Re: [PATCH] Increase lto-min-partition

2016-09-26 Thread Wilco Dijkstra
Prathamesh Kulkarni wrote: > Hi Wilco, > I am working on LTO varpool partitioning to improve performance for > section anchors. > I posted a preliminary patch posted at: > https://gcc.gnu.org/ml/gcc/2016-07/msg00033.html > Unfortunately I haven't yet been able to benchmark it on ARM yet. > I am p

Re: [PATCH] Increase lto-min-partition

2016-09-26 Thread Wilco Dijkstra
Markus Trippelsdorf wrote: > On 2016.09.26 at 09:42 +0200, Richard Biener wrote: > > On Sat, Sep 24, 2016 at 10:52 AM, Markus Trippelsdorf > > wrote: > > > On 2016.09.23 at 15:29 +0200, Richard Biener wrote: > > > If for example you limit partitions to 4 on a 4-core machine with 8GB > > > memory

Re: [PATCH] Increase lto-min-partition

2016-09-26 Thread Markus Trippelsdorf
On 2016.09.26 at 09:42 +0200, Richard Biener wrote: > On Sat, Sep 24, 2016 at 10:52 AM, Markus Trippelsdorf > wrote: > > On 2016.09.23 at 15:29 +0200, Richard Biener wrote: > >> > > >> > So 5 looks too big to me. > >> > >> I think the issue is that the default number of partitions is too high

Re: [PATCH] Increase lto-min-partition

2016-09-26 Thread Richard Biener
On Sat, Sep 24, 2016 at 10:52 AM, Markus Trippelsdorf wrote: > On 2016.09.23 at 15:29 +0200, Richard Biener wrote: >> > >> > So 5 looks too big to me. >> >> I think the issue is that the default number of partitions is too high >> (32) which pessimizes 4-core machines if the units are too smal

Re: [PATCH] Increase lto-min-partition

2016-09-24 Thread Markus Trippelsdorf
On 2016.09.23 at 15:29 +0200, Richard Biener wrote: > > > > So 5 looks too big to me. > > I think the issue is that the default number of partitions is too high > (32) which pessimizes 4-core machines if the units are too small. The more partitions are used the less memory is required at LTRA

Re: [PATCH] Increase lto-min-partition

2016-09-23 Thread Prathamesh Kulkarni
On 23 September 2016 at 19:49, Wilco Dijkstra wrote: > Richard Biener wrote: >>On Fri, Sep 23, 2016 at 3:02 PM, Markus Trippelsdorf >>wrote: >> > And tramp3d only uses ten partitions (lto-min-partition=1). >> > With lto-min-partition=5 (current patch) this decrease to only two >> > parti

Re: [PATCH] Increase lto-min-partition

2016-09-23 Thread Wilco Dijkstra
Markus Trippelsdorf wrote: > What I wanted to point out is that you of course loose the speedup you'll > get from parallel running backends with only a single partition. Absolutely. For every possible value of min-lto-partition you can find an application that will build with more parallelism if y

Re: [PATCH] Increase lto-min-partition

2016-09-23 Thread Markus Trippelsdorf
On 2016.09.23 at 14:19 +, Wilco Dijkstra wrote: > Richard Biener wrote: > >On Fri, Sep 23, 2016 at 3:02 PM, Markus Trippelsdorf > > wrote: > > > And tramp3d only uses ten partitions (lto-min-partition=1). > > > With lto-min-partition=5 (current patch) this decrease to only two > > > pa

Re: [PATCH] Increase lto-min-partition

2016-09-23 Thread Wilco Dijkstra
Richard Biener wrote: >On Fri, Sep 23, 2016 at 3:02 PM, Markus Trippelsdorf >wrote: > > And tramp3d only uses ten partitions (lto-min-partition=1). > > With lto-min-partition=5 (current patch) this decrease to only two > > partitions. As a result we loose the possible speedup on many core

Re: [PATCH] Increase lto-min-partition

2016-09-23 Thread Richard Biener
On Fri, Sep 23, 2016 at 3:29 PM, Richard Biener wrote: > On Fri, Sep 23, 2016 at 3:02 PM, Markus Trippelsdorf > wrote: >> On 2016.09.22 at 15:42 +0200, Markus Trippelsdorf wrote: >>> On 2016.09.22 at 15:36 +0200, Richard Biener wrote: >>> > On Thu, Sep 22, 2016 at 3:13 PM, Wilco Dijkstra >>> >

Re: [PATCH] Increase lto-min-partition

2016-09-23 Thread Richard Biener
On Fri, Sep 23, 2016 at 3:02 PM, Markus Trippelsdorf wrote: > On 2016.09.22 at 15:42 +0200, Markus Trippelsdorf wrote: >> On 2016.09.22 at 15:36 +0200, Richard Biener wrote: >> > On Thu, Sep 22, 2016 at 3:13 PM, Wilco Dijkstra >> > wrote: >> > > Increase the lto-min-partition size to 5 to re

Re: [PATCH] Increase lto-min-partition

2016-09-23 Thread Markus Trippelsdorf
On 2016.09.22 at 15:42 +0200, Markus Trippelsdorf wrote: > On 2016.09.22 at 15:36 +0200, Richard Biener wrote: > > On Thu, Sep 22, 2016 at 3:13 PM, Wilco Dijkstra > > wrote: > > > Increase the lto-min-partition size to 5 to reduce the number of > > > partitions. > > > See eg. https://gcc.gnu

Re: [PATCH] Increase lto-min-partition

2016-09-22 Thread Markus Trippelsdorf
On 2016.09.22 at 15:36 +0200, Richard Biener wrote: > On Thu, Sep 22, 2016 at 3:13 PM, Wilco Dijkstra > wrote: > > Increase the lto-min-partition size to 5 to reduce the number of > > partitions. > > See eg. https://gcc.gnu.org/ml/gcc-patches/2016-04/msg00235.html for a > > concise > > expl

Re: [PATCH] Increase lto-min-partition

2016-09-22 Thread Richard Biener
On Thu, Sep 22, 2016 at 3:13 PM, Wilco Dijkstra wrote: > Increase the lto-min-partition size to 5 to reduce the number of > partitions. > See eg. https://gcc.gnu.org/ml/gcc-patches/2016-04/msg00235.html for a concise > explanation why 1 is too small for modern CPU/memory size. Additional

[PATCH] Increase lto-min-partition

2016-09-22 Thread Wilco Dijkstra
Increase the lto-min-partition size to 5 to reduce the number of partitions. See eg. https://gcc.gnu.org/ml/gcc-patches/2016-04/msg00235.html for a concise explanation why 1 is too small for modern CPU/memory size. Additionally, larger values increase optimization opportunities and reduce