Stephan Diestelhorst [Mon, 2 Mar 2015 09:00:31 +0000 (04:00 -0500)]
cpu: Add a PC-value to the traffic generator requests
Have the traffic generator add its masterID as the PC address to the
requests. That way, prefetchers (and other components) that use a PC
for request classification will see per-tester streams of requests.
This enables us to test strided prefetchers with the memchecker, too.
Andreas Hansson [Mon, 2 Mar 2015 09:00:29 +0000 (04:00 -0500)]
tests: Run regression timeout as foreground
Allow the user to send signals such as Ctrl C to the gem5 runs. Note
that this assumes coreutils >= 8.13, which aligns with Ubuntu 12.04
and RHE6.
Andreas Sandberg [Mon, 2 Mar 2015 09:00:28 +0000 (04:00 -0500)]
arm: Don't truncate 16-bit ASIDs to 8 bits
The ISA code sometimes stores 16-bit ASIDs as 8-bit unsigned integers
and has a couple of inverted checks that mask out the high 8 bits of
an ASID if 16-bit ASIDs have been /enabled/. This changeset fixes both
of those issues.
Andreas Sandberg [Mon, 2 Mar 2015 09:00:27 +0000 (04:00 -0500)]
arm: Correctly access the stack pointer in GDB
We curently use INTREG_X31 instead of INTREG_SPX when accessing the
stack pointer in GDB. gem5 normally uses INTREG_SPX to access the
stack pointer, which gets mapped to the stack pointer corresponding
(INTREG_SPn) to the current exception level. This changeset updates
the GDB interface to use SPX instead of X31 (which is always zero)
when transfering CPU state to gdb.
Andreas Sandberg [Mon, 2 Mar 2015 09:00:27 +0000 (04:00 -0500)]
arm: Fix broken page table permissions checks in remote GDB
The remote GDB interface currently doesn't check if translations are
valid before reading memory. This causes a panic when GDB tries to
access unmapped memory (e.g., when getting a stack trace). There are
two reasons for this: 1) The function used to check for valid
translations (virtvalid()) doesn't work and panics on invalid
translations. 2) The method in the GDB interface used to test if a
translation is valid (RemoteGDB::acc) always returns true regardless
of the return from virtvalid().
This changeset fixes both of these issues.
Jason Power [Thu, 26 Feb 2015 15:58:26 +0000 (09:58 -0600)]
Ruby: Update backing store option to propagate through to all RubyPorts
Previously, the user would have to manually set access_backing_store=True
on all RubyPorts (Sequencers) in the config files.
Now, instead there is one global option that each RubyPort checks on
initialization.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Andreas Hansson [Mon, 16 Feb 2015 08:35:23 +0000 (03:35 -0500)]
config: Add memcheck stress test
This is a rather unfortunate copy of the memtest.py example script,
that actually stresses the system with true sharing as opposed to the
false sharing of the MemTest. To do so it uses TrafficGen instances to
generate the reads/writes, and MemCheckerMonitor combined with the
MemChecker to check the validity of the read/written values.
As a bonus, this script also enables the addition of prefetchers, and
the traffic is created to have a mix of random addresses and linear
strides. We use the TaggedPrefetcher since the packets do not have a
request with a PC.
At the moment the code is almost identical to the memtest.py script,
and no effort has been made to factor out the construction of the
tree. The challenge is that the instantiation and connection of the
testers and monitors is done as part of the tree building.
Andreas Hansson [Mon, 16 Feb 2015 08:34:55 +0000 (03:34 -0500)]
cpu: TrafficGen sinks snoops without complaining
To be able to use the TrafficGen in a system with caches we need to
allow it to sink incoming snoop requests. By default the master port
panics, so silently ignore any snoops.
Stephan Diestelhorst [Mon, 16 Feb 2015 08:34:47 +0000 (03:34 -0500)]
mem: Fix initial value problem with MemChecker
In highly loaded cases, reads might actually overlap with writes to the
initial memory state. The mem checker needs to detect such cases and
permit the read reading either from the writes (what it is doing now) or
read from the initial, unknown value.
This patch adds this logic.
Andreas Hansson [Mon, 16 Feb 2015 08:34:35 +0000 (03:34 -0500)]
dev: Fix undefined behaviuor in i8254xGBe
This patch fixes a rather unfortunate oversight where the annotation
pointer was used even though it is null. Somehow the code still works,
but UBSan is rather unhappy. The use is now guarded, and the variable
is initialised in the constructor (as well as init()).
Andreas Sandberg [Mon, 16 Feb 2015 08:34:18 +0000 (03:34 -0500)]
arm: Wire up the GIC with the platform in the base class
Move the (common) GIC initialization code that notifies the platform
code of the new GIC to the base class (BaseGic) instead of the Pl390
implementation.
