Commit graph

90 commits

Author SHA1 Message Date
Ali Saidi
71909a50de CPU: Update where the simple cpus read their cpu id from the thread context to init() to make sure they read the right value. This fixes a bug with multi-processor full-system configurations.
--HG--
extra : convert_revision : 4f2801967a271b43817d88e147c2f80c4480b2c3
2007-12-16 03:48:13 -05:00
Gabe Black
a12d5975cc Simple CPU fix simple mistake in translateDataWriteAddr.
--HG--
extra : convert_revision : 6a6a7d05f62d9d9868be0707e4dc186a5f7ecf7d
2007-11-20 15:37:56 -08:00
Ali Saidi
cf1c25dbcc AtomicSimpleCPU: Refactor resume() code to have a cleaner control path.
--HG--
extra : convert_revision : f27bb96850e7fb0252fb1f47c3d0860705c32884
2007-11-08 10:46:41 -05:00
Gabe Black
93da9eb7f6 CPU: Add functions to the "ExecContext"s that translate a given address.
--HG--
extra : convert_revision : 7d898c6b6b13094fd05326eaa0b095a3ab132397
2007-10-22 14:30:45 -07:00
Ali Saidi
8351660273 CPU: Use the ThreadContext cpu id instead of the params cpu id in all cases.
--HG--
extra : convert_revision : 6d025764682181b1f67df3b1d8d1d59099136df7
2007-10-18 13:15:08 -04:00
Ali Saidi
d2a4f595d6 Update stats for quiesced cycles
--HG--
extra : convert_revision : 703ba58f156c9f2677b020f05d36bc1e3ae0b9e5
2007-09-28 13:22:14 -04:00
Ali Saidi
d325f49b70 Rename cycles() function to ticks()
--HG--
extra : convert_revision : 790eddb793d4f5ba35813d001037bd8601bd76a5
2007-09-28 13:21:52 -04:00
Gabe Black
7227ab5f22 Merge with head
--HG--
extra : convert_revision : cc73b9aaf73e9dacf52f3350fa591e67ca4ccee6
2007-08-26 21:45:40 -07:00
Gabe Black
24bfda0fdf Simple CPU: Don't trace instructions that fault. Otherwise they show up twice.
--HG--
extra : convert_revision : 4446d9544d58bdadbd24d8322bb63016a32aa2b8
2007-08-26 20:29:09 -07:00
Gabe Black
e7e2d5ce90 Simple CPU: Added code that will split requests that cross block boundaries into multiple memory access.
--HG--
extra : convert_revision : 600f79f32ef30a6e1db951503bcfe8cd332858d1
2007-08-26 20:27:11 -07:00
Gabe Black
e056e49c45 Simple CPU: Make sure only instructions which complete without faulting are counted.
--HG--
extra : convert_revision : 01019c7129ed762d8826c3e6519989aa3fc3b5fd
2007-08-26 20:25:42 -07:00
Gabe Black
537239b278 Address Translation: Make SE mode use an actual TLB/MMU for translation like FS.
--HG--
extra : convert_revision : a04a30df0b6246e877a1cea35420dbac94b506b1
2007-08-26 20:24:18 -07:00
Vincentius Robby
ec4000e0e2 Added fastmem option.
Lets CPU accesses to physical memory bypass Bus.

--HG--
extra : convert_revision : e56e3879de47ee10951a19bfcd8b62b6acdfb30c
2007-08-08 18:43:12 -04:00
Nathan Binkert
e8e1ddd530 SimpleCPU: Add some DPRINTFs
--HG--
extra : convert_revision : 5fdd5a9595c3e5d6ce5f9e8c9af0a8e6c857551c
2007-08-04 15:56:48 -07:00
Steve Reinhardt
08474ccf68 Merge Gabe's changes from head.
--HG--
extra : convert_revision : d00b7b09c7f19bc0e37b385ef7c124f69c0e917f
2007-07-29 13:25:14 -07:00
Gabe Black
8dd7700482 Turn the instruction tracing code into pluggable sim objects.
These need to be refined a little still and given parameters.

