summaryrefslogtreecommitdiff
path: root/src/mem
AgeCommit message (Collapse)Author
2019-10-31mem-ruby: Fixed pipeline squashes caused by aliased requestsJoe Gross
This patch was created by Bihn Pham during his internship at AMD. This patch fixes a very significant performance bug when using the O3 CPU model and Ruby. The issue was Ruby returned false when it received a request to the same address that already has an outstanding request or when the memory is blocked. As a result, O3 unnecessary squashed the pipeline and re-executed instructions. This fix merges readRequestTable and writeRequestTable in Sequencer into a single request table that keeps track of all requests and allows multiple outstanding requests to the same address. This prevents O3 from squashing the pipeline. Change-Id: If934d57b4736861e342de0ab18be4feec464273d Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21219 Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com> Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-29mem-cache: Add a repeated value pattern to compressorsDaniel R. Carvalho
The repeated value pattern checks if values are composed of multiple instances of the same value. If successful, the bits of the repeated value are included only once in the compressed data. Change-Id: Ia7045b4e33a91fd8d712fe1ca689f7f8cb4e5feb Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21153 Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-29mem-cache: Inform unused bits instead of bytes in compressor patternDaniel R. Carvalho
Increase pattern precision by giving the number of unmatched bits instead of bytes. Change-Id: I5efbe9c31672cc973b4c89c741cdc8cc28d26285 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21152 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-29mem-cache: Add a masked const value pattern to compressorsDaniel R. Carvalho
The masked pattern compares values to masked const non-dictionary values to determine whether these match. If successful, the bits that do not match must be added to the compressed data. Change-Id: I4c53568694dab916136fe384cb2ee10e554f7136 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21151 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-29mem-cache: Add a masked pattern to compressorsDaniel R. Carvalho
The masked pattern compares masked values to masked dictionary entries to determine whether these values match. If successful, the bits that do not match must be added to the compressed data. Change-Id: I4b1c8feb0faa99576382b54a73a20c353f965d2a Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21150 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-29mem-cache: Add an uncompressed pattern to compressorsDaniel R. Carvalho
The uncompressed pattern always stores the original data, and therefore it is always successful. All of the derived classes of the dictionary compressor must have this pattern as the last pattern of the pattern factory. Change-Id: I2a38fd56630d88ef8b918220dc4c2824a196a8a2 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21149 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-29mem-cache: Templatize DictionaryCompressorDaniel R. Carvalho
Templatize DictionaryCompressor so that the dictionary entries' sizes can be changed. Change-Id: I3d89e3c692a721cefcd7e3c55d2ccdefa425f614 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21148 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
2019-10-29mem-cache: Factor out CPack's dictionary functionalityDaniel R. Carvalho
Factor out dictionary functionality of CPack, so that it can be used easily for other compressors. As a side effect, create an addToDictionary function to allow subclasses to chose how to handle insertion. Change-Id: I02fae4e98b02db5a40467ec470b71020d5e867cb Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21147 Tested-by: kokoro <noreply+kokoro@google.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu>
2019-10-29mem-cache: Use shouldAllocate() instead of CPack's decompress()Daniel R. Carvalho
Split decompression functionality using the proper function to determine if a dictionary entry should be allocated after decompression or not. Change-Id: I4995304f4c4508c03c9fc1685f04511622969556 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21146 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
2019-10-29mem-cache: Limit compression sizeDaniel R. Carvalho
Add a threshold so that if the compressed size is greater than it, the compression is abandoned, and the data is considered uncompressible. Change-Id: Ic416195b06ec440a40263b75bd0f0383cde2ea6a Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21144 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Bobby R. Bruce <bbruce@ucdavis.edu> Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
2019-10-29mem-cache: Do not try to compress dataless packetsDaniel R. Carvalho
Fix filling blocks so that packets that do not contain data do not generate a compression attempt. This can happen, for example, with invalidation responses, which will trigger a packet data access assertion. Change-Id: I2a1e7983657f6e5e770b148ab62c9de9ac3986ac Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22164 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-29mem: Fix DRAM controller to operate on its own address spaceNikos Nikoleris
