We were previously running them from the current directory to start
with, and then having the config script switch to the build directory.
That worked, except when output streams might be opened as part of the
global constructors which would run before the config script.
This change makes us start from the build directory directly, making
the switch in the config script unnecessary and ensuring that no files
leak outside of the build when running tests.
Change-Id: I484168793bfc5abc4e5631fb3468733fb9d829af
Reviewed-on: https://gem5-review.googlesource.com/c/14519
Reviewed-by: Gabe Black <gabeblack@google.com>
Maintainer: Gabe Black <gabeblack@google.com>
This will prevent some (but not all) output files the tests generate
from ending up outside the build directory. Because some output file
streams are constructed as global objects, their paths are resolved
relative to the CWD when gem5 starts, before the config script has a
chance to change it.
Subsequent changes will make verify.py should make gem5 start with the
correct working directory, cleaning up the remaining leaking files.
Change-Id: I75a1256719dab4c98ab868c209d09b9dcdabb458
Reviewed-on: https://gem5-review.googlesource.com/c/14518
Reviewed-by: Gabe Black <gabeblack@google.com>
Maintainer: Gabe Black <gabeblack@google.com>
The value that is not initialized has a bogus value that manifests when
using some debug-flags what makes the usage of tracediff a bit more
challenging.
In addition, while debugging with other techniques, it introduces the
problem of understanding if the value of a field is 'intended' or just
an effect of the lack of initialisation.
Change-Id: Ied88caa77479c6f1d5166d80d1a1a057503cb106
Signed-off-by: Giacomo Gabrielli <giacomo.gabrielli@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/13125
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
The Bitselect operation definition used ~ to invert the bits of a mask
value, but if that mask value is of type bool, that generates a
warning. This change casts that value to a uint64_t so that it can
always have ~ applied to it.
Change-Id: I7fbfc6ff264bc32a265f2724c772b8fae08590f7
Reviewed-on: https://gem5-review.googlesource.com/c/14655
Reviewed-by: Brandon Potter <Brandon.Potter@amd.com>
Maintainer: Gabe Black <gabeblack@google.com>
Neither assert(0) nor assert(false) give any hint as to why control
getting to them is bad, and their more descriptive versions,
assert(0 && "description") and assert(false && "description"), jury
rig assert to add an error message when the utility function panic()
already does that directly with better formatting options.
This change replaces that flavor of call to assert with panic, except
in the actual code which processes the formatting that panic uses (to
avoid infinitely recurring error handling), and in some *.sm files
since I don't know what rules those have to follow and don't want to
accidentaly break them.
Change-Id: I8addfbfaf77eaed94ec8191f2ae4efb477cefdd0
Reviewed-on: https://gem5-review.googlesource.com/c/14636
Reviewed-by: Brandon Potter <Brandon.Potter@amd.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
The implementation of the getdents syscall relies on SYS_getdents, which
is not available on all archs, because the getdents syscall has been
superseded by getdents64, and does not exist on newer archs such as
aarch64.
This leads the build to break on aarch64 hosts with error:
error: 'SYS_getdents' was not declared in this scope
Change-Id: I8701fb5b61c0418b14a9463ef135a391a7f7a9ba
Reviewed-on: https://gem5-review.googlesource.com/c/14596
Reviewed-by: Brandon Potter <Brandon.Potter@amd.com>
Maintainer: Brandon Potter <Brandon.Potter@amd.com>
ARM architectures were not covered in the endianess #if cases, which
lead the build to fail on an arm host with message:
error The file boost/detail/endian.hpp needs to be set up for your CPU
type.
Change-Id: Id012cf37810da113174a51746e290e25138739cb
Reviewed-on: https://gem5-review.googlesource.com/c/14595
Reviewed-by: Gabe Black <gabeblack@google.com>
Maintainer: Gabe Black <gabeblack@google.com>
These make it easier to extract the binary representation of floats and
doubles, and given a binary representation convert it back again.
The versions with a size prefix are safer to use since they make it
clear what size inputs/outputs are expected. The versions without are
to make writing generic code easier in case the same code snippet,
templated function, etc., needs to be applied in both circumstances.
Change-Id: Ib1f35a7e88e00806a7c639c211c5699b4af5a472
Reviewed-on: https://gem5-review.googlesource.com/c/14455
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Maintainer: Gabe Black <gabeblack@google.com>
In order to allow polymorphism of the block these two
functions have been added, and all direct status
assignments to these bits have been substituted.
