Commit graph

4397 commits

Author SHA1 Message Date
Ali Saidi
230acc291c ARM: We don't currently support ThumbEE exceptions, so don't report that we do 2010-08-23 11:18:40 -05:00
Ali Saidi
c0ca01ec36 ARM: Change how the AMBA device ID checking is done to make it more generic 2010-08-23 11:18:40 -05:00
Ali Saidi
bb5377899a ARM: Add system for ARM/Linux and bootstrapping 2010-08-23 11:18:40 -05:00
Ali Saidi
8ed4f0a02c ARM: Add I/O devices for booting linux
--HG--
rename : src/dev/arm/Versatile.py => src/dev/arm/RealView.py
rename : src/dev/arm/versatile.cc => src/dev/arm/realview.cc
rename : src/dev/arm/versatile.hh => src/dev/arm/realview.hh
2010-08-23 11:18:40 -05:00
Ali Saidi
38cf6a164d ARM: Implement some more misc registers 2010-08-23 11:18:40 -05:00
Ali Saidi
b7b2eae6fa ARM: Fix an un-initialized variable bug 2010-08-23 11:18:39 -05:00
Ali Saidi
4ab68fc999 Loader: Use address mask provided to load*Symbols when loading the symbols from the symbol table. 2010-08-23 11:18:39 -05:00
Ali Saidi
f2642e2055 Loader: Make the load address mask be a parameter of the system rather than a constant.
This allows one two different OS requirements for the same ISA to be handled.
Some OSes are compiled for a virtual address and need to be loaded into physical
memory that starts at address 0, while other bare metal tools generate
images that start at address 0.
2010-08-23 11:18:39 -05:00
Min Kyu Jeong
d4e83a4001 ARM: Finish the timing translation when taking a fault. 2010-08-23 11:18:39 -05:00
Dam Sunwoo
cb76111a7e ARM: Use a stl queue for the table walker state 2010-08-23 11:18:39 -05:00
Ali Saidi
1d1837ee98 CPU: Set a default value when readBytes faults.
This was being done in read(), but if readBytes was called directly it
wouldn't happen. Also, instead of setting the memory blob being read to -1
which would (I believe) require using memset with -1 as a parameter, this now
uses bzero. It's hoped that it's more specialized behavior will make it
slightly faster.
2010-08-23 11:18:39 -05:00
Ali Saidi
ac575a9d82 Compiler: Fixes for GCC 4.5. 2010-08-23 11:18:39 -05:00
Ali Saidi
7d191366e1 BASE: Fix genrand to generate both 0s and 1s when max equals one.
previously was only generating 0s.
2010-08-23 11:18:39 -05:00
Ali Saidi
7793773809 stats: Fix off-by-one error in distributions.
bkt size isn't evenly divisible by max-min and it would round down,
it's possible to sample a distribution and have no place to put the sample.
When this case occured the simulator would assert.
2010-08-23 11:18:39 -05:00
Gabe Black
fa01fbddeb X86: Get rid of unused file arguments.hh. 2010-08-22 18:42:23 -07:00
Gabe Black
4ad30a662d SPARC: Fix some style issues in utility.hh. 2010-08-22 18:39:39 -07:00
Gabe Black
5836023ab2 X86: Get rid of the unused getAllocator on the python base microop class.
This function is always overridden, and doesn't actually have the right
signature.
2010-08-22 18:24:09 -07:00
Brad Beckmann
8557480300 ruby: Added merge GETS optimization to hammer
Added an optimization that merges multiple pending GETS requests into a
single request to the owner node.
2010-08-20 11:46:14 -07:00
Brad Beckmann
908364a1c9 ruby: Fixed minor bug in ruby test for setting the request type 2010-08-20 11:46:14 -07:00
Brad Beckmann
e7f2da517a ruby: Stall and wait input messages instead of recycling
This patch allows messages to be stalled in their input buffers and wait
until a corresponding address changes state.  In order to make this work,
all in_ports must be ranked in order of dependence and those in_ports that
may unblock an address, must wake up the stalled messages.  Alot of this
complexity is handled in slicc and the specification files simply
annotate the in_ports.

--HG--
rename : src/mem/slicc/ast/CheckAllocateStatementAST.py => src/mem/slicc/ast/StallAndWaitStatementAST.py
rename : src/mem/slicc/ast/CheckAllocateStatementAST.py => src/mem/slicc/ast/WakeUpDependentsStatementAST.py
2010-08-20 11:46:14 -07:00
Brad Beckmann
af6b97e3ee ruby: Recycle latency fix for hammer
Patch allows each individual message buffer to have different recycle latencies
and allows the overall recycle latency to be specified at the cmd line. The
patch also adds profiling info to make sure no one processor's requests are
recycled too much.
2010-08-20 11:46:14 -07:00
Brad Beckmann
f57053473a MOESI_hammer: break down miss latency stalled cycles
This patch tracks the number of cycles a transaction is delayed at different
points of the request-forward-response loop.
2010-08-20 11:46:14 -07:00
Brad Beckmann
8b28848321 ruby: added probe filter support to hammer 2010-08-20 11:46:14 -07:00
Brad Beckmann
593ae7457e ruby: fixed DirectoryMemory's numa_high_bit configuration
This fix includes the off-by-one bit selection bug for numa mapping.
2010-08-20 11:46:13 -07:00
Brad Beckmann
ac5bb214e3 ruby: Reset ruby stats in RubySystem unserialize
The main purpose for clearing stats in the unserialize process is so
that the profiler can correctly set its start time to the unserialized
value of curTick.
2010-08-20 11:46:13 -07:00
Brad Beckmann
72044e3f5a ruby: Disable migratory sharing for token and hammer
This patch allows one to disable migratory sharing for those cache blocks that
are accessed by atomic requests.  While the implementations are different
between the token and hammer protocols, the motivation is the same.  For
Alpha, LLSC semantics expect that normal loads do not unlock cache blocks that
have been locked by LL accesses.  Therefore, locked blocks should not transfer
write permissions when responding to these load requests.  Instead, only they
only transfer read permissions so that the subsequent SC access can possibly
succeed.
2010-08-20 11:46:13 -07:00
Brad Beckmann
bcdd19df03 ruby: Added SC fail indication to trace profiling 2010-08-20 11:46:13 -07:00
Brad Beckmann
283be34a99 devices: Fixed periodic interrupts to work with draining
Added drain functions to the RTC and 8254 timer so that periodic interrupts
stop when the system is draining.  This patch is needed to checkpoint in
timing mode.  Otherwise under certain situations, the event queue will never
be completely empty.
2010-08-20 11:46:13 -07:00
Brad Beckmann
b6d08e0455 ruby: Fixed RubyPort sendTiming callbacks
Fixed RubyPort schedSendTiming calls to match ruby frequency.
2010-08-20 11:46:13 -07:00
Brad Beckmann
45f6f31d7a ruby: fixed token bugs associated with owner token counts
This patch fixes several bugs related to previous inconsistent assumptions on
how many tokens the Owner had.  Mike Marty should have fixes these bugs years
ago.  :)
2010-08-20 11:46:13 -07:00
Brad Beckmann
fb2e0f56ef ruby: MOESI_CMP_token dma fixes
This patch fixes various protocol bugs regarding races between dma requests
and persistent requests.
2010-08-20 11:46:13 -07:00
Brad Beckmann
6a4f99899b ruby: Resurrected Ruby's deterministic tests
Added the request series and invalidate deterministic tests as new cpu models
and removed the no longer needed ruby tests

