a1033448ea
Inital split up of the header files for the new memory system. Still need to fill in some of the include files, and other data types. But this will be the starting point.
Ron Dreslinski
2006-01-31 12:12:49 -05:00
ad1e46203b
Make the M5 Emacs C style default to inserting spaces instead of tabs so using different editors is consistent
Nathan Binkert
2006-01-30 14:32:00 -05:00
0e79d188e1
Hacks to avoid compiling in old FullCPU model. Needed in the interim until we port the old model over to the new interface. Long term we should have a cleaner solution for controlling which models get compiled in.
Steve Reinhardt
2006-01-29 17:35:53 -05:00
07948528fc
Add PageTable code and SConscript fixes for new syscall emulation memory model. These changes really should have been part of the previous changeset.
Steve Reinhardt
2006-01-29 17:28:04 -05:00
8b783f8ad2
sparc files that were removed from revision 1.888
Korey Sewell
2006-01-29 17:25:54 -05:00
03a2aca9a9
Changes for Process object initialization in merged-memory environment. System object now exists for both fullsys and syscall emulation, as the latter needs it so that Process objects can find the shared PhysicalMemory for initialization. Changes are incomplete: still need to fix up Process (& EioProcess) memory initialization and syscall emulation code for new mem interface.
Steve Reinhardt
2006-01-28 00:08:22 -05:00
0162c52f17
bitfields definition to support current decoder.h
Korey Sewell
2006-01-26 17:07:01 -05:00
efc4620de1
decoder skeleton code: this should be able to read any MIPS instruction and decode it but NOT produce any C++ class object. All of the code literals are empty as of now. As much as possible instructions were organized into relevant "formats" and also references to the tables I used from the MIPS manual were noted via appropriate comments.
Korey Sewell
2006-01-26 01:34:43 -05:00
4be1f418bc
more changes to the decoder ... Now does special 3 table
Korey Sewell
2006-01-25 17:36:38 -05:00
14fc0996e3
first version of my decoder function skeleton - this will decode the instructions but not doing anything to create the C++ object yet (the 1st of many steps!)
Korey Sewell
2006-01-25 17:06:23 -05:00
90aa2dbfc2
initial changes to decoder.hh and copied files from arch/sparc directory
Korey Sewell
2006-01-25 14:43:47 -05:00
9df80550d4
added Request struct and updated Packet as per meeting 24/01/2006
Ali Saidi
2006-01-24 20:09:51 -05:00
89596f0cfa
Some stuff aparently didn't get committed which was from before the new repository was created.
Gabe Black
2006-01-24 19:57:17 -05:00
f383936348
Update interface from 1/17 meeting.
Steve Reinhardt
2006-01-17 17:47:53 -05:00
c4b2b2927d
Couple more interface additions.
Steve Reinhardt
2006-01-16 13:19:10 -05:00
79a4683876
Adding the sparc ISA files which were worked on locally
Gabe Black
2006-01-10 14:57:37 -05:00
0ecb25898d
More evolution of the new interface.
Steve Reinhardt
2005-12-23 16:31:01 -05:00
dce0c77ca2
Add ChunkGenerator object for breaking arbitrary regions into block- or page-sized chunks.
Steve Reinhardt
2005-12-23 14:06:27 -05:00
91192dbe97
Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/m5 into zizzer.eecs.umich.edu:/z/stever/bk/newmem
Steve Reinhardt
2005-12-23 13:51:12 -05:00
16bda9c03e
Fix roundUp function template so explicit arg is not needed in a few more cases.
Steve Reinhardt
2005-12-23 13:50:35 -05:00
0cdcb08d90
Change base/intmath.{cc,hh} to follow m5 style.
Steve Reinhardt
2005-12-23 13:32:31 -05:00
facbcf88fd
Merge zizzer.eecs.umich.edu:/bk/m5 into ziff.eecs.umich.edu:/z/binkertn/research/m5/newmem
Nathan Binkert
2005-12-23 01:48:15 -05:00
a32a66c065
Move the memory hierarchy to oldmem and leave an empty mem directory
Nathan Binkert
2005-12-23 01:44:06 -05:00
627f540e31
Updates to Memory system changes document.
Nathan Binkert
2005-12-23 01:39:53 -05:00
89d3cc8c94
Add a more refined stab at some of the new interface.
Steve Reinhardt
2005-12-22 22:00:24 -05:00
1a19923ead
Add notes from latest memory system redesign meetings.
Steve Reinhardt
2005-12-22 14:41:49 -05:00
3b35c698ec
Make ScsiController a PioDevice so it works again.
Nathan Binkert
2005-12-21 22:19:33 -05:00
45ecb2b69e
Create the ProxyError Exception. Raise it when an unproxy operation fails because information is wrong or not available.
