Commit graph

11232 commits

Author SHA1 Message Date
Mitch Hayenga
4f26bedc18 cpu: Fix SMT scheduling issue with the O3 cpu
The o3 cpu could attempt to schedule inactive threads under round-robin SMT
mode.

This is because it maintained an independent priority list of threads from the
active thread list.  This priority list could be come stale once threads were
inactive, leading to the cpu trying to fetch/commit from inactive threads.


Additionally the fetch queue is now forcibly flushed of instrctuctions
from the de-scheduled thread.

Relevant output:

24557000: system.cpu: [tid:1]: Calling deactivate thread.
24557000: system.cpu: [tid:1]: Removing from active threads list

24557500: system.cpu:
FullO3CPU: Ticking main, FullO3CPU.
24557500: system.cpu.fetch: Running stage.
24557500: system.cpu.fetch: Attempting to fetch from [tid:1]
2014-09-03 07:42:37 -04:00
Mitch Hayenga
daedc5a491 cpu: Fix incorrect speculative branch predictor behavior
When a branch mispredicted gem5 would squash all history after and including
the mispredicted branch.  However, the mispredicted branch is still speculative
and its history is required to rollback state if another, older, branch
mispredicts.  This leads to things like RAS corruption.
2014-09-03 07:42:36 -04:00
Mitch Hayenga
ecd5300971 cpu: Add a fetch queue to the o3 cpu
This patch adds a fetch queue that sits between fetch and decode to the
o3 cpu.  This effectively decouples fetch from decode stalls allowing it
to be more aggressive, running futher ahead in the instruction stream.
2014-09-03 07:42:35 -04:00
Mitch Hayenga
1716749c8c cpu: Fix o3 front-end pipeline interlock behavior
The o3 pipeline interlock/stall logic is incorrect.  o3 unnecessicarily stalled
fetch and decode due to later stages in the pipeline.  In general, a stage
should usually only consider if it is stalled by the adjacent, downstream stage.
Forcing stalls due to later stages creates and results in bubbles in the
pipeline.  Additionally, o3 stalled the entire frontend (fetch, decode, rename)
on a branch mispredict while the ROB is being serially walked to update the
RAT (robSquashing). Only should have stalled at rename.
2014-09-03 07:42:34 -04:00
Mitch Hayenga
976f27487b cpu: Change writeback modeling for outstanding instructions
As highlighed on the mailing list gem5's writeback modeling can impact
performance.  This patch removes the limitation on maximum outstanding issued
instructions, however the number that can writeback in a single cycle is still
respected in instToCommit().
2014-09-03 07:42:33 -04:00
Mitch Hayenga
fd722946dd arch: Properly guess OpClass from optional StaticInst flags
isa_parser.py guesses the OpClass if none were given based upon the StaticInst
flags.  The existing code does not take into account optionally set flags.
This code hoists the setting of optional flags so OpClass is properly assigned.
2014-09-03 07:42:32 -04:00
Geoffrey Blake
b404ffde60 cache: Fix handling of LL/SC requests under contention
If a set of LL/SC requests contend on the same cache block we
can get into a situation where CPUs will deadlock if they expect
a failed SC to supply them data.  This case happens where 3 or
more cores are contending for a cache block using LL/SC and the system
is configured where 2 cores are connected to a local bus and the
third is connected to a remote bus.  If a core on the local bus
sends an SCUpgrade and the core on the remote bus sends and SCUpgrade
they will race to see who will win the SC access.  In the meantime
if the other core appends a read to one of the SCUpgrades it will expect
to be supplied data by that SCUpgrade transaction.  If it happens that
the SCUpgrade that was picked to supply the data is failed, it will
drop the appended request for data and never respond, leaving the requesting
core to deadlock.  This patch makes all SC's behave as normal stores to
prevent this case but still makes sure to check whether it can perform
the update.
2014-09-03 07:42:31 -04:00
Curtis Dunham
12210ada54 arm: support 16kb vm granules 2014-05-27 11:00:56 -05:00
Andreas Hansson
0756406739 mem: Add utility script to plot DRAM efficiency sweep
This patch adds basic functionality to quickly visualise the output
from the DRAM efficiency script. There are some unfortunate hacks
needed to communicate the needed information from one script to the
other, and we fall back on (ab)using the simout to do this.

