This patch moves the code for functional accesses to ruby system. This is
because the subsequent patches add support for making functional accesses
to the messages in the interconnect. Making those accesses from the ruby port
would be cumbersome.
In the current caches the hit latency is paid twice on a miss. This patch lets
a configurable response latency be set of the cache for the backward path.
This patch adds a function, periodicStatDump(long long period), which will dump
and reset the statistics every period. This function is designed to be called
from the python configuration scripts. This allows the periodic stats dumping to
be configured more easilly at run time.
The period is currently specified as a long long as there are issues passing
Tick into the C++ from the python as they have conflicting definitions. If the
period is less than curTick, the first occurance occurs at curTick. If the
period is set to 0, then the event is descheduled and the stats are not
periodically dumped.
Due to issues when resumung from a checkpoint, the StatDump event must be moved
forward such that it occues AFTER the current tick. As the function is called
from the python, the event is scheduled before the system resumes from the
checkpoint. Therefore, the event is moved using the updateEvents() function.
This is called from simulate.py once the system has resumed from the checkpoint.
NOTE: It should be noted that this is a fairly temporary patch which re-adds the
capability to extract temporal information from the communication monitors. It
should not be used at the same time as anything that relies on dumping the
statistics based on in simulation events i.e. a context switch.
Newer Linux kernels require DTB (device tree blobs) to specify platform
configurations. The input DTB filename can be specified through gem5 parameters
in LinuxArmSystem.
Instead of statically defining miscRegName to contain NUM_MISCREGS
elements, let the compiler determine the length of the array. This
allows us to use a static_assert to test that all registers are listed
in the name vector.
C++11 has support for static_asserts to provide compile-time assertion
checking. This is very useful when testing, for example, structure
sizes to make sure that the compiler got the right alignment or vector
sizes.
Remove SimObject::setMemoryMode from the main SimObject class since it
is only valid for the System class. In addition to removing the method
from the C++ sources, this patch also removes getMemoryMode and
changeTiming from SimObject.py and updates the simulation code to call
the (get|set)MemoryMode method on the System object instead.
This patch adds an explicit dependency between param_%s.i and the
Python source file defining the object. Previously, the build system
didn't rebuild SWIG interfaces correctly when an object's Python
sources were updated.
Fix the drain functionality of the RubyPort to only call drain on child ports
during a system-wide drain process, instead of calling each time that a
ruby_hit_callback is executed.
This fixes the issue of the RubyPort ports being reawakened during the drain
simulation, possibly with work they didn't previously have to complete. If
they have new work, they may call process on the drain event that they had
not registered work for, causing an assertion failure when completing the
drain event.
Also, in RubyPort, set the drainEvent to NULL when there are no events
to be drained. If not set to NULL, the drain loop can result in stale
drainEvents used.
This patch introduces a high-level model of a DRAM controller, with a
basic read/write buffer structure, a selectable and customisable
arbiter, a few address mapping options, and the basic DRAM timing
constraints. The parameters make it possible to turn this model into
any desired DDRx/LPDDRx/WideIOx memory controller.
The intention is not to be cycle accurate or capture every aspect of a
DDR DRAM interface, but rather to enable exploring of the high-level
knobs with a good simulation speed. Thus, contrary to e.g. DRAMSim
this module emphasizes simulation speed with a good-enough accuracy.
This module is merely a starting point, and there are plenty additions
and improvements to come. A notable addition is the support for
address-striping in the bus to enable a multi-channel DRAM
controller. Also note that there are still a few "todo's" in the code
base that will be addressed as we go along.
A follow-up patch will add basic performance regressions that use the
traffic generator to exercise a few well-defined corner cases.
This patch adds a traffic generator to the code base. The generator is
aimed to be used as a black box model to create appropriate use-cases
and benchmarks for the memory system, and in particular the
interconnect and the memory controller.
The traffic generator is a master module, where the actual behaviour
is captured in a state-transition graph where each state generates
some sort of traffic. By constructing a graph it is possible to create
very elaborate scenarios from basic generators. Currencly the set of
generators include idling, linear address sweeps, random address
sequences and playback of traces (recording will be done by the
Communication Monitor in a follow-up patch). At the moment the graph
and the states are described in an ad-hoc line-based format, and in
the future this should be aligned with our used of e.g. the Google
protobufs. Similarly for the traces, the format is currently a
simplistic ad-hoc line-based format that merely serves as a starting
point.
In addition to being used as a black-box model for system components,
the traffic generator is also useful for creating test cases and
regressions for the interconnect and memory system. In future patches
we will use the traffic generator to create DRAM test cases for the
controller model.
The patch following this one adds a basic regressions which also
contains an example configuration script and trace file for playback.
This patch ignores the FUTEX_PRIVATE_FLAG of the sys_futex system call
in SE mode.
With this patch, when sys_futex with the options FUTEX_WAIT_PRIVATE or
FUTEX_WAKE_PRIVATE is emulated, the FUTEX_PRIVATE_FLAG is ignored and
so their behaviours are the regular FUTEX_WAIT and FUTEX_WAKE.
Emulating FUTEX_WAIT_PRIVATE and FUTEX_WAKE_PRIVATE as if they were
non-private is safe from a functional point of view. The
FUTEX_PRIVATE_FLAG does not change the semantics of the futex, it's
just a mechanism to improve performance under certain circunstances
that can be ignored in SE mode.
This patch removes the unused file parameter from the
AbstractMemory. The patch serves to make it easier to transition to a
separation of the actual contigious host memory backing store, and the
gem5 memory controllers.
Without the file parameter it becomes easier to hide the creation of
the mmap in the PhysicalMemory, as there are no longer any reasons to
expose the actual contigious ranges to the user.
