summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2009-07-27Statetrace: Fix up headers.Gabe Black
2009-07-27ARM: Implement a basic version of the fmxr instruction.Gabe Black
2009-07-27ARM: Implement a basic version of the fmrx instruction.Gabe Black
2009-07-27ARM: Add in spots for the VFP control registers.Gabe Black
2009-07-27ARM: Fix the CLZ instruction.Gabe Black
2009-07-27ARM: Initialize the CPSR so that we're in user mode.Gabe Black
2009-07-27ARM: Set up the initial stack frame to match a recent Linux.Gabe Black
2009-07-27Elf: Add in some new aux vector type constants.Gabe Black
2009-07-27ARM: Make native trace only print when registers are changing value.Gabe Black
When registers have incorrect values but aren't actively changing, it's likely they're not being modified at all. The fact that they're still wrong isn't very important.
2009-07-27ARM: Add a native tracer.Gabe Black
--HG-- rename : src/arch/sparc/SparcNativeTrace.py => src/arch/arm/ArmNativeTrace.py rename : src/arch/sparc/nativetrace.cc => src/arch/arm/nativetrace.cc rename : src/arch/sparc/nativetrace.hh => src/arch/arm/nativetrace.hh
2009-07-27ARM: Update the reference outputs for the new binary and fstat64 struct.Gabe Black
2009-07-27ARM: Fix fstat/fstat64 structs to match EABI definitions.Ali Saidi
2009-07-27ARM: Replace hello world with an EABI version.Gabe Black
2009-07-27ARM: Handle register indexed system calls.Ali Saidi
2009-07-27ARM: Detect OABI binaries and complain that they're no-longer supported.Ali Saidi
2009-07-26se-configs: edit se.py to account for non-O3CPU workloadsKorey Sewell
2009-07-25merge sparc fix w/2t regress fixKorey Sewell
2009-07-25regress: edit 2t hello smt file to specify numThreadsKorey Sewell
2009-07-25SPARC: Fix a minor compile bug in native trace on gcc > 4.1.Gabe Black
2009-07-25o3-smt: enforce numThreads parameter for SMT SE modeKorey Sewell
2009-07-22Fixed the licences plus minor fixes for compilationPolina Dudnik
2009-07-22MIPS: Small fix I forgot to qrefresh into my last change.Gabe Black
2009-07-22MIPS: Style/formatting sweep of the decoder itself.Gabe Black
2009-07-21MIPS: Format the register index constants like the other ISAs.Gabe Black
Also a few more style fixes.
2009-07-21Automated merge with ssh://m5sim.org//repo/m5Derek Hower
2009-07-21ruby: fixed sequencer RMW data bugDerek Hower
2009-07-21ruby: libruby_init now takes parsed Ruby-lang config textDerek Hower
libruby_init now expects to get a file that contains the output of running a ruby-lang configuration, opposed to the ruby-lang configuration itself.
2009-07-21MIPS: Get MIPS_FS to compile, more style fixes.Gabe Black
Some breakage was from my BitUnion change, some was much older.
2009-07-21MIPS: Many style fixes.Gabe Black
White space, commented out code, some other minor fixes.
2009-07-20isa_parser: Get rid of the now unused ControlBitfieldOperand.Gabe Black
2009-07-20MIPS: Use BitUnions instead of bits() functions and constants.Gabe Black
Also fix style issues in regions around these changes.
2009-07-20mergeDerek Hower
2009-07-20ruby: moved cache stats from Profiler to CacheMemoryDerek Hower
Caches are now responsible for their own statistic gathering. This requires a direct callback from the protocol on misses, and so all future protocols need to take this into account.
2009-07-19CPU: Separate out native trace into ISA (in)dependent code and SimObjects.Gabe Black
--HG-- rename : src/cpu/nativetrace.cc => src/arch/sparc/nativetrace.cc rename : src/cpu/nativetrace.hh => src/arch/sparc/nativetrace.hh rename : src/cpu/NativeTrace.py => src/arch/x86/X86NativeTrace.py
2009-07-19Tracing: Add accessors so tracers can get at data in trace records.Gabe Black
2009-07-19X86: Move a displaced comment back to where it goes.Gabe Black
2009-07-19X86: Add some misc registers for FP control state.Gabe Black
2009-07-19scons: removed RubyConfig from sconsDerek Hower
2009-07-18ruby: removed all refs to old RubyConfigDerek Hower
2009-07-18ruby: removed dead filesDerek Hower
2009-07-18ruby: removed dead filesDerek Hower
2009-07-18mergeDerek Hower
2009-07-18ruby: fixed dma sequencer bugDerek Hower
The DMASequencer was still using a parameter from the old RubyConfig, causing an offset error when the requested data wasn't block aligned. This changeset also includes a fix to MI_example for a similar bug.
2009-07-18ruby: better debug print for DataBlockDerek Hower
2009-07-18slicc: made coherence profilers per-controllerDerek Hower
2009-07-17X86: Set up a named constant for the "fold bit" for int register indices.Gabe Black
2009-07-17X86: Tame the wilds of def operands.Gabe Black
2009-07-17X86: Shift some register flattening work into the decoder.Gabe Black
2009-07-16mergePolina Dudnik
2009-07-16X86: Add range checks for miscreg indexing utility functions.Gabe Black