Commit graph

2554 commits

Author SHA1 Message Date
Ron Dreslinski
9e39454f58 Make the .mpy file a .py file and convert it to the form recognized now.
--HG--
extra : convert_revision : 1019fd1e2bb484e1ea8f15db8dbe8e7a0201bd58
2006-03-28 14:58:23 -05:00
Ron Dreslinski
cdd861084a Add the detailed DRAM model into M5. See the /mem/timing/DRAM_M5.txt for discussion on setting paramaters.
SConscript:
    Add support for detailed DRAM model

--HG--
extra : convert_revision : b65f9a810fa95957b585c85632ac20f9283337d1
2006-03-27 15:06:16 -05:00
Ali Saidi
c27c122afc Add the bus and connector objects to scons
change getPort parameter from char* to string
Add an extra phase between construction and init called connect

SConscript:
    Add the bus and connector objects to scons
cpu/simple/cpu.cc:
cpu/simple/cpu.hh:
    the connection to memory shouldn't be made until we know the memory
    object exists (e.g. after construction)
dev/io_device.hh:
    change to const string
mem/bus.hh:
    change getPort parameter from char* to string
    initialize num_interfaces
mem/mem_object.hh:
    change getPort parameter from char* to string
mem/physical.cc:
mem/physical.hh:
    change getPort parameter from char* to string
    get rid of the bus object I created last time
python/m5/objects/PhysicalMemory.py:
    get rid of the bus object I created last time
sim/main.cc:
sim/sim_object.cc:
sim/sim_object.hh:
    Add an extra phase between construction and init called connect

--HG--
extra : convert_revision : 0e994f93374fa72a06d291655c440ff1b8e155a9
2006-03-26 21:44:22 -05:00
Ali Saidi
4973a16b34 update for objects having a bus
--HG--
extra : convert_revision : 96b5494b7d0b5ca702ac69cfa0bf8c4d44e1cc3b
2006-03-25 18:34:50 -05:00
Ali Saidi
b38f67d5b7 Implement a very very simple bus
requestTime -> time
responseTime -> packet.time

Make CPU and memory able to connect to the bus

dev/io_device.cc:
    update for request and packet both having a time
    hand platform off to port for eventual selection of request modes
dev/io_device.hh:
    update for request and packet both havig a time
    hand platform off to port for eventual selection of request modes
mem/bus.hh:
    Add a device map struct that maps a range to a portId
    - Which needs work it theory it should be an interval tree
    - but it is a list and works fine right now

    Add a function called findPort which returns port for an addr range

    Add a deviceBlockSize function that really shouldn't exist, but it
    was easier than fixing the translating port
mem/packet.hh:
    add a time to each packet
mem/physical.cc:
mem/physical.hh:
python/m5/objects/PhysicalMemory.py:
    Make physical memory take a MemObject parameter of what to connect to
mem/request.hh:
    remove requestTime/responseTime for just time in request which
    is requset time and the time in the packet which is responsetime
python/m5/objects/BaseCPU.py:
    Instead of memory cpu connects to any memory object
python/m5/objects/Bus.py:
    Fix for new bus object

--HG--
extra : convert_revision : 72605e8a3fcdd9e80a41f439909ee7feb3f1fe1d
2006-03-25 18:31:20 -05:00
Ron Dreslinski
b96405b7e4 Add support in the fullsys script to run the POVray benchmark.
To run it use
-ETEST=POVRAY_BENCH   to run the built in povray benchmark program (more CPU intensive, small fileset ~11MB)
-ETEST=POVRAY_AUTUMN  to run the first part of a rendering of a autumn leaves/tree scene, less cpu intensive ~500MB working set.

For now I have been running with -ESYSTEM=Simple in order to drop checkpoints (built into binary at the point the render begins) and create memory traces.
I will check in a SYSTEM=3D_DRAM and SYSTEM=3D_CACHE configuration as soon as those are ready.