--HG--
extra : convert_revision : 9a8f5a7bd9dacbebbbd2c235cd890c49a81040d7
2007-07-28 20:30:43 -07:00
Steve Reinhardt
aaf59949e5 AtomicSimpleCPU: fix inadvertent loss of endian conversion on read.
--HG--
extra : convert_revision : 367bf2431bf4f4eb7c4d5723816e5db6f7233aed
2007-07-28 18:00:05 -07:00
Nathan Binkert
f0fef8f850 Merge python and x86 changes with cache branch
--HG--
extra : convert_revision : e06a950964286604274fba81dcca362d75847233
2007-07-26 23:15:49 -07:00
Nathan Binkert
abc76f20cb Major changes to how SimObjects are created and initialized. Almost all
creation and initialization now happens in python.  Parameter objects
are generated and initialized by python.  The .ini file is now solely for
debugging purposes and is not used in construction of the objects in any
way.

--HG--
extra : convert_revision : 7e722873e417cb3d696f2e34c35ff488b7bff4ed
2007-07-23 21:51:38 -07:00
Steve Reinhardt
3ad761bc8e Make CPU models use new LoadLockedReq/StoreCondReq commands.
--HG--
extra : convert_revision : ab78d9d1d88c3698edfd653d71c8882e1272b781
2007-06-30 20:35:42 -07:00
Steve Reinhardt
ee54ad318a Event descriptions should not end in "event"
(they function as adjectives not nouns)

--HG--
extra : convert_revision : 6506474ff3356ae8c80ed276c3608d8a4680bfdb
2007-06-30 17:45:58 -07:00
Steve Reinhardt
6ab53415ef Get rid of Packet result field. Error responses are
now encoded in cmd field.

--HG--
extra : convert_revision : d67819b7e3ee4b9a5bf08541104de0a89485e90b
2007-06-30 10:16:18 -07:00
Gabe Black
ea70e6d6da Make branches work by repopulating the predecoder every time through. This is probably fine as far as the predecoder goes, but the simple cpu might want to not refetch something it already has. That reintroduces the self modifying code problem though.
--HG--
extra : convert_revision : 802197e65f8dc1ad657c6b346091e03cb563b0c0
2007-06-19 18:17:34 +00:00
Gabe Black
a7f3bbcfab Make microOp vs microop and macroOp vs macroop capitilization consistent.
src/arch/x86/isa/macroop.isa:
    Make microOp vs microop and macroOp vs macroop capitilization consistent. Also fill out the emulation environment handling a little more, and use an object to pass around output code.
src/arch/x86/isa/microops/base.isa:
    Make microOp vs microop and macroOp vs macroop capitilization consistent. Also adjust python to C++ bool translation.

--HG--
extra : convert_revision : 6f4bacfa334c42732c845f9a7f211cbefc73f96f
2007-06-12 16:21:47 +00:00
Gabe Black
6a6e62014e Changes to make simple cpu handle pcs appropriately for x86
--HG--
extra : convert_revision : cf68886d53301e0a63705247bd7d66b2ff08ea84
2007-05-18 10:42:50 -07:00
Gabe Black
74122c04cf Even if you don't want to fetch more bytes, make sure you handle a fault.
--HG--
extra : convert_revision : cfebc877b9b2ebc8927ce8267867eb40ad6d59c6
2007-04-10 17:27:12 +00:00
Gabe Black
32368a2bd6 Merge zizzer.eecs.umich.edu:/bk/newmem
into  ahchoo.blinky.homelinux.org:/home/gblack/m5/newmem-x86

