Re: [PATCH][AArch64] Fix Cortex-A53 shift costs

2015-05-01 Thread Kyrill Tkachov
On 01/05/15 14:07, Wilco Dijkstra wrote: Marcus Shawcroft wrote: On 5 March 2015 at 14:49, Wilco Dijkstra wrote: This patch fixes the shift costs for Cortex-A53 so they are more accurate - immediate shifts use SBFM/UBFM which takes 2 cycles, register controlled shifts take 1 cycle. Bootstr

RE: [PATCH][AArch64] Fix Cortex-A53 shift costs

2015-05-01 Thread Wilco Dijkstra
> Marcus Shawcroft wrote: > On 5 March 2015 at 14:49, Wilco Dijkstra wrote: > > This patch fixes the shift costs for Cortex-A53 so they are more accurate - > > immediate shifts > use > > SBFM/UBFM which takes 2 cycles, register controlled shifts take 1 cycle. > > Bootstrap and > regression > > O

RE: [PATCH][AArch64] Fix Cortex-A53 shift costs

2015-04-27 Thread Wilco Dijkstra
ping > -Original Message- > From: Wilco Dijkstra [mailto:wdijk...@arm.com] > Sent: 05 March 2015 14:49 > To: gcc-patches@gcc.gnu.org > Subject: [PATCH][AArch64] Fix Cortex-A53 shift costs > > This patch fixes the shift costs for Cortex-A53 so they are more accurate

[PATCH][AArch64] Fix Cortex-A53 shift costs

2015-03-05 Thread Wilco Dijkstra
This patch fixes the shift costs for Cortex-A53 so they are more accurate - immediate shifts use SBFM/UBFM which takes 2 cycles, register controlled shifts take 1 cycle. Bootstrap and regression OK. ChangeLog: 2015-03-05 Wilco Dijkstra * gcc/config/arm/aarch-cost-tables.h (cortexa53