derek/gem5
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • 0acb2d0108 small cleanup to sampling cpu code. Nathan Binkert 2005-03-15 12:17:22 -05:00
  • 1491a239d6 Fix comment. Steve Reinhardt 2005-03-15 12:12:32 -05:00
  • 25d131f1b6 Fix the fix, I hope... Steve Reinhardt 2005-03-15 12:10:59 -05:00
  • 5b10fdf4eb fetch.cc: undo ron's one-line fix for No suppliers - this was causing the DEADLOCK Lisa Hsu 2005-03-15 11:33:11 -05:00
  • 2ba8bc8184 fetch.cc: undo ron's fix that i checked in, it caused the deadlock. Lisa Hsu 2005-03-15 11:28:24 -05:00
  • efdab1748f Merge ktlim@zizzer.eecs.umich.edu:/bk/m5 into zamp.eecs.umich.edu:/z/ktlim2/m5 Kevin Lim 2005-03-14 18:01:07 -05:00
  • 2adf334642 g++ 3.4 fixes. Kevin Lim 2005-03-14 18:00:46 -05:00
  • 752b937ff7 helpful DPRINTF changes - more info is good! Lisa Hsu 2005-03-14 17:58:02 -05:00
  • f5ef4c5533 Merge ktlim@zizzer.eecs.umich.edu:/bk/m5 into zamp.eecs.umich.edu:/z/ktlim2/m5 Kevin Lim 2005-03-14 17:33:32 -05:00
  • cd00fa13a0 Bad addr check should be full system only. Kevin Lim 2005-03-14 16:43:03 -05:00
  • 0f11144b26 Merge ktlim@zizzer.eecs.umich.edu:/bk/m5 into zamp.eecs.umich.edu:/z/ktlim2/m5 Kevin Lim 2005-03-14 16:09:50 -05:00
  • 3cc61bd9e2 Fix for using Python 2.4 Kevin Lim 2005-03-14 16:09:36 -05:00
  • 8f2a84cbe5 Merge Kevin Lim 2005-03-14 15:40:51 -05:00
  • 76e6dd01ae Merge zizzer:/bk/m5 into zeep.eecs.umich.edu:/z/saidi/work/m5 Ali Saidi 2005-03-14 15:38:26 -05:00
  • c1f5b983f0 put the syscall emulation error stuff to bed, finally remove addr from pciconfig objects and update Monet configuration for ron's changes Ali Saidi 2005-03-14 15:37:58 -05:00
  • bc2923f78d Move adding SRCDIR/python to sys.path from multiple SConscript files to SConstruct. Steve Reinhardt 2005-03-14 14:43:10 -05:00
  • 076e1ebac2 Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/m5 into zizzer.eecs.umich.edu:/z/stever/bk/m5 Steve Reinhardt 2005-03-14 11:34:50 -05:00
  • 81169916aa print the daddr to pciconfigall DPRINTF. Lisa Hsu 2005-03-14 11:16:27 -05:00
  • b12f9321ff Ron's fix to some of the No supplier problems, don't deal with badaddrs. Lisa Hsu 2005-03-14 11:15:41 -05:00
  • e7a106eec1 fix the etherdev2 connection so that nat runs work. Lisa Hsu 2005-03-14 10:23:43 -05:00
  • de4aa84154 Move mpy_importer into m5 package (it logically belongs there since it's so tied in with m5.config). Steve Reinhardt 2005-03-14 07:52:41 -05:00
  • 1b841a871e - Add capability to auto-generate Param structs from .mpy SimObject descriptions. Structs are defined in simobj/param/ObjectName.hh. - Move compile-time python params (from CPPDEFINES) to separate dict from run-time params (from os.environ). The former are needed to generate proper param structs. This also helps prevent users from messing things up by setting the wrong environment vars (which could have overridden compile-time settings in the old system). - Other misc cleanup of m5 python package. Steve Reinhardt 2005-03-14 07:46:26 -05:00
  • 82964b2705 Minor Python config bug fix. Steve Reinhardt 2005-03-13 01:21:23 -05:00
  • d94f5bfb04 A few fixes after trying one of Nate's job scripts. Steve Reinhardt 2005-03-13 00:54:34 -05:00
  • 8dff74b26f Clean up import situation... key things are: - global tracking of legitimate param types in separate dict keeps us from having to import objects in config.py, which gets rid of nasty circular dependence - use __all__ in config.py and restrict imports from mpy_importer to reduce m5 namespace pollution Steve Reinhardt 2005-03-13 00:36:06 -05:00
  • 3bbddb43d4 fix syntax error that affected split configurations. Nathan Binkert 2005-03-12 09:42:08 -05:00
