Ali Saidi [Fri, 1 Oct 2010 21:04:04 +0000 (16:04 -0500)]
ARM: Make the TLB a little bit faster by moving most recently used items to front of list
Ali Saidi [Fri, 1 Oct 2010 21:04:02 +0000 (16:04 -0500)]
ARM: Add a fake flash controller so that unmodified linux can boot
With this change an unmodified Linux kernel can boot in M5.
Prakash Ramrakhyani [Fri, 1 Oct 2010 21:04:00 +0000 (16:04 -0500)]
ARM: Fix some subtle bugs in the GIC
The GIC code can write to the registers with 8, 16, or 32 byte
accesses which could set/clear different numbers of interrupts.
Ali Saidi [Fri, 1 Oct 2010 21:03:27 +0000 (16:03 -0500)]
ARM: Implement functional virtual to physical address translation
for debugging and program introspection.
Ali Saidi [Fri, 1 Oct 2010 21:02:46 +0000 (16:02 -0500)]
Debug: Implement getArgument() and function skipping for ARM.
In the process make add skipFuction() to handle isa specific function skipping
instead of ifdefs and other ugliness. For almost all ABIs, 64 bit arguments can
only start in even registers. Size is now passed to getArgument() so that 32
bit systems can make decisions about register selection for 64 bit arguments.
The number argument is now passed by reference because getArgument() will need
to change it based on the size of the argument and the current argument number.
For ARM, if the argument number is odd and a 64-bit register is requested the
number must first be incremented to because all 64 bit arguments are passed
in an even argument register. Then the number will be incremented again to
access both halves of the argument.
Ali Saidi [Fri, 1 Oct 2010 21:02:45 +0000 (16:02 -0500)]
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.
Ali Saidi [Thu, 30 Sep 2010 14:35:19 +0000 (09:35 -0500)]
CPU/Cache: Fix some errors exposed by valgrind
Gabe Black [Wed, 29 Sep 2010 18:31:03 +0000 (11:31 -0700)]
X86: Fix the RIP relative versions of the BT, BTC, BTR, and BTS instructions.
Steve Reinhardt [Wed, 22 Sep 2010 15:45:35 +0000 (08:45 -0700)]
python: get rid of internal.enums package.
Move generated enums into internal.params, which gets
imported into object.params, restoring backward
compatibility for scripts that expect to find them there.
Steve Reinhardt [Wed, 22 Sep 2010 06:07:35 +0000 (23:07 -0700)]
stats: update stats for previous cset
Coherence protocol change basically got rid
of UpgradeReqs in L2 caches, other minor
related cache stat changes.
Steve Reinhardt [Wed, 22 Sep 2010 06:07:34 +0000 (23:07 -0700)]
cache: improve coherence handling of writebacks
If we write back an exclusive copy, we now mark it
as such, so the cache receiving the writeback can
mark its copy as exclusive. This avoids some
unnecessary upgrade requests when a cache later
tries to re-acquire exclusive access to the block.
Steve Reinhardt [Wed, 22 Sep 2010 06:07:34 +0000 (23:07 -0700)]
diff-out: clean up options
Make diff-out sort stats changes by percentage
by default, with '-a' to use current alpha sort
(instead of requiring '-p' to sort by percentage).
Other minor options cleanup too.
Steve Reinhardt [Wed, 22 Sep 2010 06:07:34 +0000 (23:07 -0700)]
tests: print if output files match
Add '-s' flag to diff command generating outdiff
file so we have positive confirmation when
outputs match.
Gabe Black [Mon, 20 Sep 2010 09:46:42 +0000 (02:46 -0700)]
CPU: Fix O3 and possible InOrder segfaults in FS.
Steve Reinhardt [Fri, 17 Sep 2010 03:24:05 +0000 (20:24 -0700)]
devices: undo cset
017baf09599f that added timer drain functions.
It's not the right fix for the checkpoint deadlock problem
Brad was having, and creates another bug where the system can
deadlock on restore. Brad can't reproduce the original bug
right now, so we'll wait until it arises again and then try
to fix it the right way then.
