[julia-users] Re: Performance of Kernel Inlining

2016-10-29 Thread Jared Crean
The timing for the Fortran code (using -Ofast) is outer_func2 time = 0.160010 second. I checked and it is using vector instructions. I'm impressed Julia is as fast as Fortran in this case. I would have thought alias checking would Julia down. The Julia code is slow on release-0.5 as well a

[julia-users] Re: Performance of Kernel Inlining

2016-10-29 Thread Jared Crean
I noticed this morning that the loop are in the wrong order for a column major array. Reversing them, I get: testing outer_func 0.294904 seconds 0.296689 seconds testing outer_func2 0.280391 seconds 0.281223 seconds Now both versions have the phi instructions, so I guess that wasn't the

[julia-users] Re: Performance of Kernel Inlining

2016-10-29 Thread Kristoffer Carlsson
Could it be some alias checking going on? Anyway, this code is horribly slow on 0.6 (even with #19097) it seems. to_indexes(::Int64, ::Int64, ::Vararg{Int64,N}) at operators.jl:868 (repeats 3 times) kills performance. On Saturday, October 29, 2016 at 5:56:12 AM UTC+2, Jared Crean wrote: > > I'