Andreas Hansson [Mon, 16 Feb 2015 08:33:47 +0000 (03:33 -0500)]
mem: mmap the backing store with MAP_NORESERVE
This patch ensures we can run simulations with very large simulated
memories (at least 64 TB based on some quick runs on a Linux
workstation). In essence this allows us to efficiently deal with
sparse address maps without having to implement a redirection layer in
the backing store.
This opens up for run-time errors if we eventually exhausts the hosts
memory and swap space, but this should hopefully never happen.
Andreas Hansson [Mon, 16 Feb 2015 08:33:37 +0000 (03:33 -0500)]
mem: Use the range cache for lookup as well as access
This patch changes the range cache used in the global physical memory
to be an iterator so that we can use it not only as part of isMemAddr,
but also access and functionalAccess. This matches use-cases where a
core is using the atomic non-caching memory mode, and repeatedly calls
isMemAddr and access.
Linux boot on aarch32, with a single atomic CPU, is now more than 30%
faster when using "--fastmem" compared to not using the direct memory
access.
Andreas Hansson [Mon, 16 Feb 2015 08:33:28 +0000 (03:33 -0500)]
arch: Make readMiscRegNoEffect const throughout
Finally took the plunge and made this apply to all ISAs, not just ARM.
Curtis Dunham [Fri, 16 Jan 2015 20:12:03 +0000 (14:12 -0600)]
config: add --root-device machine parameter
In case /dev/sda1 is not actually the boot partition for an image,
we can override it on the command line or in a benchmark definition.
Andreas Sandberg [Mon, 16 Feb 2015 08:32:58 +0000 (03:32 -0500)]
arm: Merge ISA files with pseudo instructions
This changeset moves the pseudo instructions used to signal unknown
instructions and unimplemented instructions to the same source files
as the decoder fault.
Ali Saidi [Mon, 16 Feb 2015 08:32:38 +0000 (03:32 -0500)]
cpu: add support for outputing a protobuf formatted CPU trace
Doesn't support x86 due to static instruction representation.
--HG--
rename : src/cpu/CPUTracers.py => src/cpu/InstPBTrace.py
Marco Balboni [Wed, 11 Feb 2015 15:23:47 +0000 (10:23 -0500)]
mem: Clarification of packet crossbar timings
This patch clarifies the packet timings annotated
when going through a crossbar.
The old 'firstWordDelay' is replaced by 'headerDelay' that represents
the delay associated to the delivery of the header of the packet.
The old 'lastWordDelay' is replaced by 'payloadDelay' that represents
the delay needed to processing the payload of the packet.
For now the uses and values remain identical. However, going forward
the payloadDelay will be additive, and not include the
headerDelay. Follow-on patches will make the headerDelay capture the
pipeline latency incurred in the crossbar, whereas the payloadDelay
will capture the additional serialisation delay.
Marco Balboni [Wed, 11 Feb 2015 15:23:36 +0000 (10:23 -0500)]
mem: Clarify usage of latency in the cache
This patch adds some much-needed clarity in the specification of the
cache timing. For now, hit_latency and response_latency are kept as
top-level parameters, but the cache itself has a number of local
variables to better map the individual timing variables to different
behaviours (and sub-components).
The introduced variables are:
- lookupLatency: latency of tag lookup, occuring on any access
- forwardLatency: latency that occurs in case of outbound miss
- fillLatency: latency to fill a cache block
We keep the existing responseLatency
The forwardLatency is used by allocateInternalBuffer() for:
- MSHR allocateWriteBuffer (unchached write forwarded to WriteBuffer);
- MSHR allocateMissBuffer (cacheable miss in MSHR queue);
- MSHR allocateUncachedReadBuffer (unchached read allocated in MSHR
queue)
It is our assumption that the time for the above three buffers is the
same. Similarly, for snoop responses passing through the cache we use
forwardLatency.
Andreas Sandberg [Wed, 11 Feb 2015 15:23:34 +0000 (10:23 -0500)]
style: Fix broken m5format command
The m5format command didn't actually work due to parameter handling
issues and missing language detection. This changeset fixes those
issues and cleans up some of the code to shared between the style
checker and the format checker.
Andreas Sandberg [Wed, 11 Feb 2015 15:23:33 +0000 (10:23 -0500)]
style: Fix incorrect style checker option name
The style used to support the option -w to automatically fix white
space issues. However, this option was actually wired up to fix all
styles issues the checker encountered. This changeset cleans up the
code that handles automatic fixing and adds an option to fix all
issues, and separate options for white spaces and include ordering.
Andreas Hansson [Wed, 11 Feb 2015 15:23:31 +0000 (10:23 -0500)]
config: Revamp memtest to allow testers on any level
This patch revamps the memtest example script and allows for the
insertion of testers at any level in the cache hierarchy. Previously
all created topologies placed testers only at the very top, and the
tree was thus entirely symmetric. With the changes made, it is possible
to not only place testers at the leaf caches (L1), but also to connect
testers at the L2, L3 etc.
