Re: [PATCH] Fix PR84101, account for function ABI details in vectorization costs

2018-06-27 Thread Jeff Law
[ Returning to an old patch... ] On 02/14/2018 04:52 AM, Richard Biener wrote: > On Tue, 13 Feb 2018, Jeff Law wrote: > >> On 01/30/2018 02:59 AM, Richard Biener wrote: >>> >>> This patch tries to deal with the "easy" part of a function ABI, >>> the return value location, in vectorization costing.

Re: [PATCH] Fix PR84101, account for function ABI details in vectorization costs

2018-02-16 Thread Jeff Law
On 02/14/2018 04:57 AM, Jakub Jelinek wrote: > On Wed, Feb 14, 2018 at 12:52:45PM +0100, Richard Biener wrote: >> On Tue, 13 Feb 2018, Jeff Law wrote: >> >>> On 01/30/2018 02:59 AM, Richard Biener wrote: This patch tries to deal with the "easy" part of a function ABI, the return valu

Re: [PATCH] Fix PR84101, account for function ABI details in vectorization costs

2018-02-14 Thread Jakub Jelinek
On Wed, Feb 14, 2018 at 12:52:45PM +0100, Richard Biener wrote: > On Tue, 13 Feb 2018, Jeff Law wrote: > > > On 01/30/2018 02:59 AM, Richard Biener wrote: > > > > > > This patch tries to deal with the "easy" part of a function ABI, > > > the return value location, in vectorization costing. The t

Re: [PATCH] Fix PR84101, account for function ABI details in vectorization costs

2018-02-14 Thread Richard Biener
On Tue, 13 Feb 2018, Jeff Law wrote: > On 01/30/2018 02:59 AM, Richard Biener wrote: > > > > This patch tries to deal with the "easy" part of a function ABI, > > the return value location, in vectorization costing. The testcase > > shows that if we vectorize the returned value but the function >

Re: [PATCH] Fix PR84101, account for function ABI details in vectorization costs

2018-02-13 Thread Jeff Law
On 01/30/2018 02:59 AM, Richard Biener wrote: > > This patch tries to deal with the "easy" part of a function ABI, > the return value location, in vectorization costing. The testcase > shows that if we vectorize the returned value but the function > doesn't return in memory or in a vector registe

Re: [PATCH] Fix PR84101, account for function ABI details in vectorization costs

2018-01-31 Thread Richard Biener
On Tue, 30 Jan 2018, Richard Biener wrote: > On Tue, 30 Jan 2018, Richard Biener wrote: > > > > > This patch tries to deal with the "easy" part of a function ABI, > > the return value location, in vectorization costing. The testcase > > shows that if we vectorize the returned value but the func

Re: [PATCH] Fix PR84101, account for function ABI details in vectorization costs

2018-01-30 Thread Richard Biener
On Tue, 30 Jan 2018, Richard Biener wrote: > > This patch tries to deal with the "easy" part of a function ABI, > the return value location, in vectorization costing. The testcase > shows that if we vectorize the returned value but the function > doesn't return in memory or in a vector register

[PATCH] Fix PR84101, account for function ABI details in vectorization costs

2018-01-30 Thread Richard Biener
This patch tries to deal with the "easy" part of a function ABI, the return value location, in vectorization costing. The testcase shows that if we vectorize the returned value but the function doesn't return in memory or in a vector register but as in this case in an integer register pair (reg:T