| Age | Commit message (Collapse) | Author |
|---|
|
Packet::checkFunctional also wrote data to/from the packet depending
on if it was read/write, respectively, which the 'check' in the name
would suggest otherwise. This renames it to doFunctional, which is
more suggestive. It also renames any function called checkFunctional
which calls Packet::checkFunctional. These are
- Bridge::BridgeMasterPort::checkFunctional
- calls Packet::checkFunctional
- MSHR::checkFunctional
- calls Packet::checkFunctional
- MSHR::TargetList::checkFunctional
- calls Packet::checkFunctional
- Queue<>::checkFunctional
(of src/mem/cache/queue.hh, not src/cpu/minor/buffers.h)
- Instantiated with Queue<WriteQueueEntry> and Queue<MSHR>
- WriteQueueEntry
- calls Packet::checkFunctional
- WriteQueueEntry::TargetList
- calls Packet::checkFunctional
- MemDelay::checkFunctional
- calls QueuedSlavePort/QueuedMasterPort::checkFunctional
- Packet::checkFunctional
- PacketQueue::checkFunctional
- calls Packet::checkFunctional
- QueuedSlavePort::checkFunctional
- calls PacketQueue::doFunctional
- QueuedMasterPort::checkFunctional
- calls PacketQueue::doFunctional
- SerialLink::SerialLinkMasterPort::checkFunctional
- calls Packet::doFunctional
Change-Id: Ieca2579c020c329040da053ba8e25820801b62c5
Reviewed-on: https://gem5-review.googlesource.com/11810
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
|
|
To avoid unintentional variable capture, all std calls must be
prefixed. These are the identifiers which are in the std
namespace (according to
https://en.cppreference.com/w/cpp/symbol_index), but that will remain
unprefixed with this change:
int8_t int16_t int32_t int64_t
uint8_t uint16_t uint32_t uint64_t
The (u)int types are included from the packet header file, which
includes <inttypes.h>, where they occur in the global namespace. They
are in the std namespace in <cinttypes>/<cstdint>.
There is an occurrence of "set" in this file, which is "Packet::set"
and not "std::set", so it is not prefixed with the std namespace
Change-Id: I7f6c0b61b09658e224fe31a9f73150b81861d6f8
Reviewed-on: https://gem5-review.googlesource.com/11809
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
|
|
There was an off-by-one error in the isRead() case, as `val_end` and
`func_end` pointed to the last byte to write to (not one past the last
byte), and thus `*_end - *_start` was not the length of the data to
memcpy.
This was correct in the case of
val_start >= func_start && val_end <= func_end
where `overlap_size = size`, but if it were (as the other cases
suggest) `overlap_size = val_end - val_start`, then it would also be
off by one.
Also, the isWrite() case catered for this.
I simplified the four ifs into one case which uses min/max (this is
how I spotted the inconsistency).
Change-Id: Ib5c5da084652e752f6baf1eec56b51b4f0f5c95c
Reviewed-on: https://gem5-review.googlesource.com/11750
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
The writebacks happen before anything below, not after.
Change-Id: I7eaefbbf33aa17c496255dedd964a56118a28741
Reviewed-on: https://gem5-review.googlesource.com/11749
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
|
|
Add a memory system component that delays traffic. The base
functionality to delay packets is implemented in the abstract MemDelay
class. This class exposes three methods that control packet delays:
* delayReq(pkt)
* delayResp(pkt)
* delaySnoopResp(pkt)
These methods should be specialized to implement delays for specific
packet types.
The class SimpleMemDelay uses the MemDelay base class to implement
constant delays for read/write requests and responses.
The intention is that these classes can be used for rapid prototyping
of components that add a small fixed delay and the same throughput as
the interconnect. I.e., any buffering done in the base class will be
small and proportional to the introduced delay.
Change-Id: I158cb85f20e32bfdbcbfed66a785b4b2dd47b628
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Nicholas Lindsey <nicholas.lindsay@arm.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/11521
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
While a cache clean operation is pending, all requests to the
corresponding block get deferred. When the response of a cache clean
operation is received, if the block is present and the response is not
invalidating, we can service all deferred targets that didn't require
writable. This change implements this functionality.
