The current TLM bridge only provides a Slave Port that allows the gem5
world to send request to the SystemC world. This patch series refractors
and cleans up the existing code, and adds a Master Port that allows the
SystemC world to send requests to the gem5 world.
This patch:
* bugfix: The BEGIN_RESP also needs to be handled when END_REQ was
* skipped
and '&trans == blockingRequest && phase == tlm::BEGIN_RESP'
evaluates to true.
Reviewed at http://reviews.gem5.org/r/3797/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
The current TLM bridge only provides a Slave Port that allows the gem5
world to send request to the SystemC world. This patch series refractors
and cleans up the existing code, and adds a Master Port that allows the
SystemC world to send requests to the gem5 world.
This patch:
* Implement 'pipe through' for gem5 Packets (see explanation below)
Basically, this patch ensures that all transactions that originated in the
gem5 world are converted back to the original packet when entering the gem5
world. So far, this only worked for packets that are responded to by a
SyctemC component (e.g. when a gem5 CPU sends a request to a SystemC
memory). By implementing the 'pipe through' this patch ensures, that
packets that are responded to by a gem5 component (e.g. when a gem5 CPU
sends a request to a gem5 memory via a SystemC interconnect) are handled
properly.
Reviewed at http://reviews.gem5.org/r/3796/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Changeset 11798:3a490c57058d
---------------------------
misc: Clean up and complete the gem5<->SystemC-TLM bridge [5/10]
The current TLM bridge only provides a Slave Port that allows the gem5
world to send request to the SystemC world. This patch series refractors
and cleans up the existing code, and adds a Master Port that allows the
SystemC world to send requests to the gem5 world.
This patch:
* Introduce transactor modules that represent the gem5 ports in the
* SystemC world.
* Update the SimControl module and let it keep track of the gem5 ports.
Reviewed at http://reviews.gem5.org/r/3775/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
The current TLM bridge only provides a Slave Port that allows the gem5
world to send request to the SystemC world. This patch series refractors
and cleans up the existing code, and adds a Master Port that allows the
SystemC world to send requests to the gem5 world.
This patch:
* Move common code of the example to a common directory. Move the cli
* parsing from the SimControl module to a separate example object. Add
* comments describing the Gem5SimControl module.
Testing Done: Examples compile and run.
Reviewed at http://reviews.gem5.org/r/3695/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
The current TLM bridge only provides a Slave Port that allows the gem5
world to send request to the SystemC world. This patch series refractors
and cleans up the existing code, and adds a Master Port that allows the
SystemC world to send requests to the gem5 world.
This patch:
* Simplify the Slave Port by using a simple_initiator_socket.
Testing Done: Example applications are still running.
Reviewed at http://reviews.gem5.org/r/3686/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
The current TLM bridge only provides a Slave Port that allows the gem5
world to send request to the SystemC world. This patch series refractors
and cleans up the existing code, and adds a Master Port that allows the
SystemC world to send requests to the gem5 world.
This patch:
* Add the Master Port. Add an example application that isslustrates its
* use.
Testing Done: A simple example application consisting of a TLM traffic
generator and a gem5 memory is part of the patch.
Reviewed at http://reviews.gem5.org/r/3528/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
The current TLM bridge only provides a Slave Port that allows the gem5
world to send request to the SystemC world. This patch series refractors
and cleans up the existing code, and adds a Master Port that allows the
SystemC world to send requests to the gem5 world.
This patch:
* Restructure the existing sources in preparation of the addition of the
* new
Master Port.
* Refractor names to allow for distinction of the slave and master port.
* Replace the Makefile by a SConstruct.
Testing Done: The examples provided in util/tlm (now
util/tlm/examples/slave_port) still compile and run error free.
Reviewed at http://reviews.gem5.org/r/3527/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
The Request constructor requires a MasterID. However, an external
transactor has no chance of getting a MasterID as it does not have a
pointer to the System. This patch adds a MasterID to ExternalMaster to
allow external modules to easily genrerate new Requests.
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
The CxxConfigManager schould create objects by traversing the object tree
starting from the root object. However, currently objects are created in
aplphabetical order, which only works if the root object alphabetically
comes before any system object (e.g. 'root' < 'system'. Otherwise (e.g.
'a_system' < 'root'), object construction may fail. The reason for this
behaviour is, that the call to findObject() in the sorting code also
constructs the object if it is not yet existent. Then findTraversalOrder()
calls findObject("root") and subseqeuently calls findObject() on all the
children, and so on. However, the call to findTraversalOrder() is
redundant, since all objects are already created in alphabetical order.
