summaryrefslogtreecommitdiff
path: root/src/cpu/simple_thread.hh
AgeCommit message (Collapse)Author
2010-10-31ISA,CPU,etc: Create an ISA defined PC type that abstracts out ISA behaviors.Gabe Black
This change is a low level and pervasive reorganization of how PCs are managed in M5. Back when Alpha was the only ISA, there were only 2 PCs to worry about, the PC and the NPC, and the lsb of the PC signaled whether or not you were in PAL mode. As other ISAs were added, we had to add an NNPC, micro PC and next micropc, x86 and ARM introduced variable length instruction sets, and ARM started to keep track of mode bits in the PC. Each CPU model handled PCs in its own custom way that needed to be updated individually to handle the new dimensions of variability, or, in the case of ARMs mode-bit-in-the-pc hack, the complexity could be hidden in the ISA at the ISA implementation's expense. Areas like the branch predictor hadn't been updated to handle branch delay slots or micropcs, and it turns out that had introduced a significant (10s of percent) performance bug in SPARC and to a lesser extend MIPS. Rather than perpetuate the problem by reworking O3 again to handle the PC features needed by x86, this change was introduced to rework PC handling in a more modular, transparent, and hopefully efficient way. PC type: Rather than having the superset of all possible elements of PC state declared in each of the CPU models, each ISA defines its own PCState type which has exactly the elements it needs. A cross product of canned PCState classes are defined in the new "generic" ISA directory for ISAs with/without delay slots and microcode. These are either typedef-ed or subclassed by each ISA. To read or write this structure through a *Context, you use the new pcState() accessor which reads or writes depending on whether it has an argument. If you just want the address of the current or next instruction or the current micro PC, you can get those through read-only accessors on either the PCState type or the *Contexts. These are instAddr(), nextInstAddr(), and microPC(). Note the move away from readPC. That name is ambiguous since it's not clear whether or not it should be the actual address to fetch from, or if it should have extra bits in it like the PAL mode bit. Each class is free to define its own functions to get at whatever values it needs however it needs to to be used in ISA specific code. Eventually Alpha's PAL mode bit could be moved out of the PC and into a separate field like ARM. These types can be reset to a particular pc (where npc = pc + sizeof(MachInst), nnpc = npc + sizeof(MachInst), upc = 0, nupc = 1 as appropriate), printed, serialized, and compared. There is a branching() function which encapsulates code in the CPU models that checked if an instruction branched or not. Exactly what that means in the context of branch delay slots which can skip an instruction when not taken is ambiguous, and ideally this function and its uses can be eliminated. PCStates also generally know how to advance themselves in various ways depending on if they point at an instruction, a microop, or the last microop of a macroop. More on that later. Ideally, accessing all the PCs at once when setting them will improve performance of M5 even though more data needs to be moved around. This is because often all the PCs need to be manipulated together, and by getting them all at once you avoid multiple function calls. Also, the PCs of a particular thread will have spatial locality in the cache. Previously they were grouped by element in arrays which spread out accesses. Advancing the PC: The PCs were previously managed entirely by the CPU which had to know about PC semantics, try to figure out which dimension to increment the PC in, what to set NPC/NNPC, etc. These decisions are best left to the ISA in conjunction with the PC type itself. Because most of the information about how to increment the PC (mainly what type of instruction it refers to) is contained in the instruction object, a new advancePC virtual function was added to the StaticInst class. Subclasses provide an implementation that moves around the right element of the PC with a minimal amount of decision making. In ISAs like Alpha, the instructions always simply assign NPC to PC without having to worry about micropcs, nnpcs, etc. The added cost of a virtual function call should be outweighed by not having to figure out as much about what to do with the PCs and mucking around with the extra elements. One drawback of making the StaticInsts advance the PC is that you have to actually have one to advance the PC. This would, superficially, seem to require decoding an instruction before fetch could advance. This is, as far as I can tell, realistic. fetch would advance through memory addresses, not PCs, perhaps predicting new memory addresses using existing ones. More sophisticated decisions about control flow would be made later on, after the instruction was decoded, and handed back to fetch. If branching needs to happen, some amount of decoding needs to happen to see that it's a branch, what the target is, etc. This could get a little more complicated if that gets