summaryrefslogtreecommitdiff
path: root/src/mem/SConscript
AgeCommit message (Collapse)Author
2014-02-18mem: Add a wrapped DRAMSim2 memory controllerAndreas Hansson
This patch adds DRAMSim2 as a memory controller by wrapping the external library and creating a sublass of AbstractMemory that bridges between the semantics of gem5 and the DRAMSim2 interface. The DRAMSim2 wrapper extracts the clock period from the config file. There is no way of extracting this information from DRAMSim2 itself, so we simply read the same config file and get it from there. To properly model the response queue, the wrapper keeps track of how many transactions are in the actual controller, and how many are stacking up waiting to be sent back as responses (in the wrapper). The latter requires us to move away from the queued port and manage the packets ourselves. This is due to DRAMSim2 not having any flow control on the response path. DRAMSim2 assumes that the transactions it is given are matching the burst size of the choosen memory. The wrapper checks to ensure the cache line size of the system matches the burst size of DRAMSim2 as there are currently no provisions to split the system requests. In theory we could allow a cache line size smaller than the burst size, but that would lead to inefficient use of the DRAM, so for not we fatal also in this case.
2013-11-01mem: Use the same timing calculation for DRAM read and writeAni Udipi
This patch simplifies the DRAM model by re-using the function that computes the busy and access time for both reads and writes.
2013-09-04arch: Resurrect the NOISA build target and rename it NULLAndreas Hansson
This patch makes it possible to once again build gem5 without any ISA. The main purpose is to enable work around the interconnect and memory system without having to build any CPU models or device models. The regress script is updated to include the NULL ISA target. Currently no regressions make use of it, but all the testers could (and perhaps should) transition to it. --HG-- rename : build_opts/NOISA => build_opts/NULL rename : src/arch/noisa/SConsopts => src/arch/null/SConsopts rename : src/arch/noisa/cpu_dummy.hh => src/arch/null/cpu_dummy.hh rename : src/cpu/intr_control.cc => src/cpu/intr_control_noisa.cc
2013-01-07mem: Add tracing support in the communication monitorAndreas Hansson
This patch adds packet tracing to the communication monitor using a protobuf as the mechanism for creating the trace. If no file is specified, then the tracing is disabled. If a file is specified, then for every packet that is successfully sent, a protobuf message is serialized to the file.
2012-12-11ruby: add a prefetcherNilay Vaish
This patch adds a prefetcher for the ruby memory system. The prefetcher is based on a prefetcher implemented by others (well, I don't know who wrote the original). The prefetcher does stride-based prefetching, both unit and non-unit. It obseves the misses in the cache and trains on these. After the training period is over, the prefetcher starts issuing prefetch requests to the controller.
2012-09-25mem: Add a gasket that allows memory ranges to be re-mapped.Ali Saidi
For example if DRAM is at two locations and mirrored this patch allows the mirroring to occur.
2012-09-21DRAM: Introduce SimpleDRAM to capture a high-level controllerAndreas Hansson
This patch introduces a high-level model of a DRAM controller, with a basic read/write buffer structure, a selectable and customisable arbiter, a few address mapping options, and the basic DRAM timing constraints. The parameters make it possible to turn this model into any desired DDRx/LPDDRx/WideIOx memory controller. The intention is not to be cycle accurate or capture every aspect of a DDR DRAM interface, but rather to enable exploring of the high-level knobs with a good simulation speed. Thus, contrary to e.g. DRAMSim this module emphasizes simulation speed with a good-enough accuracy. This module is merely a starting point, and there are plenty additions and improvements to come. A notable addition is the support for address-striping in the bus to enable a multi-channel DRAM controller. Also note that there are still a few "todo's" in the code base that will be addressed as we go along. A follow-up patch will add basic performance regressions that use the traffic generator to exercise a few well-defined corner cases.
