summaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Collapse)Author
2010-08-23ARM: We don't currently support ThumbEE exceptions, so don't report that we doAli Saidi
2010-08-23ARM: Change how the AMBA device ID checking is done to make it more genericAli Saidi
2010-08-23ARM: Add system for ARM/Linux and bootstrappingAli Saidi
2010-08-23ARM: Add I/O devices for booting linuxAli Saidi
--HG-- rename : src/dev/arm/Versatile.py => src/dev/arm/RealView.py rename : src/dev/arm/versatile.cc => src/dev/arm/realview.cc rename : src/dev/arm/versatile.hh => src/dev/arm/realview.hh
2010-08-23ARM: Implement some more misc registersAli Saidi
2010-08-23ARM: Fix an un-initialized variable bugAli Saidi
2010-08-23Loader: Use address mask provided to load*Symbols when loading the symbols ↵Ali Saidi
from the symbol table.
2010-08-23Loader: Make the load address mask be a parameter of the system rather than ↵Ali Saidi
a constant. This allows one two different OS requirements for the same ISA to be handled. Some OSes are compiled for a virtual address and need to be loaded into physical memory that starts at address 0, while other bare metal tools generate images that start at address 0.
2010-08-23ARM: Finish the timing translation when taking a fault.Min Kyu Jeong
2010-08-23ARM: Use a stl queue for the table walker stateDam Sunwoo
2010-08-23CPU: Set a default value when readBytes faults.Ali Saidi
This was being done in read(), but if readBytes was called directly it wouldn't happen. Also, instead of setting the memory blob being read to -1 which would (I believe) require using memset with -1 as a parameter, this now uses bzero. It's hoped that it's more specialized behavior will make it slightly faster.
2010-08-23Compiler: Fixes for GCC 4.5.Ali Saidi
2010-08-23BASE: Fix genrand to generate both 0s and 1s when max equals one.Ali Saidi
previously was only generating 0s.
2010-08-23stats: Fix off-by-one error in distributions.Ali Saidi
bkt size isn't evenly divisible by max-min and it would round down, it's possible to sample a distribution and have no place to put the sample. When this case occured the simulator would assert.
2010-08-22X86: Get rid of unused file arguments.hh.Gabe Black
2010-08-22SPARC: Fix some style issues in utility.hh.Gabe Black
2010-08-22X86: Get rid of the unused getAllocator on the python base microop class.Gabe Black
This function is always overridden, and doesn't actually have the right signature.
2010-08-20ruby: Added merge GETS optimization to hammerBrad Beckmann
Added an optimization that merges multiple pending GETS requests into a single request to the owner node.
2010-08-20ruby: Fixed minor bug in ruby test for setting the request typeBrad Beckmann
2010-08-20ruby: Stall and wait input messages instead of recyclingBrad Beckmann
This patch allows messages to be stalled in their input buffers and wait until a corresponding address changes state. In order to make this work, all in_ports must be ranked in order of dependence and those in_ports that may unblock an address, must wake up the stalled messages. Alot of this complexity is handled in slicc and the specification files simply annotate the in_ports. --HG-- rename : src/mem/slicc/ast/CheckAllocateStatementAST.py => src/mem/slicc/ast/StallAndWaitStatementAST.py rename : src/mem/slicc/ast/CheckAllocateStatementAST.py => src/mem/slicc/ast/WakeUpDependentsStatementAST.py
2010-08-20ruby: Recycle latency fix for hammerBrad Beckmann
Patch allows each individual message buffer to have different recycle latencies and allows the overall recycle latency to be specified at the cmd line. The patch also adds profiling info to make sure no one processor's requests are recycled too much.
2010-08-20MOESI_hammer: break down miss latency stalled cyclesBrad Beckmann
This patch tracks the number of cycles a transaction is delayed at different points of the request-forward-response loop.
2010-08-20ruby: added probe filter support to hammerBrad Beckmann
2010-08-20ruby: fixed DirectoryMemory's numa_high_bit configurationBrad Beckmann
This fix includes the off-by-one bit selection bug for numa mapping.
2010-08-20ruby: Reset ruby stats in RubySystem unserializeBrad Beckmann
The main purpose for clearing stats in the unserialize process is so that the profiler can correctly set its start time to the unserialized value of curTick.
2010-08-20ruby: Disable migratory sharing for token and hammerBrad Beckmann
This patch allows one to disable migratory sharing for those cache blocks that are accessed by atomic requests. While the implementations are different between the token and hammer protocols, the motivation is the same. For Alpha, LLSC semantics expect that normal loads do not unlock cache blocks that have been locked by LL accesses. Therefore, locked blocks should not transfer write permissions when responding to these load requests. Instead, only they only transfer read permissions so that the subsequent SC access can possibly succeed.
2010-08-20ruby: Added SC fail indication to trace profilingBrad Beckmann
2010-08-20devices: Fixed periodic interrupts to work with drainingBrad Beckmann
Added drain functions to the RTC and 8254 timer so that periodic interrupts stop when the system is draining. This patch is needed to checkpoint in timing mode. Otherwise under certain situations, the event queue will never be completely empty.
2010-08-20ruby: Fixed RubyPort sendTiming callbacksBrad Beckmann
Fixed RubyPort schedSendTiming calls to match ruby frequency.