--HG--
rename : configs/example/rubytest.py => configs/example/determ_test.py
rename : src/mem/ruby/tester/DetermGETXGenerator.cc => src/cpu/directedtest/DirectedGenerator.cc
rename : src/mem/ruby/tester/DetermGETXGenerator.hh => src/cpu/directedtest/DirectedGenerator.hh
rename : src/mem/ruby/tester/DetermGETXGenerator.cc => src/cpu/directedtest/InvalidateGenerator.cc
rename : src/mem/ruby/tester/DetermGETXGenerator.hh => src/cpu/directedtest/InvalidateGenerator.hh
rename : src/cpu/rubytest/RubyTester.cc => src/cpu/directedtest/RubyDirectedTester.cc
rename : src/cpu/rubytest/RubyTester.hh => src/cpu/directedtest/RubyDirectedTester.hh
rename : src/mem/ruby/tester/DetermGETXGenerator.cc => src/cpu/directedtest/SeriesRequestGenerator.cc
rename : src/mem/ruby/tester/DetermGETXGenerator.hh => src/cpu/directedtest/SeriesRequestGenerator.hh
2010-08-20 11:46:13 -07:00
Brad Beckmann
984adf198a ruby: Updated MOESI_hammer L2 latency behavior
Previously, the MOESI_hammer protocol calculated the same latency for L1 and
L2 hits.  This was because the protocol was written using the old ruby
assumption that L1 hits used the sequencer fast path.  Since ruby no longer
uses the fast-path, the protocol delays L2 hits by placing them on the
trigger queue.
2010-08-20 11:46:13 -07:00
Brad Beckmann
29c45ccd23 ruby: Reduced ruby latencies
The previous slower ruby latencies created a mismatch between the faster M5
cpu models and the much slower ruby memory system.  Specifically smp
interrupts were much slower and infrequent, as well as cpus moving in and out
of spin locks.  The result was many cpus were idle for large periods of time.

These changes fix the latency mismatch.
2010-08-20 11:46:12 -07:00
Brad Beckmann
8e5c441a54 ruby: fix ruby llsc support to sync sc outcomes
Added support so that ruby can determine the outcome of store conditional
operations and reflect that outcome to M5 physical memory and cpus.
2010-08-20 11:46:12 -07:00
Brad Beckmann
54d76f0ce5 ruby: Fixed L2 cache miss profiling
Fixed L2 cache miss profiling for the MOESI_CMP_token protocol
2010-08-20 11:46:12 -07:00
Brad Beckmann
a3b4b9b3e3 ruby: Added bcast msg profiling to hammer and token 2010-08-20 11:46:12 -07:00
Brad Beckmann
1f82eb1a03 ruby: Added consolidated network msg stats 2010-08-20 11:46:12 -07:00
Brad Beckmann
4b4e725921 ruby: Reincarnated the responding machine profiling
This patch adds back to ruby the capability to understand the response time
for messages that hit in different levels of the cache heirarchy.
Specifically add support for the MI_example, MOESI_hammer, and MOESI_CMP_token
protocols.
2010-08-20 11:46:12 -07:00
Brad Beckmann
9fb4381ddc MOESI_CMP_token: Fixed dma persistent lockdown bugs 2010-08-20 11:46:12 -07:00
Brad Beckmann
808701a10c memtest: Memtester support for DMA
This patch adds DMA testing to the Memtester and is inherits many changes from
Polina's old tester_dma_extension patch.  Since Ruby does not work in atomic
mode, the atomic mode options are removed.
2010-08-20 11:46:12 -07:00
Brad Beckmann
64b2205992 ruby: Added ruby_request_type ostream def to libruby.hh 2010-08-20 11:46:12 -07:00
Brad Beckmann
d694cc1384 slicc: Consolidated the protocol stats printing
Created a separate ProfileDumper that consolidates the generated stats for
each controller of a certain type.
2010-08-20 11:46:12 -07:00
Brad Beckmann
09854be558 config: Added the topology description to m5 config.ini 2010-08-20 11:46:11 -07:00
Brad Beckmann
eb1e5636e3 ruby: Fixed printout when Sequencer detects a deadlock 2010-08-20 11:41:35 -07:00
Brad Beckmann
d7d73680c4 MESI_CMP_directory: bug fix for old PUTX requests 2010-08-20 11:41:35 -07:00
Steve Reinhardt
e0754c0f6c misc: add some AMD copyright notices
Meant to add these with the previous batch of csets.
2010-08-17 05:49:05 -07:00
Steve Reinhardt
164a211f10 x86: minor checkpointing bug fixes 2010-08-17 05:20:39 -07:00
Steve Reinhardt
f064aa3060 sim: revamp unserialization procedure
Replace direct call to unserialize() on each SimObject with a pair of
calls for better control over initialization in both ckpt and non-ckpt
cases.