--HG--
extra : convert_revision : fb55834a02317d5e9961a5145c932965c8bc6a0e
2006-03-23 18:05:39 -05:00
Ali Saidi
a70ce910f3 Merge zizzer:/bk/newmem
into  zeep.eecs.umich.edu:/z/saidi/work/m5.newmem

--HG--
extra : convert_revision : 45dba22ecbdfc8e1bb0df1efd06a37f40d56b67f
2006-03-21 15:45:40 -05:00
Ali Saidi
8654cfa427 Make PioPort/DmaPort,DmaDevice/PioDevice compile.
Add another type to the PacketResult enum of Unknown
Seperate time into requsetTime and responseTime.

dev/io_device.cc:
dev/io_device.hh:
    Make PioPort/DmaPort,DmaDevice/PioDevice compile.
mem/packet.hh:
    Add another type to the PacketResult enum of Unknown (e.g. no state set yet)
mem/request.hh:
    Seperate time into requsetTime and responseTime.

--HG--
extra : convert_revision : c6394cb838013296caea6492275252b8cae2882f
2006-03-21 15:45:31 -05:00
Korey Sewell
b855ea6968 Merge zizzer:/bk/newmem
into  zazzer.eecs.umich.edu:/.automount/zooks/y/ksewell/research/m5-sim/newmem-mips

--HG--
extra : convert_revision : db8490e41ec17fc8f4e2dc9548ecdc7d28b4cdd1
2006-03-19 13:41:04 -05:00
Korey Sewell
b3464ef180 support for unaligned memory access
arch/mips/isa/base.isa:
    disassembly fixes
arch/mips/isa/decoder.isa:
    support for unaligned loads/stores
arch/mips/isa_traits.hh:
    edit Syscall Reg values
arch/mips/linux_process.cc:
    call writevFunc on writev syscall

--HG--
extra : convert_revision : 4aea6d069bd7ba0e83b23d2d85c50d68532f0454
2006-03-19 13:40:03 -05:00
Steve Reinhardt
c1006e429d Merge zizzer.eecs.umich.edu:/z/m5/Bitkeeper/m5
into  zizzer.eecs.umich.edu:/z/stever/bk/newmem-head

sim/process.cc:
    Fix bad auto merge (m5 changes unnecessary in newmem).

--HG--
extra : convert_revision : a3ced4cd1668cd47bd02430872ca68b1433aae98
2006-03-18 14:42:21 -05:00
Korey Sewell
e6bc492554 more syscall fixes
arch/mips/isa_traits.hh:
    use syscall return function from alpha
arch/mips/linux_process.cc:
    fix some syntax errors,  map some functions to the desc. table

--HG--
extra : convert_revision : 75e8e8893b7d96bb4fc8e8eced53bd16c0a727d1
2006-03-18 11:31:31 -05:00
Korey Sewell
3883406a1c Merge zizzer:/bk/newmem
into  zazzer.eecs.umich.edu:/.automount/zooks/y/ksewell/research/m5-sim/newmem-mips

--HG--
extra : convert_revision : 1646b4fb065e3ed9d8de22e3f5c3aa05a2ef01b6
2006-03-18 10:52:19 -05:00
Korey Sewell
8ddd509c7c steps toward making syscalls work
arch/mips/isa/decoder.isa:
arch/mips/isa_traits.hh:
sim/syscall_emul.cc:
    make syscall instruction functional
arch/mips/linux_process.cc:
    add all MIPS/Linux syscalls to descriptor list

--HG--
extra : convert_revision : 5455a345e76be921e9f63b248aef874b6358e465
2006-03-18 10:51:28 -05:00
Gabe Black
5c6835ae3f Fixed a couple typos
--HG--
extra : convert_revision : 2ffbfc4755e46a119c9709d6a5e9ddc41fde45e0
2006-03-17 14:25:54 -05:00
Gabe Black
cf2f7e13bc Merge m5.eecs.umich.edu:/bk/newmem
into  ewok.(none):/home/gblack/m5/newmem