Gabe Black [Tue, 14 Sep 2010 19:31:37 +0000 (12:31 -0700)]
X86: Make the halt microop non-speculative.
Executing this microop makes the CPU halt even if it was misspeculated.
Gabe Black [Tue, 14 Sep 2010 19:27:30 +0000 (12:27 -0700)]
X86: Make unrecognized instructions behave better in x86.
Gabe Black [Tue, 14 Sep 2010 07:29:38 +0000 (00:29 -0700)]
CPU: Trim unnecessary includes from some common files.
This reduces the scope of those includes and makes it less likely for there to
be a dependency loop. This also moves the hashing functions associated with
ExtMachInst objects to be with the ExtMachInst definitions and out of
utility.hh.
Gabe Black [Tue, 14 Sep 2010 04:58:34 +0000 (21:58 -0700)]
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.
Gabe Black [Tue, 14 Sep 2010 02:26:03 +0000 (19:26 -0700)]
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.
Nathan Binkert [Sun, 12 Sep 2010 22:41:34 +0000 (15:41 -0700)]
swig: make all generated files go into the m5.internal package
This is necessary because versions of swig older than 1.3.39 fail to
do the right thing and try to do relative imports for everything (even
with the package= option to %module). Instead of putting params in
the m5.internal.params package, put params in the m5.internal package
and make all param modules start with param_. Same thing for
m5.internal.enums.
Also, stop importing all generated params into m5.objects. They are
not necessary and now with everything using relative imports we wound
up with pollution of the namespace (where builtin-range got overridden).
--HG--
rename : src/python/m5/internal/enums/__init__.py => src/python/m5/internal/enums.py
rename : src/python/m5/internal/params/__init__.py => src/python/m5/internal/params.py
Nathan Binkert [Fri, 10 Sep 2010 21:58:04 +0000 (14:58 -0700)]
style: fix sorting of includes and whitespace in some files
Nathan Binkert [Thu, 9 Sep 2010 21:26:29 +0000 (14:26 -0700)]
scons: Stop building the big monolithic swigged params module
kill params.i and create a separate .i for each object (param, enums, etc.)
Nathan Binkert [Thu, 9 Sep 2010 21:15:42 +0000 (14:15 -0700)]
init: don't build files that centralize python and swig code
Instead of putting all object files into m5/object/__init__.py, interrogate
the importer to find out what should be imported.
Instead of creating a single file that lists all of the embedded python
modules, use static object construction to put those objects onto a list.
Do something similar for embedded swig (C++) code.
Nathan Binkert [Thu, 9 Sep 2010 21:15:41 +0000 (14:15 -0700)]
scons: use code_formatter wherever we can in the build system
Nathan Binkert [Thu, 9 Sep 2010 21:15:41 +0000 (14:15 -0700)]
code_formatter: make it easier to insert whitespace
a newline by just doing "code()". indent() and dedent() now take a
"count" parameter to indent/dedent multiple levels.
Nathan Binkert [Thu, 9 Sep 2010 21:15:40 +0000 (14:15 -0700)]
swig: don't override SWIG_name anymore
It doesn't appear to be necessary and it is somewhat odd. I'm pretty
sure that the package parameter to %module does whatever this might
have been before. It's necessary in future revisions anyway.
Steve Reinhardt [Thu, 9 Sep 2010 18:40:19 +0000 (14:40 -0400)]
stats: update stats for preceding coherence changes
Because the handling of the E state for multilevel caches
has changed, stats are affected for any non-ruby config
with caches, even uniprocessor simple CPU.
Steve Reinhardt [Thu, 9 Sep 2010 18:40:19 +0000 (14:40 -0400)]
cache: fail SC when invalidated while waiting for bus
Corrects an oversight in cset
f97b62be544f. The fix there only
failed queued SCUpgradeReq packets that encountered an
invalidation, which meant that the upgrade had to reach the L2
cache. To handle pending requests in the L1 we must similarly
fail StoreCondReq packets too.