As part of the changes the object hierarchy is also simplified to
ensure that the visual representation from the DOT printing looks
sensible. Using SubSystems to group the objects is one of the key
features.
Andreas Hansson [Wed, 11 Feb 2015 15:23:31 +0000 (10:23 -0500)]
stats: Bump the MemTest regression stats
Reflect changes in the tester behaviour.
Andreas Hansson [Wed, 11 Feb 2015 15:23:28 +0000 (10:23 -0500)]
cpu: Tidy up the MemTest and make false sharing more obvious
The MemTest class really only tests false sharing, and as such there
was a lot of old cruft that could be removed. This patch cleans up the
tester, and also makes it more clear what the assumptions are. As part
of this simplification the reference functional memory is also
removed.
The regression configs using MemTest are updated to reflect the
changes, and the stats will be bumped in a separate patch. The example
config will be updated in a separate patch due to more extensive
re-work.
In a follow-on patch a new tester will be introduced that uses the
MemChecker to implement true sharing.
Andreas Sandberg [Wed, 11 Feb 2015 15:23:27 +0000 (10:23 -0500)]
sim: Move the BaseTLB to src/arch/generic/
The TLB-related code is generally architecture dependent and should
live in the arch directory to signify that.
--HG--
rename : src/sim/BaseTLB.py => src/arch/generic/BaseTLB.py
rename : src/sim/tlb.cc => src/arch/generic/tlb.cc
rename : src/sim/tlb.hh => src/arch/generic/tlb.hh
Andreas Sandberg [Wed, 11 Feb 2015 15:23:24 +0000 (10:23 -0500)]
base: Add compiler macros to add deprecation warnings
Gcc and clang both provide an attribute that can be used to flag a
function as deprecated at compile time. This changeset adds a gem5
compiler macro for that compiler feature. The macro can be used to
indicate that a legacy API within gem5 has been deprecated and provide
a graceful migration to the new API.
Andreas Hansson [Wed, 11 Feb 2015 15:23:23 +0000 (10:23 -0500)]
base: Do not dereference NULL in CompoundFlag creation
This patch fixes the CompoundFlag constructor, ensuring that it does
not dereference NULL. Doing so has undefined behaviuor, and both clang
and gcc's undefined-behaviour sanitiser was rather unhappy.
Andreas Sandberg [Wed, 11 Feb 2015 15:23:22 +0000 (10:23 -0500)]
dev: Remove unused system pointer in the Platform base class
The Platform base class contains a pointer to an instance of the
System which is never initialized. This can lead to subtle bugs since
some architecture-specific platform implementations contain their own
system pointer which is normally used. However, if the platform is
accessed through a pointer to its base class, the dangling pointer
will be used instead.
Alexandru Dutu [Sat, 7 Feb 2015 02:01:22 +0000 (18:01 -0800)]
cpu: Idle CPU status logic revised
This patch sets the CPU status to idle when the last active thread gets
suspended.
Steve Reinhardt [Fri, 6 Feb 2015 00:45:12 +0000 (16:45 -0800)]
config: rename 'file' var
Rename uses of 'file' as a local variable to avoid conflict
with the built-in type of the same name.
Steve Reinhardt [Fri, 6 Feb 2015 00:45:06 +0000 (16:45 -0800)]
config: make M5_PATH a real search path
Although you can put a list of colon-separated directory names
in M5_PATH, the current code just takes the first one that
exists and assumes all files must live there. This change
makes the code search the specified list of directories
for each individual binary or disk image that's requested.
The main motivation is that the x86/Alpha binaries and the
ARM binaries are in separate downloads, and thus naturally
end up in separate directories. With this change, you can
have M5_PATH point to those two directories, then run any
FS regression test without changing M5_PATH. Currently,
you either have to merge the two download directories
or change M5_PATH (or do something else I haven't figured out).
Andreas Hansson [Tue, 3 Feb 2015 19:26:02 +0000 (14:26 -0500)]
mem: Clarify express snoop behaviour
This patch adds a bit of documentation with insights around how
express snoops really work.
Andreas Hansson [Tue, 3 Feb 2015 19:25:59 +0000 (14:25 -0500)]
mem: Clarify cache behaviour for pending dirty responses
This patch adds a bit of clarification around the assumptions made in
the cache when packets are sent out, and dirty responses are
pending. As part of the change, the marking of an MSHR as in service
is simplified slightly, and comments are added to explain what
assumptions are made.
