This is the mail archive of the
mailing list for the GCC project.
[Bug middle-end/17886] variable rotate and long long rotate should be better optimized
- From: "tkho at ucla dot edu" <gcc-bugzilla at gcc dot gnu dot org>
- To: gcc-bugs at gcc dot gnu dot org
- Date: 11 Nov 2005 01:26:38 -0000
- Subject: [Bug middle-end/17886] variable rotate and long long rotate should be better optimized
- References: <email@example.com/bugzilla/>
- Reply-to: gcc-bugzilla at gcc dot gnu dot org
------- Comment #24 from tkho at ucla dot edu 2005-11-11 01:26 -------
For comparison, here's the code from gcc 2.95.3. It generates the same 18
instructions for both march=i386 and march=pentiumpro.
`gcc -c test3.c -save-temps -O2 -momit-leaf-frame-pointer -march=pentiumpro`:
Also, in comment #23, I erronously used g++. Luckily, the same code was
generated with gcc.
On another note, Mark, I tried your patch in comment #10. I grabbed gcc-head
from 2005-09-28 and compared a clean build with a build that had your patches
applied. There was no difference in the assembly for the test case in comment
#23, and there was no performance gain in our benchmark application.