Typically, a memory controller is assigned an address range of the form [start, end). This address range might be interleaved and therefore only a non-continuous subset of the addresses in the address range is handed by this controller. Prior to this patch, the DRAM controller was unaware of the interleaving and as a result the address range could affect the mapping of addresses to DRAM ranks, rows and columns. This patch changes the DRAM controller, to transform the input address to a continuous range of the form [0, size). As a result the DRAM controller always operates on a dense and continuous address range regardlesss of the system configuration. Change-Id: I7d273a630928421d1854658c9bb0ab34e9360851 Signed-off-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/19328 Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br> Reviewed-by: Wendy Elsasser <wendy.elsasser@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-29mem-cache: Avoid promotion of incompatible deferred targetsNikos Nikoleris
Often a request that hits on an MSHR has to be deferred as it can't be serviced by the current response. For example, a request that requires writable has to be deferred when the response is expected to bring in a read-only copy of the block. However, there are cases where the response, although not expected to do so, brings a writable copy and as a result we also service deferred targets. In such cases, we promote deferred targets up until the first that can't be serviced by the current response (e.g., cache maintainance operation). If the first deferred target is incompatible we don't promote any targets at all. Change-Id: Ib3e13be51120b7c0f0053b83b76bde03e1b7dd4e Signed-off-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22127 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2019-10-29mem-cache: Fix MSHR whole line write trackingNikos Nikoleris
The MSHR keeps track of outstanding writes and services them as a whole line write whenever possible. To do this the outstanding writes have to be compatible (e.g., not strictly ordered). Prior to this change, due to this tracking mechanism, the MSHR would not service a WriteLineReq with flags that do not allow merging as a full line write even if it was the first target triggering an assertion. This changeset fixes this bug. Change-Id: I2cbf5ece0c108c1fcfe6855e8f194408d5ab8ce2 Signed-off-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/22126 Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-18mem: Delete the MessageReq and MessageResp memory commands.Gabe Black
Now that Message*Port is gone, there are no users of these two memory commands. They can now be deleted, simplifying the memory system slightly. Change-Id: If157dade4a3fb2610756c2ee81dc0c3fac670a26 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20824 Reviewed-by: Gabe Black <gabeblack@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Gabe Black <gabeblack@google.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-13mem-cache: set the second chance to false when inserting a blockMingyuan
Modify second chance replacement policy so that entries are inserted without a second chance. Previously, the second chance bit was set to true when a cache line was inserted. So the cache line would gain its second chance when inserting. This is wrong because the cache block will only get a second chance when it hits. Here's a quoted citation for the second chance replacement policy: "Whenever the algorithm examines a page entry, it extracts the associated usage bit and enters it into the high-order position of a k-bit shift register after shifting the contents of the register one bit-position lower. Then if the shift register is nonzero, the page is retained; if the shift register is zero, the page is replaced by the new page. In either case the usage bit for the page is turned off and the circular list pointer is advanced." (A Paging Experiment with the Multics System, FJ Corbato, 1968) Change-Id: I0d07e56aa16c67dd36e0d490c3f457f91e46f320 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20882 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2019-10-12mem-cache: Fixed a bug in MRU replacement policyMingyuan
The lastTouchTick is set to 0 when instantiate. This will cause the candidate[0] to get evicted over and over again in MRU replacement policy. To resolve this, break the search loop whenever it finds a cold cache line. Change-Id: I33aa57ebe0efca15986f62c3ae10a146bd2b779f Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20881 Tested-by: kokoro <noreply+kokoro@google.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br> Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
2019-10-11mem-ruby: Allow Ruby to use all replacement policies in ClassicJingQuJQ
Add support in Ruby to use all replacement policies in Classic. Furthermore, if new replacement policies are added to the Classic system, the Ruby system will recognize new policies without any other changes in Ruby system. The following list all the major changes: * Make Ruby cache entries (AbstractCacheEntry) inherit from Classic cache entries (ReplaceableEntry). By doing this, replacement policies can use cache entries from Ruby caches. AccessPermission and print function are moved from AbstractEntry to AbstractCacheEntry, so AbstractEntry is no longer needed. * DirectoryMemory and all SLICC files are changed to use AbstractCacheEntry as their cache entry interface. So do the python files in mem/slicc/ast which check the entry interface. * "main='false'" argument is added to the protocol files where the DirectoryEntry is defined. This change helps differentiate DirectoryEntry from CacheEntry because they are both the instances of AbstractCacheEntry now. * Use BaseReplacementPolicy in Ruby caches instead of AbstractReplacementPolicy so that Ruby caches will recognize the replacement policies from Classic. * Add getLastAccess() and useOccupancy() function to Classic system so that Ruby caches can use them. Move lastTouchTick to ReplacementData struct because it's needed by getLastAccess() to return the correct value. * Add a 2-dimensional array of ReplacementData in Ruby caches to store information for different replacement policies. Note that, unlike Classic caches, where policy information is stored in cache entries, the policy information needs to be stored in a new 2-dimensional array. This is due to Ruby caches deleting the cache entry every time the corresponding cache line get evicted. Change-Id: Idff6fdd2102a552c103e9d5f31f779aae052943f Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20879 Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br> Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-10-03mem: Remove unused variableTommaso Marinelli
