@cpp-linter/clang-tidy-win32-x64 18.1.5 → 20.1.0

package/README.md

@@ -1,7 +1,7 @@
 # @cpp-linter/clang-tidy-win32-x64
 
-The Windows x64 binary of clang-tidy from LLVM 18.1.5, for [`@cpp-linter/clang-tidy`](https://www.npmjs.com/package/@cpp-linter/clang-tidy).
+The Windows x64 binary of clang-tidy from LLVM 20.1.0, for [`@cpp-linter/clang-tidy`](https://www.npmjs.com/package/@cpp-linter/clang-tidy).
 
 Install `@cpp-linter/clang-tidy` instead of this package: npm picks the binary for your platform.
 
-The binary is a static build from the release [`llvm-18.1.5-3`](https://github.com/cpp-linter/clang-tools-static-binaries/releases/tag/llvm-18.1.5-3) of [cpp-linter/clang-tools-static-binaries](https://github.com/cpp-linter/clang-tools-static-binaries). LLVM is licensed under the Apache License v2.0 with LLVM Exceptions (see `LICENSE.TXT`).
+The binary is a static build from the release [`llvm-20.1.0-3`](https://github.com/cpp-linter/clang-tools-static-binaries/releases/tag/llvm-20.1.0-3) of [cpp-linter/clang-tools-static-binaries](https://github.com/cpp-linter/clang-tools-static-binaries). LLVM is licensed under the Apache License v2.0 with LLVM Exceptions (see `LICENSE.TXT`).

package/bin/clang-tidy.exe

@@ -1,4 +1,4 @@
 [diffend] Oversized file quarantined before diffing.
 name: package/bin/clang-tidy.exe
-size: 59571712 bytes
-sha256: 8859ee34b6a2b1ffd908be2fa761e720433f123e9c6e21188f5d0a11cdde2d84
+size: 65729536 bytes
+sha256: 3820f1bc6c7b64b09d282aa933e4fe6b332ff33433cadcf9474e8a104435edd3

package/lib/clang/{18 → 20}/include/__clang_cuda_device_functions.h

@@ -529,6 +529,20 @@ __DEVICE__ void __threadfence(void) { __nvvm_membar_gl(); }
 __DEVICE__ void __threadfence_block(void) { __nvvm_membar_cta(); };
 __DEVICE__ void __threadfence_system(void) { __nvvm_membar_sys(); };
 __DEVICE__ void __trap(void) { __asm__ __volatile__("trap;"); }
+__DEVICE__ unsigned short
+__usAtomicCAS(unsigned short *__p, unsigned short __cmp, unsigned short __v) {
+  return __nvvm_atom_cas_gen_us(__p, __cmp, __v);
+}
+__DEVICE__ unsigned short __usAtomicCAS_block(unsigned short *__p,
+                                              unsigned short __cmp,
+                                              unsigned short __v) {
+  return __nvvm_atom_cta_cas_gen_us(__p, __cmp, __v);
+}
+__DEVICE__ unsigned short __usAtomicCAS_system(unsigned short *__p,
+                                               unsigned short __cmp,
+                                               unsigned short __v) {
+  return __nvvm_atom_sys_cas_gen_us(__p, __cmp, __v);
+}
 __DEVICE__ unsigned int __uAtomicAdd(unsigned int *__p, unsigned int __v) {
   return __nvvm_atom_add_gen_i((int *)__p, __v);
 }

package/lib/clang/{18 → 20}/include/__clang_cuda_intrinsics.h

@@ -215,9 +215,7 @@ inline __device__ unsigned int __activemask() {
 #if CUDA_VERSION < 9020
   return __nvvm_vote_ballot(1);
 #else
-  unsigned int mask;
-  asm volatile("activemask.b32 %0;" : "=r"(mask));
-  return mask;
+  return __nvvm_activemask();
 #endif
 }
 

package/lib/clang/{18 → 20}/include/__clang_cuda_math.h

@@ -12,6 +12,10 @@
 #error "This file is for CUDA compilation only."
 #endif
 
+// The __CLANG_GPU_DISABLE_MATH_WRAPPERS macro provides a way to let standard
+// libcalls reach the link step instead of being eagerly replaced.
+#ifndef __CLANG_GPU_DISABLE_MATH_WRAPPERS
+
 #ifndef __OPENMP_NVPTX__
 #if CUDA_VERSION < 9000
 #error This file is intended to be used with CUDA-9+ only.
@@ -345,4 +349,5 @@ __DEVICE__ float ynf(int __a, float __b) { return __nv_ynf(__a, __b); }
 #pragma pop_macro("__DEVICE_VOID__")
 #pragma pop_macro("__FAST_OR_SLOW")
 