To the best of my knowledge there is no use of the parameter, so the
change should not affect anyone.
This patch takes the final plunge and transitions from the templated
Range class to the more specific AddrRange. In doing so it changes the
obvious Range<Addr> to AddrRange, and also bumps the range_map to be
AddrRangeMap.
In addition to the obvious changes, including the removal of redundant
includes, this patch also does some house keeping in preparing for the
introduction of address interleaving support in the ranges. The Range
class is also stripped of all the functionality that is never used.
--HG--
rename : src/base/range.hh => src/base/addr_range.hh
rename : src/base/range_map.hh => src/base/addr_range_map.hh
This patch simplifies the Range class in preparation for the
introduction of a more specific AddrRange class that allows
interleaving/striping.
The only place where the parsing was used was in the unit test.
This patch simply removes the unused range_multimap in preparation for
a more specific AddrRangeMap that also allows interleaving in addition
to pure ranges.
This patch simplifies the Range object hierarchy in preparation for an
address range class that also allows striping (e.g. selecting a few
bits as matching in addition to the range).
To extend the AddrRange class to an AddrRegion, the first step is to
simplify the hierarchy such that we can make it as lean as possible
before adding the new functionality. The only class using Range and
MetaRange is AddrRange, and the three classes are now collapsed into
one.
This patch removes the use of g_system_ptr for event scheduling. Each consumer
object now needs to specify upfront an EventManager object it would use for
scheduling events. This makes the ruby memory system more amenable for a
multi-threaded simulation.
This patch makes a minor addition to the SimpleMemory by enforcing a
maximum data rate. The bandwidth is configurable, and a reasonable
value (12.8GB/s) has been choosen as the default.
The changes do add some complexity to the SimpleMemory, but they
should definitely be justifiable as this enables a far more realistic
setup using even this simple memory controller.
The rate regulation is done for reads and writes combined to reflect
the bidirectional data busses used by most (if not all) relevant
memories. Moreover, the regulation is done per packet as opposed to
long term, as it is the short term data rate (data bus width times
frequency) that is the limiting factor.
A follow-up patch bumps the stats for the regressions.
This patch adds Link-Time Optimization when building the fast target
using gcc >= 4.6, and adds a scons flag to disable it (-no-lto). No
check is performed to guarantee that the linker supports LTO and use
of the linker plugin, so the user has to ensure that binutils GNU ld
>= 2.21 or the gold linker is available. Typically, if gcc >= 4.6 is
available, the latter should not be a problem. Currently the LTO
option is only useful for gcc >= 4.6, due to the limited support on
clang and earlier versions of gcc. The intention is to also add
support for clang once the LTO integration matures.
The same number of jobs is used for the parallel phase of LTO as the
jobs specified on the scons command line, using the -flto=n flag that
was introduced with gcc 4.6. The gold linker also supports concurrent
and incremental linking, but this is not used at this point.
The compilation and linking time is increased by almost 50% on
average, although ARM seems to be particularly demanding with an
increase of almost 100%. Also beware when using this as gcc uses a
tremendous amount of memory and temp space in the process. You have
been warned.
After some careful consideration, and plenty discussions, the flag is
only added to the fast target, and the warning that was issued in an
earlier version of this patch is now removed. Similarly, the flag used
to enable LTO, now the default is to use it, and the flag has been
modified to disable LTO. The rationale behind this decision is that
opt is used for development, whereas fast is only used for long runs,
e.g. regressions or more elaborate experiments where the additional
compile and link time is amortized by a much larger run time.
When it comes to the return on investment, the regression seems to be
roughly 15% faster with LTO. For a bit more detail, I ran twolf on
ARM.fast, with three repeated runs, and they all finish within 42
minutes (+- 25 seconds) without LTO and 31 minutes (+- 25 seconds)
with LTO, i.e. LTO gives an impressive >25% speed-up for this case.
Without LTO (ARM.fast twolf)
real 42m37.632s
user 42m34.448s
sys 0m0.390s
real 41m51.793s
user 41m50.384s
sys 0m0.131s
real 41m45.491s
user 41m39.791s
sys 0m0.139s
With LTO (ARM.fast twolf)
real 30m33.588s
user 30m5.701s
sys 0m0.141s
real 31m27.791s
user 31m24.674s
sys 0m0.111s
real 31m25.500s
user 31m16.731s
sys 0m0.106s
This patch adds a new target called 'perf' that facilitates profiling
using google perftools rather than gprof. The perftools CPU profiler
offers plenty useful information in addition to gprof, and the latter
is kept mostly to offer profiling also on non-Linux hosts.
This patch restructures the ccflags such that the common parts are
defined in a single location, also capturing all the target types in a
single place.
The patch also adds a corresponding ldflags in preparation for
google-perf profiling support and the addition of Link-Time
Optimization.
This patch shifts the version of gcc for which we enable c++0x from
4.6 to 4.4 The more long term plan is to see what the c++0x features
can bring and what level of support would be enabled simply by bumping
the required version of gcc from 4.3 to 4.4.
A few minor things had to be fixed in the code base, most notably the
choice of a hashmap implementation. In the Ruby Sequencer there were
also a few minor issues that gcc 4.4 was not too happy about.
When switching from an atomic CPU to any of the timing CPUs, a drain is
unnecessary since no events are scheduled in atomic mode. However, when
trying to switch CPUs starting with a timing CPU, there may be events
scheduled. This change ensures that all events are drained from the system
by calling m5.drain before switching CPUs.
The profileEvent pointer is tested against NULL in various places, but
it is not initialized unless running in full-system mode. In SE mode, this
can result in segmentation faults when profileEvent default intializes to
something other than NULL.