Steve Reinhardt [Thu, 9 Sep 2010 18:40:19 +0000 (14:40 -0400)]
mem: fix functional accesses to deal with coherence change
We can't just obliviously return the first valid cache block
we find any more... see comments for details.
Steve Reinhardt [Thu, 9 Sep 2010 18:40:18 +0000 (14:40 -0400)]
cache: coherence protocol enhancements & bug fixes
Allow lower-level caches (e.g., L2 or L3) to pass exclusive
copies to higher levels (e.g., L1). This eliminates a lot
of unnecessary upgrade transactions on read-write sequences
to non-shared data.
Also some cleanup of MSHR coherence handling and multiple
bug fixes.
Gabe Black [Tue, 31 Aug 2010 16:50:49 +0000 (09:50 -0700)]
ARM: Get rid of the checkFpEnableFault function in ARM.
Gabe Black [Tue, 31 Aug 2010 16:48:05 +0000 (09:48 -0700)]
Alpha: Alpha's mt.hh was including mips header files.
Gabe Black [Tue, 31 Aug 2010 16:47:29 +0000 (09:47 -0700)]
CPU: Get rid of the unused ev5_trap function on the simple and checker CPUs.
Brad Beckmann [Mon, 30 Aug 2010 22:26:51 +0000 (15:26 -0700)]
config: fixed numa high bit setting bug
Brad Beckmann [Mon, 30 Aug 2010 19:07:21 +0000 (12:07 -0700)]
config: minor fix to probe filter index setting
Nathan Binkert [Sun, 29 Aug 2010 14:02:42 +0000 (07:02 -0700)]
ruby: None, not none
Gabe Black [Fri, 27 Aug 2010 22:35:36 +0000 (15:35 -0700)]
X86: Change the copyright holder to AMD.
I accidentally left myself as a placeholder copyright holder on this file when
I checked it in. Copyright should be assigned to AMD.
Steve Reinhardt [Thu, 26 Aug 2010 15:03:20 +0000 (08:03 -0700)]
mem: fix m5.fast compile bug in previous cset
Steve Reinhardt [Thu, 26 Aug 2010 04:55:55 +0000 (21:55 -0700)]
cache: fix a bug in atomic multilevel snoops
Steve Reinhardt [Thu, 26 Aug 2010 04:55:44 +0000 (21:55 -0700)]
memtest: fix/cleanup functional access testing
Don't assert that the response packet is marked as a response
since it won't always be so for functional accesses.
Also cleanup code to refer to functional accesses rather
than "probes" (old terminology), and mention in the
DPRINTF which type of access we're doing.
Steve Reinhardt [Thu, 26 Aug 2010 04:55:42 +0000 (21:55 -0700)]
memtest: scale associativity and mshrs according to config
Use the actual fanouts in the tree specification to scale
cache associativity and mshrs instead of dumb constants.
Ali Saidi [Thu, 26 Aug 2010 00:10:43 +0000 (19:10 -0500)]
CPU: Print out traces for faluting inst when the flag ExecFaulting is set
Min Kyu Jeong [Thu, 26 Aug 2010 00:10:43 +0000 (19:10 -0500)]
ARM: Support unaligned memory access.
Without this flag set, page-crossing requests were not split into two mem
request.
Depending on the alignment bit in the SCTLR, misaligned access could
raise a fault. However it seems unnecessary to implement that.
Gene WU [Thu, 26 Aug 2010 00:10:43 +0000 (19:10 -0500)]
ARM: Seperate the queues of L1 and L2 walker states.
Min Kyu Jeong [Thu, 26 Aug 2010 00:10:43 +0000 (19:10 -0500)]
ARM: Adding a bogus fault that does nothing.
This fault can used to flush the pipe, not including the faulting instruction.
The particular case I needed this was for a self-modifying code. It needed to
drain the store queue and force the following instruction to refetch from
icache. DCCMVAC cp15 mcr instruction is modified to raise this fault.
