Commit graph

125 commits

Author SHA1 Message Date
Gabe Black
ea8b347dc5 Merge with head, hopefully the last time for this batch. 2012-01-31 22:40:08 -08:00
Koan-Sin Tan
7d4f187700 clang: Enable compiling gem5 using clang 2.9 and 3.0
This patch adds the necessary flags to the SConstruct and SConscript
files for compiling using clang 2.9 and later (on Ubuntu et al and OSX
XCode 4.2), and also cleans up a bunch of compiler warnings found by
clang. Most of the warnings are related to hidden virtual functions,
comparisons with unsigneds >= 0, and if-statements with empty
bodies. A number of mismatches between struct and class are also
fixed. clang 2.8 is not working as it has problems with class names
that occur in multiple namespaces (e.g. Statistics in
kernel_stats.hh).

clang has a bug (http://llvm.org/bugs/show_bug.cgi?id=7247) which
causes confusion between the container std::set and the function
Packet::set, and this is currently addressed by not including the
entire namespace std, but rather selecting e.g. "using std::vector" in
the appropriate places.
2012-01-31 12:05:52 -05:00
Gabe Black
239b33e016 SE/FS: Get rid of FULL_SYSTEM in the ARM ISA. 2011-11-02 01:25:15 -07:00
Gabe Black
49a7ed0397 StaticInst: Merge StaticInst and StaticInstBase.
Having two StaticInst classes, one nominally ISA dependent and the other ISA
dependent, has not been historically useful and makes the StaticInst class
more complicated that it needs to be. This change merges StaticInstBase into
StaticInst.
2011-09-09 02:40:11 -07:00
Nathan Binkert
39a055645f includes: sort all includes 2011-04-15 10:44:06 -07:00
Ali Saidi
6fd271ffb3 ARM: Remove debugging warn that was accidently left in. 2011-04-04 11:42:23 -05:00
Ali Saidi
53ab306acc ARM: Fix subtle bug in LDM.
If the instruction faults mid-op the base register shouldn't be written back.
2011-03-17 19:20:20 -05:00
Ali Saidi
5480ec798a ARM: Identify branches as conditional or unconditional and direct or indirect. 2011-03-17 19:20:20 -05:00
Matt Horsnell
031f396c71 ARM: Fix RFE macrop.
This changes the RFE macroop into 3 microops:

URa = [sp]; URb = [sp+4]; // load CPSR,PC values from stack
sp = sp + offset;         // optionally auto-increment
PC = URa; CPSR = URb;     // write to the PC and CPSR.

