[libcxx-commits] [libcxx] [libc++] Optimize {std, ranges}::{fill, fill_n} for segmented iterators (PR #132665)
Peng Liu via libcxx-commits
libcxx-commits at lists.llvm.org
Mon Mar 24 10:43:14 PDT 2025
https://github.com/winner245 updated https://github.com/llvm/llvm-project/pull/132665
>From bb949d491f17fd1cc3e93555e7347c2759bf9231 Mon Sep 17 00:00:00 2001
From: Peng Liu <winner245 at hotmail.com>
Date: Sun, 23 Mar 2025 22:28:29 -0400
Subject: [PATCH] Optimize {std,ranges}::{fill,fill_n} for segmented iterators
---
libcxx/include/CMakeLists.txt | 1 +
libcxx/include/__algorithm/fill.h | 42 ++++++++++++++++---
libcxx/include/__algorithm/fill_n.h | 30 +++++++++----
libcxx/include/__fwd/fill.h | 26 ++++++++++++
.../alg.fill/fill.pass.cpp | 26 ++++++++++++
.../alg.fill/fill_n.pass.cpp | 26 ++++++++++++
.../alg.fill/ranges.fill.pass.cpp | 22 ++++++++++
.../alg.fill/ranges.fill_n.pass.cpp | 22 ++++++++++
8 files changed, 181 insertions(+), 14 deletions(-)
create mode 100644 libcxx/include/__fwd/fill.h
diff --git a/libcxx/include/CMakeLists.txt b/libcxx/include/CMakeLists.txt
index a021b9bb44d67..1ac582dcc1614 100644
--- a/libcxx/include/CMakeLists.txt
+++ b/libcxx/include/CMakeLists.txt
@@ -435,6 +435,7 @@ set(files
__fwd/byte.h
__fwd/complex.h
__fwd/deque.h
+ __fwd/fill.h
__fwd/format.h
__fwd/fstream.h
__fwd/functional.h
diff --git a/libcxx/include/__algorithm/fill.h b/libcxx/include/__algorithm/fill.h
index 1ce3eadb013d0..e519022f18084 100644
--- a/libcxx/include/__algorithm/fill.h
+++ b/libcxx/include/__algorithm/fill.h
@@ -10,8 +10,11 @@
#define _LIBCPP___ALGORITHM_FILL_H
#include <__algorithm/fill_n.h>
+#include <__algorithm/for_each_segment.h>
#include <__config>
#include <__iterator/iterator_traits.h>
+#include <__iterator/segmented_iterator.h>
+#include <__type_traits/enable_if.h>
#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
# pragma GCC system_header
@@ -21,23 +24,52 @@ _LIBCPP_BEGIN_NAMESPACE_STD
// fill isn't specialized for std::memset, because the compiler already optimizes the loop to a call to std::memset.
-template <class _ForwardIterator, class _Tp>
+template <class _ForwardIterator,
+ class _Sentinel,
+ class _Tp,
+ __enable_if_t<__has_forward_iterator_category<_ForwardIterator>::value, int> = 0>
inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 void
-__fill(_ForwardIterator __first, _ForwardIterator __last, const _Tp& __value, forward_iterator_tag) {
+__fill(_ForwardIterator __first, _Sentinel __last, const _Tp& __value) {
for (; __first != __last; ++__first)
*__first = __value;
}
-template <class _RandomAccessIterator, class _Tp>
+template <class _OutIter, class _Tp>
+struct _FillSegment {
+ using _Traits _LIBCPP_NODEBUG = __segmented_iterator_traits<_OutIter>;
+
+ const _Tp& __value_;
+
+ _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 explicit _FillSegment(const _Tp& __value) : __value_(__value) {}
+
+ _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 void
+ operator()(typename _Traits::__local_iterator __lfirst, typename _Traits::__local_iterator __llast) {
+ std::__fill(__lfirst, __llast, __value_);
+ }
+};
+
+template <class _RandomAccessIterator,
+ class _Tp,
+ __enable_if_t<__has_random_access_iterator_category<_RandomAccessIterator>::value &&
+ !__is_segmented_iterator<_RandomAccessIterator>::value,
+ int> = 0>
inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 void
-__fill(_RandomAccessIterator __first, _RandomAccessIterator __last, const _Tp& __value, random_access_iterator_tag) {