This patch simply removes the alphabetical ordering, leading to the objects
being created starting from 'root'.
Reviewed at http://reviews.gem5.org/r/3778/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Implementing the Module as an sc_channel allows derived classes to provide
SystemC interfaces. Other SystemC modules can connect to these interfaces.
This meachanism can be used to control gem5 and acces gem5 components from
within arbitrary SystemC moduels. Since sc_channel is derived from
sc_module, this patch does not break compatibility with existing code.
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Seeing build breakage after brandon@11801:
[ CXX] X86/sim/process.cc -> .o build/X86/sim/process.cc:137:64:
error: field '_pid' is uninitialized when used here
[-Werror,-Wuninitialized] static_cast<PageTableBase *>(new
ArchPageTable(name(), _pid, system)) : ^ build/X86/sim/process.cc:138:64:
error: field '_pid' is uninitialized when used here
[-Werror,-Wuninitialized] static_cast<PageTableBase *>(new
FuncPageTable(name(), _pid))), ^ 2 errors generated.
Testing Done: Compiles now on FreeBSD 10 with clang.
Reviewed at http://reviews.gem5.org/r/3804/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
See developers mailing list. Trying to unbreak statfs.
Testing Done:
Builds on FreeBSD now.
Reviewed at http://reviews.gem5.org/r/3803/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Various changes we found needed to build gem5 successfully on
FreeBSD.
Reviewed at http://reviews.gem5.org/r/3378/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
There are drivers writing to WUFC uncondtionally of anything. In order to
not panic gem5 in these cases, ignore writes to WUFC and WUS as we do for
WUC. Similarly return 0 (default reset value) on reads.
Testing Done: Booted in FS with such a driver revision which would
previously panic and now boots fine.
Reviewed at http://reviews.gem5.org/r/3791/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Trying to read MISCREG_CTR_EL0 on AArch64 returned 0 as is was not
implmemented. With that an operating system relying on the cache line
sizes reported in order to manage the caches would (a) panic given the
returned value 0 is not valid (high bit is RES1) or (b) worst case would
assume a cache line size of 4 doing a tremendous amount of extra
instruction work (including fetching). Return the same values as for ARMv7
as the fields seem to be the same, or RES0/1 seem to be reported
accordingly for AArch64
In collaboration with: Andrew Turner
Testing Done: Checked on FreeBSD boots with extra printfs; also observed a
reduction of a factor of about 10 in instruction fetches for a simple
micro-test.
Reviewed at http://reviews.gem5.org/r/3667/
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Python's header files set various compiler macros (e.g.,
_XOPEN_SOURCE) unconditionally. This triggers preprocessor warnings
that end up being treated as errors. The Python integration manual [1]
strongly recommends that Python.h is included before any system
header. The style guide used to mandate that Python.h is included
first in any file that needs it. This requirement was changed to
always include a source file's main header first, which ended up
triggering these errors.
This change updates the style checker to always include Python.h
before the main header file.
[1] https://docs.python.org/2/extending/extending.html
Change-Id: Id6a4f7fc64a336a8fd26691a0ca682abeb1d1579
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Pierre-Yves Péneau <pierre-yves.peneau@lirmm.fr>
protoc v3 introduces a new syntax for proto files and warns when the
syntax is not explicitly stated.
protoc relies on the fact that undefined preprocessor symbols are
explanded to 0 but since we use -Wundef they end up generating
warnings.
Change-Id: If07abeb54e932469c8f2c4d38634a97fdae40f77
Reviewed-by: Andreas Hansson <andreas.hansson@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
By default, doSyscall gets the values of six registers to be used for
system call arguments. RISC-V, by convention, only has four. Because
RISC-V's implementation of these indices is as arrays of integers rather
than as base indices plus offsets, trying to get the fifth argument
register's value will cause a crash. This patch fixes that by returning 0
for any index higher than 3.
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
This patch adds a '-n' flag to the gem5 SystemC driver which allows
multiple CPUs to be switched out to a new CPU. Primarily this involves
appending CPU numbers to the objects searched for in the config
manager if there are multiple CPUs in the system.
Note that an equivalent change should be made to the util/cxx_config driver,
but I wanted to get input on this first before making the same change over
there
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Swig wrappers for native objects currently share the _m5.internal name
space with Python code. This is undesirable if we ever want to switch
from Swig to some other framework for native binding (e.g., PyBind11
or Boost::Python). This changeset moves all of such wrappers to the
_m5 namespace, which is now reserved for native code.
