0 (the "License");

From a057be62eb5facc77cea1975e0fadbb0e21e63cc Mon Sep 17 00:00:00 2001
From: Claudio Bantaloukas <claudio.bantaloukas@arm.com>
Date: Thu, 5 Feb 2026 11:12:09 +0000
Subject: [PATCH 2/8] Add alpha support for 9.7 dot product intrinsics

This change adds
- AdvSIMD dot intrinsics available under FEAT_F16F32DOT
- SVE dot intrinsics available under either FEAT_SVE2p3 || FEAT_SME2p3
---
 main/acle.md                                  | 28 +++++++++++++++++--
 neon_intrinsics/advsimd.md                    | 17 +++++++++++
 neon_intrinsics/advsimd.template.md           |  4 +++
 tools/intrinsic_db/advsimd.csv                |  7 +++++
 tools/intrinsic_db/advsimd_classification.csv |  4 +++
 5 files changed, 58 insertions(+), 2 deletions(-)

diff --git a/main/acle.md b/main/acle.md
index b8d8d4ca..d7f44d7d 100644
--- a/main/acle.md
+++ b/main/acle.md
@@ -487,6 +487,9 @@ Armv8.4-A [[ARMARMv84]](#ARMARMv84). Support is added for the Dot Product intrin
 * Removed all references to Transactional Memory Extension (TME).
 * Added [**Alpha**](#current-status-and-anticipated-changes) support
   for Brain 16-bit floating-point vector multiplication intrinsics.
+* Added [**Alpha**](#current-status-and-anticipated-changes)
+  support for SVE2.3 (FEAT_SVE2p3), SME2.3 (FEAT_SME2p3), FEAT_F16F32DOT
+  dot product intrinsics.
 
 ### References
 
@@ -2003,6 +2006,10 @@ are available. This implies that `__ARM_FEATURE_SVE` is nonzero.
  are available and if the associated [ACLE features]
 (#sme-language-extensions-and-intrinsics) are supported.
 
+`__ARM_FEATURE_SVE2p3` is defined to 1 if the FEAT_SVE2p3 instructions
+ are available and if the associated [ACLE features]
+(#sme-language-extensions-and-intrinsics) are supported.
+
 #### NEON-SVE Bridge macro
 
 `__ARM_NEON_SVE_BRIDGE` is defined to 1 if the [`<arm_neon_sve_bridge.h>`](#arm_neon_sve_bridge.h)
@@ -2026,6 +2033,7 @@ of SME has an associated preprocessor macro, given in the table below:
 | FEAT_SME2   | __ARM_FEATURE_SME2         |
 | FEAT_SME2p1 | __ARM_FEATURE_SME2p1       |
 | FEAT_SME2p2 | __ARM_FEATURE_SME2p2       |
+| FEAT_SME2p3 | __ARM_FEATURE_SME2p3       |
 
 Each macro is defined if there is hardware support for the associated
 architecture feature and if all of the [ACLE
@@ -2380,6 +2388,18 @@ this implies:
 
   * `__ARM_NEON == 1`
 
+#### Half-precision to single-precision dot product extension
+
+This section is in
+[**Alpha** state](#current-status-and-anticipated-changes) and might change or be
+extended in the future.
+
+`__ARM_FEATURE_F16F32DOT` is defined if the half-precision dot product
+accumulating to single-precision instructions are supported and the vector
+intrinsics are available. Note that this implies:
+
+  * `__ARM_NEON == 1`
+
 #### Complex number intrinsics
 
 `__ARM_FEATURE_COMPLEX` is defined if the complex addition and complex
@@ -2662,6 +2682,7 @@ be found in [[BA]](#BA).
 | [`__ARM_FEATURE_DIRECTED_ROUNDING`](#directed-rounding)                                                                                                 | Directed Rounding                                                                                  | 1           |
 | [`__ARM_FEATURE_DOTPROD`](#availability-of-dot-product-intrinsics)                                                                                      | Dot product extension (ARM v8.2-A)                                                                 | 1           |
 | [`__ARM_FEATURE_DSP`](#dsp-instructions)                                                                                                                | DSP instructions (Arm v5E) (32-bit-only)                                                           | 1           |
+| [`__ARM_FEATURE_F16F32DOT`](#half-precision-to-single-precision-dot-product-extension)                                                                  | Half-precision to single-precision dot product extension (FEAT_F16F32DOT)                          | 1           |
 | [`__ARM_FEATURE_FAMINMAX`](#floating-point-absolute-minimum-and-maximum-extension)                                                                      | Floating-point absolute minimum and maximum extension                                              | 1           |
 | [`__ARM_FEATURE_FMA`](#fused-multiply-accumulate-fma)                                                                                                   | Floating-point fused multiply-accumulate                                                           | 1           |
 | [`__ARM_FEATURE_FP16_FML`](#fp16-fml-extension)                                                                                                         | FP16 FML extension (Arm v8.4-A, optional Armv8.2-A, Armv8.3-A)                                     | 1           |
@@ -2737,6 +2758,7 @@ be found in [[BA]](#BA).
 | [`__ARM_FEATURE_SVE2_SM4`](#sm4-extension)                                                                                                              | SVE2 support for the SM4 cryptographic extension (FEAT_SVE_SM4)                                     | 1           |
 | [`__ARM_FEATURE_SVE2p1`](#sve2)                                                                                                                         | SVE version 2.1 (FEAT_SVE2p1)
 | [`__ARM_FEATURE_SVE2p2`](#sve2)                                                                                                                         | SVE version 2.2 (FEAT_SVE2p2)
+| [`__ARM_FEATURE_SVE2p3`](#sve2)                                                                                                                         | SVE version 2.3 (FEAT_SVE2p3)
 | [`__ARM_FEATURE_SYSREG128`](#bit-system-registers)                                                                                                      | Support for 128-bit system registers (FEAT_SYSREG128)                                              | 1           |
 | [`__ARM_FEATURE_UNALIGNED`](#unaligned-access-supported-in-hardware)                                                                                    | Hardware support for unaligned access                                                              | 1           |
 | [`__ARM_FP`](#hardware-floating-point)                                                                                                                  | Hardware floating-point                                                                            | 1           |
@@ -13281,7 +13303,8 @@ Set scalar to count from predicate-as-counter. ``vl`` is expected to be 2 or 4.
 Multi-vector dot-product (2-way)
 
 ``` c
-  // Variants are also available for _s32_s16 and _u32_u16
+  // Variants are also available for _s32_s16, _u32_u16
+  // and also for _s16_s8 and _u16_u8 if (__ARM_FEATURE_SVE2p3 __ARM || _FEATURE_SME2p3).
   svfloat32_t svdot[_f32_f16](svfloat32_t zda, svfloat16_t zn,
                               svfloat16_t zm);
   svfloat32_t svdot[_n_f32_f16](svfloat32_t zda, svfloat16_t zn,
@@ -13293,7 +13316,8 @@ Multi-vector dot-product (2-way)
 Multi-vector dot-product (2-way)
 
