This patch enables tracking of cache occupancy per thread along with
ages (in buckets) per cache blocks. Cache occupancy stats are
recalculated on each stat dump.
The probe patch is motivated by the desire to move analytical and trace code
away from functional code. This is achieved by the probe interface which is
essentially a glorified observer model.
What this means to users:
* add a probe point and a "notify" call at the source of an "event"
* add an isolated module, that is being used to carry out *your* analysis (e.g. generate a trace)
* register that module as a probe listener
Note: an example is given for reference in src/cpu/o3/simple_trace.[hh|cc] and src/cpu/SimpleTrace.py
What is happening under the hood:
* every SimObject maintains has a ProbeManager.
* during initialization (src/python/m5/simulate.py) first regProbePoints and
the regProbeListeners is called on each SimObject. this hooks up the probe
point notify calls with the listeners.
FAQs:
Why did you develop probe points:
* to remove trace, stats gathering, analytical code out of the functional code.
* the belief that probes could be generically useful.
What is a probe point:
* a probe point is used to notify upon a given event (e.g. cpu commits an instruction)
What is a probe listener:
* a class that handles whatever the user wishes to do when they are notified
about an event.
What can be passed on notify:
* probe points are templates, and so the user can generate probes that pass any
type of argument (by const reference) to a listener.
What relationships can be generated (1:1, 1:N, N:M etc):
* there isn't a restriction. You can hook probe points and listeners up in a
1:1, 1:N, N:M relationship. They become useful when a number of modules
listen to the same probe points. The idea being that you can add a small
number of probes into the source code and develop a larger number of useful
analysis modules that use information passed by the probes.
Can you give examples:
* adding a probe point to the cpu's commit method allows you to build a trace
module (outputting assembler), you could re-use this to gather instruction
distribution (arithmetic, load/store, conditional, control flow) stats.
Why is the probe interface currently restricted to passing a const reference:
* the desire, initially at least, is to allow an interface to observe
functionality, but not to change functionality.
* of course this can be subverted by const-casting.
What is the performance impact of adding probes:
* when nothing is actively listening to the probes they should have a
relatively minor impact. Profiling has suggested even with a large number of
probes (60) the impact of them (when not active) is very minimal (<1%).
Add some values and methods to the request object to track the translation
and access latency for a request and which level of the cache hierarchy responded
to the request.
This patch relaxes the check performed when squashing non-speculative
instructions, as it caused problems with loads that were marked ready,
and then stalled on a blocked cache. The assertion is now allowing
memory references to be non-faulting.
the current implementation of the fetch buffer in the o3 cpu
is only allowed to be the size of a cache line. some
architectures, e.g., ARM, have fetch buffers smaller than a cache
line, see slide 22 at:
http://www.arm.com/files/pdf/at-exploring_the_design_of_the_cortex-a15.pdf
this patch allows the fetch buffer to be set to values smaller
than a cache line.
Fix a problem in the O3 CPU for instructions that are both
memory loads and memory barriers (e.g. load acquire) and
to uncacheable memory. This combination can confuse the
commit stage into commitng an instruction that hasn't
executed and got it's value yet. At the same time refactor
the code slightly to remove duplication between two of
the cases.
LSQSenderState represents the LQ/SQ index using uint8_t, which supports up to
256 entries (including the sentinel entry). Sending packets to memory with a
higher index than 255 truncates the index, such that the response matches the
wrong entry. For instance, this can result in a deadlock if a store completion
does not clear the head entry.
Convert condition code registers from being specialized
("pseudo") integer registers to using the recently
added CC register class.
Nilay Vaish also contributed to this patch.
Restructured rename map and free list to clean up some
extraneous code and separate out common code that can
be reused across different register classes (int and fp
at this point). Both components now consist of a set
of Simple* objects that are stand-alone rename map &
free list for each class, plus a Unified* object that
presents a unified interface across all register
classes and then redirects accesses to the appropriate
Simple* object as needed.
Moved free list initialization to PhysRegFile to better
isolate knowledge of physical register index mappings
to that class (and remove the need to pass a number
of parameters to the free list constructor).
Causes a small change to these stats:
cpu.rename.int_rename_lookups
cpu.rename.fp_rename_lookups
because they are now categorized on a per-operand basis
rather than a per-instruction basis.