+#endif // __CLANG_GPU_DISABLE_MATH_WRAPPERS
 #endif // __CLANG_CUDA_MATH_H__

package/lib/clang/{18 → 20}/include/__clang_hip_cmath.h

@@ -395,7 +395,12 @@ template <class _Tp> struct __numeric_type {
   // No support for long double, use double instead.
   static double __test(long double);
 
-  typedef decltype(__test(declval<_Tp>())) type;
+  template <typename _U>
+  static auto __test_impl(int) -> decltype(__test(declval<_U>()));
+
+  template <typename _U> static void __test_impl(...);
+
+  typedef decltype(__test_impl<_Tp>(0)) type;
   static const bool value = !is_same<type, void>::value;
 };
 

package/lib/clang/{18 → 20}/include/__clang_hip_math.h

@@ -13,6 +13,10 @@
 #error "This file is for HIP and OpenMP AMDGCN device compilation only."
 #endif
 
+// The __CLANG_GPU_DISABLE_MATH_WRAPPERS macro provides a way to let standard
+// libcalls reach the link step instead of being eagerly replaced.
+#ifndef __CLANG_GPU_DISABLE_MATH_WRAPPERS
+
 #if !defined(__HIPCC_RTC__)
 #include <limits.h>
 #include <stdint.h>
@@ -1321,4 +1325,5 @@ __host__ inline static int max(int __arg1, int __arg2) {
 #pragma pop_macro("__RETURN_TYPE")
 #pragma pop_macro("__FAST_OR_SLOW")
 
+#endif // __CLANG_GPU_DISABLE_MATH_WRAPPERS
 #endif // __CLANG_HIP_MATH_H__

package/lib/clang/20/include/__stdarg_header_macro.h

@@ -0,0 +1,12 @@
+/*===---- __stdarg_header_macro.h ------------------------------------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef __STDARG_H
+#define __STDARG_H
+#endif

package/lib/clang/20/include/__stddef_header_macro.h

@@ -0,0 +1,12 @@
+/*===---- __stddef_header_macro.h ------------------------------------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef __STDDEF_H
+#define __STDDEF_H
+#endif

package/lib/clang/{18 → 20}/include/adcintrin.h

@@ -15,7 +15,12 @@
 #endif
 
 /* Define the default attributes for the functions in this file. */
+#if defined(__cplusplus) && (__cplusplus >= 201103L)
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__)) constexpr
+#else
 #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__))
+#endif
 
 /* Use C++ inline semantics in C++, GNU inline for C mode. */
 #if defined(__cplusplus)

package/lib/clang/{18 → 20}/include/adxintrin.h

@@ -15,8 +15,13 @@
 #define __ADXINTRIN_H
 
 /* Define the default attributes for the functions in this file. */
+#if defined(__cplusplus) && (__cplusplus >= 201103L)
+#define __DEFAULT_FN_ATTRS                                                     \
+  __attribute__((__always_inline__, __nodebug__, __target__("adx"))) constexpr
+#else
 #define __DEFAULT_FN_ATTRS                                                     \
   __attribute__((__always_inline__, __nodebug__, __target__("adx")))
+#endif
 
 /* Use C++ inline semantics in C++, GNU inline for C mode. */
 #if defined(__cplusplus)

package/lib/clang/{18 → 20}/include/altivec.h

@@ -2502,37 +2502,37 @@ vec_cmplt(vector unsigned long long __a, vector unsigned long long __b) {
 
 static __inline__ vector unsigned char __ATTRS_o_ai
 vec_popcnt(vector signed char __a) {
-  return (vector unsigned char)__builtin_altivec_vpopcntb(
+  return (vector unsigned char)__builtin_elementwise_popcount(
       (vector unsigned char)__a);
 }
 static __inline__ vector unsigned char __ATTRS_o_ai
 vec_popcnt(vector unsigned char __a) {
-  return __builtin_altivec_vpopcntb(__a);
+  return __builtin_elementwise_popcount(__a);
 }
 static __inline__ vector unsigned short __ATTRS_o_ai
 vec_popcnt(vector signed short __a) {
-  return (vector unsigned short)__builtin_altivec_vpopcnth(
+  return (vector unsigned short)__builtin_elementwise_popcount(
       (vector unsigned short)__a);
 }
 static __inline__ vector unsigned short __ATTRS_o_ai
 vec_popcnt(vector unsigned short __a) {
-  return __builtin_altivec_vpopcnth(__a);
+  return __builtin_elementwise_popcount(__a);
 }
 static __inline__ vector unsigned int __ATTRS_o_ai
 vec_popcnt(vector signed int __a) {
-  return __builtin_altivec_vpopcntw((vector unsigned int)__a);
+  return __builtin_elementwise_popcount((vector unsigned int)__a);
 }
 static __inline__ vector unsigned int __ATTRS_o_ai
 vec_popcnt(vector unsigned int __a) {
-  return __builtin_altivec_vpopcntw(__a);
+  return __builtin_elementwise_popcount(__a);
 }
 static __inline__ vector unsigned long long __ATTRS_o_ai
 vec_popcnt(vector signed long long __a) {
-  return __builtin_altivec_vpopcntd((vector unsigned long long)__a);
+  return __builtin_elementwise_popcount((vector unsigned long long)__a);
 }
 static __inline__ vector unsigned long long __ATTRS_o_ai
 vec_popcnt(vector unsigned long long __a) {
-  return __builtin_altivec_vpopcntd(__a);
+  return __builtin_elementwise_popcount(__a);
 }
 
