@nativescript/visionos 8.6.0-alpha.0 → 8.7.0-rc.0

package/framework/internal/metadata-generator-x86_64/bin/lib/clang/{13.0.1 → 15.0.7}/include/avx512dqintrin.h

@@ -121,10 +121,10 @@ _kadd_mask16(__mmask16 __A, __mmask16 __B)
 }
 
 #define _kshiftli_mask8(A, I) \
-  (__mmask8)__builtin_ia32_kshiftliqi((__mmask8)(A), (unsigned int)(I))
+  ((__mmask8)__builtin_ia32_kshiftliqi((__mmask8)(A), (unsigned int)(I)))
 
 #define _kshiftri_mask8(A, I) \
-  (__mmask8)__builtin_ia32_kshiftriqi((__mmask8)(A), (unsigned int)(I))
+  ((__mmask8)__builtin_ia32_kshiftriqi((__mmask8)(A), (unsigned int)(I)))
 
 static __inline__ unsigned int __DEFAULT_FN_ATTRS
 _cvtmask8_u32(__mmask8 __A) {
@@ -342,19 +342,19 @@ _mm512_maskz_cvtpd_epi64 (__mmask8 __U, __m512d __A) {
 }
 
 #define _mm512_cvt_roundpd_epi64(A, R) \
-  (__m512i)__builtin_ia32_cvtpd2qq512_mask((__v8df)(__m512d)(A), \
-                                           (__v8di)_mm512_setzero_si512(), \
-                                           (__mmask8)-1, (int)(R))
+  ((__m512i)__builtin_ia32_cvtpd2qq512_mask((__v8df)(__m512d)(A), \
+                                            (__v8di)_mm512_setzero_si512(), \
+                                            (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_cvt_roundpd_epi64(W, U, A, R) \
-  (__m512i)__builtin_ia32_cvtpd2qq512_mask((__v8df)(__m512d)(A), \
-                                           (__v8di)(__m512i)(W), \
-                                           (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvtpd2qq512_mask((__v8df)(__m512d)(A), \
+                                            (__v8di)(__m512i)(W), \
+                                            (__mmask8)(U), (int)(R)))
 
 #define _mm512_maskz_cvt_roundpd_epi64(U, A, R) \
-  (__m512i)__builtin_ia32_cvtpd2qq512_mask((__v8df)(__m512d)(A), \
-                                           (__v8di)_mm512_setzero_si512(), \
-                                           (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvtpd2qq512_mask((__v8df)(__m512d)(A), \
+                                            (__v8di)_mm512_setzero_si512(), \
+                                            (__mmask8)(U), (int)(R)))
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS512
 _mm512_cvtpd_epu64 (__m512d __A) {
@@ -381,19 +381,19 @@ _mm512_maskz_cvtpd_epu64 (__mmask8 __U, __m512d __A) {
 }
 
 #define _mm512_cvt_roundpd_epu64(A, R) \
-  (__m512i)__builtin_ia32_cvtpd2uqq512_mask((__v8df)(__m512d)(A), \
-                                            (__v8di)_mm512_setzero_si512(), \
-                                            (__mmask8)-1, (int)(R))
+  ((__m512i)__builtin_ia32_cvtpd2uqq512_mask((__v8df)(__m512d)(A), \
+                                             (__v8di)_mm512_setzero_si512(), \
+                                             (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_cvt_roundpd_epu64(W, U, A, R) \
-  (__m512i)__builtin_ia32_cvtpd2uqq512_mask((__v8df)(__m512d)(A), \
-                                            (__v8di)(__m512i)(W), \
-                                            (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvtpd2uqq512_mask((__v8df)(__m512d)(A), \
+                                             (__v8di)(__m512i)(W), \
+                                             (__mmask8)(U), (int)(R)))
 
 #define _mm512_maskz_cvt_roundpd_epu64(U, A, R) \
-  (__m512i)__builtin_ia32_cvtpd2uqq512_mask((__v8df)(__m512d)(A), \
-                                            (__v8di)_mm512_setzero_si512(), \
-                                            (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvtpd2uqq512_mask((__v8df)(__m512d)(A), \
+                                             (__v8di)_mm512_setzero_si512(), \
+                                             (__mmask8)(U), (int)(R)))
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS512
 _mm512_cvtps_epi64 (__m256 __A) {
@@ -420,19 +420,19 @@ _mm512_maskz_cvtps_epi64 (__mmask8 __U, __m256 __A) {
 }
 
 #define _mm512_cvt_roundps_epi64(A, R) \
-  (__m512i)__builtin_ia32_cvtps2qq512_mask((__v8sf)(__m256)(A), \
-                                           (__v8di)_mm512_setzero_si512(), \
-                                           (__mmask8)-1, (int)(R))
+  ((__m512i)__builtin_ia32_cvtps2qq512_mask((__v8sf)(__m256)(A), \
+                                            (__v8di)_mm512_setzero_si512(), \
+                                            (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_cvt_roundps_epi64(W, U, A, R) \
-  (__m512i)__builtin_ia32_cvtps2qq512_mask((__v8sf)(__m256)(A), \
-                                           (__v8di)(__m512i)(W), \
-                                           (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvtps2qq512_mask((__v8sf)(__m256)(A), \
+                                            (__v8di)(__m512i)(W), \
+                                            (__mmask8)(U), (int)(R)))
 
 #define _mm512_maskz_cvt_roundps_epi64(U, A, R) \
-  (__m512i)__builtin_ia32_cvtps2qq512_mask((__v8sf)(__m256)(A), \
-                                           (__v8di)_mm512_setzero_si512(), \
-                                           (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvtps2qq512_mask((__v8sf)(__m256)(A), \
+                                            (__v8di)_mm512_setzero_si512(), \
+                                            (__mmask8)(U), (int)(R)))
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS512
 _mm512_cvtps_epu64 (__m256 __A) {
@@ -459,19 +459,19 @@ _mm512_maskz_cvtps_epu64 (__mmask8 __U, __m256 __A) {
 }
 
 #define _mm512_cvt_roundps_epu64(A, R) \
-  (__m512i)__builtin_ia32_cvtps2uqq512_mask((__v8sf)(__m256)(A), \
-                                            (__v8di)_mm512_setzero_si512(), \
-                                            (__mmask8)-1, (int)(R))
+  ((__m512i)__builtin_ia32_cvtps2uqq512_mask((__v8sf)(__m256)(A), \
+                                             (__v8di)_mm512_setzero_si512(), \
+                                             (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_cvt_roundps_epu64(W, U, A, R) \
-  (__m512i)__builtin_ia32_cvtps2uqq512_mask((__v8sf)(__m256)(A), \
-                                            (__v8di)(__m512i)(W), \
-                                            (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvtps2uqq512_mask((__v8sf)(__m256)(A), \
+                                             (__v8di)(__m512i)(W), \
+                                             (__mmask8)(U), (int)(R)))
 
 #define _mm512_maskz_cvt_roundps_epu64(U, A, R) \
-  (__m512i)__builtin_ia32_cvtps2uqq512_mask((__v8sf)(__m256)(A), \
-                                            (__v8di)_mm512_setzero_si512(), \
-                                            (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvtps2uqq512_mask((__v8sf)(__m256)(A), \
+                                             (__v8di)_mm512_setzero_si512(), \
+                                             (__mmask8)(U), (int)(R)))
 
 
 static __inline__ __m512d __DEFAULT_FN_ATTRS512
@@ -494,19 +494,19 @@ _mm512_maskz_cvtepi64_pd (__mmask8 __U, __m512i __A) {
 }
 
