Tested on x86_64-pc-linux-gnu.
--------- 8< -----------
Clang ICEs on _SimdImplX86::_S_divides. The function is only working
around a missed optimization and not necessary for correctness.
Therefore, don't use it for Clang.
Signed-off-by: Matthias Kretz <m.kr...@gsi.de>
libstdc++-v3/ChangeLog:
* include/experimental/bits/simd_detail.h: Don't define
_GLIBCXX_SIMD_WORKAROUND_PR90993 for Clang.
* include/experimental/bits/simd_x86.h (_S_divides): Remove
check for __clang__.
---
libstdc++-v3/include/experimental/bits/simd_detail.h | 2 ++
libstdc++-v3/include/experimental/bits/simd_x86.h | 4 ++--
2 files changed, 4 insertions(+), 2 deletions(-)
--
──────────────────────────────────────────────────────────────────────────
Dr. Matthias Kretz https://mattkretz.github.io
GSI Helmholtz Centre for Heavy Ion Research https://gsi.de
stdₓ::simd
──────────────────────────────────────────────────────────────────────────diff --git a/libstdc++-v3/include/experimental/bits/simd_detail.h b/libstdc++-v3/include/experimental/bits/simd_detail.h
index 49b94decf0a..1fb77866bb2 100644
--- a/libstdc++-v3/include/experimental/bits/simd_detail.h
+++ b/libstdc++-v3/include/experimental/bits/simd_detail.h
@@ -320,7 +320,9 @@ namespace experimental
#endif
// integer division not optimized
+#ifndef __clang__
#define _GLIBCXX_SIMD_WORKAROUND_PR90993 1
+#endif
// very bad codegen for extraction and concatenation of 128/256 "subregisters"
// with sizeof(element type) < 8: https://godbolt.org/g/mqUsgM
diff --git a/libstdc++-v3/include/experimental/bits/simd_x86.h b/libstdc++-v3/include/experimental/bits/simd_x86.h
index 7b8f1c664b3..28ba344c2b2 100644
--- a/libstdc++-v3/include/experimental/bits/simd_x86.h
+++ b/libstdc++-v3/include/experimental/bits/simd_x86.h
@@ -1469,7 +1469,7 @@ _CsrGuard()
[&__xf, &__yf](auto __i) _GLIBCXX_SIMD_ALWAYS_INLINE_LAMBDA
-> _SimdWrapper<_Float, __n_intermediate>
{
-#if !defined __clang__ && __GCC_IEC_559 == 0
+#if __GCC_IEC_559 == 0
// If -freciprocal-math is active, using the `/` operator is
// incorrect because it may be translated to an imprecise
// multiplication with reciprocal. We need to use inline
@@ -1524,7 +1524,7 @@ _CsrGuard()
*/
return _Base::_S_divides(__x, __y);
}
- #endif // _GLIBCXX_SIMD_WORKAROUND_PR90993
+#endif // _GLIBCXX_SIMD_WORKAROUND_PR90993
// }}}
// _S_modulus {{{
