@cpp-linter/clang-tidy-win32-x64 20.1.0 → 22.1.8

package/lib/clang/{20 → 22}/include/opencl-c.h

@@ -13736,8 +13736,8 @@ half __ovld atomic_fetch_min_explicit(volatile atomic_half *,
                                       half, memory_order, memory_scope);
 half __ovld atomic_fetch_max_explicit(volatile atomic_half *,
                                       half, memory_order, memory_scope);
-#endif // defined(__opencl_c_ext_fp16_global_atomic_min_max) &&                \
-    defined(__opencl_c_ext_fp16_local_atomic_min_max)
+#endif // defined(__opencl_c_ext_fp16_global_atomic_min_max) &&
+       // defined(__opencl_c_ext_fp16_local_atomic_min_max)
 
 #if defined(__opencl_c_ext_fp32_global_atomic_min_max)
 float __ovld atomic_fetch_min(volatile __global atomic_float *, float);
@@ -13777,8 +13777,8 @@ float __ovld atomic_fetch_min_explicit(volatile atomic_float *,
                                        float, memory_order, memory_scope);
 float __ovld atomic_fetch_max_explicit(volatile atomic_float *,
                                        float, memory_order, memory_scope);
-#endif // defined(__opencl_c_ext_fp32_global_atomic_min_max) &&                \
-    defined(__opencl_c_ext_fp32_local_atomic_min_max)
+#endif // defined(__opencl_c_ext_fp32_global_atomic_min_max) &&
+       // defined(__opencl_c_ext_fp32_local_atomic_min_max)
 
 #if defined(cl_khr_int64_base_atomics) && defined(cl_khr_int64_extended_atomics)
 #if defined(__opencl_c_ext_fp64_global_atomic_min_max)
@@ -13819,10 +13819,10 @@ double __ovld atomic_fetch_min_explicit(volatile atomic_double *,
                                         double, memory_order, memory_scope);
 double __ovld atomic_fetch_max_explicit(volatile atomic_double *,
                                         double, memory_order, memory_scope);
-#endif // defined(__opencl_c_ext_fp64_global_atomic_min_max) &&                \
-    defined(__opencl_c_ext_fp64_local_atomic_min_max)
-#endif // defined(cl_khr_int64_base_atomics) &&                                \
-    defined(cl_khr_int64_extended_atomics)
+#endif // defined(__opencl_c_ext_fp64_global_atomic_min_max) &&
+       // defined(__opencl_c_ext_fp64_local_atomic_min_max)
+#endif // defined(cl_khr_int64_base_atomics) &&
+       // defined(cl_khr_int64_extended_atomics)
 
 #if defined(__opencl_c_ext_fp16_global_atomic_add)
 half __ovld atomic_fetch_add(volatile __global atomic_half *, half);
@@ -13862,8 +13862,8 @@ half __ovld atomic_fetch_add_explicit(volatile atomic_half *,
                                       half, memory_order, memory_scope);
 half __ovld atomic_fetch_sub_explicit(volatile atomic_half *,
                                       half, memory_order, memory_scope);
-#endif // defined(__opencl_c_ext_fp16_global_atomic_add) &&                    \
-    defined(__opencl_c_ext_fp16_local_atomic_add)
+#endif // defined(__opencl_c_ext_fp16_global_atomic_add) &&
+       // defined(__opencl_c_ext_fp16_local_atomic_add)
 
 #if defined(__opencl_c_ext_fp32_global_atomic_add)
 float __ovld atomic_fetch_add(volatile __global atomic_float *, float);
@@ -13903,8 +13903,8 @@ float __ovld atomic_fetch_add_explicit(volatile atomic_float *,
                                        float, memory_order, memory_scope);
 float __ovld atomic_fetch_sub_explicit(volatile atomic_float *,
                                        float, memory_order, memory_scope);
-#endif // defined(__opencl_c_ext_fp32_global_atomic_add) &&                    \
-    defined(__opencl_c_ext_fp32_local_atomic_add)
+#endif // defined(__opencl_c_ext_fp32_global_atomic_add) &&
+       // defined(__opencl_c_ext_fp32_local_atomic_add)
 
 #if defined(cl_khr_int64_base_atomics) && defined(cl_khr_int64_extended_atomics)
 #if defined(__opencl_c_ext_fp64_global_atomic_add)
@@ -13945,10 +13945,10 @@ double __ovld atomic_fetch_add_explicit(volatile atomic_double *,
                                         double, memory_order, memory_scope);
 double __ovld atomic_fetch_sub_explicit(volatile atomic_double *,
                                         double, memory_order, memory_scope);
-#endif // defined(__opencl_c_ext_fp64_global_atomic_add) &&                    \
-    defined(__opencl_c_ext_fp64_local_atomic_add)
-#endif // defined(cl_khr_int64_base_atomics) &&                                \
-    defined(cl_khr_int64_extended_atomics)
+#endif // defined(__opencl_c_ext_fp64_global_atomic_add) &&
+       // defined(__opencl_c_ext_fp64_local_atomic_add)
+#endif // defined(cl_khr_int64_base_atomics) &&
+       // defined(cl_khr_int64_extended_atomics)
 
 #endif // cl_ext_float_atomics
 
@@ -15082,6 +15082,7 @@ half16 __ovld __cnfn shuffle2(half16, half16, ushort16);
 #pragma OPENCL EXTENSION cl_khr_gl_msaa_sharing : enable
 #endif //cl_khr_gl_msaa_sharing
 