Change-Id: Ief47e74d07749a6a9736ab450eb46eefa53464a2
Reviewed-on: https://gem5-review.googlesource.com/11018
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
|
|
Until now, all deferred targets of an MSHR would be promoted together
as soon as the targets were serviced. Due to the way we handle cache
clean operations we might need to promote only deferred targets that
don't require writable, leaving some targets as deferred. This change
adds support for this selective promotion.
Change-Id: I502e523dc9adbaf394955cbacea8286ab6a9b6bc
Reviewed-on: https://gem5-review.googlesource.com/11017
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
|
|
There are cases where a request which does not need a writable copy
gets an response upgraded reponse and fills in a writable copy. When
this happens, we promote deferred MSHR targets that were deferred
because they needed a writable copy to service them immediately.
Previously, we would uncoditionally promote deferred targets. Since
the deferred targets might contain a cache invalidation operation, we
have to make sure that any targets following the cache invalidation is
not promoted.
Change-Id: I1f7b28f7d35f84329e065c8f63117db21852365a
Reviewed-on: https://gem5-review.googlesource.com/11016
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
|
|
Until now, all deferred targets of an MSHR would be promoted together
as soon as the targets were serviced. When we promote deferred targets
we also clear the downstreamPending flag.
Due to the way we handle cache clean operations we might need to
promote only deferred targets that don't require writable, leaving
some targets as deferred. To allow for partial target promotion, this
change adds support for clearing the downstreamPending only for a
subset of a TargetsList.
Change-Id: Id06953643ba9a975ebacc76ac10215441e264e74
Reviewed-on: https://gem5-review.googlesource.com/11015
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Jason Lowe-Power <jason@lowepower.com>
|
|
TempCacheBlock insert() had a different signature than the parent class
which caused an error on clang. This matches the signature with default
zero values.
Change-Id: Ic096914497f3d17e88295c9e65a04d76fdddf365
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-on: https://gem5-review.googlesource.com/11349
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Previously, we used the start address to determine the right physical
memory while servicing memory requests. This change uses the full
address range to correctly determine the right physical memory and
expose bugs where requests might not fully map to a single physical
memory.
Change-Id: I183d7552918106000f917a62ceb877511ff0ff71
Reviewed-on: https://gem5-review.googlesource.com/11118
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Previously the xbar used the start address to lookup the port map and
determine the right destination of an incoming packet. This change
uses the full address range to correctly determine the right master.
Change-Id: I5118712c43ae65aba64e71bf030bca5c99770bdd
Reviewed-on: https://gem5-review.googlesource.com/11117
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Use it instead of custom implemented caching.
Change-Id: Ie21012a77a3cb6ce57f34f879fa391678913896a
Reviewed-on: https://gem5-review.googlesource.com/5244
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Use that instead of caching built into the crossbar.
Change-Id: If5a5355a0a1a6e532b14efc88a319de4c023f8c1
Reviewed-on: https://gem5-review.googlesource.com/5243
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
We need to determined whether an address range is fully contained or
it overlaps with an address range in the address range in the mmap. As
an example, we use address range maps to associate ports to address
ranges and we determine which port we will forward the request based
on which address range contains the addresses accessed by the
request. We also need to make sure that when we add a new port to the
address range map, its address range does not overlap with any of the
existing ports.
This patch splits the function find() into two functions contains()
and intersects() to implement this distinct functionality. It also
changes the xbar and the physical memory to use the right function.
Change-Id: If3fd3f774a16b27db2df76dc04f1d61824938008
Reviewed-on: https://gem5-review.googlesource.com/11115
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Fully associative caches use an unordered map to enable efficient
lookups of existing blocks. Previously this map was indexed using the
tag of the block. Security extentions allow secure and non secure
versions of a block with the same tag to co-exist in the cache. This
patch amends the block map to allow correct lookups for FALRU caches.
Change-Id: Iccf07464deab56d1d270bae14bb3b154047e3556
Reviewed-on: https://gem5-review.googlesource.com/11309
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Initialize CacheBlk's data pointer as a nullptr.