 ``` c
-  // Variants are also available for _s32_s16 and _u32_u16
+  // Variants are also available for _s32_s16, _u32_u16
+  // and also for _s16_s8 and _u16_u8  if (__ARM_FEATURE_SVE2p3 __ARM || _FEATURE_SME2p3).
   svfloat32_t svdot_lane[_f32_f16](svfloat32_t zda, svfloat16_t zn,
                                    svfloat16_t zm, uint64_t imm_idx);
   ```
diff --git a/neon_intrinsics/advsimd.md b/neon_intrinsics/advsimd.md
index 37793135..e20fc963 100644
--- a/neon_intrinsics/advsimd.md
+++ b/neon_intrinsics/advsimd.md
@@ -169,6 +169,10 @@ for more information about Arm’s trademarks.
   floating point conversion intrinsics from "Half Precision to 32-bit"
   and "Half Precision to 64-bit".
 
+### Changes for next release
+
+* Added support for FEAT_F16F32DOT
+
 <!---
 **** Do not remove! ****
 The line following this comment is necessary to generate custom geometry settings
@@ -6213,3 +6217,16 @@ The intrinsics in this section are guarded by the macro ``__ARM_NEON``.
 |---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------|-------------------------------|-------------------|---------------------------|
 | <code>float16x8_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vmmlaq_f16_mf8_fpm" target="_blank">vmmlaq_f16_mf8_fpm</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; mfloat8x16_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; mfloat8x16_t b,<br>&nbsp;&nbsp;&nbsp;&nbsp; fpm_t fpm)</code> | `r -> Vd.8H`<br>`a -> Vn.16B`<br>`b -> Vm.16B` | `FMMLA Vd.8H, Vn.16B, Vm.16B` | `Vd.8H -> result` | `A64`                     |
 | <code>float32x4_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vmmlaq_f32_mf8_fpm" target="_blank">vmmlaq_f32_mf8_fpm</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float32x4_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; mfloat8x16_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; mfloat8x16_t b,<br>&nbsp;&nbsp;&nbsp;&nbsp; fpm_t fpm)</code> | `r -> Vd.4S`<br>`a -> Vn.16B`<br>`b -> Vm.16B` | `FMMLA Vd.4S, Vn.16B, Vm.16B` | `Vd.4S -> result` | `A64`                     |
+
+## Half-precision dot product to single-precision instructions from Armv9.7-A. Requires the +f16f32dot architecture extension.
+
+### Vector arithmetic
+
+#### Dot product
+
+| Intrinsic                                                                                                                                                                                                                                                                                                                                        | Argument preparation                                             | AArch64 Instruction            | Result            | Supported architectures   |
+|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------|--------------------------------|-------------------|---------------------------|
+| <code>float32x2_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vfdot_f32_f16" target="_blank">vfdot_f32_f16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float32x2_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x4_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x4_t b)</code>                                                         | `r -> Vd.2S`<br>`a -> Vn.4H`<br>`b -> Vm.4H`                     | `FDOT Vd.2S,Vn.4H,Vm.4H`       | `Vd.2S -> result` | `A64`                     |
+| <code>float32x4_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vfdotq_f32_f16" target="_blank">vfdotq_f32_f16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float32x4_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t b)</code>                                                       | `r -> Vd.4S`<br>`a -> Vn.8H`<br>`b -> Vm.8H`                     | `FDOT Vd.4S,Vn.8H,Vm.8H`       | `Vd.4S -> result` | `A64`                     |
+| <code>float32x2_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vfdot_lane_f32_f16" target="_blank">vfdot_lane_f32_f16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float32x2_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x4_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x2_t b,<br>&nbsp;&nbsp;&nbsp;&nbsp; const int lane)</code>   | `r -> Vd.2S`<br>`a -> Vn.4H`<br>`b -> Vm.2H`<br>`0 <= lane <= 3` | `FDOT Vd.2S,Vn.4H,Vm.2H[lane]` | `Vd.2S -> result` | `A64`                     |
+| <code>float32x4_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vfdotq_lane_f32_f16" target="_blank">vfdotq_lane_f32_f16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float32x4_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x2_t b,<br>&nbsp;&nbsp;&nbsp;&nbsp; const int lane)</code> | `r -> Vd.4S`<br>`a -> Vn.8H`<br>`b -> Vm.2H`<br>`0 <= lane <= 3` | `FDOT Vd.4S,Vn.8H,Vm.2H[lane]` | `Vd.4S -> result` | `A64`                     |
diff --git a/neon_intrinsics/advsimd.template.md b/neon_intrinsics/advsimd.template.md
index 67778062..d7081d09 100644
--- a/neon_intrinsics/advsimd.template.md
+++ b/neon_intrinsics/advsimd.template.md
@@ -169,6 +169,10 @@ for more information about Arm’s trademarks.
   floating point conversion intrinsics from "Half Precision to 32-bit"
   and "Half Precision to 64-bit".
 
+### Changes for next release
+
+* Added support for FEAT_F16F32DOT
+
 <!---
 **** Do not remove! ****
 The line following this comment is necessary to generate custom geometry settings
diff --git a/tools/intrinsic_db/advsimd.csv b/tools/intrinsic_db/advsimd.csv
index 0447f568..2fa0d97c 100644
--- a/tools/intrinsic_db/advsimd.csv
+++ b/tools/intrinsic_db/advsimd.csv
@@ -4834,3 +4834,10 @@ float32x4_t vmlallttq_laneq_f32_mf8_fpm(float32x4_t vd, mfloat8x16_t vn, mfloat8
 <SECTION>	Matrix multiplication intrinsics from Armv9.6-A
 float16x8_t vmmlaq_f16_mf8_fpm(float16x8_t r, mfloat8x16_t a, mfloat8x16_t b, fpm_t fpm)	r -> Vd.8H;a -> Vn.16B;b -> Vm.16B	FMMLA Vd.8H, Vn.16B, Vm.16B	Vd.8H -> result	A64
 float32x4_t vmmlaq_f32_mf8_fpm(float32x4_t r, mfloat8x16_t a, mfloat8x16_t b, fpm_t fpm)	r -> Vd.4S;a -> Vn.16B;b -> Vm.16B	FMMLA Vd.4S, Vn.16B, Vm.16B	Vd.4S -> result	A64
+
+<SECTION>	Half-precision dot product to single-precision instructions from Armv9.7-A. Requires the +f16f32dot architecture extension.
+float32x2_t vfdot_f32_f16(float32x2_t r, float16x4_t a, float16x4_t b)	r -> Vd.2S;a -> Vn.4H;b -> Vm.4H	FDOT Vd.2S,Vn.4H,Vm.4H	Vd.2S -> result	A64
+float32x4_t vfdotq_f32_f16(float32x4_t r, float16x8_t a, float16x8_t b)	r -> Vd.4S;a -> Vn.8H;b -> Vm.8H	FDOT Vd.4S,Vn.8H,Vm.8H	Vd.4S -> result	A64
+
+float32x2_t vfdot_lane_f32_f16(float32x2_t r, float16x4_t a, float16x2_t b, __builtin_constant_p(lane))	r -> Vd.2S;a -> Vn.4H;b -> Vm.2H;0 <= lane <= 3	FDOT Vd.2S,Vn.4H,Vm.2H[lane]	Vd.2S -> result	A64
+float32x4_t vfdotq_lane_f32_f16(float32x4_t r, float16x8_t a, float16x2_t b, __builtin_constant_p(lane))	r -> Vd.4S;a -> Vn.8H;b -> Vm.2H;0 <= lane <= 3	FDOT Vd.4S,Vn.8H,Vm.2H[lane]	Vd.4S -> result	A64
diff --git a/tools/intrinsic_db/advsimd_classification.csv b/tools/intrinsic_db/advsimd_classification.csv
index cf10d904..a30df166 100644
--- a/tools/intrinsic_db/advsimd_classification.csv
+++ b/tools/intrinsic_db/advsimd_classification.csv
@@ -4719,3 +4719,7 @@ vmlallttq_lane_f32_mf8_fpm	Vector arithmetic|Multiply|Multiply-accumulate and wi
 vmlallttq_laneq_f32_mf8_fpm	Vector arithmetic|Multiply|Multiply-accumulate and widen
 vmmlaq_f16_mf8_fpm	Vector arithmetic|Matrix multiply