Nathan Binkert
2005-12-19 02:07:06 -05:00
adf47c95b0
Add a little bit of support to grab info for making graphs without using the jobfile.
Nathan Binkert
2005-12-19 02:02:58 -05:00
a95fcf7df0
Make simulation termination message less threatening... maybe people won't think they're getting an error when they're not.
Steve Reinhardt
2005-12-06 20:00:50 -05:00
ffc32970f6
Two small fixes for mem_req's and Probe path with MOSI/MOESI
Ron Dreslinski
2005-12-01 18:47:36 -05:00
481219caf6
Add support for multiple streams being configured with the INITPARAM variable
Ali Saidi
2005-11-29 18:06:15 -05:00
108cfe53d6
Make the debugger a bit more useful with m5.opt by moving stuff from #ifdef DEBUG to #ifndef NDEBUG
Nathan Binkert
2005-11-28 18:33:48 -05:00
47ff0af17e
Virtualize sinic separate the rx thread and tx thread and get rid of the dedicated flag.
Nathan Binkert
2005-11-25 13:33:36 -05:00
60e92986f7
Add the capability to iterate through the packets in a pktfifo, and to remove elements in the middle of the fifo. These elements do not free space, they are just marked removed. Space is only freed from the front of the fifo.
Nathan Binkert
2005-11-25 11:22:41 -05:00
c0a4836077
Major improvements in the graph output code. Mostly adding more options, making existing options more visible and dealing with holes in data better.
Nathan Binkert
2005-11-22 21:50:34 -05:00
7819ca6b97
Change the set of statistics that are generated when specifying "all"
Nathan Binkert
2005-11-22 21:20:36 -05:00
634a0d8469
More changes from cpus named fullX to runX
Nathan Binkert
2005-11-22 21:18:11 -05:00
690399614c
Fix the system clock at 1THz making 1 simulation tick = 1 ps
Nathan Binkert
2005-11-22 21:08:47 -05:00
7584604fa9
make the NUMCPUS parameter always refer to the total number of cpus on the test system. add an option for pio_delay_write to run.py
Nathan Binkert
2005-11-22 21:05:02 -05:00
db2bf76755
Make sure that the aiobench client has enough memory. increase from 128MB to 512MB
Nathan Binkert
2005-11-22 13:36:30 -05:00
61f59f639c
Clean up the newly updated iscsi-client script
Nathan Binkert
2005-11-22 13:33:28 -05:00
6da93ea526
Apply patch for syscall emulation provided by Antti Miettinen (apm@brigitte.dna.fi). It provides support for more syscalls in syscall emulation mode.
Kevin Lim
2005-11-22 12:08:08 -05:00
fb3ae7264f
add the cpu number of the request to various panic and trace output for sinic
Nathan Binkert
2005-11-22 00:17:05 -05:00
f806a25c9e
add support for delaying pio writes until the cache access occurs
Nathan Binkert
2005-11-21 23:43:15 -05:00
50ee8c6461
expose an environment variable for setting the linux image.
Nathan Binkert
2005-11-21 22:25:30 -05:00
1182b487a6
Rearrange the memory configurations.
Nathan Binkert
2005-11-21 22:22:40 -05:00
2b76b41b90
have sinic use the new readBar/writeBar stuff that's in the pci device base class
Nathan Binkert
2005-11-21 21:52:04 -05:00
48863a1a43
Add a bunch of functions to manage the BAR addresses. This makes it easier to implement PCI device models.
Nathan Binkert
2005-11-21 00:38:53 -05:00
d3a4781ac5
Actually, you should'nt do math on Clock in the config files.
Nathan Binkert
2005-11-21 00:22:29 -05:00
c4678ece84
BARs now of type MemorySize32
Nathan Binkert
2005-11-21 00:02:39 -05:00
d733d168ca
Make it so one can do math with a Clock type in the config files
Nathan Binkert
2005-11-20 23:57:26 -05:00
3b8b838417
Allow long as a multiplier in the python config
Nathan Binkert
2005-11-20 23:45:45 -05:00
a102318412
Deal with divide by zero in the python stats stuff.
Nathan Binkert
2005-11-20 23:42:53 -05:00
67c276ed2e
implement __str__ for all of the proxy stuff so we can actually print out a statistic.
