Steve Reinhardt [Sun, 10 Dec 2006 07:04:53 +0000 (02:04 -0500)]
Reorder CacheTags members for better cache performance.
--HG--
extra : convert_revision :
cac6e9d447675805e3fcc4342e3bfdbef179fbf5
Steve Reinhardt [Sun, 10 Dec 2006 06:42:31 +0000 (01:42 -0500)]
Merge zizzer.eecs.umich.edu:/z/stever/bk/newmem-cache2
into zizzer.eecs.umich.edu:/z/stever/bk/newmem-cache3
--HG--
extra : convert_revision :
7c78ae3298645aed2179ed4f2aa361619406f9de
Steve Reinhardt [Sun, 10 Dec 2006 06:42:16 +0000 (01:42 -0500)]
Add '-j' option directly to regress script (passed to scons).
--HG--
extra : convert_revision :
9776806b24da70b815280e47d2d5ec8674c82669
Steve Reinhardt [Sun, 10 Dec 2006 06:05:30 +0000 (22:05 -0800)]
Merge vm1.(none):/home/stever/bk/newmem-head
into vm1.(none):/home/stever/bk/newmem-cache2
--HG--
extra : convert_revision :
e1ed5c8edb95e99200b4d26317f55f71338a96df
Steve Reinhardt [Thu, 7 Dec 2006 19:41:56 +0000 (14:41 -0500)]
Change detault regression build from opt to fast.
--HG--
extra : convert_revision :
b6db0254b73a97ab6e3685c90cc9cd30ea274d4f
Kevin Lim [Wed, 6 Dec 2006 19:23:31 +0000 (14:23 -0500)]
Fix for MIPS_SE/m5.fast compile.
--HG--
extra : convert_revision :
dbb893250974ac6db7b6c1ba67263fd35098ca43
Kevin Lim [Tue, 5 Dec 2006 16:12:18 +0000 (11:12 -0500)]
Override default SConscript options and only build the SimpleCPUs.
--HG--
extra : convert_revision :
cfcfb787d8442cb76ed766aa5bc947636f067209
Steve Reinhardt [Tue, 5 Dec 2006 15:24:13 +0000 (07:24 -0800)]
Merge zizzer.eecs.umich.edu:bk/newmem-cache2
into vm1.(none):/home/stever/bk/newmem-cache2
--HG--
extra : convert_revision :
0a7d17460f17c96fe869124f54f9c92409495003
Steve Reinhardt [Tue, 5 Dec 2006 15:23:20 +0000 (10:23 -0500)]
Merge zizzer.eecs.umich.edu:/z/stever/bk/newmem-head
into zizzer.eecs.umich.edu:/z/stever/bk/newmem-cache2
--HG--
extra : convert_revision :
a5569cef10ab22da1865e368f0bb5e7532772227
Steve Reinhardt [Tue, 5 Dec 2006 15:18:35 +0000 (10:18 -0500)]
Merge zizzer.eecs.umich.edu:/z/stever/bk/newmem-head
into zizzer.eecs.umich.edu:/z/stever/bk/newmem-cache2
--HG--
extra : convert_revision :
ca78bf2fc1ddefd56b98a90eaffab57d93026626
Steve Reinhardt [Tue, 5 Dec 2006 15:16:36 +0000 (07:16 -0800)]
Don't compress data on writebacks unless it's actually necessary.
--HG--
extra : convert_revision :
7a068e28f9ea2f6aab57be7133b47bda72d10302
Steve Reinhardt [Tue, 5 Dec 2006 05:35:48 +0000 (21:35 -0800)]
Merge vm1.(none):/home/stever/bk/newmem-head
into vm1.(none):/home/stever/bk/newmem-cache2
--HG--
extra : convert_revision :
e456687d940c833d8255a88633555778480f7825
Steve Reinhardt [Tue, 5 Dec 2006 00:10:50 +0000 (16:10 -0800)]
Merge zizzer.eecs.umich.edu:/bk/newmem
into vm1.(none):/home/stever/bk/newmem-head
--HG--
extra : convert_revision :
df2b33a629ae4298c4da33383b491e3cbefab92d
Steve Reinhardt [Tue, 5 Dec 2006 00:07:00 +0000 (19:07 -0500)]
Update SPEC CPU2000 tests with actual benchmark output.