 #define _mm512_cvt_roundepi64_pd(A, R) \
-  (__m512d)__builtin_ia32_cvtqq2pd512_mask((__v8di)(__m512i)(A), \
-                                           (__v8df)_mm512_setzero_pd(), \
-                                           (__mmask8)-1, (int)(R))
+  ((__m512d)__builtin_ia32_cvtqq2pd512_mask((__v8di)(__m512i)(A), \
+                                            (__v8df)_mm512_setzero_pd(), \
+                                            (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_cvt_roundepi64_pd(W, U, A, R) \
-  (__m512d)__builtin_ia32_cvtqq2pd512_mask((__v8di)(__m512i)(A), \
-                                           (__v8df)(__m512d)(W), \
-                                           (__mmask8)(U), (int)(R))
+  ((__m512d)__builtin_ia32_cvtqq2pd512_mask((__v8di)(__m512i)(A), \
+                                            (__v8df)(__m512d)(W), \
+                                            (__mmask8)(U), (int)(R)))
 
 #define _mm512_maskz_cvt_roundepi64_pd(U, A, R) \
-  (__m512d)__builtin_ia32_cvtqq2pd512_mask((__v8di)(__m512i)(A), \
-                                           (__v8df)_mm512_setzero_pd(), \
-                                           (__mmask8)(U), (int)(R))
+  ((__m512d)__builtin_ia32_cvtqq2pd512_mask((__v8di)(__m512i)(A), \
+                                            (__v8df)_mm512_setzero_pd(), \
+                                            (__mmask8)(U), (int)(R)))
 
 static __inline__ __m256 __DEFAULT_FN_ATTRS512
 _mm512_cvtepi64_ps (__m512i __A) {
@@ -533,19 +533,19 @@ _mm512_maskz_cvtepi64_ps (__mmask8 __U, __m512i __A) {
 }
 
 #define _mm512_cvt_roundepi64_ps(A, R) \
-  (__m256)__builtin_ia32_cvtqq2ps512_mask((__v8di)(__m512i)(A), \
-                                          (__v8sf)_mm256_setzero_ps(), \
-                                          (__mmask8)-1, (int)(R))
+  ((__m256)__builtin_ia32_cvtqq2ps512_mask((__v8di)(__m512i)(A), \
+                                           (__v8sf)_mm256_setzero_ps(), \
+                                           (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_cvt_roundepi64_ps(W, U, A, R) \
-  (__m256)__builtin_ia32_cvtqq2ps512_mask((__v8di)(__m512i)(A), \
-                                          (__v8sf)(__m256)(W), (__mmask8)(U), \
-                                          (int)(R))
+  ((__m256)__builtin_ia32_cvtqq2ps512_mask((__v8di)(__m512i)(A), \
+                                           (__v8sf)(__m256)(W), (__mmask8)(U), \
+                                           (int)(R)))
 
 #define _mm512_maskz_cvt_roundepi64_ps(U, A, R) \
-  (__m256)__builtin_ia32_cvtqq2ps512_mask((__v8di)(__m512i)(A), \
-                                          (__v8sf)_mm256_setzero_ps(), \
-                                          (__mmask8)(U), (int)(R))
+  ((__m256)__builtin_ia32_cvtqq2ps512_mask((__v8di)(__m512i)(A), \
+                                           (__v8sf)_mm256_setzero_ps(), \
+                                           (__mmask8)(U), (int)(R)))
 
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS512
@@ -573,19 +573,19 @@ _mm512_maskz_cvttpd_epi64 (__mmask8 __U, __m512d __A) {
 }
 
 #define _mm512_cvtt_roundpd_epi64(A, R) \
-  (__m512i)__builtin_ia32_cvttpd2qq512_mask((__v8df)(__m512d)(A), \
-                                            (__v8di)_mm512_setzero_si512(), \
-                                            (__mmask8)-1, (int)(R))
+  ((__m512i)__builtin_ia32_cvttpd2qq512_mask((__v8df)(__m512d)(A), \
+                                             (__v8di)_mm512_setzero_si512(), \
+                                             (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_cvtt_roundpd_epi64(W, U, A, R) \
-  (__m512i)__builtin_ia32_cvttpd2qq512_mask((__v8df)(__m512d)(A), \
-                                            (__v8di)(__m512i)(W), \
-                                            (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvttpd2qq512_mask((__v8df)(__m512d)(A), \
+                                             (__v8di)(__m512i)(W), \
+                                             (__mmask8)(U), (int)(R)))
 
 #define _mm512_maskz_cvtt_roundpd_epi64(U, A, R) \
-  (__m512i)__builtin_ia32_cvttpd2qq512_mask((__v8df)(__m512d)(A), \
-                                            (__v8di)_mm512_setzero_si512(), \
-                                            (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvttpd2qq512_mask((__v8df)(__m512d)(A), \
+                                             (__v8di)_mm512_setzero_si512(), \
+                                             (__mmask8)(U), (int)(R)))
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS512
 _mm512_cvttpd_epu64 (__m512d __A) {
@@ -612,19 +612,19 @@ _mm512_maskz_cvttpd_epu64 (__mmask8 __U, __m512d __A) {
 }
 
 #define _mm512_cvtt_roundpd_epu64(A, R) \
-  (__m512i)__builtin_ia32_cvttpd2uqq512_mask((__v8df)(__m512d)(A), \
-                                             (__v8di)_mm512_setzero_si512(), \
-                                             (__mmask8)-1, (int)(R))
+  ((__m512i)__builtin_ia32_cvttpd2uqq512_mask((__v8df)(__m512d)(A), \
+                                              (__v8di)_mm512_setzero_si512(), \
+                                              (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_cvtt_roundpd_epu64(W, U, A, R) \
-  (__m512i)__builtin_ia32_cvttpd2uqq512_mask((__v8df)(__m512d)(A), \
-                                             (__v8di)(__m512i)(W), \
-                                             (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvttpd2uqq512_mask((__v8df)(__m512d)(A), \
+                                              (__v8di)(__m512i)(W), \
+                                              (__mmask8)(U), (int)(R)))
 
 #define _mm512_maskz_cvtt_roundpd_epu64(U, A, R) \
-  (__m512i)__builtin_ia32_cvttpd2uqq512_mask((__v8df)(__m512d)(A), \
-                                             (__v8di)_mm512_setzero_si512(), \
-                                             (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvttpd2uqq512_mask((__v8df)(__m512d)(A), \
+                                              (__v8di)_mm512_setzero_si512(), \
+                                              (__mmask8)(U), (int)(R)))
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS512
 _mm512_cvttps_epi64 (__m256 __A) {
@@ -651,19 +651,19 @@ _mm512_maskz_cvttps_epi64 (__mmask8 __U, __m256 __A) {
 }
 
 #define _mm512_cvtt_roundps_epi64(A, R) \
-  (__m512i)__builtin_ia32_cvttps2qq512_mask((__v8sf)(__m256)(A), \
-                                            (__v8di)_mm512_setzero_si512(), \
-                                            (__mmask8)-1, (int)(R))
+  ((__m512i)__builtin_ia32_cvttps2qq512_mask((__v8sf)(__m256)(A), \
+                                             (__v8di)_mm512_setzero_si512(), \
+                                             (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_cvtt_roundps_epi64(W, U, A, R) \
-  (__m512i)__builtin_ia32_cvttps2qq512_mask((__v8sf)(__m256)(A), \
-                                            (__v8di)(__m512i)(W), \
-                                            (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvttps2qq512_mask((__v8sf)(__m256)(A), \
+                                             (__v8di)(__m512i)(W), \
+                                             (__mmask8)(U), (int)(R)))
 
 #define _mm512_maskz_cvtt_roundps_epi64(U, A, R) \
-  (__m512i)__builtin_ia32_cvttps2qq512_mask((__v8sf)(__m256)(A), \
-                                            (__v8di)_mm512_setzero_si512(), \
-                                            (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvttps2qq512_mask((__v8sf)(__m256)(A), \
+                                             (__v8di)_mm512_setzero_si512(), \
+                                             (__mmask8)(U), (int)(R)))
 
 static __inline__ __m512i __DEFAULT_FN_ATTRS512
 _mm512_cvttps_epu64 (__m256 __A) {
@@ -690,19 +690,19 @@ _mm512_maskz_cvttps_epu64 (__mmask8 __U, __m256 __A) {
 }
 