+#if (defined(__opencl_c_images) || defined(__IMAGE_SUPPORT__))
 /**
  * Use the coordinate (coord.xy) to do an element lookup in
  * the 2D image object specified by image.
@@ -16143,6 +16144,8 @@ int __ovld __cnfn get_image_num_samples(read_write image2d_array_msaa_depth_t);
 #endif //defined(__opencl_c_read_write_images)
 #endif
 
+#endif // (defined(__opencl_c_images) || defined(__IMAGE_SUPPORT__))
+
 // OpenCL v2.0 s6.13.15 - Work-group Functions
 
 #if defined(__opencl_c_work_group_collective_functions)
@@ -17479,7 +17482,57 @@ double  __ovld __conv intel_sub_group_shuffle_up( double prev, double cur, uint
 double  __ovld __conv intel_sub_group_shuffle_xor( double, uint );
 #endif
 
-#endif //cl_intel_subgroups
+#if defined(cl_intel_subgroups_char) || defined(cl_intel_subgroups_short) ||   \
+    defined(cl_intel_subgroups_long)
+
+#if defined(__opencl_c_images)
+uint       __ovld __conv intel_sub_group_block_read_ui(read_only image2d_t, int2);
+uint2      __ovld __conv intel_sub_group_block_read_ui2(read_only image2d_t, int2);
+uint4      __ovld __conv intel_sub_group_block_read_ui4(read_only image2d_t, int2);
+uint8      __ovld __conv intel_sub_group_block_read_ui8(read_only image2d_t, int2);
+#endif // defined(__opencl_c_images)
+
+#if defined(__opencl_c_read_write_images)
+uint       __ovld __conv intel_sub_group_block_read_ui(read_write image2d_t, int2);
+uint2      __ovld __conv intel_sub_group_block_read_ui2(read_write image2d_t, int2);
+uint4      __ovld __conv intel_sub_group_block_read_ui4(read_write image2d_t, int2);
+uint8      __ovld __conv intel_sub_group_block_read_ui8(read_write image2d_t, int2);
+#endif // defined(__opencl_c_read_write_images)
+
+uint       __ovld __conv intel_sub_group_block_read_ui( const __global uint* p );
+uint2      __ovld __conv intel_sub_group_block_read_ui2( const __global uint* p );
+uint4      __ovld __conv intel_sub_group_block_read_ui4( const __global uint* p );
+uint8      __ovld __conv intel_sub_group_block_read_ui8( const __global uint* p );
+
+#if defined(__opencl_c_images)
+void       __ovld __conv intel_sub_group_block_write_ui(read_only image2d_t, int2, uint);
+void       __ovld __conv intel_sub_group_block_write_ui2(read_only image2d_t, int2, uint2);
+void       __ovld __conv intel_sub_group_block_write_ui4(read_only image2d_t, int2, uint4);
+void       __ovld __conv intel_sub_group_block_write_ui8(read_only image2d_t, int2, uint8);
+#endif // defined(__opencl_c_images)
+
+#if defined(__opencl_c_read_write_images)
+void       __ovld __conv intel_sub_group_block_write_ui(read_write image2d_t, int2, uint);
+void       __ovld __conv intel_sub_group_block_write_ui2(read_write image2d_t, int2, uint2);
+void       __ovld __conv intel_sub_group_block_write_ui4(read_write image2d_t, int2, uint4);
+void       __ovld __conv intel_sub_group_block_write_ui8(read_write image2d_t, int2, uint8);
+#endif // defined(__opencl_c_read_write_images)
+
+void       __ovld __conv intel_sub_group_block_write_ui( __global uint* p, uint data );
+void       __ovld __conv intel_sub_group_block_write_ui2( __global uint* p, uint2 data );
+void       __ovld __conv intel_sub_group_block_write_ui4( __global uint* p, uint4 data );
+void       __ovld __conv intel_sub_group_block_write_ui8( __global uint* p, uint8 data );
+
+#endif // defined(cl_intel_subgroups_char) || defined(cl_intel_subgroups_short) ||
+       // defined(cl_intel_subgroups_long)
+
+#if defined(cl_intel_subgroup_buffer_prefetch)
+void       __ovld __conv intel_sub_group_block_prefetch_ui(const __global uint *p);
+void       __ovld __conv intel_sub_group_block_prefetch_ui2(const __global uint *p);
+void       __ovld __conv intel_sub_group_block_prefetch_ui4(const __global uint *p);
+void       __ovld __conv intel_sub_group_block_prefetch_ui8(const __global uint *p);
+#endif // defined(cl_intel_subgroup_buffer_prefetch)
+#endif // cl_intel_subgroups
 
 #if defined(cl_intel_subgroups_short)
 short       __ovld __conv intel_sub_group_broadcast( short , uint sub_group_local_id );
@@ -17571,49 +17624,12 @@ ushort      __ovld __conv intel_sub_group_scan_inclusive_min( ushort  x );
 short       __ovld __conv intel_sub_group_scan_inclusive_max( short   x );
 ushort      __ovld __conv intel_sub_group_scan_inclusive_max( ushort  x );
 
-#if defined(__opencl_c_images)
-uint       __ovld __conv intel_sub_group_block_read_ui(read_only image2d_t, int2);
-uint2      __ovld __conv intel_sub_group_block_read_ui2(read_only image2d_t, int2);
-uint4      __ovld __conv intel_sub_group_block_read_ui4(read_only image2d_t, int2);
-uint8      __ovld __conv intel_sub_group_block_read_ui8(read_only image2d_t, int2);
-#endif // defined(__opencl_c_images)
-
-#if defined(__opencl_c_read_write_images)
-uint       __ovld __conv intel_sub_group_block_read_ui(read_write image2d_t, int2);
-uint2      __ovld __conv intel_sub_group_block_read_ui2(read_write image2d_t, int2);
-uint4      __ovld __conv intel_sub_group_block_read_ui4(read_write image2d_t, int2);
-uint8      __ovld __conv intel_sub_group_block_read_ui8(read_write image2d_t, int2);
-#endif // defined(__opencl_c_read_write_images)
-
-uint       __ovld __conv intel_sub_group_block_read_ui( const __global uint* p );
-uint2      __ovld __conv intel_sub_group_block_read_ui2( const __global uint* p );
-uint4      __ovld __conv intel_sub_group_block_read_ui4( const __global uint* p );
-uint8      __ovld __conv intel_sub_group_block_read_ui8( const __global uint* p );
-
-#if defined(__opencl_c_images)
-void       __ovld __conv intel_sub_group_block_write_ui(read_only image2d_t, int2, uint);
-void       __ovld __conv intel_sub_group_block_write_ui2(read_only image2d_t, int2, uint2);
-void       __ovld __conv intel_sub_group_block_write_ui4(read_only image2d_t, int2, uint4);
-void       __ovld __conv intel_sub_group_block_write_ui8(read_only image2d_t, int2, uint8);
-#endif //defined(__opencl_c_images)
-
-#if defined(__opencl_c_read_write_images)
-void       __ovld __conv intel_sub_group_block_write_ui(read_write image2d_t, int2, uint);
-void       __ovld __conv intel_sub_group_block_write_ui2(read_write image2d_t, int2, uint2);
-void       __ovld __conv intel_sub_group_block_write_ui4(read_write image2d_t, int2, uint4);
-void       __ovld __conv intel_sub_group_block_write_ui8(read_write image2d_t, int2, uint8);
-#endif // defined(__opencl_c_read_write_images)
-
-void       __ovld __conv intel_sub_group_block_write_ui( __global uint* p, uint data );
-void       __ovld __conv intel_sub_group_block_write_ui2( __global uint* p, uint2 data );
-void       __ovld __conv intel_sub_group_block_write_ui4( __global uint* p, uint4 data );
-void       __ovld __conv intel_sub_group_block_write_ui8( __global uint* p, uint8 data );
-
 #if defined(__opencl_c_images)
 ushort      __ovld __conv intel_sub_group_block_read_us(read_only image2d_t, int2);
 ushort2     __ovld __conv intel_sub_group_block_read_us2(read_only image2d_t, int2);
 ushort4     __ovld __conv intel_sub_group_block_read_us4(read_only image2d_t, int2);
 ushort8     __ovld __conv intel_sub_group_block_read_us8(read_only image2d_t, int2);
+ushort16    __ovld __conv intel_sub_group_block_read_us16(read_only image2d_t, int2);
 #endif // defined(__opencl_c_images)
 
 #if defined(__opencl_c_read_write_images)
@@ -17621,18 +17637,21 @@ ushort      __ovld __conv intel_sub_group_block_read_us(read_write image2d_t, in
 ushort2     __ovld __conv intel_sub_group_block_read_us2(read_write image2d_t, int2);
 ushort4     __ovld __conv intel_sub_group_block_read_us4(read_write image2d_t, int2);
 ushort8     __ovld __conv intel_sub_group_block_read_us8(read_write image2d_t, int2);
+ushort16    __ovld __conv intel_sub_group_block_read_us16(read_write image2d_t, int2);
 #endif // defined(__opencl_c_read_write_images)
 
 ushort      __ovld __conv intel_sub_group_block_read_us(  const __global ushort* p );
 ushort2     __ovld __conv intel_sub_group_block_read_us2( const __global ushort* p );
 ushort4     __ovld __conv intel_sub_group_block_read_us4( const __global ushort* p );
 ushort8     __ovld __conv intel_sub_group_block_read_us8( const __global ushort* p );
+ushort16    __ovld __conv intel_sub_group_block_read_us16(const __global ushort* p);
 
 #if defined(__opencl_c_images)
 void        __ovld __conv intel_sub_group_block_write_us(write_only image2d_t, int2, ushort);
 void        __ovld __conv intel_sub_group_block_write_us2(write_only image2d_t, int2, ushort2);
 void        __ovld __conv intel_sub_group_block_write_us4(write_only image2d_t, int2, ushort4);
 void        __ovld __conv intel_sub_group_block_write_us8(write_only image2d_t, int2, ushort8);
+void        __ovld __conv intel_sub_group_block_write_us16(write_only image2d_t, int2, ushort16);
 #endif // defined(__opencl_c_images)
 
 #if defined(__opencl_c_read_write_images)
@@ -17640,14 +17659,284 @@ void        __ovld __conv intel_sub_group_block_write_us(read_write image2d_t, i
 void        __ovld __conv intel_sub_group_block_write_us2(read_write image2d_t, int2, ushort2);
 void        __ovld __conv intel_sub_group_block_write_us4(read_write image2d_t, int2, ushort4);
 void        __ovld __conv intel_sub_group_block_write_us8(read_write image2d_t, int2, ushort8);
+void        __ovld __conv intel_sub_group_block_write_us16(read_write image2d_t, int2, ushort16);
 #endif // defined(__opencl_c_read_write_images)
 
 void        __ovld __conv intel_sub_group_block_write_us(  __global ushort* p, ushort  data );
 void        __ovld __conv intel_sub_group_block_write_us2( __global ushort* p, ushort2 data );
 void        __ovld __conv intel_sub_group_block_write_us4( __global ushort* p, ushort4 data );
 void        __ovld __conv intel_sub_group_block_write_us8( __global ushort* p, ushort8 data );
+void        __ovld __conv intel_sub_group_block_write_us16( __global ushort* p, ushort16 data );
+
+#if defined(cl_intel_subgroup_buffer_prefetch)
+void        __ovld __conv intel_sub_group_block_prefetch_us(const __global ushort *p);
+void        __ovld __conv intel_sub_group_block_prefetch_us2(const __global ushort *p);
+void        __ovld __conv intel_sub_group_block_prefetch_us4(const __global ushort *p);
+void        __ovld __conv intel_sub_group_block_prefetch_us8(const __global ushort *p);
+void        __ovld __conv intel_sub_group_block_prefetch_us16(const __global ushort *p);
+#endif // defined(cl_intel_subgroup_buffer_prefetch)
 #endif // cl_intel_subgroups_short
 