2012-08-22Bridge: Remove NACKs in the bridge and unify with packet queueAndreas Hansson
This patch removes the NACKing in the bridge, as the split request/response busses now ensure that protocol deadlocks do not occur, i.e. the message-dependency chain is broken by always allowing responses to make progress without being stalled by requests. The NACKs had limited support in the system with most components ignoring their use (with a suitable call to panic), and as the NACKs are no longer needed to avoid protocol deadlocks, the cleanest way is to simply remove them. The bridge is the starting point as this is the only place where the NACKs are created. A follow-up patch will remove the code that deals with NACKs in the endpoints, e.g. the X86 table walker and DMA port. Ultimately the type of packet can be complete removed (until someone sees a need for modelling more complex protocols, which can now be done in parts of the system since the port and interface is split). As a consequence of the NACK removal, the bridge now has to send a retry to a master if the request or response queue was full on the first attempt. This change also makes the bridge ports very similar to QueuedPorts, and a later patch will change the bridge to use these. A first step in this direction is taken by aligning the name of the member functions, as done by this patch. A bit of tidying up has also been done as part of the simplifications. Surprisingly, this patch has no impact on any of the regressions. Hence, there was never any NACKs issued. In a follow-up patch I would suggest changing the size of the bridge buffers set in FSConfig.py to also test the situation where the bridge fills up.
2012-07-10ruby: banked cache array resource modelBrad Beckmann
This patch models a cache as separate tag and data arrays. The patch exposes the banked array as another resource that is checked by SLICC before a transition is allowed to execute. This is similar to how TBE entries and slots in output ports are modeled.
2012-07-10ruby: tag and data cache access supportJoel Hestness
Updates to Ruby to support statistics counting of cache accesses. This feature serves multiple purposes beyond simple stats collection. It provides the foundation for ruby to model the cache tag and data arrays as physical resources, as well as provide the necessary input data for McPAT power modeling.
2012-05-31Bus: Split the bus into a non-coherent and coherent busAndreas Hansson
This patch introduces a class hierarchy of buses, a non-coherent one, and a coherent one, splitting the existing bus functionality. By doing so it also enables further specialisation of the two types of buses. A non-coherent bus connects a number of non-snooping masters and slaves, and routes the request and response packets based on the address. The request packets issued by the master connected to a non-coherent bus could still snoop in caches attached to a coherent bus, as is the case with the I/O bus and memory bus in most system configurations. No snoops will, however, reach any master on the non-coherent bus itself. The non-coherent bus can be used as a template for modelling PCI, PCIe, and non-coherent AMBA and OCP buses, and is typically used for the I/O buses. A coherent bus connects a number of (potentially) snooping masters and slaves, and routes the request and response packets based on the address, and also forwards all requests to the snoopers and deals with the snoop responses. The coherent bus can be used as a template for modelling QPI, HyperTransport, ACE and coherent OCP buses, and is typically used for the L1-to-L2 buses and as the main system interconnect. The configuration scripts are updated to use a NoncoherentBus for all peripheral and I/O buses. A bit of minor tidying up has also been done. --HG-- rename : src/mem/bus.cc => src/mem/coherent_bus.cc rename : src/mem/bus.hh => src/mem/coherent_bus.hh rename : src/mem/bus.cc => src/mem/noncoherent_bus.cc rename : src/mem/bus.hh => src/mem/noncoherent_bus.hh
2012-05-09MEM: Add the communication monitorAndreas Hansson
This patch adds a communication monitor MemObject that can be inserted between a master and slave port to provide a range of statistics about the communication passing through it. The communication monitor is non-invasive and does not change any properties or timing of the packets, with the exception of adding a sender state to be able to track latency. The statistics are only collected in timing mode (not atomic) to avoid slowing down any fast forwarding. An example of the statistics captured by the monitor are: read/write burst lengths, bandwidth, request-response latency, outstanding transactions, inter transaction time, transaction count, and address distribution. The monitor can be used in combination with periodic resetting and dumping of stats (through schedStatEvent) to study the behaviour over time. In future patches, a selection of convenience scripts will be added to aid in visualising the statistics collected by the monitor.