Change-Id: Ice85b4b11495cad4b0a160ccb9efe1be673e57e2
Reviewed-on: https://gem5-review.googlesource.com/11097
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Forward declare ReplaceableEntry where in classes where pointers
to it are used.
Change-Id: I49c08d36442a563d7a6b4c9bcd7eba3591d29b60
Reviewed-on: https://gem5-review.googlesource.com/11096
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
AtomicOpFunctor can be used to implement atomic memory operations.
AtomicOpFunctor is captured inside a memory request and executed directly
in the memory hierarchy in a single step.
This patch enables AtomicOpFunctor pointers to be included in a memory
request and executed in a single step in the classic cache system.
This patch also makes the copy constructor of Request class do a deep
copy of AtomicOpFunctor object. This prevents a copy of a Request object
from accessing a deleted AtomicOpFunctor object.
Change-Id: I6649532b37f711e55f4552ad26893efeb300dd37
Reviewed-on: https://gem5-review.googlesource.com/8185
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
There was some bitrot in the standalone SLICC script (util/slicc and
src/mem/slicc/main.py). Fix the changes to the SLICC interface and also
add some better documentation.
Change-Id: I91c0ec78d5072fba83edf32b661ae67967af7822
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-on: https://gem5-review.googlesource.com/10561
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Removes an uneccessary cast that also caused an unused variable
error (due to -Werror) when compiling .fast targets.
Change-Id: Ic043f462925e7eaa7b691455f1d9e08a1c101980
Reviewed-on: https://gem5-review.googlesource.com/11119
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
When a block is being replaced in an allocation, if successfull,
the block will be inserted. Therefore we move the insertion
functionality to allocateBlock().
allocateBlock's signature has been modified to allow this
modification.
Change-Id: I60d17a83ff4f3021fdc976378868ccde6c7507bc
Reviewed-on: https://gem5-review.googlesource.com/10812
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
The packet should not be modified within insertBlock.
Change-Id: If7d2b01fe131f9923194efd155c9e85eeab24d5a
Reviewed-on: https://gem5-review.googlesource.com/10811
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Implementation of Sector Caches, i.e., a cache with multiple
sequential data entries per tag entry for Set Associtive
placement policies.
Change-Id: I8e1e9448fa44ba308ccb16cd5bcc5fd36c988feb
Reviewed-on: https://gem5-review.googlesource.com/9741
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Initial weight was using the timestamp instead of the weight.
Change-Id: I61d3c8424f85fd6856957087c477afda111f8ca7
Reviewed-on: https://gem5-review.googlesource.com/10801
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
|
|
This patch is changing the underlying type for RequestPtr from Request*
to shared_ptr<Request>. Having memory requests being managed by smart
pointers will simplify the code; it will also prevent memory leakage and
dangling pointers.
Change-Id: I7749af38a11ac8eb4d53d8df1252951e0890fde3
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/10996
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Every usage of Request* in the code has been replaced with the
RequestPtr alias. This is a preparing patch for when RequestPtr will be
the typdefed to a smart pointer to Request rather then a raw pointer to
Request.
Change-Id: I73cbaf2d96ea9313a590cdc731a25662950cd51a
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/10995
Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
|
|
Change tag to address check for compatibility with sector design.
Cache should not use tag, as sector sub-blocks share them, and
it could lead to wrong accesses.
Change-Id: Id1fa26f417595f475c5b5c07ae1f02f5fa0684ba
Reviewed-on: https://gem5-review.googlesource.com/10723
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Sector caches must know if there was a sector hit in order
to decide whether a victim's sector must be fully evicted
to give place to a new sector or not.
In order to do so it needs the tag and secure information.
Change-Id: Ib554169e25fa131d6bf986561f7970b787c56874
Reviewed-on: https://gem5-review.googlesource.com/10722
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Move tagsInUse to children, as sector caches have different
tag invalidation and insertion, and thus they must handle
updating this variable.
Change-Id: I875c9b7364a909c76daf610d1e226c4e82063870
Reviewed-on: https://gem5-review.googlesource.com/10721
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
For both sector and compressed caches multiple blocks may need
to be evicted in order to make room for a new block.