This patch addresses a few minor issues reported by the clang static
analyzer.
The analysis was run with:
scan-build -disable-checker deadcode \
-enable-checker experimental.core \
-disable-checker experimental.core.CastToStruct \
-enable-checker experimental.cpluscplus
This seperates the functionality to clear the state in a block into
blk.hh and the functionality to udpate the tag information into the
tags. This gets rid of the case where calling invalidateBlk on an
already-invalid block does something different than calling it on a
valid block, which was confusing.
The patch introduces two predicates for condition code registers -- one
tests if a register needs to be read, the other tests whether a register
needs to be written to. These predicates are evaluated twice -- during
construction of the microop and during its execution. Register reads
and writes are elided depending on how the predicates evaluate.
The D flag bit is part of the cc flag bit register currently. But since it
is not being used any where in the implementation, it creates an unnecessary
dependency. Hence, it is being moved to a separate register.
This patch is meant for allowing predicated reads and writes. Note that this
predication is different from the ISA provided predication. They way we
currently provide the ISA description for X86, we read/write registers that
do not need to be actually read/written. This is likely to be true for other
ISAs as well. This patch allows for read and write predicates to be associated
with operands. It allows for the register indices for source and destination
registers to be decided at the time when the microop is constructed. The
run time indicies come in to play only when the at least one of the
predicates has been provided. This patch will not affect any of the ISAs that
do not provide these predicates. Also the patch assumes that the order in
which operands appear in any function of the microop is same across all the
functions of the microops. A subsequent patch will enable predication for the
x86 ISA.
If I understand correctly, this was put in place so that a debugger can be
attached when the protocol aborts. While this sounds useful, it is a problem
when the simulation is not being actively monitored. I think it is better to
remove this.
Despite gzwrite taking an unsigned for length, it returns an int for
bytes written; gzwrite fails if (int)len < 0. Because of this, call
gzwrite with len no larger than INT_MAX: write in blocks of INT_MAX if
data to be written is larger than INT_MAX.
This patch prunes the range_ops header that is no longer used. The
bridge used it to do filtering of address ranges, but this is changed
since quite some time.
Ultimately this patch aims to simplify the handling of ranges before
specialising the AddrRange to an AddrRegion that also allows striping
bits to be selected.
This patch aims to simplify the use of the Range class before
introducing a more elaborate AddrRegion to replace the AddrRange. The
SackRange is the only use of the range class besides address ranges,
and the removal of this use makes for an easier modification of the
range class.
The functionlity that is removed with this patch is not used anywhere
throughout the code base.
This patch addresses a previously highlighted issue with the default
latencies used for PIO and PCI devices. The values are merely educated
guesses and might not represent the particular system you want to
model. However, the values in this patch are definitely far more
realistic than the previous ones.
In i8254xGBe, the writeConfig method is updated to use configDelay
instead of pioDelay.
A follow-up patch will update the regression stats.
Includes a small change in sim_object.cc that adds the name space to
the output stream parameter in serializeAll. Leaving out the name
space unfortunately confuses Doxygen.
Simulation objects normally register derived statistics, presumably
what regFormulas originally was meant for, in regStats(). This patch
removes regRegformulas since there is no need to have a separate
method call to register formulas.
Implement some code we used to panic on as it actually does happen with the
e1000 driver in Linux 3.3+. We used to assume that a TSO header would never
be part of a larger payload, however it appears as though it now can be.
Some bare metal build flows seem to build binaries that we aren't necessarily
expecting. Initialize everything to 0, so we don't make any assumptions about
what is or isn't in the binary.
This patch is a first step to using Cycles as a parameter type. The
main affected modules are the CPUs and the Ruby caches. There are
definitely plenty more places that are affected, but this patch serves
as a starting point to making the transition.
An important part of this patch is to actually enable parameters to be
specified as Param.Cycles which involves some changes to params.py.
The =operator for the DataBlock class was incorrectly interpreting the class
member m_alloc. This variable stands for whether the assigned memory for the
data block needs to be freed or not by the class itself. It seems that the
=operator interpreted the variable as whether the memory is assigned to the
data block. This wrong interpretation was causing values not to propagate
to RubySystem::m_mem_vec_ptr. This caused major issues with restoring from
checkpoints when using a protocol which verified that the cache data was
consistent with the backing store (i.e. MOESI-hammer).
This patch addresses the comments and feedback on the preceding patch
that reworks the clocks and now more clearly shows where cycles
(relative cycle counts) are used to express time.
Instead of bumping the existing patch I chose to make this a separate
patch, merely to try and focus the discussion around a smaller set of
changes. The two patches will be pushed together though.
This changes done as part of this patch are mostly following directly
from the introduction of the wrapper class, and change enough code to
make things compile and run again. There are definitely more places
where int/uint/Tick is still used to represent cycles, and it will
take some time to chase them all down. Similarly, a lot of parameters
should be changed from Param.Tick and Param.Unsigned to
Param.Cycles.
In addition, the use of curTick is questionable as there should not be
an absolute cycle. Potential solutions can be built on top of this
patch. There is a similar situation in the o3 CPU where
lastRunningCycle is currently counting in Cycles, and is still an
absolute time. More discussion to be had in other words.
An additional change that would be appropriate in the future is to
perform a similar wrapping of Tick and probably also introduce a
Ticks class along with suitable operators for all these classes.
This patch introduces the notion of a clock update function that aims
to avoid costly divisions when turning the current tick into a
cycle. Each clocked object advances a private (hidden) cycle member
and a tick member and uses these to implement functions for getting
the tick of the next cycle, or the tick of a cycle some time in the
future.