arch/sparc/isa/decoder.isa:
    Hand merged

--HG--
extra : convert_revision : 5d5338602c48be48978972a091c5e93f9dd775aa
2006-03-17 14:23:48 -05:00
Gabe Black
c1a1f8ee95 An attempt to get byteswap to work accross more machines.
--HG--
extra : convert_revision : 4a73507206cf287a89e1d496b2a08cfd1fafdf4d
2006-03-17 14:11:14 -05:00
Gabe Black
4f9ead58ff Clean up and fix for compilation
--HG--
extra : convert_revision : c4e66cd678313f7fe169787cb1bf3e45f114c4fd
2006-03-17 14:02:38 -05:00
Ali Saidi
cf94242539 clean up condition codes a little bit
put back in Tcc code that was deleted in last merge

arch/sparc/isa/bitfields.isa:
    clean up condition codes a little bit

--HG--
extra : convert_revision : c554fd5c3ee8cfd6643f69f8351124a7a4b5d9fa
2006-03-16 23:09:01 -05:00
Korey Sewell
fc5d25bdb6 fix to LiveProcess (this change got deleted somehow)
--HG--
extra : convert_revision : fe4b7dc5b7d583e1d890648ba98bb0daf722a704
2006-03-16 19:01:09 -05:00
Korey Sewell
1db74514c2 Merge zizzer:/bk/newmem
into  zazzer.eecs.umich.edu:/.automount/zooks/y/ksewell/research/m5-sim/newmem-mips

--HG--
extra : convert_revision : 02fe0b0170348dc6f6a985c15123806088a8c23e
2006-03-16 18:40:54 -05:00
Korey Sewell
805b9cf1d5 Found and fixed 3 decoder.isa bugs!!! Now the hello_world program runs for a while
before getting in a infinite loop. It actually "tries" to syscall too, but syscalls
aren't implemented just yet

arch/mips/faults.cc:
    more descriptive names for faults (will help future users as well as me!)
arch/mips/isa/base.isa:
    make sure we are printing out "BasicOp" format disassembly instructions as dest,src,src instead of src,src,dest
arch/mips/isa/decoder.isa:
    FIX LW/SW Bug!!!! I was actually loading a byte instead of a word
    FIX JALR Bug!!!! I was not saving the link address in R31 for this instruction
    FIX SLL/NOP Bug!!! We now recognize the varying flavors of sll,nop,ehb,& ssnop correctly
base/loader/elf_object.cc:
    change back to original way
base/loader/elf_object.hh:
    change back to original!

--HG--
extra : convert_revision : 39b65fba31c1842ac6966346fe8a35816a4231fa
2006-03-16 18:39:54 -05:00
Gabe Black
1d741c48af Merge m5.eecs.umich.edu:/bk/newmem
into  ewok.(none):/home/gblack/m5/newmem

arch/sparc/isa/decoder.isa:
    SCCS merged

--HG--
extra : convert_revision : 460843b49bc96b3fbc5897828c23f9cf9b010ae0
2006-03-16 14:08:31 -05:00
Gabe Black
558cc7f775 Fixups towards compiling.
arch/alpha/types.hh:
    Moved the DependenceTags enum from types to constants.
arch/sparc/faults.cc:
arch/sparc/faults.hh:
    Corrected a misspelling of PriviledgeOpcode and PrivilegedAction.
arch/sparc/isa/formats.isa:
    Fixups towards compiling. Added a few additional instruction formats.

--HG--
extra : convert_revision : 4c5506877b71b8a5c8c45db41192cf759cdac374
2006-03-16 13:58:50 -05:00
Ron Dreslinski
73b0fbc3e1 Don't forget to check in the needed header file for the conditional prefetch building.
--HG--
extra : convert_revision : 2c2562da323fa1249af72af3a89c7666c745ae2b
2006-03-16 11:34:19 -05:00
Steve Reinhardt
31a20c88c5 Add warning for ignored loadable ELF segments.
base/loader/elf_object.cc:
    Print warning if there are more than two loadable segments.
    We currently assume there are at most two (text & data), and that's
    held so far, but it would be nice not to silently ignore others.