+#if defined(cl_intel_subgroups_char)
+char       __ovld __conv intel_sub_group_broadcast( char , uint sub_group_local_id );
+char2      __ovld __conv intel_sub_group_broadcast( char2, uint sub_group_local_id );
+char3      __ovld __conv intel_sub_group_broadcast( char3, uint sub_group_local_id );
+char4      __ovld __conv intel_sub_group_broadcast( char4, uint sub_group_local_id );
+char8      __ovld __conv intel_sub_group_broadcast( char8, uint sub_group_local_id );
+
+uchar      __ovld __conv intel_sub_group_broadcast( uchar , uint sub_group_local_id );
+uchar2     __ovld __conv intel_sub_group_broadcast( uchar2, uint sub_group_local_id );
+uchar3     __ovld __conv intel_sub_group_broadcast( uchar3, uint sub_group_local_id );
+uchar4     __ovld __conv intel_sub_group_broadcast( uchar4, uint sub_group_local_id );
+uchar8     __ovld __conv intel_sub_group_broadcast( uchar8, uint sub_group_local_id );
+
+char       __ovld __conv intel_sub_group_shuffle( char  , uint );
+char2      __ovld __conv intel_sub_group_shuffle( char2 , uint );
+char3      __ovld __conv intel_sub_group_shuffle( char3 , uint );
+char4      __ovld __conv intel_sub_group_shuffle( char4 , uint );
+char8      __ovld __conv intel_sub_group_shuffle( char8 , uint );
+char16     __ovld __conv intel_sub_group_shuffle( char16, uint);
+
+uchar      __ovld __conv intel_sub_group_shuffle( uchar  , uint );
+uchar2     __ovld __conv intel_sub_group_shuffle( uchar2 , uint );
+uchar3     __ovld __conv intel_sub_group_shuffle( uchar3 , uint );
+uchar4     __ovld __conv intel_sub_group_shuffle( uchar4 , uint );
+uchar8     __ovld __conv intel_sub_group_shuffle( uchar8 , uint );
+uchar16    __ovld __conv intel_sub_group_shuffle( uchar16, uint );
+
+char       __ovld __conv intel_sub_group_shuffle_down( char   cur, char   next, uint );
+char2      __ovld __conv intel_sub_group_shuffle_down( char2  cur, char2  next, uint );
+char3      __ovld __conv intel_sub_group_shuffle_down( char3  cur, char3  next, uint );
+char4      __ovld __conv intel_sub_group_shuffle_down( char4  cur, char4  next, uint );
+char8      __ovld __conv intel_sub_group_shuffle_down( char8  cur, char8  next, uint );
+char16     __ovld __conv intel_sub_group_shuffle_down( char16 cur, char16 next, uint );
+
+uchar      __ovld __conv intel_sub_group_shuffle_down( uchar   cur, uchar   next, uint );
+uchar2     __ovld __conv intel_sub_group_shuffle_down( uchar2  cur, uchar2  next, uint );
+uchar3     __ovld __conv intel_sub_group_shuffle_down( uchar3  cur, uchar3  next, uint );
+uchar4     __ovld __conv intel_sub_group_shuffle_down( uchar4  cur, uchar4  next, uint );
+uchar8     __ovld __conv intel_sub_group_shuffle_down( uchar8  cur, uchar8  next, uint );
+uchar16    __ovld __conv intel_sub_group_shuffle_down( uchar16 cur, uchar16 next, uint );
+
+char       __ovld __conv intel_sub_group_shuffle_up( char   cur, char   next, uint );
+char2      __ovld __conv intel_sub_group_shuffle_up( char2  cur, char2  next, uint );
+char3      __ovld __conv intel_sub_group_shuffle_up( char3  cur, char3  next, uint );
+char4      __ovld __conv intel_sub_group_shuffle_up( char4  cur, char4  next, uint );
+char8      __ovld __conv intel_sub_group_shuffle_up( char8  cur, char8  next, uint );
+char16     __ovld __conv intel_sub_group_shuffle_up( char16 cur, char16 next, uint );
+
+uchar      __ovld __conv intel_sub_group_shuffle_up( uchar   cur, uchar   next, uint );
+uchar2     __ovld __conv intel_sub_group_shuffle_up( uchar2  cur, uchar2  next, uint );
+uchar3     __ovld __conv intel_sub_group_shuffle_up( uchar3  cur, uchar3  next, uint );
+uchar4     __ovld __conv intel_sub_group_shuffle_up( uchar4  cur, uchar4  next, uint );
+uchar8     __ovld __conv intel_sub_group_shuffle_up( uchar8  cur, uchar8  next, uint );
+uchar16    __ovld __conv intel_sub_group_shuffle_up( uchar16 cur, uchar16 next, uint );
+
+char       __ovld __conv intel_sub_group_shuffle_xor( char  , uint );
+char2      __ovld __conv intel_sub_group_shuffle_xor( char2 , uint );
+char3      __ovld __conv intel_sub_group_shuffle_xor( char3 , uint );
+char4      __ovld __conv intel_sub_group_shuffle_xor( char4 , uint );
+char8      __ovld __conv intel_sub_group_shuffle_xor( char8 , uint );
+char16     __ovld __conv intel_sub_group_shuffle_xor( char16, uint );
+
+uchar      __ovld __conv intel_sub_group_shuffle_xor( uchar  , uint );
+uchar2     __ovld __conv intel_sub_group_shuffle_xor( uchar2 , uint );
+uchar3     __ovld __conv intel_sub_group_shuffle_xor( uchar3 , uint );
+uchar4     __ovld __conv intel_sub_group_shuffle_xor( uchar4 , uint );
+uchar8     __ovld __conv intel_sub_group_shuffle_xor( uchar8 , uint );
+uchar16    __ovld __conv intel_sub_group_shuffle_xor( uchar16, uint );
+
+char       __ovld __conv intel_sub_group_reduce_add( char   x );
+uchar      __ovld __conv intel_sub_group_reduce_add( uchar  x );
+char       __ovld __conv intel_sub_group_reduce_min( char   x );
+uchar      __ovld __conv intel_sub_group_reduce_min( uchar  x );
+char       __ovld __conv intel_sub_group_reduce_max( char   x );
+uchar      __ovld __conv intel_sub_group_reduce_max( uchar  x );
+
+char       __ovld __conv intel_sub_group_scan_exclusive_add( char   x );
+uchar      __ovld __conv intel_sub_group_scan_exclusive_add( uchar  x );
+char       __ovld __conv intel_sub_group_scan_exclusive_min( char   x );
+uchar      __ovld __conv intel_sub_group_scan_exclusive_min( uchar  x );
+char       __ovld __conv intel_sub_group_scan_exclusive_max( char   x );
+uchar      __ovld __conv intel_sub_group_scan_exclusive_max( uchar  x );
+
+char       __ovld __conv intel_sub_group_scan_inclusive_add( char   x );
+uchar      __ovld __conv intel_sub_group_scan_inclusive_add( uchar  x );
+char       __ovld __conv intel_sub_group_scan_inclusive_min( char   x );
+uchar      __ovld __conv intel_sub_group_scan_inclusive_min( uchar  x );
