Commit graph

83 commits

Author SHA1 Message Date
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
Ali Saidi
e681c0f7b3 O3: Support squashing all state after special instruction
For SPARC ASIs are added to the ExtMachInst. If the ASI is changed simply
marking the instruction as Serializing isn't enough beacuse that only
stops rename. This provides a mechanism to squash all the instructions
and refetch them
2010-12-07 16:19:57 -08:00
Giacomo Gabrielli
719f9a6d4f O3: Make all instructions that write a misc. register not perform the write until commit.
ARM instructions updating cumulative flags (ARM FP exceptions and saturation
flags) are not serialized.

Added aliases for ARM FP exceptions and saturation flags in FPSCR.  Removed
write accesses to the FP condition codes for most ARM VFP instructions: only
VCMP and VCMPE instructions update the FP condition codes.  Removed a potential
cause of seg. faults in the O3 model for NEON memory macro-ops (ARM).
2010-12-07 16:19:57 -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
8f3fbd2d13 CPU: Get rid of the now unnecessary getInst/setInst family of functions.
This code is no longer needed because of the preceeding change which adds a
StaticInstPtr parameter to the fault's invoke method, obviating the only use
for this pair of functions.
2010-09-13 21:58:34 -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
Steve Reinhardt
4bec4702e9 O3: Add flag to control whether faulting instructions are traced.
When enabled, faulting instructions appear in the trace twice
(once when they fault and again when they're re-executed).
This flag is set by the Exec compound flag for backwards compatibility.
2009-09-26 10:50:50 -07:00
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
Nathan Binkert
47877cf2db types: add a type for thread IDs and try to use it everywhere 2009-05-26 09:23:13 -07:00
Ali Saidi
d447ccb2c6 CPA: Add code to automatically record function symbols as CPU executes. 2009-02-26 19:29:17 -05:00
Nathan Binkert
489e3e7381 eventq: use the flags data structure 2008-12-06 14:18:18 -08:00
Nathan Binkert
9836d81c2b style: Use the correct m5 style for things relating to interrupts. 2008-10-21 07:12:53 -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
Kevin Lim
b784903207 O3CPU: Fix thread writeback logic.
Fix the logic in the LSQ that determines if there are any stores to
write back. In the commit stage, check for thread specific writebacks
instead of just any writeback.
2008-09-26 07:44:07 -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
Stephen Hines
6cc1573923 Make the Event::description() a const function
--HG--
extra : convert_revision : c7768d54d3f78685e93920069f5485083ca989c0
2008-02-06 16:32:40 -05:00
Gabe Black
988cdb49f2 CPU: Make the cpus check the pc event queues in SE mode.
--HG--
extra : convert_revision : 9dc4ea136c3c3f87a73d55e91bc4aae4eba70464
2007-10-02 18:25:37 -07:00
Ali Saidi
d325f49b70 Rename cycles() function to ticks()
--HG--
extra : convert_revision : 790eddb793d4f5ba35813d001037bd8601bd76a5
2007-09-28 13:21:52 -04:00
Steve Reinhardt
ee54ad318a Event descriptions should not end in "event"
(they function as adjectives not nouns)

--HG--
extra : convert_revision : 6506474ff3356ae8c80ed276c3608d8a4680bfdb
2007-06-30 17:45:58 -07:00
Gabe Black
4ad1b58fdd Merge zizzer.eecs.umich.edu:/bk/newmem
into  doughnut.mwconnections.com:/home/gblack/newmem-o3-micro

--HG--
extra : convert_revision : 545b9e98eb1895f4b9e782224fb6615c71ed6323
2007-05-09 20:50:46 -07:00
Kevin Lim
15cc194d71 Remove unnecessary check.
--HG--
extra : convert_revision : 8cc2943ebc41e4d430789ee7923dd0dc878be06b
2007-04-26 00:02:37 -04:00
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
ec09e5ad6f Remove/comment out DPRINTFs that were causing a segfault.
The removed ones were unnecessary.  The commented out ones could be useful in the future, should this problem get fixed.  See flyspray task #243.

src/cpu/o3/commit_impl.hh:
src/cpu/o3/decode_impl.hh:
src/cpu/o3/fetch_impl.hh:
src/cpu/o3/iew_impl.hh:
src/cpu/o3/inst_queue_impl.hh:
src/cpu/o3/lsq_impl.hh:
src/cpu/o3/lsq_unit_impl.hh:
src/cpu/o3/rename_impl.hh:
src/cpu/o3/rob_impl.hh:
    Remove/comment out DPRINTFs that were causing a segfault.