We also assert that the block has been invalidated
before insertion. Then the block is validated in
the insertion.
Change-Id: Ie7be42408721ad4c2c9dc880f82a62cb594f8668
Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br>
Reviewed-on: https://gem5-review.googlesource.com/c/14362
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
This includes TAGE tag sizes, TAGE table sizes, U counters reset period,
loop predictor associativity, path history size, the USE_ALT_ON_NA size
and the WITHLOOP size
Change-Id: I935823f0a5794f5d55b744263798897a813dc1bd
Signed-off-by: Pau Cabre <pau.cabre@metempsy.com>
Reviewed-on: https://gem5-review.googlesource.com/c/14417
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Increased to 2 bits of useful counter per TAGE entry as described in the
LTAGE paper (and made the size configurable)
Changed how the useful counters are incremented/decremented as described
in the LTAGE paper
Change-Id: I8c692cc7c180d29897cb77781681ff498a1d16c8
Signed-off-by: Pau Cabre <pau.cabre@metempsy.com>
Reviewed-on: https://gem5-review.googlesource.com/c/14215
Reviewed-by: Ilias Vougioukas <ilias.vougioukas@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Fixed the following fields of the loop predictor entries as described on
the LTAGE paper:
- Age counter (it was 3 bits and it should be 8 bits)
- Tag (it was 16 bits and it should be 14 bits). Also some times it used
int variables and some times uint16_t, leading to wrong behaviour
- Confidence counter (it was 2 bits ins some parts of the code and 3 bits
in some other parts. It should be 2 bits)
- Iteration counters (they were 16 bits and they should be 14 bits)
All the new sizes are now configurable
Change-Id: I8884c7454c1e510b65160eb4d5749d3259d34096
Signed-off-by: Pau Cabre <pau.cabre@metempsy.com>
Reviewed-on: https://gem5-review.googlesource.com/c/14216
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
This DPRINTF shouldn't be necessary since it shows the operands and
results of the instruction which the trace should already make
available. Also by passing the destination register to DPRINTF, the ISA
parser will assume that it's also a source when tracking dependencies.
Change-Id: I820387c82578bdbb8d2e3d91652a6c0185077f54
Reviewed-on: https://gem5-review.googlesource.com/c/14475
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Gabe Black <gabeblack@google.com>
Other objects in the simulation may try to deschedule their events when
destructed, and if they're cleaned up after the event queue is then
they might try to deschedule events on an event queue that no longer
exists.
Change-Id: I9452ce52fba78297ce3dc4b3884289b5e2f2574d
Reviewed-on: https://gem5-review.googlesource.com/c/14400
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Gabe Black <gabeblack@google.com>
This function catches a couple types of exceptions the functions it
calls might throw, but if one that it doesn't catch is thrown, then
it will propogate that exception to its own callers, and not initialize
the value it was asked to convert.
This might be considered desirable behavior since it lets errors
propogate and avoids handling them in code that might not know the
context of when it's called. On the other hand, it upsets g++ since it
thinks that there might be an uninitialized value used elsewhere, even
though that value will only be uninitialized if an exception is
propogating, and the code that would use it is after a point where that
exception would have been caught and execution would have resumed.
To satisfy g++ and to also avoid silently hiding errors, this change
adds a catch all which will panic if an unexpected exception is raised.
Change-Id: Ie94dcef3a50f7902566328a3fa2eac59b3cf9aad
Reviewed-on: https://gem5-review.googlesource.com/c/14399
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
When the native systemc API support is built in, put the systemc and
systemc.h header files in the include path so they can be used as
normal. We don't want any external systemc headers being included and
getting mixed in with our local ones.
Change-Id: I5fc01ff5f069cfadb7c19a9dead13e7ce7272976
Reviewed-on: https://gem5-review.googlesource.com/c/14397
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Gabe Black <gabeblack@google.com>
This is a reasonable size for a stack, and the default size for a stack
on Linux as determined by some quick Googling. The sc_main fiber would
normally use the primary program stack if run under the standard
systemc implementation, and so might expect to have more room to play
with.
Change-Id: Ie12344939e7b249da203630ebc7dc773a387d716
Reviewed-on: https://gem5-review.googlesource.com/c/14396
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Gabe Black <gabeblack@google.com>
Casts ticks per second value to int before passing it to C++. Python
throws an error because of incompatible type because of the recent
change.