 #define vec_vclz vec_cntlz

package/lib/clang/20/include/amdgpuintrin.h

@@ -0,0 +1,194 @@
+//===-- amdgpuintrin.h - AMDPGU intrinsic functions -----------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef __AMDGPUINTRIN_H
+#define __AMDGPUINTRIN_H
+
+#ifndef __AMDGPU__
+#error "This file is intended for AMDGPU targets or offloading to AMDGPU"
+#endif
+
+#include <stdint.h>
+
+#if !defined(__cplusplus)
+_Pragma("push_macro(\"bool\")");
+#define bool _Bool
+#endif
+
+_Pragma("omp begin declare target device_type(nohost)");
+_Pragma("omp begin declare variant match(device = {arch(amdgcn)})");
+
+// Type aliases to the address spaces used by the AMDGPU backend.
+#define __gpu_private __attribute__((address_space(5)))
+#define __gpu_constant __attribute__((address_space(4)))
+#define __gpu_local __attribute__((address_space(3)))
+#define __gpu_global __attribute__((address_space(1)))
+#define __gpu_generic __attribute__((address_space(0)))
+
+// Attribute to declare a function as a kernel.
+#define __gpu_kernel __attribute__((amdgpu_kernel, visibility("protected")))
+
+// Returns the number of workgroups in the 'x' dimension of the grid.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_num_blocks_x(void) {
+  return __builtin_amdgcn_grid_size_x() / __builtin_amdgcn_workgroup_size_x();
+}
+
+// Returns the number of workgroups in the 'y' dimension of the grid.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_num_blocks_y(void) {
+  return __builtin_amdgcn_grid_size_y() / __builtin_amdgcn_workgroup_size_y();
+}
+
+// Returns the number of workgroups in the 'z' dimension of the grid.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_num_blocks_z(void) {
+  return __builtin_amdgcn_grid_size_z() / __builtin_amdgcn_workgroup_size_z();
+}
+
+// Returns the 'x' dimension of the current AMD workgroup's id.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_block_id_x(void) {
+  return __builtin_amdgcn_workgroup_id_x();
+}
+
+// Returns the 'y' dimension of the current AMD workgroup's id.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_block_id_y(void) {
+  return __builtin_amdgcn_workgroup_id_y();
+}
+
+// Returns the 'z' dimension of the current AMD workgroup's id.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_block_id_z(void) {
+  return __builtin_amdgcn_workgroup_id_z();
+}
+
+// Returns the number of workitems in the 'x' dimension.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_num_threads_x(void) {
+  return __builtin_amdgcn_workgroup_size_x();
+}
+
+// Returns the number of workitems in the 'y' dimension.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_num_threads_y(void) {
+  return __builtin_amdgcn_workgroup_size_y();
+}
+
+// Returns the number of workitems in the 'z' dimension.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_num_threads_z(void) {
+  return __builtin_amdgcn_workgroup_size_z();
+}
+
+// Returns the 'x' dimension id of the workitem in the current AMD workgroup.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_thread_id_x(void) {
+  return __builtin_amdgcn_workitem_id_x();
+}
+
+// Returns the 'y' dimension id of the workitem in the current AMD workgroup.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_thread_id_y(void) {
+  return __builtin_amdgcn_workitem_id_y();
+}
+
+// Returns the 'z' dimension id of the workitem in the current AMD workgroup.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_thread_id_z(void) {
+  return __builtin_amdgcn_workitem_id_z();
+}
+
+// Returns the size of an AMD wavefront, either 32 or 64 depending on hardware
+// and compilation options.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_num_lanes(void) {
+  return __builtin_amdgcn_wavefrontsize();
+}
+
+// Returns the id of the thread inside of an AMD wavefront executing together.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t __gpu_lane_id(void) {