For example, when replacing a sector, all the blocks in this
sector must be evicted. A replacement, however, does not always
need to evict multiple blocks, as it is in the case of an
insertion of a block whose sector is already present in the cache
(i.e., its corresponding entry in the sector had not been brought
in yet, so it was invalid).
This patch creates the cache framework for that to happen.
Change-Id: I77bedf69637cf899fef4d9432eb6da8529ea398b
Reviewed-on: https://gem5-review.googlesource.com/10142
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
With a sector cache you can't find a block using only its set
and way, as there is the sector offset to take into account. As
all of these blocks inherit from ReplaceableEntry, the return
type of this function has been updated.
This function has also been declared closer to findBlock() due
to their similar functionality.
Change-Id: I4730a2b4ebb5738f7fc118201e208a1b9c3ba8e8
Reviewed-on: https://gem5-review.googlesource.com/10141
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Only BaseSetAssoc uses extractSet(). Besides, skewed caches need
the way information to know which set an address is located at.
Change-Id: Id222e907dc550d053018561bb2683cfc415471ec
Reviewed-on: https://gem5-review.googlesource.com/9962
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
tempBlock has its member variables manually set in order to allow
it to be used in the block address regeneration function. This is
not necessary, and ti can be simply given the address, so it does
not need to be aware of set and tag. This will simplify
implementation of sector and skewed caches.
Change-Id: Iaffb10c323509722cd5589fe1030b818d43336d6
Reviewed-on: https://gem5-review.googlesource.com/9961
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Secure bit was being updated outside insertion.
Change-Id: I83d9b010e8cf64013bbea9bae3ea68b0c414a189
Reviewed-on: https://gem5-review.googlesource.com/10622
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
This change modifies forEachBlk tags function to accept std::function
as parameter. It also adds an anyBlk tags function that given a
condition, it iterates through the blocks and returns whether the
condition is met.
Finally, it uses forEachBlk to implement the print, computeStats and
cleanupRefs functions that also work for the FALRU class.
Change-Id: I2f75f4baa1fdd5a1d343a63ecace3eb9458fbf03
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/10621
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Change-Id: I111b0f662897c43974aadb08da1ed85c7542585c
Reviewed-on: https://gem5-review.googlesource.com/10433
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
The class re-uses the existing MSHR and write queue. At the moment
every single access is handled by the cache, even uncacheable
accesses, and nothing is forwarded.
This is a modified version of a changeset put together by Andreas
Hansson <andreas.hansson@arm.com>
Change-Id: I41f7f9c2b8c7fa5ec23712a4446e8adb1c9a336a
Reviewed-on: https://gem5-review.googlesource.com/8291
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
|
|
Cache bypass is necessary for cpu models like the KvmCPU. Previously
the bypass would happen at the cache classes. With this change the
bypassing happens directly at the ports.
Change-Id: I34de9fc63383aee8590643e169501ea6060d2d62
Reviewed-on: https://gem5-review.googlesource.com/10432
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
|
|
This patch changes what goes into the BaseCache and what goes into the
Cache, to make it easier to add a NoncoherentCache with as much re-use
as possible. A number of redundant members and definitions are also
removed in the process.
This is a modified version of a changeset put together by Andreas
Hansson <andreas.hansson@arm.com>
Change-Id: Ie9dd73c4ec07732e778e7416b712dad8b4bd5d4b
Reviewed-on: https://gem5-review.googlesource.com/10431
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Change-Id: I2df24eb1a8516220bec9b685c8c09bf55be18681
Reviewed-on: https://gem5-review.googlesource.com/10430
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
|
|
For a block replacement we first select a victim block, we invalidate
it and then populate it with the new information. Prior to this change
BaseTags::insertBlock() did the invalidation and filled in the block
with the new information. Now that the replacements stat is moved to
the BaseCache, insertBlock does not need to perform the invalidation
and as a result we can unify the block eviction code in BaseCache.