+char       __ovld __conv intel_sub_group_scan_inclusive_max( char   x );
+uchar      __ovld __conv intel_sub_group_scan_inclusive_max( uchar  x );
+
+#if defined(__opencl_c_images)
+uchar      __ovld __conv intel_sub_group_block_read_uc(read_only image2d_t, int2);
+uchar2     __ovld __conv intel_sub_group_block_read_uc2(read_only image2d_t, int2);
+uchar4     __ovld __conv intel_sub_group_block_read_uc4(read_only image2d_t, int2);
+uchar8     __ovld __conv intel_sub_group_block_read_uc8(read_only image2d_t, int2);
+uchar16    __ovld __conv intel_sub_group_block_read_uc16(read_only image2d_t, int2);
+#endif // defined(__opencl_c_images)
+
+#if defined(__opencl_c_read_write_images)
+uchar      __ovld __conv intel_sub_group_block_read_uc(read_write image2d_t, int2);
+uchar2     __ovld __conv intel_sub_group_block_read_uc2(read_write image2d_t, int2);
+uchar4     __ovld __conv intel_sub_group_block_read_uc4(read_write image2d_t, int2);
+uchar8     __ovld __conv intel_sub_group_block_read_uc8(read_write image2d_t, int2);
+uchar16    __ovld __conv intel_sub_group_block_read_uc16(read_write image2d_t, int2);
+#endif // defined(__opencl_c_read_write_images)
+
+uchar      __ovld __conv intel_sub_group_block_read_uc(  const __global uchar* p );
+uchar2     __ovld __conv intel_sub_group_block_read_uc2( const __global uchar* p );
+uchar4     __ovld __conv intel_sub_group_block_read_uc4( const __global uchar* p );
+uchar8     __ovld __conv intel_sub_group_block_read_uc8( const __global uchar* p );
+uchar16    __ovld __conv intel_sub_group_block_read_uc16( const __global uchar* p );
+
+#if defined(__opencl_c_images)
+void        __ovld __conv intel_sub_group_block_write_uc(write_only image2d_t, int2, uchar);
+void        __ovld __conv intel_sub_group_block_write_uc2(write_only image2d_t, int2, uchar2);
+void        __ovld __conv intel_sub_group_block_write_uc4(write_only image2d_t, int2, uchar4);
+void        __ovld __conv intel_sub_group_block_write_uc8(write_only image2d_t, int2, uchar8);
+void        __ovld __conv intel_sub_group_block_write_uc16(write_only image2d_t, int2, uchar16);
+#endif // defined(__opencl_c_images)
+
+#if defined(__opencl_c_read_write_images)
+void        __ovld __conv intel_sub_group_block_write_uc(read_write image2d_t, int2, uchar);
+void        __ovld __conv intel_sub_group_block_write_uc2(read_write image2d_t, int2, uchar2);
+void        __ovld __conv intel_sub_group_block_write_uc4(read_write image2d_t, int2, uchar4);
+void        __ovld __conv intel_sub_group_block_write_uc8(read_write image2d_t, int2, uchar8);
+void        __ovld __conv intel_sub_group_block_write_uc16(read_write image2d_t, int2, uchar16);
+#endif // defined(__opencl_c_read_write_images)
+
+void        __ovld __conv intel_sub_group_block_write_uc(  __global uchar* p, uchar  data );
+void        __ovld __conv intel_sub_group_block_write_uc2( __global uchar* p, uchar2 data );
+void        __ovld __conv intel_sub_group_block_write_uc4( __global uchar* p, uchar4 data );
+void        __ovld __conv intel_sub_group_block_write_uc8( __global uchar* p, uchar8 data );
+void        __ovld __conv intel_sub_group_block_write_uc16( __global uchar* p, uchar16 data );
+
+#if defined(cl_intel_subgroup_buffer_prefetch)
+void        __ovld __conv intel_sub_group_block_prefetch_uc(const __global uchar *p);
+void        __ovld __conv intel_sub_group_block_prefetch_uc2(const __global uchar *p);
+void        __ovld __conv intel_sub_group_block_prefetch_uc4(const __global uchar *p);
+void        __ovld __conv intel_sub_group_block_prefetch_uc8(const __global uchar *p);
+void        __ovld __conv intel_sub_group_block_prefetch_uc16(const __global uchar *p);
+#endif // defined(cl_intel_subgroup_buffer_prefetch)
+#endif // cl_intel_subgroups_char
+
+#if defined(cl_intel_subgroups_long)
+#if defined(__opencl_c_images)
+ulong      __ovld __conv intel_sub_group_block_read_ul(read_only image2d_t, int2);
+ulong2     __ovld __conv intel_sub_group_block_read_ul2(read_only image2d_t, int2);
+ulong4     __ovld __conv intel_sub_group_block_read_ul4(read_only image2d_t, int2);
+ulong8     __ovld __conv intel_sub_group_block_read_ul8(read_only image2d_t, int2);
+ulong16    __ovld __conv intel_sub_group_block_read_ul16(read_only image2d_t, int2);
+#endif // defined(__opencl_c_images)
+
+#if defined(__opencl_c_read_write_images)
+ulong      __ovld __conv intel_sub_group_block_read_ul(read_write image2d_t, int2);
+ulong2     __ovld __conv intel_sub_group_block_read_ul2(read_write image2d_t, int2);
+ulong4     __ovld __conv intel_sub_group_block_read_ul4(read_write image2d_t, int2);
+ulong8     __ovld __conv intel_sub_group_block_read_ul8(read_write image2d_t, int2);
+ulong16    __ovld __conv intel_sub_group_block_read_ul16(read_write image2d_t, int2);
+#endif // defined(__opencl_c_read_write_images)
+
+ulong      __ovld __conv intel_sub_group_block_read_ul(  const __global ulong* p );
+ulong2     __ovld __conv intel_sub_group_block_read_ul2( const __global ulong* p );
+ulong4     __ovld __conv intel_sub_group_block_read_ul4( const __global ulong* p );
+ulong8     __ovld __conv intel_sub_group_block_read_ul8( const __global ulong* p );
+
+#if defined(__opencl_c_images)
+void        __ovld __conv intel_sub_group_block_write_ul(write_only image2d_t, int2, ulong);
+void        __ovld __conv intel_sub_group_block_write_ul2(write_only image2d_t, int2, ulong2);
+void        __ovld __conv intel_sub_group_block_write_ul4(write_only image2d_t, int2, ulong4);
+void        __ovld __conv intel_sub_group_block_write_ul8(write_only image2d_t, int2, ulong8);
+void        __ovld __conv intel_sub_group_block_write_ul16(write_only image2d_t, int2, ulong16);
+#endif // defined(__opencl_c_images)
+
+#if defined(__opencl_c_read_write_images)
+void        __ovld __conv intel_sub_group_block_write_ul(read_write image2d_t, int2, ulong);