William Wang [Thu, 26 Aug 2010 00:10:43 +0000 (19:10 -0500)]
ARM: Remove ALPHA KSeg functions.
These were erronously copied years ago into the ARM directory.
Ali Saidi [Thu, 26 Aug 2010 00:10:43 +0000 (19:10 -0500)]
ARM: Limited implementation of dprintk.
Does not work with vfp arguments or arguments passed on the stack.
Min Kyu Jeong [Thu, 26 Aug 2010 00:10:43 +0000 (19:10 -0500)]
ARM: Fixed register flattening logic (FP_Base_DepTag was set too low)
When decoding a srs instruction, invalid mode encoding returns invalid instruction.
This can happen when garbage instructions are fetched from mispredicted path
Ali Saidi [Thu, 26 Aug 2010 00:10:43 +0000 (19:10 -0500)]
ARM: Make VMSR, RFE PC/LR etc non speculative, and serializing
Ali Saidi [Thu, 26 Aug 2010 00:10:42 +0000 (19:10 -0500)]
ARM: Update regression tests for ldr/str microcode changes.
Gene WU [Thu, 26 Aug 2010 00:10:42 +0000 (19:10 -0500)]
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.
Ali Saidi [Thu, 26 Aug 2010 00:10:42 +0000 (19:10 -0500)]
ARM: Set the high bits in the part number so it's considered new by some code.
Ali Saidi [Thu, 26 Aug 2010 00:10:42 +0000 (19:10 -0500)]
ARM: Fix VFP enabled checks for mem instructions
Gabe Black [Thu, 26 Aug 2010 00:10:42 +0000 (19:10 -0500)]
ARM: Seperate out the renamable bits in the FPSCR.
Gabe Black [Thu, 26 Aug 2010 00:10:42 +0000 (19:10 -0500)]
ARM: Eliminate some unused enums.
Gabe Black [Thu, 26 Aug 2010 00:10:42 +0000 (19:10 -0500)]
ARM: Fix type comparison warnings in Neon.
Gabe Black [Thu, 26 Aug 2010 00:10:42 +0000 (19:10 -0500)]
ARM: Implement CPACR register and return Undefined Instruction when FP access is disabled.
Gabe Black [Thu, 26 Aug 2010 00:10:42 +0000 (19:10 -0500)]
ARM: Implement all ARM SIMD instructions.
Gabe Black [Thu, 26 Aug 2010 00:10:41 +0000 (19:10 -0500)]
ARM: Expand the mode checking utility functions.
inUserMode now can take either a threadcontext or a CPSR value directly. If
given a thread context it just extracts the CPSR and calls the other version.
An inPrivelegedMode function was also implemented which just returns the
opposite of inUserMode.
Ali Saidi [Thu, 26 Aug 2010 00:10:41 +0000 (19:10 -0500)]
Tracing: Fix trace so 'Predicated False' doesn't show up
Steve Reinhardt [Wed, 25 Aug 2010 21:08:27 +0000 (14:08 -0700)]
mem: fix dumb typo in copyrights
Brad Beckmann [Tue, 24 Aug 2010 21:08:23 +0000 (14:08 -0700)]
config: changed ruby config file names to be consistent
Brad Beckmann [Tue, 24 Aug 2010 20:20:32 +0000 (13:20 -0700)]
config: remove ruby's requirement on the timing cmd line param
Since ruby only works in timing mode, explicitly requiring the timing cmd line
param to be specified is not necessary.
Brad Beckmann [Tue, 24 Aug 2010 20:20:31 +0000 (13:20 -0700)]
config: fixed ruby dma device connections
Brad Beckmann [Tue, 24 Aug 2010 19:07:22 +0000 (12:07 -0700)]
testers: move testers to a new directory
This patch moves the testers to a new subdirectory under src/cpu and includes
the necessary fixes to work with latest m5 initialization patches.
