Re: [RFC/ARM] Prefer branches over conditional execution for Cortex-A15.

2012-01-09 Thread Richard Earnshaw
On 09/01/12 12:01, Matthew Gretton-Dann wrote: > The attached patch tunes the costs of conditional execution and branches > for Cortex-A15 to be the same as that for Cortex-A5. > > This gives an average improvement of over 6% on a popular embedded > benchmark. > > Note that the tuning parameter s

[RFC/ARM] Prefer branches over conditional execution for Cortex-A15.

2012-01-09 Thread Matthew Gretton-Dann
The attached patch tunes the costs of conditional execution and branches for Cortex-A15 to be the same as that for Cortex-A5. This gives an average improvement of over 6% on a popular embedded benchmark. Note that the tuning parameter structure added for Cortex-A15 is only tuned for branch costs,