3f2b039c98
change the way dprintf works so the cache accesses required to fulfill the dprintf aren't show in between the Cycle: name: printing and the actual formatted string being printed
Ali Saidi
2007-05-01 18:14:16 -04:00
39743d35a3
fix flushAddr so it doesn't modify an iterator that has been deleted
Ali Saidi
2007-05-01 18:12:58 -04:00
8371f03e0d
update for dprintk and not initializing lastTxInt
Ali Saidi
2007-05-01 13:23:40 -04:00
e0f8e57a7f
Merge zizzer:/bk/newmem into zeep.pool:/z/saidi/work/m5.newmem
Ali Saidi
2007-05-01 12:33:03 -04:00
ccdf60f7b2
initialize lastTxInt to 0
Ali Saidi
2007-05-01 12:32:30 -04:00
8d56145d7b
always skip the debugprintf function (DebugPrintf traceflag shouldn't matter). Otherwise, when you turn on debugprintf alters the execution
Ali Saidi
2007-04-30 22:49:21 -04:00
3ae12a549e
update release notes a bit
Ali Saidi
2007-04-30 14:22:18 -04:00
cd617b7d38
update refs for uart device changes
Ali Saidi
2007-04-30 14:10:40 -04:00
7baf29c9d0
fix igbe bug
Ali Saidi
2007-04-30 13:18:44 -04:00
58b9047194
fix console printing bug
Ali Saidi
2007-04-30 13:13:03 -04:00
ae4208f3a3
add the ability for the ethernet device to check if the link is busy
Ali Saidi
2007-04-30 13:09:13 -04:00
6e60d5c12f
add a udp stream benchmark and a udp loopback benchmark
Ali Saidi
2007-04-30 13:08:21 -04:00
e77aa3d212
make ping actually end
Ali Saidi
2007-04-30 13:07:05 -04:00
1c243d66a2
Merge zizzer.eecs.umich.edu:/bk/newmem into iceaxe.:/Users/nate/work/m5/incoming
Nathan Binkert
2007-04-27 13:59:44 -07:00
69d259b6ae
gcc 4.1 claims that mem_data might be used uninitialized, though I don't believe that's true. Placate it anyway.
Nathan Binkert
2007-04-27 13:59:17 -07:00
8be8261301
Merge ktlim@zizzer:/bk/newmem into zamp.eecs.umich.edu:/z/ktlim2/clean/tmp/head
Kevin Lim
2007-04-27 16:36:38 -04:00
71b6499c12
Updates for clock changes.
Kevin Lim
2007-04-27 16:36:19 -04:00
b5037ad82b
Actually move the time two minutes into the future to make sure that we get the result that we want
Nathan Binkert
2007-04-27 12:15:25 -07:00
ee188e88cd
whack the old list of outstanding issues, and put the new list at the top
Nathan Binkert
2007-04-27 11:53:14 -07:00
7f39291c81
Update Alpha reference stats for clock changes.
Kevin Lim
2007-04-27 14:35:58 -04:00
0ae6f03439
Make sure that we don't rebuild libelf stuff that we don't have to since it doesn't work well on non-linux
Nathan Binkert
2007-04-27 11:15:15 -07:00
522e59840f
Fix mutex test script for latest disk image.
Kevin Lim
2007-04-26 00:10:06 -04:00
092951e2b1
Remove extra delete that was causing segfault.
Kevin Lim
2007-04-26 00:07:42 -04:00
15cc194d71
Remove unnecessary check.
Kevin Lim
2007-04-26 00:02:37 -04:00
f42469a3cf
Merge zizzer:/bk/newmem into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/head
Ron Dreslinski
2007-04-23 16:04:15 -04:00
c47804002a
Fix the splash2 run script
Ron Dreslinski
2007-04-23 16:03:53 -04:00
d32c08c4cc
Merge zizzer:/bk/newmem into zed.eecs.umich.edu:/z/hsul/work/m5/newmem
Lisa Hsu
2007-04-23 14:41:13 -04:00
6a79ada182
update_refs for ALPHA_FS with new disk image.