 #define _mm512_cvtt_roundps_epu64(A, R) \
-  (__m512i)__builtin_ia32_cvttps2uqq512_mask((__v8sf)(__m256)(A), \
-                                             (__v8di)_mm512_setzero_si512(), \
-                                             (__mmask8)-1, (int)(R))
+  ((__m512i)__builtin_ia32_cvttps2uqq512_mask((__v8sf)(__m256)(A), \
+                                              (__v8di)_mm512_setzero_si512(), \
+                                              (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_cvtt_roundps_epu64(W, U, A, R) \
-  (__m512i)__builtin_ia32_cvttps2uqq512_mask((__v8sf)(__m256)(A), \
-                                             (__v8di)(__m512i)(W), \
-                                             (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvttps2uqq512_mask((__v8sf)(__m256)(A), \
+                                              (__v8di)(__m512i)(W), \
+                                              (__mmask8)(U), (int)(R)))
 
 #define _mm512_maskz_cvtt_roundps_epu64(U, A, R) \
-  (__m512i)__builtin_ia32_cvttps2uqq512_mask((__v8sf)(__m256)(A), \
-                                             (__v8di)_mm512_setzero_si512(), \
-                                             (__mmask8)(U), (int)(R))
+  ((__m512i)__builtin_ia32_cvttps2uqq512_mask((__v8sf)(__m256)(A), \
+                                              (__v8di)_mm512_setzero_si512(), \
+                                              (__mmask8)(U), (int)(R)))
 
 static __inline__ __m512d __DEFAULT_FN_ATTRS512
 _mm512_cvtepu64_pd (__m512i __A) {
@@ -724,20 +724,20 @@ _mm512_maskz_cvtepu64_pd (__mmask8 __U, __m512i __A) {
 }
 
 #define _mm512_cvt_roundepu64_pd(A, R) \
-  (__m512d)__builtin_ia32_cvtuqq2pd512_mask((__v8di)(__m512i)(A), \
-                                            (__v8df)_mm512_setzero_pd(), \
-                                            (__mmask8)-1, (int)(R))
+  ((__m512d)__builtin_ia32_cvtuqq2pd512_mask((__v8di)(__m512i)(A), \
+                                             (__v8df)_mm512_setzero_pd(), \
+                                             (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_cvt_roundepu64_pd(W, U, A, R) \
-  (__m512d)__builtin_ia32_cvtuqq2pd512_mask((__v8di)(__m512i)(A), \
-                                            (__v8df)(__m512d)(W), \
-                                            (__mmask8)(U), (int)(R))
+  ((__m512d)__builtin_ia32_cvtuqq2pd512_mask((__v8di)(__m512i)(A), \
+                                             (__v8df)(__m512d)(W), \
+                                             (__mmask8)(U), (int)(R)))
 
 
 #define _mm512_maskz_cvt_roundepu64_pd(U, A, R) \
-  (__m512d)__builtin_ia32_cvtuqq2pd512_mask((__v8di)(__m512i)(A), \
-                                            (__v8df)_mm512_setzero_pd(), \
-                                            (__mmask8)(U), (int)(R))
+  ((__m512d)__builtin_ia32_cvtuqq2pd512_mask((__v8di)(__m512i)(A), \
+                                             (__v8df)_mm512_setzero_pd(), \
+                                             (__mmask8)(U), (int)(R)))
 
 
 static __inline__ __m256 __DEFAULT_FN_ATTRS512
@@ -765,290 +765,290 @@ _mm512_maskz_cvtepu64_ps (__mmask8 __U, __m512i __A) {
 }
 
 #define _mm512_cvt_roundepu64_ps(A, R) \
-  (__m256)__builtin_ia32_cvtuqq2ps512_mask((__v8di)(__m512i)(A), \
-                                           (__v8sf)_mm256_setzero_ps(), \
-                                           (__mmask8)-1, (int)(R))
+  ((__m256)__builtin_ia32_cvtuqq2ps512_mask((__v8di)(__m512i)(A), \
+                                            (__v8sf)_mm256_setzero_ps(), \
+                                            (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_cvt_roundepu64_ps(W, U, A, R) \
-  (__m256)__builtin_ia32_cvtuqq2ps512_mask((__v8di)(__m512i)(A), \
-                                           (__v8sf)(__m256)(W), (__mmask8)(U), \
-                                           (int)(R))
+  ((__m256)__builtin_ia32_cvtuqq2ps512_mask((__v8di)(__m512i)(A), \
+                                            (__v8sf)(__m256)(W), (__mmask8)(U), \
+                                            (int)(R)))
 
 #define _mm512_maskz_cvt_roundepu64_ps(U, A, R) \
-  (__m256)__builtin_ia32_cvtuqq2ps512_mask((__v8di)(__m512i)(A), \
-                                           (__v8sf)_mm256_setzero_ps(), \
-                                           (__mmask8)(U), (int)(R))
+  ((__m256)__builtin_ia32_cvtuqq2ps512_mask((__v8di)(__m512i)(A), \
+                                            (__v8sf)_mm256_setzero_ps(), \
+                                            (__mmask8)(U), (int)(R)))
 
 #define _mm512_range_pd(A, B, C) \
-  (__m512d)__builtin_ia32_rangepd512_mask((__v8df)(__m512d)(A), \
-                                          (__v8df)(__m512d)(B), (int)(C), \
-                                          (__v8df)_mm512_setzero_pd(), \
-                                          (__mmask8)-1, \
-                                          _MM_FROUND_CUR_DIRECTION)
+  ((__m512d)__builtin_ia32_rangepd512_mask((__v8df)(__m512d)(A), \
+                                           (__v8df)(__m512d)(B), (int)(C), \
+                                           (__v8df)_mm512_setzero_pd(), \
+                                           (__mmask8)-1, \
+                                           _MM_FROUND_CUR_DIRECTION))
 
 #define _mm512_mask_range_pd(W, U, A, B, C) \
-  (__m512d)__builtin_ia32_rangepd512_mask((__v8df)(__m512d)(A), \
-                                          (__v8df)(__m512d)(B), (int)(C), \
-                                          (__v8df)(__m512d)(W), (__mmask8)(U), \
-                                          _MM_FROUND_CUR_DIRECTION)
+  ((__m512d)__builtin_ia32_rangepd512_mask((__v8df)(__m512d)(A), \
+                                           (__v8df)(__m512d)(B), (int)(C), \
+                                           (__v8df)(__m512d)(W), (__mmask8)(U), \
+                                           _MM_FROUND_CUR_DIRECTION))
 
 #define _mm512_maskz_range_pd(U, A, B, C) \
-  (__m512d)__builtin_ia32_rangepd512_mask((__v8df)(__m512d)(A), \
-                                          (__v8df)(__m512d)(B), (int)(C), \
-                                          (__v8df)_mm512_setzero_pd(), \
-                                          (__mmask8)(U), \
-                                          _MM_FROUND_CUR_DIRECTION)
+  ((__m512d)__builtin_ia32_rangepd512_mask((__v8df)(__m512d)(A), \
+                                           (__v8df)(__m512d)(B), (int)(C), \
+                                           (__v8df)_mm512_setzero_pd(), \
+                                           (__mmask8)(U), \
+                                           _MM_FROUND_CUR_DIRECTION))
 
 #define _mm512_range_round_pd(A, B, C, R) \
-  (__m512d)__builtin_ia32_rangepd512_mask((__v8df)(__m512d)(A), \
-                                          (__v8df)(__m512d)(B), (int)(C), \
-                                          (__v8df)_mm512_setzero_pd(), \
-                                          (__mmask8)-1, (int)(R))
+  ((__m512d)__builtin_ia32_rangepd512_mask((__v8df)(__m512d)(A), \
+                                           (__v8df)(__m512d)(B), (int)(C), \
+                                           (__v8df)_mm512_setzero_pd(), \
+                                           (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_range_round_pd(W, U, A, B, C, R) \
-  (__m512d)__builtin_ia32_rangepd512_mask((__v8df)(__m512d)(A), \
-                                          (__v8df)(__m512d)(B), (int)(C), \
-                                          (__v8df)(__m512d)(W), (__mmask8)(U), \
-                                          (int)(R))
+  ((__m512d)__builtin_ia32_rangepd512_mask((__v8df)(__m512d)(A), \
+                                           (__v8df)(__m512d)(B), (int)(C), \
+                                           (__v8df)(__m512d)(W), (__mmask8)(U), \
+                                           (int)(R)))
 