done by the predecoder, but I'm choosing to ignore that for now. Variable length instructions: To handle variable length instructions in x86 and ARM, the predecoder now takes in the current PC by reference to the getExtMachInst function. It can modify the PC however it needs to (by setting NPC to be the PC + instruction length, for instance). This could be improved since the CPU doesn't know if the PC was modified and always has to write it back. ISA parser: To support the new API, all PC related operand types were removed from the parser and replaced with a PCState type. There are two warts on this implementation. First, as with all the other operand types, the PCState still has to have a valid operand type even though it doesn't use it. Second, using syntax like PCS.npc(target) doesn't work for two reasons, this looks like the syntax for operand type overriding, and the parser can't figure out if you're reading or writing. Instructions that use the PCS operand (which I've consistently called it) need to first read it into a local variable, manipulate it, and then write it back out. Return address stack: The return address stack needed a little extra help because, in the presence of branch delay slots, it has to merge together elements of the return PC and the call PC. To handle that, a buildRetPC utility function was added. There are basically only two versions in all the ISAs, but it didn't seem short enough to put into the generic ISA directory. Also, the branch predictor code in O3 and InOrder were adjusted so that they always store the PC of the actual call instruction in the RAS, not the next PC. If the call instruction is a microop, the next PC refers to the next microop in the same macroop which is probably not desirable. The buildRetPC function advances the PC intelligently to the next macroop (in an ISA specific way) so that that case works. Change in stats: There were no change in stats except in MIPS and SPARC in the O3 model. MIPS runs in about 9% fewer ticks. SPARC runs with 30%-50% fewer ticks, which could likely be improved further by setting call/return instruction flags and taking advantage of the RAS. TODO: Add != operators to the PCState classes, defined trivially to be !(a==b). Smooth out places where PCs are split apart, passed around, and put back together later. I think this might happen in SPARC's fault code. Add ISA specific constructors that allow setting PC elements without calling a bunch of accessors. Try to eliminate the need for the branching() function. Factor out Alpha's PAL mode pc bit into a separate flag field, and eliminate places where it's blindly masked out or tested in the PC.
2010-09-13Faults: Pass the StaticInst involved, if any, to a Fault's invoke method.Gabe Black
Also move the "Fault" reference counted pointer type into a separate file, sim/fault.hh. It would be better to name this less similarly to sim/faults.hh to reduce confusion, but fault.hh matches the name of the type. We could change Fault to FaultPtr to match other pointer types, and then changing the name of the file would make more sense.
2010-08-23CPU: Print out flatten-out register index as with IntRegs/FloatRegs traceflagMin Kyu Jeong
2010-08-23ARM/O3: store the result of the predicate evaluation in DynInst or Threadstate.Min Kyu Jeong
THis allows the CPU to handle predicated-false instructions accordingly. This particular patch makes loads that are predicated-false to be sent straight to the commit stage directly, not waiting for return of the data that was never requested since it was predicated-false.
2010-06-02ARM: Implement ARM CPU interruptsAli Saidi
2010-06-02Simple CPU: Make the FloatRegs trace flag do something.Gabe Black
2009-09-23arch: nuke arch/isa_specific.hh and move stuff to generated config/the_isa.hhNathan Binkert
2009-07-29Simple CPU: Make the simple CPU handle the IntRegs trace flag.Gabe Black
2009-07-08Get rid of the unused get(Data|Inst)Asid and (inst|data)Asid functions.Gabe Black
2009-07-08Registers: Add a registers.hh file as an ISA switched header.Gabe Black
This file is for register indices, Num* constants, and register types. copyRegs and copyMiscRegs were moved to utility.hh and utility.cc. --HG-- rename : src/arch/alpha/regfile.hh => src/arch/alpha/registers.hh rename : src/arch/arm/regfile.hh => src/arch/arm/registers.hh rename : src/arch/mips/regfile.hh => src/arch/mips/registers.hh rename : src/arch/sparc/regfile.hh => src/arch/sparc/registers.hh rename : src/arch/x86/regfile.hh => src/arch/x86/registers.hh
2009-07-08Registers: Eliminate the ISA defined RegFile class.Gabe Black
2009-07-08Registers: Move the PCs out of the ISAs and into the CPUs.Gabe Black
2009-07-08ARM, Simple CPU: Fix an index and add assert checks.Gabe Black
2009-07-08Registers: Eliminate the ISA defined integer register file.Gabe Black
2009-07-08Registers: Eliminate the ISA defined floating point register file.Gabe Black
2009-07-08Registers: Get rid of the float register width parameter.Gabe Black
2009-07-08Registers: Add an ISA object which replaces the MiscRegFile.Gabe Black
This object encapsulates (or will eventually) the identity and characteristics of the ISA in the CPU.