tests/long/00.gzip/ref/alpha/linux/o3-timing/config.ini:
tests/long/00.gzip/ref/alpha/linux/o3-timing/config.out:
tests/long/00.gzip/ref/alpha/linux/o3-timing/m5stats.txt:
tests/long/00.gzip/ref/alpha/linux/o3-timing/stderr:
tests/long/00.gzip/ref/alpha/linux/o3-timing/stdout:
tests/long/00.gzip/ref/alpha/linux/simple-atomic/config.ini:
tests/long/00.gzip/ref/alpha/linux/simple-atomic/config.out:
tests/long/00.gzip/ref/alpha/linux/simple-atomic/m5stats.txt:
tests/long/00.gzip/ref/alpha/linux/simple-atomic/stderr:
tests/long/00.gzip/ref/alpha/linux/simple-atomic/stdout:
tests/long/00.gzip/ref/alpha/linux/simple-timing/config.ini:
tests/long/00.gzip/ref/alpha/linux/simple-timing/config.out:
tests/long/00.gzip/ref/alpha/linux/simple-timing/m5stats.txt:
tests/long/00.gzip/ref/alpha/linux/simple-timing/stderr:
tests/long/00.gzip/ref/alpha/linux/simple-timing/stdout:
tests/long/30.eon/ref/alpha/linux/simple-atomic/config.ini:
tests/long/30.eon/ref/alpha/linux/simple-atomic/config.out:
tests/long/30.eon/ref/alpha/linux/simple-atomic/m5stats.txt:
tests/long/30.eon/ref/alpha/linux/simple-atomic/stderr:
tests/long/30.eon/ref/alpha/linux/simple-atomic/stdout:
tests/long/30.eon/ref/alpha/linux/simple-timing/config.ini:
tests/long/30.eon/ref/alpha/linux/simple-timing/config.out:
tests/long/30.eon/ref/alpha/linux/simple-timing/m5stats.txt:
tests/long/30.eon/ref/alpha/linux/simple-timing/stderr:
tests/long/30.eon/ref/alpha/linux/simple-timing/stdout:
tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/config.ini:
tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/config.out:
tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/m5stats.txt:
tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/stderr:
tests/long/40.perlbmk/ref/alpha/linux/simple-atomic/stdout:
tests/long/40.perlbmk/ref/alpha/linux/simple-timing/config.ini:
tests/long/40.perlbmk/ref/alpha/linux/simple-timing/config.out:
tests/long/40.perlbmk/ref/alpha/linux/simple-timing/m5stats.txt:
tests/long/40.perlbmk/ref/alpha/linux/simple-timing/stderr:
tests/long/40.perlbmk/ref/alpha/linux/simple-timing/stdout:
tests/long/50.vortex/ref/alpha/linux/o3-timing/config.ini:
tests/long/50.vortex/ref/alpha/linux/o3-timing/config.out:
tests/long/50.vortex/ref/alpha/linux/o3-timing/m5stats.txt:
tests/long/50.vortex/ref/alpha/linux/o3-timing/stderr:
tests/long/50.vortex/ref/alpha/linux/o3-timing/stdout:
tests/long/50.vortex/ref/alpha/linux/simple-atomic/config.ini:
tests/long/50.vortex/ref/alpha/linux/simple-atomic/config.out:
tests/long/50.vortex/ref/alpha/linux/simple-atomic/m5stats.txt:
tests/long/50.vortex/ref/alpha/linux/simple-atomic/stderr:
tests/long/50.vortex/ref/alpha/linux/simple-atomic/stdout:
tests/long/50.vortex/ref/alpha/linux/simple-timing/config.ini:
tests/long/50.vortex/ref/alpha/linux/simple-timing/config.out:
tests/long/50.vortex/ref/alpha/linux/simple-timing/m5stats.txt:
tests/long/50.vortex/ref/alpha/linux/simple-timing/stderr:
tests/long/50.vortex/ref/alpha/linux/simple-timing/stdout:
tests/long/60.bzip2/ref/alpha/linux/o3-timing/config.ini:
tests/long/60.bzip2/ref/alpha/linux/o3-timing/config.out:
tests/long/60.bzip2/ref/alpha/linux/o3-timing/m5stats.txt:
tests/long/60.bzip2/ref/alpha/linux/o3-timing/stderr:
tests/long/60.bzip2/ref/alpha/linux/o3-timing/stdout:
tests/long/60.bzip2/ref/alpha/linux/simple-atomic/config.ini:
tests/long/60.bzip2/ref/alpha/linux/simple-atomic/config.out:
tests/long/60.bzip2/ref/alpha/linux/simple-atomic/m5stats.txt:
tests/long/60.bzip2/ref/alpha/linux/simple-atomic/stderr:
tests/long/60.bzip2/ref/alpha/linux/simple-atomic/stdout:
tests/long/60.bzip2/ref/alpha/linux/simple-timing/config.ini:
tests/long/60.bzip2/ref/alpha/linux/simple-timing/config.out:
tests/long/60.bzip2/ref/alpha/linux/simple-timing/m5stats.txt:
tests/long/60.bzip2/ref/alpha/linux/simple-timing/stderr:
tests/long/60.bzip2/ref/alpha/linux/simple-timing/stdout:
tests/long/70.twolf/ref/alpha/linux/o3-timing/config.ini:
tests/long/70.twolf/ref/alpha/linux/o3-timing/config.out:
tests/long/70.twolf/ref/alpha/linux/o3-timing/m5stats.txt:
tests/long/70.twolf/ref/alpha/linux/o3-timing/stderr:
tests/long/70.twolf/ref/alpha/linux/o3-timing/stdout:
tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.ini:
tests/long/70.twolf/ref/alpha/linux/simple-atomic/config.out:
tests/long/70.twolf/ref/alpha/linux/simple-atomic/m5stats.txt:
tests/long/70.twolf/ref/alpha/linux/simple-atomic/stderr:
tests/long/70.twolf/ref/alpha/linux/simple-atomic/stdout:
tests/long/70.twolf/ref/alpha/linux/simple-timing/config.ini:
tests/long/70.twolf/ref/alpha/linux/simple-timing/config.out:
tests/long/70.twolf/ref/alpha/linux/simple-timing/m5stats.txt:
tests/long/70.twolf/ref/alpha/linux/simple-timing/stderr:
tests/long/70.twolf/ref/alpha/linux/simple-timing/stdout:
Update with actual benchmark output.
--HG--
extra : convert_revision :
12e8de58172dd717d9cc8c5c27dd926a7257153c
Steve Reinhardt [Tue, 5 Dec 2006 00:05:09 +0000 (19:05 -0500)]
Only update stderr, stdout, m5stats.txt, and config.* on update_ref,
since we don't know which of the other files are outputs and which
are inputs.
--HG--
extra : convert_revision :
b038bd15930721ab9fceb0a18ab5c895aacb5309
Steve Reinhardt [Mon, 4 Dec 2006 23:57:17 +0000 (18:57 -0500)]
Clean up SPEC CPU2000 reference files.
Get rid of reference files for o3-atomic (non-existent configuration)
and mcf (doesn't seem to be working).
Left in empty refs for parser/simple-timing... this appears to be
dying because it's running out of memory, so maybe it will be OK
once we get the memory leak fixed.
--HG--
extra : convert_revision :
ae3bc8dfec44d09a2a084da5041ec386fe16be8b
Steve Reinhardt [Mon, 4 Dec 2006 17:10:53 +0000 (09:10 -0800)]
Turn cache MissQueue/BlockingBuffer into virtual object
instead of template parameter.
--HG--
extra : convert_revision :
fce0fbd041149b9c781eb23f480ba84fddbfd4a0
Steve Reinhardt [Mon, 4 Dec 2006 17:09:36 +0000 (09:09 -0800)]
Better handling of scons -u targets.
--HG--
extra : convert_revision :
7bf0688a1c83d8385b77a59a1c75040e9624c0ae
Steve Reinhardt [Mon, 4 Dec 2006 16:59:53 +0000 (08:59 -0800)]
SConstruct:
Couple minor fixes.
SConstruct:
Couple minor fixes.
--HG--
extra : convert_revision :
25f3c12570287334c2cbd1cf9b8227043a57e7d1
Steve Reinhardt [Mon, 4 Dec 2006 16:55:06 +0000 (08:55 -0800)]
import os.path.join as joinpath
--HG--
extra : convert_revision :
200612675e49908b9ff9c965aede35a657241391
Steve Reinhardt [Sun, 3 Dec 2006 06:26:40 +0000 (22:26 -0800)]
Merge vm1.(none):/home/stever/bk/newmem-head
into vm1.(none):/home/stever/bk/newmem-cache2
--HG--
extra : convert_revision :
321f7fcc8bd6c6aaaab92d10172814f4d07d5e65
Steve Reinhardt [Sun, 3 Dec 2006 06:24:52 +0000 (22:24 -0800)]
Support better param conversions to/from numeric subclasses.
--HG--
extra : convert_revision :
2ccb75b0912a384789458710fd9bbb65626f839e
Steve Reinhardt [Sun, 3 Dec 2006 06:23:46 +0000 (22:23 -0800)]
Fix help strings on GenRepl params.
--HG--
extra : convert_revision :
520814e193b9e86b6410f3ab98d62ed131d295aa
Steve Reinhardt [Sun, 3 Dec 2006 06:22:58 +0000 (22:22 -0800)]
Make cache compression policy a runtime virtual thing
instead of a template policy.
--HG--
extra : convert_revision :
6a4ac7a189a950390a973fdfce94f56190de92db
Steve Reinhardt [Sun, 3 Dec 2006 06:12:26 +0000 (22:12 -0800)]
Merge zizzer.eecs.umich.edu:/bk/newmem
into vm1.(none):/home/stever/bk/newmem-head
--HG--
extra : convert_revision :
4a077b463b938c54b546b00e586d8609c24ae465
Steve Reinhardt [Sun, 3 Dec 2006 06:11:24 +0000 (01:11 -0500)]
Delete src/oldmem.
util/make_release.py:
src/oldmem gone from repo, no need to delete here.
--HG--
extra : convert_revision :
570fa1b8d7144376cf13a010160a39d1c1cccbc2
Steve Reinhardt [Sun, 3 Dec 2006 03:52:26 +0000 (19:52 -0800)]
Merge zizzer.eecs.umich.edu:/bk/newmem
into vm1.(none):/home/stever/bk/newmem-head
--HG--
extra : convert_revision :
4c8de6e4c6f729c83e92abd81ea6c1347e647756
Kevin Lim [Sat, 2 Dec 2006 18:33:46 +0000 (13:33 -0500)]
Fixes for MIPS_SE compiling. Regressions seem to work, but Korey should make sure these changes (commit especially) work okay.
src/cpu/o3/commit_impl.hh:
src/cpu/o3/fetch_impl.hh:
Fixes for MIPS_SE compile.
--HG--
extra : convert_revision :
fde9616f8e72b397c5ca965774172372cff53790
Lisa Hsu [Sat, 2 Dec 2006 16:11:58 +0000 (11:11 -0500)]
stats update
--HG--
extra : convert_revision :
b47d3817d204a43e0afb89aafc8dacf619c3f910
Nathan Binkert [Sat, 2 Dec 2006 06:33:18 +0000 (22:33 -0800)]
don't blow away the whole destination directory
--HG--
extra : convert_revision :
7370bad15cc30e75ebb0c8685324d8db06fc2936
Lisa Hsu [Fri, 1 Dec 2006 18:51:49 +0000 (13:51 -0500)]
change this to be a quick one so that it's in the regressions every night - it's only maybe 15 min. long.
tests/configs/twosys-tsunami-simple-atomic.py:
don't need this import
--HG--
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/config.ini => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/config.ini
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/config.out => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/config.out
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/console.drivesys.sim_console => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/console.drivesys.sim_console
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/console.testsys.sim_console => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/console.testsys.sim_console
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/m5stats.txt => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/m5stats.txt
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/stderr => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/stderr
rename : tests/long/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/stdout => tests/quick/80.netperf-stream/ref/alpha/linux/twosys-tsunami-simple-atomic/stdout
rename : tests/long/80.netperf-stream/test.py => tests/quick/80.netperf-stream/test.py
extra : convert_revision :
68497b2ef8b21590cb6c636485703e46dc616513
Lisa Hsu [Fri, 1 Dec 2006 06:24:16 +0000 (01:24 -0500)]
Merge zizzer:/bk/newmem
into zed.eecs.umich.edu:/z/hsul/work/m5/newmem
--HG--
extra : convert_revision :
b62ca8009105aad7173bdbc5d528de243d21a82c
Lisa Hsu [Fri, 1 Dec 2006 06:24:01 +0000 (01:24 -0500)]
add a simple netperf-stream test to the long tests.