Lisa Hsu
2007-04-23 14:40:46 -04:00
3eb4ba3abb
Merge zizzer:/bk/newmem into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/head
Ron Dreslinski
2007-04-23 14:38:04 -04:00
6fec6d278a
using remote
Gabe Black
2007-04-23 12:30:03 -04:00
67fa834dfb
Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/newmem into zizzer.eecs.umich.edu:/.automount/wexford/x/gblack/m5/newmem-o3-spec
Gabe Black
2007-04-23 12:28:11 -04:00
46f6fa8b45
Update refs for CPU clock changes and O3 CPI/IPC calculation updates.
Kevin Lim
2007-04-23 12:13:19 -04:00
cca881a531
Merge zizzer.eecs.umich.edu:/n/wexford/x/gblack/m5/newmem-o3-spec into ahchoo.blinky.homelinux.org:/home/gblack/m5/newmem-o3-micro
Gabe Black
2007-04-23 15:34:40 +00:00
a006aa067a
Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/newmem into zizzer.eecs.umich.edu:/.automount/wexford/x/gblack/m5/newmem-o3-spec
Gabe Black
2007-04-23 11:34:39 -04:00
dbc1edd23d
Merge ktlim@zizzer:/bk/newmem into zamp.eecs.umich.edu:/z/ktlim2/clean/tmp/head
Kevin Lim
2007-04-22 15:31:33 -04:00
f092900696
Change mcf to use smred inputs so it doesn't take two days to run in o3.
Gabe Black
2007-04-22 19:30:47 +00:00
67a37e83f3
Updated refs for calculating IPC/CPI.
Kevin Lim
2007-04-22 15:29:59 -04:00
8c7a6e1654
Use proper cycles for IPC and CPI equations.
Kevin Lim
2007-04-22 15:11:54 -04:00
d70f01ba5c
Update refs for new CPU frequency changes.
Kevin Lim
2007-04-22 14:50:37 -04:00
d1f9414e11
Update configs to set the CPU clock properly.
Kevin Lim
2007-04-22 14:39:39 -04:00
acc62514b1
Make the floating point zero register special handling only apply for ALPHA.
Gabe Black
2007-04-22 17:50:43 +00:00
cea5435760
Make the GSR into a renamed control register. It should be split into a renamed part and a control part for the different bitfields, but the renamed part is all that's actually used.
Gabe Black
2007-04-22 17:43:45 +00:00
088a056583
Merge zizzer:/bk/newmem into zeep.pool:/tmp/newmem
Ali Saidi
2007-04-21 19:12:13 -04:00
53ba34391f
fixes for solaris compile
Ali Saidi
2007-04-21 19:11:38 -04:00
e8ace88e89
create base/fenv.c to standerdize fenv across platforms. It's a c file and not a cpp file because c99 (which defines fenv) doesn't necessarily extend to c++ and it is a problem with solaris. If really desired this could wrap the ieeefp interface found in bsd* as well, but I see no need at the moment.
Ali Saidi
2007-04-21 17:50:47 -04:00
25e92383c8
spec-surge-client.rcS: fix script to reflect new benchmark directory sturcture
Lisa Hsu
2007-04-20 20:21:59 -04:00
f3a0abbecc
Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/newmem into zizzer.eecs.umich.edu:/.automount/wexford/x/gblack/m5/newmem-o3-spec
Gabe Black
2007-04-18 21:27:37 -04:00
5825104982
update the stuff that's removed from the SConscripts since things have moved around a bit
Nathan Binkert
2007-04-18 16:56:06 -07:00
6f4c1aa475
Move the turbolaser python simobject stuff into the encumbered directory
Nathan Binkert
2007-04-18 11:15:52 -07:00
d92fff858b
fix SIGUSR1 and SIGUSR2 by clearing the variables after they're used
Nathan Binkert
2007-04-18 08:04:46 -07:00
dde2b11ae6
Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/newmem into zizzer.eecs.umich.edu:/.automount/wexford/x/gblack/m5/newmem-o3-spec
Gabe Black
2007-04-17 08:56:59 -04:00
3b95161da8
Merge zizzer:/bk/newmem into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/head
Ron Dreslinski
2007-04-16 11:32:09 -04:00
2952c34096
Fixes for splash, may conflict with Korey's SMT work and doesn't support 03cpu yet.