If restoring from a checkpoint, loadState(ckpt) is called on each
SimObject.  The default implementation simply calls unserialize() if
there is a corresponding checkpoint section, so we get backward
compatibility for existing objects.  However, objects can override
loadState() to get other behaviors, e.g., doing other programmed
initializations after unserialize(), or complaining if no checkpoint
section is found.  (Note that the default warning for a missing
checkpoint section is now gone.)

If not restoring from a checkpoint, we call the new initState() method
on each SimObject instead.  This provides a hook for state
initializations that are only required when *not* restoring from a
checkpoint.

Given this new framework, do some cleanup of LiveProcess subclasses
and X86System, which were (in some cases) emulating initState()
behavior in startup via a local flag or (in other cases) erroneously
doing initializations in startup() that clobbered state loaded earlier
by unserialize().
2010-08-17 05:17:06 -07:00
Steve Reinhardt
2519d116c9 sim: fold checkpoint restore code into instantiate()
The separate restoreCheckpoint() call is gone; just pass
the checkpoint dir as an optional arg to instantiate().
This change is a precursor to some more extensive
reworking of the startup code.
2010-08-17 05:17:06 -07:00
Steve Reinhardt
c2e1458746 sim: clean up child handling
The old code for handling SimObject children was kind of messy,
with children stored both in _values and _children, and
inconsistent and potentially buggy handling of SimObject
vectors.  Now children are always stored in _children, and
SimObject vectors are consistently handled using the
SimObjectVector class.

Also, by deferring the parenting of SimObject-valued parameters
until the end (instead of doing it at assignment), we eliminate
the hole where one could assign a vector of SimObjects to a
parameter then append to that vector, with the appended objects
never getting parented properly.

This patch induces small stats changes in tests with data races
due to changes in the object creation & initialization order.
The new code does object vectors in order and so should be more
stable.
2010-08-17 05:11:00 -07:00
Steve Reinhardt
5ea906ba16 sim: move iterating over SimObjects into Python. 2010-08-17 05:08:50 -07:00
Steve Reinhardt
c2cce96a0b sim: fail on implicit creation of orphans via ports
Orphan SimObjects (not in the config hierarchy) could get
created implicitly if they have a port connection to a SimObject
that is in the hierarchy.  This means that there are objects on
the C++ SimObject list (created via the C++ SimObject
constructor call) that are unknown to Python and will get
skipped if we walk the hierarchy from the Python side (as we are
about to do).  This patch detects this situation and prints an
error message.

Also fix the rubytester config script which happened to rely on
this behavior.
2010-08-17 05:06:22 -07:00
Steve Reinhardt
1fbe466345 sim: make Python Root object a singleton
Enforce that the Python Root SimObject is instantiated only
once.  The C++ Root object already panics if more than one is
created.  This change avoids the need to track what the root
object is, since it's available from Root.getInstance() (if it
exists).  It's now redundant to have the user pass the root
object to functions like instantiate(), checkpoint(), and
restoreCheckpoint(), so that arg is gone.  Users who use
configs/common/Simulate.py should not notice.
2010-08-17 05:06:22 -07:00
Steve Reinhardt
0685ae7a2d bus: clean up default responder code.
Clean up some minor things left over from the default responder
change in rev 9af6fb59752f.  Mostly renaming the 'responder_set'
param to 'use_default_range' to actually reflect what it does...
old name wasn't that descriptive in the first place, but now
it really doesn't make sense at all.

Also got rid of the bogus obsolete assignment to 'bus.responder'
which used to be a parameter but now is interpreted as an
implicit child assignment, and which was giving me problems in
the config restructuring to come.  (A good argument for not
allowing implicit child assignments, IMO, but that's water under
the bridge, I'm afraid.)

Also moved the Bus constructor to the .cc file since that's
where it should have been all along.
2010-08-17 05:06:21 -07:00
Gabe Black
c4ba6967a5 Inorder: Fix compilation of m5.fast.
printMemData is only used in DPRINTFs. If those are removed by compiling
m5.fast, that function is unused, gcc generates a warning, that gets turned
into an error, and the build fails. This change surrounds the function
definition with #if TRACING_ON so it only gets compiled in if the DPRINTFs do
to.
2010-08-14 01:00:45 -07:00
Gabe Black
961aafc044 Merge with head. 2010-08-13 06:16:30 -07:00
Gabe Black
aa8c6e9c95 CPU: Add readBytes and writeBytes functions to the exec contexts. 2010-08-13 06:16:02 -07:00
Gabe Black
65dbcc6ea1 InOrder: Clean up some DPRINTFs that print data sent to/from the cache. 2010-08-13 06:16:00 -07:00
Gabe Black
52a90a5998 CPU: Tidy up endianness handling for mmapped "IPR"s. 2010-08-13 06:10:45 -07:00
Joel Hestness
53c241fc16 TimingSimpleCPU: fix NO_ACCESS memory op handling
When a request is NO_ACCESS (x86 CDA microinstruction), the memory op
doesn't go to the cache, so TimingSimpleCPU::completeDataAccess needs
to handle the case where the current status of the CPU is Running
and not DcacheWaitResponse or DTBWaitResponse
2010-08-12 17:16:02 -07:00
Timothy M. Jones
97d245278d Power: The condition register should be set or cleared upon a system call
return to indicate success or failure.
2010-07-22 18:54:37 +01:00
Timothy M. Jones
607f519800 LSQ Unit: After deleting part of a split request, set it to NULL so that it
isn't accidentally deleted again later (causing a segmentation fault).
2010-07-22 18:54:37 +01:00
Timothy M. Jones
28a5ea3f99 Port: Only indicate that a SimpleTimingPort is drained if its send event is
not scheduled, as well as the transmit list being empty.
2010-07-22 18:54:37 +01:00
Timothy M. Jones
e50a880297 O3CPU: Fix a bug where stores in the cpu where never marked as split. 2010-07-22 18:52:02 +01:00
Timothy M. Jones
0d301ca4c4 Syscall: Don't close the simulator's standard file descriptors. 2010-07-22 18:47:52 +01:00
Timothy M. Jones
9a3533ec84 O3CPU: O3's tick event gets squashed when it is switched out. When repeatedly
switching between O3 and another CPU, O3's tick event might still be scheduled
in the event queue (as squashed).  Therefore, check for a squashed tick event
as well as a non-scheduled event when taking over from another CPU and deal
with it accordingly.
2010-07-22 18:47:43 +01:00
Timothy M. Jones
8c76715979 Power: Provide a utility function to copy registers from one thread context
to another in the Power ISA.
2010-07-22 18:47:03 +01:00
Nathan Binkert
21bf6ff101 stats: unify the two stats distribution type better 2010-07-21 18:54:53 -07:00
Nathan Binkert
2a1309f213 stats: cleanup a few small problems in stats 2010-07-21 15:53:53 -07:00
Nathan Binkert
76c92c3e30 python: add a sorted dictionary class
It would be nice if python had a tree class that would do this for real,
but since we don't, we'll just keep a sorted list of keys and update
it on demand.
2010-07-21 15:53:53 -07:00
Nathan Binkert
3518416917 python: Add mechanism to override code compiled into the exectuable
If the user sets the environment variable M5_OVERRIDE_PY_SOURCE to
True, then imports that would normally find python code compiled into
the executable will instead first check in the absolute location where
the code was found during the build of the executable.  This only
works for files in the src (or extras) directories, not automatically
generated files.

