public inbox for linux-8086@vger.kernel.org
 help / color / mirror / Atom feed
* BCC software operations
@ 2003-12-04 14:40 Frank Cornelis
  0 siblings, 0 replies; only message in thread
From: Frank Cornelis @ 2003-12-04 14:40 UTC (permalink / raw)
  To: linux-8086; +Cc: Frank Cornelis

Hi,

Why is bcc sometimes using software operations when there are hardware
instructions available? Avoiding calls to software implementations of
those operations can immensely speed up bcc generated code. It also
voids the endless copy&paste of the implementations of the helper
functions. BTW: Is someone still developing bcc? Is this the right
mailing-list for bcc related questions? Are there any bcc user guides?


Please CC me,
Frank.

--- softop.c.orig	1998-02-06 21:20:14.000000000 +0100
+++ softop.c	2003-12-04 15:27:24.000000000 +0100
@@ -219,7 +219,10 @@
        {
        case DIVOP:
 #ifdef I8088
-	   call("idiv_");
+	   //call("idiv_");
+	   outnop1str("cwd");
+	   outop2str("idiv\t");
+	   outnregname(INDREG0);
 #else
 	   call("idiv");
 #endif




^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2003-12-04 14:40 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2003-12-04 14:40 BCC software operations Frank Cornelis

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox