Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!tut.cis.ohio-state.edu!pt.cs.cmu.edu!MATHOM.GANDALF.CS.CMU.EDU!lindsay
From: lindsay@MATHOM.GANDALF.CS.CMU.EDU (Donald Lindsay)
Newsgroups: comp.arch
Subject: Re: Inlining subroutines at link time
Message-ID: <9804@pt.cs.cmu.edu>
Date: 4 Jul 90 02:48:03 GMT
References: <1990Jul3.194348.21178@msuinfo.cl.msu.edu>
Organization: Carnegie-Mellon University, CS/RI
Lines: 17

In article <1990Jul3.194348.21178@msuinfo.cl.msu.edu> 
	riordanmr@clvax1.cl.msu.edu (Mark Riordan) writes:
>Modules with inlined
>subprograms are larger, yet they execute faster because they avoid 
>call and return instructions, which increase execution time.

Actually, the win (when there is a win) comes from the direct binding
of the arguments, which avoids the call site having to gather
together copies/pointers.  A result can be computed directly into its
target, avoiding a copyback.  Also, the inlined routine's locals are
merged into the caller's locals, saving the stack manipulation.

The architectural tie-in is that inlining disturbs the statistical
properties of programs, increasing the number of registers used,
enlarging the code, and affecting its locality.
-- 
Don		D.C.Lindsay