[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: State of JIT compiler
From: |
Jordi Gutiérrez Hermoso |
Subject: |
Re: State of JIT compiler |
Date: |
Thu, 24 Feb 2011 11:39:21 -0600 |
On 24 February 2011 08:18, Richard Crozier <address@hidden> wrote:
> As another example where JIT would be useful, consider the ODE solver
> routines. Your function is evaluated at each time step chosen sequentially
> by the solver, and cannot therefore be vectorized.
Does it actually make a difference? Sure, every loop is slower without
JIT, but in an ODE solver your bottleneck would not be in the
iterations the interpreter has to interpret, but in the computations
that happen at each iteration?
And if your ODE is simple enough for the iterations to be the
bottleneck, it's probably simple enough for lsode.
At any rate, clearly people find some use for JIT. I wonder if it will
actually happen for 3.6 or 4.0
- Jordi G. H.
- Re: State of JIT compiler, Jordi Gutiérrez Hermoso, 2011/02/22
- Re: State of JIT compiler, Jordi Gutiérrez Hermoso, 2011/02/22
- Bls: State of JIT compiler, Mario Ray Mahardhika, 2011/02/23
- Re: State of JIT compiler, Jordi Gutiérrez Hermoso, 2011/02/23
- Bls: State of JIT compiler, Mario Ray Mahardhika, 2011/02/23
- Re: Bls: State of JIT compiler, Michael D Godfrey, 2011/02/23
- Re: Bls: State of JIT compiler, John W. Eaton, 2011/02/23
- Bls: State of JIT compiler, John W. Eaton, 2011/02/23