@cpp-linter/clang-tidy-win32-x64 13.0.0 → 14.0.0

package/lib/clang/{13.0.0 → 14.0.0}/include/ia32intrin.h

@@ -16,7 +16,7 @@
 
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__))
-#define __DEFAULT_FN_ATTRS_SSE42 __attribute__((__always_inline__, __nodebug__, __target__("sse4.2")))
+#define __DEFAULT_FN_ATTRS_CRC32 __attribute__((__always_inline__, __nodebug__, __target__("crc32")))
 
 #if defined(__cplusplus) && (__cplusplus >= 201103L)
 #define __DEFAULT_FN_ATTRS_CAST __attribute__((__always_inline__)) constexpr
@@ -282,7 +282,7 @@ _castu64_f64(unsigned long long __A) {
  *  \returns The result of adding operand \a __C to the CRC-32C checksum of
  *     operand \a __D.
  */
-static __inline__ unsigned int __DEFAULT_FN_ATTRS_SSE42
+static __inline__ unsigned int __DEFAULT_FN_ATTRS_CRC32
 __crc32b(unsigned int __C, unsigned char __D)
 {
   return __builtin_ia32_crc32qi(__C, __D);
@@ -303,7 +303,7 @@ __crc32b(unsigned int __C, unsigned char __D)
  *  \returns The result of adding operand \a __C to the CRC-32C checksum of
  *     operand \a __D.
  */
-static __inline__ unsigned int __DEFAULT_FN_ATTRS_SSE42
+static __inline__ unsigned int __DEFAULT_FN_ATTRS_CRC32
 __crc32w(unsigned int __C, unsigned short __D)
 {
   return __builtin_ia32_crc32hi(__C, __D);
@@ -324,7 +324,7 @@ __crc32w(unsigned int __C, unsigned short __D)
  *  \returns The result of adding operand \a __C to the CRC-32C checksum of
  *     operand \a __D.
  */
-static __inline__ unsigned int __DEFAULT_FN_ATTRS_SSE42
+static __inline__ unsigned int __DEFAULT_FN_ATTRS_CRC32
 __crc32d(unsigned int __C, unsigned int __D)
 {
   return __builtin_ia32_crc32si(__C, __D);
@@ -346,7 +346,7 @@ __crc32d(unsigned int __C, unsigned int __D)
  *  \returns The result of adding operand \a __C to the CRC-32C checksum of
  *     operand \a __D.
  */
-static __inline__ unsigned long long __DEFAULT_FN_ATTRS_SSE42
+static __inline__ unsigned long long __DEFAULT_FN_ATTRS_CRC32
 __crc32q(unsigned long long __C, unsigned long long __D)
 {
   return __builtin_ia32_crc32di(__C, __D);
@@ -435,7 +435,7 @@ __rorq(unsigned long long __X, int __C) {
 
 #undef __DEFAULT_FN_ATTRS
 #undef __DEFAULT_FN_ATTRS_CAST
-#undef __DEFAULT_FN_ATTRS_SSE42
+#undef __DEFAULT_FN_ATTRS_CRC32
 #undef __DEFAULT_FN_ATTRS_CONSTEXPR
 
 #endif /* __IA32INTRIN_H */

package/lib/clang/{13.0.0 → 14.0.0}/include/immintrin.h

@@ -10,6 +10,10 @@
 #ifndef __IMMINTRIN_H
 #define __IMMINTRIN_H
 
+#if !defined(__i386__) && !defined(__x86_64__)
+#error "This header is only meant to be used on x86 and x64 architecture"
+#endif
+
 #include <x86gprintrin.h>
 
 #if !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules) ||      \
@@ -210,6 +214,20 @@
 #include <avx512pfintrin.h>
 #endif
 