The variable *sys in dram_ctrl.cc was only used in an assert() check, therefore it has been removed to allow building gem5.fast without errors. A typo in a comment in abstract_mem.hh has also been corrected. Change-Id: I2663545449ecfdb5a27c3574b79dd42beb4a49c8 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21380 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com> Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
2019-10-01mem-cache: Fix invalid whenReadyDaniel R. Carvalho
When a writeback needs to be allocated the whenReady field of the block is not set, and therefore its access latency calculation uses the previously invalidated value (MaxTick), significantly delaying execution. This is fixed by assuming that the data write portion of a write access is done regardless of previous writes, and that only the tag latency is important for the critical path latency calculation. Change-Id: I739132a2deab6eb4c46d084f4ee6dd65177873fd Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20068 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
2019-09-30mem-ruby: Remove inexistent functions from UtilDaniel R. Carvalho
Remove forward declaration of inexistent functions from RubySlicc_Util.sm. Change-Id: I548bd75cb570371fbdaccf914c5eb9a7b92313d1 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21086 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-09-30mem-ruby: Make bitSelect use bits<Addr>Daniel R. Carvalho
There is no need to replicate bits<Addr>' functionality. As a side effect, ADDRESS_WIDTH is no longer used and was removed Change-Id: Ia5679f3976c81f779665d82cb758850092f2a293 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21085 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-09-30mem-ruby: Fix maskLowOrderBitsDaniel R. Carvalho
The function was wrong when number = 63. Also, use the more reliable src/base/bitfield.hh's mbits when posible. maskLowOrderBits has only been kept because SLICC does not accept a templated function. Change-Id: I8dd680da02ceb9e614e2f9cbf8f1ac52cead8d45 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21084 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-09-30mem-ruby: Remove shiftLowOrderBitsDaniel R. Carvalho
There is no need to encapsulate a shift operation. Change-Id: Ie711d8d4975d1d9dde656cc2284a048410cfdadb Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21083 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-09-30mem-ruby: Remove maskHighOrderBitsDaniel R. Carvalho
Function was not being used. If needed, src/base/bitfield.hh's mbits can be used instead: maskHighOrderBits(addr, pos) == mbits<Addr>(addr, 64-pos, 0) Change-Id: I3abd041f8d256ec157ba7502182d8588721c2a05 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21082 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-09-30mem-ruby: Remove bitRemoveDaniel R. Carvalho
bitRemove is not being used anywhere. If needed, can be used as src/base/bitfield.hh's bits: bitRemove(addr, small, big) == ((bits<Addr>(addr, 63, big + 1) << small) | bits<Addr>(addr, small, 0)) Change-Id: I45fd3bc0271ccb659d6a94e3dd00ca095dfd6aa7 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21081 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Anthony Gutierrez <anthony.gutierrez@amd.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-09-30mem: Use new-style stats in the XBar modelsAndreas Sandberg
Migrate to new-world stats with an explicit hierarchy in all of the XBar models. Change-Id: I18b6746a1303ca415638e6d382fb4757607f1123 Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21141 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br> Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
2019-09-30mem-cache: Switch to new-style statsAndreas Sandberg
This change puts cache and tag stats into a Stats::Group struct. This makes it easier to identify stat updates (they are prefixed with stat.) and adds hierarchy information for output formats that need it. Change-Id: I2b8e9138f1cb977abb445ec864d80a79b588481d Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21140 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-09-30mem: Convert DRAM controller to new-style statsAndreas Sandberg
Note that this changes the stat format used by the DRAM controller. Previously, it would have a structure looking a bit like this: - system - dram: Main DRAM controller - dram_0: Rank 0 - dram_1: Rank 1 This structure can't be replicated with new-world stats since stats are confined to the SimObject name space. This means that the new structure looks like this: - system - dram: Main DRAM controller - rank0: Rank 0 - rank1: Rank 1 Change-Id: I7435cfaf137c94b0c18de619d816362dd0da8125 Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21142 Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br> Reviewed-by: Wendy Elsasser <wendy.elsasser@arm.com>
2019-09-28ruby: 2x protocols has typo/syntax error that fails buildingTimothy Hayes
