aboutsummaryrefslogtreecommitdiff
path: root/clang/lib/Headers
diff options
context:
space:
mode:
Diffstat (limited to 'clang/lib/Headers')
-rw-r--r--clang/lib/Headers/__clang_hip_runtime_wrapper.h1
-rw-r--r--clang/lib/Headers/avx2intrin.h5
-rw-r--r--clang/lib/Headers/avx512dqintrin.h34
-rw-r--r--clang/lib/Headers/avx512fintrin.h30
-rw-r--r--clang/lib/Headers/avx512vldqintrin.h18
-rw-r--r--clang/lib/Headers/avx512vlintrin.h18
-rw-r--r--clang/lib/Headers/avxintrin.h10
-rw-r--r--clang/lib/Headers/emmintrin.h6
-rw-r--r--clang/lib/Headers/smmintrin.h3
-rw-r--r--clang/lib/Headers/xmmintrin.h4
10 files changed, 61 insertions, 68 deletions
diff --git a/clang/lib/Headers/__clang_hip_runtime_wrapper.h b/clang/lib/Headers/__clang_hip_runtime_wrapper.h
index fb0ece9..19ce7a5 100644
--- a/clang/lib/Headers/__clang_hip_runtime_wrapper.h
+++ b/clang/lib/Headers/__clang_hip_runtime_wrapper.h
@@ -26,6 +26,7 @@
#define __managed__ __attribute__((managed))
#define __cluster_dims__(...) __attribute__((cluster_dims(__VA_ARGS__)))
+#define __no_cluster__ __attribute__((no_cluster))
#if !defined(__cplusplus) || __cplusplus < 201103L
#define nullptr NULL;
diff --git a/clang/lib/Headers/avx2intrin.h b/clang/lib/Headers/avx2intrin.h
index d35bc0e..fdb825f 100644
--- a/clang/lib/Headers/avx2intrin.h
+++ b/clang/lib/Headers/avx2intrin.h
@@ -1298,9 +1298,8 @@ _mm256_min_epu32(__m256i __a, __m256i __b) {
/// \param __a
/// A 256-bit integer vector containing the source bytes.
/// \returns The 32-bit integer mask.
-static __inline__ int __DEFAULT_FN_ATTRS256
-_mm256_movemask_epi8(__m256i __a)
-{
+static __inline__ int __DEFAULT_FN_ATTRS256_CONSTEXPR
+_mm256_movemask_epi8(__m256i __a) {
return __builtin_ia32_pmovmskb256((__v32qi)__a);
}
diff --git a/clang/lib/Headers/avx512dqintrin.h b/clang/lib/Headers/avx512dqintrin.h
index 3681cca..fef1a2d 100644
--- a/clang/lib/Headers/avx512dqintrin.h
+++ b/clang/lib/Headers/avx512dqintrin.h
@@ -1200,10 +1200,10 @@ _mm512_maskz_broadcast_i64x2(__mmask8 __M, __m128i __A) {
(__v8di)_mm512_setzero_si512());
}
-#define _mm512_extractf32x8_ps(A, imm) \
- ((__m256)__builtin_ia32_extractf32x8_mask((__v16sf)(__m512)(A), (int)(imm), \
- (__v8sf)_mm256_undefined_ps(), \
- (__mmask8)-1))
+#define _mm512_extractf32x8_ps(A, imm) \
+ ((__m256)__builtin_ia32_extractf32x8_mask((__v16sf)(__m512)(A), (int)(imm), \
+ (__v8sf)_mm256_setzero_ps(), \
+ (__mmask8) - 1))
#define _mm512_mask_extractf32x8_ps(W, U, A, imm) \
((__m256)__builtin_ia32_extractf32x8_mask((__v16sf)(__m512)(A), (int)(imm), \
@@ -1215,11 +1215,10 @@ _mm512_maskz_broadcast_i64x2(__mmask8 __M, __m128i __A) {
(__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))
+#define _mm512_extractf64x2_pd(A, imm) \
+ ((__m128d)__builtin_ia32_extractf64x2_512_mask( \
+ (__v8df)(__m512d)(A), (int)(imm), (__v2df)_mm_setzero_pd(), \
+ (__mmask8) - 1))
#define _mm512_mask_extractf64x2_pd(W, U, A, imm) \
((__m128d)__builtin_ia32_extractf64x2_512_mask((__v8df)(__m512d)(A), \
@@ -1233,10 +1232,10 @@ _mm512_maskz_broadcast_i64x2(__mmask8 __M, __m128i __A) {
(__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))
+#define _mm512_extracti32x8_epi32(A, imm) \
+ ((__m256i)__builtin_ia32_extracti32x8_mask( \
+ (__v16si)(__m512i)(A), (int)(imm), (__v8si)_mm256_setzero_si256(), \
+ (__mmask8) - 1))
#define _mm512_mask_extracti32x8_epi32(W, U, A, imm) \