Curtis Dunham [Tue, 3 Feb 2015 19:25:58 +0000 (14:25 -0500)]
base: add an accessor and operators ==,!= to address ranges
Andreas Hansson [Tue, 3 Feb 2015 19:25:55 +0000 (14:25 -0500)]
config: Add XOR hashing to the DRAM channel interleaving
This patch uses the recently added XOR hashing capabilities for the
DRAM channel interleaving. This avoids channel biasing due to strided
access patterns.
Andreas Hansson [Tue, 3 Feb 2015 19:25:54 +0000 (14:25 -0500)]
base: Add XOR-based hashed address interleaving
This patch extends the current address interleaving with basic hashing
support. Instead of directly comparing a number of address bits with a
matching value, it is now possible to use two independent set of
address bits XOR'ed together. This avoids issues where strided address
patterns are heavily biased to a subset of the interleaved ranges.
Andreas Hansson [Tue, 3 Feb 2015 19:25:52 +0000 (14:25 -0500)]
config: Adjust DRAM channel interleaving defaults
This patch changes the DRAM channel interleaving default behaviour to
be more representative. The default address mapping (RoRaBaCoCh) moves
the channel bits towards the least significant bits, and uses 128 byte
as the default channel interleaving granularity.
These defaults can be overridden if desired, but should serve as a
sensible starting point for most use-cases.
Andreas Sandberg [Tue, 3 Feb 2015 19:25:50 +0000 (14:25 -0500)]
style: Update the style checker to handle new include order
As of August 2014, the gem5 style guide mandates that a source file's
primary header is included first in that source file. This helps to
ensure that the header file does not depend on include file ordering
and avoids surprises down the road when someone tries to reuse code.
In the new order, include files are grouped into the following blocks:
* Primary header file (e.g., foo.hh for foo.cc)
* Python headers
* C system/stdlib includes
* C++ stdlib includes
* Include files in the gem5 source tree
Just like before, include files within a block are required to be
sorted in alphabetical order.
This changeset updates the style checker to enforce the new order.
Andreas Sandberg [Tue, 3 Feb 2015 19:25:48 +0000 (14:25 -0500)]
sim: Remove test for non-NULL this in Event
The method Event::initialized() tests if this != NULL as a part of the
expression that tests if an event is initialized. The only case when
this check could be false is if the method is called on a null
pointer, which is illegal and leads to undefined behavior (such as
eating your pets) according to the C++ standard. Because of this,
modern compilers (specifically, recent versions of clang) warn about
this which we treat as an error. This changeset removes the redundant
check to fix said warning.
Andreas Sandberg [Tue, 3 Feb 2015 19:25:47 +0000 (14:25 -0500)]
dev: Correctly clear interrupts in VirtIO PCI
Correctly clear the PCI interrupt belonging to a VirtIO device when
the ISR register is read.
Andreas Hansson [Tue, 3 Feb 2015 19:25:43 +0000 (14:25 -0500)]
scons: Avoid implicit command dependencies
Work around a bug in scons that causes the param wrappers being
compiled twice. The easiest way for us to do so is to tell scons to
ignore implicit command dependencies.
Curtis Dunham [Fri, 19 Dec 2014 21:32:34 +0000 (15:32 -0600)]
sim: prioritize async events; prevent starvation
If a time quantum event is the only one in the queue, async
events (Ctrl-C, I/O, etc.) will never be processed.
So process them first.
Andreas Hansson [Tue, 3 Feb 2015 19:25:27 +0000 (14:25 -0500)]
cpu: Ensure timing CPU sinks response before sending new request
This patch changes how the timing CPU deals with processing responses,
always scheduling an event, even if it is for the current tick. This
helps to avoid situations where a new request shows up before a
response is finished in the crossbar, and also is more in line with
any realistic behaviour.
Geoffrey Blake [Tue, 3 Feb 2015 19:25:07 +0000 (14:25 -0500)]
config: Fix typo in Float param
The Float param was not settable on the command line
due to a typo in the class definition in
python/m5/params.py. This corrects the typo and allows
floats to be set on the command line as intended.
Malek Musleh [Fri, 30 Jan 2015 21:49:34 +0000 (15:49 -0600)]
config: arm: fix os_flags
Fix the makeArmSystem routine to reflect recent changes that support kernel
commandline option when running android. Without this fix, trying to run
android encounters a 'reference before assignment' error.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Ali Saidi [Sun, 25 Jan 2015 12:22:56 +0000 (07:22 -0500)]
arm: always set the IsFirstMicroop flag
While the IsFirstMicroop flag exists it was only occasionally used in the ARM
instructions that gem5 microOps and therefore couldn't be relied on to be correct.
Ali Saidi [Sun, 25 Jan 2015 12:22:44 +0000 (07:22 -0500)]
sim: Clean up InstRecord
Track memory size and flags as well as add some comments and consts.
Ali Saidi [Sun, 25 Jan 2015 12:22:26 +0000 (07:22 -0500)]
cpu: Remove all notion that we know when the cpu is misspeculating.