This is a developer feature!
2010-07-21 15:53:52 -07:00
Tushar Krishna
11bb678a80 Fix x86 XCHG macro-op to use locked micro-ops for all memory accesses 2010-07-21 09:55:57 -07:00
Steve Reinhardt
262b2e2b94 SimObject: transparently forward Python attribute refs to C++.
This tidbit was pulled from a larger patch for Tim's sake, so
the comment reflects functions that haven't been exported yet.
I hope to commit them soon so it didn't seem worth cleaning up.
2010-07-17 08:56:49 -07:00
Gabe Black
8cec870568 ARM: Make an SRS instruction with a bad mode cause an undefined instruction fault. 2010-07-15 02:11:56 -07:00
Gabe Black
4e3183cb1e ARM: Adjust the FP_Base_DepTag to be larger than the largest int reg index. 2010-07-13 22:41:47 -07:00
Steve Reinhardt
897247d63b cache: fix bug in SC upgrade handling
This bug was introduced with the recent rework of SC
failure handling in cset f97b62be544f.
2010-07-08 17:56:13 -07:00
Brad Beckmann
a03c1cd6e0 garnet: Added topology print function to Garnet printStats 2010-07-08 16:18:20 -07:00
Tushar Krishna
2f2962fee3 NetworkMessage copy constructor fix 2010-07-08 16:18:20 -07:00
Steve Reinhardt
26f5a9c2cb checkpointing: another small overload fix
On Nate's advice, overload 'char' as well as 'signed char'
and 'unsigned char'.
2010-07-05 22:57:23 -07:00
Steve Reinhardt
387cbffb7a sim: allow SimObject subclasses to define classmethods
(without requiring a leading underscore)
Also a little cleanup on type names in SimObject.py.
2010-07-05 21:39:38 -07:00
Steve Reinhardt
30ce620d1d sim: fold StartupCallback into SimObject
There used to be a reason to have StartupCallback
be a separate object, but not any more.  Now
it's just confusing.
2010-07-05 21:39:38 -07:00
Steve Reinhardt
345dfd1b41 checkpointing: minor cleanup.
Move some static checkpoint stuff into the
Checkpoint object namespace.
2010-07-05 21:39:38 -07:00
Steve Reinhardt
820bb3044d checkpointing: fix minor bug
Somehow we now need to explicitly specialize on
'signed char' and not just 'char' to catch cases
like int8_t
2010-07-05 21:39:38 -07:00
Steve Reinhardt
f98cce5771 process: get rid of some unused code & vars 2010-07-05 21:39:38 -07:00
Steve Reinhardt
2c2f956060 process: minor format/style cleanup 2010-07-05 21:39:38 -07:00
Tushar Krishna
66f0d26059 style: updated garnet to match M5 coding style 2010-06-22 15:36:07 -07:00
Korey Sewell
84489c5874 inorder: remove another debug stat 2010-06-28 07:33:33 -04:00
Korey Sewell
792c18a1fc inorder: remove debugging stat
m5 doesnt do stats specific to binary and this resource request stat is probably only
useful for people who really know the ins/outs of the model anyway
2010-06-26 09:41:39 -04:00
Korey Sewell
868181f24d inorder: Return Address Stack bug
the nextPC was getting sent to the branch predictor not the current PC, so
the RAS was returning the wrong PC and mispredicting everything.
2010-06-25 17:42:35 -04:00
Korey Sewell
6bfd766f2c inorder: resource scheduling backend
replace priority queue with vector of lists(1 list per stage) and place inside a class
so that we have more control of when an instruction uses a particular schedule entry
...
also, this is the 1st step toward making the InOrderCPU fully parameterizable. See the
wiki for details on this process
2010-06-25 17:42:34 -04:00
Gabe Black
6697d41693 X86: Fix div2 flag calculation. 2010-06-25 00:21:48 -07:00
Korey Sewell
71b67d408b inorder: cleanup virtual functions
remove the annotation 'virtual' from  function declaration that isnt being derived from
2010-06-24 15:34:19 -04:00
Korey Sewell
f95430d97e inorder: enforce 78-character rule 2010-06-24 15:34:12 -04:00
Korey Sewell
ecba3074c2 inorder: exe_unit_stats for resolved branches 2010-06-24 13:58:27 -04:00
Korey Sewell
1a73764403 inorder: squash from memory stall
this applies to multithreading models which would like to squash a thread on memory stall
2010-06-23 22:09:49 -04:00
Korey Sewell
1f778b3583 inorder: record load/store trace data 2010-06-23 18:21:12 -04:00
Korey Sewell
defab3ffd5 inorder: update branch predictor
- use InOrderBPred instead of Resource for DPRINTFs
- account for DELAY SLOT in updating RAS and in squashing
- don't let squashed instructions update the predictor
- the BTB needs to use the ASID not the TID to work for multithreaded programs
- add stats for BTB hits
2010-06-23 18:19:18 -04:00
Korey Sewell
9f0d8f252c inorder-stats: add instruction type stats
also, remove inst-req stats as default.good for debugging
but in terms of pure processor stats they aren't useful
2010-06-23 18:18:20 -04:00
Korey Sewell
39ac4dce04 inorder: stall signal handling
remove stall only when necessary
add debugging printfs
2010-06-23 18:15:23 -04:00
Korey Sewell
7695d4c63f inorder: tick scheduling
use nextCycle to calculate ticks after addition
2010-06-23 18:14:59 -04:00
Steve Reinhardt
de2321de81 cache: fix longstanding prefetcher bug
Thanks to Joe Gross for pointing this out (again?).
Apologies to anyone who pointed it out earlier and
we didn't listen.
2010-06-22 21:29:43 -07:00
Timothy M. Jones
96767fc721 O3ThreadContext: When taking over from a previous context, only assert that
the system pointers match in Full System mode.
2010-06-23 00:53:17 +01:00
Steve Reinhardt
f24ae2ec2a cache: fail store conditionals when upgrade loses race
Requires new "SCUpgradeReq" message that marks upgrades
for store conditionals, so downstream caches can fail
these when they run into invalidations.
See http://www.m5sim.org/flyspray/task/197
2010-06-16 15:25:57 -07:00
Steve Reinhardt
57f2b7db11 cache: fix dirty bit setting
Only set the dirty bit when we actually write to a block
(not if we thought we might but didn't, as in a failed
SC or CAS).  This requires makeing sure the dirty bit
stays set when we get an exclusive (writable) copy
in a cache-to-cache transfer from another owner, which
n turn requires copying the mem-inhibit flag from
timing-mode requests to their associated responses.
2010-06-16 15:25:57 -07:00
Nathan Binkert
f90319d3b8 stats: rename print to display in the mysql code too...sorry 2010-06-15 14:00:41 -07:00
Nathan Binkert
e54b673315 stats: rename print to display so it work in python 2010-06-15 08:34:19 -07:00
Nathan Binkert
86a93fe7b9 stats: only consider a formula initialized if there is a formula 2010-06-15 01:18:36 -07:00
Nathan Binkert
54d813adca stats: get rid of the never-really-used event stuff 2010-06-14 23:24:46 -07:00
Nathan Binkert
420402c0a3 util: clean up attrdict and import multiattrdict into m5.util 2010-06-14 23:24:46 -07:00
Nathan Binkert
5fc7adcba0 python: use ipython in --interactive if it is available 2010-06-14 23:24:46 -07:00
Nathan Binkert
dd133c7b24 ruby: get rid of PrioHeap and use STL
One big difference is that PrioHeap puts the smallest element at the
top of the heap, whereas stl puts the largest element on top, so I
changed all comparisons so they did the right thing.