  • e0d52f56e1 Merge zizzer:/bk/m5 into zeep.eecs.umich.edu:/z/saidi/work/m5 Ali Saidi 2005-03-11 19:34:43 -05:00
  • c977d2a02b remove addr from PciConfigDevice since it's not used Random some small config file stuff Ali Saidi 2005-03-11 19:34:35 -05:00
  • 05e07428f1 I don't know why from m5 import * doesn't work. Steve? Nathan Binkert 2005-03-11 18:50:04 -05:00
  • c393a51f4a move the conversion stuff that was in configs/kernel/Config.py into the m5 package as convert.py add a smartdict class which stores strings and can intelligently interpret those string variables as several other types. make the env dict use the smartdict class Nathan Binkert 2005-03-11 18:47:11 -05:00
  • e6902a907e Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/m5 into ziff.eecs.umich.edu:/z/binkertn/research/m5/current Nathan Binkert 2005-03-11 18:32:36 -05:00
  • fa1650a08e Make ConfigNodes as intermediate containers work again. Nathan Binkert 2005-03-11 18:30:44 -05:00
  • cf05fa476d stick all python stuff into a top level python directory. create an m5 package in python/m5 move the objects package into the m5 package move the m5config into the m5 package as config leave both importers outside of the package. Nathan Binkert 2005-03-11 18:28:38 -05:00
  • b1f41a7aa0 Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/m5 into zizzer.eecs.umich.edu:/z/ehallnor/work/m5 Erik Hallnor 2005-03-11 18:14:47 -05:00
  • 1eb5e618de Added config files for splash2 benchmarks. Parameters: ROOTDIR = root directory of the splash2 code NP = number of proccessors BENCHMARK = name of the splash2 benchmark (Cholesky, FFT, LUContig, LUNoncontig, Radix, Barnes, FMM, OceanContig, OceanNoncontig, Raytrace, WaterNSquared, or WaterSpatial) SYSTEM = Type of system to simulate detailed or simple Ron Dreslinski 2005-03-11 18:07:07 -05:00
  • e03680c2f2 Fixup after merging. Erik Hallnor 2005-03-11 12:40:12 -05:00
  • 51bdb242f9 Need to invalidate blocks by calling the invalidateBlk function, not setting status to 0. Erik Hallnor 2005-03-11 12:29:47 -05:00
  • c12a665c31 Merge ktlim@zizzer.eecs.umich.edu:/bk/m5 into zamp.eecs.umich.edu:/z/ktlim2/m5 Kevin Lim 2005-03-10 15:53:27 -05:00
  • aa8c9db159 Merge zizzer:/z/m5/Bitkeeper/m5 into zizzer.eecs.umich.edu:/.automount/zazzer/z/rdreslin/m5bk/timing_L1 Ron Dreslinski 2005-03-10 14:53:34 -05:00
  • de63edb752 Merge zizzer:/bk/m5 into zeep.eecs.umich.edu:/z/saidi/work/m5 Ali Saidi 2005-03-10 14:20:21 -05:00
  • ad9b28f98e Removed unecessary constructor call at each return. Ali Saidi 2005-03-10 14:20:12 -05:00
  • c9bf45ae23 Fixup checkpoint directory name Nathan Binkert 2005-03-10 13:52:39 -05:00
  • a7f51d7861 Add better support for using checkpoints. Nathan Binkert 2005-03-10 13:51:00 -05:00
  • 5af1ad62de update genini so it is more like m5 Nathan Binkert 2005-03-10 13:38:44 -05:00
  • e51850f1d2 Merge zizzer:/z/m5/Bitkeeper/m5 into zizzer.eecs.umich.edu:/.automount/zazzer/z/rdreslin/m5bk/timing_L1 Ron Dreslinski 2005-03-10 11:56:07 -05:00
  • 331460dfe8 Updated to be frequency independent Ali Saidi 2005-03-10 02:06:27 -05:00
  • 9797eedeea fix typo in SyscallReturn Object Ali Saidi 2005-03-10 02:01:43 -05:00
  • 51108a8c0a Merge ktlim@zizzer.eecs.umich.edu:/bk/m5 into zamp.eecs.umich.edu:/z/ktlim2/m5 Kevin Lim 2005-03-09 17:59:02 -05:00
  • 2897665685 Merge zizzer:/bk/m5 into zeep.eecs.umich.edu:/z/saidi/work/m5 Ali Saidi 2005-03-09 15:56:29 -05:00
  • 707a5ca06b Added new ping and memory latency stride 8 test Ali Saidi 2005-03-09 15:55:59 -05:00
  • 232134a816 Changed all syscalls to use syscall return object. Ali Saidi 2005-03-09 15:52:10 -05:00
