deal issues 15595

[Clang] VectorExprEvaluator::VisitCallExpr / InterpretBuiltin - add MMX/SSE/AVX PHADD/SUB & HADDPS/D intrinsics to be used in constexpr #155395

Author: whyuuwang

clang/lib/Headers/avx2intrin.h

@@ -886,9 +886,8 @@ _mm256_hadd_epi16(__m256i __a, __m256i __b) {
 ///    A 256-bit vector of [8 x i32] containing one of the source operands.
 /// \returns A 256-bit vector of [8 x i32] containing the sums.
 static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
-_mm256_hadd_epi32(__m256i __a, __m256i __b)
-{
-    return (__m256i)__builtin_ia32_phaddd256((__v8si)__a, (__v8si)__b);
+_mm256_hadd_epi32(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_phaddd256((__v8si)__a, (__v8si)__b);
 }
 
 /// Horizontally adds the adjacent pairs of 16-bit integers from two 256-bit
@@ -987,9 +986,8 @@ _mm256_hsub_epi16(__m256i __a, __m256i __b) {
 ///    A 256-bit vector of [8 x i32] containing one of the source operands.
 /// \returns A 256-bit vector of [8 x i32] containing the differences.
 static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
-_mm256_hsub_epi32(__m256i __a, __m256i __b)
-{
-    return (__m256i)__builtin_ia32_phsubd256((__v8si)__a, (__v8si)__b);
+_mm256_hsub_epi32(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_phsubd256((__v8si)__a, (__v8si)__b);
 }
 
 /// Horizontally subtracts adjacent pairs of 16-bit integers from two 256-bit
@@ -1023,9 +1021,8 @@ _mm256_hsub_epi32(__m256i __a, __m256i __b)
 ///    A 256-bit vector of [16 x i16] containing one of the source operands.
 /// \returns A 256-bit vector of [16 x i16] containing the differences.
 static __inline__ __m256i __DEFAULT_FN_ATTRS256_CONSTEXPR
-_mm256_hsubs_epi16(__m256i __a, __m256i __b)
-{
-    return (__m256i)__builtin_ia32_phsubsw256((__v16hi)__a, (__v16hi)__b);
+_mm256_hsubs_epi16(__m256i __a, __m256i __b) {
+  return (__m256i)__builtin_ia32_phsubsw256((__v16hi)__a, (__v16hi)__b);
 }
 
 /// Multiplies each unsigned byte from the 256-bit integer vector in \a __a

clang/lib/Headers/avxintrin.h

@@ -704,8 +704,7 @@ _mm256_xor_ps(__m256 __a, __m256 __b)
 /// \returns A 256-bit vector of [4 x double] containing the horizontal sums of
 ///    both operands.
 static __inline __m256d __DEFAULT_FN_ATTRS_CONSTEXPR
-_mm256_hadd_pd(__m256d __a, __m256d __b)
-{
+_mm256_hadd_pd(__m256d __a, __m256d __b) {
   return (__m256d)__builtin_ia32_haddpd256((__v4df)__a, (__v4df)__b);
 }
 
@@ -726,8 +725,8 @@ _mm256_hadd_pd(__m256d __a, __m256d __b)
 ///    index 2, 3, 6, 7 of a vector of [8 x float].
 /// \returns A 256-bit vector of [8 x float] containing the horizontal sums of
 ///    both operands.
-static __inline __m256 __DEFAULT_FN_ATTRS_CONSTEXPR 
-_mm256_hadd_ps(__m256 __a, __m256 __b) {
+static __inline __m256 __DEFAULT_FN_ATTRS_CONSTEXPR _mm256_hadd_ps(__m256 __a,
+                                                                   __m256 __b) {
   return (__m256)__builtin_ia32_haddps256((__v8sf)__a, (__v8sf)__b);
 }
 
