Simplify the SIMD code

[ggerganov]

This is an attempt to simplify and unify the SIMD implementation for various architectures. The idea is similar to https://github.com/ggerganov/whisper.cpp/pull/95#issuecomment-1344845687

We define a common subset of C macros which map to specific intrinsics based on the current architecture:

#define GGML_F32_VEC        ...
#define GGML_F32_VEC_ZERO   ...
#define GGML_F32_VEC_SET1   ...
#define GGML_F32_VEC_LOAD   ...
#define GGML_F32_VEC_STORE  ...
#define GGML_F32_VEC_FMA    ...
#define GGML_F32_VEC_ADD    ...
#define GGML_F32_VEC_MUL    ...
#define GGML_F32_VEC_REDUCE ...

#define GGML_F16_VEC        ...
#define GGML_F16_VEC_ZERO   ...
#define GGML_F16_VEC_SET1   ...
#define GGML_F16_VEC_LOAD   ...
#define GGML_F16_VEC_STORE  ...
#define GGML_F16_VEC_FMA    ...
#define GGML_F16_VEC_ADD    ...
#define GGML_F16_VEC_MUL    ...
#define GGML_F16_VEC_REDUCE ...

We then implement the SIMD functions using only these macros. Refactored functions:

• [x] ggml_vec_dot_f32
• [x] ggml_vec_dot_f16
• [x] ggml_vec_mad_f32
• [x] ggml_vec_mad_f16
• [x] ggml_scale_f32

Supported and tested architectures:

• [x] Arm64
• [x] ARMv7
• [x] x86
• [x] WASM
• [ ] ppc64le

Still not sure if this would be easier to maintain, but I will give it a try