src/arch/mips/utility.hh:
src/arch/x86/SConscript:
    Hand merge

--HG--
extra : convert_revision : 0ba457aab52bf6ffc9191fd1fe1006ca7704b5b0
2007-03-15 02:52:51 +00:00
Gabe Black
a2b56088fb Make the predecoder an object with it's own switched header file. Start adding predecoding functionality to x86.
src/arch/SConscript:
src/arch/alpha/utility.hh:
src/arch/mips/utility.hh:
src/arch/sparc/utility.hh:
src/cpu/base.hh:
src/cpu/o3/fetch.hh:
src/cpu/o3/fetch_impl.hh:
src/cpu/simple/atomic.cc:
src/cpu/simple/base.cc:
src/cpu/simple/base.hh:
src/cpu/static_inst.hh:
src/arch/alpha/predecoder.hh:
src/arch/mips/predecoder.hh:
src/arch/sparc/predecoder.hh:
    Make the predecoder an object with it's own switched header file.

--HG--
extra : convert_revision : 77206e29089130e86b97164c30022a062699ba86
2007-03-15 02:47:42 +00:00
Gabe Black
26c0426e44 Make sttw and sttwa use the twin memory operations.
--HG--
extra : convert_revision : 368d1c57a46fd5ca15461cb5ee8e05fd1e080daa
2007-03-11 18:12:33 -04:00
Kevin Lim
ad44834907 Two fixes:
1. Make sure connectMemPorts() only gets called when the CPU's peer gets changed.  This is done by making setPeer() virtual, and overriding it in the CPU's ports.  When it gets called on a CPU's port (dcache specifically), it calls the normal setPeer() function, and also connectMemPorts().
2. Consolidate redundant code that handles switching in a CPU.

src/cpu/base.cc:
    Move common code of switching over peers to base CPU.
src/cpu/base.hh:
    Move common code of switching over peers to BaseCPU.
src/cpu/o3/cpu.cc:
    Add in function that updates thread context's ports.
    Also use updated function to takeOverFrom() in BaseCPU.  This gets rid of some repeated code.
src/cpu/o3/cpu.hh:
    Include function to update thread context's memory ports.
src/cpu/o3/lsq.hh:
    Add function to dcache port that will update the memory ports upon getting a new peer.
    Also include a function that will tell the CPU to update those memory ports.
src/cpu/o3/lsq_impl.hh:
    Add function that will update the memory ports upon getting a new peer.
src/cpu/simple/atomic.cc:
src/cpu/simple/timing.cc:
    Add function that will update thread context's memory ports upon getting a new peer.
    Also use the new BaseCPU's take over from function.
src/cpu/simple/atomic.hh:
    Add in function (and dcache port) that will allow the dcache to update memory ports when it gets assigned a new peer.
src/cpu/simple/timing.hh:
    Add function that will update thread context's memory ports upon getting a new peer.
src/mem/port.hh:
    Make setPeer virtual so that other classes can override it.

--HG--
extra : convert_revision : 2050f1241dd2e83875d281cfc5ad5c6c8705fdaf
2007-03-09 10:06:09 -05:00
Ali Saidi
4e8d2d1593 make ldtw(a) -- Twin 32 bit load work correctly -- by doing it the same way as the twin 64 bit loads
src/arch/isa_parser.py:
src/arch/sparc/isa/decoder.isa:
src/arch/sparc/isa/operands.isa:
src/base/bigint.hh:
src/cpu/simple/atomic.cc:
src/cpu/simple/timing.cc:
src/mem/packet_access.hh:
    make ldtw(a) Twin 32 bit load work correctly

--HG--
extra : convert_revision : 2646b269d58cc1774e896065875a56cf5e313b42
2007-03-02 22:34:51 -05:00
Ali Saidi
f72a999393 some forgotten commits
--HG--
extra : convert_revision : 213440066c700ed5891a6d4568928b7f3f2fe750
2007-02-12 18:40:08 -05:00
Ali Saidi
b9005f3562 Merge zizzer:/bk/newmem
into  zeep.pool:/z/saidi/work/m5.newmem

src/cpu/simple/atomic.cc:
    merge steve's changes in.