Change-Id: I2d2bc12dbc05b57b7c5a75f072e08124413d77f3
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Curtis Dunham <curtis.dunham@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Used cppclean to help identify useless includes and removed them. This
involved erroneously included headers, but also cases where forward
declarations could have been used rather than a full include.
the GPUCoalescer code is used in the ruby profiler regardless of
whether or not the coalescer code has been compiled, which can
lead to link/run time errors. here we add #ifdefs to guard the
usage of GPUCoalescer code. eventually we should refactor this
code to use probe points.
Garnet's NetworkInterface does not consider the size of MessageBuffers when
ejecting a Message from the network. Add a size check for the MessageBuffer
and only enqueue if space is available. If space is not available, the
message if placed in a queue and the credit is held. A callback from the
MessageBuffer is implemented to wake the NetworkInterface. If there are
messages in the stalled queue, they are processed first, in a FIFO manner
and if succesfully ejected, the credit is finally sent back upstream. The
maximum size of the stall queue is equal to the number of valid VNETs
with MessageBuffers attached.
This patch is an updated version of /r/3297.
"The most important statistic for measuring memory hierarchy performance is
throughput, which is affected by independent variables, buffer sizing and
communication latency. It is difficult/impossible to debug performance issues
through series buffers without knowing which are the bottlenecks. For finite
buffers, this patch adds statistics for the average number of messages in the
buffer, the occupancy of the buffer slots, and number of message stalls."
The NetworkInterface wakeup currently iterates over all VNETs and breaks the
loop if a VNET is unable to allocate a VC. This can cause a deadlock if a
lower numbered VNET is unable to allocate a VC while a higher numbered VNET
has idle VCs. This seems like a bug as Garnet 1.0 uses a while loop over an
if-statement, suggesting the break was intended for this while loop. This
patch removes the break statement, which allows up to one message to be
dequeued from a VNET and injected into the network.
The class was crammed into syscall_emul.hh which has tons of forward
declarations and template definitions. To clean it up a bit, moved the
class into separate files and commented the class with doxygen style
comments. Also, provided some encapsulation by adding some accessors and
a mutator.
The syscallreturn.hh file was renamed syscall_return.hh to make it consistent
with other similarly named files in the src/sim directory.
The DPRINTF_SYSCALL macro was moved into its own header file with the
include the Base and Verbose flags as well.
--HG--
rename : src/sim/syscallreturn.hh => src/sim/syscall_return.hh
The non-standard sc_time constructors
- sc_time( uint64, bool scale )
- sc_time( double, bool scale )
have been deprecated in SystemC 2.3.1 and a warning is issued when being
used. Insted the new 'sc_time::from_value' function is used to omit the
warning message.
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Updates for READMEs of /util/cxx_config, /util/systemc, /util/tlm.
Some minor corrections, mostly with respect to MAC/OSX
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Bugfix for Elastic Traces
This patch fixes the bug when elastic traces are used:
build/ARM/gem5.opt \
configs/example/fs.py \
--cpu-type=arm_detailed \
--num-cpu=1 \
--mem-type=SimpleMemory \
--mem-size=512MB \
--mem-channels=1 \
--caches \
--elastic-trace-en \
--data-trace-file=data.proto.gz \
--inst-trace-file=inst.proto.gz \
--machine-type=VExpress_EMM \
--dtb-filename=vexpress.aarch32.ll_20131205.0-gem5.1cpu.dtb \
--kernel=vmlinux.aarch32.ll_20131205.0-gem5 \
--disk-image=linux-aarch32-ael.img
NameError: global name 'CpuConfig' is not defined
Signed-off by: Jason Lowe-Power <jason@lowepower.com>
The CountedDrainEvent event was used to keep track of objects that
required additional simulation to drain. It was removed as a part of
the great drain rewrite, but the declaration remained.
Change-Id: I767a3213669040d3f27e2afafa2e4a5bb997e325
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Curtis Dunham <curtis.dunham@arm.com>
Call the stat visitor from the stat itself rather than casting stats
in Python. This reduces the number of ways visitors are called.
