From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 2181) id F28973858D35; Sat, 18 Nov 2023 21:44:01 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org F28973858D35 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1700343841; bh=yHGI/vqKaf2d18n/EioIvVErjOdnbSdQk2WJG0HtJSI=; h=From:To:Subject:Date:From; b=m8uuNKf9H7XTNbXDioNkpu2MSjxK1+f5AyMWRGUHjyu4fjUlJIUaULQvkl8RTu2Pv ao1CBJZmrJruCPkymI/T+ATkv8fZO3LOFsoHgouvgEyiRZd7rtAlMA3RgBx+7854ij aXKyJqAstPXqUhpWCLmsD+8Gp5lu34fEk0MMnFvA= MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset="utf-8" From: Jonathan Wakely To: gcc-cvs@gcc.gnu.org, libstdc++-cvs@gcc.gnu.org Subject: [gcc r14-5587] libstdc++: Add fast path for std::format("{}", x) [PR110801] X-Act-Checkin: gcc X-Git-Author: Jonathan Wakely X-Git-Refname: refs/heads/master X-Git-Oldrev: 84c5dede83de84e0a06b018103be0b9ede5b04a1 X-Git-Newrev: 41a5ea4cab2c59f9911325281f7df1d3ae846d48 Message-Id: <20231118214401.F28973858D35@sourceware.org> Date: Sat, 18 Nov 2023 21:44:01 +0000 (GMT) List-Id: https://gcc.gnu.org/g:41a5ea4cab2c59f9911325281f7df1d3ae846d48 commit r14-5587-g41a5ea4cab2c59f9911325281f7df1d3ae846d48 Author: Jonathan Wakely Date: Tue Aug 15 22:43:41 2023 +0100 libstdc++: Add fast path for std::format("{}", x) [PR110801] This optimizes the simple case of formatting a single string, integer or bool, with no format-specifier (so no padding, alignment, alternate form etc.) libstdc++-v3/ChangeLog: PR libstdc++/110801 * include/std/format (_Sink_iter::_M_reserve): New member function. (_Sink::_Reservation): New nested class. (_Sink::_M_reserve, _Sink::_M_bump): New virtual functions. (_Seq_sink::_M_reserve, _Seq_sink::_M_bump): New virtual overrides. (_Iter_sink::_M_reserve): Likewise. (__do_vformat_to): Use new functions to optimize "{}" case. Diff: --- libstdc++-v3/include/std/format | 164 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 163 insertions(+), 1 deletion(-) diff --git a/libstdc++-v3/include/std/format b/libstdc++-v3/include/std/format index 8ec1c8a0b9a..7c52cce5dbb 100644 --- a/libstdc++-v3/include/std/format +++ b/libstdc++-v3/include/std/format @@ -2442,6 +2442,10 @@ namespace __format iter_difference_t<_Out> size; }; +_GLIBCXX_BEGIN_NAMESPACE_CONTAINER +template class vector; +_GLIBCXX_END_NAMESPACE_CONTAINER + /// @cond undocumented namespace __format { @@ -2492,6 +2496,10 @@ namespace __format [[__gnu__::__always_inline__]] constexpr _Sink_iter operator++(int) { return *this; } + + auto + _M_reserve(size_t __n) const + { return _M_sink->_M_reserve(__n); } }; // Abstract base class for type-erased character sinks. @@ -2508,6 +2516,7 @@ namespace __format // Called when the span is full, to make more space available. // Precondition: _M_next != _M_span.begin() // Postcondition: _M_next != _M_span.end() + // TODO: remove the precondition? could make overflow handle it. virtual void _M_overflow() = 0; protected: @@ -2572,6 +2581,46 @@ namespace __format } } + // A successful _Reservation can be used to directly write + // up to N characters to the sink to avoid unwanted buffering. + struct _Reservation + { + // True if the reservation was successful, false otherwise. + explicit operator bool() const noexcept { return _M_sink; } + // A pointer to write directly to the sink. + _CharT* get() const noexcept { return _M_sink->_M_next.operator->(); } + // Add n to the _M_next iterator for the sink. + void _M_bump(size_t __n) { _M_sink->_M_bump(__n); } + _Sink* _M_sink; + }; + + // Attempt to reserve space to write n characters to the sink. + // If anything is written to the reservation then there must be a call + // to _M_bump(N2) before any call to another member function of *this, + // where N2 is the number of characters written. + virtual _Reservation + _M_reserve(size_t __n) + { + auto __avail = _M_unused(); + if (__n <= __avail.size()) + return { this }; + + if (__n <= _M_span.size()) // Cannot meet the request. + { + _M_overflow(); // Make more space available. + __avail = _M_unused(); + if (__n <= __avail.size()) + return { this }; + } + return { nullptr }; + } + + // Update