--HG--
extra : convert_revision : a17eda37cd63c9380af6fe68b0aef4b1e1974231
2007-02-12 13:22:36 -05:00
Ali Saidi
b5a4d95811 rename store conditional stuff as extra data so it can be used for conditional swaps as well
Add support for a twin 64 bit int load
Add Memory barrier and write barrier flags as appropriate
Make atomic memory ops atomic

src/arch/alpha/isa/mem.isa:
src/arch/alpha/locked_mem.hh:
src/cpu/base_dyn_inst.hh:
src/mem/cache/cache_blk.hh:
src/mem/cache/cache_impl.hh:
    rename store conditional stuff as extra data so it can be used for conditional swaps as well
src/arch/alpha/types.hh:
src/arch/mips/types.hh:
src/arch/sparc/types.hh:
    add a largest read data type for statically allocating read buffers in atomic simple cpu
src/arch/isa_parser.py:
    Add support for a twin 64 bit int load
src/arch/sparc/isa/decoder.isa:
    Make atomic memory ops atomic
    Add Memory barrier and write barrier flags as appropriate
src/arch/sparc/isa/formats/mem/basicmem.isa:
    add post access code block and define a twinload format for twin loads
src/arch/sparc/isa/formats/mem/blockmem.isa:
    remove old microcoded twin load coad
src/arch/sparc/isa/formats/mem/mem.isa:
    swap.isa replaces the code in loadstore.isa
src/arch/sparc/isa/formats/mem/util.isa:
    add a post access code block
src/arch/sparc/isa/includes.isa:
    need bigint.hh for Twin64_t
src/arch/sparc/isa/operands.isa:
    add a twin 64 int type
src/cpu/simple/atomic.cc:
src/cpu/simple/atomic.hh:
src/cpu/simple/base.hh:
src/cpu/simple/timing.cc:
    add support for twinloads
    add support for swap and conditional swap instructions
    rename store conditional stuff as extra data so it can be used for conditional swaps as well
src/mem/packet.cc:
src/mem/packet.hh:
    Add support for atomic swap memory commands
src/mem/packet_access.hh:
    Add endian conversion function for Twin64_t type
src/mem/physical.cc:
src/mem/physical.hh:
src/mem/request.hh:
    Add support for atomic swap memory commands
    Rename sc code to extradata

--HG--
extra : convert_revision : 69d908512fb34a4e28b29a6e58b807fb1a6b1656
2007-02-12 13:06:30 -05:00
Steve Reinhardt
f78bc80bd7 Move store conditional result checking from SimpleAtomicCpu write
function into Alpha ISA description.  write now just generically
returns a result value if the res pointer is non-null (which means
we can only provide a res pointer if we expect a valid result
value).

--HG--
extra : convert_revision : fb1c315515787f5fbbf7d1af7e428bdbfe8148b8
2007-02-12 09:26:47 -08:00
Steve Reinhardt
997fc505a8 Make memory commands dense again to avoid cache stat table explosion.
Created MemCmd class to wrap enum and provide handy methods to
check attributes, convert to string/int, etc.

--HG--
extra : convert_revision : 57f147ad893443e3a2040c6d5b4cdb1a8033930b
2007-02-07 10:53:37 -08:00
Ali Saidi
ecfd628ecd Modify ISA and staticInst to support a IsFirstMicroOp flag
Increment instruction count on first micro-op instead of last

src/arch/sparc/isa/decoder.isa:
    Implement a twin load for ASI_LDTX_P(0xe2)
src/arch/sparc/isa/formats/mem/blockmem.isa:
    set the new flag IsFirstMicroOp when needed
src/cpu/simple/atomic.cc:
    Increment instruction count on first micro-op instead of last (because if we take a fault on a micro coded instruction it should be counted twice acording to legion)
src/cpu/static_inst.hh:
    Add IsFirstMicroop flag to static insts

