@cpp-linter/clang-tidy-win32-x64 16.0.3 → 17.0.6

package/README.md

@@ -1,7 +1,7 @@
 # @cpp-linter/clang-tidy-win32-x64
 
-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).
+The Windows x64 binary of clang-tidy from LLVM 17.0.6, 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-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`).
+The binary is a static build from the release [`llvm-17.0.6-2`](https://github.com/cpp-linter/clang-tools-static-binaries/releases/tag/llvm-17.0.6-2) 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: 56313344 bytes
-sha256: ab529f465e647397c98f2f5d18189d95c4b6d90b88da9133efdf63231d4a9c8c
+size: 55870464 bytes
+sha256: 0fd441c2bf8cfcd841e9f304d4a96ec73295115de82bc7aeb71bb6ec42f1dc33

package/lib/clang/{16 → 17}/include/__clang_cuda_intrinsics.h

@@ -513,6 +513,197 @@ __device__ inline cuuint32_t __nvvm_get_smem_pointer(void *__ptr) {
   return __nv_cvta_generic_to_shared_impl(__ptr);
 }
 } // extern "C"
+
+#if !defined(__CUDA_ARCH__) || __CUDA_ARCH__ >= 800
+__device__ inline unsigned __reduce_add_sync(unsigned __mask,
+                                             unsigned __value) {
+  return __nvvm_redux_sync_add(__mask, __value);
+}
+__device__ inline unsigned __reduce_min_sync(unsigned __mask,
+                                             unsigned __value) {
+  return __nvvm_redux_sync_umin(__mask, __value);
+}
+__device__ inline unsigned __reduce_max_sync(unsigned __mask,
+                                             unsigned __value) {
+  return __nvvm_redux_sync_umax(__mask, __value);
+}
+__device__ inline int __reduce_min_sync(unsigned __mask, int __value) {
+  return __nvvm_redux_sync_min(__mask, __value);
+}
+__device__ inline int __reduce_max_sync(unsigned __mask, int __value) {
+  return __nvvm_redux_sync_max(__mask, __value);
+}
+__device__ inline unsigned __reduce_or_sync(unsigned __mask, unsigned __value) {
+  return __nvvm_redux_sync_or(__mask, __value);
+}
+__device__ inline unsigned __reduce_and_sync(unsigned __mask,
+                                             unsigned __value) {
+  return __nvvm_redux_sync_and(__mask, __value);
+}
+__device__ inline unsigned __reduce_xor_sync(unsigned __mask,
+                                             unsigned __value) {
+  return __nvvm_redux_sync_xor(__mask, __value);
+}
+
+__device__ inline void __nv_memcpy_async_shared_global_4(void *__dst,
+                                                         const void *__src,
+                                                         unsigned __src_size) {
+  __nvvm_cp_async_ca_shared_global_4(
+      (void __attribute__((address_space(3))) *)__dst,
+      (const void __attribute__((address_space(1))) *)__src, __src_size);
+}
+__device__ inline void __nv_memcpy_async_shared_global_8(void *__dst,
+                                                         const void *__src,
+                                                         unsigned __src_size) {
+  __nvvm_cp_async_ca_shared_global_8(
+      (void __attribute__((address_space(3))) *)__dst,
+      (const void __attribute__((address_space(1))) *)__src, __src_size);
+}
+__device__ inline void __nv_memcpy_async_shared_global_16(void *__dst,
+                                                          const void *__src,
+                                                          unsigned __src_size) {
+  __nvvm_cp_async_ca_shared_global_16(
+      (void __attribute__((address_space(3))) *)__dst,
+      (const void __attribute__((address_space(1))) *)__src, __src_size);
+}
+
+__device__ inline void *
+__nv_associate_access_property(const void *__ptr, unsigned long long __prop) {
+  // TODO: it appears to provide compiler with some sort of a hint. We do not
+  // know what exactly it is supposed to do. However, CUDA headers suggest that
+  // just passing through __ptr should not affect correctness. They do so on
+  // pre-sm80 GPUs where this builtin is not available.
+  return (void*)__ptr;
+}
+#endif // !defined(__CUDA_ARCH__) || __CUDA_ARCH__ >= 800
+
+#if !defined(__CUDA_ARCH__) || __CUDA_ARCH__ >= 900
+__device__ inline unsigned __isCtaShared(const void *ptr) {
+  return __isShared(ptr);
+}
+
