Commit Graph

  • b937d54510 Fix compile of m5.fast Nathan Binkert 2006-10-19 23:34:59 -07:00
  • 0d2908a584 Delete unused file src/mem/cache.hh Steve Reinhardt 2006-10-19 22:59:38 -07:00
  • 3772e4fc97 m5term: assume localhost if host name not provided. Steve Reinhardt 2006-10-19 21:42:30 -07:00
  • 780aa0a0eb Fix corner case on assertion. I need to move over to using the fixPacket function so I don't have to make the same changes everywhere. Still a functional access bug someplace I need to track down in timing mode. Ron Dreslinski 2006-10-19 21:26:46 -04:00
  • cc1feb9f6d Fix memtester to use functional access, fix cache to work functionally now that we could test it. Ron Dreslinski 2006-10-19 21:07:53 -04:00
  • 210e73f2a2 Small changes: ?? doesn't compile in warn statements Should have been false, where I had a true. Ron Dreslinski 2006-10-19 20:18:17 -04:00
  • e34e564f79 Fixes to get single level uni-coherence to work. Now to try L2 caches in FS. Ron Dreslinski 2006-10-19 20:02:57 -04:00
  • 9cf063eb8e Merge zizzer:/bk/newmem into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest Ron Dreslinski 2006-10-19 19:00:43 -04:00
  • 39d24f7241 Always get the functional access from the highest level of cache first. Ron Dreslinski 2006-10-19 19:00:27 -04:00
  • bf917535f8 Also mark the packet as successful. Ron Dreslinski 2006-10-19 18:29:42 -04:00
  • 76c07ea46b Cleaned up the function a bit to help route out bugs. Gabe Black 2006-10-19 14:57:06 -04:00
  • 50f5ba5d96 Properly update the state in the cache block on functional access. Mark as satisfied for functional snoops. Ron Dreslinski 2006-10-19 14:55:54 -04:00
  • 11f0badbaa Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/newmem into zizzer.eecs.umich.edu:/z/stever/bk/newmem-head Steve Reinhardt 2006-10-19 13:33:08 -04:00
  • a78e92381b Add "All" compund flag to enable all defined trace flags. Steve Reinhardt 2006-10-19 10:32:08 -07:00
  • e78684fc6c Add new event priority for trace enable events so that tracing gets turned on as the very first thing in the selected cycle (tick). Steve Reinhardt 2006-10-19 10:21:23 -07:00
  • bba3dfb0d3 First cut at LL/SC support in caches (atomic mode only). Steve Reinhardt 2006-10-19 00:33:33 -07:00
  • 54c9701a25 Zeroed out the actual LSB in addition to moving it's original value the MSB. Gabe Black 2006-10-18 20:53:59 -04:00
  • bb2ab310eb Fixed up exetrace.cc to deal with microcode, and to made floating point register numbers correlate to the numbers used in SPARC in m5 and statetrace. Gabe Black 2006-10-18 20:52:34 -04:00
  • 849d5e2efb Fixed a compiler error, disassembly output, and corrected the address calculation. Gabe Black 2006-10-18 20:48:08 -04:00
  • 94926a72e9 Fixed up ldblockf_p, implemented stdfa properly, and got rid of some old code. Gabe Black 2006-10-18 20:44:51 -04:00
  • 75ecd3be60 how did i not commit this already? the other way doesn't seem to work, need to convert to System ptr first to access System method. Lisa Hsu 2006-10-18 18:04:53 -04:00
  • 15770fb7b4 need some initializations before doing the loop. Lisa Hsu 2006-10-18 18:01:33 -04:00
  • c2c48645c9 only do this assert after you know you're not switched out or idle. Lisa Hsu 2006-10-18 17:59:11 -04:00
  • 5bcdc74fe2 Fix WriteInvalidateResp Ron Dreslinski 2006-10-18 16:38:02 -04:00
  • 63c2a782d6 Merge zizzer:/bk/newmem into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest Ron Dreslinski 2006-10-18 13:34:52 -04:00