 vmmlaq_f32_mf8_fpm	Vector arithmetic|Matrix multiply
+vfdot_f32_f16	Vector arithmetic|Dot product
+vfdotq_f32_f16	Vector arithmetic|Dot product
+vfdot_lane_f32_f16	Vector arithmetic|Dot product
+vfdotq_lane_f32_f16	Vector arithmetic|Dot product

From d3f2e4e0ae9748b6cd1df7531eb4effa74e18380 Mon Sep 17 00:00:00 2001
From: Claudio Bantaloukas <claudio.bantaloukas@arm.com>
Date: Thu, 5 Feb 2026 11:17:46 +0000
Subject: [PATCH 3/8] Add alpha support for 9.7 mmla intrinsics

This change adds
- AdvSIMD intrinsics based on FMMLA available under FEAT_F16F32MM and FEAT_F16MM
- SVE intrinsics available under either FEAT_F16MM and FEAT_SVE_B16MM
---
 main/acle.md                                  | 43 +++++++++++++++++++
 neon_intrinsics/advsimd.md                    | 21 +++++++++
 tools/intrinsic_db/advsimd.csv                |  6 +++
 tools/intrinsic_db/advsimd_classification.csv |  2 +
 4 files changed, 72 insertions(+)

diff --git a/main/acle.md b/main/acle.md
index d7f44d7d..6e338100 100644
--- a/main/acle.md
+++ b/main/acle.md
@@ -490,6 +490,8 @@ Armv8.4-A [[ARMARMv84]](#ARMARMv84). Support is added for the Dot Product intrin
 * Added [**Alpha**](#current-status-and-anticipated-changes)
   support for SVE2.3 (FEAT_SVE2p3), SME2.3 (FEAT_SME2p3), FEAT_F16F32DOT
   dot product intrinsics.
+* Added [**Alpha**](#current-status-and-anticipated-changes)
+  support for FEAT_F16F32MM, FEAT_F16MM and FEAT_SVE_B16MM mmla intrinsics.
 
 ### References
 
@@ -2170,6 +2172,20 @@ See [Half-precision brain
 floating-point](#half-precision-brain-floating-point) for details
 of half-precision brain floating-point types.
 
+#### Brain 16-bit floating-point matrix multiplication support
+
+This section is in
+[**Alpha** state](#current-status-and-anticipated-changes) and might change or be
+extended in the future.
+
+`__ARM_FEATURE_SVE_B16MM` is defined to `1` if there is hardware
+support for the SVE BF16 matrix multiply extension and if the
+associated ACLE intrinsics are available.
+
+See [Half-precision brain
+floating-point](#half-precision-brain-floating-point) for details
+of half-precision brain floating-point types.
+
 ### Cryptographic extensions
 
 #### “Crypto” extension
@@ -2445,6 +2461,21 @@ instructions and if the associated ACLE intrinsics are available.
 for the SVE 16-bit floating-point to 32-bit floating-point matrix multiply and add
 (FEAT_SVE_F16F32MM) instructions and if the associated ACLE intrinsics are available.
 
+##### Multiplication of 16-bit floating-point matrices (AdvSIMD)
+
+This section is in
+[**Alpha** state](#current-status-and-anticipated-changes) and might change or be
+extended in the future.
+
+`__ARM_FEATURE_F16F32MM` is defined if the NEON half-precision matrix multiply
+accumulating to single-precision instruction is supported. Note that this implies:
+
+  * `__ARM_NEON == 1`
+
+`__ARM_FEATURE_F16MM` is defined if the NEON non-widening half-precision matrix multiply instruction instruction is supported. Note that this implies:
+
+  * `__ARM_NEON == 1`
+
 ##### Multiplication of 32-bit floating-point matrices
 
 `__ARM_FEATURE_SVE_MATMUL_FP32` is defined to `1` if there is hardware support
@@ -2683,6 +2714,8 @@ be found in [[BA]](#BA).
 | [`__ARM_FEATURE_DOTPROD`](#availability-of-dot-product-intrinsics)                                                                                      | Dot product extension (ARM v8.2-A)                                                                 | 1           |
 | [`__ARM_FEATURE_DSP`](#dsp-instructions)                                                                                                                | DSP instructions (Arm v5E) (32-bit-only)                                                           | 1           |
 | [`__ARM_FEATURE_F16F32DOT`](#half-precision-to-single-precision-dot-product-extension)                                                                  | Half-precision to single-precision dot product extension (FEAT_F16F32DOT)                          | 1           |
+| [`__ARM_FEATURE_F16F32MM`](#multiplication-of-16-bit-floating-point-matrices-advsimd)                                                                   | Half-precision to single-precision matrix multiply accumulating extension (FEAT_F16F32MM).         | 1           |
+| [`__ARM_FEATURE_F16MM`](#multiplication-of-16-bit-floating-point-matrices-advsimd)                                                                      | Half-precision matrix multiply accumulating extension (FEAT_F16MM)                                 | 1           |
 | [`__ARM_FEATURE_FAMINMAX`](#floating-point-absolute-minimum-and-maximum-extension)                                                                      | Floating-point absolute minimum and maximum extension                                              | 1           |
 | [`__ARM_FEATURE_FMA`](#fused-multiply-accumulate-fma)                                                                                                   | Floating-point fused multiply-accumulate                                                           | 1           |
 | [`__ARM_FEATURE_FP16_FML`](#fp16-fml-extension)                                                                                                         | FP16 FML extension (Arm v8.4-A, optional Armv8.2-A, Armv8.3-A)                                     | 1           |
@@ -2735,6 +2768,7 @@ be found in [[BA]](#BA).
 | [`__ARM_FEATURE_SSVE_FP8FMA`](#modal-8-bit-floating-point-extensions)                                                                                   | Modal 8-bit floating-point extensions                                                              | 1           |
 | [`__ARM_FEATURE_SVE`](#scalable-vector-extension-sve)                                                                                                   | Scalable Vector Extension (FEAT_SVE)                                                               | 1           |
 | [`__ARM_FEATURE_SVE_B16B16`](#non-widening-brain-16-bit-floating-point-support)                                                                         | Non-widening brain 16-bit floating-point intrinsics (FEAT_SVE_B16B16)                              | 1           |
+| [`__ARM_FEATURE_SVE_B16MM`](#brain-16-bit-floating-point-matrix-multiplication-support)                                                                 | SVE brain 16-bit floating-point matrix multiply extension (FEAT_SVE_B16MM)                         | 1           |
 | [`__ARM_FEATURE_SVE_BF16`](#brain-16-bit-floating-point-support)                                                                                        | SVE support for the 16-bit brain floating-point extension (FEAT_BF16)                              | 1           |
 | [`__ARM_FEATURE_SVE_BFSCALE`](#brain-16-bit-floating-point-vector-multiplication-support)                                                               | SVE support for the 16-bit brain floating-point vector multiplication extension (FEAT_SVE_BFSCALE) | 1           |
 | [`__ARM_FEATURE_SVE_BITS`](#scalable-vector-extension-sve)                                                                                              | The number of bits in an SVE vector, when known in advance                                         | 256         |
@@ -9616,6 +9650,15 @@ BFloat16 floating-point adjust exponent vectors.
 
