llvm dev - Jun 2011 - [LLVMdev] contraction of FP operations

Hi,

clang deals with #pragma STDC FP_CONTRACT and updates the setting of
FPOptions::fp_contract, but how is this made use of in the back end?
Is there some way to find out, for any given pair of floating-point
operations, whether they can be contracted into one (according to
their local pragma settings), or is this not yet implemented?

Al

-- IMPORTANT NOTICE: The contents of this email and any attachments are
confidential and may also be privileged. If you are not the intended recipient,
please notify the sender immediately and do not disclose the contents to any
other person, use it for any purpose, or store or copy the information in any
medium.  Thank you.

On Jun 12, 2011, at 1:51 PM, Alasdair Grant wrote:
> Hi,
> 
> clang deals with #pragma STDC FP_CONTRACT and updates the setting of
> FPOptions::fp_contract, but how is this made use of in the back end?
> Is there some way to find out, for any given pair of floating-point
> operations, whether they can be contracted into one (according to
> their local pragma settings), or is this not yet implemented?
Not yet implemented.  Propagating this through the optimizer is a large amount
of work.  We do have various global variables in
include/llvm/Target/TargetOptions.h that get set for -ffast-math and other
global settings, but these are huge hacks.

-Chris