2009-05-26types: add a type for thread IDs and try to use it everywhereNathan Binkert
2009-05-17includes: sort includes againNathan Binkert
2009-05-17types: Move stuff for global types into src/base/types.hhNathan Binkert
--HG-- rename : src/sim/host.hh => src/base/types.hh
2009-04-15Get rid of the Unallocated thread context state.Steve Reinhardt
Basically merge it in with Halted. Also had to get rid of a few other functions that called ThreadContext::deallocate(), including: - InOrderCPU's setThreadRescheduleCondition. - ThreadContext::exit(). This function was there to avoid terminating simulation when one thread out of a multi-thread workload exits, but we need to find a better (non-cpu-centric) way.
2009-04-08tlb: Don't separate the TLB classes into an instruction TLB and a data TLBGabe Black
2009-02-27Processes: Make getting and setting system call arguments part of a process ↵Gabe Black
object.
2009-02-25ISA: Replace the translate functions in the TLBs with translateAtomic.Gabe Black
2009-02-25CPU: Get rid of translate... functions from various interface classes.Gabe Black
2009-01-19thread_context: move getSystemPtr so SE mode can get to it.Nathan Binkert
There was really no reason that it should be FS only.
2008-12-16SPARC: Truncate syscall args and return values appropriately.Gabe Black
2008-11-04get rid of all instances of readTid() and getThreadNum(). Unify and eliminateLisa Hsu
redundancies with threadId() as their replacement.
2008-10-20O3CPU: Undo Gabe's changes to remove hwrei and simpalcheck from O3 CPU. ↵Ali Saidi
Removing hwrei causes the instruction after the hwrei to be fetched before the ITB/DTB_CM register is updated in a call pal call sys and thus the translation fails because the user is attempting to access a super page address. Minimally, it seems as though some sort of fetch stall or refetch after a hwrei is required. I think this works currently because the hwrei uses the exec context interface, and the o3 stalls when that occurs. Additionally, these changes don't update the LOCK register and probably break ll/sc. Both o3 changes were removed since a great deal of manual patching would be required to only remove the hwrei change.