Some usage of PrioHeap was simply changed to a std::vector, using sort
at the right time, other usage had me just use the various heap functions
in the stl.
2010-06-10 23:17:07 -07:00
Nathan Binkert
3df84fd8a0 ruby: get rid of the Map class 2010-06-10 23:17:07 -07:00
Nathan Binkert
006818aeea ruby: get rid of Vector and use STL
add a couple of helper functions to base for deleteing all pointers in
a container and outputting containers to a stream
2010-06-10 23:17:07 -07:00
Nathan Binkert
bc87fa30d7 ruby: get rid of RefCnt and Allocator stuff use base/refcnt.hh
This was somewhat tricky because the RefCnt API was somewhat odd.  The
biggest confusion was that the the RefCnt object's constructor that
took a TYPE& cloned the object.  I created an explicit virtual clone()
function for things that took advantage of this version of the
constructor.  I was conservative and used clone() when I was in doubt
of whether or not it was necessary.  I still think that there are
probably too many instances of clone(), but hopefully not too many.

I converted several instances of const MsgPtr & to a simple MsgPtr.
If the function wants to avoid the overhead of creating another
reference, then it should just use a regular pointer instead of a ref
counting ptr.

There were a couple of instances where refcounted objects were created
on the stack.  This seems pretty dangerous since if you ever
accidentally make a reference to that object with a ref counting
pointer, bad things are bound to happen.
2010-06-10 23:17:06 -07:00
Lisa Hsu
aa78887970 flags: add comment to avoid future deletions since code appears redundant. 2010-06-09 10:47:37 -07:00
Lisa Hsu
d28572499f flags: Unserializing old checkpoints before the introduction
of the Initialized flag would break, set Initialized for events upon
unserialization.
2010-06-08 17:16:36 -07:00
Steve Reinhardt
4977d8b58f scons: make RUBY a regular (non-global) sticky var
and force it to True for builds that imply Ruby protocols
(else unexpected things happen when testing these builds
with RUBY=False).
2010-06-07 12:19:59 -04:00
Steve Reinhardt
d0af5e9df6 More minor gdb-related cleanup.
Found several more stale includes and forward decls.
2010-06-03 19:41:34 -07:00
Steve Reinhardt
a529dbfe65 Act like enabling CPUs is no big deal,
rather than a scary thing that might not work.
2010-06-03 16:54:28 -07:00
Steve Reinhardt
f92e91e853 Minor remote GDB cleanup.
Expand the help text on the --remote-gdb-port option so
people know you can use it to disable remote gdb without
reading the source code, and thus don't waste any time
trying to add a separate option to do that.
Clean up some gdb-related cruft I found while looking
for where one would add a gdb disable option, before
I found the comment that told me that I didn't need
to do that.
2010-06-03 16:54:26 -07:00
Lisa Hsu
4a3ce94386 Stats: fix dist stat and enable VectorDistStat 2010-06-03 11:06:12 -07:00
Ali Saidi
d2186857b1 ARM: Fix issue with m5.fast and ARM 2010-06-03 12:20:49 -04:00
Ali Saidi
5268067f14 ARM: Fix SPEC2000 benchmarks in SE mode. With this patch all
Spec2k benchmarks seem to run with atomic or timing mode simple
CPUs. Fixed up some constants, handling of 64 bit arguments,
and marked a few more syscalls ignoreFunc.
2010-06-02 12:58:18 -05:00
Min Kyu Jeong
5d5bf8cbc7 ARM: Fix IT state not updating when an instruction memory instruction faults. 2010-06-02 12:58:18 -05:00
Dam Sunwoo
4325519fc5 ARM: Allow multiple outstanding TLB walks to queue. 2010-06-02 12:58:18 -05:00
Ali Saidi
2bad5138e4 ARM TLB: Fix bug in memAttrs getting a bogus thread context 2010-06-02 12:58:18 -05:00
Dam Sunwoo
6b00c7fa22 ARM: Support table walks in timing mode. 2010-06-02 12:58:18 -05:00
Dam Sunwoo
6c8dd32fa4 ARM: Added support for Access Flag and some CP15 regs (V2PCWPR, V2PCWPW, V2PCWUR, V2PCWUW,...) 2010-06-02 12:58:18 -05:00
Gabe Black
85ba2a3243 ARM: Decode the neon instruction space. 2010-06-02 12:58:18 -05:00
Gabe Black
e50e6a260f ARM: Add a comment to vfp.cc that explains the asm statements. 2010-06-02 12:58:18 -05:00
Gabe Black
10031a0327 ARM: Move some case values out of ##included files.
This will help keep the high level decode together and not have it spread into
the subordinate decode stuff. The ##include lines still need to be on a line
by themselves, though.
