Commit graph

79 commits

Author SHA1 Message Date
Andreas Hansson
b3f930c884 CPU: Moving towards a more general port across CPU models
This patch performs minimal changes to move the instruction and data
ports from specialised subclasses to the base CPU (to the largest
degree possible). Ultimately it servers to make the CPU(s) have a
well-defined interface to the memory sub-system.
2012-01-17 12:55:08 -06:00
Andreas Hansson
f85286b3de MEM: Add port proxies instead of non-structural ports
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
2012-01-17 12:55:08 -06:00
Ali Saidi
1444103998 O3: Add stat that counts how many cycles the O3 cpu was quiesced.
--HG--
extra : rebase_source : 043b9307eef3c5b87f8e6370765641e016ed1fa7
2011-12-01 00:15:22 -08:00
Geoffrey Blake
5f425b8bd1 Fix bugs due to interaction between SEV instructions and O3 pipeline
SEV instructions were originally implemented to cause asynchronous squashes
via the generateTCSquash() function in the O3 pipeline when updating the
SEV_MAILBOX miscReg. This caused race conditions between CPUs in an MP system
that would lead to a pipeline either going inactive indefinitely or not being
able to commit squashed instructions. Fixed SEV instructions to behave like
interrupts and cause synchronous sqaushes inside the pipeline, eliminating
the race conditions. Also fixed up the semantics of the WFE instruction to
behave as documented in the ARMv7 ISA description to not sleep if SEV_MAILBOX=1
or unmasked interrupts are pending.
2011-08-19 15:08:07 -05:00
Gabe Black
5c0e6e6092 O3: Get rid of the unused addToRemoveList function. 2011-08-07 15:41:10 -07:00
Ali Saidi
60579e8d74 O3: Make sure fetch doesn't go off into the weeds during speculation. 2011-07-10 12:56:08 -05:00
Nathan Binkert
39a055645f includes: sort all includes 2011-04-15 10:44:06 -07:00
Joel Hestness
b4c10bd680 mcpat: Adds McPAT performance counters
Updated patches from Rick Strong's set that modify performance counters for
McPAT
2011-02-06 22:14:17 -08:00
Steve Reinhardt
6f1187943c Replace curTick global variable with accessor functions.
This step makes it easy to replace the accessor functions
(which still access a global variable) with ones that access
per-thread curTick values.
2011-01-07 21:50:29 -08:00
Steve Reinhardt
89cf3f6e85 Move sched_list.hh and timebuf.hh from src/base to src/cpu.
These files really aren't general enough to belong in src/base.
This patch doesn't reorder include lines, leaving them unsorted
in many cases, but Nate's magic script will fix that up shortly.

--HG--
rename : src/base/sched_list.hh => src/cpu/sched_list.hh
rename : src/base/timebuf.hh => src/cpu/timebuf.hh
2011-01-03 14:35:47 -08:00
Gabe Black
6f4bd2c1da ISA,CPU,etc: Create an ISA defined PC type that abstracts out ISA behaviors.
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.
2010-10-31 00:07:20 -07:00
Gabe Black
ab8d7eee76 CPU: Fix O3 and possible InOrder segfaults in FS. 2010-09-20 02:46:42 -07:00
Gabe Black
6833ca7eed Faults: Pass the StaticInst involved, if any, to a Fault's invoke method.
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.
2010-09-13 19:26:03 -07:00
Gabe Black
aa8c6e9c95 CPU: Add readBytes and writeBytes functions to the exec contexts. 2010-08-13 06:16:02 -07:00
Timothy M. Jones
29e8bcead5 O3PCU: Split loads and stores that cross cache line boundaries.
When each load or store is sent to the LSQ, we check whether it will cross a
cache line boundary and, if so, split it in two. This creates two TLB
translations and two memory requests. Care has to be taken if the first
packet of a split load is sent but the second blocks the cache. Similarly,
for a store, if the first packet cannot be sent, we must store the second
one somewhere to retry later.

This modifies the LSQSenderState class to record both packets in a split
load or store.

