[AArch64] Implement intrinsics for SME2 FSCALE (#100128)

This patch implements these intrinsics:

FSCALE SINGLE AND MULTI
``` 
  // Variants are also available for:
  // [_single_f32_x2], [_single_f64_x2],
  // [_single_f16_x4], [_single_f32_x4], [_single_f64_x4]
  svfloat16x2_t svscale[_single_f16_x2](svfloat16x2_t zd, svfloat16_t zm) __arm_streaming;

  // Variants are also available for:
  //  [_f32_x2], [_f64_x2],
  //  [_f16_x4], [_f32_x4], [_f64_x4]
  svfloat16x2_t svscale[_f16_x2](svfloat16x2_t zd, svfloat16x2_t zm) __arm_streaming

```
(cf. ARM-software/acle#323)

Co-authored-by: Caroline Concatto <[email protected]>

Author: Lukacma

clang/include/clang/Basic/arm_sve.td

@@ -2418,6 +2418,16 @@ let SVETargetGuard = InvalidMode, SMETargetGuard = "sme2" in {
   def SVUUNPK_X4 : SInst<"svunpk_{d}[_{3}_x4]", "42.h", "UsUiUl", MergeNone, "aarch64_sve_uunpk_x4", [IsStreaming], []>;
 }
 
+//
+// Multi-vector scaling
+//
+let  SVETargetGuard = InvalidMode, SMETargetGuard = "sme2,fp8" in {
+  def FSCALE_SINGLE_X2 : Inst<"svscale[_single_{d}_x2]", "22x", "fhd", MergeNone, "aarch64_sme_fp8_scale_single_x2", [IsStreaming],[]>;
+  def FSCALE_SINGLE_X4 : Inst<"svscale[_single_{d}_x4]", "44x", "fhd", MergeNone, "aarch64_sme_fp8_scale_single_x4", [IsStreaming],[]>;
+  def FSCALE_X2 : Inst<"svscale[_{d}_x2]", "222.x", "fhd", MergeNone, "aarch64_sme_fp8_scale_x2", [IsStreaming],[]>;
+  def FSCALE_X4 : Inst<"svscale[_{d}_x4]", "444.x", "fhd", MergeNone, "aarch64_sme_fp8_scale_x4", [IsStreaming],[]>;
+}
+
 let SVETargetGuard = "sve2p1", SMETargetGuard = "sme2" in {
 // == BFloat16 multiply-subtract ==
   def SVBFMLSLB : SInst<"svbfmlslb[_{d}]", "dd$$", "f", MergeNone, "aarch64_sve_bfmlslb", [IsOverloadNone, VerifyRuntimeMode], []>;