Change-Id: Ibcaf8c327f1be0dba38763975d389584addd8373
Reviewed-on: https://gem5-review.googlesource.com/c/14375
Reviewed-by: Gabe Black <gabeblack@google.com>
Maintainer: Gabe Black <gabeblack@google.com>
Summary: Usage of const DynInstPtr& when possible and introduction of
move operators to RefCountingPtr.
In many places, scoped references to dynamic instructions do a copy of
the DynInstPtr when a reference would do. This is detrimental to
performance. On top of that, in case there is a need for reference
tracking for debugging, the redundant copies make the process much more
painful than it already is.
Also, from the theoretical point of view, a function/method that
defines a convenience name to access an instruction should not be
considered an owner of the data, i.e., doing a copy and not a reference
is not justified.
On a related topic, C++11 introduces move semantics, and those are
useful when, for example, there is a class modelling a HW structure that
contains a list, and has a getHeadOfList function, to prevent doing a
copy to an internal variable -> update pointer, remove from the list ->
update pointer, return value making a copy to the assined variable ->
update pointer, destroy the returned value -> update pointer.
Change-Id: I3bb46c20ef23b6873b469fd22befb251ac44d2f6
Signed-off-by: Giacomo Gabrielli <giacomo.gabrielli@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/13105
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
Move the unordered_map outside of the PCTable, as it
belongs to the StridePrefetcher. By doing so we are
moving towards a table that ressembles the ones of
the Tags classes.
Some functions have been moved from the prefetcher to
the PCTable, as they didn't belong there. As such, they
have been renamed to remove the unnecessary prefix.
Change-Id: I3e54bc7dee65e1f78d96b0d548ac8345b7bd4364
Signed-off-by: Daniel <odanrc@yahoo.com.br>
Reviewed-on: https://gem5-review.googlesource.com/c/14358
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
Return a pointer to the entry instead of returning a
boolean and passing a pointer reference. As a side
effect, change the name of the function to be more
descriptive of the functionality.
Change-Id: Iad44979e98031754c1d0857b1790c0eaf77e9765
Signed-off-by: Daniel <odanrc@yahoo.com.br>
Reviewed-on: https://gem5-review.googlesource.com/c/14356
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
This option can significantly speedup link time on Linux systems, which is
the main bottleneck to rebuild after small changes.
Change-Id: I3b0bdd61f7dcef0d73629c8ee2ee98091953fec3
Reviewed-on: https://gem5-review.googlesource.com/c/14075
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Gabe Black <gabeblack@google.com>
Access latency was not being calculated properly, as it was
always assuming that for hits reads take as long as writes,
and that parallel accesses would produce the same latency
for read and write misses.
By moving the calculation to the Cache we can use the write/
read information, reduce latency variables duplication and
remove Cache dependency from Tags.
The tag lookup latency is still calculated by the Tags.
Change-Id: I71bc68fb5c3515b372c3bf002d61b6f048a45540
Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br>
Reviewed-on: https://gem5-review.googlesource.com/c/13697
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
This patch is moving template overloading for BitUnions into the
showParam, parseParams functions. Henceforth BitUnion types will use the
common param wrapper.
This patch implicitly implements (UN)SERIALIZE_CONTAINER for BitUnions.
Change-Id: I0e1faadb4afd4dc9de5dc5fca40041e349c9ba73
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/13636
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
This patch is moving the definitions of paramIn/Out templates to
the header file. In this way we gain:
1) We don't have to do explicit instantiation anymore for user defined
types. This spares us from including data type header files into
serialize.cc
2) We can overload show/parseParam for BitUnions or any other type
that requires special handling when serializing. Just by overloading
the two templates we get all the containers' (list, vector, array..)
serialization for free
2) gtest: With the idea of adding unit tests for Serializable objects,
we can avoid importing serialize.cc and just redefine Serializable
methods in the test source, implementing a Serializable stub
Change-Id: I45a9bb87d5ef886a3668fd477005cd105f612e36
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/13635
Reviewed-by: Gabe Black <gabeblack@google.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Requests, for which a cache has already committed to respond do not
perform any lookups. Previously in atomic mode the packet would pay
the lookup latency while in timing it wouldn't. This patch aligns
recvAtomic with recvTimingReq and removes the lookup latency from the
the handling of such requests.
Change-Id: I50a0631f8058e5086d94d55af0e1788a60e2883f
Signed-off-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/14175
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