+__fill(_RandomAccessIterator __first, _RandomAccessIterator __last, const _Tp& __value) {
std::fill_n(__first, __last - __first, __value);
}
+template <class _SegmentedIterator,
+ class _Tp,
+ __enable_if_t<__is_segmented_iterator<_SegmentedIterator>::value, int> = 0>
+inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 void
+__fill(_SegmentedIterator __first, _SegmentedIterator __last, const _Tp& __value) {
+ std::__for_each_segment(__first, __last, _FillSegment<_SegmentedIterator, _Tp>(__value));
+}
+
template <class _ForwardIterator, class _Tp>
inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 void
fill(_ForwardIterator __first, _ForwardIterator __last, const _Tp& __value) {
- std::__fill(__first, __last, __value, typename iterator_traits<_ForwardIterator>::iterator_category());
+ std::__fill(__first, __last, __value);
}
_LIBCPP_END_NAMESPACE_STD
diff --git a/libcxx/include/__algorithm/fill_n.h b/libcxx/include/__algorithm/fill_n.h
index 0da78e1f38c4c..c492ec882a483 100644
--- a/libcxx/include/__algorithm/fill_n.h
+++ b/libcxx/include/__algorithm/fill_n.h
@@ -12,7 +12,12 @@
#include <__algorithm/min.h>
#include <__config>
#include <__fwd/bit_reference.h>
+#include <__fwd/fill.h>
+#include <__iterator/iterator_traits.h>
+#include <__iterator/next.h>
+#include <__iterator/segmented_iterator.h>
#include <__memory/pointer_traits.h>
+#include <__type_traits/enable_if.h>
#include <__utility/convert_to_integral.h>
#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
@@ -26,9 +31,13 @@ _LIBCPP_BEGIN_NAMESPACE_STD
// fill_n isn't specialized for std::memset, because the compiler already optimizes the loop to a call to std::memset.
-template <class _OutputIterator, class _Size, class _Tp>
-inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 _OutputIterator
-__fill_n(_OutputIterator __first, _Size __n, const _Tp& __value);
+template <class _OutIter, class _Size, class _Tp, __enable_if_t<!__is_segmented_iterator<_OutIter>::value, int> = 0>
+inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 _OutIter
+__fill_n(_OutIter __first, _Size __n, const _Tp& __value) {
+ for (; __n > 0; ++__first, (void)--__n)
+ *__first = __value;
+ return __first;
+}
template <bool _FillVal, class _Cp>
_LIBCPP_CONSTEXPR_SINCE_CXX20 _LIBCPP_HIDE_FROM_ABI void
@@ -68,12 +77,15 @@ __fill_n(__bit_iterator<_Cp, false> __first, _Size __n, const bool& __value) {
return __first + __n;
}
-template <class _OutputIterator, class _Size, class _Tp>
-inline _LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 _OutputIterator
-__fill_n(_OutputIterator __first, _Size __n, const _Tp& __value) {
- for (; __n > 0; ++__first, (void)--__n)
- *__first = __value;
- return __first;
+template < class _OutIter,
+ class _Size,
+ class _Tp,
+ __enable_if_t<__is_segmented_iterator<_OutIter>::value && __has_forward_iterator_category<_OutIter>::value,
+ int> = 0>
+_LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX14 _OutIter __fill_n(_OutIter __first, _Size __n, const _Tp& __value) {
+ _OutIter __last = std::next(__first, __n);
+ std::fill(__first, __last, __value);
+ return __last;
}
template <class _OutputIterator, class _Size, class _Tp>
diff --git a/libcxx/include/__fwd/fill.h b/libcxx/include/__fwd/fill.h
new file mode 100644
index 0000000000000..628c552757201
--- /dev/null
+++ b/libcxx/include/__fwd/fill.h
@@ -0,0 +1,26 @@
+//===----------------------------------------------------------------------===//
+//
+// 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___FWD_FILL_H