+void        __ovld __conv intel_sub_group_block_write_ul2(read_write image2d_t, int2, ulong2);
+void        __ovld __conv intel_sub_group_block_write_ul4(read_write image2d_t, int2, ulong4);
+void        __ovld __conv intel_sub_group_block_write_ul8(read_write image2d_t, int2, ulong8);
+void        __ovld __conv intel_sub_group_block_write_ul16(read_write image2d_t, int2, ulong16);
+#endif // defined(__opencl_c_read_write_images)
+
+void        __ovld __conv intel_sub_group_block_write_ul(  __global ulong* p, ulong  data );
+void        __ovld __conv intel_sub_group_block_write_ul2( __global ulong* p, ulong2 data );
+void        __ovld __conv intel_sub_group_block_write_ul4( __global ulong* p, ulong4 data );
+void        __ovld __conv intel_sub_group_block_write_ul8( __global ulong* p, ulong8 data);
+
+#if defined(cl_intel_subgroup_buffer_prefetch)
+void        __ovld __conv intel_sub_group_block_prefetch_ul(const __global ulong *p);
+void        __ovld __conv intel_sub_group_block_prefetch_ul2(const __global ulong *p);
+void        __ovld __conv intel_sub_group_block_prefetch_ul4(const __global ulong *p);
+void        __ovld __conv intel_sub_group_block_prefetch_ul8(const __global ulong *p);
+#endif // defined(cl_intel_subgroup_buffer_prefetch)
+#endif // cl_intel_subgroups_long
+
+#if defined(cl_intel_subgroup_local_block_io)
+uint    __ovld __conv intel_sub_group_block_read( const __local uint* p );
+uint2   __ovld __conv intel_sub_group_block_read2( const __local uint* p );
+uint4   __ovld __conv intel_sub_group_block_read4( const __local uint* p );
+uint8   __ovld __conv intel_sub_group_block_read8( const __local uint* p );
+
+void    __ovld __conv intel_sub_group_block_write( __local uint* p, uint data );
+void    __ovld __conv intel_sub_group_block_write2( __local uint* p, uint2 data );
+void    __ovld __conv intel_sub_group_block_write4( __local uint* p, uint4 data );
+void    __ovld __conv intel_sub_group_block_write8( __local uint* p, uint8 data );
+
+#if defined(cl_intel_subgroups_char) || defined(cl_intel_subgroups_short) ||   \
+    defined(cl_intel_subgroups_long)
+uint       __ovld __conv intel_sub_group_block_read_ui( const __local uint* p );
+uint2      __ovld __conv intel_sub_group_block_read_ui2( const __local uint* p );
+uint4      __ovld __conv intel_sub_group_block_read_ui4( const __local uint* p );
+uint8      __ovld __conv intel_sub_group_block_read_ui8( const __local uint* p );
+
+void       __ovld __conv intel_sub_group_block_write_ui( __local uint* p, uint data );
+void       __ovld __conv intel_sub_group_block_write_ui2( __local uint* p, uint2 data );
+void       __ovld __conv intel_sub_group_block_write_ui4( __local uint* p, uint4 data );
+void       __ovld __conv intel_sub_group_block_write_ui8( __local uint* p, uint8 data );
+#endif // defined(cl_intel_subgroups_char) || defined(cl_intel_subgroups_short) ||
+       // defined(cl_intel_subgroups_long)
+
+#if defined(cl_intel_subgroups_char)
+uchar      __ovld __conv intel_sub_group_block_read_uc(   const __local uchar* p );
+uchar2     __ovld __conv intel_sub_group_block_read_uc2(  const __local uchar* p );
+uchar4     __ovld __conv intel_sub_group_block_read_uc4(  const __local uchar* p );
+uchar8     __ovld __conv intel_sub_group_block_read_uc8(  const __local uchar* p );
+uchar16    __ovld __conv intel_sub_group_block_read_uc16( const __local uchar* p );
+
+void        __ovld __conv intel_sub_group_block_write_uc(   __local uchar* p, uchar  data );
+void        __ovld __conv intel_sub_group_block_write_uc2(  __local uchar* p, uchar2 data );
+void        __ovld __conv intel_sub_group_block_write_uc4(  __local uchar* p, uchar4 data );
+void        __ovld __conv intel_sub_group_block_write_uc8(  __local uchar* p, uchar8 data );
+void        __ovld __conv intel_sub_group_block_write_uc16( __local uchar* p, uchar16 data );
+#endif // defined(cl_intel_subgroups_char)
+
+#if defined(cl_intel_subgroups_short)
+ushort      __ovld __conv intel_sub_group_block_read_us(  const __local ushort* p );
+ushort2     __ovld __conv intel_sub_group_block_read_us2( const __local ushort* p );
+ushort4     __ovld __conv intel_sub_group_block_read_us4( const __local ushort* p );
+ushort8     __ovld __conv intel_sub_group_block_read_us8( const __local ushort* p );
+ushort16    __ovld __conv intel_sub_group_block_read_us16( const __local ushort* p );
+
+void        __ovld __conv intel_sub_group_block_write_us(  __local ushort* p, ushort  data );
+void        __ovld __conv intel_sub_group_block_write_us2( __local ushort* p, ushort2 data );
+void        __ovld __conv intel_sub_group_block_write_us4( __local ushort* p, ushort4 data );
+void        __ovld __conv intel_sub_group_block_write_us8( __local ushort* p, ushort8 data );
+void        __ovld __conv intel_sub_group_block_write_us16( __local ushort* p, ushort16 data );
+#endif // defined(cl_intel_subgroups_short)
+
+#if defined(cl_intel_subgroups_long)
+ulong      __ovld __conv intel_sub_group_block_read_ul(  const __local ulong* p );
+ulong2     __ovld __conv intel_sub_group_block_read_ul2( const __local ulong* p );
+ulong4     __ovld __conv intel_sub_group_block_read_ul4( const __local ulong* p );
+ulong8     __ovld __conv intel_sub_group_block_read_ul8( const __local ulong* p );
+
+void        __ovld __conv intel_sub_group_block_write_ul(  __local ulong* p, ulong  data );
+void        __ovld __conv intel_sub_group_block_write_ul2( __local ulong* p, ulong2 data );
+void        __ovld __conv intel_sub_group_block_write_ul4( __local ulong* p, ulong4 data );
+void        __ovld __conv intel_sub_group_block_write_ul8( __local ulong* p, ulong8 data );
+#endif // defined(cl_intel_subgroups_long)
+#endif // cl_intel_subgroup_local_block_io
+
 #ifdef cl_intel_device_side_avc_motion_estimation
 #pragma OPENCL EXTENSION cl_intel_device_side_avc_motion_estimation : begin
 