Importantly:
- writing to PC is handled in the last micro-op.
- loading occurs prior to state changes.
2011-03-17 19:20:19 -05:00
Matt Horsnell
adbd84ab9f ARM: The ARM decoder should not panic when decoding undefined holes is arch.
This can abort simulations when the fetch unit runs ahead and speculatively
decodes instructions that are off the execution path.
2011-01-18 16:30:05 -06:00
Ali Saidi
a3232b534b ARM: fix mismatched new/delete. 2011-01-18 16:30:01 -06:00
Ali Saidi
08c5673d56 ARM: Use the correct delete operator for RFE 2010-11-15 14:04:03 -06:00
Ali Saidi
f4f5d03ed2 ARM: Make all ARM uops delayed commit. 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
Ali Saidi
b331b02669 ARM: Clean up use of TBit and JBit.
Rather tha constantly using ULL(1) << PcXBitShift define those directly.
Additionally, add some helper functions to further clean up the code.
2010-10-01 16:02:45 -05:00
Gene WU
4d8f4db8d1 ARM: Use fewer micro-ops for register update loads if possible.
Allow some loads that update the base register to use just two micro-ops. three
micro-ops are only used if the destination register matches the offset register
or the PC is the destination regsiter. If the PC is updated it needs to be
the last micro-op otherwise O3 will mispredict.
2010-08-25 19:10:42 -05:00
Gabe Black
54a919f225 ARM: Implement CPACR register and return Undefined Instruction when FP access is disabled. 2010-08-25 19:10:42 -05:00
Gabe Black
6368edb281 ARM: Implement all ARM SIMD instructions. 2010-08-25 19:10:42 -05:00
Min Kyu Jeong
e6a0be648e ARM: Improve printing of uop disassembly. 2010-08-23 11:18:42 -05:00
Gabe Black
e50e6a260f ARM: Add a comment to vfp.cc that explains the asm statements. 2010-06-02 12:58:18 -05:00
Gabe Black
fcee2b3f31 ARM: Add comments to the classes in macromem.hh. 2010-06-02 12:58:18 -05:00
Gabe Black
362b747fdc ARM: Move code from vfp.hh to vfp.cc. 2010-06-02 12:58:18 -05:00
Ali Saidi
35e35fc825 ARM: Make some of the trace code more compact 2010-06-02 12:58:18 -05:00
Gabe Black
0abec53564 ARM: Move the longer MemoryReg::printoffset function in mem.hh into the cc file. 2010-06-02 12:58:18 -05:00
Gabe Black
b6c2548a27 ARM: Get rid of the binary dumping function in utility.hh. 2010-06-02 12:58:17 -05:00
Gabe Black
f8d2ed708b ARM: Get rid of the empty branch.cc. 2010-06-02 12:58:17 -05:00
Gabe Black
0c574987c8 ARM: Mark some ARM static inst functions as inline. 2010-06-02 12:58:17 -05:00
Gabe Black
358fdc2a40 ARM: Decode to specialized conditional/unconditional versions of instructions.
This is to avoid condition code based dependences from effectively serializing
instructions when the instruction doesn't actually use them.
2010-06-02 12:58:17 -05:00
Gabe Black
e9c8f68c0f ARM: Make undefined instructions obey predication. 2010-06-02 12:58:16 -05:00
Ali Saidi
b8ec214553 ARM: Implement ARM CPU interrupts 2010-06-02 12:58:16 -05:00
Gabe Black
237c0617a0 ARM: Implement conversion to/from half precision. 2010-06-02 12:58:16 -05:00
Gabe Black
04e196f422 ARM: Clean up VFP 2010-06-02 12:58:16 -05:00
Gabe Black
0fe0390f73 ARM: Clean up the implementation of the VFP instructions. 2010-06-02 12:58:16 -05:00
Gabe Black
c919ab5b4f ARM: Fix double precision load/store multiple decrement.
When decrementing, the higher addressed half of a double word is at a 4 byte
smaller displacement.
2010-06-02 12:58:15 -05:00
Gabe Black
23ba9c7b96 ARM: Fix vcvtr so that it uses the rounding mode in the FPSCR. 2010-06-02 12:58:15 -05:00
Gabe Black
347ab6c704 ARM: Compensate for ARM's underflow coming from -before- rounding, but x86's after. 2010-06-02 12:58:15 -05:00
Gabe Black
fd82a47b96 ARM: Implement flush to zero for destinations as well. 2010-06-02 12:58:15 -05:00
Gabe Black
186273e5f3 ARM: Fix up nans to match ARM's expected behavior. 2010-06-02 12:58:15 -05:00
Gabe Black
8466999aef ARM: Implement flush to zero mode for VFP, and clean up some corner cases. 2010-06-02 12:58:15 -05:00
Gabe Black
efbceff96a ARM: Add barriers that make sure FP operations happen where they're supposed to. 2010-06-02 12:58:15 -05:00
Gabe Black
aa05e5401c ARM: Implement the floating/fixed point VCVT instructions. 2010-06-02 12:58:15 -05:00
Gabe Black
86a1093992 ARM: Add code to extract and record VFP exceptions. 2010-06-02 12:58:14 -05:00
Gabe Black
c1f7bf7f0e ARM: Add support for VFP vector mode. 2010-06-02 12:58:14 -05:00
Gabe Black
f245f4937b ARM: Introduce new VFP base classes that are optionally microops. 2010-06-02 12:58:14 -05:00
Gabe Black
65f5204325 ARM: Implement the VFP version of vmul. 2010-06-02 12:58:14 -05:00
Gabe Black
1fcd389fa3 ARM: Make sure macroops aren't interrupted midinstruction.
Do this by setting the delayed commit flag for all but the last microop.
2010-06-02 12:58:12 -05:00
Gabe Black
67766cbf17 ARM: Fix the implementation of the VFP ldm and stm macroops.
There were four bugs in these instructions. First, the loaded value was being
stored into a floating point register as floating point, changing the value as
it was transfered. Second, the meaning of the "up" bit had been reversed.
Third, the statically sized microop array wasn't bit enough for all possible
inputs. It's now dynamically sized and should always be big enough. Fourth,
the offset was stored as an unsigned 8 bit value. Negative offsets would look
like moderately large positive offsets.
2010-06-02 12:58:12 -05:00
Gabe Black
1f059541d6 ARM: Add a new RegImmOp base class. 2010-06-02 12:58:12 -05:00
Gabe Black
6976b4890a ARM: Add a RegRegImmOp base class. 2010-06-02 12:58:12 -05:00
Gabe Black
186cfe3ae3 ARM: Widen the immediate fields in the misc instruction classes. 2010-06-02 12:58:12 -05:00