[libcxx] Improve code generation for vector::clear().

Summary:
By manipulating a local variable in the loop, when the loop can
be optimized away (due to no non-trivial destructors), this lets
it be fully optimized away and we modify the __end_ separately.

This results in a substantial improvement in the generated code.

Prior to this change, this would be generated (on x86_64):

    movq    (%rdi), %rdx
    movq    8(%rdi), %rcx
    cmpq    %rdx, %rcx
    je    LBB2_2
    leaq    -12(%rcx), %rax
    subq    %rdx, %rax
    movabsq    $-6148914691236517205, %rdx ## imm = 0xAAAAAAAAAAAAAAAB
    mulq    %rdx
    shrq    $3, %rdx
    notq    %rdx
    leaq    (%rdx,%rdx,2), %rax
    leaq    (%rcx,%rax,4), %rax
    movq    %rax, 8(%rdi)

And after:

    movq    (%rdi), %rax
    movq    %rax, 8(%rdi)

This brings this in line with what other implementations do.

Subscribers: cfe-commits

Differential Revision: https://reviews.llvm.org/D25241

llvm-svn: 298601

1 files changed, 4 insertions, 2 deletions

diff --git a/libcxx/include/vector b/libcxx/include/vector
index ded057b10c8..8f404dc4211 100644
--- a/libcxx/include/vector
+++ b/libcxx/include/vector
@@ -413,8 +413,10 @@ inline _LIBCPP_INLINE_VISIBILITY
 void
 __vector_base<_Tp, _Allocator>::__destruct_at_end(pointer __new_last) _NOEXCEPT
 {
-    while (__new_last != __end_)
-        __alloc_traits::destroy(__alloc(), _VSTD::__to_raw_pointer(--__end_));
+    pointer __soon_to_be_end = __end_;
+    while (__new_last != __soon_to_be_end)
+        __alloc_traits::destroy(__alloc(), _VSTD::__to_raw_pointer(--__soon_to_be_end));
+    __end_ = __new_last;
 }
 
 template <class _Tp, class _Allocator>