@@ -749,8 +748,7 @@ _mm256_hadd_ps(__m256 __a, __m256 __b) {
 /// \returns A 256-bit vector of [4 x double] containing the horizontal
 ///    differences of both operands.
 static __inline __m256d __DEFAULT_FN_ATTRS_CONSTEXPR
-_mm256_hsub_pd(__m256d __a, __m256d __b)
-{
+_mm256_hsub_pd(__m256d __a, __m256d __b) {
   return (__m256d)__builtin_ia32_hsubpd256((__v4df)__a, (__v4df)__b);
 }
 
@@ -771,9 +769,8 @@ _mm256_hsub_pd(__m256d __a, __m256d __b)
 ///    elements with index 2, 3, 6, 7 of a vector of [8 x float].
 /// \returns A 256-bit vector of [8 x float] containing the horizontal
 ///    differences of both operands.
-static __inline __m256 __DEFAULT_FN_ATTRS_CONSTEXPR
-_mm256_hsub_ps(__m256 __a, __m256 __b)
-{
+static __inline __m256 __DEFAULT_FN_ATTRS_CONSTEXPR _mm256_hsub_ps(__m256 __a,
+                                                                   __m256 __b) {
   return (__m256)__builtin_ia32_hsubps256((__v8sf)__a, (__v8sf)__b);
 }
 

clang/lib/Headers/pmmintrin.h

@@ -89,8 +89,8 @@ _mm_addsub_ps(__m128 __a, __m128 __b)
 ///    destination.
 /// \returns A 128-bit vector of [4 x float] containing the horizontal sums of
 ///    both operands.
-static __inline__ __m128 __DEFAULT_FN_ATTRS_CONSTEXPR 
-_mm_hadd_ps(__m128 __a, __m128 __b) {
+static __inline__ __m128 __DEFAULT_FN_ATTRS_CONSTEXPR _mm_hadd_ps(__m128 __a,
+                                                                  __m128 __b) {
   return __builtin_ia32_haddps((__v4sf)__a, (__v4sf)__b);
 }
 

clang/lib/Headers/tmmintrin.h

@@ -206,8 +206,7 @@ _mm_abs_epi32(__m128i __a) {
 ///    both operands.
 static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR
 _mm_hadd_epi16(__m128i __a, __m128i __b) {
-  return (__m128i)__builtin_ia32_phaddw128(
-      (__v8hi)__a, (__v8hi)__b);
+  return (__m128i)__builtin_ia32_phaddw128((__v8hi)__a, (__v8hi)__b);
 }
 
 /// Horizontally adds the adjacent pairs of values contained in 2 packed
@@ -249,8 +248,8 @@ _mm_hadd_epi32(__m128i __a, __m128i __b) {
 ///    destination.
 /// \returns A 64-bit vector of [4 x i16] containing the horizontal sums of both
 ///    operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR
- _mm_hadd_pi16(__m64 __a, __m64 __b) {
+static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR _mm_hadd_pi16(__m64 __a,
+                                                                   __m64 __b) {
   return __trunc64(__builtin_ia32_phaddw128(
       (__v8hi)__builtin_shufflevector(__a, __b, 0, 1), (__v8hi){}));
 }
@@ -272,11 +271,10 @@ static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR
 ///    destination.
 /// \returns A 64-bit vector of [2 x i32] containing the horizontal sums of both
 ///    operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR
-_mm_hadd_pi32(__m64 __a, __m64 __b)
-{
-    return __trunc64(__builtin_ia32_phaddd128(
-        (__v4si)__builtin_shufflevector(__a, __b, 0, 1), (__v4si){}));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR _mm_hadd_pi32(__m64 __a,
+                                                                   __m64 __b) {
+  return __trunc64(__builtin_ia32_phaddd128(
+      (__v4si)__builtin_shufflevector(__a, __b, 0, 1), (__v4si){}));
 }
 