As part of this patch we also trim the efficiency sweep to stop at 512
bytes as this should be sufficient for all forseeable DRAMs.
2014-09-03 07:42:29 -04:00
Andreas Hansson
77c28cc395 mem: Packet queue clean up
No change in functionality, just a bit of tidying up.
2014-09-03 07:42:28 -04:00
Mitch Hayenga
71769d2d7b dev: Avoid invalid sized reads in PL390 with DPRINTF enabled
The first DPRINTF() in PL390::writeDistributor always read a uint32_t, though a
packet may have only been 1 or 2 bytes.  This caused an assertion in
packet->get().
2014-09-03 07:42:27 -04:00
Andrew Bardsley
87f6034462 sim: Fix checkpoint restore for Ticked
This patch makes restoring the 'lastStopped' value for Ticked-containing
objects (including MinorCPU) optional so that Ticked-containing objects
can be restored from non-Ticked-containing objects (such as AtomicSimpleCPU).
2014-09-03 07:42:25 -04:00
Andreas Sandberg
326662b01b arch, cpu: Factor out the ExecContext into a proper base class
We currently generate and compile one version of the ISA code per CPU
model. This is obviously wasting a lot of resources at compile
time. This changeset factors out the interface into a separate
ExecContext class, which also serves as documentation for the
interface between CPUs and the ISA code. While doing so, this
changeset also fixes up interface inconsistencies between the
different CPU models.

The main argument for using one set of ISA code per CPU model has
always been performance as this avoid indirect branches in the
generated code. However, this argument does not hold water. Booting
Linux on a simulated ARM system running in atomic mode
(opt/10.linux-boot/realview-simple-atomic) is actually 2% faster
(compiled using clang 3.4) after applying this patch. Additionally,
compilation time is decreased by 35%.
2014-09-03 07:42:22 -04:00
Andreas Hansson
e1ac962939 arch: Cleanup unused ISA traits constants
This patch prunes unused values, and also unifies how the values are
defined (not using an enum for ALPHA), aligning the use of int vs Addr
etc.

The patch also removes the duplication of PageBytes/PageShift and
VMPageSize/LogVMPageSize. For all ISAs the two pairs had identical
values and the latter has been removed.
2014-09-03 07:42:21 -04:00
Mitch Hayenga
23c8540756 config: Change parsing of Addr so hex values work from scripts
When passed from a configuration script with a hexadecimal value (like
"0x80000000"), gem5 would error out. This is because it would call
"toMemorySize" which requires the argument to end with a size specifier (like
1MB, etc).

This modification makes it so raw hex values can be passed through Addr
parameters from the configuration scripts.
2014-09-03 07:42:20 -04:00
Andreas Hansson
1046b8d6e5 arm: Fix ExtMachInst hash operator underlying type
This patch fixes the hash operator used for ARM ExtMachInst, which
incorrectly was still using uint32_t. Instead of changing it to
uint64_t it is not using the underlying data type of the BitUnion.
2014-09-03 07:42:19 -04:00
Nilay Vaish
fa1fbcf020 stats: updates due to recent ruby and x86 changes
Also updates many out of date config files.
2014-09-01 16:55:52 -05:00
Nilay Vaish
2cbe7c705b ruby: remove typedef of Index as int64
The Index type defined as typedef int64 does not really provide any help
since in most places we use primitive types instead of Index.  Also, the name
Index is very generic that it does not merit being used as a typename.
2014-09-01 16:55:50 -05:00
Nilay Vaish
4ccdf8fb81 x86: set op class of two fp instructions
This patch sets op class of two fp instructions: movfp and pop x87 stack
as IntAluOp since these instructions do not make use of the fp alu.
2014-09-01 16:55:49 -05:00
Nilay Vaish
b4dade6fb2 ruby: PerfectSwitch: moves code to a per vnet helper function
This patch moves code from the wakeup() function to a operateVnet().
The aim is to improve the readiblity of the code.
2014-09-01 16:55:48 -05:00
Nilay Vaish
7a0d5aafe4 ruby: message buffers: significant changes
This patch is the final patch in a series of patches.  The aim of the series
is to make ruby more configurable than it was.  More specifically, the
connections between controllers are not at all possible (unless one is ready
to make significant changes to the coherence protocol).  Moreover the buffers
themselves are magically connected to the network inside the slicc code.
These connections are not part of the configuration file.