2010-08-20ruby: fixed token bugs associated with owner token countsBrad Beckmann
This patch fixes several bugs related to previous inconsistent assumptions on how many tokens the Owner had. Mike Marty should have fixes these bugs years ago. :)
2010-08-20ruby: MOESI_CMP_token dma fixesBrad Beckmann
This patch fixes various protocol bugs regarding races between dma requests and persistent requests.
2010-08-20ruby: Resurrected Ruby's deterministic testsBrad Beckmann
Added the request series and invalidate deterministic tests as new cpu models and removed the no longer needed ruby tests --HG-- rename : configs/example/rubytest.py => configs/example/determ_test.py rename : src/mem/ruby/tester/DetermGETXGenerator.cc => src/cpu/directedtest/DirectedGenerator.cc rename : src/mem/ruby/tester/DetermGETXGenerator.hh => src/cpu/directedtest/DirectedGenerator.hh rename : src/mem/ruby/tester/DetermGETXGenerator.cc => src/cpu/directedtest/InvalidateGenerator.cc rename : src/mem/ruby/tester/DetermGETXGenerator.hh => src/cpu/directedtest/InvalidateGenerator.hh rename : src/cpu/rubytest/RubyTester.cc => src/cpu/directedtest/RubyDirectedTester.cc rename : src/cpu/rubytest/RubyTester.hh => src/cpu/directedtest/RubyDirectedTester.hh rename : src/mem/ruby/tester/DetermGETXGenerator.cc => src/cpu/directedtest/SeriesRequestGenerator.cc rename : src/mem/ruby/tester/DetermGETXGenerator.hh => src/cpu/directedtest/SeriesRequestGenerator.hh
2010-08-20ruby: Updated MOESI_hammer L2 latency behaviorBrad Beckmann
Previously, the MOESI_hammer protocol calculated the same latency for L1 and L2 hits. This was because the protocol was written using the old ruby assumption that L1 hits used the sequencer fast path. Since ruby no longer uses the fast-path, the protocol delays L2 hits by placing them on the trigger queue.
2010-08-20ruby: Reduced ruby latenciesBrad Beckmann
The previous slower ruby latencies created a mismatch between the faster M5 cpu models and the much slower ruby memory system. Specifically smp interrupts were much slower and infrequent, as well as cpus moving in and out of spin locks. The result was many cpus were idle for large periods of time. These changes fix the latency mismatch.
2010-08-20ruby: fix ruby llsc support to sync sc outcomesBrad Beckmann
Added support so that ruby can determine the outcome of store conditional operations and reflect that outcome to M5 physical memory and cpus.
2010-08-20ruby: Fixed L2 cache miss profilingBrad Beckmann
Fixed L2 cache miss profiling for the MOESI_CMP_token protocol
2010-08-20ruby: Added bcast msg profiling to hammer and tokenBrad Beckmann
2010-08-20ruby: Added consolidated network msg statsBrad Beckmann
2010-08-20ruby: Reincarnated the responding machine profilingBrad Beckmann
This patch adds back to ruby the capability to understand the response time for messages that hit in different levels of the cache heirarchy. Specifically add support for the MI_example, MOESI_hammer, and MOESI_CMP_token protocols.
2010-08-20MOESI_CMP_token: Fixed dma persistent lockdown bugsBrad Beckmann
2010-08-20memtest: Memtester support for DMABrad Beckmann
This patch adds DMA testing to the Memtester and is inherits many changes from Polina's old tester_dma_extension patch. Since Ruby does not work in atomic mode, the atomic mode options are removed.
2010-08-20ruby: Added ruby_request_type ostream def to libruby.hhBrad Beckmann
2010-08-20slicc: Consolidated the protocol stats printingBrad Beckmann
Created a separate ProfileDumper that consolidates the generated stats for each controller of a certain type.
2010-08-20config: Added the topology description to m5 config.iniBrad Beckmann
2010-08-20ruby: Fixed printout when Sequencer detects a deadlockBrad Beckmann
2010-08-20MESI_CMP_directory: bug fix for old PUTX requestsBrad Beckmann
2010-08-17misc: add some AMD copyright noticesSteve Reinhardt
Meant to add these with the previous batch of csets.
2010-08-17x86: minor checkpointing bug fixesSteve Reinhardt
2010-08-17sim: revamp unserialization procedureSteve Reinhardt
Replace direct call to unserialize() on each SimObject with a pair of calls for better control over initialization in both ckpt and non-ckpt cases. If restoring from a checkpoint, loadState(ckpt) is called on each SimObject. The default implementation simply calls unserialize() if there is a corresponding checkpoint section, so we get backward compatibility for existing objects. However, objects can override loadState() to get other behaviors, e.g., doing other programmed initializations after unserialize(), or complaining if no checkpoint section is found. (Note that the default warning for a missing checkpoint section is now gone.) If not restoring from a checkpoint, we call the new initState() method on each SimObject instead. This provides a hook for state initializations that are only required when *not* restoring from a checkpoint. Given this new framework, do some cleanup of LiveProcess subclasses and X86System, which were (in some cases) emulating initState() behavior in startup via a local flag or (in other cases) erroneously doing initializations in startup() that clobbered state loaded earlier by unserialize().
2010-08-17sim: fold checkpoint restore code into instantiate()Steve Reinhardt
The separate restoreCheckpoint() call is gone; just pass the checkpoint dir as an optional arg to instantiate(). This change is a precursor to some more extensive reworking of the startup code.