@cpp-linter/clang-tidy-win32-x64 19.1.0 → 21.1.0

package/lib/clang/{19 → 21}/include/opencl-c.h

@@ -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 +17482,50 @@ 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)
+#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 +17617,12 @@ 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 +17630,21 @@ 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 +17652,261 @@ 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 );
 #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 );
+#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);
+#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
 

package/lib/clang/{19 → 21}/include/openmp_wrappers/__clang_openmp_device_functions.h

@@ -10,17 +10,15 @@
 #ifndef __CLANG_OPENMP_DEVICE_FUNCTIONS_H__
 #define __CLANG_OPENMP_DEVICE_FUNCTIONS_H__
 
-#ifndef _OPENMP
-#error "This file is for OpenMP compilation only."
-#endif
-
 #ifdef __cplusplus
 extern "C" {
 #endif
 
+#ifdef __NVPTX__
 #pragma omp begin declare variant match(                                       \
     device = {arch(nvptx, nvptx64)}, implementation = {extension(match_any)})
 
+#pragma push_macro("__CUDA__")
 #define __CUDA__
 #define __OPENMP_NVPTX__
 
@@ -31,9 +29,10 @@ extern "C" {
 #include <__clang_cuda_device_functions.h>
 
 #undef __OPENMP_NVPTX__
-#undef __CUDA__
+#pragma pop_macro("__CUDA__")
 
 #pragma omp end declare variant
+#endif
 
 #ifdef __AMDGCN__
 #pragma omp begin declare variant match(device = {arch(amdgcn)})

package/lib/clang/{19 → 21}/include/openmp_wrappers/complex_cmath.h

@@ -64,8 +64,13 @@ template <class _Tp> __DEVICE__ _Tp norm(const std::complex<_Tp> &__c) {
 }
 
 // conj
-
-template <class _Tp> std::complex<_Tp> conj(const std::complex<_Tp> &__c) {
+#ifdef _GLIBCXX20_CONSTEXPR
+#define CXX20_CONSTEXPR_DEVICE __DEVICE__
+#else
+#define CXX20_CONSTEXPR_DEVICE
+#endif
+template <class _Tp>
+CXX20_CONSTEXPR_DEVICE std::complex<_Tp> conj(const std::complex<_Tp> &__c) {
   return std::complex<_Tp>(__c.real(), -__c.imag());
 }
 

package/lib/clang/{19 → 21}/include/pmmintrin.h

@@ -17,9 +17,21 @@
 #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
+#else
+#define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS
+#endif
 
 /// Loads data from an unaligned memory location to elements in a 128-bit
 ///    vector.
@@ -122,7 +134,7 @@ _mm_hsub_ps(__m128 __a, __m128 __b)
 ///    destination.
 /// \returns A 128-bit vector of [4 x float] containing the moved and duplicated
 ///    values.
-static __inline__ __m128 __DEFAULT_FN_ATTRS
+static __inline__ __m128 __DEFAULT_FN_ATTRS_CONSTEXPR
 _mm_movehdup_ps(__m128 __a)
 {
   return __builtin_shufflevector((__v4sf)__a, (__v4sf)__a, 1, 1, 3, 3);
@@ -143,7 +155,7 @@ _mm_movehdup_ps(__m128 __a)
 ///    destination.
 /// \returns A 128-bit vector of [4 x float] containing the moved and duplicated
 ///    values.
-static __inline__ __m128 __DEFAULT_FN_ATTRS
+static __inline__ __m128 __DEFAULT_FN_ATTRS_CONSTEXPR
 _mm_moveldup_ps(__m128 __a)
 {
   return __builtin_shufflevector((__v4sf)__a, (__v4sf)__a, 0, 0, 2, 2);
@@ -244,7 +256,7 @@ _mm_hsub_pd(__m128d __a, __m128d __b)
 ///    [127:64] and [63:0] of the destination.
 /// \returns A 128-bit vector of [2 x double] containing the moved and
 ///    duplicated values.
-static __inline__ __m128d __DEFAULT_FN_ATTRS
+static __inline__ __m128d __DEFAULT_FN_ATTRS_CONSTEXPR
 _mm_movedup_pd(__m128d __a)
 {
   return __builtin_shufflevector((__v2df)__a, (__v2df)__a, 0, 0);
@@ -297,5 +309,6 @@ _mm_mwait(unsigned __extensions, unsigned __hints)
 }
 
 #undef __DEFAULT_FN_ATTRS
+#undef __DEFAULT_FN_ATTRS_CONSTEXPR
 
 #endif /* __PMMINTRIN_H */

package/lib/clang/{19 → 21}/include/popcntintrin.h

@@ -11,12 +11,13 @@
 #define __POPCNTINTRIN_H
 
 /* Define the default attributes for the functions in this file. */
-#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("popcnt")))
-
 #if defined(__cplusplus) && (__cplusplus >= 201103L)
-#define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS constexpr
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("popcnt"))) constexpr
 #else
-#define __DEFAULT_FN_ATTRS_CONSTEXPR __DEFAULT_FN_ATTRS
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__, __target__("popcnt")))
 #endif
 
 /// Counts the number of bits in the source operand having a value of 1.
@@ -29,7 +30,7 @@
 ///    An unsigned 32-bit integer operand.
 /// \returns A 32-bit integer containing the number of bits with value 1 in the
 ///    source operand.
-static __inline__ int __DEFAULT_FN_ATTRS_CONSTEXPR
+static __inline__ int __DEFAULT_FN_ATTRS
 _mm_popcnt_u32(unsigned int __A)
 {
   return __builtin_popcount(__A);
@@ -46,7 +47,7 @@ _mm_popcnt_u32(unsigned int __A)
 ///    An unsigned 64-bit integer operand.
 /// \returns A 64-bit integer containing the number of bits with value 1 in the
 ///    source operand.
-static __inline__ long long __DEFAULT_FN_ATTRS_CONSTEXPR
+static __inline__ long long __DEFAULT_FN_ATTRS
 _mm_popcnt_u64(unsigned long long __A)
 {
   return __builtin_popcountll(__A);
@@ -54,6 +55,5 @@ _mm_popcnt_u64(unsigned long long __A)
 #endif /* __x86_64__ */
 
 #undef __DEFAULT_FN_ATTRS
-#undef __DEFAULT_FN_ATTRS_CONSTEXPR
 
 #endif /* __POPCNTINTRIN_H */

package/lib/clang/{19 → 21}/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 */