This is the mail system at host daystrom.m5sim.org.
I'm sorry to have to inform you that your message could not
be delivered to one or more recipients. It's attached below.
For further assistance, please send mail to postmaster.
If you do so, please include this problem report. You can
delete
changeset d33c963656cb in /z/repo/inorder-patches
details: inorder-patches?cmd=changeset;node=d33c963656cb
description:
organize patches
diffstat:
10 files changed, 3446 insertions(+), 10152 deletions(-)
fix_compile.diff| 94
fix_mdu_latency_bug | 533 ---
changeset 40721d032036 in /z/repo/inorder-patches
details: inorder-patches?cmd=changeset;node=40721d032036
description:
Make sure everything compiles just fine
diffstat:
2 files changed, 15 insertions(+), 11 deletions(-)
import_mixie |4 +---
prepare_cpus.diff | 22
changeset d3fea0b4646c in /z/repo/inorder-patches
details: inorder-patches?cmd=changeset;node=d3fea0b4646c
description:
Rename mixie to inorder
diffstat:
3 files changed, 1185 insertions(+), 1185 deletions(-)
import_mixie| 2364 +--
changeset 8c1aa74572e4 in /z/repo/m5
details: http://repo.m5sim.org/m5?cmd=changeset;node=8c1aa74572e4
description:
Quell g++ 4.3 warning about operator ambiguity
diffstat:
1 file changed, 1 insertion(+), 1 deletion(-)
src/arch/x86/isa/microops/regop.isa |2 +-
diffs (12 lines):
I notice that we have static inst flags called IsMemBarrier and
IsWriteBarrier, but no IsReadBarrier or equivalent. Should we? I need
something like that to implement the lfence instruction.
Gabe
___
m5-dev mailing list
m5-dev@m5sim.org
We don't have it because we haven't implemented an ISA that supports
it, so I see no reason not to add it. (It's pretty odd to put a fence
in for reads and not want writes to be fenced too.)
Nate
On Fri, Feb 6, 2009 at 9:06 PM, Gabe Black gbl...@eecs.umich.edu wrote:
I notice that we
Yeah, well, x86 cornered the market on odd.
Gabe
nathan binkert wrote:
We don't have it because we haven't implemented an ISA that supports
it, so I see no reason not to add it. (It's pretty odd to put a fence
in for reads and not want writes to be fenced too.)
Nate
On Fri, Feb 6,
scons: *** [build/ALPHA_SE/python/m5/defines.py.fo] Error 1
scons: *** [build/ALPHA_FS/python/m5/defines.py.fo] Error 1
scons: *** [build/MIPS_SE/python/m5/defines.py.fo] Error 1
scons: *** [build/SPARC_SE/python/m5/defines.py.fo] Error 1
scons: *** [build/X86_SE/python/m5/defines.py.fo] Error 1