+__device__ inline unsigned __isClusterShared(const void *__ptr) {
+  return __nvvm_isspacep_shared_cluster(__ptr);
+}
+
+__device__ inline void *__cluster_map_shared_rank(const void *__ptr,
+                                                  unsigned __rank) {
+  return __nvvm_mapa((void *)__ptr, __rank);
+}
+
+__device__ inline unsigned __cluster_query_shared_rank(const void *__ptr) {
+  return __nvvm_getctarank((void *)__ptr);
+}
+
+__device__ inline uint2
+__cluster_map_shared_multicast(const void *__ptr,
+                               unsigned int __cluster_cta_mask) {
+  return make_uint2((unsigned)__cvta_generic_to_shared(__ptr),
+                    __cluster_cta_mask);
+}
+
+__device__ inline unsigned __clusterDimIsSpecified() {
+  return __nvvm_is_explicit_cluster();
+}
+
+__device__ inline dim3 __clusterDim() {
+  return dim3(__nvvm_read_ptx_sreg_cluster_nctaid_x(),
+              __nvvm_read_ptx_sreg_cluster_nctaid_y(),
+              __nvvm_read_ptx_sreg_cluster_nctaid_z());
+}
+
+__device__ inline dim3 __clusterRelativeBlockIdx() {
+  return dim3(__nvvm_read_ptx_sreg_cluster_ctaid_x(),
+              __nvvm_read_ptx_sreg_cluster_ctaid_y(),
+              __nvvm_read_ptx_sreg_cluster_ctaid_z());
+}
+
+__device__ inline dim3 __clusterGridDimInClusters() {
+  return dim3(__nvvm_read_ptx_sreg_nclusterid_x(),
+              __nvvm_read_ptx_sreg_nclusterid_y(),
+              __nvvm_read_ptx_sreg_nclusterid_z());
+}
+
+__device__ inline dim3 __clusterIdx() {
+  return dim3(__nvvm_read_ptx_sreg_clusterid_x(),
+              __nvvm_read_ptx_sreg_clusterid_y(),
+              __nvvm_read_ptx_sreg_clusterid_z());
+}
+
+__device__ inline unsigned __clusterRelativeBlockRank() {
+  return __nvvm_read_ptx_sreg_cluster_ctarank();
+}
+
+__device__ inline unsigned __clusterSizeInBlocks() {
+  return __nvvm_read_ptx_sreg_cluster_nctarank();
+}
+
+__device__ inline void __cluster_barrier_arrive() {
+  __nvvm_barrier_cluster_arrive();
+}
+
+__device__ inline void __cluster_barrier_arrive_relaxed() {
+  __nvvm_barrier_cluster_arrive_relaxed();
+}
+
+__device__ inline void __cluster_barrier_wait() {
+  __nvvm_barrier_cluster_wait();
+}
+
+__device__ inline void __threadfence_cluster() { __nvvm_fence_sc_cluster(); }
+
+__device__ inline float2 atomicAdd(float2 *__ptr, float2 __val) {
+  float2 __ret;
+  __asm__("atom.add.v2.f32         {%0, %1}, [%2], {%3, %4};"
+          : "=f"(__ret.x), "=f"(__ret.y)
+          : "l"(__ptr), "f"(__val.x), "f"(__val.y));
+  return __ret;
+}
+
+__device__ inline float2 atomicAdd_block(float2 *__ptr, float2 __val) {
+  float2 __ret;
+  __asm__("atom.cta.add.v2.f32         {%0, %1}, [%2], {%3, %4};"
+          : "=f"(__ret.x), "=f"(__ret.y)
+          : "l"(__ptr), "f"(__val.x), "f"(__val.y));
+  return __ret;
+}
+
+__device__ inline float2 atomicAdd_system(float2 *__ptr, float2 __val) {
+  float2 __ret;
+  __asm__("atom.sys.add.v2.f32         {%0, %1}, [%2], {%3, %4};"
+          : "=f"(__ret.x), "=f"(__ret.y)
+          : "l"(__ptr), "f"(__val.x), "f"(__val.y));
+  return __ret;
+}
+
+__device__ inline float4 atomicAdd(float4 *__ptr, float4 __val) {
+  float4 __ret;
+  __asm__("atom.add.v4.f32         {%0, %1, %2, %3}, [%4], {%5, %6, %7, %8};"
+          : "=f"(__ret.x), "=f"(__ret.y), "=f"(__ret.z), "=f"(__ret.w)
+          : "l"(__ptr), "f"(__val.x), "f"(__val.y), "f"(__val.z), "f"(__val.w));
+  return __ret;
+}
+
+__device__ inline float4 atomicAdd_block(float4 *__ptr, float4 __val) {
+  float4 __ret;
+  __asm__(
+      "atom.cta.add.v4.f32         {%0, %1, %2, %3}, [%4], {%5, %6, %7, %8};"
+      : "=f"(__ret.x), "=f"(__ret.y), "=f"(__ret.z), "=f"(__ret.w)
+      : "l"(__ptr), "f"(__val.x), "f"(__val.y), "f"(__val.z), "f"(__val.w));
+  return __ret;
+}
+
+__device__ inline float4 atomicAdd_system(float4 *__ptr, float4 __val) {
+  float4 __ret;
+  __asm__(
+      "atom.sys.add.v4.f32         {%0, %1, %2, %3}, [%4], {%5, %6, %7, %8};"
+      : "=f"(__ret.x), "=f"(__ret.y), "=f"(__ret.z), "=f"(__ret.w)
+      : "l"(__ptr), "f"(__val.x), "f"(__val.y), "f"(__val.z), "f"(__val.w)
+      :);
+  return __ret;
+}
+
+#endif // !defined(__CUDA_ARCH__) || __CUDA_ARCH__ >= 900
 #endif // CUDA_VERSION >= 11000
 