That is, an instruction with mixed fp/int/misc operand
types will have each operand categorized independently,
where previously the lookup was categorized based on
the instruction type.
Make these names more meaningful.
Specifically, made these substitutions:
s/FP_Base_DepTag/FP_Reg_Base/g;
s/Ctrl_Base_DepTag/Misc_Reg_Base/g;
s/Max_DepTag/Max_Reg_Index/g;
It had a bunch of fields (and associated constructor
parameters) thet it didn't really use, and the array
initialization was needlessly verbose.
Also just hardwired the getReg() method to aleays
return true for misc regs, rather than having an array
of bits that we always kept marked as ready.
No need for PhysRegFile to be a template class, or
have a pointer back to the CPU. Also made some methods
for checking the physical register type (int vs. float)
based on the phys reg index, which will come in handy later.
Move from a poorly documented scheme where the mapping
of unified architectural register indices to register
classes is hardcoded all over to one where there's an
enum for the register classes and a function that
encapsulates the mapping.
Previously, the LSQ would instantiate MaxThreads LSQUnits in the body of it's
object, but it would only initialize numThreads LSQUnits as specified by the
user. This had the effect of leaving some LSQUnits uninitialized when the
number of threads was less than MaxThreads, and when adding statistics to the
LSQUnit that must be initialized, this caused the stats initialization check to
fail. By dynamically instantiating LSQUnits, they are all initialized and this
avoids uninitialized LSQUnits from floating around during runtime.
The branch predictor is guarded by having either the in-order or
out-of-order CPU as one of the available CPU models and therefore
should not be used in the BaseCPU. This patch moves the parameter to
the relevant CPU classes.
This patch fixes a bug in the O3 fetch stage that was introduced when
the cache line size was moved to the system. By mistake, the
initialisation and resetting of the fetch stage was merged and put in
the constructor. The resetting is now re-added where it should be.
This patch removes the notion of a peer block size and instead sets
the cache line size on the system level.
Previously the size was set per cache, and communicated through the
interconnect. There were plenty checks to ensure that everyone had the
same size specified, and these checks are now removed. Another benefit
that is not yet harnessed is that the cache line size is now known at
construction time, rather than after the port binding. Hence, the
block size can be locally stored and does not have to be queried every
time it is used.
A follow-on patch updates the configuration scripts accordingly.
This patch adds the notion of source- and derived-clock domains to the
ClockedObjects. As such, all clock information is moved to the clock
domain, and the ClockedObjects are grouped into domains.
The clock domains are either source domains, with a specific clock
period, or derived domains that have a parent domain and a divider
(potentially chained). For piece of logic that runs at a derived clock
(a ratio of the clock its parent is running at) the necessary derived
clock domain is created from its corresponding parent clock
domain. For now, the derived clock domain only supports a divider,
thus ensuring a lower speed compared to its parent. Multiplier
functionality implies a PLL logic that has not been modelled yet
(create a separate clock instead).
The clock domains should be used as a mechanism to provide a
controllable clock source that affects clock for every clocked object
lying beneath it. The clock of the domain can (in a future patch) be
controlled by a handler responsible for dynamic frequency scaling of
the respective clock domains.
All the config scripts have been retro-fitted with clock domains. For
the System a default SrcClockDomain is created. For CPUs that run at a
different speed than the system, there is a seperate clock domain
created. This domain incorporates the CPU and the associated
caches. As before, Ruby runs under its own clock domain.
The clock period of all domains are pre-computed, such that no virtual
functions or multiplications are needed when calling
clockPeriod. Instead, the clock period is pre-computed when any
changes occur. For this to be possible, each clock domain tracks its
children.
This patch changes the IEW drain check to include the FU pool as there
can be instructions that are "stored" in FU completion events and thus
not covered by the existing checks. With this patch, we simply include
a check to see if all the FUs are considered non-busy in the next
tick.
Without this patch, the pc-switcheroo-full regression fails after
minor changes to the cache timing (aligning to clock edge).
Previously, nextCycle() could return the *current* cycle if the current tick was
already aligned with the clock edge. This behavior is not only confusing (not
quite what the function name implies), but also caused problems in the
drainResume() function. When exiting/re-entering the sim loop (e.g., to take
checkpoints), the CPUs will drain and resume. Due to the previous behavior of
nextCycle(), the CPU tick events were being rescheduled in the same ticks that
were already processed before draining. This caused divergence from runs that
did not exit/re-entered the sim loop. (Initially a cycle difference, but a
significant impact later on.)