--HG--
extra : convert_revision : 1b3e693e95ba1210b09528b97819a7fa86426edc
2006-03-16 10:31:00 -05:00
Korey Sewell
77a2f97c35 Merge zizzer:/bk/newmem
into  zazzer.eecs.umich.edu:/.automount/zooks/y/ksewell/research/m5-sim/newmem-mips

--HG--
extra : convert_revision : 9bdde9b5bd3049744451eda1134f080b7c4b1b59
2006-03-15 23:38:55 -05:00
Ali Saidi
7359e2df01 implement the Tcc instruction to call syscall.
arch/sparc/isa/bitfields.isa:
    the trap field is 7:0
arch/sparc/isa/decoder.isa:
    add code to in the Tcc instruction to call a syscall
arch/sparc/isa_traits.hh:
    We need the syscall num register

--HG--
extra : convert_revision : 0861ec1dd8c7cac57765b22bc408fdffbe63fe2a
2006-03-15 18:12:01 -05:00
Ron Dreslinski
beff73f1fa Merge zizzer:/z/m5/Bitkeeper/m5
into  zazzer.eecs.umich.edu:/z/rdreslin/m5bk/m5

--HG--
extra : convert_revision : a4de274ec50821218121ba38f9215f2348262c27
2006-03-15 17:53:49 -05:00
Ron Dreslinski
52cc2d5bad Add support for conditional compiling in of prefetchers.
--HG--
extra : convert_revision : 357554632f102224357c8c3848bc4bc7cbb9dc54
2006-03-15 17:53:21 -05:00
Ali Saidi
97e424982a add translations for new sections that are mmapped or when the brk
is changed
Add a default machine width parameter
Arch based live processes

arch/alpha/linux/process.cc:
arch/alpha/linux/process.hh:
arch/alpha/process.cc:
arch/alpha/process.hh:
arch/alpha/tru64/process.cc:
arch/alpha/tru64/process.hh:
arch/mips/linux_process.cc:
arch/mips/process.cc:
arch/mips/process.hh:
arch/sparc/linux/process.cc:
arch/sparc/linux/process.hh:
arch/sparc/process.cc:
arch/sparc/process.hh:
configs/test/test.py:
python/m5/objects/Process.py:
sim/process.cc:
sim/process.hh:
    Architecture based live processes
arch/mips/isa_traits.hh:
arch/sparc/isa_traits.hh:
    Add a default machine width parameter
mem/port.hh:
    gcc 4 really wants  a virtual destructor
sim/byteswap.hh:
    remove the comment around long and unsigned long even though uint32_t
    and int32_t are defined. Seems to work with gcc 4 and 3.4.3.
sim/syscall_emul.cc:
sim/syscall_emul.hh:
    add translations for new sections that are mmapped or when the brk
    is changed

--HG--
extra : convert_revision : e2f9f228113c7127c87ef2358209a399c30ed5c6
2006-03-15 17:04:50 -05:00
Korey Sewell
e2b558112b add mips simple test in config directory
configs/test/hello_mips:
    hello world mips binary

--HG--
extra : convert_revision : 5a495e1bfb1cbddc0879f8e80c02bd7435a02acb
2006-03-15 16:29:18 -05:00
Korey Sewell
c32b4ecac1 infinitesimal small baby steps toward MIPS actually working
arch/mips/isa/formats/branch.isa:
    let user know that we alter r31 in disassembly
arch/mips/isa_traits.cc:
    add copyRegs function ...
    comment out serialize float code for now
arch/mips/isa_traits.hh:
    make FloatRegFile a class ... change values of architectural regs
arch/mips/process.cc:
    change MIPS to Mips
base/loader/elf_object.cc:
    get global pointer initialized to a value
base/loader/elf_object.hh:
    Add global_ptr to elf_object constructor
base/loader/object_file.hh:
    MIPS to Mips
base/traceflags.py:
    SimpleCPU trace flag
cpu/simple/cpu.cc:
    DPRINTF flags for SimpleCPU
cpu/static_inst.hh:
    Add Decoder functions to static_inst.hh

--HG--
extra : convert_revision : 0544a8524d3fe4229428cb06822f7da208c72459
2006-03-15 16:26:40 -05:00
Kevin Lim
dc75cf121c Don't access init_regs directly. This does not affect newmem; Steve already changed this in newmem.
--HG--
extra : convert_revision : 19b1ed0bb2c8bcde72843e62f73635e84adf95b5
2006-03-15 15:38:14 -05:00
Korey Sewell
0d8cfed042 Merge zizzer:/bk/newmem
into  zazzer.eecs.umich.edu:/.automount/zooks/y/ksewell/research/m5-sim/newmem

