@cpp-linter/clang-tidy-win32-x64 15.0.2 → 16.0.3

package/README.md

@@ -1,7 +1,7 @@
 # @cpp-linter/clang-tidy-win32-x64
 
-The Windows x64 binary of clang-tidy from LLVM 15.0.2, for [`@cpp-linter/clang-tidy`](https://www.npmjs.com/package/@cpp-linter/clang-tidy).
+The Windows x64 binary of clang-tidy from LLVM 16.0.3, 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-15.0.2-2`](https://github.com/cpp-linter/clang-tools-static-binaries/releases/tag/llvm-15.0.2-2) 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-16.0.3-2`](https://github.com/cpp-linter/clang-tools-static-binaries/releases/tag/llvm-16.0.3-2) 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: 51731456 bytes
-sha256: 18a01006e07c9ece3d8697f9233f4cda5ab17d8bb7c76f5600e2567bc1b19599
+size: 56313344 bytes
+sha256: ab529f465e647397c98f2f5d18189d95c4b6d90b88da9133efdf63231d4a9c8c

package/lib/clang/{15.0.2 → 16}/include/__clang_cuda_texture_intrinsics.h

@@ -666,6 +666,7 @@ __device__ static void __tex_fetch(__T *__ptr, cudaTextureObject_t __handle,
       __tex_fetch_v4<__op>::template __run<__FetchT>(__handle, __args...));
 }
 
+#if CUDA_VERSION < 12000
 // texture<> objects get magically converted into a texture reference.  However,
 // there's no way to convert them to cudaTextureObject_t on C++ level. So, we
 // cheat a bit and use inline assembly to do it. It costs us an extra register
@@ -713,6 +714,7 @@ __tex_fetch(__DataT *, __RetT *__ptr,
       __tex_fetch_v4<__op>::template __run<__FetchT>(
           __tex_handle_to_obj(__handle), __args...));
 }
+#endif // CUDA_VERSION
 } // namespace __cuda_tex
 } // namespace
 #pragma pop_macro("__ASM_OUT")

package/lib/clang/{15.0.2 → 16}/include/__clang_hip_libdevice_declares.h

@@ -288,12 +288,17 @@ __llvm_amdgcn_rsq_f64(double __x) {
 
 __device__ __attribute__((const)) _Float16 __ocml_ceil_f16(_Float16);
 __device__ _Float16 __ocml_cos_f16(_Float16);
+__device__ __attribute__((const)) _Float16 __ocml_cvtrtn_f16_f32(float);
+__device__ __attribute__((const)) _Float16 __ocml_cvtrtp_f16_f32(float);
+__device__ __attribute__((const)) _Float16 __ocml_cvtrtz_f16_f32(float);
 __device__ __attribute__((pure)) _Float16 __ocml_exp_f16(_Float16);
 __device__ __attribute__((pure)) _Float16 __ocml_exp10_f16(_Float16);
 __device__ __attribute__((pure)) _Float16 __ocml_exp2_f16(_Float16);
 __device__ __attribute__((const)) _Float16 __ocml_floor_f16(_Float16);
 __device__ __attribute__((const)) _Float16 __ocml_fma_f16(_Float16, _Float16,
                                                           _Float16);
+__device__ __attribute__((const)) _Float16 __ocml_fmax_f16(_Float16, _Float16);
+__device__ __attribute__((const)) _Float16 __ocml_fmin_f16(_Float16, _Float16);
 __device__ __attribute__((const)) _Float16 __ocml_fabs_f16(_Float16);
 __device__ __attribute__((const)) int __ocml_isinf_f16(_Float16);
 __device__ __attribute__((const)) int __ocml_isnan_f16(_Float16);

package/lib/clang/{15.0.2 → 16}/include/__clang_hip_math.h

@@ -70,9 +70,9 @@ __DEVICE__ void __static_assert_equal_size() {
 #endif
 
 __DEVICE__
-uint64_t __make_mantissa_base8(const char *__tagp) {
+uint64_t __make_mantissa_base8(const char *__tagp __attribute__((nonnull))) {
   uint64_t __r = 0;
-  while (__tagp) {
+  while (*__tagp != '\0') {
     char __tmp = *__tagp;
 
     if (__tmp >= '0' && __tmp <= '7')
@@ -87,9 +87,9 @@ uint64_t __make_mantissa_base8(const char *__tagp) {
 }
 