 #endif // defined(__CLANG_CUDA_INTRINSICS_H__)

package/lib/clang/{16 → 17}/include/__clang_cuda_math.h

@@ -36,7 +36,7 @@
 // because the OpenMP overlay requires constexpr functions here but prior to
 // c++14 void return functions could not be constexpr.
 #pragma push_macro("__DEVICE_VOID__")
-#ifdef __OPENMP_NVPTX__ && defined(__cplusplus) && __cplusplus < 201402L
+#if defined(__OPENMP_NVPTX__) && defined(__cplusplus) && __cplusplus < 201402L
 #define __DEVICE_VOID__ static __attribute__((always_inline, nothrow))
 #else
 #define __DEVICE_VOID__ __DEVICE__

package/lib/clang/{16 → 17}/include/__clang_hip_cmath.h

@@ -171,7 +171,7 @@ __DEVICE__ __CONSTEXPR__ bool signbit(double __x) { return ::__signbit(__x); }
 // Other functions.
 __DEVICE__ __CONSTEXPR__ _Float16 fma(_Float16 __x, _Float16 __y,
                                       _Float16 __z) {
-  return __ocml_fma_f16(__x, __y, __z);
+  return __builtin_fmaf16(__x, __y, __z);
 }
 __DEVICE__ __CONSTEXPR__ _Float16 pow(_Float16 __base, int __iexp) {
   return __ocml_pown_f16(__base, __iexp);

package/lib/clang/{16 → 17}/include/__clang_hip_libdevice_declares.h

@@ -10,6 +10,10 @@
 #ifndef __CLANG_HIP_LIBDEVICE_DECLARES_H__
 #define __CLANG_HIP_LIBDEVICE_DECLARES_H__
 
+#if !defined(__HIPCC_RTC__) && __has_include("hip/hip_version.h")
+#include "hip/hip_version.h"
+#endif // __has_include("hip/hip_version.h")
+
 #ifdef __cplusplus
 extern "C" {
 #endif
@@ -137,23 +141,6 @@ __device__ __attribute__((const)) float __ocml_fma_rte_f32(float, float, float);
 __device__ __attribute__((const)) float __ocml_fma_rtn_f32(float, float, float);
 __device__ __attribute__((const)) float __ocml_fma_rtp_f32(float, float, float);
 __device__ __attribute__((const)) float __ocml_fma_rtz_f32(float, float, float);
-
-__device__ inline __attribute__((const)) float
-__llvm_amdgcn_cos_f32(float __x) {
-  return __builtin_amdgcn_cosf(__x);
-}
-__device__ inline __attribute__((const)) float
-__llvm_amdgcn_rcp_f32(float __x) {
-  return __builtin_amdgcn_rcpf(__x);
-}
-__device__ inline __attribute__((const)) float
-__llvm_amdgcn_rsq_f32(float __x) {
-  return __builtin_amdgcn_rsqf(__x);
-}
-__device__ inline __attribute__((const)) float
-__llvm_amdgcn_sin_f32(float __x) {
-  return __builtin_amdgcn_sinf(__x);
-}
 // END INTRINSICS
 // END FLOAT
 
