The XBar uses the concept of Layers to model throughput and
instantiates one Layer per master. As it forwards a packet to and from
master, the corresponding Layer is marked as occupied for a number of
cycles. Requests/responses to/from a master are blocked while the
corresponding Layer is occupied. Previously the delay would be
calculated based on the formula 1 + size / width, which assumes that
the Layer is always occupied for 1 cycle while processing the packet
header. This changes makes the header latency a parameter which
defaults to 1.
Change-Id: I12752ab4415617a94fbd8379bcd2ae8982f91fd8
Signed-off-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/30054
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Tested-by: kokoro <noreply+kokoro@google.com>
Setting disable_partial part way through the checks for various build
targets is incorrect and will affect targets based on the order they're
checked.
This change moves the check earlier, makes it consistent across all
builds whether fast is included or not, and stops passing it in as an
option to makeEnv since it now applies universally.
By disabling partial linking consistently, we avoid missing bugs where
only the "fast" version of gem5 doesn't build correctly because of the
multitude of g++ bugs having to do with combining LTO and partial
linking.
This also simplifies the logic in the SConscript by having fewer
independently moving parts.
Change-Id: Iff69f39868e948d3b9a5b11ea80bbfed19419b59
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29303
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Gabe Black <gabeblack@google.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
The ThreadContext can be used to access the cpu if needed, and is a
more representative interface to various pieces of state than the CPU
itself. Also convert some of the methods in Interupts to use the
locally stored ThreadContext pointer instead of taking one as an
argument. This makes calling those methods simpler and less error
prone.
Change-Id: I740bd99f92e54e052a618a4ae2927ea1c4ece193
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/28988
Reviewed-by: Gabe Black <gabeblack@google.com>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
The System class has a few different arrays of values which each
correspond to a thread of execution based on their position. This
change collects them together into a single class to make managing them
easier and less error prone. It also collects methods for manipulating
those threads as an API for that class.
This class acts as a collection point for thread based state which the
System class can look into to get at all its state. It also acts as an
interface for interacting with threads for other classes. This forces
external consumers to use the API instead of accessing the individual
arrays which improves consistency.
Change-Id: Idc4575c5a0b56fe75f5c497809ad91c22bfe26cc
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/25144
Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu>
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Tested-by: kokoro <noreply+kokoro@google.com>
Instead of calling into object files after the fact and asking them to
put symbols into a target symbol table, this change makes object files
fill in a symbol table themselves at construction. Then, that table can
be retrieved and used to fill in aggregate tables, masked, moved,
and/or filtered to have only one type of symbol binding.
This simplifies the symbol management API of the object file types
significantly, and makes it easier to deal with symbol tables alongside
binaries in the FS workload classes.
Change-Id: Ic9006ca432033d72589867c93d9c5f8a1d87f73c
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/24787
Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
When the write buffer is full, it still has space to store an additional
number of entries (reserve) equal to the number of MSHRs so that if any
of them requires a writeback this can be handled. Even if the slave port
is blocked, a prefetcher can generate new MSHR entries that may lead to
additional writebacks and eventually saturate the reserve space. This is
solved by checking if the cache is blocked for accesses before
prefetching data.
Change-Id: Iaad04dd6786a09eab7afae4a53d1b1299c341f33
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29615
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>
All other considerations aside, DTRACE probably fits best in trace.hh
where it is now, but unfortunately that creates an awkward dependence
between that file and eventq.hh and eventq_impl.hh. DTRACE only depends
on flags in the Debug namespace and a universal macro TRACING_ON, so
even though it won't be alongside the things it's most logically
associated with, it will be alongside all of its dependencies.
An alternative would be to re-implement DTRACE in eventq_impl.hh which
wouldn't be too big of a problem because it's so simple, but it's
cleaner and less error prone to still keep a single definition.
Because base/trace.hh includes base/debug.hh, any consumers expecting to
find DTRACE in base/trace.hh will still get that definition, even though
it's no longer direct.
Change-Id: I0dac83295891630686c3a8038eb54138cf40ab44
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29411
Maintainer: Gabe Black <gabeblack@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
After commit e2a5063e5f some
memory references now tracked as barriers were not having
their completion properly notified to the MemDepUnit.
This patch fixes InstructionQueue and changes MemDepUnit's
completeBarrier to completeInst, which now should be called
for both memory references and barrier instructions.