2012-04-06MEM: Enable multiple distributed generalized memoriesAndreas Hansson
This patch removes the assumption on having on single instance of PhysicalMemory, and enables a distributed memory where the individual memories in the system are each responsible for a single contiguous address range. All memories inherit from an AbstractMemory that encompasses the basic behaviuor of a random access memory, and provides untimed access methods. What was previously called PhysicalMemory is now SimpleMemory, and a subclass of AbstractMemory. All future types of memory controllers should inherit from AbstractMemory. To enable e.g. the atomic CPU and RubyPort to access the now distributed memory, the system has a wrapper class, called PhysicalMemory that is aware of all the memories in the system and their associated address ranges. This class thus acts as an infinitely-fast bus and performs address decoding for these "shortcut" accesses. Each memory can specify that it should not be part of the global address map (used e.g. by the functional memories by some testers). Moreover, each memory can be configured to be reported to the OS configuration table, useful for populating ATAG structures, and any potential ACPI tables. Checkpointing support currently assumes that all memories have the same size and organisation when creating and resuming from the checkpoint. A future patch will enable a more flexible re-organisation. --HG-- rename : src/mem/PhysicalMemory.py => src/mem/AbstractMemory.py rename : src/mem/PhysicalMemory.py => src/mem/SimpleMemory.py rename : src/mem/physical.cc => src/mem/abstract_mem.cc rename : src/mem/physical.hh => src/mem/abstract_mem.hh rename : src/mem/physical.cc => src/mem/simple_mem.cc rename : src/mem/physical.hh => src/mem/simple_mem.hh
2012-03-30MEM: Remove legacy DRAM in preparation for memory updatesAndreas Hansson
This patch removes the DRAM memory class in preparation for updates to the memory system, with the first one introducing an abstract memory class, and removing the assumption of a single physical memory.
2012-03-22MEM: Split SimpleTimingPort into PacketQueue and portsAndreas Hansson
This patch decouples the queueing and the port interactions to simplify the introduction of the master and slave ports. By separating the queueing functionality from the port itself, it becomes much easier to distinguish between master and slave ports, and still retain the queueing ability for both (without code duplication). As part of the split into a PacketQueue and a port, there is now also a hierarchy of two port classes, QueuedPort and SimpleTimingPort. The QueuedPort is useful for ports that want to leave the packet transmission of outgoing packets to the queue and is used by both master and slave ports. The SimpleTimingPort inherits from the QueuedPort and adds the implemention of recvTiming and recvFunctional through recvAtomic. The PioPort and MessagePort are cleaned up as part of the changes. --HG-- rename : src/mem/tport.cc => src/mem/packet_queue.cc rename : src/mem/tport.hh => src/mem/packet_queue.hh
2012-02-24MEM: Move all read/write blob functions from Port to PortProxyAndreas Hansson
This patch moves the readBlob/writeBlob/memsetBlob from the Port class to the PortProxy class, thus making a clear separation of the basic port functionality (recv/send functional/atomic/timing), and the higher-level functional accessors available on the port proxies. There are only a few places in the code base where the blob functions were used on ports, and they are all for peeking into the memory system without making a normal memory access (in the memtest, and the malta and tsunami pchip). The memtest also exemplifies how easy it is to create a non-translating proxy if desired. The malta and tsunami pchip used a slave port to perform a functional read, and this is now changed to rely on the physProxy of the system (to which they already have a pointer).
2012-01-28Merge with the main repo.Gabe Black
--HG-- rename : src/mem/vport.hh => src/mem/fs_translating_port_proxy.hh rename : src/mem/translating_port.cc => src/mem/se_translating_port_proxy.cc rename : src/mem/translating_port.hh => src/mem/se_translating_port_proxy.hh
2012-01-16Merge yet again with the main repository.Gabe Black
2012-01-17MEM: Add port proxies instead of non-structural portsAndreas Hansson
Port proxies are used to replace non-structural ports, and thus enable all ports in the system to correspond to a structural entity. This has the advantage of accessing memory through the normal memory subsystem and thus allowing any constellation of distributed memories, address maps, etc. Most accesses are done through the "system port" that is used for loading binaries, debugging etc. For the entities that belong to the CPU, e.g. threads and thread contexts, they wrap the CPU data port in a port proxy. The following replacements are made: FunctionalPort > PortProxy TranslatingPort > SETranslatingPortProxy VirtualPort > FSTranslatingPortProxy --HG-- rename : src/mem/vport.cc => src/mem/fs_translating_port_proxy.cc rename : src/mem/vport.hh => src/mem/fs_translating_port_proxy.hh rename : src/mem/translating_port.cc => src/mem/se_translating_port_proxy.cc rename : src/mem/translating_port.hh => src/mem/se_translating_port_proxy.hh
2012-01-11Ruby Debug Flags: Remove one, add anotherNilay Vaish
The flag RubyStoreBuffer is being removed, instead RubySystem is being added
2012-01-11Ruby: Add infrastructure for recording cache contentsNilay Vaish
This patch changes CacheRecorder, CacheMemory, CacheControllers so that the contents of a cache can be recorded for checkpointing purposes.