--HG--
extra : convert_revision : 054833d2f7019b9a1247efc4451ccb143242059d
2006-03-14 18:30:09 -05:00
Korey Sewell
6547e8882b Minor Sconscript edit ... mips decoder changes ... initialize NNPC and output fault name in simple cpu
SConscript:
    Separate Alpha EIO from syscall building for other architectures
arch/isa_specific.hh:
    change MIPS constant to 34k
arch/mips/isa/decoder.isa:
    Allow sll,ssnop,nop, and ehb to be determined through decoder using
    the different types of default cases
arch/mips/isa/formats/branch.isa:
    Delete debug code
arch/mips/isa/formats/noop.isa:
    add a Nop format
arch/mips/isa_traits.hh:
    use constants instead of enums
arch/mips/process.cc:
    point to the correct header file
cpu/simple/cpu.cc:
    Output the actual fault name
sim/process.cc:
    Inititalize NNPC

--HG--
extra : convert_revision : adb0026dfad25b14c98fb03c98bfe9c681bba6f8
2006-03-14 18:28:51 -05:00
Ron Dreslinski
7405a3530b Remove unneeded header files.
Add some forward declerations.
Fix ordering problem of variables in constructor (see sourceforge)
Factor out code from header into _impl file to speed building process (keep cache_builder smaller in size)

--HG--
extra : convert_revision : 20087f88f95628af716094e09c2287e09580149e
2006-03-14 18:03:34 -05:00
Gabe Black
67a1b7a61b added *.swp
--HG--
extra : convert_revision : 90e4387da5bbe5e3f05c4d25713d6a362c6724e8
2006-03-14 16:41:38 -05:00
Gabe Black
78b9a789d7 Fixed up after a hand merge.
arch/alpha/utility.hh:
    Got rid of unnecessary extern and static qualifiers, and fixed up the hand merge.
arch/sparc/regfile.hh:
    Fixed up SPARC after a hand merge.

--HG--
extra : convert_revision : 56e2d90ddd144f3386dbea50fa96cfc461d46b81
2006-03-14 16:39:59 -05:00
Gabe Black
fa763d2ecf Merge m5.eecs.umich.edu:/bk/newmem
into  ewok.(none):/home/gblack/m5/newmem

cpu/cpu_exec_context.cc:
    Hand merge

--HG--
rename : arch/alpha/registerfile.hh => arch/alpha/regfile.hh
extra : convert_revision : bd18966f7c37c67c2bc7ca2633b58f70ce64409c
2006-03-14 16:08:32 -05:00
Gabe Black
efe46430fa Moved registerfile.hh to regfile.hh
--HG--
rename : arch/alpha/registerfile.hh => arch/alpha/regfile.hh
extra : convert_revision : 27df93cd2259dab85057f966c801c0db2cb6f022
2006-03-14 16:05:44 -05:00
Gabe Black
538919445c Added the sparc regfile.hh to bitkeeper
--HG--
extra : convert_revision : 7bc8ca989a4f0225ad5644980c8dbc34b0c0e35f
2006-03-14 16:01:21 -05:00
Gabe Black
bb8b27d5a8 SPARC clean up towards compilability.
--HG--
extra : convert_revision : 156670995fa61599e763b002cd70f31f19b108d1
2006-03-14 15:59:19 -05:00
Gabe Black
160d1374a7 Missed this in the float register changeset.
--HG--
extra : convert_revision : 35e967fb39fc16e38da13ab1a093d7d0916cffeb
2006-03-14 15:58:05 -05:00
Gabe Black
d745f4d664 Moved some full system functions into utility.hh
--HG--
extra : convert_revision : dd2cd11213890b30975fdabdf7d9bc4652511434
2006-03-14 15:57:28 -05:00
Gabe Black
8e4ec55703 Changed the floating point register file into a class with appropriate accessor functions. The width of the floating point register to access can be specified, and if not, it will be accessed at its "natural" width. That is, the width of each individual register. Also, the functions which access the bit representation of floating point registers can use the blahblahBits functions now instead of blahblahInt.
arch/alpha/arguments.cc:
    Renamed readFloatRegInt to readFloatRegBits
arch/alpha/ev5.cc:
    Removed the Double from setFloatRegDouble
arch/alpha/registerfile.hh:
    Changed the floating point register file from a union of arrays to a class with appropriate accessor functions. The interface is necessary for SPARC.
arch/alpha/types.hh:
    Changed the FloatReg type from a union of uint64_t and double to a double, and defined a new type FloatRegBits which is a uint64_t and is used to return the bits which compose a floating point register rather than the value of the register.
arch/isa_parser.py:
    Adjusted the makeRead and makeWrite functions to generate the new versions of readFloatReg and setFloatReg.
base/remote_gdb.cc:
kern/tru64/tru64.hh:
    Replaced setFloatRegInt with setFloatRegBits
cpu/cpu_exec_context.cc:
    Removed the duplicated code for setting the floating point registers, and renamed the function to setFloatRegBits and readFloatRegBits.
cpu/cpu_exec_context.hh:
cpu/exec_context.hh:
cpu/o3/alpha_cpu_impl.hh:
cpu/o3/alpha_dyn_inst.hh:
cpu/o3/cpu.cc:
cpu/o3/cpu.hh:
cpu/o3/regfile.hh:
cpu/ozone/cpu.hh:
cpu/simple/cpu.hh:
    Implemented the new versions of the floating point read and set functions.
cpu/simple/cpu.cc:
    Replaced setFloatRegDouble with setFloatReg