  • 0e2561710b Break a lot of overly long lines. Factor out some asserts that were on both sides of an if/else. Steve Reinhardt 2006-10-18 08:41:05 -07:00
  • caf123586f Get rid of doData() lines (were already commented out). Reindent due to resulting changes in nesting. Steve Reinhardt 2006-10-18 08:24:24 -07:00
  • 6cd187e1f0 Get rid of obsolete in-cache copy support. Steve Reinhardt 2006-10-18 08:16:22 -07:00
  • 0128b73d05 Add --caches option to add caches to server CPUs. Steve Reinhardt 2006-10-17 23:30:11 -07:00
  • f735399b39 Include packet_impl.hh (need this on my laptop, but not on zizzer... g++ 4 thing maybe?) Steve Reinhardt 2006-10-17 21:16:17 -07:00
  • 05c487ef3c Enable MP systems via cmd-line flag in fs.py. Steve Reinhardt 2006-10-17 21:15:11 -07:00
  • e51b075a27 add code to serialize se structures. Lisa is working on the python side of things and will test Ali Saidi 2006-10-17 19:38:36 -04:00
  • 9c582c7e14 Fixes for uni-coherence in timing mode for FS. Still a bug in atomic uni-coherence in FS. Ron Dreslinski 2006-10-17 18:50:19 -04:00
  • 4fff6d4603 Fixes to cache eliminating the assumption that the Packet is still valid after sending out a request. Still need to rework upgrades into this system, but works for now. Ron Dreslinski 2006-10-17 16:47:22 -04:00
  • 6e8bfa4e63 Properly chack the pkt pointer on upgrades to insure no segfaults when writebacks delete the packet. Ron Dreslinski 2006-10-17 15:07:40 -04:00
  • 288b98eb69 Fix it so that the cache does not assume to gave the packet it sent out via sendTiming. Still need to fix upgrades to use this path Ron Dreslinski 2006-10-17 15:05:21 -04:00
  • db6cc97e31 Merge zizzer:/bk/newmem into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest Ron Dreslinski 2006-10-17 14:28:17 -04:00
  • 96737c8a9b Rename 'Machine' to 'SysConfig'. Clean up a little. Steve Reinhardt 2006-10-17 11:08:49 -07:00
  • 685e588b45 Merge zizzer:/bk/newmem into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest Ron Dreslinski 2006-10-17 14:05:23 -04:00
  • b55271aee9 Corrected the "Authors" line Gabe Black 2006-10-16 15:59:48 -04:00
  • 519d11bab3 Merge zizzer.eecs.umich.edu:/bk/newmem into zeep.eecs.umich.edu:/home/gblack/m5/newmem Gabe Black 2006-10-16 15:56:53 -04:00
  • f1661baf30 Fix up microcode support. Gabe Black 2006-10-16 15:56:46 -04:00
  • 7fefa2a621 Changed how floating point register numbers are decoded to fit with the spec. Gabe Black 2006-10-16 15:53:48 -04:00
  • 546dff6b6a Made sure the constructor for insts use ExtMachInst rather than MachInst, since otherwise the EXT_ASI field is lost. Gabe Black 2006-10-16 15:52:14 -04:00
  • 67794ace5c Added in missing portions of the stat structure copying function. Gabe Black 2006-10-15 21:54:59 -04:00
  • 333a7c4ba2 Started implementing microcode. Gabe Black 2006-10-15 21:04:14 -04:00
  • dc7d9af582 Added an execute function to the macro op so it can be instantiated. Gabe Black 2006-10-15 20:54:35 -04:00
  • 7009d0e523 Fix how additional template parameters are handled. Non string parameters are not processed as code. Gabe Black 2006-10-15 20:37:28 -04:00
  • 9202422d6e Get rid of unused CacheBlk << output operator. Steve Reinhardt 2006-10-14 02:09:05 -04:00
  • c2a6550366 Merge 141.212.106.238:/home/gblack/m5/newmem_bus into zizzer.eecs.umich.edu:/.automount/wexford/x/gblack/m5/newmem_bus Gabe Black 2006-10-13 19:09:46 -04:00