 __DEVICE__
-uint64_t __make_mantissa_base10(const char *__tagp) {
+uint64_t __make_mantissa_base10(const char *__tagp __attribute__((nonnull))) {
   uint64_t __r = 0;
-  while (__tagp) {
+  while (*__tagp != '\0') {
     char __tmp = *__tagp;
 
     if (__tmp >= '0' && __tmp <= '9')
@@ -104,9 +104,9 @@ uint64_t __make_mantissa_base10(const char *__tagp) {
 }
 
 __DEVICE__
-uint64_t __make_mantissa_base16(const char *__tagp) {
+uint64_t __make_mantissa_base16(const char *__tagp __attribute__((nonnull))) {
   uint64_t __r = 0;
-  while (__tagp) {
+  while (*__tagp != '\0') {
     char __tmp = *__tagp;
 
     if (__tmp >= '0' && __tmp <= '9')
@@ -125,10 +125,7 @@ uint64_t __make_mantissa_base16(const char *__tagp) {
 }
 
 __DEVICE__
-uint64_t __make_mantissa(const char *__tagp) {
-  if (!__tagp)
-    return 0u;
-
+uint64_t __make_mantissa(const char *__tagp __attribute__((nonnull))) {
   if (*__tagp == '0') {
     ++__tagp;
 
@@ -233,7 +230,7 @@ __DEVICE__
 float expm1f(float __x) { return __ocml_expm1_f32(__x); }
 
 __DEVICE__
-float fabsf(float __x) { return __ocml_fabs_f32(__x); }
+float fabsf(float __x) { return __builtin_fabsf(__x); }
 
 __DEVICE__
 float fdimf(float __x, float __y) { return __ocml_fdim_f32(__x, __y); }
@@ -359,7 +356,7 @@ float modff(float __x, float *__iptr) {
 }
 
 __DEVICE__
-float nanf(const char *__tagp) {
+float nanf(const char *__tagp __attribute__((nonnull))) {
   union {
     float val;
     struct ieee_float {
@@ -792,7 +789,7 @@ __DEVICE__
 double expm1(double __x) { return __ocml_expm1_f64(__x); }
 
 __DEVICE__
-double fabs(double __x) { return __ocml_fabs_f64(__x); }
+double fabs(double __x) { return __builtin_fabs(__x); }
 
 __DEVICE__
 double fdim(double __x, double __y) { return __ocml_fdim_f64(__x, __y); }

package/lib/clang/{15.0.2 → 16}/include/__clang_hip_runtime_wrapper.h

@@ -113,6 +113,7 @@ __attribute__((weak)) inline __device__ void free(void *__ptr) {
 
 #include <__clang_hip_libdevice_declares.h>
 #include <__clang_hip_math.h>
+#include <__clang_hip_stdlib.h>
 
 #if defined(__HIPCC_RTC__)
 #include <__clang_hip_cmath.h>

package/lib/clang/16/include/__clang_hip_stdlib.h

@@ -0,0 +1,43 @@
+/*===---- __clang_hip_stdlib.h - Device-side HIP math support --------------===
+ *
+ * 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 __CLANG_HIP_STDLIB_H__
+
+#if !defined(__HIP__) && !defined(__OPENMP_AMDGCN__)
+#error "This file is for HIP and OpenMP AMDGCN device compilation only."
+#endif
+
+#if !defined(__cplusplus)
+
+#include <limits.h>
+
+#ifdef __OPENMP_AMDGCN__
+#define __DEVICE__ static inline __attribute__((always_inline, nothrow))
+#else
+#define __DEVICE__ static __device__ inline __attribute__((always_inline))
+#endif
+
+__DEVICE__
+int abs(int __x) {
+  int __sgn = __x >> (sizeof(int) * CHAR_BIT - 1);
+  return (__x ^ __sgn) - __sgn;
+}
+__DEVICE__
+long labs(long __x) {
+  long __sgn = __x >> (sizeof(long) * CHAR_BIT - 1);
+  return (__x ^ __sgn) - __sgn;
+}
+__DEVICE__
+long long llabs(long long __x) {
+  long long __sgn = __x >> (sizeof(long long) * CHAR_BIT - 1);
+  return (__x ^ __sgn) - __sgn;
+}
+
+#endif // !defined(__cplusplus)
+
+#endif // #define __CLANG_HIP_STDLIB_H__