+#define _LIBCPP___FWD_FILL_H
+
+#include <__config>
+
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+# pragma GCC system_header
+#endif
+
+_LIBCPP_BEGIN_NAMESPACE_STD
+
+template <class _ForwardIterator, class _Tp>
+_LIBCPP_HIDE_FROM_ABI _LIBCPP_CONSTEXPR_SINCE_CXX20 void
+fill(_ForwardIterator __first, _ForwardIterator __last, const _Tp& __value);
+
+_LIBCPP_END_NAMESPACE_STD
+
+#endif // _LIBCPP___FWD_FILL_H
diff --git a/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/fill.pass.cpp b/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/fill.pass.cpp
index 9b403db85ebf9..0b87f9038e618 100644
--- a/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/fill.pass.cpp
+++ b/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/fill.pass.cpp
@@ -17,6 +17,8 @@
#include <array>
#include <cassert>
#include <cstddef>
+#include <deque>
+#include <ranges>
#include <vector>
#include "sized_allocator.h"
@@ -93,6 +95,27 @@ TEST_CONSTEXPR_CXX20 bool test_vector_bool(std::size_t N) {
return true;
}
+/*TEST_CONSTEXPR_CXX23*/ void
+test_segmented_iterator() { // TODO: Mark this test as TEST_CONSTEXPR_CXX23 when std::deque is constexpr
+ { // std::deque iterator
+ std::deque<int> in(20);
+ std::deque<int> expected(in.size(), 42);
+ std::fill(in.begin(), in.end(), 42);
+ assert(in == expected);
+ }
+
+#if TEST_STD_VER >= 20
+ { // join_view iterator
+ std::vector<std::vector<int>> v{{1, 2}, {1, 2, 3}, {0, 0}, {3, 4, 5}, {6}, {7, 8, 9, 6}, {0, 1, 2, 3, 0, 1, 2}};
+ auto jv = std::ranges::join_view(v);
+ std::fill(jv.begin(), jv.end(), 42);
+ for (const auto& vec : v)
+ for (auto n : vec)
+ assert(n == 42);
+ }
+#endif
+}
+
TEST_CONSTEXPR_CXX20 bool test() {
types::for_each(types::forward_iterator_list<char*>(), Test<char>());
types::for_each(types::forward_iterator_list<int*>(), Test<int>());
@@ -138,6 +161,9 @@ TEST_CONSTEXPR_CXX20 bool test() {
}
}
+ if (!TEST_IS_CONSTANT_EVALUATED) // TODO: Use TEST_STD_AT_LEAST_23_OR_RUNTIME_EVALUATED when std::deque is made constexpr
+ test_segmented_iterator();
+
return true;
}
diff --git a/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/fill_n.pass.cpp b/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/fill_n.pass.cpp
index 4dda8714d2cfa..3d397bc6c9f06 100644
--- a/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/fill_n.pass.cpp
+++ b/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/fill_n.pass.cpp
@@ -17,6 +17,8 @@
#include <array>
#include <cassert>
#include <cstddef>
+#include <deque>
+#include <ranges>
#include <vector>
#include "sized_allocator.h"
@@ -176,6 +178,27 @@ TEST_CONSTEXPR_CXX20 void test_struct_array() {
}
}
+/*TEST_CONSTEXPR_CXX23*/ void
+test_segmented_iterator() { // TODO: Mark this test as TEST_CONSTEXPR_CXX23 when std::deque is constexpr
+ { // std::deque iterator
+ std::deque<int> in(20);
+ std::deque<int> expected(in.size(), 42);
+ std::fill_n(in.begin(), in.size(), 42);
+ assert(in == expected);
+ }
+
+#if TEST_STD_VER >= 20
+ { // join_view iterator
+ std::vector<std::vector<int>> v{{1, 2}, {1, 2, 3}, {0, 0}, {3, 4, 5}, {6}, {7, 8, 9, 6}, {0, 1, 2, 3, 0, 1, 2}};
+ auto jv = std::ranges::join_view(v);
+ std::fill_n(jv.begin(), std::distance(jv.begin(), jv.end()), 42);
+ for (const auto& vec : v)
+ for (auto n : vec)
+ assert(n == 42);
+ }
+#endif
+}
+
TEST_CONSTEXPR_CXX20 bool test() {
types::for_each(types::forward_iterator_list<char*>(), Test<char>());
types::for_each(types::forward_iterator_list<int*>(), Test<int>());
@@ -225,6 +248,9 @@ TEST_CONSTEXPR_CXX20 bool test() {