+/*
+ * FIXME: _Float16 type is legal only when HW support float16 operation.
+ * We use __AVX512FP16__ to identify if float16 is supported or not, so
+ * when float16 is not supported, the related header is not included.
+ *
+ */
+#if defined(__AVX512FP16__)
+#include <avx512fp16intrin.h>
+#endif
+
+#if defined(__AVX512FP16__) && defined(__AVX512VL__)
+#include <avx512vlfp16intrin.h>
+#endif
+
 #if !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules) ||      \
     defined(__AVX512BF16__)
 #include <avx512bf16intrin.h>
@@ -525,13 +543,13 @@ extern "C" {
 #if defined(__i386__) || defined(__x86_64__)
 static __inline__ long __DEFAULT_FN_ATTRS
 _InterlockedExchange_HLEAcquire(long volatile *_Target, long _Value) {
-  __asm__ __volatile__(".byte 0xf2 ; lock ; xchg %0, %1"
+  __asm__ __volatile__(".byte 0xf2 ; lock ; xchg {%0, %1|%1, %0}"
                        : "+r" (_Value), "+m" (*_Target) :: "memory");
   return _Value;
 }
 static __inline__ long __DEFAULT_FN_ATTRS
 _InterlockedExchange_HLERelease(long volatile *_Target, long _Value) {
-  __asm__ __volatile__(".byte 0xf3 ; lock ; xchg %0, %1"
+  __asm__ __volatile__(".byte 0xf3 ; lock ; xchg {%0, %1|%1, %0}"
                        : "+r" (_Value), "+m" (*_Target) :: "memory");
   return _Value;
 }
@@ -539,13 +557,13 @@ _InterlockedExchange_HLERelease(long volatile *_Target, long _Value) {
 #if defined(__x86_64__)
 static __inline__ __int64 __DEFAULT_FN_ATTRS
 _InterlockedExchange64_HLEAcquire(__int64 volatile *_Target, __int64 _Value) {
-  __asm__ __volatile__(".byte 0xf2 ; lock ; xchg %0, %1"
+  __asm__ __volatile__(".byte 0xf2 ; lock ; xchg {%0, %1|%1, %0}"
                        : "+r" (_Value), "+m" (*_Target) :: "memory");
   return _Value;
 }
 static __inline__ __int64 __DEFAULT_FN_ATTRS
 _InterlockedExchange64_HLERelease(__int64 volatile *_Target, __int64 _Value) {
-  __asm__ __volatile__(".byte 0xf3 ; lock ; xchg %0, %1"
+  __asm__ __volatile__(".byte 0xf3 ; lock ; xchg {%0, %1|%1, %0}"
                        : "+r" (_Value), "+m" (*_Target) :: "memory");
   return _Value;
 }
@@ -557,7 +575,7 @@ _InterlockedExchange64_HLERelease(__int64 volatile *_Target, __int64 _Value) {
 static __inline__ long __DEFAULT_FN_ATTRS
 _InterlockedCompareExchange_HLEAcquire(long volatile *_Destination,
                               long _Exchange, long _Comparand) {
-  __asm__ __volatile__(".byte 0xf2 ; lock ; cmpxchg %2, %1"
+  __asm__ __volatile__(".byte 0xf2 ; lock ; cmpxchg {%2, %1|%1, %2}"
                        : "+a" (_Comparand), "+m" (*_Destination)
                        : "r" (_Exchange) : "memory");
   return _Comparand;
@@ -565,7 +583,7 @@ _InterlockedCompareExchange_HLEAcquire(long volatile *_Destination,
 static __inline__ long __DEFAULT_FN_ATTRS
 _InterlockedCompareExchange_HLERelease(long volatile *_Destination,
                               long _Exchange, long _Comparand) {
-  __asm__ __volatile__(".byte 0xf3 ; lock ; cmpxchg %2, %1"
+  __asm__ __volatile__(".byte 0xf3 ; lock ; cmpxchg {%2, %1|%1, %2}"
                        : "+a" (_Comparand), "+m" (*_Destination)
                        : "r" (_Exchange) : "memory");
   return _Comparand;
@@ -575,7 +593,7 @@ _InterlockedCompareExchange_HLERelease(long volatile *_Destination,
 static __inline__ __int64 __DEFAULT_FN_ATTRS
 _InterlockedCompareExchange64_HLEAcquire(__int64 volatile *_Destination,
                               __int64 _Exchange, __int64 _Comparand) {
-  __asm__ __volatile__(".byte 0xf2 ; lock ; cmpxchg %2, %1"
+  __asm__ __volatile__(".byte 0xf2 ; lock ; cmpxchg {%2, %1|%1, %2}"
                        : "+a" (_Comparand), "+m" (*_Destination)
                        : "r" (_Exchange) : "memory");
   return _Comparand;
@@ -583,7 +601,7 @@ _InterlockedCompareExchange64_HLEAcquire(__int64 volatile *_Destination,
 static __inline__ __int64 __DEFAULT_FN_ATTRS
 _InterlockedCompareExchange64_HLERelease(__int64 volatile *_Destination,
                               __int64 _Exchange, __int64 _Comparand) {
-  __asm__ __volatile__(".byte 0xf3 ; lock ; cmpxchg %2, %1"
+  __asm__ __volatile__(".byte 0xf3 ; lock ; cmpxchg {%2, %1|%1, %2}"
                        : "+a" (_Comparand), "+m" (*_Destination)
                        : "r" (_Exchange) : "memory");
   return _Comparand;