 /// Horizontally adds, with saturation, the adjacent pairs of values contained
@@ -324,11 +322,10 @@ _mm_hadds_epi16(__m128i __a, __m128i __b) {
 ///    destination.
 /// \returns A 64-bit vector of [4 x i16] containing the horizontal saturated
 ///    sums of both operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR
-_mm_hadds_pi16(__m64 __a, __m64 __b)
-{
-    return __trunc64(__builtin_ia32_phaddsw128(
-        (__v8hi)__builtin_shufflevector(__a, __b, 0, 1), (__v8hi){}));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR _mm_hadds_pi16(__m64 __a,
+                                                                    __m64 __b) {
+  return __trunc64(__builtin_ia32_phaddsw128(
+      (__v8hi)__builtin_shufflevector(__a, __b, 0, 1), (__v8hi){}));
 }
 
 /// Horizontally subtracts the adjacent pairs of values contained in 2
@@ -392,11 +389,10 @@ _mm_hsub_epi32(__m128i __a, __m128i __b) {
 ///    the destination.
 /// \returns A 64-bit vector of [4 x i16] containing the horizontal differences
 ///    of both operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR
-_mm_hsub_pi16(__m64 __a, __m64 __b)
-{
-    return __trunc64(__builtin_ia32_phsubw128(
-        (__v8hi)__builtin_shufflevector(__a, __b, 0, 1), (__v8hi){}));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR _mm_hsub_pi16(__m64 __a,
+                                                                   __m64 __b) {
+  return __trunc64(__builtin_ia32_phsubw128(
+      (__v8hi)__builtin_shufflevector(__a, __b, 0, 1), (__v8hi){}));
 }
 
 /// Horizontally subtracts the adjacent pairs of values contained in 2
@@ -416,11 +412,10 @@ _mm_hsub_pi16(__m64 __a, __m64 __b)
 ///    the destination.
 /// \returns A 64-bit vector of [2 x i32] containing the horizontal differences
 ///    of both operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR
-_mm_hsub_pi32(__m64 __a, __m64 __b)
-{
-    return __trunc64(__builtin_ia32_phsubd128(
-        (__v4si)__builtin_shufflevector(__a, __b, 0, 1), (__v4si){}));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR _mm_hsub_pi32(__m64 __a,
+                                                                   __m64 __b) {
+  return __trunc64(__builtin_ia32_phsubd128(
+      (__v4si)__builtin_shufflevector(__a, __b, 0, 1), (__v4si){}));
 }
 
 /// Horizontally subtracts, with saturation, the adjacent pairs of values
@@ -468,11 +463,10 @@ _mm_hsubs_epi16(__m128i __a, __m128i __b) {
 ///    the destination.
 /// \returns A 64-bit vector of [4 x i16] containing the horizontal saturated
 ///    differences of both operands.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR
-_mm_hsubs_pi16(__m64 __a, __m64 __b)
-{
-    return __trunc64(__builtin_ia32_phsubsw128(
-        (__v8hi)__builtin_shufflevector(__a, __b, 0, 1), (__v8hi){}));
+static __inline__ __m64 __DEFAULT_FN_ATTRS_CONSTEXPR _mm_hsubs_pi16(__m64 __a,
+                                                                    __m64 __b) {
+  return __trunc64(__builtin_ia32_phsubsw128(
+      (__v8hi)__builtin_shufflevector(__a, __b, 0, 1), (__v8hi){}));
 }
 
 /// Multiplies corresponding pairs of packed 8-bit unsigned integer
@@ -553,9 +547,8 @@ _mm_maddubs_pi16(__m64 __a, __m64 __b) {
 /// \returns A 128-bit vector of [8 x i16] containing the rounded and scaled
 ///    products of both operands.
 static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR
-_mm_mulhrs_epi16(__m128i __a, __m128i __b)
-{
-    return (__m128i)__builtin_ia32_pmulhrsw128((__v8hi)__a, (__v8hi)__b);
+_mm_mulhrs_epi16(__m128i __a, __m128i __b) {
+  return (__m128i)__builtin_ia32_pmulhrsw128((__v8hi)__a, (__v8hi)__b);
 }
 
 /// Multiplies packed 16-bit signed integer values, truncates the 32-bit