 ### SVE2 floating-point matrix multiply-accumulate instructions.
 
+#### BFMMLA, FMMLA(non-widening)
+
+16-bit floating-point matrix multiply-accumulate.
+```c
+  // Only if __ARM_FEATURE_SVE_B16MM
+  // Variant also available for _f16 if (__ARM_FEATURE_SVE2p2 && __ARM_FEATURE_F16MM).
+  svbfloat16_t svmmla[_bf16](svbfloat16_t zda, svbfloat16_t zn, svbfloat16_t zm);
+```
+
 #### FMMLA (widening, FP8 to FP16)
 
 Modal 8-bit floating-point matrix multiply-accumulate to half-precision.
diff --git a/neon_intrinsics/advsimd.md b/neon_intrinsics/advsimd.md
index e20fc963..05e91323 100644
--- a/neon_intrinsics/advsimd.md
+++ b/neon_intrinsics/advsimd.md
@@ -172,6 +172,7 @@ for more information about Arm’s trademarks.
 ### Changes for next release
 
 * Added support for FEAT_F16F32DOT
+* Added support for FEAT_F16F32MM and FEAT_F16MM
 
 <!---
 **** Do not remove! ****
@@ -6230,3 +6231,23 @@ The intrinsics in this section are guarded by the macro ``__ARM_NEON``.
 | <code>float32x4_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vfdotq_f32_f16" target="_blank">vfdotq_f32_f16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float32x4_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t b)</code>                                                       | `r -> Vd.4S`<br>`a -> Vn.8H`<br>`b -> Vm.8H`                     | `FDOT Vd.4S,Vn.8H,Vm.8H`       | `Vd.4S -> result` | `A64`                     |
 | <code>float32x2_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vfdot_lane_f32_f16" target="_blank">vfdot_lane_f32_f16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float32x2_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x4_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x2_t b,<br>&nbsp;&nbsp;&nbsp;&nbsp; const int lane)</code>   | `r -> Vd.2S`<br>`a -> Vn.4H`<br>`b -> Vm.2H`<br>`0 <= lane <= 3` | `FDOT Vd.2S,Vn.4H,Vm.2H[lane]` | `Vd.2S -> result` | `A64`                     |
 | <code>float32x4_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vfdotq_lane_f32_f16" target="_blank">vfdotq_lane_f32_f16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float32x4_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x2_t b,<br>&nbsp;&nbsp;&nbsp;&nbsp; const int lane)</code> | `r -> Vd.4S`<br>`a -> Vn.8H`<br>`b -> Vm.2H`<br>`0 <= lane <= 3` | `FDOT Vd.4S,Vn.8H,Vm.2H[lane]` | `Vd.4S -> result` | `A64`                     |
+
+## Half-precision matrix multiply accumulating to single-precision instruction from Armv9.7-A. Requires the +f16f32mm architecture extension.
+
+### Vector arithmetic
+
+#### Matrix multiply
+
+| Intrinsic                                                                                                                                                                                                                                                                                  | Argument preparation                         | AArch64 Instruction         | Result            | Supported architectures   |
+|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------|-----------------------------|-------------------|---------------------------|
+| <code>float32x4_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vmmlaq_f32_f16" target="_blank">vmmlaq_f32_f16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float32x4_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t b)</code> | `r -> Vd.4S`<br>`a -> Vn.8H`<br>`b -> Vm.8H` | `FMMLA Vd.4S, Vn.8H, Vm.8H` | `Vd.4S -> result` | `A64`                     |
+
+## Non-widening half-precision matrix multiply instruction. Requires the +f16mm architecture extension.
+
+### Vector arithmetic
+
+#### Matrix multiply
+
+| Intrinsic                                                                                                                                                                                                                                                                                  | Argument preparation                         | AArch64 Instruction         | Result            | Supported architectures   |
+|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------|-----------------------------|-------------------|---------------------------|
+| <code>float16x8_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vmmlaq_f16_f16" target="_blank">vmmlaq_f16_f16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t b)</code> | `r -> Vd.8H`<br>`a -> Vn.8H`<br>`b -> Vm.8H` | `FMMLA Vd.8H, Vn.8H, Vm.8H` | `Vd.8H -> result` | `A64`                     |
diff --git a/tools/intrinsic_db/advsimd.csv b/tools/intrinsic_db/advsimd.csv
index 2fa0d97c..37b39331 100644
--- a/tools/intrinsic_db/advsimd.csv
+++ b/tools/intrinsic_db/advsimd.csv
@@ -4841,3 +4841,9 @@ float32x4_t vfdotq_f32_f16(float32x4_t r, float16x8_t a, float16x8_t b)	r -> Vd.
 
 float32x2_t vfdot_lane_f32_f16(float32x2_t r, float16x4_t a, float16x2_t b, __builtin_constant_p(lane))	r -> Vd.2S;a -> Vn.4H;b -> Vm.2H;0 <= lane <= 3	FDOT Vd.2S,Vn.4H,Vm.2H[lane]	Vd.2S -> result	A64
 float32x4_t vfdotq_lane_f32_f16(float32x4_t r, float16x8_t a, float16x2_t b, __builtin_constant_p(lane))	r -> Vd.4S;a -> Vn.8H;b -> Vm.2H;0 <= lane <= 3	FDOT Vd.4S,Vn.8H,Vm.2H[lane]	Vd.4S -> result	A64
+
+<SECTION>	Half-precision matrix multiply accumulating to single-precision instruction from Armv9.7-A. Requires the +f16f32mm architecture extension.
+float32x4_t vmmlaq_f32_f16(float32x4_t r, float16x8_t a, float16x8_t b)	r -> Vd.4S;a -> Vn.8H;b -> Vm.8H	FMMLA Vd.4S, Vn.8H, Vm.8H	Vd.4S -> result	A64
+
+<SECTION>	Non-widening half-precision matrix multiply instruction. Requires the +f16mm architecture extension.
+float16x8_t vmmlaq_f16_f16(float16x8_t r, float16x8_t a, float16x8_t b)	r -> Vd.8H;a -> Vn.8H;b -> Vm.8H	FMMLA Vd.8H, Vn.8H, Vm.8H	Vd.8H -> result	A64
diff --git a/tools/intrinsic_db/advsimd_classification.csv b/tools/intrinsic_db/advsimd_classification.csv
index a30df166..f6b90efd 100644
--- a/tools/intrinsic_db/advsimd_classification.csv
+++ b/tools/intrinsic_db/advsimd_classification.csv
@@ -4723,3 +4723,5 @@ vfdot_f32_f16	Vector arithmetic|Dot product
 vfdotq_f32_f16	Vector arithmetic|Dot product
 vfdot_lane_f32_f16	Vector arithmetic|Dot product
 vfdotq_lane_f32_f16	Vector arithmetic|Dot product
+vmmlaq_f32_f16	Vector arithmetic|Matrix multiply
+vmmlaq_f16_f16	Vector arithmetic|Matrix multiply

From 3a64c9649c03d34148e29d77f20200e77df0ae65 Mon Sep 17 00:00:00 2001
From: Claudio Bantaloukas <claudio.bantaloukas@arm.com>
Date: Thu, 5 Feb 2026 11:20:23 +0000
Subject: [PATCH 4/8] Add alpha support for 9.7 lookup table intrinsics

This change adds support for the svluti6 operations under FEAT_SVE2p3 and FEAT_SME2p3.
---
 main/acle.md | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 69 insertions(+)

diff --git a/main/acle.md b/main/acle.md
index 6e338100..b69b47c4 100644
--- a/main/acle.md
+++ b/main/acle.md
@@ -492,6 +492,8 @@ Armv8.4-A [[ARMARMv84]](#ARMARMv84). Support is added for the Dot Product intrin
   dot product intrinsics.
 * Added [**Alpha**](#current-status-and-anticipated-changes)
   support for FEAT_F16F32MM, FEAT_F16MM and FEAT_SVE_B16MM mmla intrinsics.
+* Added [**Alpha**](#current-status-and-anticipated-changes)
+  support for SVE2.3 (FEAT_SVE2p3) and SME2.3 lookup table intrinsics.
 
 ### References
 
@@ -10020,6 +10022,22 @@ Lookup table read with 4-bit indices.
   svint16_t svluti4_lane[_s16_x2](svint16x2_t table, svuint8_t indices, uint64_t imm_idx);
 ```
 
