This is the mail archive of the
gcc-bugs@gcc.gnu.org
mailing list for the GCC project.
[Bug optimization/9531] Problem with -fprefetch-loop-arrays -funroll-loops
- From: "dhazeghi at yahoo dot com" <gcc-bugzilla at gcc dot gnu dot org>
- To: gcc-bugs at gcc dot gnu dot org
- Date: 5 Jun 2003 01:05:44 -0000
- Subject: [Bug optimization/9531] Problem with -fprefetch-loop-arrays -funroll-loops
- References: <20030201002600.9531.green@localhost.localdomain>
- Reply-to: gcc-bugzilla at gcc dot gnu dot org
PLEASE REPLY TO gcc-bugzilla@gcc.gnu.org ONLY, *NOT* gcc-bugs@gcc.gnu.org.
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=9531
dhazeghi@yahoo.com changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|WAITING |NEW
Ever Confirmed| |1
Last reconfirmed|0000-00-00 00:00:00 |2003-06-05 01:05:44
date| |
------- Additional Comments From dhazeghi@yahoo.com 2003-06-05 01:05 -------
Confirmed with gcc 3.3 branch and mainline (20030604). With branch, there are 12 prefetch
instructions in a row. With mainline, there are 10 prefetch instructions, but they are spread out.
This is with a mips-elf cross-compiler using -O3 -funroll-loops -fprefetch-loop-arrays -
march=mips4.
Dara
P.S. Oh the reason this bug report had i686-linux as the target initially is that's what Target was
set to in the original GNATS report...
------- You are receiving this mail because: -------
You are on the CC list for the bug, or are watching someone who is.