 #define _mm512_maskz_range_round_pd(U, A, B, C, R) \
-  (__m512d)__builtin_ia32_rangepd512_mask((__v8df)(__m512d)(A), \
-                                          (__v8df)(__m512d)(B), (int)(C), \
-                                          (__v8df)_mm512_setzero_pd(), \
-                                          (__mmask8)(U), (int)(R))
+  ((__m512d)__builtin_ia32_rangepd512_mask((__v8df)(__m512d)(A), \
+                                           (__v8df)(__m512d)(B), (int)(C), \
+                                           (__v8df)_mm512_setzero_pd(), \
+                                           (__mmask8)(U), (int)(R)))
 
 #define _mm512_range_ps(A, B, C) \
-  (__m512)__builtin_ia32_rangeps512_mask((__v16sf)(__m512)(A), \
-                                         (__v16sf)(__m512)(B), (int)(C), \
-                                         (__v16sf)_mm512_setzero_ps(), \
-                                         (__mmask16)-1, \
-                                         _MM_FROUND_CUR_DIRECTION)
+  ((__m512)__builtin_ia32_rangeps512_mask((__v16sf)(__m512)(A), \
+                                          (__v16sf)(__m512)(B), (int)(C), \
+                                          (__v16sf)_mm512_setzero_ps(), \
+                                          (__mmask16)-1, \
+                                          _MM_FROUND_CUR_DIRECTION))
 
 #define _mm512_mask_range_ps(W, U, A, B, C) \
-  (__m512)__builtin_ia32_rangeps512_mask((__v16sf)(__m512)(A), \
-                                         (__v16sf)(__m512)(B), (int)(C), \
-                                         (__v16sf)(__m512)(W), (__mmask16)(U), \
-                                         _MM_FROUND_CUR_DIRECTION)
+  ((__m512)__builtin_ia32_rangeps512_mask((__v16sf)(__m512)(A), \
+                                          (__v16sf)(__m512)(B), (int)(C), \
+                                          (__v16sf)(__m512)(W), (__mmask16)(U), \
+                                          _MM_FROUND_CUR_DIRECTION))
 
 #define _mm512_maskz_range_ps(U, A, B, C) \
-  (__m512)__builtin_ia32_rangeps512_mask((__v16sf)(__m512)(A), \
-                                         (__v16sf)(__m512)(B), (int)(C), \
-                                         (__v16sf)_mm512_setzero_ps(), \
-                                         (__mmask16)(U), \
-                                         _MM_FROUND_CUR_DIRECTION)
+  ((__m512)__builtin_ia32_rangeps512_mask((__v16sf)(__m512)(A), \
+                                          (__v16sf)(__m512)(B), (int)(C), \
+                                          (__v16sf)_mm512_setzero_ps(), \
+                                          (__mmask16)(U), \
+                                          _MM_FROUND_CUR_DIRECTION))
 
 #define _mm512_range_round_ps(A, B, C, R) \
-  (__m512)__builtin_ia32_rangeps512_mask((__v16sf)(__m512)(A), \
-                                         (__v16sf)(__m512)(B), (int)(C), \
-                                         (__v16sf)_mm512_setzero_ps(), \
-                                         (__mmask16)-1, (int)(R))
+  ((__m512)__builtin_ia32_rangeps512_mask((__v16sf)(__m512)(A), \
+                                          (__v16sf)(__m512)(B), (int)(C), \
+                                          (__v16sf)_mm512_setzero_ps(), \
+                                          (__mmask16)-1, (int)(R)))
 
 #define _mm512_mask_range_round_ps(W, U, A, B, C, R) \
-  (__m512)__builtin_ia32_rangeps512_mask((__v16sf)(__m512)(A), \
-                                         (__v16sf)(__m512)(B), (int)(C), \
-                                         (__v16sf)(__m512)(W), (__mmask16)(U), \
-                                         (int)(R))
+  ((__m512)__builtin_ia32_rangeps512_mask((__v16sf)(__m512)(A), \
+                                          (__v16sf)(__m512)(B), (int)(C), \
+                                          (__v16sf)(__m512)(W), (__mmask16)(U), \
+                                          (int)(R)))
 
 #define _mm512_maskz_range_round_ps(U, A, B, C, R) \
-  (__m512)__builtin_ia32_rangeps512_mask((__v16sf)(__m512)(A), \
-                                         (__v16sf)(__m512)(B), (int)(C), \
-                                         (__v16sf)_mm512_setzero_ps(), \
-                                         (__mmask16)(U), (int)(R))
+  ((__m512)__builtin_ia32_rangeps512_mask((__v16sf)(__m512)(A), \
+                                          (__v16sf)(__m512)(B), (int)(C), \
+                                          (__v16sf)_mm512_setzero_ps(), \
+                                          (__mmask16)(U), (int)(R)))
 
 #define _mm_range_round_ss(A, B, C, R) \
-  (__m128)__builtin_ia32_rangess128_round_mask((__v4sf)(__m128)(A), \
-                                               (__v4sf)(__m128)(B), \
-                                               (__v4sf)_mm_setzero_ps(), \
-                                               (__mmask8) -1, (int)(C),\
-                                               (int)(R))
+  ((__m128)__builtin_ia32_rangess128_round_mask((__v4sf)(__m128)(A), \
+                                                (__v4sf)(__m128)(B), \
+                                                (__v4sf)_mm_setzero_ps(), \
+                                                (__mmask8) -1, (int)(C),\
+                                                (int)(R)))
 
 #define _mm_range_ss(A ,B , C) _mm_range_round_ss(A, B, C ,_MM_FROUND_CUR_DIRECTION)
 
 #define _mm_mask_range_round_ss(W, U, A, B, C, R) \
-  (__m128)__builtin_ia32_rangess128_round_mask((__v4sf)(__m128)(A), \
-                                               (__v4sf)(__m128)(B), \
-                                               (__v4sf)(__m128)(W),\
-                                               (__mmask8)(U), (int)(C),\
-                                               (int)(R))
+  ((__m128)__builtin_ia32_rangess128_round_mask((__v4sf)(__m128)(A), \
+                                                (__v4sf)(__m128)(B), \
+                                                (__v4sf)(__m128)(W),\
+                                                (__mmask8)(U), (int)(C),\
+                                                (int)(R)))
 
 #define _mm_mask_range_ss(W , U, A, B, C) _mm_mask_range_round_ss(W, U, A, B, C , _MM_FROUND_CUR_DIRECTION)
 
 #define _mm_maskz_range_round_ss(U, A, B, C, R) \
-  (__m128)__builtin_ia32_rangess128_round_mask((__v4sf)(__m128)(A), \
-                                               (__v4sf)(__m128)(B), \
-                                               (__v4sf)_mm_setzero_ps(), \
-                                               (__mmask8)(U), (int)(C),\
-                                               (int)(R))
+  ((__m128)__builtin_ia32_rangess128_round_mask((__v4sf)(__m128)(A), \
+                                                (__v4sf)(__m128)(B), \
+                                                (__v4sf)_mm_setzero_ps(), \
+                                                (__mmask8)(U), (int)(C),\
+                                                (int)(R)))
 
 #define _mm_maskz_range_ss(U, A ,B , C) _mm_maskz_range_round_ss(U, A, B, C ,_MM_FROUND_CUR_DIRECTION)
 
 #define _mm_range_round_sd(A, B, C, R) \
-  (__m128d)__builtin_ia32_rangesd128_round_mask((__v2df)(__m128d)(A), \
-                                                (__v2df)(__m128d)(B), \
-                                                (__v2df)_mm_setzero_pd(), \
-                                                (__mmask8) -1, (int)(C),\
-                                                (int)(R))
+  ((__m128d)__builtin_ia32_rangesd128_round_mask((__v2df)(__m128d)(A), \
+                                                 (__v2df)(__m128d)(B), \
+                                                 (__v2df)_mm_setzero_pd(), \
+                                                 (__mmask8) -1, (int)(C),\
+                                                 (int)(R)))
 
 #define _mm_range_sd(A ,B , C) _mm_range_round_sd(A, B, C ,_MM_FROUND_CUR_DIRECTION)
 
 #define _mm_mask_range_round_sd(W, U, A, B, C, R) \
-  (__m128d)__builtin_ia32_rangesd128_round_mask((__v2df)(__m128d)(A), \
-                                                (__v2df)(__m128d)(B), \
-                                                (__v2df)(__m128d)(W),\
-                                                (__mmask8)(U), (int)(C),\
-                                                (int)(R))
+  ((__m128d)__builtin_ia32_rangesd128_round_mask((__v2df)(__m128d)(A), \
+                                                 (__v2df)(__m128d)(B), \
+                                                 (__v2df)(__m128d)(W),\
+                                                 (__mmask8)(U), (int)(C),\
+                                                 (int)(R)))
 
 #define _mm_mask_range_sd(W, U, A, B, C) _mm_mask_range_round_sd(W, U, A, B, C ,_MM_FROUND_CUR_DIRECTION)
 
 #define _mm_maskz_range_round_sd(U, A, B, C, R) \
-  (__m128d)__builtin_ia32_rangesd128_round_mask((__v2df)(__m128d)(A), \
-                                                (__v2df)(__m128d)(B), \
-                                                (__v2df)_mm_setzero_pd(), \
-                                                (__mmask8)(U), (int)(C),\
-                                                (int)(R))
+  ((__m128d)__builtin_ia32_rangesd128_round_mask((__v2df)(__m128d)(A), \
+                                                 (__v2df)(__m128d)(B), \
+                                                 (__v2df)_mm_setzero_pd(), \
+                                                 (__mmask8)(U), (int)(C),\
+                                                 (int)(R)))
 
 #define _mm_maskz_range_sd(U, A, B, C) _mm_maskz_range_round_sd(U, A, B, C ,_MM_FROUND_CUR_DIRECTION)
 
 #define _mm512_reduce_pd(A, B) \
-  (__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
-                                           (__v8df)_mm512_setzero_pd(), \
-                                           (__mmask8)-1, \
-                                           _MM_FROUND_CUR_DIRECTION)
+  ((__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
+                                            (__v8df)_mm512_setzero_pd(), \
+                                            (__mmask8)-1, \
+                                            _MM_FROUND_CUR_DIRECTION))
 
 #define _mm512_mask_reduce_pd(W, U, A, B) \
-  (__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
-                                           (__v8df)(__m512d)(W), \
-                                           (__mmask8)(U), \
-                                           _MM_FROUND_CUR_DIRECTION)
+  ((__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
+                                            (__v8df)(__m512d)(W), \
+                                            (__mmask8)(U), \
+                                            _MM_FROUND_CUR_DIRECTION))
 
 #define _mm512_maskz_reduce_pd(U, A, B) \
-  (__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
-                                           (__v8df)_mm512_setzero_pd(), \
-                                           (__mmask8)(U), \
-                                           _MM_FROUND_CUR_DIRECTION)
+  ((__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
+                                            (__v8df)_mm512_setzero_pd(), \
+                                            (__mmask8)(U), \
+                                            _MM_FROUND_CUR_DIRECTION))
 
 #define _mm512_reduce_ps(A, B) \
-  (__m512)__builtin_ia32_reduceps512_mask((__v16sf)(__m512)(A), (int)(B), \
-                                          (__v16sf)_mm512_setzero_ps(), \
-                                          (__mmask16)-1, \
-                                          _MM_FROUND_CUR_DIRECTION)
+  ((__m512)__builtin_ia32_reduceps512_mask((__v16sf)(__m512)(A), (int)(B), \
+                                           (__v16sf)_mm512_setzero_ps(), \
+                                           (__mmask16)-1, \
+                                           _MM_FROUND_CUR_DIRECTION))
 
 #define _mm512_mask_reduce_ps(W, U, A, B) \
-  (__m512)__builtin_ia32_reduceps512_mask((__v16sf)(__m512)(A), (int)(B), \
-                                          (__v16sf)(__m512)(W), \
-                                          (__mmask16)(U), \
-                                          _MM_FROUND_CUR_DIRECTION)
+  ((__m512)__builtin_ia32_reduceps512_mask((__v16sf)(__m512)(A), (int)(B), \
+                                           (__v16sf)(__m512)(W), \
+                                           (__mmask16)(U), \
+                                           _MM_FROUND_CUR_DIRECTION))
 
 #define _mm512_maskz_reduce_ps(U, A, B) \
-  (__m512)__builtin_ia32_reduceps512_mask((__v16sf)(__m512)(A), (int)(B), \
-                                          (__v16sf)_mm512_setzero_ps(), \
-                                          (__mmask16)(U), \
-                                          _MM_FROUND_CUR_DIRECTION)
+  ((__m512)__builtin_ia32_reduceps512_mask((__v16sf)(__m512)(A), (int)(B), \
+                                           (__v16sf)_mm512_setzero_ps(), \
+                                           (__mmask16)(U), \
+                                           _MM_FROUND_CUR_DIRECTION))
 
 #define _mm512_reduce_round_pd(A, B, R) \
-  (__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
-                                           (__v8df)_mm512_setzero_pd(), \
-                                           (__mmask8)-1, (int)(R))
+  ((__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
+                                            (__v8df)_mm512_setzero_pd(), \
+                                            (__mmask8)-1, (int)(R)))
 
 #define _mm512_mask_reduce_round_pd(W, U, A, B, R) \
-  (__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
-                                           (__v8df)(__m512d)(W), \
-                                           (__mmask8)(U), (int)(R))
+  ((__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
+                                            (__v8df)(__m512d)(W), \
+                                            (__mmask8)(U), (int)(R)))
 
 #define _mm512_maskz_reduce_round_pd(U, A, B, R) \
-  (__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
-                                           (__v8df)_mm512_setzero_pd(), \
-                                           (__mmask8)(U), (int)(R))
+  ((__m512d)__builtin_ia32_reducepd512_mask((__v8df)(__m512d)(A), (int)(B), \
+                                            (__v8df)_mm512_setzero_pd(), \
+                                            (__mmask8)(U), (int)(R)))
 
 #define _mm512_reduce_round_ps(A, B, R) \
-  (__m512)__builtin_ia32_reduceps512_mask((__v16sf)(__m512)(A), (int)(B), \
-                                          (__v16sf)_mm512_setzero_ps(), \
-                                          (__mmask16)-1, (int)(R))
+  ((__m512)__builtin_ia32_reduceps512_mask((__v16sf)(__m512)(A), (int)(B), \
+                                           (__v16sf)_mm512_setzero_ps(), \
+                                           (__mmask16)-1, (int)(R)))
 
 #define _mm512_mask_reduce_round_ps(W, U, A, B, R) \
-  (__m512)__builtin_ia32_reduceps512_mask((__v16sf)(__m512)(A), (int)(B), \
-                                          (__v16sf)(__m512)(W), \
-                                          (__mmask16)(U), (int)(R))
+  ((__m512)__builtin_ia32_reduceps512_mask((__v16sf)(__m512)(A), (int)(B), \
+                                           (__v16sf)(__m512)(W), \
+                                           (__mmask16)(U), (int)(R)))
 
