Re: [PATCH 1/4] sched/fair: Optimize sum computation with a lookup table

[Yuyang Du]

On Tue, Apr 12, 2016 at 04:19:52PM +0200, Peter Zijlstra wrote:
> On Tue, Apr 12, 2016 at 03:17:12AM +0800, Yuyang Du wrote:
> > On Mon, Apr 11, 2016 at 05:59:11PM +0100, Dietmar Eggemann wrote:
> > > On 10/04/16 23:36, Yuyang Du wrote:
> > > > __compute_runnable_contrib() uses a loop to compute sum, whereas a
> > > > table loopup can do it faster in a constant time.
> > > > 
> > > > The following python script can be used to generate the constants:
> > > > 
> > > > print " #:     yN_inv   yN_sum"
> > > > print "-----------------------"
> > > > y = (0.5)**(1/32.0)
> > > > x = 2**32
> > > > xx = 1024
> > > > for i in range(0, 32):
> > > > 	if i == 0:
> > > > 		x = x-1
> > > > 		xx = xx*y
> > > > 	else:
> > > > 		x = x*y
> > > > 		xx = int(xx*y + 1024*y)
> > > > 	print "%2d: %#x %8d" % (i, int(x), int(xx))
> > > > 
> > > > print " #:  sum_N32"
> > > > print "------------"
> > > > xxx = xx
> > > > for i in range(0, 11):
> > > > 	if i == 0:
> > > > 		xxx = xx
> > > > 	else:
> > > > 		xxx = xxx/2 + xx
> > > > 	print "%2d: %8d" % (i, xxx)
> > > >
> > > 
> > > IMHO, it would be nice to add this to the existing tool from the patch
> > > header of commit 5b51f2f80b3b
> > > ("sched: Make __update_entity_runnable_avg() fast") simply because people
> > > already use this one to tweak their pelt tables. Maybe something like
> >  
> > I'd prefer not, and recommend switching from the C program for this
> > kind of job. :)
> 
> I much prefer C because I don't speak snake or any of the other popular
> languages -- mostly because I simply don't use them enough to remember
> how they work.
> 
> Also, if we're going to edit that program, maybe change it such that at
> the end it prints the numbers in a copy/paste-able C form, just for the
> lazy amongst us :-)

Sure thing, :)