@@ -18151,6 +18440,22 @@ intel_sub_group_avc_mce_convert_to_sic_result(
 #pragma OPENCL EXTENSION cl_intel_device_side_avc_motion_estimation : end
 #endif // cl_intel_device_side_avc_motion_estimation
 
+#if defined(cl_intel_bfloat16_conversions)
+ushort __ovld intel_convert_bfloat16_as_ushort(float source);
+ushort2 __ovld intel_convert_bfloat162_as_ushort2(float2 source);
+ushort3 __ovld intel_convert_bfloat163_as_ushort3(float3 source);
+ushort4 __ovld intel_convert_bfloat164_as_ushort4(float4 source);
+ushort8 __ovld intel_convert_bfloat168_as_ushort8(float8 source);
+ushort16 __ovld intel_convert_bfloat1616_as_ushort16(float16 source);
+
+float __ovld intel_convert_as_bfloat16_float(ushort source);
+float2 __ovld intel_convert_as_bfloat162_float2(ushort2 source);
+float3 __ovld intel_convert_as_bfloat163_float3(ushort3 source);
+float4 __ovld intel_convert_as_bfloat164_float4(ushort4 source);
+float8 __ovld intel_convert_as_bfloat168_float8(ushort8 source);
+float16 __ovld intel_convert_as_bfloat1616_float16(ushort16 source);
+#endif // cl_intel_bfloat16_conversions
+
 #ifdef cl_amd_media_ops
 uint __ovld amd_bitalign(uint, uint, uint);
 uint2 __ovld amd_bitalign(uint2, uint2, uint2);