((__m256i)__builtin_ia32_extracti32x8_mask((__v16si)(__m512i)(A), (int)(imm), \
@@ -1248,11 +1247,10 @@ _mm512_maskz_broadcast_i64x2(__mmask8 __M, __m128i __A) {
(__v8si)_mm256_setzero_si256(), \
(__mmask8)(U)))
-#define _mm512_extracti64x2_epi64(A, imm) \
- ((__m128i)__builtin_ia32_extracti64x2_512_mask((__v8di)(__m512i)(A), \
- (int)(imm), \
- (__v2di)_mm_undefined_si128(), \
- (__mmask8)-1))
+#define _mm512_extracti64x2_epi64(A, imm) \
+ ((__m128i)__builtin_ia32_extracti64x2_512_mask( \
+ (__v8di)(__m512i)(A), (int)(imm), (__v2di)_mm_setzero_si128(), \
+ (__mmask8) - 1))
#define _mm512_mask_extracti64x2_epi64(W, U, A, imm) \
((__m128i)__builtin_ia32_extracti64x2_512_mask((__v8di)(__m512i)(A), \
diff --git a/clang/lib/Headers/avx512fintrin.h b/clang/lib/Headers/avx512fintrin.h
index 07de036..18c4a44 100644
--- a/clang/lib/Headers/avx512fintrin.h
+++ b/clang/lib/Headers/avx512fintrin.h
@@ -3156,10 +3156,10 @@ _mm512_maskz_permutex2var_epi64(__mmask8 __U, __m512i __A, __m512i __I,
(__v16si)_mm512_setzero_si512()))
/* Vector Extract */
-#define _mm512_extractf64x4_pd(A, I) \
- ((__m256d)__builtin_ia32_extractf64x4_mask((__v8df)(__m512d)(A), (int)(I), \
- (__v4df)_mm256_undefined_pd(), \
- (__mmask8)-1))
+#define _mm512_extractf64x4_pd(A, I) \
+ ((__m256d)__builtin_ia32_extractf64x4_mask((__v8df)(__m512d)(A), (int)(I), \
+ (__v4df)_mm256_setzero_pd(), \
+ (__mmask8) - 1))
#define _mm512_mask_extractf64x4_pd(W, U, A, imm) \
((__m256d)__builtin_ia32_extractf64x4_mask((__v8df)(__m512d)(A), (int)(imm), \
@@ -3171,10 +3171,10 @@ _mm512_maskz_permutex2var_epi64(__mmask8 __U, __m512i __A, __m512i __I,
(__v4df)_mm256_setzero_pd(), \
(__mmask8)(U)))
-#define _mm512_extractf32x4_ps(A, I) \
- ((__m128)__builtin_ia32_extractf32x4_mask((__v16sf)(__m512)(A), (int)(I), \
- (__v4sf)_mm_undefined_ps(), \
- (__mmask8)-1))
+#define _mm512_extractf32x4_ps(A, I) \
+ ((__m128)__builtin_ia32_extractf32x4_mask((__v16sf)(__m512)(A), (int)(I), \
+ (__v4sf)_mm_setzero_ps(), \
+ (__mmask8) - 1))
#define _mm512_mask_extractf32x4_ps(W, U, A, imm) \
((__m128)__builtin_ia32_extractf32x4_mask((__v16sf)(__m512)(A), (int)(imm), \
@@ -7089,10 +7089,10 @@ _mm512_mask_cvtepi64_storeu_epi16 (void *__P, __mmask8 __M, __m512i __A)
__builtin_ia32_pmovqw512mem_mask ((__v8hi *) __P, (__v8di) __A, __M);
}
-#define _mm512_extracti32x4_epi32(A, imm) \
- ((__m128i)__builtin_ia32_extracti32x4_mask((__v16si)(__m512i)(A), (int)(imm), \
- (__v4si)_mm_undefined_si128(), \
- (__mmask8)-1))
+#define _mm512_extracti32x4_epi32(A, imm) \
+ ((__m128i)__builtin_ia32_extracti32x4_mask( \
+ (__v16si)(__m512i)(A), (int)(imm), (__v4si)_mm_setzero_si128(), \
+ (__mmask8) - 1))
#define _mm512_mask_extracti32x4_epi32(W, U, A, imm) \
((__m128i)__builtin_ia32_extracti32x4_mask((__v16si)(__m512i)(A), (int)(imm), \
@@ -7104,10 +7104,10 @@ _mm512_mask_cvtepi64_storeu_epi16 (void *__P, __mmask8 __M, __m512i __A)
(__v4si)_mm_setzero_si128(), \
(__mmask8)(U)))
-#define _mm512_extracti64x4_epi64(A, imm) \
+#define _mm512_extracti64x4_epi64(A, imm) \
((__m256i)__builtin_ia32_extracti64x4_mask((__v8di)(__m512i)(A), (int)(imm), \
- (__v4di)_mm256_undefined_si256(), \
- (__mmask8)-1))
+ (__v4di)_mm256_setzero_si256(), \
+ (__mmask8) - 1))
#define _mm512_mask_extracti64x4_epi64(W, U, A, imm) \