@@ -277,15 +264,6 @@ __device__ __attribute__((const)) double __ocml_fma_rtp_f64(double, double,
 __device__ __attribute__((const)) double __ocml_fma_rtz_f64(double, double,
                                                             double);
 
-__device__ inline __attribute__((const)) double
-__llvm_amdgcn_rcp_f64(double __x) {
-  return __builtin_amdgcn_rcp(__x);
-}
-__device__ inline __attribute__((const)) double
-__llvm_amdgcn_rsq_f64(double __x) {
-  return __builtin_amdgcn_rsq(__x);
-}
-
 __device__ __attribute__((const)) _Float16 __ocml_ceil_f16(_Float16);
 __device__ _Float16 __ocml_cos_f16(_Float16);
 __device__ __attribute__((const)) _Float16 __ocml_cvtrtn_f16_f32(float);
@@ -305,7 +283,6 @@ __device__ __attribute__((const)) int __ocml_isnan_f16(_Float16);
 __device__ __attribute__((pure)) _Float16 __ocml_log_f16(_Float16);
 __device__ __attribute__((pure)) _Float16 __ocml_log10_f16(_Float16);
 __device__ __attribute__((pure)) _Float16 __ocml_log2_f16(_Float16);
-__device__ __attribute__((const)) _Float16 __llvm_amdgcn_rcp_f16(_Float16);
 __device__ __attribute__((const)) _Float16 __ocml_rint_f16(_Float16);
 __device__ __attribute__((const)) _Float16 __ocml_rsqrt_f16(_Float16);
 __device__ _Float16 __ocml_sin_f16(_Float16);
@@ -316,8 +293,15 @@ __device__ __attribute__((pure)) _Float16 __ocml_pown_f16(_Float16, int);
 typedef _Float16 __2f16 __attribute__((ext_vector_type(2)));
 typedef short __2i16 __attribute__((ext_vector_type(2)));
 
+// We need to match C99's bool and get an i1 in the IR.
+#ifdef __cplusplus
+typedef bool __ockl_bool;
+#else
+typedef _Bool __ockl_bool;
+#endif
+
 __device__ __attribute__((const)) float __ockl_fdot2(__2f16 a, __2f16 b,
-                                                     float c, bool s);
+                                                     float c, __ockl_bool s);
 __device__ __attribute__((const)) __2f16 __ocml_ceil_2f16(__2f16);
 __device__ __attribute__((const)) __2f16 __ocml_fabs_2f16(__2f16);
 __device__ __2f16 __ocml_cos_2f16(__2f16);
@@ -332,11 +316,29 @@ __device__ __attribute__((const)) __2i16 __ocml_isnan_2f16(__2f16);
 __device__ __attribute__((pure)) __2f16 __ocml_log_2f16(__2f16);
 __device__ __attribute__((pure)) __2f16 __ocml_log10_2f16(__2f16);
 __device__ __attribute__((pure)) __2f16 __ocml_log2_2f16(__2f16);
+
+#if HIP_VERSION_MAJOR * 100 + HIP_VERSION_MINOR >= 560
+#define __DEPRECATED_SINCE_HIP_560(X) __attribute__((deprecated(X)))
+#else
+#define __DEPRECATED_SINCE_HIP_560(X)
+#endif
+
+// Deprecated, should be removed when rocm releases using it are no longer
+// relevant.
+__DEPRECATED_SINCE_HIP_560("use ((_Float16)1.0) / ")
+__device__ inline _Float16 __llvm_amdgcn_rcp_f16(_Float16 x) {
+  return ((_Float16)1.0f) / x;
+}
+
+__DEPRECATED_SINCE_HIP_560("use ((__2f16)1.0) / ")
 __device__ inline __2f16
-__llvm_amdgcn_rcp_2f16(__2f16 __x) // Not currently exposed by ROCDL.
+__llvm_amdgcn_rcp_2f16(__2f16 __x)
 {
-  return (__2f16)(__llvm_amdgcn_rcp_f16(__x.x), __llvm_amdgcn_rcp_f16(__x.y));
+  return ((__2f16)1.0f) / __x;
 }
+
+#undef __DEPRECATED_SINCE_HIP_560
+
 __device__ __attribute__((const)) __2f16 __ocml_rint_2f16(__2f16);
 __device__ __attribute__((const)) __2f16 __ocml_rsqrt_2f16(__2f16);
 __device__ __2f16 __ocml_sin_2f16(__2f16);