}
}
+ if (!TEST_IS_CONSTANT_EVALUATED) // TODO: Use TEST_STD_AT_LEAST_23_OR_RUNTIME_EVALUATED when std::deque is made constexpr
+ test_segmented_iterator();
+
return true;
}
diff --git a/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/ranges.fill.pass.cpp b/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/ranges.fill.pass.cpp
index 61a659fb0028c..e610fd3c3cb06 100644
--- a/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/ranges.fill.pass.cpp
+++ b/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/ranges.fill.pass.cpp
@@ -18,6 +18,7 @@
#include <algorithm>
#include <array>
#include <cassert>
+#include <deque>
#include <ranges>
#include <string>
#include <vector>
@@ -128,6 +129,24 @@ constexpr bool test_vector_bool(std::size_t N) {
}
#endif
+/*TEST_CONSTEXPR_CXX23*/ void
+test_segmented_range() { // TODO: Mark this test as TEST_CONSTEXPR_CXX23 when std::deque is constexpr
+ { // std::deque
+ std::deque<int> in(20);
+ std::deque<int> expected(in.size(), 42);
+ std::ranges::fill(in, 42);
+ assert(in == expected);
+ }
+ { // join_view
+ std::vector<std::vector<int>> v{{1, 2}, {1, 2, 3}, {0, 0}, {3, 4, 5}, {6}, {7, 8, 9, 6}, {0, 1, 2, 3, 0, 1, 2}};
+ auto jv = std::ranges::join_view(v);
+ std::ranges::fill(jv, 42);
+ for (const auto& vec : v)
+ for (auto n : vec)
+ assert(n == 42);
+ }
+}
+
constexpr bool test() {
test_iterators<cpp17_output_iterator<int*>, sentinel_wrapper<cpp17_output_iterator<int*>>>();
test_iterators<cpp20_output_iterator<int*>, sentinel_wrapper<cpp20_output_iterator<int*>>>();
@@ -227,6 +246,9 @@ constexpr bool test() {
}
#endif
+ if (!TEST_IS_CONSTANT_EVALUATED) // TODO: Use TEST_STD_AT_LEAST_23_OR_RUNTIME_EVALUATED when std::deque is made constexpr
+ test_segmented_range();
+
return true;
}
diff --git a/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/ranges.fill_n.pass.cpp b/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/ranges.fill_n.pass.cpp
index 2d6e24a03e0b3..2c7b0fe091c04 100644
--- a/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/ranges.fill_n.pass.cpp
+++ b/libcxx/test/std/algorithms/alg.modifying.operations/alg.fill/ranges.fill_n.pass.cpp
@@ -16,6 +16,7 @@
#include <algorithm>
#include <array>
#include <cassert>
+#include <deque>
#include <ranges>
#include <string>
#include <vector>
@@ -101,6 +102,24 @@ constexpr bool test_vector_bool(std::size_t N) {
}
#endif
+/*TEST_CONSTEXPR_CXX23*/ void
+test_segmented_range() { // TODO: Mark this test as TEST_CONSTEXPR_CXX23 when std::deque is constexpr
+ { // std::deque
+ std::deque<int> in(20);
+ std::deque<int> expected(in.size(), 42);
+ std::ranges::fill_n(std::ranges::begin(in), std::ranges::size(in), 42);
+ assert(in == expected);
+ }
+ { // join_view
+ std::vector<std::vector<int>> v{{1, 2}, {1, 2, 3}, {0, 0}, {3, 4, 5}, {6}, {7, 8, 9, 6}, {0, 1, 2, 3, 0, 1, 2}};
+ auto jv = std::ranges::join_view(v);
+ std::ranges::fill_n(std::ranges::begin(jv), std::ranges::distance(jv), 42);
+ for (const auto& vec : v)
+ for (auto n : vec)
+ assert(n == 42);
+ }
+}
+
constexpr bool test() {
test_iterators<cpp17_output_iterator<int*>, sentinel_wrapper<cpp17_output_iterator<int*>>>();
test_iterators<cpp20_output_iterator<int*>, sentinel_wrapper<cpp20_output_iterator<int*>>>();
@@ -175,6 +194,9 @@ constexpr bool test() {
}
#endif
+ if (!TEST_IS_CONSTANT_EVALUATED) // TODO: Use TEST_STD_AT_LEAST_23_OR_RUNTIME_EVALUATED when std::deque is made constexpr
+ test_segmented_range();
+
return true;
}
More information about the libcxx-commits
mailing list