--HG--
extra : convert_revision : 3dad06224723137f6033c335fb8f6395636767f2
2006-03-14 15:55:00 -05:00
Kevin Lim
f045b110cf Have a copyRegs function defined in the ISA that copies registers from one ExecContext to another ExecContext. This makes it easier for anything that needs to copy architected registers to do so in an ISA independent fashion.
arch/alpha/ev5.cc:
    copyIprs now copies from a source ExecContext to a destination ExecContext.
arch/alpha/registerfile.hh:
    Have ISA specific functions to copy all architected registers from one ExecContext to another.
cpu/cpu_exec_context.cc:
    Call the ISA in order to copy any architected registers.

--HG--
extra : convert_revision : 056cc3b3a9f345535d5a57c6524b114bbd5ae3c8
2006-03-13 17:04:24 -05:00
Steve Reinhardt
af975813e5 Add simple eio-based test.
--HG--
extra : convert_revision : 969e8fddad1b87eaa294857945a4c46cb175984d
2006-03-12 17:24:02 -05:00
Steve Reinhardt
f03e1fb5ab Oops, this goes with the previous changeset!
mem/mem_object.hh:
    Change getPort() to be anonymous by default.

--HG--
extra : convert_revision : 6998885ddccfbf26bc470112f40c3f19913ba7e2
2006-03-12 17:23:18 -05:00
Steve Reinhardt
e2b329d574 Replace Memory with MemObject; no need for two different levels of hierarchy there.
Get rid of addPort().
Change getPort() behavior on PhysicalMemory.

SConscript:
cpu/simple/cpu.hh:
sim/system.cc:
sim/system.hh:
    Replace Memory with MemObject.
cpu/base.hh:
    No need to declare Port here anymore.
cpu/cpu_exec_context.hh:
    Need PageTable definition.
cpu/simple/cpu.cc:
mem/physical.cc:
mem/physical.hh:
    Replace Memory with MemObject.
    Get rid of addPort(); allow getting anonymous ports with getPort().
mem/translating_port.hh:
    Remove unneeded header.
sim/process.cc:
    Replace Memory with MemObject.
    Change how initialization port gets set up to deal with change in
    addPort()/getPort().  Current solution is not ideal but it works.
sim/process.hh:
    Remove unneeded headers and declarations.
    Make LiveProcess::getDesc() abstract instead of panicing if called.
sim/syscall_emul.hh:
    Fix includes.

--HG--
extra : convert_revision : 11d4ffb54230038afcf7219cc46e51f809329a2f
2006-03-12 17:21:59 -05:00