tests/SConscript:
add a new configuration for two-system tests (atomic simple only)
--HG--
extra : convert_revision :
16c260ab16f38779fe17b1cab18f36d5c7a70846
Nathan Binkert [Fri, 1 Dec 2006 04:53:30 +0000 (20:53 -0800)]
Merge zizzer.eecs.umich.edu:/bk/newmem
into iceaxe.:/Volumes/work/m5/incoming
--HG--
extra : convert_revision :
05060a06e0b6d66a9c1e7005c233047c6e8ba15f
Nathan Binkert [Fri, 1 Dec 2006 04:50:47 +0000 (20:50 -0800)]
Get rid of the old release-edits script and create make_release.py
which takes care of almost everything needed for putting together
a release.
--HG--
extra : convert_revision :
b05d418a1002633b1286591eb8a8588ba33f5df1
Ron Dreslinski [Thu, 30 Nov 2006 20:01:49 +0000 (15:01 -0500)]
Update stats to match writeback fix that was made
--HG--
extra : convert_revision :
3e0ed2b374d8d96798ea9b3416c9e5579cafacda
Lisa Hsu [Thu, 30 Nov 2006 16:53:33 +0000 (11:53 -0500)]
netperf-maerts-client.rcS:
change /netperf/netperf to /netperf-bin/netperf
nat-netperf-maerts-client.rcS:
bad comment that went with the file - accidentally committed but probably doesn't matter, i ust eliminated an ivlb in the script.
configs/boot/nat-netperf-maerts-client.rcS:
replace netperf/netperf with netperf-bin/netperf
configs/boot/netperf-maerts-client.rcS:
change /netperf/netperf to /netperf-bin/netperf
--HG--
extra : convert_revision :
32fed0042e267f315d3e688ebc4b66d7002b85f0
Steve Reinhardt [Wed, 29 Nov 2006 21:17:41 +0000 (13:17 -0800)]
cscope-find.py:
Write directly to 'cscope.files' and run 'cscope -b' .
Now this script does everything automatically.
cscope-index.py:
Rename: util/cscope-find.py -> util/cscope-index.py
util/cscope-find.py:
Write directly to 'cscope.files' and run 'cscope -b' .
Now this script does everything automatically.
--HG--
rename : util/cscope-find.py => util/cscope-index.py
extra : convert_revision :
cd6fa5cc0c2146f7184c9213956aff67c7cb9341
Kevin Lim [Wed, 29 Nov 2006 21:08:19 +0000 (16:08 -0500)]
Merge ktlim@zizzer:/bk/newmem
into zamp.eecs.umich.edu:/z/ktlim2/clean/tmp/test-regress
--HG--
extra : convert_revision :
3142f68356458ecd2677c30e9cf0a65005b782c2
Kevin Lim [Wed, 29 Nov 2006 21:07:55 +0000 (16:07 -0500)]
Change the connecting of the physPort and virtPort to the memory object below the CPU to happen every time activateContext is called. The overhead is probably a little higher than necessary, but allows these connections to properly be made when there are CPUs that are inactive until they are switched in.
Right now this introduces a minor memory leak as old physPorts and virtPorts are not deleted when new ones are created. A flyspray task has been created for this issue. It can not be resolved until we determine how the bus will handle giving out ID's to functional ports that may be deleted.
src/cpu/o3/cpu.cc:
src/cpu/simple/atomic.cc:
src/cpu/simple/timing.cc:
Change the setup of the physPort and virtPort to instead happen every time the CPU has a context activated. This is a little high overhead, but keeps it working correctly when the CPU does not have a physical memory attached to it until it switches in (like the case of switch CPUs).
src/cpu/o3/thread_context.hh:
Change function from being called at init() to just being called whenever the memory ports need to be connected.
src/cpu/o3/thread_context_impl.hh:
Update this to not delete the port if it's the same as the virtPort.
src/cpu/thread_context.hh:
Change function from being called at init() to whenever the memory ports need to be connected.
src/cpu/thread_state.cc:
Instead of initializing the ports, simply connect them, deleting any old ports that might exist. This allows these functions to be called multiple times.
src/cpu/thread_state.hh:
Ports are no longer initialized, but rather connected at context activation time.
--HG--
extra : convert_revision :
e399ce5dfbd6ad658c953a7c9c7b69b89a70219e
Kevin Lim [Wed, 29 Nov 2006 16:50:03 +0000 (11:50 -0500)]
Add in O3CPU to default CPU list.
--HG--
extra : convert_revision :
4aaaae058cb763580ea0b9019d4a9346938121d4
Ali Saidi [Tue, 28 Nov 2006 21:02:13 +0000 (16:02 -0500)]
add 2.0b2 release notes
--HG--
extra : convert_revision :
ce34f8086f682cc732bf868f6b9700e42c604ca3
Kevin Lim [Tue, 28 Nov 2006 16:41:17 +0000 (11:41 -0500)]
Merge ktlim@zizzer:/bk/newmem
into zamp.eecs.umich.edu:/z/ktlim2/clean/tmp/test-regress
--HG--
extra : convert_revision :
ffc7931d7da153b421b3c838a0968e484fd182ec
Kevin Lim [Tue, 28 Nov 2006 16:41:08 +0000 (11:41 -0500)]
Remove assertion. It's not needed and messes up writebacks when a 2 level cache is used in a uniprocessor setting.