2010-06-02 12:58:18 -05:00
Gabe Black
22f15ab94e ARM: Combine some redundant cases in one of the data decode functions. 2010-06-02 12:58:18 -05:00
Gabe Black
fcee2b3f31 ARM: Add comments to the classes in macromem.hh. 2010-06-02 12:58:18 -05:00
Gabe Black
362b747fdc ARM: Move code from vfp.hh to vfp.cc. 2010-06-02 12:58:18 -05:00
Ali Saidi
35e35fc825 ARM: Make some of the trace code more compact 2010-06-02 12:58:18 -05:00
Gabe Black
0abec53564 ARM: Move the longer MemoryReg::printoffset function in mem.hh into the cc file. 2010-06-02 12:58:18 -05:00
Gabe Black
9223725973 ARM: Move the ISA "clear" function into isa.cc. 2010-06-02 12:58:17 -05:00
Gabe Black
b6c2548a27 ARM: Get rid of the binary dumping function in utility.hh. 2010-06-02 12:58:17 -05:00
Gabe Black
f8d2ed708b ARM: Get rid of the empty branch.cc. 2010-06-02 12:58:17 -05:00
Gabe Black
0c574987c8 ARM: Mark some ARM static inst functions as inline. 2010-06-02 12:58:17 -05:00
Gabe Black
ba7a7b0394 ARM: Move some predecoder stuff into a .cc file.
--HG--
rename : src/arch/arm/predecoder.hh => src/arch/arm/predecoder.cc
2010-06-02 12:58:17 -05:00
Gabe Black
358fdc2a40 ARM: Decode to specialized conditional/unconditional versions of instructions.
This is to avoid condition code based dependences from effectively serializing
instructions when the instruction doesn't actually use them.
2010-06-02 12:58:17 -05:00
Gabe Black
596cbe19d4 ARM: Make sure undefined unconditional ARM instructions decode as such. 2010-06-02 12:58:17 -05:00
Gabe Black
6101e1b062 ARM: Implement a version of mcr and mrc that works in user mode. 2010-06-02 12:58:17 -05:00
Gabe Black
e91e6ff9a4 ARM: Hook the misc instructions into the thumb decoder. 2010-06-02 12:58:17 -05:00
Gabe Black
22d1a84509 ARM: Move some miscellaneous instructions out of the decoder to share with thumb. 2010-06-02 12:58:17 -05:00
Gabe Black
0e556e9dfb ARM: Treat LDRD in ARM with an odd index as an undefined instruction. 2010-06-02 12:58:17 -05:00
Ali Saidi
3dc6a8070e ARM: fix sizes of structs for ARM Linux 2010-06-02 12:58:17 -05:00
Ali Saidi
d3a519ef0c ARM: Fixup native trace support and add some v7/recent stack code 2010-06-02 12:58:17 -05:00
Gabe Black
5a6bf8301a ARM: Detect a bad offset field for the VFP Ldm/Stm instructions in the decoder. 2010-06-02 12:58:17 -05:00
Gabe Black
563db6cb99 ARM: Make sure the upc is zeroed when vectoring to a fault. 2010-06-02 12:58:17 -05:00
Ali Saidi
5d67be7b1e ARM: Implement the getrusage syscall. 2010-06-02 12:58:17 -05:00
Gabe Black
6e39288be0 ARM: Implement the bkpt instruction. 2010-06-02 12:58:16 -05:00
Gabe Black
e9c8f68c0f ARM: Make undefined instructions obey predication. 2010-06-02 12:58:16 -05:00
Gabe Black
05bd3eb4ec ARM: Implement support for the IT instruction and the ITSTATE bits of CPSR. 2010-06-02 12:58:16 -05:00
Gabe Black
b93ceef538 ARM: Get rid of some of the old FP implementation. 2010-06-02 12:58:16 -05:00
Ali Saidi
c1e1de8d69 ARM: Some TLB bug fixes. 2010-06-02 12:58:16 -05:00
Ali Saidi
7de7ea3b22 ARM: Move Miscreg functions out of isa.hh 2010-06-02 12:58:16 -05:00
Ali Saidi
cb9936cfde ARM: Implement the ARM TLB/Tablewalker. Needs performance improvements. 2010-06-02 12:58:16 -05:00
Ali Saidi
f246be4cbc DMA: Make DmaPort generic enough to be used other places 2010-06-02 12:58:16 -05:00
Ali Saidi
1546d8208b ARM: SE needs a definition for PageTable::serialize/unserialize 2010-06-02 12:58:16 -05:00
Ali Saidi
d2ba9243f5 ARM: Add BKPT instruction
--HG--
rename : src/arch/arm/isa/formats/unknown.isa => src/arch/arm/isa/formats/breakpoint.isa
2010-06-02 12:58:16 -05:00
Ali Saidi
b8ec214553 ARM: Implement ARM CPU interrupts 2010-06-02 12:58:16 -05:00
Ali Saidi
3aea20d143 ARM: Start over with translation from Alpha code as opposed to something that has cruft from 4 different ISAs. 2010-06-02 12:58:16 -05:00
Gabe Black
237c0617a0 ARM: Implement conversion to/from half precision. 2010-06-02 12:58:16 -05:00
Gabe Black
04e196f422 ARM: Clean up VFP 2010-06-02 12:58:16 -05:00
Gabe Black
0fe0390f73 ARM: Clean up the implementation of the VFP instructions. 2010-06-02 12:58:16 -05:00
Gabe Black
c919ab5b4f ARM: Fix double precision load/store multiple decrement.
When decrementing, the higher addressed half of a double word is at a 4 byte
smaller displacement.
2010-06-02 12:58:15 -05:00
Gabe Black
