summaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Collapse)Author
2011-08-19ARM: Fix a memory leak with the table walker.Ali Saidi
2011-08-19Prefetcher: Fix some memory leaks with the prefetcher.Ali Saidi
2011-08-19ARM: quiet what can be a very noise CLCD controller.Ali Saidi
2011-08-16InOrder: Make cache_unit.hh include hashmap.hh explicitly, not transitively.Gabe Black
2011-08-16O3: Make lsq_unit.hh include arch/isa_traits.hh directly, not transitively.Gabe Black
2011-08-15Ruby: Initialize some variables.Nilay Vaish
2011-08-14O3: When squashing, restore the macroop that should be used for fetching.Gabe Black
2011-08-14O3: Add a pointer to the macroop for a microop in the dyninst.Gabe Black
2011-08-13X86: Use IsSquashAfter if an instruction could affect fetch translation.Gabe Black
Control register operands are set up so that writing to them is serialize after, serialize before, and non-speculative. These are probably overboard, but they should usually be safe. Unfortunately there are times when even these aren't enough. If an instruction modifies state that affects fetch, later serialized instructions which come after it might have already gone through fetch and decode by the time it commits. These instructions may have been translated incorrectly or interpretted incorrectly and need to be destroyed. This change modifies instructions which will or may have this behavior so that they use the IsSquashAfter flag when necessary.
2011-08-13O3: At the end of an instruction, force fetchAddr to something sensible.Gabe Black
It's possible (though until now very unlikely) for fetchAddr to get out of sync with the actual PC of the current instruction. This change forcefull resets fetchAddr at the end of every instruction.
2011-08-09O3: Stop using the current macroop no matter why you're leaving it.Gabe Black
Until now, the only reason a macroop would be left was because it ended at a microop marked as the last microop. In O3 with branch prediction, it's possible for the branch predictor to have entries which originally came from different instructions which happened to have the same RIP. This could theoretically happen in many ways, but it was encountered specifically when different programs in different address spaces ran one after the other in X86_FS. What would happen in that case was that the macroop would continue to be looped over and microops fetched from it until it reached the last microop even though the macropc had moved out from under it. If things lined up properly, this could mean that the end bytes of an instruction actually fell into the instruction sized block of memory after the one in the predecoder. The fetch loop implicitly assumes that the last instruction sized chunk of memory processed was the last one needed for the instruction it just finished executing. It would then tell the predecoder to move to an offset within the bytes it was given that is larger than those bytes, and that would trip an assert in the x86 predecoder. This change fixes this problem by making fetch stop processing the current macroop if the address it should be fetching from changed when the PC is updated. That happens when the last microop was reached because the instruction handled it properly, and it also catches the case where the branch predictor makes fetch do a macro level branch when it shouldn't. The check of isLastMicroop is retained because otherwise, a macroop that branches back to itself would act like a single, long macroop instead of multiple instances of the same microop. There may be situations (which may turn out to be purely hypothetical) where that matters. This also fixes a relatively minor issue where the curMacroop variable would be set to NULL immediately after seeing that a microop was the last one before curMacroop was used to build the dyninst. The traceData structure would have a NULL pointer to the macroop for that microop.
2011-08-09O3: When waiting to handle an interrupt, let everything drain out.Gabe Black
Before this change, the commit stage would wait until the ROB and store queue were empty before recognizing an interrupt. The fetch stage would stop generating instructions at an appropriate point, so commit would then wait until a valid time to interrupt the instruction stream. Instructions might be in flight after fetch but not the in the ROB or store queue (in rename, for instance), so this change makes commit wait until all in flight instructions are finished.
2011-08-08BuildEnv: Eliminate RUBY as build environment variableNilay Vaish
This patch replaces RUBY with PROTOCOL in all the SConscript files as the environment variable that decides whether or not certain components of the simulator are compiled.
2011-08-07O3: Get rid of the unused addToRemoveList function.Gabe Black
2011-08-07O3: Let squashed and deferred instructions issue.Gabe Black
Let squahsed and deferred instructions issue so they don't accumulate and clog up the CPU.
2011-08-07O3: Fix uninitialized variable in the tournament branch predictor.Ali Saidi
2011-08-07Translation: Use a pointer type as the template argument.Gabe Black
This allows regular pointers and reference counted pointers without having to use any shim structures or other tricks.
2011-08-03Ruby: Remove files and includes not in useNilay Vaish
2011-08-02O3: Get rid of the raw ExtMachInst constructor on DynInsts.Gabe Black
This constructor assumes that the ExtMachInst can be decoded directly into a StaticInst that's useful to execute. With the advent of microcoded instructions that's no longer true.
2011-08-02Scons: Make some Action objects fit the abreviated output format.Gabe Black
2011-08-02Scons: Drop RUBY as compile time option.Nilay Vaish
This patch drops RUBY as a compile time option. Instead the PROTOCOL option is used to figure out whether or not to build Ruby. If the specified protocol is 'None', then Ruby is not compiled.
2011-07-31O3: Implement memory mapped IPRs for O3.Gabe Black
2011-07-30O3: Fix corner case squashing into the microcode ROM.Gabe Black
When fetching from the microcode ROM, if the PC is set so that it isn't in the cache block that's been fetched the CPU will get stuck. The fetch stage notices that it's in the ROM so it doesn't try to fetch from the current PC. It then later notices that it's outside of the current cache block so it skips generating instructions expecting to continue once the right bytes have been fetched. This change lets the fetch stage attempt to generate instructions, and only checks if the bytes it's going to use are valid if it's really going to use them.