Finally, a new const variable, HasUnalignedMemAcc, is added to each ISA
to indicate whether unaligned memory accesses are allowed. This is used
throughout the changed code so that compiler can optimise away code dealing
with split requests for ISAs that don't need them.
2010-02-12 19:53:20 +00:00
Steve Reinhardt
fbfe92b5b8 o3: get rid of unused physmem pointer 2009-11-04 14:23:25 -08:00
Nathan Binkert
d9f39c8ce7 arch: nuke arch/isa_specific.hh and move stuff to generated config/the_isa.hh 2009-09-23 08:34:21 -07:00
Gabe Black
c9a27d85b9 Get rid of the unused get(Data|Inst)Asid and (inst|data)Asid functions. 2009-07-08 23:02:22 -07:00
Gabe Black
25884a8773 Registers: Get rid of the float register width parameter. 2009-07-08 23:02:20 -07:00
Gabe Black
32daf6fc3f Registers: Add an ISA object which replaces the MiscRegFile.
This object encapsulates (or will eventually) the identity and characteristics
of the ISA in the CPU.
2009-07-08 23:02:20 -07:00
Nathan Binkert
47877cf2db types: add a type for thread IDs and try to use it everywhere 2009-05-26 09:23:13 -07:00
Gabe Black
7b5a96f06b tlb: Don't separate the TLB classes into an instruction TLB and a data TLB 2009-04-08 22:21:27 -07:00
Nathan Binkert
cc95b57390 stats: Fix all stats usages to deal with template fixes 2009-03-05 19:09:53 -08:00
Gabe Black
9a000c5173 Processes: Make getting and setting system call arguments part of a process object. 2009-02-27 09:22:14 -08:00
Gabe Black
a1aba01a02 CPU: Get rid of translate... functions from various interface classes. 2009-02-25 10:15:34 -08:00
Nathan Binkert
f0fb3ac060 cpu: provide a wakeup mechanism that can be used to pull CPUs out of sleep.
Make interrupts use the new wakeup method, and pull all of the interrupt
stuff into the cpu base class so that only the wakeup code needs to be updated.
I tried to make wakeup, wakeCPU, and the various other mechanisms for waking
and sleeping a little more sane, but I couldn't understand why the statistics
were changing the way they were.  Maybe we'll try again some day.
2009-01-24 07:27:21 -08:00
Clint Smullen
1adfe5c7f3 O3CPU: Make the instcount debugging stuff per-cpu.
This is to prevent the assertion from firing if you have a large multicore.
Also make sure that it's not compiled in when NDEBUG is defined
2008-11-10 11:51:18 -08:00
Lisa Hsu
c55a467a06 make BaseCPU the provider of _cpuId, and cpuId() instead of being scattered
across the subclasses. generally make it so that member data is _cpuId and
accessor functions are cpuId(). The ID val comes from the python (default -1 if
none provided), and if it is -1, the index of cpuList will be given. this has
passed util/regress quick and se.py -n4 and fs.py -n4 as well as standard
switch.
2008-11-02 21:56:57 -05:00
Lisa Hsu
8788d703f8 s/cpu_id/cpuId in o3 (to be consistent and match style), also fix some typos in
comments.
2008-10-23 16:49:17 -04:00
Nathan Binkert
9836d81c2b style: Use the correct m5 style for things relating to interrupts. 2008-10-21 07:12:53 -07:00
Ali Saidi
b760b99f4d O3CPU: Undo Gabe's changes to remove hwrei and simpalcheck from O3 CPU. 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.
2008-10-20 16:22:59 -04:00
Gabe Black
f621b7b81f CPU: Eliminate the simPalCheck funciton. 2008-10-11 12:17:24 -07:00
Gabe Black
da7209ec93 CPU: Eliminate the hwrei function. 2008-10-11 02:27:21 -07:00
Nathan Binkert
e06321091d eventq: convert all usage of events to use the new API.
For now, there is still a single global event queue, but this is
necessary for making the steps towards a parallelized m5.
2008-10-09 04:58:24 -07:00
Gabe Black
e09c403d32 O3: Generalize the O3 CPU object so it isn't split out by ISA. 2008-10-09 00:08:50 -07:00
Nathan Binkert
ee62a0fec8 params: Convert the CPU objects to use the auto generated param structs.
A whole bunch of stuff has been converted to use the new params stuff, but
the CPU wasn't one of them.  While we're at it, make some things a bit
more stylish. Most of the work was done by Gabe, I just cleaned stuff up
a bit more at the end.
2008-08-11 12:22:16 -07:00
Gabe Black
8b4796a367 TLB: Make a TLB base class and put a virtual demapPage function in it.
--HG--
extra : convert_revision : cc0e62a5a337fd5bf332ad33bed61c0d505a936f
2008-02-26 23:38:51 -05:00
Stephen Hines
6cc1573923 Make the Event::description() a const function
--HG--
extra : convert_revision : c7768d54d3f78685e93920069f5485083ca989c0
2008-02-06 16:32:40 -05:00
Ali Saidi
d325f49b70 Rename cycles() function to ticks()
--HG--
extra : convert_revision : 790eddb793d4f5ba35813d001037bd8601bd76a5
2007-09-28 13:21:52 -04:00
Gabe Black
537239b278 Address Translation: Make SE mode use an actual TLB/MMU for translation like FS.
--HG--
extra : convert_revision : a04a30df0b6246e877a1cea35420dbac94b506b1
2007-08-26 20:24:18 -07:00
Gabe Black
82f78ebd39 Move the "translate" member functions back into the base o3 class.
--HG--
extra : convert_revision : 3c480537bf38f74f0f1d72e75c70aa46ba91b759
2007-08-13 16:01:09 -07:00
Gabe Black
49490b334a Merge zizzer.eecs.umich.edu:/bk/newmem
into  ahchoo.blinky.homelinux.org:/home/gblack/m5/newmem-o3-micro