package/lib/clang/{13.0.0 → 14.0.0}/include/intrin.h

@@ -97,8 +97,9 @@ unsigned long __readcr8(void);
 unsigned int __readdr(unsigned int);
 #ifdef __i386__
 unsigned char __readfsbyte(unsigned long);
-unsigned __int64 __readfsqword(unsigned long);
 unsigned short __readfsword(unsigned long);
+unsigned long __readfsdword(unsigned long);
+unsigned __int64 __readfsqword(unsigned long);
 #endif
 unsigned __int64 __readmsr(unsigned long);
 unsigned __int64 __readpmc(unsigned long);
@@ -149,10 +150,8 @@ long _InterlockedExchangeAdd_HLEAcquire(long volatile *, long);
 long _InterlockedExchangeAdd_HLERelease(long volatile *, long);
 __int64 _InterlockedExchangeAdd64_HLEAcquire(__int64 volatile *, __int64);
 __int64 _InterlockedExchangeAdd64_HLERelease(__int64 volatile *, __int64);
-void __attribute__((__deprecated__(
-    "use other intrinsics or C++11 atomics instead"))) _ReadBarrier(void);
-void __attribute__((__deprecated__(
-    "use other intrinsics or C++11 atomics instead"))) _ReadWriteBarrier(void);
+void _ReadBarrier(void);
+void _ReadWriteBarrier(void);
 unsigned int _rorx_u32(unsigned int, const unsigned int);
 int _sarx_i32(int, unsigned int);
 #if __STDC_HOSTED__
@@ -163,8 +162,7 @@ unsigned int _shrx_u32(unsigned int, unsigned int);
 void _Store_HLERelease(long volatile *, long);
 void _Store64_HLERelease(__int64 volatile *, __int64);
 void _StorePointer_HLERelease(void *volatile *, void *);
-void __attribute__((__deprecated__(
-    "use other intrinsics or C++11 atomics instead"))) _WriteBarrier(void);
+void _WriteBarrier(void);
 unsigned __int32 xbegin(void);
 void _xend(void);
 