--HG--
extra : convert_revision : 02bea93d38c03bbafe4570665eb4c01c11caa2fc
2007-01-16 19:06:05 -05:00
Ali Saidi
92c5a5c8cb More changes to get SPARC fs closer. Now at 1.2M cycles before difference
configs/common/FSConfig.py:
    seperate the hypervisor memory and the guest0 memory. In reality we're going to need a better way to do this at some point. Perhaps auto generating the hv-desc image based on the specified config.
src/arch/sparc/isa/decoder.isa:
    change reads/writes to the [hs]tick(cmpr) registers to use readmiscregwitheffect
src/arch/sparc/miscregfile.cc:
    For niagra stick and tick are aliased to one value (if we end up doing mps we might not want this).
    Use instruction count from cpu rather than cycles because that is what legion does
    we can change it back after were done with legion
src/base/bitfield.hh:
    add a new function mbits() that just masks off bits of interest but doesn't shift
src/cpu/base.cc:
src/cpu/base.hh:
    add instruction count to cpu
src/cpu/exetrace.cc:
src/cpu/m5legion_interface.h:
    compare instruction count between legion and m5 too
src/cpu/simple/atomic.cc:
    change asserts of packet success to if panics wrapped with NDEBUG defines
    so we can get some more useful information when we have a bad address
src/dev/isa_fake.cc:
src/dev/isa_fake.hh:
src/python/m5/objects/Device.py:
    expand isa fake a bit more having data for each size request, the ability to have writes update the data and to warn on accesses
src/python/m5/objects/System.py:
    convert some tabs to spaces
src/python/m5/objects/T1000.py:
    add more fake devices for each l1 bank and each memory controller

--HG--
extra : convert_revision : 8024ae07b765a04ff6f600e5875b55d8a7d3d276
2006-12-04 00:54:40 -05:00
Ali Saidi
544f4b4d81 Merge zizzer:/bk/newmem
into  zeep.pool:/z/saidi/work/m5.newmem

--HG--
extra : convert_revision : c358d5e3211756bbf905eef2a62b65a2e56a86f3
2006-11-29 17:11:20 -05:00
Ali Saidi
b2eecd643c Add support for mmapped iprs to atomic cpu
src/arch/SConscript:
    add mmaped_ipr.hh to switch headers
src/arch/sparc/asi.hh:
    make ASI_IMPLICT=0 so by default nothing needs to be done
src/arch/sparc/miscregfile.hh:
    miscregfile no longer needs to include asi.hh
src/arch/sparc/tlb.cc:
src/arch/sparc/tlb.hh:
    implement panic instructions for mmaped ipr reads
src/cpu/simple/atomic.cc:
    add check for mmaped iprs and handle them if it exists
src/mem/request.hh:
    allocate space in the flags for mmaped iprs. Put in in the first 8 bits so that by default its fast. Move the other flags up 8 bits

--HG--
extra : convert_revision : 31255b0494588c4d06a727fe35241121d741b115
2006-11-29 17:11:10 -05:00
Kevin Lim
c96160cef5 Change the connecting of the physPort and virtPort to the memory object below the CPU to happen every time activateContext is called. The overhead is probably a little higher than necessary, but allows these connections to properly be made when there are CPUs that are inactive until they are switched in.
Right now this introduces a minor memory leak as old physPorts and virtPorts are not deleted when new ones are created.  A flyspray task has been created for this issue.  It can not be resolved until we determine how the bus will handle giving out ID's to functional ports that may be deleted.

