This is the mail archive of the
gcc-bugs@gcc.gnu.org
mailing list for the GCC project.
[Bug target/77468] [7 Regression] C-ray regression on Aarch64
- From: "jgreenhalgh at gcc dot gnu.org" <gcc-bugzilla at gcc dot gnu dot org>
- To: gcc-bugs at gcc dot gnu dot org
- Date: Mon, 05 Sep 2016 08:45:14 +0000
- Subject: [Bug target/77468] [7 Regression] C-ray regression on Aarch64
- Auto-submitted: auto-generated
- References: <bug-77468-4@http.gcc.gnu.org/bugzilla/>
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=77468
James Greenhalgh <jgreenhalgh at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |jgreenhalgh at gcc dot gnu.org
--- Comment #5 from James Greenhalgh <jgreenhalgh at gcc dot gnu.org> ---
It doesn't look like vectorization to me. The nasty code-generation from the
assembly in the report looks like extra stack reloads in the key loop (an
inlined copy of ray_sphere in trace and shade and recursively inlined in to
render_scanline).
In the traces here, you can see the loops at:
0x401bb0 -> 0x401c54 on GCC5
0x401a8c -> 0x401b64 on GCC7
Are particularly lively for activity, and have a clear regression on GCC7 with
all those extra stack accesses.