((__m256i)__builtin_ia32_extracti64x4_mask((__v8di)(__m512i)(A), (int)(imm), \
diff --git a/clang/lib/Headers/avx512vldqintrin.h b/clang/lib/Headers/avx512vldqintrin.h
index ee7974e..707d039 100644
--- a/clang/lib/Headers/avx512vldqintrin.h
+++ b/clang/lib/Headers/avx512vldqintrin.h
@@ -1062,11 +1062,10 @@ _mm256_maskz_broadcast_i64x2(__mmask8 __M, __m128i __A) {
(__v4di)_mm256_setzero_si256());
}
-#define _mm256_extractf64x2_pd(A, imm) \
- ((__m128d)__builtin_ia32_extractf64x2_256_mask((__v4df)(__m256d)(A), \
- (int)(imm), \
- (__v2df)_mm_undefined_pd(), \
- (__mmask8)-1))
+#define _mm256_extractf64x2_pd(A, imm) \
+ ((__m128d)__builtin_ia32_extractf64x2_256_mask( \
+ (__v4df)(__m256d)(A), (int)(imm), (__v2df)_mm_setzero_pd(), \
+ (__mmask8) - 1))
#define _mm256_mask_extractf64x2_pd(W, U, A, imm) \
((__m128d)__builtin_ia32_extractf64x2_256_mask((__v4df)(__m256d)(A), \
@@ -1080,11 +1079,10 @@ _mm256_maskz_broadcast_i64x2(__mmask8 __M, __m128i __A) {
(__v2df)_mm_setzero_pd(), \
(__mmask8)(U)))
-#define _mm256_extracti64x2_epi64(A, imm) \
- ((__m128i)__builtin_ia32_extracti64x2_256_mask((__v4di)(__m256i)(A), \
- (int)(imm), \
- (__v2di)_mm_undefined_si128(), \
- (__mmask8)-1))
+#define _mm256_extracti64x2_epi64(A, imm) \
+ ((__m128i)__builtin_ia32_extracti64x2_256_mask( \
+ (__v4di)(__m256i)(A), (int)(imm), (__v2di)_mm_setzero_si128(), \
+ (__mmask8) - 1))
#define _mm256_mask_extracti64x2_epi64(W, U, A, imm) \
((__m128i)__builtin_ia32_extracti64x2_256_mask((__v4di)(__m256i)(A), \
diff --git a/clang/lib/Headers/avx512vlintrin.h b/clang/lib/Headers/avx512vlintrin.h
index 676b5a0..92bb444 100644
--- a/clang/lib/Headers/avx512vlintrin.h
+++ b/clang/lib/Headers/avx512vlintrin.h
@@ -7545,11 +7545,10 @@ _mm256_mask_cvtepi64_storeu_epi16 (void * __P, __mmask8 __M, __m256i __A)
__builtin_ia32_pmovqw256mem_mask ((__v8hi *) __P, (__v4di) __A, __M);
}
-#define _mm256_extractf32x4_ps(A, imm) \
- ((__m128)__builtin_ia32_extractf32x4_256_mask((__v8sf)(__m256)(A), \
- (int)(imm), \
- (__v4sf)_mm_undefined_ps(), \
- (__mmask8)-1))
+#define _mm256_extractf32x4_ps(A, imm) \
+ ((__m128)__builtin_ia32_extractf32x4_256_mask( \
+ (__v8sf)(__m256)(A), (int)(imm), (__v4sf)_mm_setzero_ps(), \
+ (__mmask8) - 1))
#define _mm256_mask_extractf32x4_ps(W, U, A, imm) \
((__m128)__builtin_ia32_extractf32x4_256_mask((__v8sf)(__m256)(A), \
@@ -7563,11 +7562,10 @@ _mm256_mask_cvtepi64_storeu_epi16 (void * __P, __mmask8 __M, __m256i __A)
(__v4sf)_mm_setzero_ps(), \
(__mmask8)(U)))
-#define _mm256_extracti32x4_epi32(A, imm) \
- ((__m128i)__builtin_ia32_extracti32x4_256_mask((__v8si)(__m256i)(A), \
- (int)(imm), \
- (__v4si)_mm_undefined_si128(), \
- (__mmask8)-1))
+#define _mm256_extracti32x4_epi32(A, imm) \
+ ((__m128i)__builtin_ia32_extracti32x4_256_mask( \
+ (__v8si)(__m256i)(A), (int)(imm), (__v4si)_mm_setzero_si128(), \
+ (__mmask8) - 1))
#define _mm256_mask_extracti32x4_epi32(W, U, A, imm) \
((__m128i)__builtin_ia32_extracti32x4_256_mask((__v8si)(__m256i)(A), \
diff --git a/clang/lib/Headers/avxintrin.h b/clang/lib/Headers/avxintrin.h
index 696ec31..4aef924 100644
--- a/clang/lib/Headers/avxintrin.h
+++ b/clang/lib/Headers/avxintrin.h
@@ -2941,9 +2941,8 @@ _mm256_testnzc_si256(__m256i __a, __m256i __b) {
/// A 256-bit vector of [4 x double] containing the double-precision
/// floating point values with sign bits to be extracted.
/// \returns The sign bits from the operand, written to bits [3:0].
-static __inline int __DEFAULT_FN_ATTRS
-_mm256_movemask_pd(__m256d __a)
-{
+static __inline int __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm256_movemask_pd(__m256d __a) {
return __builtin_ia32_movmskpd256((__v4df)__a);
}
@@ -2959,9 +2958,8 @@ _mm256_movemask_pd(__m256d __a)
/// A 256-bit vector of [8 x float] containing the single-precision floating
/// point values with sign bits to be extracted.
/// \returns The sign bits from the operand, written to bits [7:0].
-static __inline int __DEFAULT_FN_ATTRS
-_mm256_movemask_ps(__m256 __a)
-{
+static __inline int __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm256_movemask_ps(__m256 __a) {
return __builtin_ia32_movmskps256((__v8sf)__a);
}
diff --git a/clang/lib/Headers/emmintrin.h b/clang/lib/Headers/emmintrin.h
index 454e9a2..dbe5ca0 100644
--- a/clang/lib/Headers/emmintrin.h
+++ b/clang/lib/Headers/emmintrin.h
@@ -4280,7 +4280,8 @@ _mm_packus_epi16(__m128i __a, __m128i __b) {
/// A 128-bit integer vector containing the values with bits to be extracted.
/// \returns The most significant bits from each 8-bit element in \a __a,
/// written to bits [15:0]. The other bits are assigned zeros.
-static __inline__ int __DEFAULT_FN_ATTRS _mm_movemask_epi8(__m128i __a) {
+static __inline__ int __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_movemask_epi8(__m128i __a) {
return __builtin_ia32_pmovmskb128((__v16qi)__a);
}
@@ -4699,7 +4700,8 @@ _mm_unpacklo_pd(__m128d __a, __m128d __b) {
/// be extracted.
/// \returns The sign bits from each of the double-precision elements in \a __a,
/// written to bits [1:0]. The remaining bits are assigned values of zero.
-static __inline__ int __DEFAULT_FN_ATTRS _mm_movemask_pd(__m128d __a) {
+static __inline__ int __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_movemask_pd(__m128d __a) {
return __builtin_ia32_movmskpd((__v2df)__a);
}
diff --git a/clang/lib/Headers/smmintrin.h b/clang/lib/Headers/smmintrin.h
index 4f197d5..511a135 100644
--- a/clang/lib/Headers/smmintrin.h
+++ b/clang/lib/Headers/smmintrin.h
@@ -1524,7 +1524,8 @@ _mm_packus_epi32(__m128i __V1, __m128i __V2) {
/// \returns A 128-bit value where bits [15:0] contain the minimum value found
/// in parameter \a __V, bits [18:16] contain the index of the minimum value
/// and the remaining bits are set to 0.
-static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_minpos_epu16(__m128i __V) {
+static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_minpos_epu16(__m128i __V) {
return (__m128i)__builtin_ia32_phminposuw128((__v8hi)__V);
}
diff --git a/clang/lib/Headers/xmmintrin.h b/clang/lib/Headers/xmmintrin.h
index 605409c..fe6afdc 100644
--- a/clang/lib/Headers/xmmintrin.h
+++ b/clang/lib/Headers/xmmintrin.h
@@ -3014,9 +3014,7 @@ _mm_cvtps_pi8(__m128 __a)
/// \returns A 32-bit integer value. Bits [3:0] contain the sign bits from each
/// single-precision floating-point element of the parameter. Bits [31:4] are
/// set to zero.
-static __inline__ int __DEFAULT_FN_ATTRS
-_mm_movemask_ps(__m128 __a)
-{
+static __inline__ int __DEFAULT_FN_ATTRS_CONSTEXPR _mm_movemask_ps(__m128 __a) {
return __builtin_ia32_movmskps((__v4sf)__a);
}
generated by cgit v1.1 at 2025-10-22 06:39:29 +0000