Nathan Binkert
2005-11-20 23:30:13 -05:00
d003c30a8c
fixup benchmark names a bit
Nathan Binkert
2005-11-20 18:49:54 -05:00
63bb46b6d8
Serialize the symbol tables
Nathan Binkert
2005-11-20 18:42:12 -05:00
4e393f38ec
get rid of allSymtab if we want something like allSymtab, we should create a symbol table proxy class
Nathan Binkert
2005-11-20 18:39:31 -05:00
64fc410ecb
switch all profiling stuff to the kernelSymtab since allSymtab is going away
Nathan Binkert
2005-11-20 18:33:59 -05:00
b62e7d24ec
clear the function profile on a stats reset
Nathan Binkert
2005-11-20 18:33:17 -05:00
9e8151f392
use Counter to avoid overflowing an int
Nathan Binkert
2005-11-20 18:32:22 -05:00
441c43d36c
Merge zizzer.eecs.umich.edu:/bk/m5 into ziff.eecs.umich.edu:/z/binkertn/research/m5/head
Nathan Binkert
2005-11-20 18:25:43 -05:00
0b1ed9c3a9
better placement of database commits better mysql error messages
Nathan Binkert
2005-11-20 18:25:31 -05:00
6e6422ab22
For SimpleCPU profiling code, only update the exec context's profileNode if we got a new one
Nathan Binkert
2005-11-20 17:55:11 -05:00
0dcb288365
Cleanup the StackTrace interfaces and profile interfaces so they are more efficient and reduce the number of new/delete calls
Nathan Binkert
2005-11-20 17:44:58 -05:00
f66ba90640
remove duplicate profile event code that is already in the BaseCPU class
Nathan Binkert
2005-11-20 17:28:57 -05:00
12d903a650
io_bus is split out into pio_bus and dma_bus so that any device can specify either independently.
Nathan Binkert
2005-11-20 16:57:53 -05:00
ccae5838fd
add symbol opcode
Ali Saidi
2005-11-19 01:25:34 -05:00
746841856c
Add checktrace.sh. Checks all the ethertrace files in */ethertrace for retransmissions, out of order packets, lost packets, duplicate ack, window full, etc. Easy way to see if you have a problem with a run.
Ali Saidi
2005-11-11 18:43:09 -05:00
60480de7c3
Update random come to always have explict min/max
Ali Saidi
2005-11-11 18:41:45 -05:00
4410876773
Actually free Process fd_map entries when a file is closed... amazingly we never did that before. Caused us to run out of file descriptors in twolf.
Steve Reinhardt
2005-11-10 21:08:33 -05:00
99bf6ed084
Syscall DPRINTF and warning cleanup.
Steve Reinhardt
2005-11-10 21:05:31 -05:00
d727c2b6cf
Fix Lisa's CPU trace system check for syscall emulation.
Steve Reinhardt
2005-11-10 20:30:04 -05:00
3532a661c5
just commit what i need for dumping traces compatible with intel's casper
Lisa Hsu
2005-11-09 16:42:36 -05:00
6e192b5704
Merge zizzer:/bk/m5 into zed.eecs.umich.edu:/z/hsul/work/m5/intel
Lisa Hsu
2005-11-09 16:40:51 -05:00
b018a01f0c
new rcS file for open-iscsi rather than the old linux-iscsi
Lisa Hsu
2005-11-09 16:40:27 -05:00
e701cf48d9
A couple of FP-related fixes (prompted by Adam having trouble running SPEC FP codes).
Steve Reinhardt
2005-11-09 09:52:07 -05:00
902e27e692
Qdo should kill its subordinate qsub more aggressively on a timeout.
Steve Reinhardt
2005-11-03 13:14:28 -05:00
d9f94e966b
Check for MySQL 4.1 or newer only (3.23 does not work as we supposed it did).
Steve Reinhardt
2005-11-03 13:13:31 -05:00
cb929af345
allow conversion floats -> long so that 100e9 and such work as Ticks
Ali Saidi
2005-11-02 15:37:47 -05:00
f0ee50c32f
Don't call Random.uniform() unnecessarily
Ali Saidi
2005-11-02 15:29:08 -05:00
36f134786f
I left a printf in on accident.
Ali Saidi
2005-11-02 15:23:21 -05:00
d69bcc6492
Changes to integer types broke this... Oops.
Ali Saidi
2005-11-02 15:22:09 -05:00
3b66cb49ec
Merge zizzer:/bk/m5 into zeep.eecs.umich.edu:/z/saidi/work/m5
Ali Saidi
2005-11-02 14:56:18 -05:00
0523736b96
Change the output of stability info a little bit
Ali Saidi
2005-11-02 14:55:05 -05:00
4b6540c264
add a few more options to the help menu
Ali Saidi
2005-11-02 14:54:21 -05:00
f36b854ca5
Don't bother putting distributions in the DB, they aren't really supported.
Ali Saidi
2005-11-02 14:48:49 -05:00
07ef1170e0
Add ability to slightly perturb latency of ethernet/memory
Ali Saidi
2005-11-02 14:47:37 -05:00
0b3c27f149
Fix bug where simulation terminates same cycle as last stat dump causing a duplicate row in db
Ali Saidi
2005-11-02 14:45:35 -05:00
Ron Dreslinski