On Tue, 2018-02-27 at 14:21 +, Wilco Dijkstra wrote:
> Richard Biener
>
> > It happens that on some targets doing two FMAs in parallel and one
> > non-FMA operation merging them is faster than chaining three
> > FMAs...
>
> Like I mentioned in the PR, long chains should be broken, but for
>
Richard Biener
> It happens that on some targets doing two FMAs in parallel and one
> non-FMA operation merging them is faster than chaining three FMAs...
Like I mentioned in the PR, long chains should be broken, but for that we need
a new parameter to state how long a chain may be before it is
On Mon, Feb 26, 2018 at 11:25 PM, James Greenhalgh
wrote:
> On Thu, Feb 22, 2018 at 11:38:03AM +, Wilco Dijkstra wrote:
>> As discussed in the PR, the reassociation phase runs before FMAs are formed
>> and so can significantly reduce FMA opportunities. Although reassociation
>> could be switc
On Thu, Feb 22, 2018 at 11:38:03AM +, Wilco Dijkstra wrote:
> As discussed in the PR, the reassociation phase runs before FMAs are formed
> and so can significantly reduce FMA opportunities. Although reassociation
> could be switched off, it helps in many cases, so a better alternative is to
>
As discussed in the PR, the reassociation phase runs before FMAs are formed
and so can significantly reduce FMA opportunities. Although reassociation
could be switched off, it helps in many cases, so a better alternative is to
only avoid reassociation of floating point additions. This fixes the t
