[WebAssembly] Improve macro hygiene in wasm_simd128.h

[tlively]

Summary

The shuffle intrinsic macros did not parenthesize usages of their
constant parameters, which could lead to incorrect results due to
operator precedence issues. This patch fixes the problem by adding the
missing paretheses.

[aheejin]

clang/lib/Headers/wasm_simd128.h

1040

It's interesting that clang-format deletes whitespaces around parenthesized expressions...

clang/lib/Headers/wasm_simd128.h

#define wasm_v8x16_shuffle(__a, __b, __c0, __c1, __c2, __c3, __c4, __c5, __c6, \
                            __c14, __c15)                                       \
   ((v128_t)__builtin_wasm_shuffle_v8x16(                                       \
       (__i8x16)(__a), (__i8x16)(__b), __c0, __c1, __c2, __c3, __c4, __c5,      \
       __c6, __c7, __c8, __c9, __c10, __c11, __c12, __c13, __c14, __c15))
 
 #define wasm_v16x8_shuffle(__a, __b, __c0, __c1, __c2, __c3, __c4, __c5, __c6, \
                            __c7)                                               \
   ((v128_t)__builtin_wasm_shuffle_v8x16(                                       \
-      (__i8x16)(__a), (__i8x16)(__b), __c0 * 2, __c0 * 2 + 1, __c1 * 2,        \
-      __c1 * 2 + 1, __c2 * 2, __c2 * 2 + 1, __c3 * 2, __c3 * 2 + 1, __c4 * 2,  \
-      __c4 * 2 + 1, __c5 * 2, __c5 * 2 + 1, __c6 * 2, __c6 * 2 + 1, __c7 * 2,  \
-      __c7 * 2 + 1))
+      (__i8x16)(__a), (__i8x16)(__b), (__c0)*2, (__c0)*2 + 1, (__c1)*2,        \
+      (__c1)*2 + 1, (__c2)*2, (__c2)*2 + 1, (__c3)*2, (__c3)*2 + 1, (__c4)*2,  \
+      (__c4)*2 + 1, (__c5)*2, (__c5)*2 + 1, (__c6)*2, (__c6)*2 + 1, (__c7)*2,  \
+      (__c7)*2 + 1))
 
 #define wasm_v32x4_shuffle(__a, __b, __c0, __c1, __c2, __c3)                   \
   ((v128_t)__builtin_wasm_shuffle_v8x16(                                       \
-      (__i8x16)(__a), (__i8x16)(__b), __c0 * 4, __c0 * 4 + 1, __c0 * 4 + 2,    \
-      __c0 * 4 + 3, __c1 * 4, __c1 * 4 + 1, __c1 * 4 + 2, __c1 * 4 + 3,        \
-      __c2 * 4, __c2 * 4 + 1, __c2 * 4 + 2, __c2 * 4 + 3, __c3 * 4,            \
-      __c3 * 4 + 1, __c3 * 4 + 2, __c3 * 4 + 3))
+      (__i8x16)(__a), (__i8x16)(__b), (__c0)*4, (__c0)*4 + 1, (__c0)*4 + 2,    \
+      (__c0)*4 + 3, (__c1)*4, (__c1)*4 + 1, (__c1)*4 + 2, (__c1)*4 + 3,        \
+      (__c2)*4, (__c2)*4 + 1, (__c2)*4 + 2, (__c2)*4 + 3, (__c3)*4,            \
+      (__c3)*4 + 1, (__c3)*4 + 2, (__c3)*4 + 3))
 
 #define wasm_v64x2_shuffle(__a, __b, __c0, __c1)                               \
   ((v128_t)__builtin_wasm_shuffle_v8x16(                                       \
-      (__i8x16)(__a), (__i8x16)(__b), __c0 * 8, __c0 * 8 + 1, __c0 * 8 + 2,    \
-      __c0 * 8 + 3, __c0 * 8 + 4, __c0 * 8 + 5, __c0 * 8 + 6, __c0 * 8 + 7,    \
-      __c1 * 8, __c1 * 8 + 1, __c1 * 8 + 2, __c1 * 8 + 3, __c1 * 8 + 4,        \
-      __c1 * 8 + 5, __c1 * 8 + 6, __c1 * 8 + 7))
+      (__i8x16)(__a), (__i8x16)(__b), (__c0)*8, (__c0)*8 + 1, (__c0)*8 + 2,    \
+      (__c0)*8 + 3, (__c0)*8 + 4, (__c0)*8 + 5, (__c0)*8 + 6, (__c0)*8 + 7,    \
+      (__c1)*8, (__c1)*8 + 1, (__c1)*8 + 2, (__c1)*8 + 3, (__c1)*8 + 4,        \
+      (__c1)*8 + 5, (__c1)*8 + 6, (__c1)*8 + 7))
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_v8x16_swizzle(v128_t __a,
                                                                v128_t __b) {
   return (v128_t)__builtin_wasm_swizzle_v8x16((__i8x16)__a, (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS
 wasm_i8x16_narrow_i16x8(v128_t __a, v128_t __b) {