Change-Id: I5bdf00b2dab2752ed2137ab7201ed1dc451333b3
Reviewed-on: https://gem5-review.googlesource.com/10429
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
|
|
The recvAtomic function in the cache handles atomic requests. Over
time, recvAtomic has grown in complexity and code size. This change
factors out some of its functionality in a separate functiona. The new
functions handles atomic requests that miss.
Change-Id: If77d2de1e3e802e1da37f889f68910e700c59209
Reviewed-on: https://gem5-review.googlesource.com/10425
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
The recvTimingReq function in the cache handles timing requests. Over
time, recvTimingReq has grown in complexity and code size. This change
factors out some of its functionality in two separate functions. The
new functions handle timing requests that hit and timing requests that
miss separately.
Change-Id: I09902d648d7272f0f9ec2851fa6376f7305ba418
Reviewed-on: https://gem5-review.googlesource.com/10424
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
The recvTimingResp function in the cache handles timing
responses. Over time, recvTimingResp has grown in complexity and code
size. This change factors out some of its functionality to a separate
function. The new function iterates through the in-service targets and
handles them accordingly.
Change-Id: I0ef28288640f6be1b30452b0664d32432e692ea6
Reviewed-on: https://gem5-review.googlesource.com/10423
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Random replacement policy's data was being instantiated with
the incorrect class.
Change-Id: Ib573a6b5a63868d6069997c6279bec3b10c6b9b9
Reviewed-on: https://gem5-review.googlesource.com/10623
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
To decide whether we allocate upon receiving a response we need to
determine if any of the currently serviced requests (non-deferred
targets) is comming from another cache. This change adds support for
tracking this information in the MSHR.
Change-Id: If1db93c12b6af5813b91b9d6b6e5e196d327f038
Reviewed-on: https://gem5-review.googlesource.com/10422
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
This patch has 2 main aspects:
1) Add new parameter to adjust write-to-write delay
2) Enable support of more than 64 banks per controller
Changes for new parameter:
Incorporated a new parameter, tCCD_L_WR, which defaults to tCCD_L.
This parameter can be used to set a unique delay between writes and
between reads.
To incorporate this parameter in the controller, modified the DRAMCtrl
class to have separate variables for read and write column delays.
Used these variables to account for tRTW, tWTR, tBURST, tCCD_L, and tCS
as well as the new tCCD_L_WR parameter.
Changes to support more than 64 banks:
Modified the logic selecting the next command (reorderQueue
and minBankPrep functions). Replaced the unint64_t variables with
a vector of uint32_t elements. There is a uint32_t element defined
per ranks to allow up to 32 banks per rank. This will automatically
scale with ranks without issue.
Change will allow analysis of memory sub-systems beyond the current
landscape.
Change-Id: I0ce466efed58276f843ad90e9ecc0ece6c37d646
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/10103
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Self-refresh is entered during a refresh event, when the
rank was previously in a precharge power-down state.
The original code would enter self-refresh after a refresh
was issued. The device subsequently will issue a refresh
on self-refresh entry. On self-refresh exit, the controller
will issue another refresh command.
Devices require at least one additional refresh to be issued
between self-refresh exit and re-entry. This ensures that enough
refreshes occur in the case when the device narrowly missed a
refresh on self-refresh exit.
To minimize the number of refresh operations and still maintain
the device requirement, the current logic does the following:
1) The controller will still enter self-refresh from a refresh
event, when the previous state was precharge power-down.
However, the refresh itself will be bypassed and the controller
will immediately issue a self-refresh entry.
2) On a self-refresh exit, the controller will immediately
issue a refresh command (per the original logic). This ensures
the devices requirements are met and is a convenient way to
kick off the command state machine.
Change-Id: I1c4b0dcbfa3bdafd755f3ccd65e267fcd700c491
Reviewed-by: Curtis Dunham <curtis.dunham@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/10102
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
The tags in the cache keep track of the number of references to the
blocks as well as the average number of references between an
insertion and the next invalidation. Previously the stats where
updated only on block insertion and invalidations were ignored. This
changes moves the update of the counters to the block invalidation
function.
Change-Id: Ie7672c13813ec278a65232694024d2e5e17c4612
Reviewed-on: https://gem5-review.googlesource.com/10428
Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br>
|