This patch makes changes so that these connections will now be made in the
python configuration files associated with the protocols.  This requires
each state machine to expose the message buffers it uses for input and output.
So, the patch makes these buffers configurable members of the machines.

The patch drops the slicc code that usd to connect these buffers to the
network.  Now these buffers are exposed to the python configuration system
as Master and Slave ports.  In the configuration files, any master port
can be connected any slave port.  The file pyobject.cc has been modified to
take care of allocating the actual message buffer.  This is inline with how
other port connections work.
2014-09-01 16:55:47 -05:00
Nilay Vaish
00286fc5cb build opts: add MI_example to NULL ISA
A later changeset changes the file src/python/swig/pyobject.cc to include
a header file that includes a header file generated at build time depending
on the PROTOCOL in use.  Since NULL ISA was not specifying any protocol,
this resulted in compilation problems.  Hence, the changeset.
2014-09-01 16:55:46 -05:00
Nilay Vaish
d07abd9b5b mem: change the namespace Message to ProtoMessage
The namespace Message conflicts with the Message data type used extensively
in Ruby.  Since Ruby is being moved to the same Master/Slave ports based
configuration style as the rest of gem5, this conflict needs to be resolved.
Hence, the namespace is being renamed to ProtoMessage.
2014-09-01 16:55:46 -05:00
Nilay Vaish
cee8faaad0 ruby: slicc: change the way configurable members are specified
There are two changes this patch makes to the way configurable members of a
state machine are specified in SLICC.  The first change is that the data
member declarations will need to be separated by a semi-colon instead of a
comma.  Secondly, the default value to be assigned would now use SLICC's
assignment operator i.e. ':='.
2014-09-01 16:55:45 -05:00
Nilay Vaish
b1d3873ec5 ruby: slicc: improve the grammar
This patch changes the grammar for SLICC so as to remove some of the
redundant / duplicate rules.  In particular rules for object/variable
declaration and class member declaration have been unified. Similarly, the
rules for a general function and a class method have been unified.

One more change is in the priority of two rules.  The first rule is on
declaring a function with all the params typed and named.  The second rule is
on declaring a function with all the params only typed.  Earlier the second
rule had a higher priority.  Now the first rule has a higher priority.
2014-09-01 16:55:44 -05:00
Nilay Vaish
3202ec98e7 ruby: mesi three level: slight naming changes. 2014-09-01 16:55:44 -05:00
Nilay Vaish
557200725c ruby: slicc: donot prefix machine name to variables
This changeset does away with prefixing of member variables of state machines
with the identity of the machine itself.
2014-09-01 16:55:43 -05:00
Nilay Vaish
6ceb1aadc2 ruby: remove unused toString() from AbstractController 2014-09-01 16:55:42 -05:00
Nilay Vaish
00dbadcbb0 ruby: network: move getNumNodes() to base class
All the implementations were doing the same things.
2014-09-01 16:55:42 -05:00
Nilay Vaish
cc2cc58869 ruby: eliminate type Time
There is another type Time in src/base class which results in a conflict.
2014-09-01 16:55:41 -05:00
Nilay Vaish
82d136285d ruby: move files from ruby/system to ruby/structures
The directory ruby/system is crowded and unorganized. Hence, the files the
hold actual physical structures, are being moved to the directory
ruby/structures.  This includes Cache Memory, Directory Memory,
Memory Controller, Wire Buffer, TBE Table, Perfect Cache Memory, Timer Table,
Bank Array.