In the different modules using the clocks, changes are made to avoid
counting in ticks only to later translate to cycles. There are a few
oddities in how the O3 and inorder CPU count idle cycles, as seen by a
few locations where a cycle is subtracted in the calculation. This is
done such that the regression does not change any stats, but should be
revisited in a future patch.
Another, much needed, change that is not done as part of this patch is
to introduce a new typedef uint64_t Cycle to be able to at least hint
at the unit of the variables counting Ticks vs Cycles. This will be
done as a follow-up patch.
As an additional follow up, the thread context still uses ticks for
the book keeping of last activate and last suspend and this should
probably also be changed into cycles as well.
This patch tightens up the semantics around port binding and checks
that the ports that are being bound are currently not connected, and
similarly connected before unbind is called.
The patch consequently also changes the order of the unbind and bind
for the switching of CPUs to ensure that the rules are adhered
to. Previously the ports would be "over-written" without any check.
There are no changes in behaviour due to this patch, and the only
place where the unbind functionality is used is in the CPU.
This patch updates how the checker CPU handles the ports such that the
regressions will once again run without causing a panic.
A minor amount of tidying up was also done as part of this patch.
This patch disables a warning for unused values which causes problems
when compiling the swig-generated sources using recent llvm-based
compilers like llvm-gcc and clang.
The memory size variable was a 32-bit int. This meant that the size of the
memory was limited to 4GB. This patch changes the type of the variable to
64-bit to support larger memory sizes. Thanks to Raghuraman Balasubramanian
for bringing this to notice.
This patch does a bunch of house-keeping updates on the DMA, including
indentation, and formatting, but most importantly breaks out the
response handling such that it can be shared between the atomic and
timing modes. It also removes a potential bug caused by the atomic
handling of responses only deleting the allocated request (pkt->req)
once the DMA action completes instead of doing so for every packet.
Before this patch, the handling of responses was near identical for
atomic and timing, but the code was simply duplicated. With this
patch, the handleResp method deals with the responses in both cases.
There are further updates to make after removing the NACKs, but that
will be part of a separate follow-up patch. This patch does not change
the behaviour of any regression.
This patch removes the NACK frrom the packet as there is no longer any
module in the system that issues them (the bridge was the only one and
the previous patch removes that).
The handling of NACKs was mostly avoided throughout the code base, by
using e.g. panic or assert false, but in a few locations the NACKs
were actually dealt with (although NACKs never occured in any of the
regressions). Most notably, the DMA port will now never receive a NACK
and the backoff time is thus never changed. As a consequence, the
entire backoff mechanism (similar to a PCI bus) is now removed and the
DMA port entirely relies on the bus performing the arbitration and
issuing a retry when appropriate. This is more in line with e.g. PCIe.
Surprisingly, this patch has no impact on any of the regressions. As
mentioned in the patch that removes the NACK from the bridge, a
follow-up patch should change the request and response buffer size for
at least one regression to also verify that the system behaves as
expected when the bridge fills up.
This patch removes the NACKing in the bridge, as the split
request/response busses now ensure that protocol deadlocks do not
occur, i.e. the message-dependency chain is broken by always allowing
responses to make progress without being stalled by requests. The
NACKs had limited support in the system with most components ignoring
their use (with a suitable call to panic), and as the NACKs are no
longer needed to avoid protocol deadlocks, the cleanest way is to
simply remove them.
The bridge is the starting point as this is the only place where the
NACKs are created. A follow-up patch will remove the code that deals
with NACKs in the endpoints, e.g. the X86 table walker and DMA
port. Ultimately the type of packet can be complete removed (until
someone sees a need for modelling more complex protocols, which can
now be done in parts of the system since the port and interface is
split).
As a consequence of the NACK removal, the bridge now has to send a
retry to a master if the request or response queue was full on the
first attempt. This change also makes the bridge ports very similar to
QueuedPorts, and a later patch will change the bridge to use these. A
first step in this direction is taken by aligning the name of the
member functions, as done by this patch.
A bit of tidying up has also been done as part of the simplifications.
Surprisingly, this patch has no impact on any of the
regressions. Hence, there was never any NACKs issued. In a follow-up
patch I would suggest changing the size of the bridge buffers set in
FSConfig.py to also test the situation where the bridge fills up.
This patch extends the queued port interfaces with methods for
scheduling the transmission of a timing request/response. The methods
are named similar to the corresponding sendTiming(Snoop)Req/Resp,
replacing the "send" with "sched". As the queues are currently
unbounded, the methods always succeed and hence do not return a value.
This functionality was previously provided in the subclasses by
calling PacketQueue::schedSendTiming with the appropriate
parameters. With this change, there is no need to introduce these
extra methods in the subclasses, and the use of the queued interface
is more uniform and explicit.
This patch removes the overloading of the parameter, which seems both
redundant, and possibly incorrect.
The PciConfigAll now also uses a Param.Latency rather than a
Param.Tick. For backwards compatibility it still sets the pio_latency
to 1 tick. All the comments have also been updated to not state that
it is in simticks when it is not necessarily the case.
This patch removes the overloading of the parameter, which seems both
redundant, and possibly incorrect.
The inorder CPU is particularly interesting as it uses a different
name for the parameter, and never make any use of it internally.
This patch allows packets to be enqueued in the same tick as they are
intended to be sent. This does not imply they actually are sent that
tick, although that is possible.
This change is useful for module that use the queued ports primarly to
avoid handling the flow control involved in sending and retrying
packets.
This patch tidies up the EventManager constructor and prunes a corner
case where the EventManager would initialise its eventq pointer to
NULL. This would cause segmentation faults on actual use and should
never happen.
This patch makes the Tick unsigned and removes the UTick typedef. The
ticks should never be negative, and there was only one major issue
with removing it, caused by the o3 CPU using a -1 as an initial value.