Change-Id: I28b5f112b45778f6272e71bb3766b364c3d2e7db
Signed-off-by: Tiago Mück <tiago.muck@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29654
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
makeLineAddress function uses m_block_size_bits to create
masked addresses. m_block_size_bits is used to specify
cache, directory, and memory controller interleaving,
and it can be larger than the cache line size.
To generate addresses that can align with the cache line
rather than the interleaving granularity, a version of
makeLineAddress is created to specify bits that need to
be masked.
Change-Id: I06deec4949da7fa46f1d6f7575334f18ee61c786
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/28135
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Reviewed-by: Onur Kayıran <onur.kayiran@amd.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
This changeset allows setting a variable for interleaving.
That value is used together with the number of directories to
calculate numa_high_bit, which is in turn used to set up
cache, directory, and memory controller interleaving.
A similar approach is used to set xor_low_bit, and calculate
xor_high_bit for address hashing.
Change-Id: Ia342c77c59ca2e3438db218b5c399c3373618320
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/28134
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
This patch enables cache controllers to make response
messages in advance, store them in a per-address saved
map in an output message buffer and enqueue them altogether
in the future. This patch introduces new slicc statement
called defer_enqueueing. This patch would help simplify
the logic of state machines that deal with coalesing
multiple requests from different requestors.
Change-Id: I566d4004498b367764238bb251260483c5a1a5e5
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/28132
Reviewed-by: Tuan Ta <qtt2@cornell.edu>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Doing arithmetic on a null pointer is undefined behavior in C/C++. Clang
compilers complain when this occurs. As this MACRO is used twice, and
does nothing important, it has been removed in favor of a more simple
solution. A comment has been added explaining the MACRO's removal.
Change-Id: I42d9356179ee0fa5cb20f827af34bb11780ad1a9
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29534
Maintainer: Bobby R. Bruce <bbruce@ucdavis.edu>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Without this fix `error: call to function 'operator<<' that is neither
visible in the template definition nor found by argument-dependent
loopup` is thrown when compiling HSAIL_X86 using a clang compiler (at
`base/cprintf_formats.hhi:139`).
This error is due to a "<<" operator in a template declared prior to its
definition in the code. The operator is used in
`base/cprintf_formats.hh`, included in `base/cprintf.hh`, and defined in
`mem/ruby/common/BoolVec.hh`. Therefore, for clang to compile without
error, `mem/ruby/common/BoolVec.hh` must be included before
`base/cprintf.hh` when generating the
`mem/ruby/protocol/RegionBuffer_Controller.cc` in
`mem/slicc/symbols/StateMachine.py`.
Due to the gem5 style-checker, an overly-verbose solution was required
to permit this patch to be committed to the codebase.
Change-Id: Ie0ae4053e4adc8c4e918e4a714035637925ca104
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29532
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Add support for multiple networks per RubySystem. This is done by
introducing local IDs to each network and translating from a global ID
passed around through Ruby and SLICC code. The local IDs represents the
NodeID of a MachineType in the network and are ordered the same way
that NodeIDs are ordered using MachineType_base_number. If there are
not multiple networks in a RubySystem the local and global IDs are the
same value.
This is useful in cases where multiple isolated networks are needed to
support devices with Ruby caches which do not interact with other
networks. For example, a dGPU device will have a cache hierarchy that
will not interact with the CPU cache hierachy.
Change-Id: I33a917b3a394eec84b16fbf001c3c2c44c047f66
JIRA: https://gem5.atlassian.net/browse/GEM5-445
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/27927
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Reviewed-by: Bradford Beckmann <brad.beckmann@amd.com>
Maintainer: Bradford Beckmann <brad.beckmann@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Newer versions of sfdisk have changed the format of the dump output,
as well as the options for partitioning a disk.
Updated the gem5img.py script to work with the new version of sfdisk.
The script should still work with older versions of sfdisk, but this
has not been tested (see https://askubuntu.com/a/819614).
Tested on Ubuntu 18.04.2 LTS with sfdisk from util-linux 2.31.1.
Change-Id: I1197ecacabdd7caaab00327977fb9ab6eae06654
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/29472
Reviewed-by: Jason Lowe-Power <power.jg@gmail.com>
Maintainer: Jason Lowe-Power <power.jg@gmail.com>
Tested-by: kokoro <noreply+kokoro@google.com>
