merge main into amd-staging (llvm#1501)

Author: ronlieb

.github/workflows/libcxx-build-and-test.yaml

@@ -197,10 +197,20 @@ jobs:
           os: macos-15
         - config: apple-configuration
           os: macos-15
+        # TODO: These jobs are intended to test back-deployment (building against ToT libc++ but running against an
+        #       older system-provided libc++.dylib). Doing this properly would require building the test suite on a
+        #       recent macOS using a recent Clang (hence recent Xcode), and then running the actual test suite on an
+        #       older mac. We could do that by e.g. sharing artifacts between the two jobs.
+        #
+        #       However, our Lit configuration currently doesn't provide a good way to do that in a batch, so our only
+        #       alternative is to actually build on the same host that we're going to run on. Sadly, that doesn't work
+        #       since older macOSes don't support newer Xcodes. For now, we run the "backdeployment" jobs on recent
+        #       macOS versions as a way to avoid rotting that configuration, but it doesn't provide a lot of additional
+        #       coverage.
         - config: apple-system
-          os: macos-13
+          os: macos-15
         - config: apple-system-hardened
-          os: macos-13
+          os: macos-15
     runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2

clang/lib/Headers/amxcomplexintrin.h

@@ -135,9 +135,8 @@ _tile_cmmrlfp16ps_internal(unsigned short m, unsigned short n, unsigned short k,
 ///    The 1st source tile. Max size is 1024 Bytes.
 /// \param src1
 ///    The 2nd source tile. Max size is 1024 Bytes.
-__DEFAULT_FN_ATTRS_COMPLEX
-static void __tile_cmmimfp16ps(__tile1024i *dst, __tile1024i src0,
-                               __tile1024i src1) {
+static __inline__ void __DEFAULT_FN_ATTRS_COMPLEX
+__tile_cmmimfp16ps(__tile1024i *dst, __tile1024i src0, __tile1024i src1) {
   dst->tile = _tile_cmmimfp16ps_internal(src0.row, src1.col, src0.col,
                                          dst->tile, src0.tile, src1.tile);
 }
@@ -158,9 +157,8 @@ static void __tile_cmmimfp16ps(__tile1024i *dst, __tile1024i src0,
 ///    The 1st source tile. Max size is 1024 Bytes.
 /// \param src1
 ///    The 2nd source tile. Max size is 1024 Bytes.
-__DEFAULT_FN_ATTRS_COMPLEX
-static void __tile_cmmrlfp16ps(__tile1024i *dst, __tile1024i src0,
-                               __tile1024i src1) {
+static __inline__ void __DEFAULT_FN_ATTRS_COMPLEX
+__tile_cmmrlfp16ps(__tile1024i *dst, __tile1024i src0, __tile1024i src1) {
   dst->tile = _tile_cmmrlfp16ps_internal(src0.row, src1.col, src0.col,
                                          dst->tile, src0.tile, src1.tile);
 }

libcxx/docs/FeatureTestMacroTable.rst

@@ -374,7 +374,7 @@ Status
     ---------------------------------------------------------- -----------------
     ``__cpp_lib_ranges_find_last``                             ``202207L``
     ---------------------------------------------------------- -----------------
-    ``__cpp_lib_ranges_iota``                                  *unimplemented*
+    ``__cpp_lib_ranges_iota``                                  ``202202L``
     ---------------------------------------------------------- -----------------
     ``__cpp_lib_ranges_join_with``                             *unimplemented*
     ---------------------------------------------------------- -----------------

libcxx/docs/Status/Cxx23.rst

@@ -40,4 +40,4 @@ Library Working Group Issues Status
 .. csv-table::
    :file: Cxx23Issues.csv
    :header-rows: 1
-   :widths: auto
+   :widths: auto

