Re: [PATCH][ARM] Improve max_insns_skipped logic

2017-09-05 Thread Kyrill Tkachov
On 05/09/17 11:32, Wilco Dijkstra wrote: Kyrill Tkachov wrote: I like the simplifications in the selection logic here :) However, changing the value for ARM from 6 to 4 looks a bit arbitrary to me. There's probably a reason why default values for ARM and Thumb-2 are different (maybe not a good

Re: [PATCH][ARM] Improve max_insns_skipped logic

2017-09-05 Thread Wilco Dijkstra
Kyrill Tkachov wrote: > I like the simplifications in the selection logic here :) > However, changing the value for ARM from 6 to 4 looks a bit arbitrary to me. > There's probably a reason why default values for ARM and Thumb-2 are > different > (maybe not a good one) and I'd rather not change it

Re: [PATCH][ARM] Improve max_insns_skipped logic

2017-09-04 Thread Kyrill Tkachov
On 27/06/17 16:38, Wilco Dijkstra wrote: ping From: Wilco Dijkstra Sent: 10 November 2016 17:19 To: GCC Patches Cc: nd Subject: [PATCH][ARM] Improve max_insns_skipped logic Improve the logic when setting max_insns_skipped. Limit the maximum size of IT to MAX_INSN_PER_IT_BLOCK as

Re: [PATCH][ARM] Improve max_insns_skipped logic

2017-06-27 Thread Wilco Dijkstra
  ping From: Wilco Dijkstra Sent: 10 November 2016 17:19 To: GCC Patches Cc: nd Subject: [PATCH][ARM] Improve max_insns_skipped logic     Improve the logic when setting max_insns_skipped.  Limit the maximum size of IT to MAX_INSN_PER_IT_BLOCK as otherwise multiple IT instructions are needed

Re: [PATCH][ARM] Improve max_insns_skipped logic

2017-06-13 Thread Wilco Dijkstra
ping From: Wilco Dijkstra Sent: 10 November 2016 17:19 To: GCC Patches Cc: nd Subject: [PATCH][ARM] Improve max_insns_skipped logic     Improve the logic when setting max_insns_skipped.  Limit the maximum size of IT to MAX_INSN_PER_IT_BLOCK as otherwise multiple IT instructions are needed

Re: [PATCH][ARM] Improve max_insns_skipped logic

2017-04-20 Thread Wilco Dijkstra
ping From: Wilco Dijkstra Sent: 10 November 2016 17:19 To: GCC Patches Cc: nd Subject: [PATCH][ARM] Improve max_insns_skipped logic   Improve the logic when setting max_insns_skipped.  Limit the maximum size of IT to MAX_INSN_PER_IT_BLOCK as otherwise multiple IT instructions are needed

Re: [PATCH][ARM] Improve max_insns_skipped logic

2017-02-23 Thread Wilco Dijkstra
    ping From: Wilco Dijkstra Sent: 10 November 2016 17:19 To: GCC Patches Cc: nd Subject: [PATCH][ARM] Improve max_insns_skipped logic     Improve the logic when setting max_insns_skipped.  Limit the maximum size of IT to MAX_INSN_PER_IT_BLOCK as otherwise multiple IT instructions are

Re: [PATCH][ARM] Improve max_insns_skipped logic

2017-02-02 Thread Wilco Dijkstra
  ping From: Wilco Dijkstra Sent: 10 November 2016 17:19 To: GCC Patches Cc: nd Subject: [PATCH][ARM] Improve max_insns_skipped logic     Improve the logic when setting max_insns_skipped.  Limit the maximum size of IT to MAX_INSN_PER_IT_BLOCK as otherwise multiple IT instructions are

Re: [PATCH][ARM] Improve max_insns_skipped logic

2017-01-17 Thread Wilco Dijkstra
ping From: Wilco Dijkstra Sent: 10 November 2016 17:19 To: GCC Patches Cc: nd Subject: [PATCH][ARM] Improve max_insns_skipped logic     Improve the logic when setting max_insns_skipped.  Limit the maximum size of IT to MAX_INSN_PER_IT_BLOCK as otherwise multiple IT instructions are needed

Re: [PATCH][ARM] Improve max_insns_skipped logic

2016-12-14 Thread Wilco Dijkstra
  ping From: Wilco Dijkstra Sent: 10 November 2016 17:19 To: GCC Patches Cc: nd Subject: [PATCH][ARM] Improve max_insns_skipped logic     Improve the logic when setting max_insns_skipped.  Limit the maximum size of IT to MAX_INSN_PER_IT_BLOCK as otherwise multiple IT instructions are

Re: [PATCH][ARM] Improve max_insns_skipped logic

2016-12-06 Thread Wilco Dijkstra
ping From: Wilco Dijkstra Sent: 10 November 2016 17:19 To: GCC Patches Cc: nd Subject: [PATCH][ARM] Improve max_insns_skipped logic   Improve the logic when setting max_insns_skipped.  Limit the maximum size of IT to MAX_INSN_PER_IT_BLOCK as otherwise multiple IT instructions are needed

Re: [PATCH][ARM] Improve max_insns_skipped logic

2016-11-14 Thread Wilco Dijkstra
Wilco Dijkstra wrote: > Richard Earnshaw wrote: > On 10/11/16 17:19, Wilco Dijkstra wrote: > Long conditional sequences are slow on modern cores - the value 6 for > max_insns_skipped is a few decades out of date as it was meant for ARM2! > Even with -Os the performance loss for larger values is no

Re: [PATCH][ARM] Improve max_insns_skipped logic

2016-11-11 Thread Wilco Dijkstra
Richard Earnshaw wrote: > On 10/11/16 17:19, Wilco Dijkstra wrote: > > Improve the logic when setting max_insns_skipped.  Limit the maximum size > > of IT > > to MAX_INSN_PER_IT_BLOCK as otherwise multiple IT instructions are needed, > > increasing codesize.  > > You don't provide any information

Re: [PATCH][ARM] Improve max_insns_skipped logic

2016-11-11 Thread Richard Earnshaw
On 10/11/16 17:19, Wilco Dijkstra wrote: > Improve the logic when setting max_insns_skipped. Limit the maximum size of > IT > to MAX_INSN_PER_IT_BLOCK as otherwise multiple IT instructions are needed, > increasing codesize. > You don't provide any information about what benefits this brings.

[PATCH][ARM] Improve max_insns_skipped logic

2016-11-10 Thread Wilco Dijkstra
Improve the logic when setting max_insns_skipped. Limit the maximum size of IT to MAX_INSN_PER_IT_BLOCK as otherwise multiple IT instructions are needed, increasing codesize. Given 4 works well for Thumb-2, use the same limit for ARM for consistency. ChangeLog: 2016-11-04 Wilco Dijkstra