The patch has no impact on any regressions.
This patch moves the clock of the CPU, bus, and numerous devices to
the new class ClockedObject, that sits in between the SimObject and
MemObject in the class hierarchy. Although there are currently a fair
amount of MemObjects that do not make use of the clock, they
potentially should do so, e.g. the caches should at some point have
the same clock as the CPU, potentially with a 1:n ratio. This patch
does not introduce any new clock objects or object hierarchies
(clusters, clock domains etc), but is still a step in the direction of
having a more structured approach clock domains.
The most contentious part of this patch is the serialisation of clocks
that some of the modules (but not all) did previously. This
serialisation should not be needed as the clock is set through the
parameters even when restoring from the checkpoint. In other words,
the state is "stored" in the Python code that creates the modules.
The nextCycle methods are also simplified and the clock phase
parameter of the CPU is removed (this could be part of a clock object
once they are introduced).
Alpha System was overriding loadState() function to setup some functional
event. The system tried to read/write to memory before the Ruby memory had
unserialized the state. With this patch, Alpha System overrides the
startup() function, and sets up functional events in this function. This
works because startup() is called after Ruby memory system has unserialized
the memory state.
This patch fixes some problems with the drain/switchout functionality
for the O3 cpu and for the ARM ISA and adds some useful debug print
statements.
This is an incremental fix as there are still a few bugs/mem leaks with the
switchout code. Particularly when switching from an O3CPU to a
TimingSimpleCPU. However, when switching from O3 to O3 cores with the ARM ISA
I haven't encountered any more assertion failures; now the kernel will
typically panic inside of simulation.
New tool chains seem to be looking for kernel versions newer than what
this this was previously set to. Also take this opportunity to change
the hostname we report in uname to sim.gem5.org.
This patch moves instantiateTopology into Ruby.py and removes the
mem/ruby/network/topologies directory. It also adds some extra inheritance to
the topologies to clean up some issues in the existing topologies.
Off-by-one loop termination meant that we were stuffing
the terminating '\0' into the std::string value, which
makes for difficult-to-debug string comparison failures.
This replaces a (potentially uninitialized) string
field with a virtual function so that we can have
a safe interface without requiring changes to the
eio code.
Enable different whitelists for different OS/arch combinations,
since some use the generic Linux definitions only, and others
use definitions inherited from earlier Unix flavors on those
architectures.
Also update x86 function pointers so ioctl is no longer
unimplemented on that platform.
This patch is a revised version of Vince Weaver's earlier patch.
when using the checker i ran into problems where an instruction reading the
cpu id register failed because the ids did not match, and hence, the result
of the instruction did not match. this patch ensures that the ids match so
this instruction does not fail. this problem only seemed to manifest itself
when multiple cores were in the system, either multi-core, or extra switched-
out cores present in the system.
removes the optimization that forwards an exclusive copy to a requester on a
read, only for the i-cache. this optimization isn't necessary because we
typically won't be writing to the i-cache.
According to the A15 TRM the value of this register is as follows (assuming 16 word = 64 byte lines)
[31:29] Format - b100 specifies v7
[28] RAZ - b0
[27:24] CWG log2(max writeback size #words) - 0x4 16 words
[23:20] ERG log2(max reservation size #words) - 0x4 16 words
[19:16] DminLine log2(smallest dcache line #words) - 0x4 16 words
[15:14] L1Ip L1 index/tagging policy - b11 specifies PIPT
[13:4] RAZ - b0000000000
[3:0] IminLine log2(smallest icache line #words) - 0x4 16 words
This patch changes the simple memory to have a single slave port
rather than a vector port. The simple memory makes no attempts at
modelling the contention between multiple ports, and any such
multiplexing and demultiplexing could be done in a bus (or crossbar)
outside the memory controller. This scenario also matches with the
ongoing work on a SimpleDRAM model, which will be a single-ported
single-channel controller that can be used in conjunction with a bus
(or crossbar) to create a multi-port multi-channel controller.
There are only very few regressions that make use of the vector port,
and these are all for functional accesses only. To facilitate these
cases, memtest and memtest-ruby have been updated to also have a
"functional" bus to perform the (de)multiplexing of the functional
memory accesses.
This patch removes printConfig() functions from all structures in Ruby.
Most of the information is already part of config.ini, and where ever it
is not, it would become in due course.
This enables configuration scripts to set up mappings
from process virtual addresses to specific physical
addresses in SE mode. This feature is needed to
support modeling of user-accessible memories or
devices in SE mode, avoiding the complexities of FS
mode and the need to write a device driver.
This patch models a cache as separate tag and data arrays. The patch exposes
the banked array as another resource that is checked by SLICC before a
transition is allowed to execute. This is similar to how TBE entries and slots
in output ports are modeled.
Updates to Ruby to support statistics counting of cache accesses. This feature
serves multiple purposes beyond simple stats collection. It provides the
foundation for ruby to model the cache tag and data arrays as physical
resources, as well as provide the necessary input data for McPAT power
modeling.
Instead of just passing a list of controllers to the makeTopology function
in src/mem/ruby/network/topologies/<Topo>.py we pass in a function pointer
which knows how to make the topology, possibly with some extra state set
in the configs/ruby/<protocol>.py file. Thus, we can move all of the files
from network/topologies to configs/topologies. A new class BaseTopology
is added which all topologies in configs/topologies must inheirit from and
follow its API.