--HG--
extra : convert_revision :
020a9799cd7177fdb85a767701d6fcb8cf018827
Steve Reinhardt [Mon, 27 Nov 2006 07:16:24 +0000 (02:16 -0500)]
Add TRACING_ON setting for m5.prof.
--HG--
extra : convert_revision :
ebda49bff30d76d3209acce55458d3f4e29594d3
Kevin Lim [Sun, 26 Nov 2006 16:46:58 +0000 (11:46 -0500)]
Include check for making sure caches are enabled.
--HG--
extra : convert_revision :
e3902b065db524ebe5bf762e44a840133ccb8d75
Steve Reinhardt [Fri, 24 Nov 2006 17:32:33 +0000 (12:32 -0500)]
Add no-op versions of ivlb and ivle back in for backwards compatibility.
--HG--
extra : convert_revision :
383b72c130b20f3d7cde4e08fa36a481f3c0bf7c
Steve Reinhardt [Thu, 23 Nov 2006 15:46:24 +0000 (10:46 -0500)]
Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/newmem
into zizzer.eecs.umich.edu:/z/stever/bk/newmem-head
--HG--
extra : convert_revision :
154bc605c62b1e51c32e65916d4c2eda3a3f22fd
Ron Dreslinski [Thu, 23 Nov 2006 01:20:38 +0000 (20:20 -0500)]
Do a functional access to levels above on a read as a temporary solution for L2's in FS
Fix a small writeback bug when missing in the L2 in atomic mode
src/mem/bus.cc:
Fix a comment to make sense
src/mem/cache/cache_impl.hh:
Do a functional access to levels above on a read as a temporary solution for L2's in FS
Also fix a small writeback miss in L2 issue
src/mem/cache/coherence/simple_coherence.hh:
src/mem/cache/coherence/uni_coherence.cc:
src/mem/cache/coherence/uni_coherence.hh:
Do a functional access to levels above on a read as a temporary solution for L2's in FS
tests/quick/00.hello/ref/alpha/linux/o3-timing/m5stats.txt:
tests/quick/00.hello/ref/alpha/linux/simple-timing/m5stats.txt:
tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt:
Update ref's for writeback changes
--HG--
extra : convert_revision :
937febd577b16b7fd97a5a68acaf53541828a251
Kevin Lim [Mon, 20 Nov 2006 16:44:27 +0000 (11:44 -0500)]
Fix typo.
--HG--
extra : convert_revision :
2dd830c6b3b5df894608b7596250b0181a3dfdf0
Steve Reinhardt [Sun, 19 Nov 2006 23:38:12 +0000 (18:38 -0500)]
Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/newmem
into zizzer.eecs.umich.edu:/z/stever/bk/newmem-head
--HG--
extra : convert_revision :
c2b7784377d85df5b8ee39c891cd3da9907410d8
Kevin Lim [Sun, 19 Nov 2006 22:43:03 +0000 (17:43 -0500)]
Update Virtual and Physical ports.
src/cpu/o3/alpha/cpu_impl.hh:
Handle the PhysicalPort and VirtualPort in the ThreadState.
src/cpu/o3/cpu.cc:
Initialize the thread context.
src/cpu/o3/thread_context.hh:
Add new function to initialize thread context.
src/cpu/o3/thread_context_impl.hh:
Use code now put into function.
src/cpu/simple_thread.cc:
Move code to ThreadState and use the new helper function.
src/cpu/simple_thread.hh:
Remove init() in this derived class; use init() from ThreadState base class.
src/cpu/thread_state.cc:
Move setting up of Physical and Virtual ports here. Change getMemFuncPort() to connectToMemFunc(), which connects a port to a functional port of the memory object below the CPU.
src/cpu/thread_state.hh:
Update functions.
--HG--
extra : convert_revision :
ff254715ef0b259dc80d08f13543b63e4024ca8d
Ron Dreslinski [Sat, 18 Nov 2006 03:01:18 +0000 (22:01 -0500)]
Merge zizzer:/bk/newmem
into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest
--HG--
extra : convert_revision :
1fc55d7d5707bb7c63790aab306ca5ea8ade5fab
Ron Dreslinski [Sat, 18 Nov 2006 02:55:28 +0000 (21:55 -0500)]
Make an initialization pass for the thread context and set the [phys,virt]Port correctly
src/cpu/simple/atomic.cc:
src/cpu/simple/timing.cc:
Call the thread context initialization
--HG--
extra : convert_revision :
d7dc2a8b893dc670077b7f6150d4b710a1778620
Nathan Binkert [Thu, 16 Nov 2006 21:18:21 +0000 (13:18 -0800)]
add warn_once which will print any given warning message
only once.
--HG--
extra : convert_revision :
b64bb495c1bd0c4beb3db6ca28fad5af4d05ef8e
Nathan Binkert [Thu, 16 Nov 2006 21:10:38 +0000 (13:10 -0800)]
Implement a single config file to encompass all of the SPEC
CPU2000 stuff, and use it in all of the tests that currently
use SPEC
--HG--
extra : convert_revision :
8cd26a597e51a90b6d2810d344a075f5aa0f011b
Nathan Binkert [Thu, 16 Nov 2006 21:08:29 +0000 (13:08 -0800)]
implement RUSAGE_CHILDREN for getrusage since it's trivial
--HG--
extra : convert_revision :
bc12b3b2e9ee02f42c437cbc20680ea00e19a801
Nathan Binkert [Thu, 16 Nov 2006 20:43:11 +0000 (12:43 -0800)]
Implement current working directory for LiveProcesses
--HG--
extra : convert_revision :
a2d3cf29ab65c61af27d82a8c421a41a19fd5aeb
Ron Dreslinski [Wed, 15 Nov 2006 23:22:15 +0000 (18:22 -0500)]
Add L2 cache option to fs.py --l2cache
--HG--
extra : convert_revision :
5bdd1129c3b23e91d441e7b83f6a824ef7740fab
Ron Dreslinski [Tue, 14 Nov 2006 23:41:37 +0000 (18:41 -0500)]
Merge zizzer:/bk/newmem
into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest
--HG--
extra : convert_revision :
8d61b474428d494b1a5382e4cf95934ad54e35dd
Kevin Lim [Tue, 14 Nov 2006 22:22:32 +0000 (17:22 -0500)]
Various fixes to delete packet and request a little better.
src/cpu/simple/timing.cc:
Various updates for deleting requests more properly.