92bdf57be4 ARM: Even though writes to MVFR0/1 should be unpredictable, we need to make them to do nothing. 2010-06-02 12:58:15 -05:00
Gabe Black
4398075254 ARM: Make various bits of the FP control registers read only. 2010-06-02 12:58:15 -05:00
Gabe Black
2d08b8de91 ARM: Implement the version of VMRS that writes to the APSR. 2010-06-02 12:58:15 -05:00
Gabe Black
57c4d37c10 ARM: Ignore reads and writes to DCIMVAC. 2010-06-02 12:58:15 -05:00
Gabe Black
fd37095fa6 ARM: Make MPIDR return 0 and ignore writes. 2010-06-02 12:58:15 -05:00
Gabe Black
49b7088b91 ARM: Implement the VCMPE instruction. 2010-06-02 12:58:15 -05:00
Gabe Black
23ba9c7b96 ARM: Fix vcvtr so that it uses the rounding mode in the FPSCR. 2010-06-02 12:58:15 -05:00
Gabe Black
1fda944716 ARM: Fix saturation of VCVT from fp to integer. 2010-06-02 12:58:15 -05:00
Gabe Black
347ab6c704 ARM: Compensate for ARM's underflow coming from -before- rounding, but x86's after. 2010-06-02 12:58:15 -05:00
Gabe Black
fd82a47b96 ARM: Implement flush to zero for destinations as well. 2010-06-02 12:58:15 -05:00
Gabe Black
186273e5f3 ARM: Fix up nans to match ARM's expected behavior. 2010-06-02 12:58:15 -05:00
Gabe Black
98e2315f1c ARM: Set the value of the MVFR0 and MVFR1 registers. 2010-06-02 12:58:15 -05:00
Gabe Black
8466999aef ARM: Implement flush to zero mode for VFP, and clean up some corner cases. 2010-06-02 12:58:15 -05:00
Gabe Black
efbceff96a ARM: Add barriers that make sure FP operations happen where they're supposed to. 2010-06-02 12:58:15 -05:00
Gabe Black
1b3b75ee68 ARM: Implement the version of VCVT float to int that rounds towards zero. 2010-06-02 12:58:15 -05:00
Gabe Black
aa05e5401c ARM: Implement the floating/fixed point VCVT instructions. 2010-06-02 12:58:15 -05:00
Gabe Black
86a1093992 ARM: Add code to extract and record VFP exceptions. 2010-06-02 12:58:14 -05:00
Gabe Black
e478df35f5 ARM: Implement the VFP version of VCMP. 2010-06-02 12:58:14 -05:00
Gabe Black
c1f7bf7f0e ARM: Add support for VFP vector mode. 2010-06-02 12:58:14 -05:00
Gabe Black
f245f4937b ARM: Introduce new VFP base classes that are optionally microops. 2010-06-02 12:58:14 -05:00
Gabe Black
41012d2418 ARM: Implement VCVT between double and single width FP. 2010-06-02 12:58:14 -05:00
Gabe Black
a430f749ce ARM: Implement vcvt between int and fp. Ignore rounding. 2010-06-02 12:58:14 -05:00
Gabe Black
a9d1de4769 ARM: Consolidate the VFP register index computation code. 2010-06-02 12:58:14 -05:00
Gabe Black
80fa3a7ccf ARM: Implement the VFP negated multiplies. 2010-06-02 12:58:14 -05:00
Gabe Black
3111a62169 ARM: Implement the VFP versions of VMLA and VMLS. 2010-06-02 12:58:14 -05:00
Gabe Black
90d70a22cb ARM: Implement the VFP version of vdiv and vsqrt. 2010-06-02 12:58:14 -05:00
Gabe Black
cc665240a4 ARM: Implement the VFP version of vsub. 2010-06-02 12:58:14 -05:00
Gabe Black
44759669aa ARM: Implement the VFP version of vadd. 2010-06-02 12:58:14 -05:00
Gabe Black
9e32ff3491 ARM: Implement the VFP version of vabs. 2010-06-02 12:58:14 -05:00
Gabe Black
cd0a6a1303 ARM: Implement the VFP version of vneg. 2010-06-02 12:58:14 -05:00
Gabe Black
65f5204325 ARM: Implement the VFP version of vmul. 2010-06-02 12:58:14 -05:00
Gabe Black
19e05d7e8d ARM: Move the VFP data operation decode into a function. 2010-06-02 12:58:14 -05:00
Gabe Black
527b735cfc ARM: Implement and update the DFSR and IFSR registers on faults. 2010-06-02 12:58:14 -05:00
Gabe Black
4491170df6 ARM: Make integer division by zero return a fault. 2010-06-02 12:58:13 -05:00
Gabe Black
cd86e34187 ARM: Add in some missing SCTLR fields. 2010-06-02 12:58:13 -05:00
Gabe Black
c5a8a1d673 ARM: Decode ARM unconditional MRC and MCR instructions. 2010-06-02 12:58:13 -05:00
Gabe Black
98fe7b0fbe ARM: Move the CP15 decode block into a function. 2010-06-02 12:58:13 -05:00
Gabe Black
5d9191a428 ARM: Decode the unconditional version of ARM fp instructions. 2010-06-02 12:58:13 -05:00
Gabe Black
81b7c3d264 ARM: Move the FP decode blocks into functions. 2010-06-02 12:58:13 -05:00
Gabe Black
e21f93702a ARM: Warn/ignore when TLB maintenance operations are performed. 2010-06-02 12:58:13 -05:00
Gabe Black
eac239b4d6 ARM: Handle accesses to TLBTR. 2010-06-02 12:58:13 -05:00
Gabe Black
9fb573d91e ARM: Handle accesses to the DACR. 2010-06-02 12:58:13 -05:00
Gabe Black