--HG--
rename : src/mem/ruby/network/topologies/Crossbar.py => configs/topologies/Crossbar.py
rename : src/mem/ruby/network/topologies/Mesh.py => configs/topologies/Mesh.py
rename : src/mem/ruby/network/topologies/MeshDirCorners.py => configs/topologies/MeshDirCorners.py
rename : src/mem/ruby/network/topologies/Pt2Pt.py => configs/topologies/Pt2Pt.py
rename : src/mem/ruby/network/topologies/Torus.py => configs/topologies/Torus.py
This patch renames the queue() accessor to the less ambigious
eventQueue, and also removes the cast operator. The queue() member
function cause problems in derived classes that declare members with
the same name, e.g. a MemObject subclass that has a packet queue on
its own. The operator is not causing any harm at this point, but as it
is not used there is little point in keeping it.
This patch makes the queue implementation in the SimpleTimingPort
private to avoid confusion with the protected member queue in the
QueuedSlavePort. The SimpleTimingPort provides the queue_impl to the
QueuedSlavePort and it can be accessed via the reference in the base
class. The use of the member name queue is thus no longer overloaded.
This patch is a first step to align the port names used in the Python
world and the C++ world. Ultimately it serves to make the use of
config.json together with output from the simulation easier, including
post-processing of statistics.
Most notably, the CPU, cache, and bus is addressed in this patch, and
there might be other ports that should be updated accordingly. The
dash name separator has also been replaced with a "." which is what is
used to concatenate the names in python, and a separation is made
between the master and slave port in the bus.
This patch changes the default bus width to a more sensible 8 bytes
(64 bits), which is in line with most on-chip buses. Although there
are cases where a wider or narrower bus is useful, the 8 bytes is a
good compromise to serve as the default.
This patch changes essentially all statistics, and will be bundled
with the outstanding changes to the bus.
This patch splits the existing buses into multiple layers. The
non-coherent bus is split into a request and a response layer, and the
coherent bus adds an additional layer for the snoop responses. The
layer is modified to be templatised on the port type, such that the
different layers can have retryLists with either master or slave
ports. This patch also removes the dynamic cast from the retry, as
previously promised when moving the recvRetry from the port base class
to the master/slave port respectively.
Overall, the split bus more closely reflects any modern on-chip bus
and should be at step in the right direction. From this point, it
would be reasonable straight forward to add separate layers (and thus
contention points and arbitration) for each port and thus create a
true crossbar.
The regressions all produce the correct output, but have varying
degrees of changes to their statistics. A separate patch will be
pushed with the updates to the reference statistics.
This patch moves all flow control, arbitration and state information
into a bus layer. The layer is thus responsible for all the state
transitions, and for keeping hold of the retry list. Consequently the
layer is also responsible for the draining.
With this change, the non-coherent and coherent bus are given a single
layer to avoid changing any temporal behaviour, but the patch opens up
for adding more layers.
This patch adds a state enum and member variable in the bus, tracking
the bus state, thus eliminating the need for tickNextIdle and inRetry,
and fixing an issue that allowed the bus to be occupied by multiple
packets at once (hopefully it also makes it easier to understand the
code).
The bus, in its current form, uses tickNextIdle and inRetry to keep
track of the state of the bus. However, it only updates tickNextIdle
_after_ forwarding a packet using sendTiming, and the result is that
the bus is still seen as idle, and a module that receives the packet
and starts transmitting new packets in zero time will still see the
bus as idle (and this is done by a number of DMA devices). The issue
can also be seen in isOccupied where the bus calls reschedule on an
event instead of schedule.
This patch addresses the problem by marking the bus as _not_ idle
already by the time we conclude that the bus is not occupied and we
will deal with the packet.
As a result of not allowing multiple packets to occupy the bus, some
regressions have slight changes in their statistics. A separate patch
updates these accordingly.
Further ahead, a follow-on patch will introduce a separate state
variable for request/responses/snoop responses, and thus implement a
split request/response bus with separate flow control for the
different message types (even further ahead it will introduce a
multi-layer bus).
This patch makes getAddrRanges const throughout the code base. There
is no reason why it should not be, and making it const prevents adding
any unintentional side-effects.
This patch adds getAddrRanges to the master port, and thus avoids
going through getSlavePort to be able to ask the slave. Similar to the
previous patch that added isSnooping to the SlavePort, this patch aims
to introduce an additional level of hierarchy in the ports (base port
being protocol-agnostic) and getSlave/MasterPort will return port
pointers to these base classes.
The function is named getAddrRanges also on the master port, but does
nothing besides asking the connected slave port. The slave port, as
before, has to provide an implementation and actually produce a list
of address ranges. The initial design used the name getSlaveAddrRanges
for the new function, but the more verbose name was later changed.
This patch adds isSnooping to the slave port, and thus avoids going
through getMasterPort to be able to ask the master. Over the course of
the next few patches, all getMasterPort/getSlavePort in Port and
MemObject are to be protocol agnostic, and the snooping is part of the
protocol layer.
The function is already present on the master port, where it is
implemented by the module itself, e.g. a cache. On the slave side, it
is merely asking the connected master port. The same name is used by
both functions despite their difference in behaviour. The initial
design used isMasterSnooping on the slave port side, but the more
verbose function name was later changed.
This patch is the last part of moving all protocol-related
functionality out of the Port base class. All the send/recv functions
are already moved, and the retry (which still governs all the timing
transport functions) is the only part that remained in the base class.
The only point where this currently causes a bit of inconvenience is
in the bus where the retry list is global and holds Port pointers (not
Master/SlavePort). This is about to change with the split into a
request/response bus and will soon be removed anyway.
The patch has no impact on any regressions.
This patch is the result of static analysis identifying a number of
memory leaks. The leaks are all benign as they are a result of not
deallocating memory in the desctructor. The fix still has value as it
removes false positives in the static analysis.