+  return __builtin_amdgcn_mbcnt_hi(~0u, __builtin_amdgcn_mbcnt_lo(~0u, 0u));
+}
+
+// Returns the bit-mask of active threads in the current wavefront.
+_DEFAULT_FN_ATTRS static __inline__ uint64_t __gpu_lane_mask(void) {
+  return __builtin_amdgcn_read_exec();
+}
+
+// Copies the value from the first active thread in the wavefront to the rest.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t
+__gpu_read_first_lane_u32(uint64_t __lane_mask, uint32_t __x) {
+  return __builtin_amdgcn_readfirstlane(__x);
+}
+
+// Copies the value from the first active thread in the wavefront to the rest.
+_DEFAULT_FN_ATTRS __inline__ uint64_t
+__gpu_read_first_lane_u64(uint64_t __lane_mask, uint64_t __x) {
+  uint32_t __hi = (uint32_t)(__x >> 32ull);
+  uint32_t __lo = (uint32_t)(__x & 0xFFFFFFFF);
+  return ((uint64_t)__builtin_amdgcn_readfirstlane(__hi) << 32ull) |
+         ((uint64_t)__builtin_amdgcn_readfirstlane(__lo));
+}
+
+// Returns a bitmask of threads in the current lane for which \p x is true.
+_DEFAULT_FN_ATTRS static __inline__ uint64_t __gpu_ballot(uint64_t __lane_mask,
+                                                          bool __x) {
+  // The lane_mask & gives the nvptx semantics when lane_mask is a subset of
+  // the active threads
+  return __lane_mask & __builtin_amdgcn_ballot_w64(__x);
+}
+
+// Waits for all the threads in the block to converge and issues a fence.
+_DEFAULT_FN_ATTRS static __inline__ void __gpu_sync_threads(void) {
+  __builtin_amdgcn_s_barrier();
+  __builtin_amdgcn_fence(__ATOMIC_SEQ_CST, "workgroup");
+}
+
+// Wait for all threads in the wavefront to converge, this is a noop on AMDGPU.
+_DEFAULT_FN_ATTRS static __inline__ void __gpu_sync_lane(uint64_t __lane_mask) {
+  __builtin_amdgcn_wave_barrier();
+}
+
+// Shuffles the the lanes inside the wavefront according to the given index.
+_DEFAULT_FN_ATTRS static __inline__ uint32_t
+__gpu_shuffle_idx_u32(uint64_t __lane_mask, uint32_t __idx, uint32_t __x,
+                      uint32_t __width) {
+  uint32_t __lane = __idx + (__gpu_lane_id() & ~(__width - 1));
+  return __builtin_amdgcn_ds_bpermute(__lane << 2, __x);
+}
+
+// Shuffles the the lanes inside the wavefront according to the given index.
+_DEFAULT_FN_ATTRS static __inline__ uint64_t
+__gpu_shuffle_idx_u64(uint64_t __lane_mask, uint32_t __idx, uint64_t __x,
+                      uint32_t __width) {
+  uint32_t __hi = (uint32_t)(__x >> 32ull);
+  uint32_t __lo = (uint32_t)(__x & 0xFFFFFFFF);
+  return ((uint64_t)__gpu_shuffle_idx_u32(__lane_mask, __idx, __hi, __width)
+          << 32ull) |
+         ((uint64_t)__gpu_shuffle_idx_u32(__lane_mask, __idx, __lo, __width));
+}
+
+// Returns true if the flat pointer points to AMDGPU 'shared' memory.
+_DEFAULT_FN_ATTRS static __inline__ bool __gpu_is_ptr_local(void *ptr) {
+  return __builtin_amdgcn_is_shared((void [[clang::address_space(0)]] *)((
+      void [[clang::opencl_generic]] *)ptr));
+}
+
+// Returns true if the flat pointer points to AMDGPU 'private' memory.
+_DEFAULT_FN_ATTRS static __inline__ bool __gpu_is_ptr_private(void *ptr) {
+  return __builtin_amdgcn_is_private((void [[clang::address_space(0)]] *)((
+      void [[clang::opencl_generic]] *)ptr));
+}
+
+// Terminates execution of the associated wavefront.
+_DEFAULT_FN_ATTRS [[noreturn]] static __inline__ void __gpu_exit(void) {
+  __builtin_amdgcn_endpgm();
+}
+
+// Suspend the thread briefly to assist the scheduler during busy loops.
+_DEFAULT_FN_ATTRS static __inline__ void __gpu_thread_suspend(void) {
+  __builtin_amdgcn_s_sleep(2);
+}
+
+_Pragma("omp end declare variant");
+_Pragma("omp end declare target");
+
+#if !defined(__cplusplus)
+_Pragma("pop_macro(\"bool\")");
+#endif
+
+#endif // __AMDGPUINTRIN_H