Ron Dreslinski
2007-04-16 11:31:54 -04:00
68221b708c
Merge ktlim@zizzer:/bk/newmem into zamp.eecs.umich.edu:/z/ktlim2/clean/tmp/head
Kevin Lim
2007-04-15 22:40:18 -04:00
733a57d45a
Update long test refs.
Kevin Lim
2007-04-15 22:29:37 -04:00
8248af53b1
Make an inner loop which pulls microops out of macroops. These aren't checked for control flow because we can pull out microops until we run out of buffer. This prevents microops from being interpretted as branches because the pc doesn't become npc.
Gabe Black
2007-04-15 21:52:38 +00:00
308b2f0ce3
Add extra constructors to Alpha and MIPS
Gabe Black
2007-04-15 21:51:05 +00:00
c3081d9c1c
Add support for microcode and pull out the special branch delay slot handling. Branch delay slots need to be squash on a mispredict as well because the nnpc they saw was incorrect.
Gabe Black
2007-04-14 17:13:18 +00:00
5a3dcc172a
Make register indexes larger so they can actually hold all the legal values. Oops!
Gabe Black
2007-04-14 17:08:24 +00:00
3140dd88bc
Make the fsr a serializing register. Other control registers probably need this as well.
Gabe Black
2007-04-14 17:07:24 +00:00
9be23ea4ae
Merge zizzer:/bk/newmem into udhcp-macvpn-501.public.engin.umich.edu:/Users/ali/work/m5.newmem
Ali Saidi
2007-04-13 13:34:04 -04:00
2778458eb5
take a first stab at the release notes
Ali Saidi
2007-04-13 13:33:32 -04:00
e9c6012acf
Adjust references to reflect differences without special delay slot handling. Performance actually went up slightly.
Gabe Black
2007-04-13 14:00:42 +00:00
c7f1cf1d58
Remove most of the special handling for delay slots since they have to be squashed anyway on a mispredict. This is because the NNPC value they saw when executing was incorrect.
Gabe Black
2007-04-13 13:59:31 +00:00
a575fbd4aa
Completely re-work how the scons framework incorporates swig and python code into m5 to allow swig an python code to easily added by any SConscript instead of just the one in src/python. This provides SwigSource and PySource for adding new files to m5 (similar to Source for C++). Also provides SimObject for including files that contain SimObject information and build the m5.objects __init__.py file.
Nathan Binkert
2007-04-12 21:20:04 -07:00
eefbda7f7c
Don't allow Source to accept multiple arguments, lists, or automatically do Split(). It isn't used anywhere, and isn't very consistent with the python features that are about to be added. Do accept SCons.Node.FS.File arguments though.
Nathan Binkert
2007-04-12 09:07:59 -07:00
e04208f046
Fix NextEthernetAddr. unproxy() needs to return a new object otherwise all instances will use the same value. This fix is more or less unique to NextEthernetAddr because its use of the proxy stuff is a bit different than everything else.
Nathan Binkert
2007-04-12 08:37:55 -07:00
fa2a93a236
Add a scons hack to force symlinks to the swig .i files to be created
Nathan Binkert
2007-04-12 08:35:19 -07:00
6ec510385d
Merge zizzer.eecs.umich.edu:/bk/newmem into ahchoo.blinky.homelinux.org:/home/gblack/m5/newmem-o3-spec
Gabe Black
2007-04-11 15:30:09 +00:00
c382bdf93d
Use a computed mask to mask out the fetch address and not a hard coded one.
Gabe Black
2007-04-11 14:16:54 +00:00
54abc8b337
Make the itlb set the PHYSICAL flag on a request when it translates it. This gets it out of the cpu.
Gabe Black
2007-04-11 14:02:03 +00:00
121a5438a5
Make trying to execute macroops fail with a better error message.
Gabe Black
2007-04-11 12:26:23 +00:00
e72f1e63f0
Create a filter and a union to translate the SPARC instruction implementations from using doubles to using concatenated singles.
Gabe Black
2007-04-11 12:25:00 +00:00
fcc35a67e0
Merge zizzer.eecs.umich.edu:/bk/newmem into ahchoo.blinky.homelinux.org:/home/gblack/m5/newmem-x86
Gabe Black
2007-04-10 17:27:33 +00:00
74122c04cf
Even if you don't want to fetch more bytes, make sure you handle a fault.