libcxx/docs/Status/Cxx23Papers.csv

@@ -46,7 +46,7 @@
 "`P2255R2 <https://wg21.link/P2255R2>`__","A type trait to detect reference binding to temporary","2022-02 (Virtual)","|Partial|","","Implemented the type traits only."
 "`P2273R3 <https://wg21.link/P2273R3>`__","Making ``std::unique_ptr`` constexpr","2022-02 (Virtual)","|Complete|","16",""
 "`P2387R3 <https://wg21.link/P2387R3>`__","Pipe support for user-defined range adaptors","2022-02 (Virtual)","|Complete|","19",""
-"`P2440R1 <https://wg21.link/P2440R1>`__","``ranges::iota``, ``ranges::shift_left`` and ``ranges::shift_right``","2022-02 (Virtual)","","",""
+"`P2440R1 <https://wg21.link/P2440R1>`__","``ranges::iota``, ``ranges::shift_left`` and ``ranges::shift_right``","2022-02 (Virtual)","|Partial|","","Only ``ranges::iota`` is implemented."
 "`P2441R2 <https://wg21.link/P2441R2>`__","``views::join_with``","2022-02 (Virtual)","|In Progress|","",""
 "`P2442R1 <https://wg21.link/P2442R1>`__","Windowing range adaptors: ``views::chunk`` and ``views::slide``","2022-02 (Virtual)","","",""
 "`P2443R1 <https://wg21.link/P2443R1>`__","``views::chunk_by``","2022-02 (Virtual)","|Complete|","18",""

libcxx/include/CMakeLists.txt

@@ -64,6 +64,7 @@ set(files
   __algorithm/next_permutation.h
   __algorithm/none_of.h
   __algorithm/nth_element.h
+  __algorithm/out_value_result.h
   __algorithm/partial_sort.h
   __algorithm/partial_sort_copy.h
   __algorithm/partition.h
@@ -615,6 +616,7 @@ set(files
   __numeric/midpoint.h
   __numeric/partial_sum.h
   __numeric/pstl.h
+  __numeric/ranges_iota.h
   __numeric/reduce.h
   __numeric/saturation_arithmetic.h
   __numeric/transform_exclusive_scan.h

libcxx/include/__algorithm/out_value_result.h

@@ -0,0 +1,56 @@
+// -*- 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 _LIBCPP___ALGORITHM_OUT_VALUE_RESULT_H
+#define _LIBCPP___ALGORITHM_OUT_VALUE_RESULT_H
+
+#include <__concepts/convertible_to.h>
+#include <__config>
+#include <__utility/move.h>
+
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+#  pragma GCC system_header
+#endif
+
+_LIBCPP_PUSH_MACROS
+#include <__undef_macros>
+
+_LIBCPP_BEGIN_NAMESPACE_STD
+
+#if _LIBCPP_STD_VER >= 23
+
+namespace ranges {
+
+template <class _OutIter1, class _ValType1>
+struct out_value_result {
+  _LIBCPP_NO_UNIQUE_ADDRESS _OutIter1 out;
+  _LIBCPP_NO_UNIQUE_ADDRESS _ValType1 value;
+
+  template <class _OutIter2, class _ValType2>
+    requires convertible_to<const _OutIter1&, _OutIter2> && convertible_to<const _ValType1&, _ValType2>
+  _LIBCPP_HIDE_FROM_ABI constexpr operator out_value_result<_OutIter2, _ValType2>() const& {
+    return {out, value};
+  }
+
+  template <class _OutIter2, class _ValType2>
+    requires convertible_to<_OutIter1, _OutIter2> && convertible_to<_ValType1, _ValType2>
+  _LIBCPP_HIDE_FROM_ABI constexpr operator out_value_result<_OutIter2, _ValType2>() && {
+    return {std::move(out), std::move(value)};
+  }
+};
+
+} // namespace ranges
+
+#endif // _LIBCPP_STD_VER >= 23
+
+_LIBCPP_END_NAMESPACE_STD
+
+_LIBCPP_POP_MACROS
+
+#endif // _LIBCPP___ALGORITHM_OUT_VALUE_RESULT_H