MOESI_hammer and MOESI_CMP_token contain incorrect lines. Change-Id: I1f9ac429d0f4dcb0241f21c8c9b831bee7aa37a4 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21259 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-09-25mem-ruby: prevent cacheProbe being called multiple timesJing Qu
The cacheProbe() function will return the victim entry, and it gets called for multiple times in trigger function in a single miss. This will cause a problem when we try to add a new replacement policy to the Ruby system. Certain policy, like RRIP, will modify the block information every time the getVictim() function gets called. To prevent future problems, we need to store the victim entry, so that we only call it once in one miss. Change-Id: Ic5ca05f789d9bbfb963b8e993ef707020f243702 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/21099 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Pouya Fotouhi <pfotouhi@ucdavis.edu> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-09-23cpu, mem: Changing AtomicOpFunctor* for unique_ptr<AtomicOpFunctor>Jordi Vaquero
This change is based on modify the way we move the AtomicOpFunctor* through gem5 in order to mantain proper ownership of the object and ensuring its destruction when it is no longer used. Doing that we fix at the same time a memory leak in Request.hh where we were assigning a new AtomicOpFunctor* without destroying the previous one. This change creates a new type AtomicOpFunctor_ptr as a std::unique_ptr<AtomicOpFunctor> and move its ownership as needed. Except for its only usage when AtomicOpFunc() is called. Change-Id: Ic516f9d8217cb1ae1f0a19500e5da0336da9fd4f Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20919 Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Andreas Sandberg <andreas.sandberg@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-09-21mem: Delete the now unused Message*Port classes.Gabe Black
This port type is no longer used. Change-Id: If4abbb774819644bea58fd82e00dfdec8f79b5a6 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20822 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Gabe Black <gabeblack@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Gabe Black <gabeblack@google.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2019-09-12mem-cache: Fix BDI size calculationDaniel R. Carvalho
The bitmask field indicates to which base a delta refers, and in the original paper it is fixed and proportional to the highest number of bases allowed in the compressed data. Change-Id: I271bf2e19e0765de52b933eaf6d4fcc2ce25d185 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/19748 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-09-10mem-ruby: Move Bloom Filters to baseDaniel R. Carvalho
All Bloom Filters are completely independent of Ruby, and therefore can be used everywhere. As a side effect, Ruby was not using the filters, so their dependency was removed. Change-Id: Ic5f430610c33c0791fb81c79101ebe737189497e Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18875 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com>
2019-09-10mem: Mark MemObject as deprecated.Gabe Black
It's constructor will now warn that it's deprecated and suggest using ClockedObject directly. This change also gets rid of the params() method and the Params typedef since they are functionally equivalent to the ClockedObject versions. It also removes the include of mem/port.hh which is not used in mem_object.hh. This may break code which purposefully or (more likely) accidentally depended on that transitive include from mem_object.hh. Change-Id: I6dab3ba626e3f3ab6a6bd86edcf4f5cb4d6d2c45 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20720 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Gabe Black <gabeblack@google.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-09-03ruby: Fix the way stall map size is checked for availabilitySrikant Bharadwaj
To ensure that enqueuer observes the practical availability. We check the message buffer queue size at the start of the cycle. We also add the size of the stall queue to consider the total queue size. However, messages can be moved from regular queue to stall map. This leads to messages being considered twice leading to false flow control. This patch fixes it by storing the stall map size at the beginning of the cycle and considering it for checking availability. Change-Id: I6ea94f34fe5279b91f74e106d43263e55ec4bf06 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20389 Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
2019-08-29mem-cache: Use SatCounter for RRPVDaniel R. Carvalho
Use SatCounter in RRIP's RRPV. As such, move validation functionality to a proper variable. Change-Id: I142db2b7f6cd518ac3a2b68c9ed48005402b3464 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20452 Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Maintainer: Jason Lowe-Power <jason@lowepower.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-08-29mem: Convert CommMonitor to the new stat frameworkAndreas Sandberg
Change-Id: I851c29909f3e6923c0233505a4d0f2d266bc254f Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/19371 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Daniel Carvalho <odanrc@yahoo.com.br> Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
2019-08-28mem-ruby: Define BloomFilter namespaceDaniel R. Carvalho
Define a BloomFilter namespace and put all BloomFilter related code in it. As a side effect the BloomFilter classes have been renamed to remove the "BloomFilter" suffix. Change-Id: I3ee8cc225bf3b820e561c3e25a6bf38e0012e3a8 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18874 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-08-28mem-ruby: Make H3 inherit from MultiBitSelBloomFilterDaniel R. Carvalho
