[clang] [llvm] [AArch64] Add intrinsics for multi-vector FEAT_SVE_BFSCALE instructions (PR #163536)

[via llvm-commits]

https://github.com/CarolineConcatto approved this pull request.

LGTM. 
I would only update the commit message to add the C intrinsics:

These are the intrinsics prototype implemented, according to [1]
//BFMUL:
 svbfloat16x2_t svmul[_bf16_x2](svbfloat16x2_t zd, svbfloat16x2_t zm) __arm_streaming;
   svbfloat16x2_t svmul[_single_bf16_x2](svbfloat16x2_t zd, svbfloat16_t zm) __arm_streaming;
   svbfloat16x4_t svmul[_bf16_x4](svbfloat16x4_t zd, svbfloat16x4_t zm) __arm_streaming;
   svbfloat16x4_t svmul[_single_bf16_x4](svbfloat16x4_t zd, svbfloat16_t zm) __arm_streaming;

//BFSCALE
   svbfloat16x2_t svscale[_bf16_x2](svbfloat16x2_t zdn, svint16x2_t zm)  __arm_streaming;
   svbfloat16x2_t svscale[_single_bf16_x2](svbfloat16x2_t zn, svint16_t zm)  __arm_streaming;
   svbfloat16x4_t svscale[_bf16_x4](svbfloat16x4_t zdn, svint16x4_t zm)  __arm_streaming;
   svbfloat16x4_t svscale[_single_bf16_x4](svbfloat16x4_t zn, svint16_t zm)  __arm_streaming;
[1]https://github.com/ARM-software/acle/pull/410

https://github.com/llvm/llvm-project/pull/163536