2012-01-07Merge with main repository.Gabe Black
2011-11-14Ruby: Process packet instead of RubyRequest in SequencerNilay Vaish
This patch changes the implementation of Ruby's recvTiming() function so that it pushes a packet in to the Sequencer instead of a RubyRequest. This requires changes in the Sequencer's makeRequest() and issueRequest() functions, as they also need to operate on a Packet instead of RubyRequest.
2011-10-16SE/FS: Turn on the page table class in FS.Gabe Black
2011-10-16SE/FS: Build in the tport in FS mode.Gabe Black
2011-10-16SE/FS: Build/expose vport in SE mode.Gabe Black
2011-06-02scons: rename TraceFlags to DebugFlagsNathan Binkert
2011-03-19RubyPort: minor fixes to trace flag and dprintfsBrad Beckmann
2011-01-10ruby: get rid of ruby's Debug.hhNathan Binkert
Get rid of the Debug class Get rid of ASSERT and use assert Use DPRINTFR for ProtocolTrace
2010-12-01ruby: Converted old ruby debug calls to M5 debug callsNilay Vaish
This patch developed by Nilay Vaish converts all the old GEMS-style ruby debug calls to the appropriate M5 debug calls.
2010-11-19SCons: Support building without an ISAAli Saidi
2010-01-29ruby: Convert most Ruby objects to M5 SimObjects.Steve Reinhardt
The necessary companion conversion of Ruby objects generated by SLICC are converted to M5 SimObjects in the following patch, so this patch alone does not compile. Conversion of Garnet network models is also handled in a separate patch; that code is temporarily disabled from compiling to allow testing of interim code.
2009-11-18ruby: Support for merging ALPHA_FS and rubyBrad Beckmann
Connects M5 cpu and dma ports directly to ruby sequencers and dma sequencers. Rubymem also includes a pio port so that pio requests and be forwarded to a special pio bus connecting to device pio ports.
2009-05-11ruby: add RUBY sticky option that must be set to add ruby to the buildNathan Binkert
Default is false
2009-05-11ruby: Working M5 interface and updated Ruby interface.Daniel Sanchez
This changeset also includes a lot of work from Derek Hower <drh5@cs.wisc.edu> RubyMemory is now both a driver for Ruby and a port for M5. Changed makeRequest/hitCallback interface. Brought packets (superficially) into the sequencer. Modified tester infrastructure to be packet based. and Ruby can be used together through the example ruby_se.py script. SPARC parallel applications work, and the timing *seems* right from combined M5/Ruby debug traces. To run, % build/ALPHA_SE/m5.debug configs/example/ruby_se.py -c tests/test-progs/hello/bin/alpha/linux/hello -n 4 -t
2009-01-13SCons: centralize the Dir() workaround for newer versions of scons.Nathan Binkert
Scons bug id: 2006 M5 Bug id: 308
2008-10-12Create a message port for sending messages as apposed to reading/writing a ↵Gabe Black
memory range.