The directory ruby/systems has the glue code that holds these structures
together.

--HG--
rename : src/mem/ruby/system/MachineID.hh => src/mem/ruby/common/MachineID.hh
rename : src/mem/ruby/buffers/MessageBuffer.cc => src/mem/ruby/network/MessageBuffer.cc
rename : src/mem/ruby/buffers/MessageBuffer.hh => src/mem/ruby/network/MessageBuffer.hh
rename : src/mem/ruby/buffers/MessageBufferNode.cc => src/mem/ruby/network/MessageBufferNode.cc
rename : src/mem/ruby/buffers/MessageBufferNode.hh => src/mem/ruby/network/MessageBufferNode.hh
rename : src/mem/ruby/system/AbstractReplacementPolicy.hh => src/mem/ruby/structures/AbstractReplacementPolicy.hh
rename : src/mem/ruby/system/BankedArray.cc => src/mem/ruby/structures/BankedArray.cc
rename : src/mem/ruby/system/BankedArray.hh => src/mem/ruby/structures/BankedArray.hh
rename : src/mem/ruby/system/Cache.py => src/mem/ruby/structures/Cache.py
rename : src/mem/ruby/system/CacheMemory.cc => src/mem/ruby/structures/CacheMemory.cc
rename : src/mem/ruby/system/CacheMemory.hh => src/mem/ruby/structures/CacheMemory.hh
rename : src/mem/ruby/system/DirectoryMemory.cc => src/mem/ruby/structures/DirectoryMemory.cc
rename : src/mem/ruby/system/DirectoryMemory.hh => src/mem/ruby/structures/DirectoryMemory.hh
rename : src/mem/ruby/system/DirectoryMemory.py => src/mem/ruby/structures/DirectoryMemory.py
rename : src/mem/ruby/system/LRUPolicy.hh => src/mem/ruby/structures/LRUPolicy.hh
rename : src/mem/ruby/system/MemoryControl.cc => src/mem/ruby/structures/MemoryControl.cc
rename : src/mem/ruby/system/MemoryControl.hh => src/mem/ruby/structures/MemoryControl.hh
rename : src/mem/ruby/system/MemoryControl.py => src/mem/ruby/structures/MemoryControl.py
rename : src/mem/ruby/system/MemoryNode.cc => src/mem/ruby/structures/MemoryNode.cc
rename : src/mem/ruby/system/MemoryNode.hh => src/mem/ruby/structures/MemoryNode.hh
rename : src/mem/ruby/system/MemoryVector.hh => src/mem/ruby/structures/MemoryVector.hh
rename : src/mem/ruby/system/PerfectCacheMemory.hh => src/mem/ruby/structures/PerfectCacheMemory.hh
rename : src/mem/ruby/system/PersistentTable.cc => src/mem/ruby/structures/PersistentTable.cc
rename : src/mem/ruby/system/PersistentTable.hh => src/mem/ruby/structures/PersistentTable.hh
rename : src/mem/ruby/system/PseudoLRUPolicy.hh => src/mem/ruby/structures/PseudoLRUPolicy.hh
rename : src/mem/ruby/system/RubyMemoryControl.cc => src/mem/ruby/structures/RubyMemoryControl.cc
rename : src/mem/ruby/system/RubyMemoryControl.hh => src/mem/ruby/structures/RubyMemoryControl.hh
rename : src/mem/ruby/system/RubyMemoryControl.py => src/mem/ruby/structures/RubyMemoryControl.py
rename : src/mem/ruby/system/SparseMemory.cc => src/mem/ruby/structures/SparseMemory.cc
rename : src/mem/ruby/system/SparseMemory.hh => src/mem/ruby/structures/SparseMemory.hh
rename : src/mem/ruby/system/TBETable.hh => src/mem/ruby/structures/TBETable.hh
rename : src/mem/ruby/system/TimerTable.cc => src/mem/ruby/structures/TimerTable.cc
rename : src/mem/ruby/system/TimerTable.hh => src/mem/ruby/structures/TimerTable.hh
rename : src/mem/ruby/system/WireBuffer.cc => src/mem/ruby/structures/WireBuffer.cc
rename : src/mem/ruby/system/WireBuffer.hh => src/mem/ruby/structures/WireBuffer.hh
rename : src/mem/ruby/system/WireBuffer.py => src/mem/ruby/structures/WireBuffer.py
rename : src/mem/ruby/recorder/CacheRecorder.cc => src/mem/ruby/system/CacheRecorder.cc
rename : src/mem/ruby/recorder/CacheRecorder.hh => src/mem/ruby/system/CacheRecorder.hh
2014-09-01 16:55:40 -05:00
Emilio Castillo ext:(%2C%20Nilay%20Vaish%20%3Cnilay%40cs.wisc.edu%3E)
01f792a367 ruby: Fixes clock domains in configuration files
This patch fixes scripts related to ruby by adding the ruby clock domain.
Now the L1 controllers and  the Sequencer shares the cpu clock domain,
while the rest of the components use the ruby clock domain.