the next output position after writing directly to the sink. + // pre: no calls to _M_write or _M_overflow since _M_reserve. + virtual void + _M_bump(size_t __n) + { _M_next += __n; } + public: _Sink(const _Sink&) = delete; _Sink& operator=(const _Sink&) = delete; @@ -2596,6 +2645,8 @@ namespace __format { } }; + using _GLIBCXX_STD_C::vector; + // A sink that fills a sequence (e.g. std::string, std::vector, std::deque). // Writes to a buffer then appends that to the sequence when it fills up. template @@ -2619,6 +2670,45 @@ namespace __format this->_M_rewind(); } + typename _Sink<_CharT>::_Reservation + _M_reserve(size_t __n) override + { + if constexpr (__is_specialization_of<_Seq, basic_string> + || __is_specialization_of<_Seq, vector>) + { + // Flush the buffer to _M_seq first: + if (this->_M_used().size()) + _M_overflow(); + // Expand _M_seq to make __n new characters available: + const auto __sz = _M_seq.size(); + if constexpr (is_same_v || is_same_v) + _M_seq.__resize_and_overwrite(__sz + __n, + [](auto, auto __n2) { + return __n2; + }); + else + _M_seq.resize(__sz + __n); + // Set _M_used() to be a span over the original part of _M_seq: + this->_M_reset(_M_seq, __sz); + return { this }; + } + else // Try to use the base class' buffer. + return _Sink<_CharT>::_M_reserve(); + } + + void + _M_bump(size_t __n) override + { + if constexpr (__is_specialization_of<_Seq, basic_string> + || __is_specialization_of<_Seq, vector>) + { + // Truncate the sequence to the part that was actually written to: + _M_seq.resize(this->_M_used().size() + __n); + // Switch back to using buffer: + this->_M_reset(this->_M_buf); + } + } + public: // TODO: for SSO string, use SSO buffer as initial span, then switch // to _M_buf if it overflows? Or even do that for all unused capacity? @@ -2744,6 +2834,21 @@ namespace __format } } + typename _Sink<_CharT>::_Reservation + _M_reserve(size_t __n) final + { + auto __avail = this->_M_unused(); + if (__n > __avail.size()) + { + if (_M_max >= 0) + return {}; // cannot grow + + auto __s = this->_M_used(); + this->_M_reset({__s.data(), __s.size() + __n}, __s.size()); + } + return { this }; + } + private: static span<_CharT> _S_make_span(_CharT* __ptr, iter_difference_t<_OutIter> __n, @@ -2773,7 +2878,7 @@ namespace __format uint64_t __off = reinterpret_cast(__ptr) % 1024; __n = (1024 - __off) / sizeof(_CharT); if (__n > 0) [[likely]] - return {__ptr, static_cast(__n)}; + return {__ptr, static_cast(__n)}; else // Misaligned/packed buffer of wchar_t? return {__ptr, 1}; } @@ -3835,6 +3940,63 @@ namespace __format else __sink_out = __sink.out(); + if constexpr (is_same_v<_CharT, char>) + if (__fmt.size() == 2 && __fmt[0] == '{' && __fmt[1] == '}') + { + bool __done = false; + std::visit_format_arg([&](auto& __arg) { + using _Tp = remove_cvref_t; + if constexpr (is_same_v<_Tp, bool>) + { + size_t __len = 4 + !__arg; + const char* __chars[] = { "false", "true" }; + if (auto __res = __sink_out._M_reserve(__len)) + { + __builtin_memcpy(__res.get(), __chars[__arg], __len); + __res._M_bump(__len); + __done = true; + } + } + else if constexpr (is_integral_v<_Tp>) + { + make_unsigned_t<_Tp> __uval; + const bool __neg = __arg < 0; + if (__neg) + __uval = make_unsigned_t<_Tp>(~__arg) + 1u; + else + __uval = __arg; + const auto __n = __detail::__to_chars_len(__uval) + __neg; + if (auto __res = __sink_out._M_reserve(__n)) + { + auto __ptr = __res.get(); + *__ptr = '-'; + __detail::__to_chars_10_impl(__ptr + (int)__neg, __n, + __uval); + __res._M_bump(__n); + __done = true; + } + } + else if constexpr (is_convertible_v<_Tp, string_view>) + { + string_view __sv = __arg; + if (auto __res = __sink_out._M_reserve(__sv.size())) + { + __builtin_memcpy(__res.get(), __sv.data(), __sv.size()); + __res._M_bump(__sv.size()); + __done = true; + } + } + }, __args.get(0)); + + if (__done) + { + if constexpr (is_same_v<_Out, _Sink_iter<_CharT>>) + return __sink_out; + else + return std::move(__sink)._M_finish().out; + } + } + auto __ctx = __loc == nullptr ? _Context(__args, __sink_out) : _Context(__args, __sink_out, *__loc);