We have no way of knowing if a CPU model is on the wrong path with
our execute-in-execute CPU models. Don't pretend that we do.
Ali Saidi [Sun, 25 Jan 2015 12:22:17 +0000 (07:22 -0500)]
cpu: Put all CPU instruction tracers in a single file
Ali Saidi [Sun, 25 Jan 2015 12:22:05 +0000 (07:22 -0500)]
cpu: remove legion tracer
If someone wants to debug with legion again they can restore the
code from the repository, but no need to have it hang around indefinately.
Curtis Dunham [Tue, 23 Dec 2014 17:51:40 +0000 (11:51 -0600)]
sim: fix reference counting of PythonEvent
When gem5 is a slave to another simulator and the Python is only used
to initialize the configuration (and not perform actual simulation), a
"debug start" (--debug-start) event will get freed during or immediately
after the initial Python frame's execution rather than remaining in the
event queue. This tricky patch fixes the GC issue causing this.
Andreas Hansson [Thu, 22 Jan 2015 10:01:31 +0000 (05:01 -0500)]
mem: Remove unused Packet src and dest fields
This patch takes the final step in removing the src and dest fields in
the packet. These fields were rather confusing in that they only
remember a single multiplexing component, and pushed the
responsibility to the bridge and caches to store the fields in a
senderstate, thus effectively creating a stack. With the recent
changes to the crossbar response routing the crossbar is now
responsible without relying on the packet fields. Thus, these
variables are now unused and can be removed.
Andreas Hansson [Thu, 22 Jan 2015 10:01:30 +0000 (05:01 -0500)]
mem: Remove Packet source from ForwardResponseRecord
This patch removes the source field from the ForwardResponseRecord,
but keeps the class as it is part of how the cache identifies
responses to hardware prefetches that are snooped upwards.
Andreas Hansson [Thu, 22 Jan 2015 10:01:27 +0000 (05:01 -0500)]
mem: Remove unused RequestState in the bridge
This patch removes the bridge sender state as the Crossbar now takes
care of remembering its own routing decisions.
Andreas Hansson [Thu, 22 Jan 2015 10:01:24 +0000 (05:01 -0500)]
mem: Always use SenderState for response routing in RubyPort
This patch aligns how the response routing is done in the RubyPort,
using the SenderState for both memory and I/O accesses. Before this
patch, only the I/O used the SenderState, whereas the memory accesses
relied on the src field in the packet. With this patch we shift to
using SenderState in both cases, thus not relying on the src field any
longer.
Andreas Hansson [Thu, 22 Jan 2015 10:01:14 +0000 (05:01 -0500)]
mem: Make the XBar responsible for tracking response routing
This patch removes the need for a source and destination field in the
packet by shifting the onus of the tracking to the crossbar, much like
a real implementation. This change in behaviour also means we no
longer need a SenderState to remember the source/dest when ever we
have multiple crossbars in the system. Thus, the stack that was
created by the SenderState is not needed, and each crossbar locally
tracks the response routing.
The fields in the packet are still left behind as the RubyPort (which
also acts as a crossbar) does routing based on them. In the succeeding
patches the uses of the src and dest field will be removed. Combined,
these patches improve the simulation performance by roughly 2%.
Andreas Hansson [Thu, 22 Jan 2015 10:00:57 +0000 (05:00 -0500)]
stats: Update stats to reflect x86 table walker changes
Andreas Hansson [Thu, 22 Jan 2015 10:00:54 +0000 (05:00 -0500)]
x86: Delay X86 table walk on receiving walker response
This patch fixes a minor issue in the X86 page table walker where it
ended up sending new request packets to the crossbar before the
response processing was finished (recvTimingResp is directly calling
sendTimingReq). Under certain conditions this caused the crossbar to
see illegal combinations of request/response overlap, in turn causing
problems with a slightly modified crossbar implementation.
Andreas Hansson [Thu, 22 Jan 2015 10:00:53 +0000 (05:00 -0500)]
mem: Clean up Request initialisation
This patch tidies up how we create and set the fields of a Request. In
essence it tries to use the constructor where possible (as opposed to
setPhys and setVirt), thus avoiding spreading the information across a
number of locations. In fact, setPhys is made private as part of this
patch, and a number of places where we callede setVirt instead uses
the appropriate constructor.
Malek Musleh [Tue, 20 Jan 2015 20:15:28 +0000 (14:15 -0600)]
config, ruby: connect dma to network
DMA Controller was not being connected to the network for the MESI_Three_Level
protocol as was being done in the other protocol config files. Without this
patch, this protocol segfaults during startup.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Nikos Nikoleris [Tue, 20 Jan 2015 20:15:27 +0000 (14:15 -0600)]
cpu: commit probe notification on every microop or macroop
The ppCommit should notify the attached listener every time the cpu commits
a microop or non microcoded insturction. The listener can then decide
whether it will process only the last microop (eg. SimPoint probe).