  • 7d91bda6bf Add support for using the variables that m5 was compiled with for determining which parameters belong to a class. This allows us to remove the disable flag since it is not the correct model for variable checking anyway. Nathan Binkert 2005-03-09 14:42:30 -05:00
  • 4a3ad218e1 We should import m5config *after* we do the CPPDEFINES stuff, otherwise m5config and the object descriptions cannot take advantage of them. Nathan Binkert 2005-03-09 14:39:35 -05:00
  • ffaba200d1 Merge zizzer:/z/m5/Bitkeeper/m5 into zizzer.eecs.umich.edu:/.automount/zazzer/z/rdreslin/m5bk/timing_L1 Ron Dreslinski 2005-03-09 13:44:19 -05:00
  • 21946f0710 fix typo in the fixed etherlink serialization. Lisa Hsu 2005-03-09 11:04:19 -05:00
  • de540a4aee Fix tracediff to work with new parameter and output directory structure. Steve Reinhardt 2005-03-09 00:22:42 -05:00
  • dbd60761f5 Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/m5 into zizzer.eecs.umich.edu:/z/stever/bk/m5-head Steve Reinhardt 2005-03-09 00:17:20 -05:00
  • 4b69debac6 Fix a couple of bugs introduced (or tickled) by the .ini sorting change. Steve Reinhardt 2005-03-09 00:17:09 -05:00
  • d191b14ff7 Pass all scons defined pre-processor macro variables to the python configuration stuff as environment variables. Nathan Binkert 2005-03-08 23:06:54 -05:00
  • 689f6d1b02 Split the string importer from the rest of the mpy parsing and importing stuff to avoid some confusion. Nathan Binkert 2005-03-08 22:07:26 -05:00
  • 2162b433ad Hand-merge static_inst.hh. These execute functions are within an external file in the new CPU case. Kevin Lim 2005-03-08 21:03:20 -05:00
  • 550e6a5010 Merge zizzer:/bk/m5 into zed.eecs.umich.edu:/z/hsul/work/m5/pact05 Lisa Hsu 2005-03-08 17:38:08 -05:00
  • 91601f4494 make some changes to bonnie - now that the simulator uses more memory the old config didn't fit anymore in pools VM, this does fit. Lisa Hsu 2005-03-08 17:25:32 -05:00
  • e05788935b By default, we don't want to be sampling Nathan Binkert 2005-03-08 12:48:37 -05:00
  • b9c847563d Fix serialization of the EtherLink object Nathan Binkert 2005-03-08 12:47:55 -05:00
  • 47dec0f411 Fix the singalling from server to client so that the benchmark begins properly. Nathan Binkert 2005-03-08 12:37:08 -05:00
  • dedf16a6c6 Only try to import cpt.mpy if we need it. Nathan Binkert 2005-03-08 12:35:17 -05:00
  • 31d9d3bfe1 Merge zizzer:/bk/m5 into vm1.reinhardt.house:/z/stever/bk/m5 Steve Reinhardt 2005-03-07 20:56:17 -05:00
  • c720389366 More restructuring on Python config code for auto-generating of Param structs. Steve Reinhardt 2005-03-07 20:56:02 -05:00
  • a99607863f Merge zizzer:/z/m5/Bitkeeper/m5 into zizzer.eecs.umich.edu:/.automount/zazzer/z/rdreslin/m5bk/timing_L1 Ron Dreslinski 2005-03-07 18:04:49 -05:00
  • 2b89c38172 Make it easier to find a jobfile. Nathan Binkert 2005-03-07 13:05:41 -05:00
  • b290ecf1bb Merge zizzer:/z/m5/Bitkeeper/m5 into zizzer.eecs.umich.edu:/.automount/zazzer/z/rdreslin/m5bk/timing_L1 Ron Dreslinski 2005-03-07 10:58:15 -05:00
  • e5f945967b Sort fields in .ini files generated by Python config to make it easier to diff output from modified versions. Steve Reinhardt 2005-03-05 19:28:43 -05:00
  • 0804a7530f the client and server aren't rate-matched anymore and the timing of the netcats are off - add a sleep 1 to make it actually work. Lisa Hsu 2005-03-05 15:16:29 -05:00
  • 9f8d889f5f fix naming error - before we set CLIENT_MEMORY_SIZE and then when we wanted that value, used CLIENT_MEMSIZE! This caused the NFS failure I was seeing. Lisa Hsu 2005-03-03 11:43:20 -05:00
  • 59c041cc1f Make AddToPath and LoadMpyFile visible inside .mpy modules even though they're not in m5config anymore. Steve Reinhardt 2005-03-02 15:14:18 -05:00