--HG--
extra : convert_revision : b5aeda1c6300dfde5e0a3e9b8c4c5f6fa00b9862
2007-04-02 13:55:45 -04:00
Kevin Lim
5c044cf1f6 Update for new trace data behavior.
--HG--
extra : convert_revision : c3df20c5187614febc4cc9f4d4c68bfecfba1ea7
2007-03-24 23:47:14 -05:00
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
941d3168d0 Updates for commit.
1. Move interrupt handling to a separate function to clean up main commit() function a bit.  Also gate the function call off properly based on whether or not there are outstanding interrupts, and the system is not in PAL mode.
2. Better handling of updating instruction's status bits.  Instructions are not marked "atCommit" until other stages view it (pushed off to IEW/IQ), and they have been properly handled (faults).
3. Don't consider the ROB "empty" for the purpose of other stages until the ROB is empty, all stores have written back, and there was no store commits this cycle.  The last is necessary in case a store committed, in which case it would look like all stores have written back but in actuality have not.

src/cpu/o3/commit.hh:
    Slightly modify how interrupts are handled.  Also include some extra bools to keep track of state properly.
src/cpu/o3/commit_impl.hh:
    Slightly modify how interrupts are handled.  Also include some extra bools to keep track of state.

    General correctness updates, most specifically for when commit broadcasts to other stages that the ROB is empty.

--HG--
extra : convert_revision : 682ec6ccf4ee6ed0c8a030ceaba1c90a3619d102
2007-03-23 13:13:10 -04:00
Nathan Binkert
184decd196 Clean up tracing stuff more, get rid of the trace log since
its not all that useful. Fix a few bugs with python/C++
integration.

--HG--
extra : convert_revision : a706512f7dc8b0c88f1ff96fe35ab8fbf9548b78
2007-02-10 15:14:50 -08:00
Gabe Black
0358ccee23 Merge zizzer:/bk/newmem
into  zower.eecs.umich.edu:/eecshome/m5/newmem

src/arch/sparc/isa/formats/mem/util.isa:
src/arch/sparc/isa_traits.hh:
src/arch/sparc/system.cc:
    Hand Merge

--HG--
extra : convert_revision : d5e0c97caebb616493e2f642e915969d7028109c
2007-01-27 01:59:20 -05:00
Lisa Hsu
202d7f62b9 eliminate cpu checkInterrupts bool, it is redundant and unnecessary.
--HG--
extra : convert_revision : 58e960e5019f944c7ec5606e4b8c93ce42330719
2007-01-26 12:51:07 -05:00
Gabe Black
8840ebcb00 Merge zizzer:/bk/newmem
into  zower.eecs.umich.edu:/eecshome/m5/newmem

--HG--
extra : convert_revision : f4a05accb8fa24d425dd818b1b7f268378180e99
2007-01-03 00:52:30 -05:00
Kevin Lim
7d7f3d0e99 Fix up previous commit to proper logic.
src/cpu/o3/commit_impl.hh:
    Oops, changed the logic a little bit.  Fix it up to how it used to be.

--HG--
extra : convert_revision : df7f69b0997207b611374c3c92880f3a405e88be
2006-12-30 13:21:25 -05:00
Kevin Lim
0bd7518480 Remove some #if FULL_SYSTEMs so MP stuff works even in SE mode.
--HG--
extra : convert_revision : 5c334ec806305451b3883c7fd0ed9cd695c038bc
2006-12-26 01:43:18 -05:00
Nathan Binkert
9aecfb3e3b don't use (*activeThreads).begin(), use activeThreads->blah().
Also don't call (*activeThreads).end() over and over.  Just
call activeThreads->end() once and save the result.
Make sure we always check that there are elements in the list
before we grab the first one.

--HG--
extra : convert_revision : d769d8ed52da99532d57a9bbc93e92ddf22b7e58
2006-12-20 22:20:11 -08:00
Gabe Black
dfafe6741f Make sure you only handle branch delay slots specially when there actually was a branch.
--HG--
extra : convert_revision : ea6d33b1b9c2ba5c24225af4b10a9bd25558f1dd
2006-12-18 18:18:37 -05:00
Gabe Black
37b9966eb4 Made branch delay slots get squashed, and passed back an NPC and NNPC to start fetching from.
--HG--
extra : convert_revision : a2e4845fedf113b5a2fd92d3d28ce5b006278103
2006-12-16 07:32:06 -05:00
Gabe Black
90907f6b3c Merge zizzer:/bk/newmem/
into  zower.eecs.umich.edu:/eecshome/m5/newmem