package/lib/clang/{20 → 22}/include/pmmintrin.h

@@ -17,15 +17,9 @@
 #include <emmintrin.h>
 
 /* Define the default attributes for the functions in this file. */
-#if defined(__EVEX512__) && !defined(__AVX10_1_512__)
-#define __DEFAULT_FN_ATTRS                                                     \
-  __attribute__((__always_inline__, __nodebug__,                               \
-                 __target__("sse3,no-evex512"), __min_vector_width__(128)))
-#else
 #define __DEFAULT_FN_ATTRS                                                     \
   __attribute__((__always_inline__, __nodebug__, __target__("sse3"),           \
                  __min_vector_width__(128)))
-#endif
 
 #if defined(__cplusplus) && (__cplusplus >= 201103L)
 #define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS constexpr
@@ -66,9 +60,8 @@ _mm_lddqu_si128(__m128i_u const *__p)
 ///    A 128-bit vector of [4 x float] containing the right source operand.
 /// \returns A 128-bit vector of [4 x float] containing the alternating sums and
 ///    differences of both operands.
-static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_addsub_ps(__m128 __a, __m128 __b)
-{
+static __inline__ __m128 __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_addsub_ps(__m128 __a, __m128 __b) {
   return __builtin_ia32_addsubps((__v4sf)__a, (__v4sf)__b);
 }
 
@@ -89,9 +82,8 @@ _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
-_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);
 }
 
@@ -112,9 +104,8 @@ _mm_hadd_ps(__m128 __a, __m128 __b)
 ///    bits of the destination.
 /// \returns A 128-bit vector of [4 x float] containing the horizontal
 ///    differences of both operands.
-static __inline__ __m128 __DEFAULT_FN_ATTRS
-_mm_hsub_ps(__m128 __a, __m128 __b)
-{
+static __inline__ __m128 __DEFAULT_FN_ATTRS_CONSTEXPR _mm_hsub_ps(__m128 __a,
+                                                                  __m128 __b) {
   return __builtin_ia32_hsubps((__v4sf)__a, (__v4sf)__b);
 }
 
@@ -174,9 +165,8 @@ _mm_moveldup_ps(__m128 __a)
 ///    A 128-bit vector of [2 x double] containing the right source operand.
 /// \returns A 128-bit vector of [2 x double] containing the alternating sums
 ///    and differences of both operands.
-static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_addsub_pd(__m128d __a, __m128d __b)
-{
+static __inline__ __m128d __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_addsub_pd(__m128d __a, __m128d __b) {
   return __builtin_ia32_addsubpd((__v2df)__a, (__v2df)__b);
 }
 
@@ -197,9 +187,8 @@ _mm_addsub_pd(__m128d __a, __m128d __b)
 ///    destination.
 /// \returns A 128-bit vector of [2 x double] containing the horizontal sums of
 ///    both operands.
-static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_hadd_pd(__m128d __a, __m128d __b)
-{
+static __inline__ __m128d __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_hadd_pd(__m128d __a, __m128d __b) {
   return __builtin_ia32_haddpd((__v2df)__a, (__v2df)__b);
 }
 
@@ -220,9 +209,8 @@ _mm_hadd_pd(__m128d __a, __m128d __b)
 ///    the destination.
 /// \returns A 128-bit vector of [2 x double] containing the horizontal
 ///    differences of both operands.
-static __inline__ __m128d __DEFAULT_FN_ATTRS
-_mm_hsub_pd(__m128d __a, __m128d __b)
-{
+static __inline__ __m128d __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_hsub_pd(__m128d __a, __m128d __b) {
   return __builtin_ia32_hsubpd((__v2df)__a, (__v2df)__b);
 }
 

package/lib/clang/{20 → 22}/include/prfchwintrin.h

@@ -14,6 +14,10 @@
 #ifndef __PRFCHWINTRIN_H
 #define __PRFCHWINTRIN_H
 
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
 /// Loads a memory sequence containing the specified memory address into
 ///    all data cache levels.
 ///
@@ -26,11 +30,7 @@
 ///
 /// \param __P
 ///    A pointer specifying the memory address to be prefetched.
-static __inline__ void __attribute__((__always_inline__, __nodebug__))
-_m_prefetch(void *__P)
-{
-  __builtin_prefetch (__P, 0, 3 /* _MM_HINT_T0 */);
-}
+void _m_prefetch(void *__P);
 
 /// Loads a memory sequence containing the specified memory address into
 ///    the L1 data cache and sets the cache-coherency state to modified.
@@ -48,13 +48,10 @@ _m_prefetch(void *__P)
 ///
 /// \param __P
 ///    A pointer specifying the memory address to be prefetched.
-static __inline__ void __attribute__((__always_inline__, __nodebug__))
-_m_prefetchw(volatile const void *__P)
-{
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Wcast-qual"
-  __builtin_prefetch ((const void*)__P, 1, 3 /* _MM_HINT_T0 */);
-#pragma clang diagnostic pop
-}
+void _m_prefetchw(volatile const void *__P);
+
+#if defined(__cplusplus)
+} // extern "C"
+#endif
 
 #endif /* __PRFCHWINTRIN_H */