@@ -457,7 +455,9 @@ static __inline__ void __DEFAULT_FN_ATTRS __movsb(unsigned char *__dst,
                        :
                        : "memory");
 #else
-  __asm__ __volatile__("xchg %%esi, %1\nrep movsb\nxchg %%esi, %1"
+  __asm__ __volatile__("xchg {%%esi, %1|%1, esi}\n"
+                       "rep movsb\n"
+                       "xchg {%%esi, %1|%1, esi}"
                        : "+D"(__dst), "+r"(__src), "+c"(__n)
                        :
                        : "memory");
@@ -467,12 +467,14 @@ static __inline__ void __DEFAULT_FN_ATTRS __movsd(unsigned long *__dst,
                                                   unsigned long const *__src,
                                                   size_t __n) {
 #if defined(__x86_64__)
-  __asm__ __volatile__("rep movsl"
+  __asm__ __volatile__("rep movs{l|d}"
                        : "+D"(__dst), "+S"(__src), "+c"(__n)
                        :
                        : "memory");
 #else
-  __asm__ __volatile__("xchg %%esi, %1\nrep movsl\nxchg %%esi, %1"
+  __asm__ __volatile__("xchg {%%esi, %1|%1, esi}\n"
+                       "rep movs{l|d}\n"
+                       "xchg {%%esi, %1|%1, esi}"
                        : "+D"(__dst), "+r"(__src), "+c"(__n)
                        :
                        : "memory");
@@ -487,7 +489,9 @@ static __inline__ void __DEFAULT_FN_ATTRS __movsw(unsigned short *__dst,
                        :
                        : "memory");
 #else
-  __asm__ __volatile__("xchg %%esi, %1\nrep movsw\nxchg %%esi, %1"
+  __asm__ __volatile__("xchg {%%esi, %1|%1, esi}\n"
+                       "rep movsw\n"
+                       "xchg {%%esi, %1|%1, esi}"
                        : "+D"(__dst), "+r"(__src), "+c"(__n)
                        :
                        : "memory");
@@ -496,7 +500,7 @@ static __inline__ void __DEFAULT_FN_ATTRS __movsw(unsigned short *__dst,
 static __inline__ void __DEFAULT_FN_ATTRS __stosd(unsigned long *__dst,
                                                   unsigned long __x,
                                                   size_t __n) {
-  __asm__ __volatile__("rep stosl"
+  __asm__ __volatile__("rep stos{l|d}"
                        : "+D"(__dst), "+c"(__n)
                        : "a"(__x)
                        : "memory");
@@ -538,9 +542,9 @@ static __inline__ void __DEFAULT_FN_ATTRS __stosq(unsigned __int64 *__dst,
 #else
 /* x86-64 uses %rbx as the base register, so preserve it. */
 #define __cpuid_count(__leaf, __count, __eax, __ebx, __ecx, __edx)             \
-  __asm("xchgq %%rbx,%q1\n"                                                    \
+  __asm("xchg{q} {%%rbx, %q1|%q1, rbx}\n"                                      \
         "cpuid\n"                                                              \
-        "xchgq %%rbx,%q1"                                                      \
+        "xchg{q} {%%rbx, %q1|%q1, rbx}"                                        \
         : "=a"(__eax), "=r"(__ebx), "=c"(__ecx), "=d"(__edx)                   \
         : "0"(__leaf), "2"(__count))
 #endif
@@ -600,13 +604,17 @@ __readmsr(unsigned long __register) {
 
 static __inline__ unsigned __LPTRINT_TYPE__ __DEFAULT_FN_ATTRS __readcr3(void) {
   unsigned __LPTRINT_TYPE__ __cr3_val;
-  __asm__ __volatile__ ("mov %%cr3, %0" : "=r"(__cr3_val) : : "memory");
+  __asm__ __volatile__(
+                       "mov {%%cr3, %0|%0, cr3}"
+                       : "=r"(__cr3_val)
+                       :
+                       : "memory");
   return __cr3_val;
 }
 
 static __inline__ void __DEFAULT_FN_ATTRS
 __writecr3(unsigned __INTPTR_TYPE__ __cr3_val) {
-  __asm__ ("mov %0, %%cr3" : : "r"(__cr3_val) : "memory");
+  __asm__ ("mov {%0, %%cr3|cr3, %0}" : : "r"(__cr3_val) : "memory");
 }
 