 #define _mm512_maskz_reduce_round_ps(U, A, B, R) \
-  (__m512)__builtin_ia32_reduceps512_mask((__v16sf)(__m512)(A), (int)(B), \
-                                          (__v16sf)_mm512_setzero_ps(), \
-                                          (__mmask16)(U), (int)(R))
+  ((__m512)__builtin_ia32_reduceps512_mask((__v16sf)(__m512)(A), (int)(B), \
+                                           (__v16sf)_mm512_setzero_ps(), \
+                                           (__mmask16)(U), (int)(R)))
 
 #define _mm_reduce_ss(A, B, C) \
-  (__m128)__builtin_ia32_reducess_mask((__v4sf)(__m128)(A), \
-                                       (__v4sf)(__m128)(B), \
-                                       (__v4sf)_mm_setzero_ps(), (__mmask8)-1, \
-                                       (int)(C), _MM_FROUND_CUR_DIRECTION)
+  ((__m128)__builtin_ia32_reducess_mask((__v4sf)(__m128)(A), \
+                                        (__v4sf)(__m128)(B), \
+                                        (__v4sf)_mm_setzero_ps(), (__mmask8)-1, \
+                                        (int)(C), _MM_FROUND_CUR_DIRECTION))
 
 #define _mm_mask_reduce_ss(W, U, A, B, C) \
-  (__m128)__builtin_ia32_reducess_mask((__v4sf)(__m128)(A), \
-                                       (__v4sf)(__m128)(B), \
-                                       (__v4sf)(__m128)(W), (__mmask8)(U), \
-                                       (int)(C), _MM_FROUND_CUR_DIRECTION)
+  ((__m128)__builtin_ia32_reducess_mask((__v4sf)(__m128)(A), \
+                                        (__v4sf)(__m128)(B), \
+                                        (__v4sf)(__m128)(W), (__mmask8)(U), \
+                                        (int)(C), _MM_FROUND_CUR_DIRECTION))
 
 #define _mm_maskz_reduce_ss(U, A, B, C) \
-  (__m128)__builtin_ia32_reducess_mask((__v4sf)(__m128)(A), \
-                                       (__v4sf)(__m128)(B), \
-                                       (__v4sf)_mm_setzero_ps(), \
-                                       (__mmask8)(U), (int)(C), \
-                                       _MM_FROUND_CUR_DIRECTION)
+  ((__m128)__builtin_ia32_reducess_mask((__v4sf)(__m128)(A), \
+                                        (__v4sf)(__m128)(B), \
+                                        (__v4sf)_mm_setzero_ps(), \
+                                        (__mmask8)(U), (int)(C), \
+                                        _MM_FROUND_CUR_DIRECTION))
 
 #define _mm_reduce_round_ss(A, B, C, R) \
-  (__m128)__builtin_ia32_reducess_mask((__v4sf)(__m128)(A), \
-                                       (__v4sf)(__m128)(B), \
-                                       (__v4sf)_mm_setzero_ps(), (__mmask8)-1, \
-                                       (int)(C), (int)(R))
+  ((__m128)__builtin_ia32_reducess_mask((__v4sf)(__m128)(A), \
+                                        (__v4sf)(__m128)(B), \
+                                        (__v4sf)_mm_setzero_ps(), (__mmask8)-1, \
+                                        (int)(C), (int)(R)))
 
 #define _mm_mask_reduce_round_ss(W, U, A, B, C, R) \
-  (__m128)__builtin_ia32_reducess_mask((__v4sf)(__m128)(A), \
-                                       (__v4sf)(__m128)(B), \
-                                       (__v4sf)(__m128)(W), (__mmask8)(U), \
-                                       (int)(C), (int)(R))
+  ((__m128)__builtin_ia32_reducess_mask((__v4sf)(__m128)(A), \
+                                        (__v4sf)(__m128)(B), \
+                                        (__v4sf)(__m128)(W), (__mmask8)(U), \
+                                        (int)(C), (int)(R)))
 
 #define _mm_maskz_reduce_round_ss(U, A, B, C, R) \
-  (__m128)__builtin_ia32_reducess_mask((__v4sf)(__m128)(A), \
-                                       (__v4sf)(__m128)(B), \
-                                       (__v4sf)_mm_setzero_ps(), \
-                                       (__mmask8)(U), (int)(C), (int)(R))
+  ((__m128)__builtin_ia32_reducess_mask((__v4sf)(__m128)(A), \
+                                        (__v4sf)(__m128)(B), \
+                                        (__v4sf)_mm_setzero_ps(), \
+                                        (__mmask8)(U), (int)(C), (int)(R)))
 
 #define _mm_reduce_sd(A, B, C) \
-  (__m128d)__builtin_ia32_reducesd_mask((__v2df)(__m128d)(A), \
-                                        (__v2df)(__m128d)(B), \
-                                        (__v2df)_mm_setzero_pd(), \
-                                        (__mmask8)-1, (int)(C), \
-                                        _MM_FROUND_CUR_DIRECTION)
+  ((__m128d)__builtin_ia32_reducesd_mask((__v2df)(__m128d)(A), \
+                                         (__v2df)(__m128d)(B), \
+                                         (__v2df)_mm_setzero_pd(), \
+                                         (__mmask8)-1, (int)(C), \
+                                         _MM_FROUND_CUR_DIRECTION))
 
 #define _mm_mask_reduce_sd(W, U, A, B, C) \
-  (__m128d)__builtin_ia32_reducesd_mask((__v2df)(__m128d)(A), \
-                                        (__v2df)(__m128d)(B), \
-                                        (__v2df)(__m128d)(W), (__mmask8)(U), \
-                                        (int)(C), _MM_FROUND_CUR_DIRECTION)
+  ((__m128d)__builtin_ia32_reducesd_mask((__v2df)(__m128d)(A), \
+                                         (__v2df)(__m128d)(B), \
+                                         (__v2df)(__m128d)(W), (__mmask8)(U), \
+                                         (int)(C), _MM_FROUND_CUR_DIRECTION))
 
 #define _mm_maskz_reduce_sd(U, A, B, C) \
-  (__m128d)__builtin_ia32_reducesd_mask((__v2df)(__m128d)(A), \
-                                        (__v2df)(__m128d)(B), \
-                                        (__v2df)_mm_setzero_pd(), \
-                                        (__mmask8)(U), (int)(C), \
-                                        _MM_FROUND_CUR_DIRECTION)
+  ((__m128d)__builtin_ia32_reducesd_mask((__v2df)(__m128d)(A), \
+                                         (__v2df)(__m128d)(B), \
+                                         (__v2df)_mm_setzero_pd(), \
+                                         (__mmask8)(U), (int)(C), \
+                                         _MM_FROUND_CUR_DIRECTION))
 
 #define _mm_reduce_round_sd(A, B, C, R) \
-  (__m128d)__builtin_ia32_reducesd_mask((__v2df)(__m128d)(A), \
-                                        (__v2df)(__m128d)(B), \
-                                        (__v2df)_mm_setzero_pd(), \
-                                        (__mmask8)-1, (int)(C), (int)(R))
+  ((__m128d)__builtin_ia32_reducesd_mask((__v2df)(__m128d)(A), \
+                                         (__v2df)(__m128d)(B), \
+                                         (__v2df)_mm_setzero_pd(), \
+                                         (__mmask8)-1, (int)(C), (int)(R)))
 
 #define _mm_mask_reduce_round_sd(W, U, A, B, C, R) \
-  (__m128d)__builtin_ia32_reducesd_mask((__v2df)(__m128d)(A), \
-                                        (__v2df)(__m128d)(B), \
-                                        (__v2df)(__m128d)(W), (__mmask8)(U), \
-                                        (int)(C), (int)(R))
+  ((__m128d)__builtin_ia32_reducesd_mask((__v2df)(__m128d)(A), \
+                                         (__v2df)(__m128d)(B), \
+                                         (__v2df)(__m128d)(W), (__mmask8)(U), \
+                                         (int)(C), (int)(R)))
 