2008-04-10SCons: add comments to SConscript documenting bug workaroundAli Saidi
--HG-- extra : convert_revision : e6cdffe953d56b96c76c7ff14d2dcc3de3ccfcc3
2008-04-08SCons: Manually specifying header only directories with Dir() works around ↵Ali Saidi
the problem --HG-- extra : convert_revision : d9713228d934cf4a45114a972603b8bca2bd27d3
2007-10-31Traceflags: Add SCons function to created a traceflag instead of having one ↵Ali Saidi
file with them all. --HG-- extra : convert_revision : 427f6bd8f050861ace3bc0d354a1afa5fc8319e6
2007-05-27Move SimObject python files alongside the C++ and fixNathan Binkert
the SConscript files so that only the objects that are actually available in a given build are compiled in. Remove a bunch of files that aren't used anymore. --HG-- rename : src/python/m5/objects/AlphaTLB.py => src/arch/alpha/AlphaTLB.py rename : src/python/m5/objects/SparcTLB.py => src/arch/sparc/SparcTLB.py rename : src/python/m5/objects/BaseCPU.py => src/cpu/BaseCPU.py rename : src/python/m5/objects/FuncUnit.py => src/cpu/FuncUnit.py rename : src/python/m5/objects/IntrControl.py => src/cpu/IntrControl.py rename : src/python/m5/objects/MemTest.py => src/cpu/memtest/MemTest.py rename : src/python/m5/objects/FUPool.py => src/cpu/o3/FUPool.py rename : src/python/m5/objects/FuncUnitConfig.py => src/cpu/o3/FuncUnitConfig.py rename : src/python/m5/objects/O3CPU.py => src/cpu/o3/O3CPU.py rename : src/python/m5/objects/OzoneCPU.py => src/cpu/ozone/OzoneCPU.py rename : src/python/m5/objects/SimpleOzoneCPU.py => src/cpu/ozone/SimpleOzoneCPU.py rename : src/python/m5/objects/BadDevice.py => src/dev/BadDevice.py rename : src/python/m5/objects/Device.py => src/dev/Device.py rename : src/python/m5/objects/DiskImage.py => src/dev/DiskImage.py rename : src/python/m5/objects/Ethernet.py => src/dev/Ethernet.py rename : src/python/m5/objects/Ide.py => src/dev/Ide.py rename : src/python/m5/objects/Pci.py => src/dev/Pci.py rename : src/python/m5/objects/Platform.py => src/dev/Platform.py rename : src/python/m5/objects/SimConsole.py => src/dev/SimConsole.py rename : src/python/m5/objects/SimpleDisk.py => src/dev/SimpleDisk.py rename : src/python/m5/objects/Uart.py => src/dev/Uart.py rename : src/python/m5/objects/AlphaConsole.py => src/dev/alpha/AlphaConsole.py rename : src/python/m5/objects/Tsunami.py => src/dev/alpha/Tsunami.py rename : src/python/m5/objects/T1000.py => src/dev/sparc/T1000.py rename : src/python/m5/objects/Bridge.py => src/mem/Bridge.py rename : src/python/m5/objects/Bus.py => src/mem/Bus.py rename : src/python/m5/objects/MemObject.py => src/mem/MemObject.py rename : src/python/m5/objects/PhysicalMemory.py => src/mem/PhysicalMemory.py rename : src/python/m5/objects/BaseCache.py => src/mem/cache/BaseCache.py rename : src/python/m5/objects/CoherenceProtocol.py => src/mem/cache/coherence/CoherenceProtocol.py rename : src/python/m5/objects/Repl.py => src/mem/cache/tags/Repl.py rename : src/python/m5/objects/Process.py => src/sim/Process.py rename : src/python/m5/objects/Root.py => src/sim/Root.py rename : src/python/m5/objects/System.py => src/sim/System.py extra : convert_revision : 173f8764bafa8ef899198438fa5573874e407321
2007-03-10Rework the way SCons recurses into subdirectories, making itNathan Binkert
automatic. The point is that now a subdirectory can be added to the build process just by creating a SConscript file in it. The process has two passes. On the first pass, all subdirs of the root of the tree are searched for SConsopts files. These files contain any command line options that ought to be added for a particular subdirectory. On the second pass, all subdirs of the src directory are searched for SConscript files. These files describe how to build any given subdirectory. I have added a Source() function. Any file (relative to the directory in which the SConscript resides) passed to that function is added to the build. Clean up everything to take advantage of Source(). function is added to the list of files to be built. --HG-- extra : convert_revision : 103f6b490d2eb224436688c89cdc015211c4fd30