Commit graph

73 commits

Author SHA1 Message Date
Gabe Black
63a934d152 ISA parser: Define operand types with a ctype directly. 2011-07-05 16:52:15 -07:00
Gabe Black
aade13769f ISA: Use readBytes/writeBytes for all instruction level memory operations. 2011-07-02 22:34:29 -07:00
Deyaun Guo
5aaddc129e mips: fix nmsub and nmadd definitions
the -/+ signs were flipped for nmsub_s, nmsub_d, and nmadd_d
2011-06-22 23:35:21 -04:00
Nathan Binkert
eddac53ff6 trace: reimplement the DTRACE function so it doesn't use a vector
At the same time, rename the trace flags to debug flags since they
have broader usage than simply tracing.  This means that
--trace-flags is now --debug-flags and --trace-help is now --debug-help
2011-04-15 10:44:32 -07:00
Nathan Binkert
39a055645f includes: sort all includes 2011-04-15 10:44:06 -07:00
Korey Sewell
e65c15e931 inorder: remove unused isa ops
pass/fail ops were used for testing but arent part of isa
2011-02-12 10:14:26 -05:00
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
Gabe Black
672d6a4b98 Style: Replace some tabs with spaces. 2010-12-20 16:24:40 -05:00
Gabe Black
f26051eb1a MIPS: Take advantage of new PCState syntax. 2010-12-08 10:45:14 -08:00
Ali Saidi
cdacbe734a ARM/Alpha/Cpu: Change prefetchs to be more like normal loads.
This change modifies the way prefetches work. They are now like normal loads
that don't writeback a register. Previously prefetches were supposed to call
prefetch() on the exection context, so they executed with execute() methods
instead of initiateAcc() completeAcc(). The prefetch() methods for all the CPUs
are blank, meaning that they get executed, but don't actually do anything.

On Alpha dead cache copy code was removed and prefetches are now normal ops.
They count as executed operations, but still don't do anything and IsMemRef is
not longer set on them.

On ARM IsDataPrefetch or IsInstructionPreftech is now set on all prefetch
instructions. The timing simple CPU doesn't try to do anything special for
prefetches now and they execute with the normal memory code path.
2010-11-08 13:58:22 -06:00
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
29676286c8 ISA: Simplify various implementations of completeAcc. 2010-10-22 00:23:19 -07:00
Gabe Black
b289966a78 Mem: Reclaim some request flags used by MIPS for alignment checking.
These flags were being used to identify what alignment a request needed, but
the same information is available using the request size. This change also
eliminates the isMisaligned function. If more complicated alignment checks are
needed, they can be signaled using the ASI_BITS space in the flags vector like
is currently done with ARM.
2010-10-16 00:00:54 -07:00
Steve Reinhardt
4d77ea7a57 cpu: fix exec tracing memory corruption bug
Accessing traceData (to call setAddress() and/or setData())
after initiating a timing translation was causing crashes,
since a failed translation could delete the traceData
object before returning.

It turns out that there was never a need to access traceData
after initiating the translation, as the traced data was
always available earlier; this ordering was merely
historical.  Furthermore, traceData->setAddress() and
traceData->setData() were being called both from the CPU
model and the ISA definition, often redundantly.

This patch standardizes all setAddress and setData calls
for memory instructions to be in the CPU models and not
in the ISA definition.  It also moves those calls above
the translation calls to eliminate the crashes.
2010-03-23 08:50:57 -07:00
Gabe Black
ecaa7070e6 MIPS: Implement the SE mode version of rdhwr. 2009-12-31 15:30:51 -05:00
Gabe Black
c70f3c93af MIPS: Fix decoding of the rdhwr instruction. 2009-12-31 15:30:51 -05:00
Gabe Black
d3ed32b989 MIPS: Create an artificial control register to hold the thread pointer.
In Linux, the set_thread_area system call stores the address of the thread
local storage area into a field of the current thread_info structure. Later,
to access that value, the program uses the rdhwr instruction to read a
"hardware register" with index 29. The 64 bit MIPS manual, volume II, says
that index 29 is reserved for a future ABI extension and should cause a
"Reserved Instruction Exception". In Linux (and potentially other ISAs) that
exception is trapped and emulated to return the value stored by
set_thread_area as if that were actually stored by a physical register.