Gabe Black
2007-04-10 17:27:12 +00:00
798caa36ad
Include the new GenFault microop.
Gabe Black
2007-04-10 17:26:04 +00:00
9f4ebf9156
Reworked x86 a bit
Gabe Black
2007-04-10 17:25:15 +00:00
d6f81e02b4
Updated for the new instruction stubs.
Gabe Black
2007-04-10 17:23:47 +00:00
b79cacaf3f
Changed some instruction names to be in all caps, and "implemented" move to test the stub code for instructions.
Gabe Black
2007-04-10 17:22:45 +00:00
321ca32152
Added stub implementations of the x86 instructions categorized like they are in the AMD64 manuals' instruction summary in volume 1.
Gabe Black
2007-04-10 17:18:59 +00:00
7d53e54019
A new microop which generates a specified fault.
Gabe Black
2007-04-10 17:16:22 +00:00
1320e294fe
Added a class which lets you manipulate all the strings returned by the parser as a unit.
Gabe Black
2007-04-10 17:14:51 +00:00
c59f9456b9
Fix up the base x86 fault object and create a fault to be generated by unimplemented instructions in their microcode. This is useful if certain variations of an instruction are implemented, but, for instance, it's memory based versions aren't.
Gabe Black
2007-04-10 17:13:26 +00:00
f71a6c8fed
Merge zizzer.eecs.umich.edu:/bk/newmem into ahchoo.blinky.homelinux.org:/home/gblack/m5/newmem-o3-spec
Gabe Black
2007-04-10 01:53:04 +00:00
5476247623
Fixed a compile error.
Gabe Black
2007-04-10 01:52:38 +00:00
438b951a5b
add code to whack the intel gbe model from the relase.... it's not tested and it's configuration is a hack
Ali Saidi
2007-04-09 18:49:02 -04:00
d54b8b73ed
Comment out the remote gdb object for SE mode.
Gabe Black
2007-04-09 18:30:50 +00:00
64b4572c3e
Merge ktlim@zizzer:/bk/newmem into zamp.eecs.umich.edu:/z/ktlim2/clean/tmp/head
Kevin Lim
2007-04-09 14:30:49 -04:00
0cc343d41d
Fix bug when blocking due to no free registers.
Kevin Lim
2007-04-09 14:29:59 -04:00
f53d2ccbfc
Merge zizzer.eecs.umich.edu:/bk/newmem into ahchoo.blinky.homelinux.org:/home/gblack/m5/newmem-x86
Gabe Black
2007-04-09 07:59:57 +00:00
97e8111b46
Added SPARC o3 insttest regression.
Gabe Black
2007-04-09 03:59:56 -04:00
7e1807acfb
Added SPARC simple timing regression for insttest
Gabe Black
2007-04-09 03:52:15 -04:00
d9da10199e
Make SPARC build o3 by default.
Gabe Black
2007-04-09 03:40:21 -04:00
85f9213b8a
Accidentally didn't save when moving the specialization code out of here.
Gabe Black
2007-04-09 01:08:05 +00:00
c7bb106886
Take into account that the flattened integer register space is a different size than the architected one. Also fixed some asserts.
Gabe Black
2007-04-08 23:31:11 +00:00
d29979b043
Merge zizzer.eecs.umich.edu:/bk/newmem into ahchoo.blinky.homelinux.org:/home/gblack/m5/newmem-o3-spec
Gabe Black
2007-04-08 01:54:08 +00:00
3bb5fd8c44
Get the "hard" SPARC instructions working in o3. I don't like that the IsStoreConditional flag needs to be set for them because they aren't store conditional instructions, and I should fix the format code which is not handling the opt_flags correctly.
Gabe Black
2007-04-08 01:42:42 +00:00
5d52cd6409
Move the instruction specialization stuff out of the microassembler file, and added some comments to main.isa
Gabe Black
2007-04-06 16:55:56 +00:00
a3ed19f82a
Merge zizzer.eecs.umich.edu:/bk/newmem into ahchoo.blinky.homelinux.org:/home/gblack/m5/newmem-x86
Gabe Black
2007-04-06 16:39:47 +00:00
Ali Saidi