 #define _mm_maskz_reduce_round_sd(U, A, B, C, R) \
-  (__m128d)__builtin_ia32_reducesd_mask((__v2df)(__m128d)(A), \
-                                        (__v2df)(__m128d)(B), \
-                                        (__v2df)_mm_setzero_pd(), \
-                                        (__mmask8)(U), (int)(C), (int)(R))
+  ((__m128d)__builtin_ia32_reducesd_mask((__v2df)(__m128d)(A), \
+                                         (__v2df)(__m128d)(B), \
+                                         (__v2df)_mm_setzero_pd(), \
+                                         (__mmask8)(U), (int)(C), (int)(R)))
 
 static __inline__ __mmask16 __DEFAULT_FN_ATTRS512
 _mm512_movepi32_mask (__m512i __A)
@@ -1218,158 +1218,158 @@ _mm512_maskz_broadcast_i64x2(__mmask8 __M, __m128i __A)
 }
 
 #define _mm512_extractf32x8_ps(A, imm) \
-  (__m256)__builtin_ia32_extractf32x8_mask((__v16sf)(__m512)(A), (int)(imm), \
-                                           (__v8sf)_mm256_undefined_ps(), \
-                                           (__mmask8)-1)
+  ((__m256)__builtin_ia32_extractf32x8_mask((__v16sf)(__m512)(A), (int)(imm), \
+                                            (__v8sf)_mm256_undefined_ps(), \
+                                            (__mmask8)-1))
 
 #define _mm512_mask_extractf32x8_ps(W, U, A, imm) \
-  (__m256)__builtin_ia32_extractf32x8_mask((__v16sf)(__m512)(A), (int)(imm), \
-                                           (__v8sf)(__m256)(W), \
-                                           (__mmask8)(U))
+  ((__m256)__builtin_ia32_extractf32x8_mask((__v16sf)(__m512)(A), (int)(imm), \
+                                            (__v8sf)(__m256)(W), \
+                                            (__mmask8)(U)))
 
 #define _mm512_maskz_extractf32x8_ps(U, A, imm) \
-  (__m256)__builtin_ia32_extractf32x8_mask((__v16sf)(__m512)(A), (int)(imm), \
-                                           (__v8sf)_mm256_setzero_ps(), \
-                                           (__mmask8)(U))
+  ((__m256)__builtin_ia32_extractf32x8_mask((__v16sf)(__m512)(A), (int)(imm), \
+                                            (__v8sf)_mm256_setzero_ps(), \
+                                            (__mmask8)(U)))
 
 #define _mm512_extractf64x2_pd(A, imm) \
-  (__m128d)__builtin_ia32_extractf64x2_512_mask((__v8df)(__m512d)(A), \
-                                                (int)(imm), \
-                                                (__v2df)_mm_undefined_pd(), \
-                                                (__mmask8)-1)
+  ((__m128d)__builtin_ia32_extractf64x2_512_mask((__v8df)(__m512d)(A), \
+                                                 (int)(imm), \
+                                                 (__v2df)_mm_undefined_pd(), \
+                                                 (__mmask8)-1))
 
 #define _mm512_mask_extractf64x2_pd(W, U, A, imm) \
-  (__m128d)__builtin_ia32_extractf64x2_512_mask((__v8df)(__m512d)(A), \
-                                                (int)(imm), \
-                                                (__v2df)(__m128d)(W), \
-                                                (__mmask8)(U))
+  ((__m128d)__builtin_ia32_extractf64x2_512_mask((__v8df)(__m512d)(A), \
+                                                 (int)(imm), \
+                                                 (__v2df)(__m128d)(W), \
+                                                 (__mmask8)(U)))
 
 #define _mm512_maskz_extractf64x2_pd(U, A, imm) \
-  (__m128d)__builtin_ia32_extractf64x2_512_mask((__v8df)(__m512d)(A), \
-                                                (int)(imm), \
-                                                (__v2df)_mm_setzero_pd(), \
-                                                (__mmask8)(U))
+  ((__m128d)__builtin_ia32_extractf64x2_512_mask((__v8df)(__m512d)(A), \
+                                                 (int)(imm), \
+                                                 (__v2df)_mm_setzero_pd(), \
+                                                 (__mmask8)(U)))
 
 #define _mm512_extracti32x8_epi32(A, imm) \
-  (__m256i)__builtin_ia32_extracti32x8_mask((__v16si)(__m512i)(A), (int)(imm), \
-                                            (__v8si)_mm256_undefined_si256(), \
-                                            (__mmask8)-1)
+  ((__m256i)__builtin_ia32_extracti32x8_mask((__v16si)(__m512i)(A), (int)(imm), \
+                                             (__v8si)_mm256_undefined_si256(), \
+                                             (__mmask8)-1))
 
 #define _mm512_mask_extracti32x8_epi32(W, U, A, imm) \
-  (__m256i)__builtin_ia32_extracti32x8_mask((__v16si)(__m512i)(A), (int)(imm), \
-                                            (__v8si)(__m256i)(W), \
-                                            (__mmask8)(U))
+  ((__m256i)__builtin_ia32_extracti32x8_mask((__v16si)(__m512i)(A), (int)(imm), \
+                                             (__v8si)(__m256i)(W), \
+                                             (__mmask8)(U)))
 
 #define _mm512_maskz_extracti32x8_epi32(U, A, imm) \
-  (__m256i)__builtin_ia32_extracti32x8_mask((__v16si)(__m512i)(A), (int)(imm), \
-                                            (__v8si)_mm256_setzero_si256(), \
-                                            (__mmask8)(U))
+  ((__m256i)__builtin_ia32_extracti32x8_mask((__v16si)(__m512i)(A), (int)(imm), \
+                                             (__v8si)_mm256_setzero_si256(), \
+                                             (__mmask8)(U)))
 
 #define _mm512_extracti64x2_epi64(A, imm) \
-  (__m128i)__builtin_ia32_extracti64x2_512_mask((__v8di)(__m512i)(A), \
+  ((__m128i)__builtin_ia32_extracti64x2_512_mask((__v8di)(__m512i)(A), \
                                                 (int)(imm), \
                                                 (__v2di)_mm_undefined_si128(), \
-                                                (__mmask8)-1)
+                                                (__mmask8)-1))
 
 #define _mm512_mask_extracti64x2_epi64(W, U, A, imm) \
-  (__m128i)__builtin_ia32_extracti64x2_512_mask((__v8di)(__m512i)(A), \
-                                                (int)(imm), \
-                                                (__v2di)(__m128i)(W), \
-                                                (__mmask8)(U))
+  ((__m128i)__builtin_ia32_extracti64x2_512_mask((__v8di)(__m512i)(A), \
+                                                 (int)(imm), \
+                                                 (__v2di)(__m128i)(W), \
+                                                 (__mmask8)(U)))
 
 #define _mm512_maskz_extracti64x2_epi64(U, A, imm) \
-  (__m128i)__builtin_ia32_extracti64x2_512_mask((__v8di)(__m512i)(A), \
-                                                (int)(imm), \
-                                                (__v2di)_mm_setzero_si128(), \
-                                                (__mmask8)(U))
+  ((__m128i)__builtin_ia32_extracti64x2_512_mask((__v8di)(__m512i)(A), \
+                                                 (int)(imm), \
+                                                 (__v2di)_mm_setzero_si128(), \
+                                                 (__mmask8)(U)))
 
 #define _mm512_insertf32x8(A, B, imm) \
-  (__m512)__builtin_ia32_insertf32x8((__v16sf)(__m512)(A), \
-                                     (__v8sf)(__m256)(B), (int)(imm))
+  ((__m512)__builtin_ia32_insertf32x8((__v16sf)(__m512)(A), \
+                                      (__v8sf)(__m256)(B), (int)(imm)))
 