This patch separates out the two behaviors (nextCycle() and clockEdge()),
uses nextCycle() in drainResume, and uses clockEdge() everywhere else.
Nothing (other than name) should change except for the drainResume timing.
This change fixes the switcheroo test that broke earlier this month. The code
that was checking for the pipeline being blocked wasn't checking for a pending
translation, only for a icache access.
Currently the commit stage keeps a local copy of the interrupt object.
Since the interrupt is usually handled several cycles after the commit
stage becomes aware of it, it is possible that the local copy of the
interrupt object may not be the interrupt that is actually handled.
It is possible that another interrupt occurred in the
interval between interrupt detection and interrupt handling.
This patch creates a copy of the interrupt just before the interrupt
is handled. The local copy is ignored.
This patch changes the port in the CPU classes to use MasterPort
instead of the derived CpuPort. The functions of the CpuPort are now
distributed across the relevant subclasses. The port accessor
functions (getInstPort and getDataPort) now return a MasterPort
instead of a CpuPort. This simplifies creating derivative CPUs that do
not use the CpuPort.
This change fixes the switcheroo test that broke earlier this month. The code
that was checking for the pipeline being blocked wasn't checking for a pending
translation, only for a icache access.
This patch address the most important name shadowing warnings (as
produced when using gcc/clang with -Wshadow). There are many
locations where constructor parameters and function parameters shadow
local variables, but these are left unchanged.
setMiscReg currently makes a new entry for each write to a misc reg without
checking for duplicates, this can cause a triggering of the assert if an
instruction get replayed and writes to the same misc regs multiple times.
This fix prevents duplicate entries and instead updates the value.
The rename can mis-handle serializing instructions (i.e. strex) if it gets
into a resource constrained situation and the serializing instruction has
to be placed on the skid buffer to handle blocking. In this situation the
instruction informs the pipeline it is serializing and logs that the next
instruction must be serialized, but since we are blocking the pipeline
defers this action to place the serializing instruction and
incoming instructions into the skid buffer. When resuming from blocking,
rename will pull the serializing instruction from the skid buffer and
the current logic will see this as the "next" instruction that has to
be serialized and because of flags set on the serializing instruction,
it passes through the pipeline stage as normal and resets rename to
non-serializing. This causes instructions to follow the serializing inst
incorrectly and eventually leads to an error in the pipeline. To fix this
rename should check first if it has to block before checking for serializing
instructions.
Fixes the tick used from rename:
- previously this gathered the tick on leaving rename which was always 1 less
than the dispatch. This conflated the decode ticks when back pressure built
in the pipeline.
- now picks up tick on entry.
Added --store_completions flag:
- will additionally display the store completion tail in the viewer.
- this highlights periods when large numbers of stores are outstanding (>16 LSQ
blocking)
Allows selection by tick range (previously this caused an infinite loop)
Virtualized CPUs and the fastmem mode of the atomic CPU require direct
access to physical memory. We currently require caches to be disabled
when using them to prevent chaos. This is not ideal when switching
between hardware virutalized CPUs and other CPU models as it would
require a configuration change on each switch. This changeset
introduces a new version of the atomic memory mode,
'atomic_noncaching', where memory accesses are inserted into the
memory system as atomic accesses, but bypass caches.
To make memory mode tests cleaner, the following methods are added to
the System class:
* isAtomicMode() -- True if the memory mode is 'atomic' or 'direct'.
* isTimingMode() -- True if the memory mode is 'timing'.
* bypassCaches() -- True if caches should be bypassed.
The old getMemoryMode() and setMemoryMode() methods should never be
used from the C++ world anymore.
CPUs need to test that the memory system is in the right mode in two
places, when the CPU is initialized (unless it's switched out) and on
a drainResume(). This led to some code duplication in the CPU
models. This changeset introduces the verifyMemoryMode() method which
is called by BaseCPU::init() if the CPU isn't switched out. The
individual CPU models are responsible for calling this method when
resuming from a drain as this code is CPU model specific.