package/lib/clang/{15.0.2 → 16}/include/altivec.h

@@ -17323,32 +17323,32 @@ provided.
 #define vec_ncipherlast_be __builtin_altivec_crypto_vncipherlast
 
 #ifdef __VSX__
-static __inline__ vector unsigned long long __attribute__((__always_inline__))
-__builtin_crypto_vsbox(vector unsigned long long __a) {
+static __inline__ vector unsigned char __attribute__((__always_inline__))
+__builtin_crypto_vsbox(vector unsigned char __a) {
   return __builtin_altivec_crypto_vsbox(__a);
 }
 
-static __inline__ vector unsigned long long __attribute__((__always_inline__))
-__builtin_crypto_vcipher(vector unsigned long long __a,
-                         vector unsigned long long __b) {
+static __inline__ vector unsigned char __attribute__((__always_inline__))
+__builtin_crypto_vcipher(vector unsigned char __a,
+                         vector unsigned char __b) {
   return __builtin_altivec_crypto_vcipher(__a, __b);
 }
 
-static __inline__ vector unsigned long long __attribute__((__always_inline__))
-__builtin_crypto_vcipherlast(vector unsigned long long __a,
-                             vector unsigned long long __b) {
+static __inline__ vector unsigned char __attribute__((__always_inline__))
+__builtin_crypto_vcipherlast(vector unsigned char __a,
+                             vector unsigned char __b) {
   return __builtin_altivec_crypto_vcipherlast(__a, __b);
 }
 
-static __inline__ vector unsigned long long __attribute__((__always_inline__))
-__builtin_crypto_vncipher(vector unsigned long long __a,
-                          vector unsigned long long __b) {
+static __inline__ vector unsigned char __attribute__((__always_inline__))
+__builtin_crypto_vncipher(vector unsigned char __a,
+                          vector unsigned char __b) {
   return __builtin_altivec_crypto_vncipher(__a, __b);
 }
 
-static __inline__ vector unsigned long long __attribute__((__always_inline__))
-__builtin_crypto_vncipherlast(vector unsigned long long __a,
-                              vector unsigned long long __b) {
+static __inline__ vector unsigned char  __attribute__((__always_inline__))
+__builtin_crypto_vncipherlast(vector unsigned char __a,
+                              vector unsigned char __b) {
   return __builtin_altivec_crypto_vncipherlast(__a, __b);
 }
 #endif /* __VSX__ */

package/lib/clang/16/include/amxfp16intrin.h

@@ -0,0 +1,58 @@
+/*===------------- amxfp16intrin.h - AMX_FP16 intrinsics -*- C++ -*---------===
+ *
+ * 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 __IMMINTRIN_H
+#error "Never use <amxfp16intrin.h> directly; use <immintrin.h> instead."
+#endif /* __IMMINTRIN_H */
+
+#ifndef __AMX_FP16INTRIN_H
+#define __AMX_FP16INTRIN_H
+#ifdef __x86_64__
+
+/// Compute dot-product of FP16 (16-bit) floating-point pairs in tiles \a a
+///    and \a b, accumulating the intermediate single-precision (32-bit)
+///    floating-point elements with elements in \a dst, and store the 32-bit
+///    result back to tile \a dst.
+///
+/// \headerfile <immintrin.h>
+///
+/// \code
+/// void _tile_dpfp16ps (__tile dst, __tile a, __tile b)
+/// \endcode
+///
+/// \code{.operation}
+/// FOR m := 0 TO dst.rows - 1
+///	tmp := dst.row[m]
+///	FOR k := 0 TO (a.colsb / 4) - 1
+///		FOR n := 0 TO (dst.colsb / 4) - 1
+///			tmp.fp32[n] += FP32(a.row[m].fp16[2*k+0]) *
+///					FP32(b.row[k].fp16[2*n+0])
+///			tmp.fp32[n] += FP32(a.row[m].fp16[2*k+1]) *
+///					FP32(b.row[k].fp16[2*n+1])
+///		ENDFOR
+///	ENDFOR
+///	write_row_and_zero(dst, m, tmp, dst.colsb)
+/// ENDFOR
+/// zero_upper_rows(dst, dst.rows)
+/// zero_tileconfig_start()
+/// \endcode
+///
+/// This intrinsic corresponds to the \c TDPFP16PS instruction.
+///
+/// \param dst
+///    The destination tile. Max size is 1024 Bytes.
+/// \param a
+///    The 1st source tile. Max size is 1024 Bytes.
+/// \param b
+///    The 2nd source tile. Max size is 1024 Bytes.
+#define _tile_dpfp16ps(dst, a, b)                                \
+  __builtin_ia32_tdpfp16ps(dst, a, b)
+
+#endif /* __x86_64__ */
+#endif /* __AMX_FP16INTRIN_H */