 #ifdef __cplusplus

package/lib/clang/{13.0.0 → 14.0.0}/include/keylockerintrin.h

@@ -99,7 +99,7 @@ _mm_loadiwkey (unsigned int __ctl, __m128i __intkey,
 }
 
 /// Wrap a 128-bit AES key from __key into a key handle and output in
-/// ((__m128i*)__h) to ((__m128i*)__h) + 5  and a 32-bit value as return.
+/// ((__m128i*)__h) to ((__m128i*)__h) + 2  and a 32-bit value as return.
 /// The explicit source operand __htype specifies handle restrictions.
 ///
 /// \headerfile <x86intrin.h>
@@ -120,9 +120,6 @@ _mm_loadiwkey (unsigned int __ctl, __m128i __intkey,
 /// MEM[__h+127:__h] := Handle[127:0]   // AAD
 /// MEM[__h+255:__h+128] := Handle[255:128] // Integrity Tag
 /// MEM[__h+383:__h+256] := Handle[383:256] // CipherText
-/// MEM[__h+511:__h+384] := 0 // Reserved for future usage
-/// MEM[__h+639:__h+512] := 0 // Reserved for future usage
-/// MEM[__h+767:__h+640] := 0 // Reserved for future usage
 /// OF := 0
 /// SF := 0
 /// ZF := 0
@@ -136,7 +133,7 @@ _mm_encodekey128_u32(unsigned int __htype, __m128i __key, void *__h) {
 }
 
 /// Wrap a 256-bit AES key from __key_hi:__key_lo into a key handle, then
-/// output handle in ((__m128i*)__h) to ((__m128i*)__h) + 6 and
+/// output handle in ((__m128i*)__h) to ((__m128i*)__h) + 3 and
 /// a 32-bit value as return.
 /// The explicit source operand __htype specifies handle restrictions.
 ///
@@ -160,9 +157,6 @@ _mm_encodekey128_u32(unsigned int __htype, __m128i __key, void *__h) {
 /// MEM[__h+255:__h+128] := Handle[255:128] // Tag
 /// MEM[__h+383:__h+256] := Handle[383:256] // CipherText[127:0]
 /// MEM[__h+511:__h+384] := Handle[511:384] // CipherText[255:128]
-/// MEM[__h+639:__h+512] := 0 // Reserved for future usage
-/// MEM[__h+767:__h+640] := 0 // Reserved for future usage
-/// MEM[__h+895:__h+768] := 0 Integrity// Reserved for future usage
 /// OF := 0
 /// SF := 0
 /// ZF := 0

package/lib/clang/{13.0.0 → 14.0.0}/include/limits.h

@@ -62,6 +62,26 @@
 
 #define CHAR_BIT  __CHAR_BIT__
 
+/* C2x 5.2.4.2.1 */
+/* FIXME: This is using the placeholder dates Clang produces for these macros
+   in C2x mode; switch to the correct values once they've been published. */
+#if __STDC_VERSION__ >= 202000L
+#define BOOL_WIDTH   __BOOL_WIDTH__
+#define CHAR_WIDTH   CHAR_BIT
+#define SCHAR_WIDTH  CHAR_BIT
+#define UCHAR_WIDTH  CHAR_BIT
+#define USHRT_WIDTH  __SHRT_WIDTH__
+#define SHRT_WIDTH   __SHRT_WIDTH__
+#define UINT_WIDTH   __INT_WIDTH__
+#define INT_WIDTH    __INT_WIDTH__
+#define ULONG_WIDTH  __LONG_WIDTH__
+#define LONG_WIDTH   __LONG_WIDTH__
+#define ULLONG_WIDTH __LLONG_WIDTH__
+#define LLONG_WIDTH  __LLONG_WIDTH__
+
+#define BITINT_MAXWIDTH __BITINT_MAXWIDTH__
+#endif
+
 #ifdef __CHAR_UNSIGNED__  /* -funsigned-char */
 #define CHAR_MIN 0
 #define CHAR_MAX UCHAR_MAX

package/lib/clang/{13.0.0 → 14.0.0}/include/mmintrin.h

@@ -10,6 +10,10 @@
 #ifndef __MMINTRIN_H
 #define __MMINTRIN_H
 
+#if !defined(__i386__) && !defined(__x86_64__)
+#error "This header is only meant to be used on x86 and x64 architecture"
+#endif
+
 typedef long long __m64 __attribute__((__vector_size__(8), __aligned__(8)));
 