This patch fixes two warnings, one related to a narrowing conversion
(int to MachInst), and one due to the cast operator for arguments and
a mismatch in const-ness (const void* and void*).
The LRU policy always evicted the least recently touched way, even if it
contained valid data and another way was invalid, as can happen if a block has
been invalidated by coherance. This can result in caches never warming up even
though they are replacing blocks. This modifies the LRU policy to move blocks
to LRU position on invalidation.
Currently when multiple CPUs perform a load-linked/store-conditional sequence,
the loads all create a list of reservations which is then scanned when the
stores occur. A reservation matching the context and address of the store is
sought, BUT all reservations matching the address are also erased at this point.
The upshot is that a store-conditional will remove all reservations even if the
store itself does not succeed. A livelock was observed using 7-8 CPUs where a
thread would erase the reservations of other threads, not succeed, loop and put
its own reservation in again only to have it blown by another thread that
unsuccessfully now tries to store-conditional -- no forward progress was made,
hanging the system.
The correct way to do this is to only blow a reservation when a store
(conditional or not) actually /occurs/ to its address. One thread always wins
(the one that does the store-conditional first).
Add new flag (named pushedRAS) in the PredictorHistory structure.
This flag tracks whether the RAS has been pushed or not during a prediction.
Then, in the squash function it is used to pop the RAS if necessary.
npc in PCState for ARM was being calculated before the current flags were
updated with the next flags. This causes an issue as the npc is incremented by
two or four depending on the current flags (thumb or not) and was leading to
branches that were predicted correctly being identified as mispredicted.
This patch fixes a failing compilation caused by MaxMiscDestRegs being
zero. According to gcc 4.6, the result is a comparison that is always
false due to limited range of data type.
This patch is a temporary fix until Andreas' four-phase patches
get reviewed and committed. Removing FastAlloc seems to have exposed
an issue which previously was reasonable rare in which packets are freed
before the sending cache is done with them. This change puts incoming packets
no a pendingDelete queue which are deleted at the start of the next call and
thus breaks the dependency between when the caller returns true and when the
packet is actually used by the sending cache.
Running valgrind on a multi-core linux boot and the memtester results in no
valgrind warnings.
Due to recent changes to X86 TLB, gem5 stopped compiling on
gcc version 4.4.3. This patch provides the fix for that problem. The patch
is tested on gcc 4.4.3. The change is not required for more recent
versions of gcc (like on 4.6.3).
initCPU() will be called to initialize switched out CPUs for the simple and
inorder CPU models. this patch prevents those CPUs from being initialized
because they should get their state from the active CPU when it is switched
out.
This change allows designating a system as MP capable or not as some
bootloaders/kernels care that it's set right. You can have a single
processor MP capable system, but you can't have a multi-processor
UP only system. This change also fixes the initialization of the MIDR
register.
While FastAlloc provides a small performance increase (~1.5%) over regular malloc it isn't thread safe.
After removing FastAlloc and using tcmalloc I've seen a performance increase of 12% over libc malloc
when running twolf for ARM.
The CPUID instruction was implemented so that it would only write its results
if the instruction was successful. This works fine on the simple CPU where
unwritten registers retain their old values, but on a CPU like O3 with
renaming this is broken. The instruction needs to write the old values back
into the registers explicitly if they aren't being changed.
There are some bits of some fields of the ExtMachInst which are not actually
used for anything but are included in the hash of an ExtMachInst for
simplicity and efficiency. This change makes sure the decoder's internal
working ExtMachInst is completely initialized, even these unused bits, so that
there isn't any nondeterministic behavior, no valgrind messages about
uninitialized variables, and no potential false misses/redundant entries in
the decode cache.
This patch introduces a class hierarchy of buses, a non-coherent one,
and a coherent one, splitting the existing bus functionality. By doing
so it also enables further specialisation of the two types of buses.
A non-coherent bus connects a number of non-snooping masters and
slaves, and routes the request and response packets based on the
address. The request packets issued by the master connected to a
non-coherent bus could still snoop in caches attached to a coherent
bus, as is the case with the I/O bus and memory bus in most system
configurations. No snoops will, however, reach any master on the
non-coherent bus itself. The non-coherent bus can be used as a
template for modelling PCI, PCIe, and non-coherent AMBA and OCP buses,
and is typically used for the I/O buses.
A coherent bus connects a number of (potentially) snooping masters and
slaves, and routes the request and response packets based on the
address, and also forwards all requests to the snoopers and deals with
the snoop responses. The coherent bus can be used as a template for
modelling QPI, HyperTransport, ACE and coherent OCP buses, and is
typically used for the L1-to-L2 buses and as the main system
interconnect.
The configuration scripts are updated to use a NoncoherentBus for all
peripheral and I/O buses.
A bit of minor tidying up has also been done.
--HG--
rename : src/mem/bus.cc => src/mem/coherent_bus.cc
rename : src/mem/bus.hh => src/mem/coherent_bus.hh
rename : src/mem/bus.cc => src/mem/noncoherent_bus.cc
rename : src/mem/bus.hh => src/mem/noncoherent_bus.hh
This patch makes two very minor changes to please gcc 4.7. The
CopyData function no longer exists and this has been replaced. For
some reason previous versions of gcc did not complain on the const
char casting not having an implementation, but this is now addressed.
This patch merely remove the Packet* from the isOccupied member
function. Historically this was used to check if the packet was an
express snoop, but this is now done outside this function (where
relevant).
The main aim of this patch is to arrive at a suitable port interface
for vector ports, including both the packet and the port id. This
patch changes the bus transport functions
(recvFunctional/Atomic/Timing) to require a PortId parameter
indicating the source port. Previously this information was passed by
setting the source field of the packet, and this is only required in
the case of a timing request.