The major change is moving the deletion of the fetch request/packet to after the instruction has executed and completed. This should fix a few bugs because Ron's memory system didn't expect a call for a functional access while a timing access was being processed.
--HG--
extra : convert_revision :
c7cf114bb1ff3cdaa7b0a40ed4c5302dc9d3a522
Ron Dreslinski [Tue, 14 Nov 2006 22:19:57 +0000 (17:19 -0500)]
Merge zizzer:/bk/newmem
into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest
--HG--
extra : convert_revision :
b216fcdb2632dce68ac18932b0c13408eb1aeaf4
Ron Dreslinski [Tue, 14 Nov 2006 22:15:05 +0000 (17:15 -0500)]
Fix bugs around uni-coherence invalidates being propogated properly.
src/mem/bus.cc:
Make it so that invalidates being sent from the responder up don't call the responder
but they should also not Panic.
src/mem/packet.hh:
If we don't have data in the packet, don't call deleteData:
Example: InvalidateRequests never have data.
--HG--
extra : convert_revision :
18766bc9f3bb4d852ac651d094254d347abd1634
Lisa Hsu [Tue, 14 Nov 2006 18:00:05 +0000 (13:00 -0500)]
Merge zizzer:/bk/newmem
into zed.eecs.umich.edu:/z/hsul/work/sparc/m5
--HG--
extra : convert_revision :
6abd919711966eaaa157483557a3f953b02dde01
Lisa Hsu [Tue, 14 Nov 2006 17:59:57 +0000 (12:59 -0500)]
interrupts.hh:
make a likewise updateIntrInfo for Sparc that's blank so it doesn't fart on build
src/arch/sparc/interrupts.hh:
make a likewise updateIntrInfo for Sparc that's blank so it doesn't fart on build
--HG--
extra : convert_revision :
5f469d0cf897479b42703104cd801a8ef923fcae
Ron Dreslinski [Tue, 14 Nov 2006 15:09:13 +0000 (10:09 -0500)]
If all the targets aren't satisfied, reinitialize the packet.
--HG--
extra : convert_revision :
5b0a977a162a1b881b97a3185fb386cc76632a4a
Ron Dreslinski [Tue, 14 Nov 2006 06:38:42 +0000 (01:38 -0500)]
Update atomic and functional paths for snoops as well
--HG--
extra : convert_revision :
566d73438efb87ca683e4dee23454d880db3dfc7
Ron Dreslinski [Tue, 14 Nov 2006 06:13:26 +0000 (01:13 -0500)]
Update phase param in the .py file for the cpus
--HG--
extra : convert_revision :
cd2eb8c00adcb34b8693a4d1a66187927c0f6803
Ron Dreslinski [Tue, 14 Nov 2006 06:12:52 +0000 (01:12 -0500)]
Update bus bridges now that snoop ranges are passed properly
src/mem/bridge.cc:
Update brdiges, now that snoop addresses are properly forwarded.
Bus bridge should only handle snoops on the second phase (SNOOP_COMMIT)
src/mem/bus.cc:
src/mem/bus.hh:
Make sure if a busBridge has access to both things that snoop and things that respond it only takes the request once
--HG--
extra : convert_revision :
26cc9ee4429be45d4476fa435e0e9a54843c2509
Ron Dreslinski [Tue, 14 Nov 2006 06:10:36 +0000 (01:10 -0500)]
Make cpu's capable of having a phase shift
--HG--
extra : convert_revision :
7f082ba5c1cd2445aec731950c31a877aac23a75
Ron Dreslinski [Tue, 14 Nov 2006 03:37:22 +0000 (22:37 -0500)]
Fix a bug to handle the fact that a CPU can send Functional accesses while a sendTiming has not returned in the call stack.
src/mem/cache/base_cache.cc:
Sometimes a functional access comes while waiting on a outstanding packet being sent.
This could be because Timing CPU does some post processing on the recvTiming which send functional access.
Either the CPU should leave the pkt/req around (so They can be referenced in the mem system). Or the mem
system should remove them from outstanding lists and reinsert them if they fail in the sendTiming.
I did the later, eventually we should consider doing the former if that is the correct behavior.
--HG--
extra : convert_revision :
be41e0d2632369dca9d7c15e96e5576d7583fe6a
Ron Dreslinski [Tue, 14 Nov 2006 02:59:50 +0000 (21:59 -0500)]
Merge zizzer:/bk/newmem
into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest
--HG--
extra : convert_revision :
253766a17bb5e109f8ad76b3c54e443db5274ef5
Ron Dreslinski [Tue, 14 Nov 2006 02:34:25 +0000 (21:34 -0500)]
If we didn't satisfy all targets, reset the packet we are requesting with.