Make MultiBitSelBloomFilter a generic BloomFilter that maps multiple entries to an address, and therefore uses multiple hash functions. This allows the common functionality of both filters to be merged into one, since they only differ in the hash functions being used. Change-Id: I0984067b710a208715f5f2727b8c4312feb6529b Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18873 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-08-28mem-ruby: Finish implementing BloomFilter mergeDaniel R. Carvalho
Not all Bloom Filters had their union functionality implemented. This change adds them. Change-Id: I86af18d3c5eabd0da8280b57a88789b3af803c04 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18872 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
2019-08-28mem-ruby: Remove NonCountingBloomFilterDaniel R. Carvalho
Make BlockBloomFilter accept having a single bitfield, in which case it behaves exactly as the NonCountingBloomFilter, and thus the latter can be removed. Change-Id: I56d96a89290c933293ce434bbe0e8bcd4bbcaa42 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18871 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-08-28mem-ruby: Make MultiGrainBloomFilter genericDaniel R. Carvalho
Allow combining any number of Bloom Filters in the MultiGrain. Change-Id: I73ae33063e1feed731af6f625d2f64245f21df18 Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18869 Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-08-28mem-ruby: Parameterize xor bits in BlockBloomFilterDaniel R. Carvalho
Parameterize bitfield ranges in BlockBloomFilter such that the hash is applied between masked bitfields of an address. Change-Id: I008bd873458e9815e98530e308491adb65bb34cb Signed-off-by: Daniel R. Carvalho <odanrc@yahoo.com.br> Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/18870 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Nikos Nikoleris <nikos.nikoleris@arm.com>
2019-08-28cpu, mem: Add new getSendFunctional method to the base CPU.Gabe Black
This returns a sendFunctional delegate references which can be used to send functional accesses directly, or more likely when constructing a PortProxy subclass. In those cases only the functional capabilities of those ports are needed so there's no reason to require a full port which supports all three protocols. Also, this removes the last remaining use of get(Data|Inst)Port which relies on those returning a port which supports the gem5 protocols, except the default implementations of this new function. If a CPU doesn't have traditional gem5 style ports, it can override this function to do whatever other behavior is necessary and return its real ports through get(Data|Inst)Port. Change-Id: Ide4da81e3bc679662cd85902ba6bd537cce54a53 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20237 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-08-28mem: Make PortProxy use a delegate for a sendFunctional function.Gabe Black
The only part of the MaserPort the PortProxy uses is the sendFunctional function which is part of the functional protocol. Rather than require a MasterPort which comes along with a lot of other mechanisms, this change slightly adjusts the PortProxy to only require that function through the use of a delegate. That allows lots of flexibility in how the actual packet gets sent and what sends it. In cases where code constructs a PortProxy and passes its constructor an unbound MasterPort, the PortProxy will create a delegate to the sendFunctional method on its own. This should also make it easier for objects which don't have traditional gem5 style ports, for instance systemc models, to implement just the little bit of the protocol they need, rather than having to stub out a whole port class, most of which will be ignored. Change-Id: I234b42ce050f12313b551a61736186ddf2c9e2c7 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20229 Maintainer: Gabe Black <gabeblack@google.com> Reviewed-by: Gabe Black <gabeblack@google.com> Tested-by: kokoro <noreply+kokoro@google.com>
2019-08-28mem: Eliminate the Base(Slave|Master)Port classes.Gabe Black
The Port class has assumed all the duties of the less generic Base*Port classes, making them unnecessary. Since they don't add anything but make the code more complex, this change eliminates them. Change-Id: Ibb9c56def04465f353362595c1f1c5ac5083e5e9 Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20236 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Maintainer: Gabe Black <gabeblack@google.com>
2019-08-27cpu, dev, mem: Use the new Port methods.Gabe Black
Use getPeer, takeOverFrom, and << to simplify the use of ports in some areas. Change-Id: Idfbda27411b5d6b742f5e4927894302ea6d6a53d Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20235 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com> Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
2019-08-27mem, sim, systemc: Reorganize Port and co.s bind, unbind slightly.Gabe Black
The base Port class can keep track of its peer, and also whether it's connected. This is partially delegated away from the port subclasses which still keep track of a cast version of their peer pointer for their own conveneince, so that it can be used by generic code. Even with the Port mechanism's new flexibility, each port still has exactly one peer and is either connected or not based on whether there is a peer currently. Change-Id: Id3228617dd1604d196814254a1aadeac5ade7cde Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/20232 Tested-by: kokoro <noreply+kokoro@google.com> Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com> Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com> Maintainer: Gabe Black <gabeblack@google.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-28 03:38:22 +0000