The tp_value address (as named in the Linux kernel) is ironically stored as a
control register so that it goes with a particular ThreadContext. Syscall
emulation will use that to emulate storing to the OS's thread info structure,
and rdhwr will emulate faulting and returning that value from software by
returning the value itself, as if it was in hardware. In other words, we fake
faking the register in SE mode. In an FS mode implementation it should
work as specified in the manual.
2009-12-31 15:30:50 -05:00
Gabe Black
b8120f6c38 Mem: Eliminate the NO_FAULT request flag. 2009-11-10 21:10:18 -08:00
Gabe Black
9ba2ed8532 MIPS: Small fix I forgot to qrefresh into my last change. 2009-07-22 01:57:55 -07:00
Gabe Black
7f0c07bf03 MIPS: Style/formatting sweep of the decoder itself. 2009-07-22 01:51:10 -07:00
Gabe Black
c874bfae3f MIPS: Format the register index constants like the other ISAs.
Also a few more style fixes.
2009-07-21 23:38:26 -07:00
Gabe Black
74584d79b6 MIPS: Get MIPS_FS to compile, more style fixes.
Some breakage was from my BitUnion change, some was much older.
2009-07-21 01:09:05 -07:00
Gabe Black
5161bc19d9 MIPS: Use BitUnions instead of bits() functions and constants.
Also fix style issues in regions around these changes.
2009-07-20 20:14:15 -07:00
Gabe Black
60577eb4ca ISAs: Get rid of the IControl operand type.
A separate operand type is not necessary to use two bitfields to generate the
index.
2009-07-10 01:21:04 -07:00
Gabe Black
de7f462219 MIPS: Fold the MiscRegFile all the way into the ISA object. 2009-07-09 20:28:39 -07:00
Gabe Black
25884a8773 Registers: Get rid of the float register width parameter. 2009-07-08 23:02:20 -07:00
Korey Sewell
1f4c954590 inorder-mips: Remove eaComp & memAcc; use 'visible' eaComp
Inorder expects eaComp to be visible through StaticInst object. This mirrors a similar change
to ALPHA... Needs to be done for SPARC and whatever other ISAs want to use InOrderCPU
2009-05-13 01:26:46 -04:00
Gabe Black
3e5f487663 Memory: Rename LOCKED for load locked store conditional to LLSC. 2009-04-19 04:25:01 -07:00
Korey Sewell
e501e1af54 mips-syscall: mark with correct flag. \nMIPS was using wrong serialization flag on syscall instructions allowing O3 to handle SE mode syscalls incorrectly and speculate on instructions after a syscall 2009-04-18 10:42:29 -04:00
Korey Sewell
5c1742b822 o3-delay-slot-bpred: fix decode stage handling of uncdtl. branches.\n decode stage was not setting the predicted PC correctly or passing that information back to fetch correctly 2009-04-18 10:42:29 -04:00
Nathan Binkert
5711282f87 Fix a bunch of bugs I introduced when I changed the flags stuff for packets.
I did some of the flags and assertions wrong. Thanks to Brad Beckmann
for pointing this out.  I should have run the opt regressions instead
of the fast. I also screwed up some of the logical functions in the Flags
class.
2008-11-14 04:55:30 -08:00
Nathan Binkert
9c49bc7b00 mem: update stuff for changes to Packet and Request 2008-11-10 11:51:17 -08:00
Lisa Hsu
dd99ff23c6 get rid of all instances of readTid() and getThreadNum(). Unify and eliminate
redundancies with threadId() as their replacement.
2008-11-04 11:35:42 -05:00
Korey Sewell
6c046a28dc fix shadow set bugs in MIPS code that caused out of bounds access...
panic rdpgpr/wrpgpr instructions until a better impl.
of MIPS shadow sets is available.
2008-10-06 02:07:04 -04:00
Nathan Binkert
80d9be86e6 gcc: Add extra parens to quell warnings.
Even though we're not incorrect about operator precedence, let's add
some parens in some particularly confusing places to placate GCC 4.3
so that we don't have to turn the warning off.  Agreed that this is a
bit of a pain for those users who get the order of operations correct,
but it is likely to prevent bugs in certain cases.
2008-09-27 21:03:49 -07:00
Korey Sewell
5d23f86e98 add back in clobbered MIPS fix for g++ 4.2
--HG--
extra : convert_revision : 80ad1cc32c6e59925526abd274132e4f9e35f0c1
2007-11-17 00:02:56 -05:00
Korey Sewell
f2fea63c65 go back and fix up MIPS copyright headers
--HG--
extra : convert_revision : 886e762e13b7a05d6d8a14bde6c2a3567c32a4d1
2007-11-16 21:32:22 -05:00
Korey Sewell
3110b157e6 fix MIPS headers
--HG--
extra : convert_revision : 2870a146a1be0e8c80878090f39c0eaa15d2eb13
2007-11-15 14:21:01 -05:00
Korey Sewell
789153dff6 Get MIPS simple regression working. Take out unecessary functions "setShadowSet", "CacheOp"
--HG--
extra : convert_revision : a9ae8a7e62c27c2db16fd3cfa7a7f0bf5f0bf8ea
2007-11-15 03:10:41 -05:00
Korey Sewell
5f7879a935 Get MIPS_SE actually working again by actually by fixing TLB stuff and running hello world
--HG--
extra : convert_revision : 0944e7661934baddca1f1a895af0b75be2d96b10
2007-11-14 06:24:47 -05:00
Korey Sewell
2692590049 Add in files from merge-bare-iron, get them compiling in FS and SE mode
--HG--
extra : convert_revision : d4e19afda897bc3797868b40469ce2ec7ec7d251
2007-11-13 16:58:16 -05:00
Steve Reinhardt
4b49bd47f4 String constant const-ness changes to placate g++ 4.2.
Also some bug fixes in MIPS ISA uncovered by g++ warnings
(Python string compares don't work in C++!).