2011-07-27SLICC: Put functions of a controller in its .cc fileNilay Vaish
Currently, functions associated with a controller go into separate files. This patch puts all the functions in the controller's .cc file. This should hopefully take away some time from compilation.
2011-07-15Mem: Fix issue with prefetches originating at non-L1 caches getting stale dataAli Saidi
Prefetch requests issued from the L2 or below wouldn't check if valid data is present higher in the system. If a prefetch into the L2 occured at the same time as writeback from a higher-level cache the dirty data could be replaced in by unmodified data in memory.
2011-07-15O3: Create a pipeline activity viewer for the O3 CPU model.Giacomo Gabrielli
Implemented a pipeline activity viewer as a python script (util/o3-pipeview.py) and modified O3 code base to support an extra trace flag (O3PipeView) for generating traces to be used as inputs by the tool.
2011-07-15ARM: Fix SWP/SWPB undefined instruction behaviorWade Walker
SWP and SWPB now throw an undefined instruction exception if SCTLR.SW == 0. This also required the MIDR to be changed slightly so programs can correctly determine that gem5 supports the ARM v7 behavior of SWP/SWPB (in ARM v6, SWP/SWPB were deprecated, but not disabled at CPU startup).
2011-07-15ARM: Add two unimplemented miscellaneous registers.Wade Walker
Adds MISCREG_ID_MMFR2 and removes break on access to MISCREG_CLIDR. Both registers now return values that are consistent with current ARM implementations.
2011-07-11X86: implements copyRegs() functionNilay Vaish
This patch implements the copyRegs() function for the x86 architecture. The patch assumes that no side effects other than TLB invalidation need to be considered while copying the registers. This may not hold true in future.
2011-07-11ISA: Get rid of the unused mem_acc_type template parameter.Gabe Black
2011-07-10Branch predictor: Fixes the tournament branch predictor.Mrinmoy Ghosh
Branch predictor could not predict a branch in a nested loop because: 1. The global history was not updated after a mispredict squash. 2. The global history was updated in the fetch stage. The choice predictors that were updated used the changed global history. This is incorrect, as it incorporates the state of global history after the branch in encountered. Fixed update to choice predictor using the global history state before the branch happened. 3. The global predictor table was also updated using the global history state before the branch happened as above. Additionally, parameters to initialize ctr and history size were reversed.
2011-07-10O3: Fix up pipelining icache accesses in fetch stage to function properlyGeoffrey Blake
Fixed up the patch from Yasuko Watanabe that enabled pipelining of fetch accessess to icache to work with recent changes to main repository. Also added in ability for fetch stage to delay issuing the fault carrying nop when a pipeline fetch causes a fault and no fetch bandwidth is available until the next cycle.
2011-07-10IO: Handle case where ISA Fake device is being used as a fake memory.Ali Saidi
2011-07-10O3: Make sure fetch doesn't go off into the weeds during speculation.Ali Saidi
2011-07-10Config: Add support for a Self.all proxy objectAli Saidi
2011-07-10ARM: Fix mp interrupt bug in GIC.Daniel Johnson
Missing "!" made multiprocessor interrupts operate incorrectly.
2011-07-07alpha:hwrei:rollback for o3Korey Sewell
change hwrei back to being a non-control instruction so O3-FS mode will work add squash in inorder that will catch a hwrei (or any other genric instruction) that isnt a control inst but changes the PC. Additional testing still needs to be done for inorder-FS mode but this change will free O3 development back up in the interim
2011-07-06ruby: added generic dma machineBrad Beckmann
2011-07-06MOESI_hammer: Fixed uniprocessor DMA bugBrad Beckmann
2011-07-05slicc: add a protocol statement and an include statementNathan Binkert
All protocols must specify their name The include statement allows any file to include another file.
2011-07-05slicc: cleanup slicc code and make it less verboseNathan Binkert
2011-07-05grammar: better encapsulation of a grammar and parsingNathan Binkert
This makes it possible to use the grammar multiple times and use the multiple instances concurrently. This makes implementing an include statement as part of a grammar possible.
2011-07-05ISAs: Streamline some spots where Mem is used in the ISA descriptions.Gabe Black
2011-07-05ISA parser: Define operand types with a ctype directly.Gabe Black
2011-07-05ISA parser: Simplify operand type handling.Gabe Black
This change simplifies the code surrounding operand type handling and makes it depend only on the ctype that goes with each operand type. Future changes will allow defining operand types by their ctypes directly, convert the ISAs over to that style of definition, and then remove support for the old style. These changes are to make it easier to use non-builtin types like classes or structures as the type for operands.
2011-07-03Merged with Gabe's recent changes.Nilay Vaish
2011-07-03Network_test: Conform it with functional access changes in RubyNilay Vaish
Addition of functional access support to Ruby necessitated some changes to the way coherence protocols are written. I had forgotten to update the Network_test protocol. This patch makes those updates.
2011-07-02ExecContext: Rename the readBytes/writeBytes functions to readMem and writeMem.Gabe Black
readBytes and writeBytes had the word "bytes" in their names because they accessed blobs of bytes. This distinguished them from the read and write functions which handled higher level data types. Because those functions don't exist any more, this change renames readBytes and writeBytes to more general names, readMem and writeMem, which reflect the fact that they are how you read and write memory. This also makes their names more consistent with the register reading/writing functions, although those are still read and set for some reason.
2011-07-02ExecContext: Get rid of the now unused read/write templated functions.Gabe Black
2011-07-02ISA: Use readBytes/writeBytes for all instruction level memory operations.Gabe Black