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Andreas Hansson [Tue, 20 Jan 2015 13:12:45 +0000 (08:12 -0500)]
scons: Do not build the InOrderCPU
One step closer to shifting focus to the MinorCPU.
Andreas Hansson [Tue, 20 Jan 2015 13:12:02 +0000 (08:12 -0500)]
tests: Remove deprecated InOrderCPU tests
This patch removes the three MIPS and SPARC regressions that use the
deprecated InOrderCPU.
This is the first step in completely removing the code from the tree,
avoiding confusion, and focusing all development efforts on the
MinorCPU. Brave new world.
Andreas Hansson [Tue, 20 Jan 2015 13:12:01 +0000 (08:12 -0500)]
mem: Fix bug in cache request retry mechanism
This patch ensures that inhibited packets that are about to be turned
into express snoops do not update the retry flag in the cache.
Andreas Hansson [Tue, 20 Jan 2015 13:11:58 +0000 (08:11 -0500)]
cpu: Fix retry bug in MinorCPU LSQ
Andreas Hansson [Tue, 20 Jan 2015 13:11:55 +0000 (08:11 -0500)]
mem: Move DRAM interleaving check to init
This patch fixes a bug where the DRAM controller tried to access the
system cacheline size before the system pointer was initialised. It
also fixes a bug where the granularity is 0 (no interleaving).
Nilay Vaish [Sun, 11 Jan 2015 00:06:43 +0000 (18:06 -0600)]
stats: changes due to recent changesets.
Emilio Castillo [Sat, 10 Jan 2015 20:30:53 +0000 (14:30 -0600)]
x86 : fxsave and fxrestore missing template code
This patch corrects the FXSAVE and FXRSTOR Macroops. The actual code used for
saving/restore the FP registers is in the file but it was not used.
The FXSAVE and FXRSTOR instructions are used in the kernel for saving and
loading the state of the mmx,xmm and fpu registers.
This operation is triggered in FS by issuing a Device Not Available Fault. The
cr0 register has a TS flag that is set upon each context change. Every time a
task access any FP related register (SIMD as well) if the TS flag is set to
one, the device not available fault is issued. The kernel saves the current
state of the registers, and restore the previous state of the currently running
task.
Right now Gem5 lacks of this capability. the Device Not Available Fault is
never issued, leading to several problems when different threads share the same
CPU and SMT is not used. The PARSEC Ferret benchmark is an example of this
behavior.
In order to test this a hack in the atomic cpu code was done to detect if a
static instruction has any FP operands and the cr0 reg TS bit is set. This
check must be done in the ISA dependent code. But it seems to be tricky to
access the cr0 register while executing an instruction.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Nikos Nikoleris [Sat, 10 Jan 2015 20:30:53 +0000 (14:30 -0600)]
cpu: fix RetiredStores probe point
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
cdirik [Tue, 6 Jan 2015 22:10:22 +0000 (15:10 -0700)]
dev: prevent intel 8254 timer counter events firing before startup
This change includes edits to Intel8254Timer to prevent counter events firing
before startup to comply with SimObject initialization call sequence.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Gabe Black [Wed, 7 Jan 2015 08:34:40 +0000 (00:34 -0800)]
test: Add a unittest for the BitUnion types.
Gabe Black [Wed, 7 Jan 2015 08:31:46 +0000 (00:31 -0800)]
base: Fix assigning between identical bitfields.
If two bitfields are of the same type, also implying that they have the same
first and last bit positions, the existing implementation would copy the
entire bitfield. That includes the __data member which is shared among all the
bitfields, effectively overwritting the entire bitunion.
This change also adjusts the write only signed bitfield assignment operator to
be like the unsigned version, using "using" instead of implementing it again
and calling down to the underlying implementation.
Gabe Black [Wed, 7 Jan 2015 08:31:09 +0000 (00:31 -0800)]
stats: x86: Update stats for the CPUID change.
Gabe Black [Wed, 7 Jan 2015 06:15:00 +0000 (22:15 -0800)]
x86: Enable three bits in the FamilyModelStepping ECX CPUID bitfield.
These are for the monitor/mwait instructions, SSSE3, and XSAVE.
Gabe Black [Wed, 7 Jan 2015 06:13:56 +0000 (22:13 -0800)]
cpuid, x86: Revert "Enabling more features in CPUid"
That change enables CPUID bits for features that aren't implemented in gem5.
If a simulated system tries to use those features because it was told it
could, bad things can happen.
Nilay Vaish [Sun, 4 Jan 2015 19:02:12 +0000 (13:02 -0600)]
stats: changes due to recent changesets.