package/lib/clang/{15.0.2 → 16}/include/amxintrin.h

@@ -22,6 +22,8 @@
   __attribute__((__always_inline__, __nodebug__, __target__("amx-int8")))
 #define __DEFAULT_FN_ATTRS_BF16                                                \
   __attribute__((__always_inline__, __nodebug__, __target__("amx-bf16")))
+#define __DEFAULT_FN_ATTRS_FP16                                                \
+  __attribute__((__always_inline__, __nodebug__, __target__("amx-fp16")))
 
 /// Load tile configuration from a 64-byte memory location specified by
 /// "mem_addr". The tile configuration includes the tile type palette, the
@@ -290,6 +292,13 @@ _tile_dpbf16ps_internal(unsigned short m, unsigned short n, unsigned short k,
   return __builtin_ia32_tdpbf16ps_internal(m, n, k, dst, src1, src2);
 }
 
+/// This is internal intrinsic. C/C++ user should avoid calling it directly.
+static __inline__ _tile1024i __DEFAULT_FN_ATTRS_FP16
+_tile_dpfp16ps_internal(unsigned short m, unsigned short n, unsigned short k,
+                        _tile1024i dst, _tile1024i src1, _tile1024i src2) {
+  return __builtin_ia32_tdpfp16ps_internal(m, n, k, dst, src1, src2);
+}
+
 /// This struct pack the shape and tile data together for user. We suggest
 /// initializing the struct as early as possible, because compiler depends
 /// on the shape information to do configure. The constant value is preferred
@@ -484,9 +493,32 @@ static __inline__ void __tile_dpbf16ps(__tile1024i *dst, __tile1024i src0,
                                       src0.tile, src1.tile);
 }
 
+/// Compute dot-product of FP16 (16-bit) floating-point pairs in tiles src0 and
+/// src1, accumulating the intermediate single-precision (32-bit) floating-point
+/// elements with elements in "dst", and store the 32-bit result back to tile
+/// "dst".
+///
+/// \headerfile <immintrin.h>
+///
+/// This intrinsic corresponds to the <c> TDPFP16PS </c> instruction.
+///
+/// \param dst
+///    The destination tile. Max size is 1024 Bytes.
+/// \param src0
+///    The 1st source tile. Max size is 1024 Bytes.
+/// \param src1
+///    The 2nd source tile. Max size is 1024 Bytes.
+__DEFAULT_FN_ATTRS_FP16
+static __inline__ void __tile_dpfp16ps(__tile1024i *dst, __tile1024i src0,
+                                       __tile1024i src1) {
+  dst->tile = _tile_dpfp16ps_internal(src0.row, src1.col, src0.col, dst->tile,
+                                      src0.tile, src1.tile);
+}
+
 #undef __DEFAULT_FN_ATTRS_TILE
 #undef __DEFAULT_FN_ATTRS_INT8
 #undef __DEFAULT_FN_ATTRS_BF16
+#undef __DEFAULT_FN_ATTRS_FP16
 
 #endif /* __x86_64__ */
 #endif /* __AMXINTRIN_H */