libcxx/include/__numeric/ranges_iota.h

@@ -0,0 +1,65 @@
+// -*- 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 _LIBCPP___NUMERIC_RANGES_IOTA_H
+#define _LIBCPP___NUMERIC_RANGES_IOTA_H
+
+#include <__algorithm/out_value_result.h>
+#include <__config>
+#include <__iterator/concepts.h>
+#include <__ranges/access.h>
+#include <__ranges/concepts.h>
+#include <__ranges/dangling.h>
+#include <__utility/as_const.h>
+#include <__utility/move.h>
+
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+#  pragma GCC system_header
+#endif
+
+_LIBCPP_PUSH_MACROS
+#include <__undef_macros>
+
+_LIBCPP_BEGIN_NAMESPACE_STD
+
+#if _LIBCPP_STD_VER >= 23
+namespace ranges {
+template <typename _Out, typename _Tp>
+using iota_result = ranges::out_value_result<_Out, _Tp>;
+
+struct __iota_fn {
+public:
+  template <input_or_output_iterator _Out, sentinel_for<_Out> _Sent, weakly_incrementable _Tp>
+    requires indirectly_writable<_Out, const _Tp&>
+  _LIBCPP_HIDE_FROM_ABI static constexpr iota_result<_Out, _Tp> operator()(_Out __first, _Sent __last, _Tp __value) {
+    while (__first != __last) {
+      *__first = std::as_const(__value);
+      ++__first;
+      ++__value;
+    }
+    return {std::move(__first), std::move(__value)};
+  }
+
+  template <weakly_incrementable _Tp, ranges::output_range<const _Tp&> _Range>
+  _LIBCPP_HIDE_FROM_ABI static constexpr iota_result<ranges::borrowed_iterator_t<_Range>, _Tp>
+  operator()(_Range&& __r, _Tp __value) {
+    return operator()(ranges::begin(__r), ranges::end(__r), std::move(__value));
+  }
+};
+
+inline constexpr auto iota = __iota_fn{};
+} // namespace ranges
+
+#endif // _LIBCPP_STD_VER >= 23
+
+_LIBCPP_END_NAMESPACE_STD
+
+_LIBCPP_POP_MACROS
+
+#endif // _LIBCPP___NUMERIC_RANGES_IOTA_H

libcxx/include/algorithm

@@ -45,6 +45,9 @@ namespace ranges {
   template <class I, class T>
     struct in_value_result;              // since C++23
 
+  template <class O, class T>
+    struct out_value_result;             // since C++23
+
   template<forward_iterator I, sentinel_for<I> S, class Proj = identity,
     indirect_strict_weak_order<projected<I, Proj>> Comp = ranges::less>                                   // since C++20
   constexpr I min_element(I first, S last, Comp comp = {}, Proj proj = {});
@@ -1936,6 +1939,7 @@ template <class BidirectionalIterator, class Compare>
 #    include <__algorithm/in_out_result.h>
 #    include <__algorithm/lexicographical_compare_three_way.h>
 #    include <__algorithm/min_max_result.h>
+#    include <__algorithm/out_value_result.h>
 #    include <__algorithm/ranges_adjacent_find.h>
 #    include <__algorithm/ranges_all_of.h>
 #    include <__algorithm/ranges_any_of.h>

libcxx/include/module.modulemap

@@ -490,6 +490,7 @@ module std [system] {
     module next_permutation                       { header "__algorithm/next_permutation.h" }
     module none_of                                { header "__algorithm/none_of.h" }
     module nth_element                            { header "__algorithm/nth_element.h" }
+    module out_value_result                       { header "__algorithm/out_value_result.h" }
     module partial_sort_copy                      { header "__algorithm/partial_sort_copy.h" }
     module partial_sort                           { header "__algorithm/partial_sort.h" }
     module partition_copy                         { header "__algorithm/partition_copy.h" }
@@ -1727,6 +1728,7 @@ module std [system] {
     module partial_sum                { header "__numeric/partial_sum.h" }
     module pstl                       { header "__numeric/pstl.h" }
     module reduce                     { header "__numeric/reduce.h" }
+    module ranges_iota                { header "__numeric/ranges_iota.h" }
     module saturation_arithmetic      { header "__numeric/saturation_arithmetic.h" }
     module transform_exclusive_scan   { header "__numeric/transform_exclusive_scan.h" }
     module transform_inclusive_scan   { header "__numeric/transform_inclusive_scan.h" }