[llvm-bugs] [Bug 29083] [X86][SSE] Improve costs for floating point operations

[via llvm-bugs]

https://bugs.llvm.org/show_bug.cgi?id=29083

Simon Pilgrim <llvm-dev at redking.me.uk> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
         Resolution|---                         |FIXED
             Status|NEW                         |RESOLVED

--- Comment #2 from Simon Pilgrim <llvm-dev at redking.me.uk> ---
Resolving this, the costs are now much more realistic.

We now have a staggered set of costs that represent the worst throughput for
various hardware generations that supports up to a particular SSE level.

e.g. v4f32 sqrt:
7cy on AVX2 (Haswell)
14cy on AVX1 (SandyBridge)
18cy on SSE42 (Nehalem)
56cy on SSE1 (Pentium3)

-- 
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20171226/bb73789e/attachment.html>