Before this patch, running simulations with the cpu clock set at 2GHz or
1GHz will output the same time results and could distort power measurements.

Committed by: Nilay Vaish <nilay@cs.wisc.edu>
2014-09-01 16:55:30 -05:00
Alexandru
5efbb4442a mem: adding architectural page table support for SE mode
This patch enables the use of page tables that are stored in system memory
and respect x86 specification, in SE mode. It defines an architectural
page table for x86 as a MultiLevelPageTable class and puts a placeholder
class for other ISAs page tables, giving the possibility for future
implementation.
2014-08-28 10:11:44 -05:00
Alexandru
26ac28dec2 mem: adding a multi-level page table class
This patch defines a multi-level page table class that stores the page table in
system memory, consistent with ISA specifications. In this way, cpu models that
use the actual hardware to execute (e.g. KvmCPU), are able to traverse the page
table.
2014-04-01 12:18:12 -05:00
Nilay Vaish
6dc90da08f Added tag stable_2014_08_26 for changeset cb2e6950956d 2014-08-26 14:41:23 -05:00
Andreas Hansson
9e4cd5bf1e mem: Fix DRAMSim2 cycle check when restoring from checkpoint
This patch ensures the cycle check is still valid even restoring from
a checkpoint. In this case the DRAMSim2 cycle count is relative to the
startTick rather than 0.
2014-08-26 10:14:38 -04:00
Andreas Hansson
6fa8015b7f base: Add const to intmath and be more flexible with typing
This patch ensures the functions can be used on const variables.
2014-08-26 10:14:32 -04:00
Andreas Sandberg
2e17d83629 style: Add support for a style ignore list and ignore ext/
There are some directories within the repository where we don't want
to enforce our coding style. Specifically, we don't want the style
hooks to warn whenever we update external code in the ext/ directory.
2014-08-26 10:14:30 -04:00
Andreas Sandberg
35bc5210d3 style: Fixup strange semantics in hg m5style
The 'hg m5style' command had some rather strange semantics. When
called without arguments, it applied the style checker to all added
files and modified regions of modified files. However, when providing
a list of files, it used that list as an ignore list instead of
specifically checking those files.