  • d83ccdfe5d Fix stats for new bus model Gabe Black 2006-10-13 18:59:29 -04:00
  • a50e83c134 Fix assertion. I haven't tested it fully (I can't reproduce Lisa's error) but I believe it should fix what she's running into (which was definitely a bug). Kevin Lim 2006-10-13 17:35:23 -04:00
  • 1871495b8d Merge zizzer:/bk/newmem into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest Ron Dreslinski 2006-10-13 15:47:35 -04:00
  • a17afb1649 Fix for DMA's in FS caches. Fix CSHR's for flow control. Fix for Bus Bridges reusing packets (clean flags up) Ron Dreslinski 2006-10-13 15:47:05 -04:00
  • ca4063ac00 fix a bug in CopyStringOut. dprintk appears to work again. Ali Saidi 2006-10-13 14:28:46 -04:00
  • 339b1f8516 Merge zizzer:/bk/newmem into zed.eecs.umich.edu:/z/hsul/work/m5/newmem Lisa Hsu 2006-10-12 18:56:57 -04:00
  • 92fd211a07 Changed the sign extension function from mine to the provided one. Mine relied on implementation specific behavior, namely right shifting a signed value. Gabe Black 2006-10-12 17:39:15 -04:00
  • 98b00d92fd Some support for handling block loads and stores and ASIs properly. Gabe Black 2006-10-12 17:38:06 -04:00
  • 866dda9778 StaticInst support for microcode Gabe Black 2006-10-12 17:32:02 -04:00
  • 6943c731ea The beginnings of an instruction format to deal with block loads and stores. This takes advantage of microcode. Gabe Black 2006-10-12 17:30:25 -04:00
  • b2d9c65db7 Some support for macro/micro instructions in SPARC. Gabe Black 2006-10-12 17:29:28 -04:00
  • dd217a9d3f Support for returning unimplemented instruction in the decoder, lifted from Alpha Gabe Black 2006-10-12 17:27:06 -04:00
  • 3d2764acf3 replace functional code in tport with fixPacket(). fixPacket() should be used anywhere a functional packet and timing packet are found to have the same address. Ali Saidi 2006-10-12 15:30:30 -04:00
  • e11c0d380a Merge zizzer:/bk/newmem into zooks.eecs.umich.edu:/y/ksewell/research/m5-sim/cleanrepo Korey Sewell 2006-10-12 15:05:29 -04:00
  • 790e746bd9 config file updates Korey Sewell 2006-10-12 15:04:14 -04:00
  • eddbb6801f Fix CSHR retrys Ron Dreslinski 2006-10-12 15:02:56 -04:00
  • 4a96779350 Merge zizzer:/bk/newmem into zeep.pool:/z/saidi/work/m5.newmem.head Ali Saidi 2006-10-12 15:02:50 -04:00
  • 0615d92d33 small bus updates for functional accesses Ali Saidi 2006-10-12 15:02:25 -04:00
  • 1ebe4b0dec Merge zizzer:/bk/newmem into zooks.eecs.umich.edu:/y/ksewell/research/m5-sim/cleanrepo Korey Sewell 2006-10-12 14:36:41 -04:00
  • 665901de8a Add test binary & inputs Korey Sewell 2006-10-12 14:36:21 -04:00
  • 3aaa3456dc Merge zizzer:/bk/newmem into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest Ron Dreslinski 2006-10-12 14:31:31 -04:00
  • fe230ddb8f Remove bus and top level parameters from cache Ron Dreslinski 2006-10-12 14:21:25 -04:00
  • 2c9d506f46 Merge zizzer:/bk/newmem into zeep.pool:/z/saidi/work/m5.newmem.head Ali Saidi 2006-10-12 14:18:42 -04:00
  • 3ba2ed6aef add a traceflag for functional accesses implement fix packet and add the ability to print a packet to a ostream remove tabs in packet.hh (Could people stop inserting them??!?!?!) mark const functions in packet.hh as such Ali Saidi 2006-10-12 14:15:09 -04:00