--HG--
extra : convert_revision :
736372131b046eccf3520292fb3c086dc568d918
Ron Dreslinski [Tue, 14 Nov 2006 02:33:01 +0000 (21:33 -0500)]
Fix some errors related to snooping and functional access in the bus
src/mem/bus.cc:
Only call snoop once per port, need to fix it so snoop ranges that overlap aren't added to list
Functional accesses that call snoop and it goes to a higher bus may change the src, reset it after each snoop.
--HG--
extra : convert_revision :
7276059c798a85cb9d138ccc5531298ecd055c13
Ron Dreslinski [Tue, 14 Nov 2006 00:56:34 +0000 (19:56 -0500)]
Fix problems with snoop ranges not working properly on functional accesses
src/mem/bus.cc:
Actually return the snoop list when asked for it.
Don't get stuck in infinite functional loops
--HG--
extra : convert_revision :
8e6dafbd10b30d48d28b6b5d4b464e8e8f6a3ddc
Ron Dreslinski [Tue, 14 Nov 2006 00:12:45 +0000 (19:12 -0500)]
Changes needed for a bus from CPU->L1
src/cpu/simple/atomic.cc:
Make the atomic cpu return 0 on snoops.
--HG--
extra : convert_revision :
aad96ad36e0c764c7cfef8b0c8e97877574f5845
Ron Dreslinski [Tue, 14 Nov 2006 00:00:50 +0000 (19:00 -0500)]
Since cpus now send out snoop ranges, remove it from the cache.
--HG--
extra : convert_revision :
82882eb131aa66eba9f281b64db21d5cbfefb1b9
Ron Dreslinski [Mon, 13 Nov 2006 23:51:16 +0000 (18:51 -0500)]
Make CPU models signal to update the snoop ranges
--HG--
extra : convert_revision :
717b62510f28a69af99453309fbbb458359eeb2a
Lisa Hsu [Mon, 13 Nov 2006 21:18:47 +0000 (16:18 -0500)]
main.i:
swig still thought the default arg for simulate() was -1, make it MaxTick
--HG--
extra : convert_revision :
2bcbef7e5e5d28cf55645fdc53d43e3953b1a11c
Ron Dreslinski [Mon, 13 Nov 2006 21:09:47 +0000 (16:09 -0500)]
Update splash2 config files
configs/splash2/run.py:
Fix MaxTick for splash configs
configs/splash2/cluster.py:
Add a config that allows clusters of CPU's to be attached to a single L1
--HG--
extra : convert_revision :
1bb0a0c5f4889316940a9858be90ae2eaa849f1a
Nathan Binkert [Mon, 13 Nov 2006 20:20:08 +0000 (12:20 -0800)]
Expose debugBreakCycle through swig and get rid of
the Debug param context
--HG--
extra : convert_revision :
40e9dcfa9faedbe0c90a43f908f20a7c14ded6a4
Nathan Binkert [Mon, 13 Nov 2006 20:18:36 +0000 (12:18 -0800)]
Clean up comment
--HG--
extra : convert_revision :
75c6415c49305e2f8cf7f833c66a46a4dee503ea
Ali Saidi [Mon, 13 Nov 2006 18:26:36 +0000 (13:26 -0500)]
Parse CC/CXX early so that we use the correct compiler for testing dependencies/versions/libraries/etc
--HG--
extra : convert_revision :
b34ee03e44b35df30b746c4c570316db75d6ffe5
Kevin Lim [Mon, 13 Nov 2006 07:49:13 +0000 (02:49 -0500)]
Merge ktlim@zizzer:/bk/newmem
into zamp.eecs.umich.edu:/z/ktlim2/clean/newmem-busfix
--HG--
extra : convert_revision :
6ef2249bfa3f7149830efdb42a313422090da7d7
Kevin Lim [Mon, 13 Nov 2006 07:49:03 +0000 (02:49 -0500)]
More interrupt reworking.
--HG--
extra : convert_revision :
40dfbb72c4e418c54e909c54dad5fe6ef7017cb4
Steve Reinhardt [Mon, 13 Nov 2006 06:04:00 +0000 (22:04 -0800)]
Merge zizzer.eecs.umich.edu:/bk/newmem
into vm1.(none):/home/stever/bk/newmem-head
--HG--
extra : convert_revision :
faab7569deefde94c20133b2f70a8567bcaa2960
Steve Reinhardt [Mon, 13 Nov 2006 06:03:42 +0000 (22:03 -0800)]
Make setRegWithEffect do something in SE mode.
--HG--
extra : convert_revision :
88fdaa403fe6d083f8c8fc064cb0d0d6a8b8daf8
Kevin Lim [Mon, 13 Nov 2006 05:26:38 +0000 (00:26 -0500)]
Change warn to DPRINTF.
--HG--
extra : convert_revision :
746bdf92334d220158eb0eb6bf113b4dcedbb354
Kevin Lim [Mon, 13 Nov 2006 05:24:22 +0000 (00:24 -0500)]
Update output refs. Some FS statistics will change (namely the ITB) due to the recent TLB changes. Now PAL mode accesses are counted as hits in the TLB.