+### SVE2.3 lookup table
+
+The intrinsics in this section are defined by the header file
+[`<arm_sve.h>`](#arm_sve.h) when `__ARM_FEATURE_SVE2p3` is defined to 1.
+
+#### LUTI6
+
+Lookup table read with 6-bit indices (8-bit).
+
+Use of this intrinsic if `svcntb() * 8 < 256` results in undefined behaviour.
+
+```c
+  // Variant is  also available for: _u8 _mf8
+  svint8_t svluti6[_s8](svint8x2_t table, svuint8_t indices);
+```
+
 ### SVE2 Multi-vector AES and 128-bit polynomial multiply long instructions
 
 The specification for SVE2 Multi-vector AES and 128-bit polynomial multiply long instructions is in
@@ -13924,6 +13942,27 @@ Scalar index of first/last true predicate element (predicated).
 
   ```
 
+### SVE2.3 and SME2.3 instruction intrinsics
+
+The specification for SVE2.3 and SME2.3 are in
+[**Alpha** state](#current-status-and-anticipated-changes) and might change or be
+extended in the future.
+
+The functions in this section are defined by either the header file
+ [`<arm_sve.h>`](#arm_sve.h) or [`<arm_sme.h>`](#arm_sme.h)
+when `__ARM_FEATURE_SVE2p3` or `__ARM_FEATURE_SME2p3` is defined, respectively.
+
+#### LUTI6
+
+Lookup table read with 6-bit indices (16-bit).
+
+Use of this intrinsic if `svcntb() * 8 < 512` results in undefined behaviour.
+
+``` c
+  // Variants are also available for _u16_x2 and _f16_x2.
+  svint16_t svluti6_lane[_s16_x2](svint16x2_t table, svuint8_t indices, uint64_t imm_idx);
+  ```
+
 ### SME2 maximum and minimum absolute value
 