 typedef long long __v1di __attribute__((__vector_size__(8)));

package/lib/clang/{13.0.0 → 14.0.0}/include/nmmintrin.h

@@ -10,6 +10,10 @@
 #ifndef __NMMINTRIN_H
 #define __NMMINTRIN_H
 
+#if !defined(__i386__) && !defined(__x86_64__)
+#error "This header is only meant to be used on x86 and x64 architecture"
+#endif
+
 /* To match expectations of gcc we put the sse4.2 definitions into smmintrin.h,
    just include it now then.  */
 #include <smmintrin.h>

package/lib/clang/{13.0.0 → 14.0.0}/include/opencl-c-base.h

@@ -12,8 +12,8 @@
 // Define extension macros
 
 #if (defined(__OPENCL_CPP_VERSION__) || __OPENCL_C_VERSION__ >= 200)
-// For SPIR all extensions are supported.
-#if defined(__SPIR__)
+// For SPIR and SPIR-V all extensions are supported.
+#if defined(__SPIR__) || defined(__SPIRV__)
 #define cl_khr_subgroup_extended_types 1
 #define cl_khr_subgroup_non_uniform_vote 1
 #define cl_khr_subgroup_ballot 1
@@ -25,12 +25,31 @@
 #define cl_khr_integer_dot_product 1
 #define __opencl_c_integer_dot_product_input_4x8bit 1
 #define __opencl_c_integer_dot_product_input_4x8bit_packed 1
+#define cl_ext_float_atomics 1
+#ifdef cl_khr_fp16
+#define __opencl_c_ext_fp16_global_atomic_load_store 1
+#define __opencl_c_ext_fp16_local_atomic_load_store 1
+#define __opencl_c_ext_fp16_global_atomic_add 1
+#define __opencl_c_ext_fp16_local_atomic_add 1
+#define __opencl_c_ext_fp16_global_atomic_min_max 1
+#define __opencl_c_ext_fp16_local_atomic_min_max 1
+#endif
+#ifdef cl_khr_fp64
+#define __opencl_c_ext_fp64_global_atomic_add 1
+#define __opencl_c_ext_fp64_local_atomic_add 1
+#define __opencl_c_ext_fp64_global_atomic_min_max 1
+#define __opencl_c_ext_fp64_local_atomic_min_max 1
+#endif
+#define __opencl_c_ext_fp32_global_atomic_add 1
+#define __opencl_c_ext_fp32_local_atomic_add 1
+#define __opencl_c_ext_fp32_global_atomic_min_max 1
+#define __opencl_c_ext_fp32_local_atomic_min_max 1
 
-#endif // defined(__SPIR__)
+#endif // defined(__SPIR__) || defined(__SPIRV__)
 #endif // (defined(__OPENCL_CPP_VERSION__) || __OPENCL_C_VERSION__ >= 200)
 
 // Define feature macros for OpenCL C 2.0
-#if (defined(__OPENCL_CPP_VERSION__) || __OPENCL_C_VERSION__ == 200)
+#if (__OPENCL_CPP_VERSION__ == 100 || __OPENCL_C_VERSION__ == 200)
 #define __opencl_c_pipes 1
 #define __opencl_c_generic_address_space 1
 #define __opencl_c_work_group_collective_functions 1
@@ -45,12 +64,21 @@
 #endif
 
 // Define header-only feature macros for OpenCL C 3.0.
-#if (__OPENCL_C_VERSION__ == 300)
-// For the SPIR target all features are supported.
-#if defined(__SPIR__)
+#if (__OPENCL_CPP_VERSION__ == 202100 || __OPENCL_C_VERSION__ == 300)
+// For the SPIR and SPIR-V target all features are supported.
+#if defined(__SPIR__) || defined(__SPIRV__)
+#define __opencl_c_atomic_order_seq_cst 1
+#define __opencl_c_atomic_scope_device 1
 #define __opencl_c_atomic_scope_all_devices 1
+#define __opencl_c_read_write_images 1
 #endif // defined(__SPIR__)
-#endif // (__OPENCL_C_VERSION__ == 300)
+#endif // (__OPENCL_CPP_VERSION__ == 202100 || __OPENCL_C_VERSION__ == 300)
+
+#if !defined(__opencl_c_generic_address_space)
+// Internal feature macro to provide named (global, local, private) address
+// space overloads for builtin functions that take a pointer argument.
+#define __opencl_c_named_address_space_builtins 1
+#endif // !defined(__opencl_c_generic_address_space)
 