  • f89b56b61a Check the response queue on functional accesses. The response queue is not tying up an MSHR, should we change that or assume infinite storage for responses? Ron Dreslinski 2006-10-12 13:59:03 -04:00
  • 6ffdc7b4d7 Another memleak in the memtester (need [] with the delete) Ron Dreslinski 2006-10-12 13:45:28 -04:00
  • dd18ffe51d Fix a memory leak in the memtester Ron Dreslinski 2006-10-12 13:43:12 -04:00
  • ba4c224c39 Fix problems with unCacheable addresses in timing-coherence Ron Dreslinski 2006-10-12 13:33:21 -04:00
  • 866cfaf9dc Merge zizzer.eecs.umich.edu:/bk/newmem into zeep.eecs.umich.edu:/home/gblack/m5/newmem Gabe Black 2006-10-12 10:58:45 -04:00
  • 78aec04b66 Merge zizzer:/bk/newmem into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest Ron Dreslinski 2006-10-11 21:04:11 -04:00
  • 388d484269 Make default ID unique (not broadcast) Fix a segfault associated with DefaultId Ron Dreslinski 2006-10-11 20:54:06 -04:00
  • 14c8e8b227 Forgot to mark myself as on the retry list Ron Dreslinski 2006-10-11 19:47:11 -04:00
  • 652a09a512 add spec2k tests Korey Sewell 2006-10-11 19:26:56 -04:00
  • 3c7e0ec752 Fix bus in FS mode. Ron Dreslinski 2006-10-11 19:25:48 -04:00
  • 7442bd2664 add bzip test-prog Korey Sewell 2006-10-11 19:07:10 -04:00
  • ba795552f5 System not global object, need to preface it with objects. Lisa Hsu 2006-10-11 18:54:31 -04:00
  • 8acecfef9b since memoryMode was put into the System (from SimObject), things got broken - this fixes it so that changeToTiming/changeToAtomic works. Lisa Hsu 2006-10-11 18:53:50 -04:00
  • 024b33a1ef some drain changes in timing (kevin's) and some memory mode assertion changes so that when you come out of resume, you only assert if you're really wrong. Lisa Hsu 2006-10-11 18:44:48 -04:00
  • 567afbf6ce More cache fixes. Atomic coherence now works as well. Ron Dreslinski 2006-10-11 18:28:33 -04:00
  • 03c42ea590 Update for Atomic Coherece with Gabes bus Ron Dreslinski 2006-10-11 01:59:38 -04:00
  • 60252f8e63 Interesting memtest finally. Get over 500,000 reads on each of 8 testers before memory leak becomes large. Ron Dreslinski 2006-10-11 01:18:20 -04:00
  • 4e35c5656f Merge zizzer:/n/wexford/x/gblack/m5/newmem_bus into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest Ron Dreslinski 2006-10-11 01:02:18 -04:00
  • c2012601e9 Use bus response time paramteres Fix bug with deadlocking Ron Dreslinski 2006-10-11 01:01:40 -04:00
  • 7767f5af73 Don't call recvRetry if the bus is busy anyway. This takes care of a corner case as well when dealing with grants that aren't used. Gabe Black 2006-10-11 00:54:47 -04:00
  • 07dad71f6f Merge zizzer:/n/wexford/x/gblack/m5/newmem_bus into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest Ron Dreslinski 2006-10-11 00:31:40 -04:00
  • a139e4394d Make the bus work if the other sides recvRetry doesn't call sendTiming for some reason. Gabe Black 2006-10-11 00:26:21 -04:00
  • 04f71f1226 When turning asserts into if's don't forget to invert. Ron Dreslinski 2006-10-11 00:19:31 -04:00
  • 23bbd14426 Writebacks can be pulled out from under the BusRequest when snoops of uprgades to owned blocks hit in the WB buffer Ron Dreslinski 2006-10-11 00:13:53 -04:00
  • c9102b08fa Only issue responses if we aren;t already blocked Ron Dreslinski 2006-10-10 23:53:10 -04:00
  • ca694ca7b1 Merge zizzer:/n/wexford/x/gblack/m5/newmem_bus into zazzer.eecs.umich.edu:/z/rdreslin/m5bk/newmemcleanest Ron Dreslinski 2006-10-10 23:37:14 -04:00