Anthony Gutierrez [Sat, 3 Jan 2015 23:51:48 +0000 (17:51 -0600)]
arm: fix build_drive_system when not using default options
when trying to dual boot on arm build_drive_system will only use the default
values for the dtb file, number of processors, and disk image. if you are using
the non-default files by passing values on the command line for example, or by
making a new entry in Benchmarks.py, the build config scripts will still look
for the default files. this will lead to the wrong system files being used, or
the simulator will fail if you do not have them.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Andrew Lukefahr [Sat, 3 Jan 2015 23:51:48 +0000 (17:51 -0600)]
minor: fixed LSQ MasterPortID
Minor was reporting the data cache access as ".inst" accesses.
This just switches the MasterPortID to dataMasterPortId.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
mike upton [Sat, 3 Jan 2015 23:51:48 +0000 (17:51 -0600)]
arm: Add unlinkat syscall implementation
added ARM aarch64 unlinkat syscall support, modeled on other <xxx>at syscalls.
This gets all of the cpu2006 int workloads passing in SE mode on aarch64.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Maxime Martinasso [Sat, 3 Jan 2015 23:51:48 +0000 (17:51 -0600)]
x86: implements the simd128 ADDSUBPD instruction
This patch implements the simd128 ADDSUBPD instruction for the x86 architecture.
Tested with a simple program in assembly language which executes the
instruction. Checked that different versions of the instruction are executed
by using the execution tracing option.
Committed by: Nilay Vaish <nilay@cs.wisc.edu
Cagdas Dirik [Sat, 3 Jan 2015 23:51:48 +0000 (17:51 -0600)]
dev: prevent RTC events firing before startup
This change includes edits to MC146818 timer to prevent RTC events
firing before startup to comply with SimObject initialization call sequence.
Committed by: Nilay Vaish <nilay@cs.wisc.edu>
Nilay Vaish [Sat, 3 Jan 2015 23:51:48 +0000 (17:51 -0600)]
configs: ruby: removes bug introduced by
05b5a6cf3521
Joel Hestness [Sat, 27 Dec 2014 19:48:40 +0000 (13:48 -0600)]
syscall_emul: Return correct writev value
According to Linux man pages, if writev is successful, it returns the total
number of bytes written. Otherwise, it returns an error code. Instead of
returning 0, return the result from the actual call to writev in the system
call.
Andreas Hansson [Tue, 23 Dec 2014 14:31:20 +0000 (09:31 -0500)]
stats: Bump stats for decoder, TLB, prefetcher and DRAM changes
Changes due to speculative execution of an unaligned PC, introduction
of TLB stats, changes and re-work of the prefetcher, and the
introduction of rank-wise refresh in the DRAM controller.
Mitch Hayenga [Tue, 23 Dec 2014 14:31:19 +0000 (09:31 -0500)]
mem: Change prefetcher to use random_mt
Prefechers has used rand() to generate random numers previously.
Curtis Dunham [Tue, 23 Dec 2014 14:31:19 +0000 (09:31 -0500)]
mem: Hide WriteInvalidate requests from prefetchers
Without this tweak, a prefetcher will happily prefetch data that will
promptly be invalidated and overwritten by a WriteInvalidate.
Mitch Hayenga [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
mem: Fix event scheduling issue for prefetches
The cache's MemSidePacketQueue schedules a sendEvent based upon
nextMSHRReadyTime() which is the time when the next MSHR is ready or whenever
a future prefetch is ready. However, a prefetch being ready does not guarentee
that it can obtain an MSHR. So, when all MSHRs are full,
the simulation ends up unnecessiciarly scheduling a sendEvent every picosecond
until an MSHR is finally freed and the prefetch can happen.
This patch fixes this by not signaling the prefetch ready time if the prefetch
could not be generated. The event is rescheduled as soon as a MSHR becomes
available.
Mitch Hayenga [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
mem: Fix bug relating to writebacks and prefetches
Previously the code commented about an unhandled case where it might be
possible for a writeback to arrive after a prefetch was generated but
before it was sent to the memory system. I hit that case. Luckily
the prefetchSquash() logic already in the code handles dropping prefetch
request in certian circumstances.
Mitch Hayenga [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
mem: Rework the structuring of the prefetchers
Re-organizes the prefetcher class structure. Previously the
BasePrefetcher forced multiple assumptions on the prefetchers that
inherited from it. This patch makes the BasePrefetcher class truly
representative of base functionality. For example, the base class no
longer enforces FIFO order. Instead, prefetchers with FIFO requests
(like the existing stride and tagged prefetchers) now inherit from a
new QueuedPrefetcher base class.
Finally, the stride-based prefetcher now assumes a custimizable lookup table
(sets/ways) rather than the previous fully associative structure.
Mitch Hayenga [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
mem: Add parameter to reserve MSHR entries for demand access
Adds a new parameter that reserves some number of MSHR entries for demand
accesses. This helps prevent prefetchers from taking all MSHRs, forcing demand
requests from the CPU to stall.