This patch makes the m5style command behave more like other Mercurial
commands where the arguments are used to specify which files to work
on instead of which files to ignore.
2014-08-26 10:14:07 -04:00
Andreas Sandberg
70176fecd1 base: Replace the internal varargs stuff with C++11 constructs
We currently use our own home-baked support for type-safe variadic
functions. This is confusing and somewhat limited (e.g., cprintf only
supports a limited number of arguments). This changeset converts all
uses of our internal varargs support to use C++11 variadic macros.
2014-08-26 10:13:45 -04:00
Andreas Sandberg
f3e5fee743 base: Add compiler macros for C++11 final/override
Add the macros M5_ATTR_FINAL and M5_ATTR_OVERRIDE which are defined to
final and override respectively if supported by the compiler. This is
done to allow a smooth transition to gcc >= 4.7.
2014-08-26 10:13:33 -04:00
Mitch Hayenga
0da99b7e0c mips: Fix RLIMIT_RSS naming
MIPS defined RLIMIT_RSS in a way that could cause a naming conflict with
RLIMIT_RSS from the host system.  Broke clang+MacOS build.
2014-08-26 10:13:31 -04:00
Andreas Sandberg
61b8d5e4e4 base: Add a static assert to check bit union ranges
If a bit field in a bit union specified as Bitfield<LSB, MSB> instead
of Bitfield<MSB, LSB> the code silently fails and the field is read as
zero. This changeset introduces a static assert that tests, at compile
time, that the bit order is correct.
2014-08-26 10:13:28 -04:00
Andreas Sandberg
a3d3eb0ff7 sparc: Fixup bit ordering in the PSTATE bit union
The order of the MSB and LSB bit of the mm field in the PSTATE union
is wrong. Any access to this field will currently be ignored and reads
will always return zero. This patch fixes the ordering so it is <MSB,
LSB> instead of <LSB, MSB>.
2014-08-26 10:13:23 -04:00
Andreas Hansson
3efabb4b2f mem: Update DRAM controller comments
Update comments and add a reference for more information.
2014-08-26 10:13:03 -04:00
Andreas Hansson
56b7796e0d mem: Fix address interleaving bug in DRAM controller
This patch fixes a bug in the DRAM controller address decoding. In
cases where the DRAM burst size (e.g. 32 bytes in a rank with a single
LPDDR3 x32) was smaller than the channel interleaving size
(e.g. systems with a 64-byte cache line) one address bit effectively
got used as a channel bit when it should have been a low-order column
bit.

This patch adds a notion of "columns per stripe", and more clearly
deals with the low-order column bits and high-order column bits. The
patch also relaxes the granularity check such that it is possible to
use interleaving granularities other than the cache line size.

The patch also adds a missing M5_CLASS_VAR_USED to the tCK member as
it is only used in the debug build for now.
2014-08-26 10:12:45 -04:00
Curtis Dunham
04d1f61ae8 sim: bump checkpoint version for multiple event queues
This patch adds a fix for older checkpoints before support for
multiple event queues were added in changeset 2cce74fe359e. The change
in checkpoint version should really hav ebeen part of the
aforementioned changeset.
2014-02-05 16:17:41 -06:00
Andreas Hansson
4a3abf3020 misc: README direct to website for dependencies
This patch updates the README to direct the user to the appropriate
sections on the gem5.org website rather than duplicating information.
2014-08-26 10:12:04 -04:00
Dam Sunwoo
b04d6c7c33 arm: change MISCREG_L2ERRSR to warn not fail
Some newer binaries compiled for Versatile Express TC2 contain access
to implementation specific L2MERRSR registers. This causes an infinite
loop of undefined exceptions. This patch changes the behavior to "warn
not fail" to keep the workloads going.
2014-08-13 06:57:36 -04:00
Dam Sunwoo
74a4926fe0 sim: remove kernel mapping check for baremetal workloads
Baremetal workloads are specified using the "kernel" parameter, but
don't always have the correct address mappings. This patch adds a
boolean flag to the system and bypasses the kernel addr mapping checks
when running in baremetal mode.
2014-08-13 06:57:35 -04:00