Checker CPUs currently don't inherit from the CheckerCPU in the Python
object hierarchy. This has two consequences:
* It makes CPU model discovery from the Python world somewhat
complicated as there is no way of testing if a CPU is a checker.
* Parameters are duplicated in the checker configuration
specification.
This changeset makes all checker CPUs inherit from the base checker
CPU class.
The configuration scripts currently hard-code the requirements of each
CPU. This is clearly not optimal as it makes writing new configuration
scripts painful and adding new CPU models requires existing scripts to
be updated. This patch adds the following class methods to the base
CPU and all relevant CPUs:
* memory_mode -- Return a string describing the current memory mode
(invalid/atomic/timing).
* require_caches -- Does the CPU model require caches?
* support_take_over -- Does the CPU support CPU handover?
Fix a case in the O3 CPU where the decode stage blocks and unblocks in a
single cycle sending both signals to fetch which causes an assert or worse.
The previous check could never work before since the status was set to Blocked
before a test for the status being Unblocking was executed.
Check if an instruction just enabled interrupts and we've previously had an
interrupt pending that was not handled because interrupts were subsequently
disabled before the pipeline reached a place to handle the interrupt. In that
case squash now to make sure the interrupt is handled.
This patch moves the branch predictor files in the o3 and inorder directories
to src/cpu/pred. This allows sharing the branch predictor across different
cpu models.
This patch was originally posted by Timothy Jones in July 2010
but never made it to the repository.
--HG--
rename : src/cpu/o3/bpred_unit.cc => src/cpu/pred/bpred_unit.cc
rename : src/cpu/o3/bpred_unit.hh => src/cpu/pred/bpred_unit.hh
rename : src/cpu/o3/bpred_unit_impl.hh => src/cpu/pred/bpred_unit_impl.hh
rename : src/cpu/o3/sat_counter.hh => src/cpu/pred/sat_counter.hh
There was an issue w/ the rename logic, which would assign a previous physical
register to the ZeroReg architectural register in x86. This issue was giving
problems for instructions squashed in threads w/ ID different from 0,
sometimes allowing non-mispredicted instructions to obtain a value different
from zero when reading the zeroReg.
The changes made by the changeset 270c9a75e91f do not work well with switching
of cpus. The problem is that decoder for the old thread context holds state
that is not taken over by the new decoder.
This patch adds a takeOverFrom() function to Decoder class in each ISA. Except
for x86, functions in other ISAs are blank. For x86, the function copies state
from the old decoder to the new decoder.
Move the increment/decrement of wbOutstanding outside of the comparison
in incrWb and decrWb in the IEW. This also fixes a compiler bug with gcc
4.4.7, which incorrectly optimizes "-- ==" as "-=".
The changes made by the changeset 9376 were not quite correct. The patch made
changes to the code which resulted in decoder not getting initialized correctly
when the state was restored from a checkpoint.
This patch adds a startup function to each ISA object. For x86, this function
sets the required state in the decoder. For other ISAs, the function is empty
right now.
Cleanup the serialization code for the simple CPUs and the O3 CPU. The
CPU-specific code has been replaced with a (un)serializeThread that
serializes the thread state / context of a specific thread. Assuming
that the thread state class uses the CPU-specific thread state uses
the base thread state serialization code, this allows us to restore a
checkpoint with any of the CPU models.
Previously, the O3 CPU could stop in the middle of a microcode
sequence. This patch makes sure that the pipeline stops when it has
committed a normal instruction or exited from a microcode
sequence. Additionally, it makes sure that the pipeline has no
instructions in flight when it is drained, which should make draining
more robust.
Draining is controlled in the commit stage, which checks if the next
PC after a committed instruction is in microcode. If this isn't the
case, it requests a squash of all instructions after that the
instruction that just committed and immediately signals a drain stall
to the fetch stage. The CPU then continues to execute until the
pipeline and all associated buffers are empty.
The thread context handover code used to break when multiple handovers
were performed during the same quiesce period. Previously, the thread
contexts would assign the TC pointer in the old quiesce event to the
new TC. This obviously broke in cases where multiple switches were
performed within the same quiesce period, in which case the TC pointer
in the quiesce event would point to an old CPU.
The new implementation deschedules pending quiesce events in the old
TC and schedules a new quiesce event in the new TC. The code has been
refactored to remove most of the code duplication.
