Extend SME2.1 intrinsics to mf8

SME2.1 intrinsics were developed in parallel with FP8 and thus lacked support for the svmfloat8_t type. This patch adds
support for consistency.

Author: rockdreamer

main/acle.md

@@ -11,7 +11,7 @@ toc: true
 ---
 
 <!--
-SPDX-FileCopyrightText: Copyright 2011-2024 Arm Limited and/or its affiliates <[email protected]>
+SPDX-FileCopyrightText: Copyright 2011-2025 Arm Limited and/or its affiliates <[email protected]>
 SPDX-FileCopyrightText: Copyright 2022 Google LLC.
 CC-BY-SA-4.0 AND Apache-Patent-License
 See LICENSE.md file for details
@@ -435,6 +435,7 @@ Armv8.4-A [[ARMARMv84]](#ARMARMv84). Support is added for the Dot Product intrin
 * Added [`__arm_agnostic`](#arm_agnostic) keyword attribute.
 * Refined function versioning scope and signature rules to use the default
   version scope and signature.
+* Added mf8 variants of SME 2.1 intrinsics.
 
 ### References
 
@@ -12509,7 +12510,7 @@ The intrinsics in this section are defined by the header file
 Move and zero ZA tile slice to vector register.
 
 ```
-  // And similarly for u8.
+  // And similarly for u8 and mf8.
   svint8_t svreadz_hor_za8_s8(uint64_t tile, uint32_t slice)
     __arm_streaming __arm_inout("za");
 
@@ -12525,11 +12526,12 @@ Move and zero ZA tile slice to vector register.
   svint64_t svreadz_hor_za64_s64(uint64_t tile, uint32_t slice)
     __arm_streaming __arm_inout("za");
 
-  // And similarly for s16, s32, s64, u8, u16, u32, u64, bf16, f16, f32, f64
+  // And similarly for s16, s32, s64, u8, u16, u32, u64,
+  // mf8, bf16, f16, f32, f64
   svint8_t svreadz_hor_za128_s8(uint64_t tile, uint32_t slice)
     __arm_streaming __arm_inout("za");
 
-  // And similarly for u8.
+  // And similarly for u8 and mf8.
   svint8_t svreadz_ver_za8_s8(uint64_t tile, uint32_t slice)
     __arm_streaming __arm_inout("za");
 
@@ -12545,7 +12547,8 @@ Move and zero ZA tile slice to vector register.
   svint64_t svreadz_ver_za64_s64(uint64_t tile, uint32_t slice)
     __arm_streaming __arm_inout("za");
 
-  // And similarly for s16, s32, s64, u8, u16, u32, u64, bf16, f16, f32, f64
+  // And similarly for s16, s32, s64, u8, u16, u32, u64,
+  // mf8, bf16, f16, f32, f64
   svint8_t svreadz_ver_za128_s8(uint64_t tile, uint32_t slice)
     __arm_streaming __arm_inout("za");
 ```
@@ -12555,28 +12558,28 @@ Move and zero ZA tile slice to vector register.
 Move and zero multiple ZA tile slices to vector registers
 
 ``` c
-  // Variants are also available for _za8_u8, _za16_s16, _za16_u16,
+  // Variants are also available for _za8_u8, _za8_mf8, _za16_s16, _za16_u16,
   // _za16_f16, _za16_bf16, _za32_s32, _za32_u32, _za32_f32,
   // _za64_s64, _za64_u64 and _za64_f64
   svint8x2_t svreadz_hor_za8_s8_vg2(uint64_t tile, uint32_t slice)
     __arm_streaming __arm_inout("za");
 
 
-  // Variants are also available for _za8_u8, _za16_s16, _za16_u16,
+  // Variants are also available for _za8_u8, _za8_mf8, _za16_s16, _za16_u16,
   // _za16_f16, _za16_bf16, _za32_s32, _za32_u32, _za32_f32,
   // _za64_s64, _za64_u64 and _za64_f64
   svint8x4_t svreadz_hor_za8_s8_vg4(uint64_t tile, uint32_t slice)
     __arm_streaming __arm_inout("za");
 
 
-  // Variants are also available for _za8_u8, _za16_s16, _za16_u16,
+  // Variants are also available for _za8_u8, _za8_mf8, _za16_s16, _za16_u16,
   // _za16_f16, _za16_bf16, _za32_s32, _za32_u32, _za32_f32,
   // _za64_s64, _za64_u64 and _za64_f64
   svint8x2_t svreadz_ver_za8_s8_vg2(uint64_t tile, uint32_t slice)
     __arm_streaming __arm_inout("za");
 
 
-  // Variants are also available for _za8_u8, _za16_s16, _za16_u16,
+  // Variants are also available for _za8_u8, _za8_mf8, _za16_s16, _za16_u16,
   // _za16_f16, _za16_bf16, _za32_s32, _za32_u32, _za32_f32,
   // _za64_s64, _za64_u64 and _za64_f64
   svint8x4_t svreadz_ver_za8_s8_vg4(uint64_t tile, uint32_t slice)
@@ -12588,14 +12591,14 @@ Move and zero multiple ZA tile slices to vector registers
 Move and zero multiple ZA single-vector groups to vector registers
 
 ```
-  // Variants are also available for _za8_u8, _za16_s16, _za16_u16,
+  // Variants are also available for _za8_u8, _za8_mf8, _za16_s16, _za16_u16,
   // _za16_f16, _za16_bf16, _za32_s32, _za32_u32, _za32_f32,
   // _za64_s64, _za64_u64 and _za64_f64
   svint8x2_t svreadz_za8_s8_vg1x2(uint32_t slice)
     __arm_streaming __arm_inout("za");
 
 
-  // Variants are also available for _za8_u8, _za16_s16, _za16_u16,
+  // Variants are also available for _za8_u8, _za8_mf8, _za16_s16, _za16_u16,
   // _za16_f16, _za16_bf16, _za32_s32, _za32_u32, _za32_f32,
   // _za64_s64, _za64_u64 and _za64_f64
   svint8x4_t svreadz_za8_s8_vg1x4(uint32_t slice)