  • 761d104f7b Merge zizzer:/bk/m5 into zeep.eecs.umich.edu:/z/saidi/work/m5 Ali Saidi 2005-03-02 00:53:23 -05:00
  • 50a4ed87d0 Two fixes to try and get TLB miss cost more in line with real platform: 1) Add fault_handler_delay param to FullCPU to wait N cycles after committing faulting instruction before fetching fault handler. 2) Make hw_rei a serializing instruction (flushes pipe, basically). Steve Reinhardt 2005-03-01 22:32:14 -05:00
  • d9de7c5783 add the new func unit into the overall list. Lisa Hsu 2005-03-01 16:59:42 -05:00
  • 6172f79d9e add some comments. Nathan Binkert 2005-03-01 11:07:44 -05:00
  • 0aa624b3f1 Add FUDesc for IprAccess Ali Saidi 2005-03-01 02:08:39 -05:00
  • 3d33abe63f Merge zizzer:/bk/m5 into zeep.eecs.umich.edu:/z/saidi/work/m5 Ali Saidi 2005-03-01 01:16:54 -05:00
  • 8268426f30 Updated Monet Configuration and validations tests Ali Saidi 2005-03-01 01:03:37 -05:00
  • ddcec6a6f5 Fix stats incompatibility with g++ 3.4. Steve Reinhardt 2005-03-01 00:41:19 -05:00
  • 58c29640b7 Add a new operation class for IPR accesses, and have IPR-accessing instructions use it (instead of IntALU, as before). Default config has a single non-pipelined 3-cycle unit. A bit conservative for the ev6 (some are 1, some are 3). Steve Reinhardt 2005-03-01 00:39:57 -05:00
  • 89dc94f3bc Make all StaticInst methods const. StaticInst objects represent a particular binary machine instruction and should be immutable after they are constructed. Steve Reinhardt 2005-02-25 21:44:33 -05:00
  • bb41c21d6a Merge ktlim@zizzer.eecs.umich.edu:/bk/m5 into zamp.eecs.umich.edu:/z/ktlim2/m5 Kevin Lim 2005-02-25 18:01:19 -05:00
  • 5c4714c1a9 Initial light-weight OoO CPU checkin, along with gcc-3.4 fixes. Kevin Lim 2005-02-25 18:00:49 -05:00
  • 45eb26e67c Merge zizzer:/z/m5/Bitkeeper/m5 into zizzer.eecs.umich.edu:/.automount/zazzer/z/rdreslin/m5bk/timing_L1 Ron Dreslinski 2005-02-25 15:12:05 -05:00
  • d697721f57 Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/m5 into zizzer.eecs.umich.edu:/z/stever/bk/m5 Steve Reinhardt 2005-02-25 14:49:39 -05:00
  • b5c788bf8a Merge zizzer:/z/m5/Bitkeeper/m5 into zizzer.eecs.umich.edu:/.automount/zazzer/z/rdreslin/m5bk/timing_L1 Ron Dreslinski 2005-02-25 14:39:55 -05:00
  • fbe2d26487 Make the SimConsole device dump its output to a file by default Nathan Binkert 2005-02-25 14:38:00 -05:00
  • 368882a847 Fix timing modeling of faults: functionally the very next instruction after a faulting instruction is the fault handler, which appears as an independent instruction to the timing model. New code will stall fetch and not fetch the fault handler as long as there's a faulting instruction in the pipeline (i.e., the faulting inst has to commit first). Steve Reinhardt 2005-02-25 12:41:08 -05:00
  • 107233adf1 Merge zizzer:/bk/m5 into zeep.eecs.umich.edu:/z/saidi/work/m5 Ali Saidi 2005-02-24 15:59:29 -05:00
  • fcf52e8543 if we have an invalid addr and it's not a miss-speculation panic Ali Saidi 2005-02-24 15:57:52 -05:00
  • 986ff12da1 Fix an error with Exclusive state and timing coherence Add more useful comments Add a missing header file Ron Dreslinski 2005-02-24 13:43:33 -05:00
  • e11e26872e Merge out, the L2 is now part of the system, not connected to the processor Ron Dreslinski 2005-02-24 12:08:57 -05:00
  • d5d41d696c Fix it so that using a sampler works with the occ and ocp configurations. Ron Dreslinski 2005-02-24 11:43:03 -05:00
  • 4de9689135 Print an error message if a Checkpoint number was defined, but no checkpoint file was sourced Ron Dreslinski 2005-02-24 11:34:58 -05:00
  • b78b634107 Fix the python panic message Nathan Binkert 2005-02-23 12:26:35 -05:00