 The intrinsics in this section are defined by the header file
@@ -14648,6 +14687,36 @@ non-overloaded names to indicate which vector argument is a vector register pair
     __arm_streaming __arm_inout("za");
 ```
 
+### SME2.3 lookup table
+
+The intrinsics in this section are defined by the header file
+[`<arm_sme.h>`](#arm_sme.h) when `__ARM_FEATURE_SME2p3` is defined to 1.
+
+#### LUTI6
+
+Lookup table read with 6-bit indices (16-bit)
+
+Use of this intrinsic if `svcntb() * 8 < 512` results in undefined behaviour.
+
+```c
+  // Variant are also available for: _u16, _f16 and _bf16.
+  svint16x4_t svluti6_lane_s16_x4[_s16_x2](svint16x2_t table, svuint8x2_t indices, uint64_t imm_idx);
+```
+
+Lookup table read with 6-bit indices (four registers, 8-bit)
+
+``` c
+  // Variants are also available for: _u8 and _mf8.
+  svint8x4_t svluti6_zt_s8_x4(uint64_t zt0, svuint8x3_t zn) __arm_streaming __arm_in("zt0");
+```
+
+Lookup table read with 6-bit indices (table, single, 8-bit)
+
+``` c
+  // Variants are also available for: _u8 and _mf8.
+  svint8_t svluti6_zt_s8(uint64_t zt0, svuint8_t zn) __arm_streaming __arm_in("zt0");
+```
+
 # M-profile Vector Extension (MVE) intrinsics
 
 The M-profile Vector Extension (MVE) [[MVE-spec]](#MVE-spec) instructions provide packed Single

From 8e4420561cb28f42bdbec1140612c8881b2ad891 Mon Sep 17 00:00:00 2001
From: Claudio Bantaloukas <claudio.bantaloukas@arm.com>
Date: Thu, 5 Feb 2026 11:22:05 +0000
Subject: [PATCH 5/8] Add alpha support for 9.7 pairwise operation intrinsics

This change adds support for the svaddqp, svaddsubp and svsubp operations under FEAT_SVE2p3 and FEAT_SME2p3.
---
 main/acle.md | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/main/acle.md b/main/acle.md
index b69b47c4..b700cd92 100644
--- a/main/acle.md
+++ b/main/acle.md
@@ -494,6 +494,8 @@ Armv8.4-A [[ARMARMv84]](#ARMARMv84). Support is added for the Dot Product intrin
   support for FEAT_F16F32MM, FEAT_F16MM and FEAT_SVE_B16MM mmla intrinsics.
 * Added [**Alpha**](#current-status-and-anticipated-changes)
   support for SVE2.3 (FEAT_SVE2p3) and SME2.3 lookup table intrinsics.
+* Added [**Alpha**](#current-status-and-anticipated-changes)
+  support for SVE2.3 (FEAT_SVE2p3) and SME2.3 pairwise operation intrinsics.
 
 ### References
 
@@ -13952,6 +13954,24 @@ The functions in this section are defined by either the header file
  [`<arm_sve.h>`](#arm_sve.h) or [`<arm_sme.h>`](#arm_sme.h)
 when `__ARM_FEATURE_SVE2p3` or `__ARM_FEATURE_SME2p3` is defined, respectively.
 
+#### ADDQP
+
+Add pairwise within quadword vector segments.
+
+``` c
+  // Variants are also available for _s16, _s32, _s64, _u8, _u16, _u32 and _u64.
+  svint8_t svaddqp[_s8](svint8_t zn, svint8_t zm);
+  ```
+
+#### ADDSUBP
+
+Add subtract pairwise.
+
+``` c
+  // Variants are also available for _s16, _s32, _s64, _u8, _u16, _u32 and _u64.
+  svint8_t svaddsubp[_s8](svint8_t zn, svint8_t zm);
+  ```
+
 #### LUTI6
 
 Lookup table read with 6-bit indices (16-bit).
@@ -13963,6 +13983,15 @@ Use of this intrinsic if `svcntb() * 8 < 512` results in undefined behaviour.
   svint16_t svluti6_lane[_s16_x2](svint16x2_t table, svuint8_t indices, uint64_t imm_idx);
   ```
 