Curtis Dunham [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
arm: Add stats to table walker
This patch adds table walker stats for:
- Walk events
- Instruction vs Data
- Page size histogram
- Wait time and service time histograms
- Pending requests histogram (per cycle) - measures dist. of L
(p(1..) = how often busy, p(0) = how often idle)
- Squashes, before starting and after completion
Andreas Hansson [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
config: Expose the DRAM ranks as a command-line option
This patch gives the user direct influence over the number of DRAM
ranks to make it easier to tune the memory density without affecting
the bandwidth (previously the only means of scaling the device count
was through the number of channels).
The patch also adds some basic sanity checks to ensure that the number
of ranks is a power of two (since we rely on bit slices in the address
decoding).
Andreas Hansson [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
mem: Ensure DRAM controller is idle when in atomic mode
This patch addresses an issue seen with the KVM CPU where the refresh
events scheduled by the DRAM controller forces the simulator to switch
out of the KVM mode, thus killing performance.
The current patch works around the fact that we currently have no
proper API to inform a SimObject of the mode switches. Instead we rely
on drainResume being called after any switch, and cache the previous
mode locally to be able to decide on appropriate actions.
The switcheroo regression require a minor stats bump as a result.
Omar Naji [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
mem: Add rank-wise refresh to the DRAM controller
This patch adds rank-wise refresh to the controller, as opposed to the
channel-wide refresh currently in place. In essence each rank can be
refreshed independently, and for this to be possible the controller
is extended with a state machine per rank.
Without this patch the data bus is always idle during a refresh, as
all the ranks are refreshing at the same time. With the rank-wise
refresh it is possible to use one rank while another one is
refreshing, and thus the data bus can be kept busy.
The patch introduces a Rank class to encapsulate the state per rank,
and also shifts all the relevant banks, activation tracking etc to the
rank. The arbitration is also updated to consider the state of the rank.
Omar Naji [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
mem: Fix a bug in the DRAM controller arbitration
Fix a minor issue that affects multi-rank systems.
Andreas Hansson [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
tests: Add a regression for the stack distance calculator
Re-use the existing traffic generator regression, and enable the stack
distance calculation in the comm monitor, along with the verification
stack.
The traffic generator config is also tuned to not increase the
run-time too much (and actually have some address re-use).
Kanishk Sugand [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
mem: Add stack distance statistics to the CommMonitor
This patch adds the stack distance calculator to the CommMonitor. The
stats are disabled by default.
Kanishk Sugand [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
mem: Add a stack distance calculator
This patch adds a stand-alone stack distance calculator. The stack
distance calculator is a passive SimObject that observes the addresses
passed to it. It calculates stack distances (LRU Distances) of
incoming addresses based on the partial sum hierarchy tree algorithm
described by Alamasi et al. http://doi.acm.org/10.1145/773039.773043.
For each transaction a hashtable look-up is performed. At every
non-unique transaction the tree is traversed from the leaf at the
returned index to the root, the old node is deleted from the tree, and
the sums (to the right) are collected and decremented. The collected
sum represets the stack distance of the found node. At every unique
transaction the stack distance is returned as
numeric_limits<uint64>::max().
In addition to the basic stack distance calculation, a feature to mark
an old node in the tree is added. This is useful if it is required to
see the reuse pattern. For example, Writebacks to the lower level
(e.g. membus from L2), can be marked instead of being removed from the
stack (isMarked flag of Node set to True). And then later if this same
address is accessed (by L1), the value of the isMarked flag would be
True. This gives some insight on how the Writeback policy of the
lower level affect the read/write accesses in an application.
Debugging is enabled by setting the verify flag to true. Debugging is
implemented using a dummy stack that behaves in a naive way, using STL
vectors. Note that this has a large impact on run time.
Marco Elver [Tue, 23 Dec 2014 14:31:18 +0000 (09:31 -0500)]
config: Add --memchecker option
This patch adds the --memchecker option, to denote that a MemChecker
should be instantiated for the system. The exact usage of the MemChecker
depends on the system configuration.
For now CacheConfig.py makes use of the option, adding MemCheckerMonitor
instances between CPUs and D-Caches.
Note, however, that currently this only provides limited checking on a
running system; other parts of the system, such as I/O devices are not
monitored, and may cause warnings to be issued by the monitor.
Marco Elver [Tue, 23 Dec 2014 14:31:17 +0000 (09:31 -0500)]
mem: Add MemChecker and MemCheckerMonitor
This patch adds the MemChecker and MemCheckerMonitor classes. While
MemChecker can be integrated anywhere in the system and is independent,
the most convenient usage is through the MemCheckerMonitor -- this
however, puts limitations on where the MemChecker is able to observe
read/write transactions.