tests/quick/00.hello/ref/alpha/linux/o3-timing/config.ini:
tests/quick/00.hello/ref/alpha/linux/o3-timing/config.out:
tests/quick/00.hello/ref/alpha/linux/o3-timing/stderr:
tests/quick/00.hello/ref/alpha/linux/o3-timing/stdout:
tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.ini:
tests/quick/00.hello/ref/alpha/linux/simple-atomic/config.out:
tests/quick/00.hello/ref/alpha/linux/simple-timing/config.ini:
tests/quick/00.hello/ref/alpha/linux/simple-timing/config.out:
tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.ini:
tests/quick/00.hello/ref/alpha/tru64/o3-timing/config.out:
tests/quick/00.hello/ref/alpha/tru64/o3-timing/stderr:
tests/quick/00.hello/ref/alpha/tru64/o3-timing/stdout:
tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.ini:
tests/quick/00.hello/ref/alpha/tru64/simple-atomic/config.out:
tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.ini:
tests/quick/00.hello/ref/alpha/tru64/simple-timing/config.out:
tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.ini:
tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/config.out:
tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/m5stats.txt:
tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stderr:
tests/quick/01.hello-2T-smt/ref/alpha/linux/o3-timing/stdout:
tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/config.ini:
tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/config.out:
tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic-dual/m5stats.txt:
tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/config.ini:
tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/config.out:
tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-atomic/m5stats.txt:
tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/config.ini:
tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/config.out:
tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing-dual/m5stats.txt:
tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/config.ini:
tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/config.out:
tests/quick/10.linux-boot/ref/alpha/linux/tsunami-simple-timing/m5stats.txt:
tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.ini:
tests/quick/20.eio-short/ref/alpha/eio/simple-atomic/config.out:
tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.ini:
tests/quick/20.eio-short/ref/alpha/eio/simple-timing/config.out:
Update refs.
--HG--
extra : convert_revision :
6798c5753d4d7bd7b5667d59cf564012b781ce8a
Kevin Lim [Mon, 13 Nov 2006 04:31:29 +0000 (23:31 -0500)]
Fix typo.
--HG--
extra : convert_revision :
05db10e20d33302fe830d5759b8881b1233aca87
Kevin Lim [Mon, 13 Nov 2006 04:30:09 +0000 (23:30 -0500)]
Fix for regression failure.
src/cpu/o3/fetch_impl.hh:
Fetch needs to make sure it isn't waiting on an Icache access.
--HG--
extra : convert_revision :
b53eb58b9e5a00bdb394134586d1f84f84d1c6e1
Kevin Lim [Mon, 13 Nov 2006 02:57:58 +0000 (21:57 -0500)]
Merge ktlim@zamp:./local/clean/tmp/test-regress
into zamp.eecs.umich.edu:/z/ktlim2/clean/newmem-busfix
--HG--
extra : convert_revision :
b98236507bb8996ce605b48b5a5a6a7aac297dc5
Kevin Lim [Mon, 13 Nov 2006 02:49:51 +0000 (21:49 -0500)]
Fix for non-FS compile.
--HG--
extra : convert_revision :
661b412b0ae670181b89cb7dbc5e9d813804aa7a
Nathan Binkert [Mon, 13 Nov 2006 02:49:16 +0000 (18:49 -0800)]
Create a module called internal where swigged stuff goes.
Rename cc_main to internal.main
--HG--
extra : convert_revision :
e938005f600fbf8a43435e29426a948f4501f072
Kevin Lim [Mon, 13 Nov 2006 01:15:30 +0000 (20:15 -0500)]
Updates to support new interrupt processing and removal of PcPAL.
src/arch/alpha/interrupts.hh:
No need for this now that the ThreadContext is being used to set these IPRs in interrupts.
Also split up the interrupt checking from the updating of the IPL and interrupt summary.
src/arch/alpha/tlb.cc:
Check the PC for whether or not it's in PAL mode, not the addr.
src/cpu/o3/alpha/cpu.hh:
Split up getting the interrupt from actually processing the interrupt.
src/cpu/o3/alpha/cpu_impl.hh:
Splut up the processing of interrupts.
src/cpu/o3/commit_impl.hh:
Update for ISA-oriented interrupt changes.
src/cpu/o3/fetch_impl.hh:
Fix broken if statement from PcPAL updates, and properly populate the request fields.
Also more debugging output.
src/cpu/ozone/cpu_impl.hh:
Updates for ISA-oriented interrupt stuff.
src/cpu/ozone/front_end_impl.hh:
Populate request fields properly.
src/cpu/simple/base.cc:
Update for interrupt stuff.
--HG--
extra : convert_revision :
9bac3f9ffed4948ee788699b2fa8419bc1ca647c
Ron Dreslinski [Sun, 12 Nov 2006 16:42:07 +0000 (11:42 -0500)]
Update for maxtick in splash2/memtest configs
configs/example/memtest.py:
configs/splash2/run.py:
Update for maxtick
--HG--
extra : convert_revision :
94106625be1ebc2b614db16720a4861e47222c0b
Ron Dreslinski [Sun, 12 Nov 2006 16:07:34 +0000 (11:07 -0500)]
Update refs for functional access fixes
--HG--
extra : convert_revision :
aa34e0e7254daf20ecb7c14d430f08927a8fb9ca
Ron Dreslinski [Sun, 12 Nov 2006 15:41:18 +0000 (10:41 -0500)]
Merge zizzer:/bk/newmem
into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest
--HG--
extra : convert_revision :
498304c24435437f8f1942bb8aeafe69ba22a089
Ron Dreslinski [Sun, 12 Nov 2006 14:30:12 +0000 (09:30 -0500)]
Physical memory overrides the tport version of recvFunctional, need to do the
check here for responses that match as well
--HG--
extra : convert_revision :
69c3628a381a9da885fab0272abf40c3411a5f0f
Ron Dreslinski [Sun, 12 Nov 2006 14:06:15 +0000 (09:06 -0500)]
Handle packets being deleted by lower level properly.
Fixes for Mem Leak associated with Writebacks.
src/mem/cache/miss/mshr_queue.cc:
Fixes for Mem Leak associated with Writebacks. (Double Delete removed)
--HG--
extra : convert_revision :
7a52ddd57da35995896f2c4438a58aa53f762416