+#### SUBP
+
+Subtract pairwise.
+
+``` c
+  // Variants are also available for _s16, _s32, _s64, _u8, _u16, _u32 and _u64.
+  svint8_t svsubp[_s8](svbool_t pg, svint8_t zn, svint8_t zm);
+  ```
+
 ### SME2 maximum and minimum absolute value
 
 The intrinsics in this section are defined by the header file

From 752c7ccd1f7d541d1fac3d733587e4e5abea63ba Mon Sep 17 00:00:00 2001
From: Claudio Bantaloukas <claudio.bantaloukas@arm.com>
Date: Thu, 5 Feb 2026 11:25:02 +0000
Subject: [PATCH 6/8] Add alpha support for 9.7 conversion intrinsics

This change adds support for the svcvt* operations under FEAT_SVE2p3 and FEAT_SME2p3.
---
 main/acle.md | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/main/acle.md b/main/acle.md
index b700cd92..8789f9ca 100644
--- a/main/acle.md
+++ b/main/acle.md
@@ -496,6 +496,8 @@ Armv8.4-A [[ARMARMv84]](#ARMARMv84). Support is added for the Dot Product intrin
   support for SVE2.3 (FEAT_SVE2p3) and SME2.3 lookup table intrinsics.
 * Added [**Alpha**](#current-status-and-anticipated-changes)
   support for SVE2.3 (FEAT_SVE2p3) and SME2.3 pairwise operation intrinsics.
+* Added [**Alpha**](#current-status-and-anticipated-changes)
+  support for SVE2.3 (FEAT_SVE2p3) and SME2.3 conversion intrinsics.
 
 ### References
 
@@ -13983,6 +13985,29 @@ Use of this intrinsic if `svcntb() * 8 < 512` results in undefined behaviour.
   svint16_t svluti6_lane[_s16_x2](svint16x2_t table, svuint8_t indices, uint64_t imm_idx);
   ```
 
+#### FCVTZSN, FCVTZUN
+
+Floating-point narrowing convert to interleaved integer, rounding toward zero
+
+``` c
+  // Variants are also available for
+  //               _s16[_f32_x2], _s32[_f64_x2],
+  // _u8[_f16_x2], _u16[_f32_x2], _u32[_f64_x2].
+  svint8_t svcvt_s8[_f16_x2](svfloat16x2_t zn);
+```
+
+#### SCVTF, SCVTFLT, UCVTF, UCVTFLT
+
+Integer convert to floating-point (top and bottom).
+
+``` c
+  // Variants are also available for
+  //            _f32[_s16], _f64[_s32],
+  // _f16[_u8], _f32[_u16], _f64[_u32].
+  svfloat16_t svcvtt_f16[_s8](svint8_t zn);
+  svfloat16_t svcvtb_f16[_s8](svint8_t zn);
+```
+
 #### SUBP
 
 Subtract pairwise.