 // built-in scalar data types:
 
@@ -329,11 +357,17 @@ typedef enum memory_scope {
   memory_scope_device = __OPENCL_MEMORY_SCOPE_DEVICE,
 #if defined(__opencl_c_atomic_scope_all_devices)
   memory_scope_all_svm_devices = __OPENCL_MEMORY_SCOPE_ALL_SVM_DEVICES,
-#if (__OPENCL_C_VERSION__ >= CL_VERSION_3_0)
+#if (__OPENCL_C_VERSION__ >= CL_VERSION_3_0 || __OPENCL_CPP_VERSION__ >= 202100)
   memory_scope_all_devices = memory_scope_all_svm_devices,
-#endif // __OPENCL_C_VERSION__ >= CL_VERSION_3_0
+#endif // (__OPENCL_C_VERSION__ >= CL_VERSION_3_0 || __OPENCL_CPP_VERSION__ >= 202100)
 #endif // defined(__opencl_c_atomic_scope_all_devices)
-#if defined(cl_intel_subgroups) || defined(cl_khr_subgroups)
+/**
+ * Subgroups have different requirements on forward progress, so just test
+ * all the relevant macros.
+ * CL 3.0 sub-groups "they are not guaranteed to make independent forward progress"
+ * KHR subgroups "Subgroups within a workgroup are independent, make forward progress with respect to each other"
+ */
+#if defined(cl_intel_subgroups) || defined(cl_khr_subgroups) || defined(__opencl_c_subgroups)
   memory_scope_sub_group = __OPENCL_MEMORY_SCOPE_SUB_GROUP
 #endif
 } memory_scope;
@@ -473,12 +507,14 @@ typedef int clk_profiling_info;
 
 #define MAX_WORK_DIM 3
 
+#ifdef __opencl_c_device_enqueue
 typedef struct {
   unsigned int workDimension;
   size_t globalWorkOffset[MAX_WORK_DIM];
   size_t globalWorkSize[MAX_WORK_DIM];
   size_t localWorkSize[MAX_WORK_DIM];
 } ndrange_t;
+#endif // __opencl_c_device_enqueue
 
 #endif // defined(__OPENCL_CPP_VERSION__) || (__OPENCL_C_VERSION__ >= CL_VERSION_2_0)
 
@@ -572,6 +608,28 @@ typedef struct {
 #define as_intptr_t(x) __builtin_astype((x), intptr_t)
 #define as_uintptr_t(x) __builtin_astype((x), uintptr_t)
 
+// C++ for OpenCL - __remove_address_space
+#if defined(__OPENCL_CPP_VERSION__)
+template <typename _Tp> struct __remove_address_space { using type = _Tp; };
+#if defined(__opencl_c_generic_address_space)
+template <typename _Tp> struct __remove_address_space<__generic _Tp> {
+  using type = _Tp;
+};
+#endif
+template <typename _Tp> struct __remove_address_space<__global _Tp> {
+  using type = _Tp;
+};
+template <typename _Tp> struct __remove_address_space<__private _Tp> {
+  using type = _Tp;
+};
+template <typename _Tp> struct __remove_address_space<__local _Tp> {
+  using type = _Tp;
+};
+template <typename _Tp> struct __remove_address_space<__constant _Tp> {
+  using type = _Tp;
+};
+#endif
+
 // OpenCL v1.1 s6.9, v1.2/2.0 s6.10 - Function qualifiers
 
 #define __kernel_exec(X, typen) __kernel \