Rather that repeatedly call SD_GET_CLASS() in a loop, call it once before
a loop starts.
Signed-off-by: Igor Mitsyanko
---
hw/omap_mmc.c|9 +
hw/pl181.c |7 ---
hw/pxa2xx_mmci.c |6 --
3 files changed, 13 insertions(+), 9 deletions(-)
diff --git a/hw/omap_m
On 27 July 2012 20:29, Igor Mitsyanko wrote:
> Rather that repeatedly call SD_GET_CLASS() in a loop, call it once before
> a loop starts.
Anthony claims that SD_GET_CLASS should be cheap enough that we don't
need to hoist it out of loops like this. Do you have profiling data
or similar that cause
On 07/31/2012 07:43 PM, Peter Maydell wrote:
On 27 July 2012 20:29, Igor Mitsyanko wrote:
Rather that repeatedly call SD_GET_CLASS() in a loop, call it once before
a loop starts.
Anthony claims that SD_GET_CLASS should be cheap enough that we don't
need to hoist it out of loops like this. Do y
On 31 July 2012 18:33, Igor Mitsyanko wrote:
> On 07/31/2012 07:43 PM, Peter Maydell wrote:
>> Anthony claims that SD_GET_CLASS should be cheap enough that we don't
>> need to hoist it out of loops like this. Do you have profiling data
>> or similar that caused you to write this patch?
> Well, I'
On 07/31/2012 09:47 PM, Peter Maydell wrote:
On 31 July 2012 18:33, Igor Mitsyanko wrote:
On 07/31/2012 07:43 PM, Peter Maydell wrote:
Anthony claims that SD_GET_CLASS should be cheap enough that we don't
need to hoist it out of loops like this. Do you have profiling data
or similar that cause
Igor Mitsyanko writes:
> On 07/31/2012 07:43 PM, Peter Maydell wrote:
>> On 27 July 2012 20:29, Igor Mitsyanko wrote:
>>> Rather that repeatedly call SD_GET_CLASS() in a loop, call it once before
>>> a loop starts.
>> Anthony claims that SD_GET_CLASS should be cheap enough that we don't
>> need
On 07/31/2012 10:15 PM, Anthony Liguori wrote:
How many loop iterations that? 300us is a huge amount of time, unless
you were looping on every byte, I have a hard time understanding that
delta.
I'm not sure I understand what you mean, I did loop on every byte,
that's how our SD model works. S