With this patch, the use of the source and destination field is also
more restrictive, as they are only needed for timing accesses. The
modifications to these fields for atomic snoops is now removed
entirely, also making minor modifications to the cache.
This patch removes the Packet::NodeID typedef and unifies it with the
Port::PortId. The src and dest fields in the packet are used to hold a
port id (e.g. in the bus), and thus the two should actually be the
same.
The typedef PortID is now global (in base/types.hh) and aligned with
the ThreadID in terms of capitalisation and naming of the
InvalidPortID constant.
Before this patch, two flags were used for valid destination and
source, rather than relying on a named value (InvalidPortID), and
this is now redundant, as the src and dest field themselves are
sufficient to tell whether the current value is a valid port
identifier or not. Consequently, the VALID_SRC and VALID_DST are
removed.
As part of the cleaning up, a number of int parameters and local
variables are updated to use PortID.
Note that Ruby still has its own NodeID typedef. Furthermore, the
MemObject getMaster/SlavePort still has an int idx parameter with a
default value of -1 which should eventually change to PortID idx =
InvalidPortID.
This patch updates the comments for the src and dest fields to reflect
their actual use. Due to a number of patches (e.g. removing the
Broadcast flag), the old comments are no longer indicative of the
current usage.
This patch splits the PacketBuffer class into a RequestState and a
DeferredRequest and DeferredResponse. Only the requests need a
SenderState, and the deferred requests and responses only need an
associated point in time for the request and the response queue.
Besides the cleaning up, the goal is to simplify the transition to a
new port handshake, and with these changes, the two packet queues are
starting to look very similar to the generic packet queue, but
currently they do a few unique things relating to the NACK and
counting of requests/responses that the packet queue cannot be
conveniently used. This will be addressed in a later patch.
The GDT can be accessed by user level software running in compatibility mode
by moving segment selectors into segment registers. The GDT needs to be set up
at an address accessible in this mode.
A small change was added a while ago to keep addresses from overflowing 32
bits when larger addresses shouldn't be accessible to software. That change
truncated when not in long mode, but really it should have truncated when not
in 64 bit mode. The difference is whether compatibility mode is included, a
mode that's supposed to act like a legacy 32 bit mode.
This will allow it to be specialized by the ISAs. The existing caching scheme
is provided by the BasicDecodeCache in the GenericISA namespace and is built
from the generalized components.
--HG--
rename : src/cpu/decode_cache.cc => src/arch/generic/decode_cache.cc
These classes are always used together, and merging them will give the ISAs
more flexibility in how they cache things and manage the process.
--HG--
rename : src/arch/x86/predecoder_tables.cc => src/arch/x86/decoder_tables.cc
This patch removes unused commands and attributes from the packet to
avoid any confusion. It is part of an effort to clear up how and where
different commands and attributes are used.
This patch changes the organisation of the JSON output slightly to
make it easier to traverse and use the files. Most importantly, the
hierarchical dictionaries now use keys that correspond to the
attribute names also in the case of VectorParams (used to be
e.f. "cpu0 cpu1"). It also adds the name and the path to each
SimObject directory entry. Before this patch, to get cpu0, you would
have to query dict['system']['cpu0 cpu1'][0] and this could be a dict
with 'cpu0' : { cpu parameters }. Now you use dict['system']['cpu'][0]
and get { cpu parameters } (where one is "name" : "cpu0").
Additionally this patch includes more verbose information about the
ports, specifying their role, and using a JSON array rather than a
concatenated string for the peer.
This patch moves the DMA device to its own set of files, splitting it
from the IO device. There are no behavioural changes associated with
this patch.
The patch also grabs the opportunity to do some very minor tidying up,
including some white space removal and pruning some redundant
parameters.
Besides the immediate benefits of the separation-of-concerns, this
patch also makes upcoming changes more streamlined as it split the
devices that are only slaves and the DMA device that also acts as a
master.
--HG--
rename : src/dev/io_device.cc => src/dev/dma_device.cc
rename : src/dev/io_device.hh => src/dev/dma_device.hh
This patch makes the (device) DmaPort non-snooping and removes the
recvSnoop constructor parameter and instead introduces a
SnoopingDmaPort subclass for the ARM table walker.
Functionality is unchanged, as are the stats, and the patch merely
clarifies that the normal DMA ports are not snooping (although they
may issue requests that are snooped by others, as done with PCI, PCIe,
AMBA4 ACE etc).
Currently this port is declared in the ARM table walker as it is not
used anywhere else. If other ports were to have similar behaviour it
could be moved in a future patch.
This patch turns the existing warning into a fatal, as there should
never be any cases where a (non-vector) port is assigned to and then
later connected to something else. If this behaviour is allowed, as it
used to be, there are cases where the wrong number of C++ ports are
created when instantiating objects with VectorPorts (obviously that
could be fixed, but the better approach is to simply not allow it).
The scheduling of the deadlock check event was being done incorrectly as the
clock was not being multiplied, so as to convert the time into ticks. This
patch removes that bug.
This patch moves the ECF and EZF bits to individual registers (ecfBit and
ezfBit) and the CF and OF bits to cfofFlag registers. This is being done
so as to lower the read after write dependencies on the the condition code
register. Ultimately we will have the following registers [ZAPS], [OF],
[CF], [ECF], [EZF] and [DF]. Note that this is only one part of the
solution for lowering the dependencies. The other part will check whether
or not the condition code register needs to be actually read. This would
be done through a separate patch.
If the length argument to mmap is larger than the arbitrary but reasonable
limit of 4GB, there's a good chance that the value is nonsense and not
intentional. Rather than attempting to satisfy the mmap anyway, this change
makes gem5 warn to make it more apparent what's going wrong.