951b7edaba ARM: Handle accesses to TTBR0 and TTBR1. 2010-06-02 12:58:13 -05:00
Gabe Black
b5cfa9361b ARM: Convert the CP15 registers from MPU to MMU. 2010-06-02 12:58:13 -05:00
Ali Saidi
556ea0ee57 ARM: Add some support for wfi/wfe/yield/etc 2010-06-02 12:58:13 -05:00
Ali Saidi
5e6d28996a ARM: Move PC mode bits around so they can be used for exectrace 2010-06-02 12:58:13 -05:00
Ali Saidi
aec73ba6af ARM: Add a traceflag to print cpsr 2010-06-02 12:58:13 -05:00
Ali Saidi
65a5177b53 ARM: Undef instruction on invalid user CP15 access 2010-06-02 12:58:13 -05:00
Gabe Black
2e4ddbd234 ARM: Decode the VSTR instruction. 2010-06-02 12:58:12 -05:00
Gabe Black
6106bd18cd ARM: Implement the vstr instruction. 2010-06-02 12:58:12 -05:00
Ali Saidi
f64c8bafd2 ARM: BXJ should be BX when there is no J support 2010-06-02 12:58:12 -05:00
Gabe Black
1fcd389fa3 ARM: Make sure macroops aren't interrupted midinstruction.
Do this by setting the delayed commit flag for all but the last microop.
2010-06-02 12:58:12 -05:00
Gabe Black
67766cbf17 ARM: Fix the implementation of the VFP ldm and stm macroops.
There were four bugs in these instructions. First, the loaded value was being
stored into a floating point register as floating point, changing the value as
it was transfered. Second, the meaning of the "up" bit had been reversed.
Third, the statically sized microop array wasn't bit enough for all possible
inputs. It's now dynamically sized and should always be big enough. Fourth,
the offset was stored as an unsigned 8 bit value. Negative offsets would look
like moderately large positive offsets.
2010-06-02 12:58:12 -05:00
Gabe Black
d149e43c41 Simple CPU: Make the FloatRegs trace flag do something. 2010-06-02 12:58:12 -05:00
Gabe Black
ad9c5af945 ARM: Fix up thumb decoding of coproc instructions. 2010-06-02 12:58:12 -05:00
Gabe Black
dea707704f ARM: Clean up some redundancy and fault behavior for unimplemented thumb MCR, MRC. 2010-06-02 12:58:12 -05:00
Ali Saidi
b504b44b2f CPU: Reset fetch offset after a exception 2010-06-02 12:58:12 -05:00
Gabe Black
943b77b9bb ARM: Decode the VLDR instruction. 2010-06-02 12:58:12 -05:00
Gabe Black
4f130683e0 ARM: Implement the VLDR instruction. 2010-06-02 12:58:12 -05:00
Gabe Black
dbec303864 ARM: Decode all the various forms of vmov. 2010-06-02 12:58:12 -05:00
Gabe Black
ff3996b24d ARM: Make VFP load/store and 64 bit move decode correspond with CP10 and CP11. 2010-06-02 12:58:12 -05:00
Gabe Black
dd1aedc98b ARM: Implement the various versions of VMOV. 2010-06-02 12:58:12 -05:00
Gabe Black
1f059541d6 ARM: Add a new RegImmOp base class. 2010-06-02 12:58:12 -05:00
Gabe Black
6976b4890a ARM: Add a RegRegImmOp base class. 2010-06-02 12:58:12 -05:00
Gabe Black
186cfe3ae3 ARM: Widen the immediate fields in the misc instruction classes. 2010-06-02 12:58:12 -05:00
Gabe Black
b87ebf382f ARM: Add a function to decode VFP modified immediate constants. 2010-06-02 12:58:12 -05:00
Gabe Black
7eb4d02dd9 ARM: Add a function to decode SIMD modified immediate constants. 2010-06-02 12:58:12 -05:00
Gabe Black
abda50173c ARM: Add fp operands to operands.isa. 2010-06-02 12:58:12 -05:00
Gabe Black
6365d29c21 ARM: Decode the VMRS instruction. 2010-06-02 12:58:11 -05:00
Gabe Black
fbf2ad5ae8 ARM: Update the set of FP related miscregs. 2010-06-02 12:58:11 -05:00
Gabe Black
aade63a8fe ARM: Implement the VMRS instruction. 2010-06-02 12:58:11 -05:00
Gabe Black
a8b56b452c ARM: Decode the VMSR instruction. 2010-06-02 12:58:11 -05:00
Gabe Black
06008c54eb ARM: Implement the VMSR instruction. 2010-06-02 12:58:11 -05:00
Gabe Black
0ff71c7c34 ARM: Decode 8, 16, and 32 bit transfers between core and extension (fp) registers. 2010-06-02 12:58:11 -05:00
Gabe Black
c9c4dfc09d ARM: Ignore attempts to disable coprocessors that aren't implemented anyway. 2010-06-02 12:58:11 -05:00
Gabe Black
c3bf29bbea ARM: Implement the udiv instruction. 2010-06-02 12:58:11 -05:00
Gabe Black
f3e65c2de2 ARM: Implement the sdiv instruction. 2010-06-02 12:58:11 -05:00
Gabe Black
5943f0fc84 ARM: Ignore writing a bad mode to CPSR with MSR. 2010-06-02 12:58:11 -05:00
Gabe Black
ba33db8fd6 ARM: Decode the CPS instruction. 2010-06-02 12:58:11 -05:00
Gabe Black
7861b084f6 ARM: Implement the CPS instruction. 2010-06-02 12:58:11 -05:00
Gabe Black
eb1447302d ARM: Decode the SRS instruction. 2010-06-02 12:58:11 -05:00