[09/11] libstdc++: Ensure unrolled loops inline the lambda

Message ID 8456007.brqZDK0HF6@excalibur
State New
Headers show
Series
  • stdx::simd optimizations, corrections, and cleanups
Related show

Commit Message

Matthias Kretz June 8, 2021, 12:11 p.m.
From: Matthias Kretz <kretz@kde.org>

Signed-off-by: Matthias Kretz <m.kretz@gsi.de>

libstdc++-v3/ChangeLog:

	* include/experimental/bits/simd.h (__execute_on_index_sequence,
	__execute_on_index_sequence_with_return,
	__call_with_n_evaluations, __call_with_subscripts): Add flatten
	attribute.
---
 libstdc++-v3/include/experimental/bits/simd.h | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)


--
──────────────────────────────────────────────────────────────────────────
 Dr. Matthias Kretz                           https://mattkretz.github.io
 GSI Helmholtz Centre for Heavy Ion Research               https://gsi.de
 std::experimental::simd              https://github.com/VcDevel/std-simd
──────────────────────────────────────────────────────────────────────────

Patch

diff --git a/libstdc++-v3/include/experimental/bits/simd.h b/libstdc++-v3/include/experimental/bits/simd.h
index 5d243f22434..21100c1087d 100644
--- a/libstdc++-v3/include/experimental/bits/simd.h
+++ b/libstdc++-v3/include/experimental/bits/simd.h
@@ -234,7 +234,8 @@  namespace __detail
 // unrolled/pack execution helpers
 // __execute_n_times{{{
 template <typename _Fp, size_t... _I>
-  _GLIBCXX_SIMD_INTRINSIC constexpr void
+  [[__gnu__::__flatten__]] _GLIBCXX_SIMD_INTRINSIC constexpr
+  void
   __execute_on_index_sequence(_Fp&& __f, index_sequence<_I...>)
   { ((void)__f(_SizeConstant<_I>()), ...); }
 
@@ -254,7 +255,8 @@  template <size_t _Np, typename _Fp>
 // }}}
 // __generate_from_n_evaluations{{{
 template <typename _R, typename _Fp, size_t... _I>
-  _GLIBCXX_SIMD_INTRINSIC constexpr _R
+  [[__gnu__::__flatten__]] _GLIBCXX_SIMD_INTRINSIC constexpr
+  _R
   __execute_on_index_sequence_with_return(_Fp&& __f, index_sequence<_I...>)
   { return _R{__f(_SizeConstant<_I>())...}; }
 
@@ -269,7 +271,8 @@  template <size_t _Np, typename _R, typename _Fp>
 // }}}
 // __call_with_n_evaluations{{{
 template <size_t... _I, typename _F0, typename _FArgs>
-  _GLIBCXX_SIMD_INTRINSIC constexpr auto
+  [[__gnu__::__flatten__]] _GLIBCXX_SIMD_INTRINSIC constexpr
+  auto
   __call_with_n_evaluations(index_sequence<_I...>, _F0&& __f0, _FArgs&& __fargs)
   { return __f0(__fargs(_SizeConstant<_I>())...); }
 
@@ -285,7 +288,8 @@  template <size_t _Np, typename _F0, typename _FArgs>
 // }}}
 // __call_with_subscripts{{{
 template <size_t _First = 0, size_t... _It, typename _Tp, typename _Fp>
-  _GLIBCXX_SIMD_INTRINSIC constexpr auto
+  [[__gnu__::__flatten__]] _GLIBCXX_SIMD_INTRINSIC constexpr
+  auto
   __call_with_subscripts(_Tp&& __x, index_sequence<_It...>, _Fp&& __fun)
   { return __fun(__x[_First + _It]...); }