--HG--
extra : convert_revision : 17d6c49ee15af5d192dedf82871159219d4277cd
2006-12-12 18:10:00 -05:00
Kevin Lim
b618e733bd Fix for MIPS_SE/m5.fast compile.
--HG--
extra : convert_revision : dbb893250974ac6db7b6c1ba67263fd35098ca43
2006-12-06 14:23:31 -05:00
Gabe Black
2dcf00bc8b Merge zizzer:/bk/newmem
into  zower.eecs.umich.edu:/eecshome/m5/newmem

src/cpu/o3/commit_impl.hh:
    Hand Merge

--HG--
extra : convert_revision : 6984db90d5b5ec71c31f1c345f5a77eed540059e
2006-12-06 06:05:28 -05:00
Gabe Black
20340b5e26 Change how optional delay slot instructions are detected and squashed.
--HG--
extra : convert_revision : ffd019d4adc2fbbc0a663d8dc6ef73edce12511b
2006-12-06 05:51:18 -05:00
Kevin Lim
c0f21b09c8 Fixes for MIPS_SE compiling. Regressions seem to work, but Korey should make sure these changes (commit especially) work okay.
src/cpu/o3/commit_impl.hh:
src/cpu/o3/fetch_impl.hh:
    Fixes for MIPS_SE compile.

--HG--
extra : convert_revision : fde9616f8e72b397c5ca965774172372cff53790
2006-12-02 13:33:46 -05:00
Kevin Lim
41a9196f60 More interrupt reworking.
--HG--
extra : convert_revision : 40dfbb72c4e418c54e909c54dad5fe6ef7017cb4
2006-11-13 02:49:03 -05:00
Kevin Lim
437436a2f7 Fix for non-FS compile.
--HG--
extra : convert_revision : 661b412b0ae670181b89cb7dbc5e9d813804aa7a
2006-11-12 21:49:51 -05:00
Kevin Lim
12e26c68c3 Updates to support new interrupt processing and removal of PcPAL.
src/arch/alpha/interrupts.hh:
    No need for this now that the ThreadContext is being used to set these IPRs in interrupts.
    Also split up the interrupt checking from the updating of the IPL and interrupt summary.
src/arch/alpha/tlb.cc:
    Check the PC for whether or not it's in PAL mode, not the addr.
src/cpu/o3/alpha/cpu.hh:
    Split up getting the interrupt from actually processing the interrupt.
src/cpu/o3/alpha/cpu_impl.hh:
    Splut up the processing of interrupts.
src/cpu/o3/commit_impl.hh:
    Update for ISA-oriented interrupt changes.
src/cpu/o3/fetch_impl.hh:
    Fix broken if statement from PcPAL updates, and properly populate the request fields.

    Also more debugging output.
src/cpu/ozone/cpu_impl.hh:
    Updates for ISA-oriented interrupt stuff.
src/cpu/ozone/front_end_impl.hh:
    Populate request fields properly.
src/cpu/simple/base.cc:
    Update for interrupt stuff.

--HG--
extra : convert_revision : 9bac3f9ffed4948ee788699b2fa8419bc1ca647c
2006-11-12 20:15:30 -05:00
Gabe Black
67b9a2ebd8 Move the check to see if you're in user mode into the isa directory.
--HG--
extra : convert_revision : b5b7cdf4a5e5e54228c592093516bf18d0f7dbe6
2006-11-08 13:55:48 -05:00
Gabe Black
118b9dc1f9 Got rid of "inPalMode". Some places are still effectively checking if they are in PAL mode, however.
--HG--
extra : convert_revision : b52d9642efc474eaf97437fa2df879efefa0062b
2006-11-03 04:25:33 -05:00
Kevin Lim
d48ea81ba2 Updates to O3 CPU. It should now work in FS mode, although sampling still has a bug.
src/cpu/o3/commit_impl.hh:
    Fixes for compile and sampling.
src/cpu/o3/cpu.cc:
    Deallocate and activate threads properly.  Also hopefully fix being able to use caches while switching over.
src/cpu/o3/cpu.hh:
    Fixes for deallocating and activating threads.
src/cpu/o3/fetch_impl.hh:
src/cpu/o3/lsq_unit.hh:
    Handle getting back a BadAddress result from the access.
src/cpu/o3/iew_impl.hh:
    More debug output.
src/cpu/o3/lsq_unit_impl.hh:
    Fixup store conditional handling (still a bit of a hack, but works now).

    Also handle getting back a BadAddress result from the access.
src/cpu/o3/thread_context_impl.hh:
    Deallocate context now records if the context should be fully removed.

--HG--
extra : convert_revision : 55f81660602d0e25367ce1f5b0b9cfc62abe7bf9
2006-10-08 00:53:41 -04:00