From 6365c01c1ef66a60eccea9f2e09f6c6e4904b192 Mon Sep 17 00:00:00 2001
From: Claudio Bantaloukas <claudio.bantaloukas@arm.com>
Date: Thu, 5 Feb 2026 11:31:32 +0000
Subject: [PATCH 7/8] Add alpha support for 9.7 absolute difference
 accumulation intrinsics

This change adds support for the svaba operations under FEAT_SVE2p3 and FEAT_SME2p3.
---
 main/acle.md | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/main/acle.md b/main/acle.md
index 8789f9ca..fe3916ce 100644
--- a/main/acle.md
+++ b/main/acle.md
@@ -498,6 +498,9 @@ Armv8.4-A [[ARMARMv84]](#ARMARMv84). Support is added for the Dot Product intrin
   support for SVE2.3 (FEAT_SVE2p3) and SME2.3 pairwise operation intrinsics.
 * Added [**Alpha**](#current-status-and-anticipated-changes)
   support for SVE2.3 (FEAT_SVE2p3) and SME2.3 conversion intrinsics.
+* Added [**Alpha**](#current-status-and-anticipated-changes)
+  support for SVE2.3 (FEAT_SVE2p3) and SME2.3 absolute difference accumulation
+  intrinsics.
 
 ### References
 
@@ -13996,6 +13999,17 @@ Floating-point narrowing convert to interleaved integer, rounding toward zero
   svint8_t svcvt_s8[_f16_x2](svfloat16x2_t zn);
 ```
 
+#### SABAL, UABAL
+
+Two-way absolute difference sum and accumulate long.
+
+``` c
+  // Variants are also available for
+  //            _s32[_s16], _s64[_s32],
+  // _u16[_u8], _u32[_u16], _u64[_u32].
+  svint16_t svaba_s16[_s8](svint16_t zda, svint8_t zn, svint8_t zm);
+```
+
 #### SCVTF, SCVTFLT, UCVTF, UCVTFLT
 
 Integer convert to floating-point (top and bottom).

From f0458c993b04a020b7c89ec5146c3390d01100bd Mon Sep 17 00:00:00 2001
From: Claudio Bantaloukas <claudio.bantaloukas@arm.com>
Date: Thu, 5 Feb 2026 11:32:32 +0000
Subject: [PATCH 8/8] Add alpha support for 9.7 shift right narrow intrinsics

This change adds support for new svqshrn, svqshrun operations under FEAT_SVE2p3 and FEAT_SME2p3.
---
 main/acle.md | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/main/acle.md b/main/acle.md
index fe3916ce..0d68ccdd 100644
--- a/main/acle.md
+++ b/main/acle.md
@@ -501,6 +501,8 @@ Armv8.4-A [[ARMARMv84]](#ARMARMv84). Support is added for the Dot Product intrin
 * Added [**Alpha**](#current-status-and-anticipated-changes)
   support for SVE2.3 (FEAT_SVE2p3) and SME2.3 absolute difference accumulation
   intrinsics.
+* Added [**Alpha**](#current-status-and-anticipated-changes)
+  support for SVE2.3 (FEAT_SVE2p3) and SME2.3 shift right narrow intrinsics.
 
 ### References
 
@@ -13640,6 +13642,7 @@ Multi-vector saturating rounding shift right narrow and interleave
 
 ``` c
   // Variants are also available for _u16[_u32_x2]
+  // and also _s8[_s16_x2] and _u8[_u16_x2] if __ARM_FEATURE_SVE2p3 || __ARM_FEATURE_SME2p3.
   svint16_t svqrshrn[_n]_s16[_s32_x2](svint32x2_t zn, uint64_t imm);
   ```
 
@@ -13648,6 +13651,7 @@ Multi-vector saturating rounding shift right narrow and interleave
 Multi-vector saturating rounding shift right unsigned narrow and interleave
 
 ``` c
+  // Variant for _u8[_u16_x2] is available if __ARM_FEATURE_SVE2p3 || __ARM_FEATURE_SME2p3.
   svuint16_t svqrshrun[_n]_u16[_s32_x2](svint32x2_t zn, uint64_t imm);
   ```
 
@@ -14022,6 +14026,24 @@ Integer convert to floating-point (top and bottom).
   svfloat16_t svcvtb_f16[_s8](svint8_t zn);
 ```
 
+#### SQSHRN, UQSHRN
+
+Multi-vector saturating shift right narrow and interleave.
+
+``` c
+  // Variants are also available for _s8[_s16_x2], _u16[_u32_x2] and _u8[_u16_x2].
+  svint16_t svqshrn[_n]_s16[_s32_x2](svint32x2_t zn, uint64_t imm);
+  ```
+
+#### SQSHRUN
+
+Signed saturating shift right narrow by immediate to interleaved unsigned integer.
+
+``` c
+  // Variant for _u8[_s16_x2] is also available.
+  svuint16_t svqshrun[_n]_u16[_s32_x2](svint32x2_t zn, uint64_t imm);
+  ```
+
 #### SUBP
 
 Subtract pairwise.