--HG--
extra : convert_revision : b347cc0108f23890e9b73b3ee96059f0cea96cf6
2007-10-31 18:04:22 -07:00
Gabe Black
239d124e83 MIPS: Cleaned up includes to break loops, and got rid of isa_traits.cc
Loops of header files including each other was causing compilation to fail. To fix it, a bunch of unnecessary includes were removed, and the code in isa_traits.cc which brought a bunch of include chains together was broken up and put in proximity to the header files that delcared it.

--HG--
extra : convert_revision : 66ef7762024b72bb91147a5589a0779e279521e0
2007-08-01 13:55:47 -07:00
Gabe Black
4bdabe1254 Add a flag to indicate an instruction triggers a syscall in SE mode.
--HG--
extra : convert_revision : 1d0b3afdd8254f5b2fb4bbff1fa4a0536f78bb06
2007-07-31 17:34:08 -07:00
Korey Sewell
738ecc495b fix store instructions, pass fast/quick Atomic/TimingSimpleCPU regressions...
src/arch/mips/isa/decoder.isa:
    commment out deret instruction for now...
src/arch/mips/isa/formats/fp.isa:
    edit fp format
src/arch/mips/isa/formats/mem.isa:
    fix for basic store instructions

--HG--
extra : convert_revision : 30cb5a474e78ac9292b6ab37d433db947a177731
2007-06-29 15:13:50 -04:00
Korey Sewell
e28cbc98a0 o3cpu build for mips
--HG--
extra : convert_revision : 2c0be7a8c0a54ba5b1b2b69468f788d20abc8452
2007-06-28 05:30:46 -04:00
Korey Sewell
753adb38d5 mips import pt. 1
src/arch/mips/SConscript:
    "mips import pt.1".

--HG--
extra : convert_revision : 2e393341938bebf32fb638a209262d074fad4cc1
2007-06-22 19:03:42 -04:00
Ali Saidi
689cab36c9 *MiscReg->*MiscRegNoEffect, *MiscRegWithEffect->*MiscReg
--HG--
extra : convert_revision : f799b65f1b2a6bf43605e6870b0f39b473dc492b
2007-03-07 15:04:31 -05:00
Steve Reinhardt
f55fd68f88 Update MIPS ISA description to work with new write result interface
for store conditional.

--HG--
extra : convert_revision : 73efd2ca17994e0e19c08746441874a2ac8183af
2007-02-13 08:09:09 -08:00
Ali Saidi
ca5cd68df4 fix compiling problems
--HG--
extra : convert_revision : 9ecfd5a0a151c03503e42faf98240da12fd719b1
2007-02-13 10:07:50 -05:00