 #define _mm512_mask_insertf32x8(W, U, A, B, imm) \
-  (__m512)__builtin_ia32_selectps_512((__mmask16)(U), \
+  ((__m512)__builtin_ia32_selectps_512((__mmask16)(U), \
                                  (__v16sf)_mm512_insertf32x8((A), (B), (imm)), \
-                                 (__v16sf)(__m512)(W))
+                                 (__v16sf)(__m512)(W)))
 
 #define _mm512_maskz_insertf32x8(U, A, B, imm) \
-  (__m512)__builtin_ia32_selectps_512((__mmask16)(U), \
+  ((__m512)__builtin_ia32_selectps_512((__mmask16)(U), \
                                  (__v16sf)_mm512_insertf32x8((A), (B), (imm)), \
-                                 (__v16sf)_mm512_setzero_ps())
+                                 (__v16sf)_mm512_setzero_ps()))
 
 #define _mm512_insertf64x2(A, B, imm) \
-  (__m512d)__builtin_ia32_insertf64x2_512((__v8df)(__m512d)(A), \
-                                          (__v2df)(__m128d)(B), (int)(imm))
+  ((__m512d)__builtin_ia32_insertf64x2_512((__v8df)(__m512d)(A), \
+                                           (__v2df)(__m128d)(B), (int)(imm)))
 
 #define _mm512_mask_insertf64x2(W, U, A, B, imm) \
-  (__m512d)__builtin_ia32_selectpd_512((__mmask8)(U), \
+  ((__m512d)__builtin_ia32_selectpd_512((__mmask8)(U), \
                                   (__v8df)_mm512_insertf64x2((A), (B), (imm)), \
-                                  (__v8df)(__m512d)(W))
+                                  (__v8df)(__m512d)(W)))
 
 #define _mm512_maskz_insertf64x2(U, A, B, imm) \
-  (__m512d)__builtin_ia32_selectpd_512((__mmask8)(U), \
+  ((__m512d)__builtin_ia32_selectpd_512((__mmask8)(U), \
                                   (__v8df)_mm512_insertf64x2((A), (B), (imm)), \
-                                  (__v8df)_mm512_setzero_pd())
+                                  (__v8df)_mm512_setzero_pd()))
 
 #define _mm512_inserti32x8(A, B, imm) \
-  (__m512i)__builtin_ia32_inserti32x8((__v16si)(__m512i)(A), \
-                                      (__v8si)(__m256i)(B), (int)(imm))
+  ((__m512i)__builtin_ia32_inserti32x8((__v16si)(__m512i)(A), \
+                                       (__v8si)(__m256i)(B), (int)(imm)))
 
 #define _mm512_mask_inserti32x8(W, U, A, B, imm) \
-  (__m512i)__builtin_ia32_selectd_512((__mmask16)(U), \
+  ((__m512i)__builtin_ia32_selectd_512((__mmask16)(U), \
                                  (__v16si)_mm512_inserti32x8((A), (B), (imm)), \
-                                 (__v16si)(__m512i)(W))
+                                 (__v16si)(__m512i)(W)))
 
 #define _mm512_maskz_inserti32x8(U, A, B, imm) \
-  (__m512i)__builtin_ia32_selectd_512((__mmask16)(U), \
+  ((__m512i)__builtin_ia32_selectd_512((__mmask16)(U), \
                                  (__v16si)_mm512_inserti32x8((A), (B), (imm)), \
-                                 (__v16si)_mm512_setzero_si512())
+                                 (__v16si)_mm512_setzero_si512()))
 
 #define _mm512_inserti64x2(A, B, imm) \
-  (__m512i)__builtin_ia32_inserti64x2_512((__v8di)(__m512i)(A), \
-                                          (__v2di)(__m128i)(B), (int)(imm))
+  ((__m512i)__builtin_ia32_inserti64x2_512((__v8di)(__m512i)(A), \
+                                           (__v2di)(__m128i)(B), (int)(imm)))
 
 #define _mm512_mask_inserti64x2(W, U, A, B, imm) \
-  (__m512i)__builtin_ia32_selectq_512((__mmask8)(U), \
+  ((__m512i)__builtin_ia32_selectq_512((__mmask8)(U), \
                                   (__v8di)_mm512_inserti64x2((A), (B), (imm)), \
-                                  (__v8di)(__m512i)(W))
+                                  (__v8di)(__m512i)(W)))
 
 #define _mm512_maskz_inserti64x2(U, A, B, imm) \
-  (__m512i)__builtin_ia32_selectq_512((__mmask8)(U), \
+  ((__m512i)__builtin_ia32_selectq_512((__mmask8)(U), \
                                   (__v8di)_mm512_inserti64x2((A), (B), (imm)), \
-                                  (__v8di)_mm512_setzero_si512())
+                                  (__v8di)_mm512_setzero_si512()))
 
 #define _mm512_mask_fpclass_ps_mask(U, A, imm) \
-  (__mmask16)__builtin_ia32_fpclassps512_mask((__v16sf)(__m512)(A), \
-                                              (int)(imm), (__mmask16)(U))
+  ((__mmask16)__builtin_ia32_fpclassps512_mask((__v16sf)(__m512)(A), \
+                                               (int)(imm), (__mmask16)(U)))
 
 #define _mm512_fpclass_ps_mask(A, imm) \
-  (__mmask16)__builtin_ia32_fpclassps512_mask((__v16sf)(__m512)(A), \
-                                              (int)(imm), (__mmask16)-1)
+  ((__mmask16)__builtin_ia32_fpclassps512_mask((__v16sf)(__m512)(A), \
+                                               (int)(imm), (__mmask16)-1))
 
 #define _mm512_mask_fpclass_pd_mask(U, A, imm) \
-  (__mmask8)__builtin_ia32_fpclasspd512_mask((__v8df)(__m512d)(A), (int)(imm), \
-                                             (__mmask8)(U))
+  ((__mmask8)__builtin_ia32_fpclasspd512_mask((__v8df)(__m512d)(A), (int)(imm), \
+                                              (__mmask8)(U)))
 
 #define _mm512_fpclass_pd_mask(A, imm) \
-  (__mmask8)__builtin_ia32_fpclasspd512_mask((__v8df)(__m512d)(A), (int)(imm), \
-                                             (__mmask8)-1)
+  ((__mmask8)__builtin_ia32_fpclasspd512_mask((__v8df)(__m512d)(A), (int)(imm), \
+                                              (__mmask8)-1))
 
 #define _mm_fpclass_sd_mask(A, imm) \
-  (__mmask8)__builtin_ia32_fpclasssd_mask((__v2df)(__m128d)(A), (int)(imm), \
-                                          (__mmask8)-1)
+  ((__mmask8)__builtin_ia32_fpclasssd_mask((__v2df)(__m128d)(A), (int)(imm), \
+                                           (__mmask8)-1))
 
 #define _mm_mask_fpclass_sd_mask(U, A, imm) \
-  (__mmask8)__builtin_ia32_fpclasssd_mask((__v2df)(__m128d)(A), (int)(imm), \
-                                          (__mmask8)(U))
+  ((__mmask8)__builtin_ia32_fpclasssd_mask((__v2df)(__m128d)(A), (int)(imm), \
+                                           (__mmask8)(U)))
 
 #define _mm_fpclass_ss_mask(A, imm) \
-  (__mmask8)__builtin_ia32_fpclassss_mask((__v4sf)(__m128)(A), (int)(imm), \
-                                          (__mmask8)-1)
+  ((__mmask8)__builtin_ia32_fpclassss_mask((__v4sf)(__m128)(A), (int)(imm), \
+                                           (__mmask8)-1))
 
 #define _mm_mask_fpclass_ss_mask(U, A, imm) \
-  (__mmask8)__builtin_ia32_fpclassss_mask((__v4sf)(__m128)(A), (int)(imm), \
-                                          (__mmask8)(U))
+  ((__mmask8)__builtin_ia32_fpclassss_mask((__v4sf)(__m128)(A), (int)(imm), \
+                                           (__mmask8)(U)))
 
 #undef __DEFAULT_FN_ATTRS512
 #undef __DEFAULT_FN_ATTRS