[LLVMdev] Question about FMA formation
echristo at gmail.com
Wed Dec 12 17:20:17 PST 2012
Why not just form them via a fast IR level pass and just have patterns
match in fast isel instead of trying to form code? Or are we saying the
same thing? (Your words of "fast isel spot"ting and "form better code"
caused me to think you mean to do optimizations within the fast isel pass).
On Wed, Dec 12, 2012 at 5:14 PM, Michael Ilseman <milseman at apple.com> wrote:
> Right now we're shying towards having a re-association helper in
> codegen-prepare that will re-associate expressions (if allowed). This would
> allow fast-isel to more easily spot FMA opportunities, and form better code.
> On Dec 12, 2012, at 5:11 PM, Eric Christopher <echristo at gmail.com> wrote:
> You hit send right when I did!
>> For your example, do you mean that it's grouped like:
>> (fadd (fadd (fmul a b) (fmul c d)) e)
>> How would your pass go about handling these patterns and is that
>> something that would be too complicated for fast-isel to do on the fly?
> Depends on how they're grouped, but if the formation happens prior to
> codegen then fast-isel will just handle whatever new instruction you've
> got. An example of IR would be useful though :)
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the llvm-dev