src/cpu/o3/cpu.cc:
src/cpu/simple/atomic.cc:
src/cpu/simple/timing.cc:
    Change the setup of the physPort and virtPort to instead happen every time the CPU has a context activated.  This is a little high overhead, but keeps it working correctly when the CPU does not have a physical memory attached to it until it switches in (like the case of switch CPUs).
src/cpu/o3/thread_context.hh:
    Change function from being called at init() to just being called whenever the memory ports need to be connected.
src/cpu/o3/thread_context_impl.hh:
    Update this to not delete the port if it's the same as the virtPort.
src/cpu/thread_context.hh:
    Change function from being called at init() to whenever the memory ports need to be connected.
src/cpu/thread_state.cc:
    Instead of initializing the ports, simply connect them, deleting any old ports that might exist.  This allows these functions to be called multiple times.
src/cpu/thread_state.hh:
    Ports are no longer initialized, but rather connected at context activation time.

--HG--
extra : convert_revision : e399ce5dfbd6ad658c953a7c9c7b69b89a70219e
2006-11-29 16:07:55 -05:00
Ron Dreslinski
cd0b65508e Make an initialization pass for the thread context and set the [phys,virt]Port correctly
src/cpu/simple/atomic.cc:
src/cpu/simple/timing.cc:
    Call the thread context initialization

--HG--
extra : convert_revision : d7dc2a8b893dc670077b7f6150d4b710a1778620
2006-11-17 21:55:28 -05:00
Ron Dreslinski
7babf6b3a8 Make cpu's capable of having a phase shift
--HG--
extra : convert_revision : 7f082ba5c1cd2445aec731950c31a877aac23a75
2006-11-14 01:10:36 -05:00
Ron Dreslinski
dfc82bdcfc Changes needed for a bus from CPU->L1
src/cpu/simple/atomic.cc:
    Make the atomic cpu return 0 on snoops.

--HG--
extra : convert_revision : aad96ad36e0c764c7cfef8b0c8e97877574f5845
2006-11-13 19:12:45 -05:00
Ron Dreslinski
a962fc4f56 Make CPU models signal to update the snoop ranges
--HG--
extra : convert_revision : 717b62510f28a69af99453309fbbb458359eeb2a
2006-11-13 18:51:16 -05:00
Kevin Lim
3052632b68 Merge ktlim@zamp:./local/clean/tmp/test-regress
into  zamp.eecs.umich.edu:/z/ktlim2/clean/newmem-busfix

--HG--
extra : convert_revision : b98236507bb8996ce605b48b5a5a6a7aac297dc5
2006-11-12 21:57:58 -05:00
Nathan Binkert
b16e559177 Get rid of the ParamContext for pseudo instructions and move
the parameters to the BaseCPU object.

--HG--
extra : convert_revision : 557292cffb40918133647b0c9ac653ee5112df2e
2006-11-11 17:22:10 -08:00
Kevin Lim
0b0d5a282a Draining fixes.
src/cpu/o3/cpu.cc:
    Handle draining properly when CPU isn't actually being used.
src/cpu/simple/atomic.cc:
    Be sure to set status properly when draining.
src/mem/bus.cc:
    Fix for draining.

--HG--
extra : convert_revision : d9796e6693e974f022159029fc9743c49a970c8f
2006-11-09 11:33:44 -05:00
Kevin Lim
652281a61c Clean up clock phase drift code a bit.
src/cpu/base.cc:
    Move clock phase drift code to the base CPU so that any CPU model can use it.
src/cpu/base.hh:
    Added two functions to help get the next cycle the CPU should be scheduled.
src/cpu/simple/atomic.cc:
src/cpu/simple/timing.cc:
    Use the function now in BaseCPU.

--HG--
extra : convert_revision : 444494b66ffc85fc473c23f57683c5f9458ad80c
2006-11-06 13:27:45 -05:00
Gabe Black
b565660c42 Merge zizzer.eecs.umich.edu:/bk/newmem/
into  zeep.eecs.umich.edu:/home/gblack/m5/newmemmemops

--HG--
extra : convert_revision : c2f7398a0d14dd11108579bb243ada7420285a22
2006-11-01 19:00:59 -05:00