src/cpu/o3/fetch_impl.hh:
    hand merge

--HG--
extra : convert_revision : 3f71f3ac2035eec8b6f7bceb6906edb4dd09c045
2007-06-21 20:35:25 +00:00
Nathan Binkert
f65e2710ec Don't do checker stuff if the checker is not defined
--HG--
extra : convert_revision : 1c920b050c21e592a386410e4e9f45354f8e4441
2007-06-20 08:15:06 -07:00
Gabe Black
c3081d9c1c Add support for microcode and pull out the special branch delay slot handling. Branch delay slots need to be squash on a mispredict as well because the nnpc they saw was incorrect.
--HG--
extra : convert_revision : 8b9c603616bcad254417a7a3fa3edfb4c8728719
2007-04-14 17:13:18 +00:00
Gabe Black
c7f1cf1d58 Remove most of the special handling for delay slots since they have to be squashed anyway on a mispredict. This is because the NNPC value they saw when executing was incorrect.
--HG--
extra : convert_revision : b42c4eb28b4fbba66c65cbd0a5033bf886c1532d
2007-04-13 13:59:31 +00:00
Kevin Lim
6ff6621f20 Pass ISA-specific O3 CPU as a constructor parameter instead of using setCPU functions.
src/cpu/o3/alpha/cpu_impl.hh:
    Pass ISA-specific O3 CPU to FullO3CPU as a constructor parameter instead of using setCPU functions.

--HG--
extra : convert_revision : 74f4b1f5fb6f95a56081f367cce7ff44acb5688a
2007-04-04 15:38:59 -04:00
Kevin Lim
047f77102b Merge ktlim@zizzer:/bk/newmem
into  zamp.eecs.umich.edu:/z/ktlim2/clean/tmp/clean2

src/cpu/base_dyn_inst.hh:
    Hand merge.  Line is no longer needed because it's handled in the ISA.

--HG--
extra : convert_revision : 0be4067aa38759a5631c6940f0167d48fde2b680
2007-03-23 13:20:19 -04:00
Kevin Lim
55a45d3644 A couple of minor fixes.
1. Set CPU ID in all modes for the O3 CPU.
2. Use nextCycle() function to prevent phase drift in O3 CPU.
3. Remove assertion in rename map that is no longer true.

src/cpu/o3/alpha/cpu_builder.cc:
    Allow for CPU id in all modes, not just full system.  Also include a parameter that was left out by accident.
src/cpu/o3/alpha/cpu_impl.hh:
    Set the CPU ID properly.
src/cpu/o3/cpu.cc:
src/cpu/o3/cpu.hh:
    Use nextCycle() function so that the CPU does not get out of phase when starting up from quiesces.
src/cpu/o3/rename_map.cc:
    Remove assertion that is no longer true.
tests/configs/o3-timing.py:
    Set CPU's id to 0.

--HG--
extra : convert_revision : 2b69c19adfce2adcc2d1939e89d702bd6674d5d5
2007-03-23 11:22:43 -04:00
Kevin Lim
ad44834907 Two fixes:
1. Make sure connectMemPorts() only gets called when the CPU's peer gets changed.  This is done by making setPeer() virtual, and overriding it in the CPU's ports.  When it gets called on a CPU's port (dcache specifically), it calls the normal setPeer() function, and also connectMemPorts().
2. Consolidate redundant code that handles switching in a CPU.

src/cpu/base.cc:
    Move common code of switching over peers to base CPU.
src/cpu/base.hh:
    Move common code of switching over peers to BaseCPU.
src/cpu/o3/cpu.cc:
    Add in function that updates thread context's ports.
    Also use updated function to takeOverFrom() in BaseCPU.  This gets rid of some repeated code.
src/cpu/o3/cpu.hh:
    Include function to update thread context's memory ports.
src/cpu/o3/lsq.hh:
    Add function to dcache port that will update the memory ports upon getting a new peer.
    Also include a function that will tell the CPU to update those memory ports.
src/cpu/o3/lsq_impl.hh:
    Add function that will update the memory ports upon getting a new peer.
src/cpu/simple/atomic.cc:
src/cpu/simple/timing.cc:
    Add function that will update thread context's memory ports upon getting a new peer.
    Also use the new BaseCPU's take over from function.
src/cpu/simple/atomic.hh:
    Add in function (and dcache port) that will allow the dcache to update memory ports when it gets assigned a new peer.
src/cpu/simple/timing.hh:
    Add function that will update thread context's memory ports upon getting a new peer.
src/mem/port.hh:
    Make setPeer virtual so that other classes can override it.

--HG--
extra : convert_revision : 2050f1241dd2e83875d281cfc5ad5c6c8705fdaf
2007-03-09 10:06:09 -05:00
Gabe Black
6826ee53db Got rid of some typedefs, moved the tlbs to the base o3 cpu, and called the architecture defined setSyscallReturn function instead of a duplicate copy.
src/cpu/o3/alpha/cpu.hh:
    Got rid of some typedefs, and moved the tlbs to the base o3 cpu.
src/cpu/o3/alpha/thread_context.hh:
src/cpu/o3/cpu.cc:
    Moved the tlbs to the base o3 cpu.

--HG--
extra : convert_revision : 1805613aa230b8974a226ee3d2584c85f7a578aa
2006-12-06 11:36:40 -05:00