Change-Id: Ic4d0b7b32e3ab9897b9a34cd22d353f4da62d738
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Sascha Bischoff <sascha.bischoff@arm.com>
Reviewed-by: Curtis Dunham <curtis.dunham@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Joe Gross <joseph.gross@amd.com>
The headers declared in export_method_cxx_predecls are redundant since a
SimObject's main header is automatically included.
Change-Id: Ied9e84630b36960e54efe91d16f8c66fba7e0da0
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Curtis Dunham <curtis.dunham@arm.com>
Reviewed-by: Joe Gross <joseph.gross@amd.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
This changeset adds a maintainer script, create_patches.sh, that can
be used to prepare for upstream from a git repository. The script can
be used to generate patches in Mercurial or git format. The commit
messages in the exported patches are all filtered, see
upstream_msg_filter.sed, to ensure that irrelevant meta data isn't
included in the upstream commit.
Kudos to Curtis Dunham and Nikos Nikoleris for reviews and usability
enhancements for earlier versions of this patch.
Change-Id: Ia4cd089a32834b5e046ef58c0a173ca285b77bca
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Curtis Dunham <curtis.dunham@arm.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
When restoring from a checkpoint, the simulation used to use file handles from
the checkpoint. This disallows multiple separate restore simulations from using
separate input and output files and directories, and plays havoc when the
checkpointed file locations may have changed. Add handling to allow the command
line specified files to be used as input/output for the restored simulation
(Note: this is the similar functionality to FS mode for output and error).
The Minor and o3 cpu models share the branch prediction
code. Minor relies on the BPredUnit::squash() function
to update the branch predictor tables on a branch mispre-
diction. This is fine because Minor executes in-order, so
the update is on the correct path. However, this causes the
branch predictor to be updated on out-of-order branch
mispredictions when using the o3 model, which should not
be the case.
This patch guards against speculative update of the branch
prediction tables. On a branch misprediction, BPredUnit::squash()
calls BpredUnit::update(..., squashed = true). The underlying
branch predictor tests against the value of squashed. If it is
true, it restores any speculatively updated internal state
it might have (e.g., global/local branch history), then returns.
If false, it updates its prediction tables. Previously, exist-
ing predictors did not test against the "squashed" parameter.
To accomodate for this change, the Minor model must now call
BPredUnit::squash() then BPredUnit::update(..., squashed = false)
on branch mispredictions. Before, calling BpredUnit::squash()
performed the prediction tables update.
The effect is a slight MPKI improvement when using the o3
model. A further patch should perform the same modifications
for the indirect target predictor and BTB (less critical).
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
The tournament predictor is presented as doing speculative
update of the global history and non-speculative update
of the local history used to generate the branch prediction.
However, the code does speculative update of both histories.
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
The target of taken conditional direct branches does not
need to be resolved in IEW: the target can be computed at
decode, usually using the decoded instruction word and the PC.
The higher-than-necessary penalty is taken only on conditional
branches that are predicted taken but miss in the BTB. Thus,
this is mostly inconsequential on IPC if the BTB is big/associative
enough (fewer capacity/conflict misses). Nonetheless, what gem5
simulates is not representative of how conditional branch targets
can be handled.
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
cachePorts currently constrains the number of store packets written to the
D-Cache each cycle), but loads currently affect this variable. This leads
to unexpected congestion (e.g., setting cachePorts to a realistic 1 will
in fact allow a store to WB only if no loads have accessed the D-Cache
this cycle). In the absence of arbitration, this patch decouples how many
loads can be done per cycle from how many stores can be done per cycle.
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
When Ruby controllers stall messages in MessageBuffers, the buffer moves those
messages off the priority heap and into a per-address stall map. When buffers
are finite-sized, the test areNSlotsAvailable() only checks the size of the
priority heap, but ignores the stall map, so the map is allowed to grow
unbounded if the controller stalls numerous messages. This patch fixes the
problem by tracking the stall map size and testing the total number of messages
in the buffer appropriately.
the iterator declared in DMASequencer::ackCallback() is only used in an
assert, this causes clang to fail when building fast. here we move
the find call on the request table directly into the assert.
The aforementioned upgrader in [1] assumes every option in [system]
has a delimiting '.', and also seems to do its rewriting work a bit too
unconditionally. Most checkpoints in the wild don't have this device,
in which case this script should be a safe no-op.
[1] 2aa4d7b dist, dev: Fixed the packet ordering in etherswitch
Change-Id: Icfd0350985109df1628eb9ab864cda42c54060a8
Reviewed-by: Gabor Dozsa <gabor.dozsa@arm.com>
