https://bugs.llvm.org/show_bug.cgi?id=35614
Bug ID: 35614
Summary: std::rotate can be order of magnitude faster, if it
can allocate a buffer.
Product: libc++
Version: unspecified
Hardware: PC
OS: All
Status: NEW
Severity: enhancement
Priority: P
Component: All Bugs
Assignee: unassignedclangb...@nondot.org
Reporter: denis.yaroshevs...@gmail.com
CC: llvm-bugs@lists.llvm.org, mclow.li...@gmail.com
Hi!
For one sided rotation you do optimize for one element on the stack:
https://github.com/llvm-mirror/libcxx/blob/master/include/algorithm#L2435
Actually this is a valid optimization for arbitrary number of elements and it
can give you an order of magnitude speed up.
Here is a very naive implementation with measurements:
http://quick-bench.com/KjyAe88UUBAjSmDAbUsbkt1mLxQ
Is it ok for std::rotate to do this?
I'm happy to create a patch but some guidance on the benchmark and restrictions
would be nice.
Best,
Dennis
--
You are receiving this mail because:
You are on the CC list for the bug._______________________________________________
llvm-bugs mailing list
llvm-bugs@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