2008-10-12Get rid of old RegContext code.Gabe Black
2008-10-11CPU: Eliminate the simPalCheck funciton.Gabe Black
2008-10-11CPU: Eliminate the hwrei function.Gabe Black
2008-09-10style: Remove non-leading tabs everywhere they shouldn't be. Developers ↵Ali Saidi
should configure their editors to not insert tabs
2008-07-01Remove delVirtPort() and make getVirtPort() only return cached version.Ali Saidi
2008-02-26TLB: Make a TLB base class and put a virtual demapPage function in it.Gabe Black
--HG-- extra : convert_revision : cc0e62a5a337fd5bf332ad33bed61c0d505a936f
2007-11-15Get MIPS simple regression working. Take out unecessary functions ↵Korey Sewell
"setShadowSet", "CacheOp" --HG-- extra : convert_revision : a9ae8a7e62c27c2db16fd3cfa7a7f0bf5f0bf8ea
2007-11-13Add in files from merge-bare-iron, get them compiling in FS and SE modeKorey Sewell
--HG-- extra : convert_revision : d4e19afda897bc3797868b40469ce2ec7ec7d251
2007-09-25SPARC: Fix a stupid mistake which was breaking the SPARC regressions.Gabe Black
--HG-- extra : convert_revision : 34a11df0d467ea249211dd3aba86bc8d2aea45de
2007-09-19X86: Put in the foundation for x87 stack based fp registers.Gabe Black
--HG-- extra : convert_revision : 940f92efd4a9dc59106e991cc6d9836861ab69de
2007-08-26Address Translation: Make SE mode use an actual TLB/MMU for translation like FS.Gabe Black
--HG-- extra : convert_revision : a04a30df0b6246e877a1cea35420dbac94b506b1
2007-07-26X86: Fix argument register indexing.Gabe Black
Code was assuming that all argument registers followed in order from ArgumentReg0. There is now an ArgumentReg array which is indexed to find the right index. There is a constant, NumArgumentRegs, which can be used to protect against using an invalid ArgumentReg. --HG-- extra : convert_revision : f448a3ca4d6adc3fc3323562870f70eec05a8a1f
2007-06-22mips import pt. 1Korey Sewell
src/arch/mips/SConscript: "mips import pt.1". --HG-- extra : convert_revision : 2e393341938bebf32fb638a209262d074fad4cc1
2007-05-28Remove unnecessary include of physical.hh.Steve Reinhardt
--HG-- extra : convert_revision : bccafe884e58a55b02ff408448e6644196e439a4
2007-03-07*MiscReg->*MiscRegNoEffect, *MiscRegWithEffect->*MiscRegAli Saidi
--HG-- extra : convert_revision : f799b65f1b2a6bf43605e6870b0f39b473dc492b
2006-12-12Merge zizzer:/bk/newmem/Gabe Black
into zower.eecs.umich.edu:/eecshome/m5/newmem --HG-- extra : convert_revision : 17d6c49ee15af5d192dedf82871159219d4277cd
2006-12-12Get rid of unused lock code.Steve Reinhardt
--HG-- extra : convert_revision : a8030132268662ca54f487b8d32d09ba224317a8
2006-12-06Flattening and syscallReturn fixesGabe Black
src/cpu/o3/thread_context_impl.hh: Use flattened indices src/cpu/simple_thread.hh: Use flattened indices, and pass a thread context to setSyscallReturn rather than a register file. src/cpu/thread_context.hh: The SyscallReturn class is no longer in arch/syscallreturn.hh --HG-- extra : convert_revision : ed84bb8ac5ef0774526ecd0d7270b0c60cd3708e
2006-11-19Update Virtual and Physical ports.Kevin Lim
src/cpu/o3/alpha/cpu_impl.hh: Handle the PhysicalPort and VirtualPort in the ThreadState. src/cpu/o3/cpu.cc: Initialize the thread context. src/cpu/o3/thread_context.hh: Add new function to initialize thread context. src/cpu/o3/thread_context_impl.hh: Use code now put into function. src/cpu/simple_thread.cc: Move code to ThreadState and use the new helper function. src/cpu/simple_thread.hh: Remove init() in this derived class; use init() from ThreadState base class. src/cpu/thread_state.cc: Move setting up of Physical and Virtual ports here. Change getMemFuncPort() to connectToMemFunc(), which connects a port to a functional port of the memory object below the CPU. src/cpu/thread_state.hh: Update functions. --HG-- extra : convert_revision : ff254715ef0b259dc80d08f13543b63e4024ca8d
2006-11-17Make an initialization pass for the thread context and set the ↵Ron Dreslinski
[phys,virt]Port correctly src/cpu/simple/atomic.cc: src/cpu/simple/timing.cc: Call the thread context initialization --HG-- extra : convert_revision : d7dc2a8b893dc670077b7f6150d4b710a1778620
2006-11-07Moved the switched version of kernel_stats.hh back to kern, and moved the ↵Gabe Black
base kernel_stats to base_kernel_stats --HG-- extra : convert_revision : 2a010d2eb7ea2586ff063b99b8bcde6eb1e8e017