[PATCH] Document HLE metadata

Nadav Rotem nrotem at apple.com
Mon Mar 25 21:46:32 PDT 2013


On Mar 25, 2013, at 4:14 PM, Michael Liao <michael.liao at intel.com> wrote:

> Hi Nadav
> 
> Almost miss this. The motivation to hint atomic instruction is that it
> make programmer's lock primitives (based on atomic instruction) works on
> both targets with or without HLE support.

I understand, but this can also be done using if-defs in the code or by placing the atomic operation in a library.  

> If different intrinsics need providing, we need at least atomicrmw
> {xchg/add/sub/and/nand/or/xor} and cmpxchg for various data types.

Okay. 

> To propagate HLE hint from LLVM IR into target code generator, I adds
> HLEHint (2 bits in SubclassData) in atomic node and necessary code to
> propagate them. Except that, there's nothing fancy.

I understand, but this is added complexity that all of the targets need to maintain.  SelectionDAG is already complex and we don't want to add additional complexity. 


I still think that target-specific intrinsics is the best way to go. 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20130325/333693a2/attachment.html>


More information about the llvm-commits mailing list