--HG--
rename : configs/example/determ_test.py => configs/example/ruby_direct_test.py
rename : src/cpu/directedtest/DirectedGenerator.cc => src/cpu/testers/directedtest/DirectedGenerator.cc
rename : src/cpu/directedtest/DirectedGenerator.hh => src/cpu/testers/directedtest/DirectedGenerator.hh
rename : src/cpu/directedtest/InvalidateGenerator.cc => src/cpu/testers/directedtest/InvalidateGenerator.cc
rename : src/cpu/directedtest/InvalidateGenerator.hh => src/cpu/testers/directedtest/InvalidateGenerator.hh
rename : src/cpu/directedtest/RubyDirectedTester.cc => src/cpu/testers/directedtest/RubyDirectedTester.cc
rename : src/cpu/directedtest/RubyDirectedTester.hh => src/cpu/testers/directedtest/RubyDirectedTester.hh
rename : src/cpu/directedtest/RubyDirectedTester.py => src/cpu/testers/directedtest/RubyDirectedTester.py
rename : src/cpu/directedtest/SConscript => src/cpu/testers/directedtest/SConscript
rename : src/cpu/directedtest/SeriesRequestGenerator.cc => src/cpu/testers/directedtest/SeriesRequestGenerator.cc
rename : src/cpu/directedtest/SeriesRequestGenerator.hh => src/cpu/testers/directedtest/SeriesRequestGenerator.hh
rename : src/cpu/memtest/MemTest.py => src/cpu/testers/memtest/MemTest.py
rename : src/cpu/memtest/SConscript => src/cpu/testers/memtest/SConscript
rename : src/cpu/memtest/memtest.cc => src/cpu/testers/memtest/memtest.cc
rename : src/cpu/memtest/memtest.hh => src/cpu/testers/memtest/memtest.hh
rename : src/cpu/rubytest/Check.cc => src/cpu/testers/rubytest/Check.cc
rename : src/cpu/rubytest/Check.hh => src/cpu/testers/rubytest/Check.hh
rename : src/cpu/rubytest/CheckTable.cc => src/cpu/testers/rubytest/CheckTable.cc
rename : src/cpu/rubytest/CheckTable.hh => src/cpu/testers/rubytest/CheckTable.hh
rename : src/cpu/rubytest/RubyTester.cc => src/cpu/testers/rubytest/RubyTester.cc
rename : src/cpu/rubytest/RubyTester.hh => src/cpu/testers/rubytest/RubyTester.hh
rename : src/cpu/rubytest/RubyTester.py => src/cpu/testers/rubytest/RubyTester.py
rename : src/cpu/rubytest/SConscript => src/cpu/testers/rubytest/SConscript
Brad Beckmann [Tue, 24 Aug 2010 19:06:53 +0000 (12:06 -0700)]
MOESI_hammer: fixed bug for dma reads in single cpu systems
Gabe Black [Mon, 23 Aug 2010 23:23:47 +0000 (16:23 -0700)]
Faults: Get rid of some commented out code in sim/faults.hh.
Gabe Black [Mon, 23 Aug 2010 23:14:24 +0000 (16:14 -0700)]
X86: Create a directory for files that define register indexes.
This is to help tidy up arch/x86. These files should not be used external to
the ISA.
--HG--
rename : src/arch/x86/apicregs.hh => src/arch/x86/regs/apic.hh
rename : src/arch/x86/floatregs.hh => src/arch/x86/regs/float.hh
rename : src/arch/x86/intregs.hh => src/arch/x86/regs/int.hh
rename : src/arch/x86/miscregs.hh => src/arch/x86/regs/misc.hh
rename : src/arch/x86/segmentregs.hh => src/arch/x86/regs/segment.hh
Gabe Black [Mon, 23 Aug 2010 23:14:23 +0000 (16:14 -0700)]
Power: Get rid of unused checkFpEnableFault.
This function was brought in from another ISA and doesn't actually do anything
or get used.
Gabe Black [Mon, 23 Aug 2010 23:14:20 +0000 (16:14 -0700)]
ISA: Get rid of old, unused utility functions cluttering up the ISAs.
Gabe Black [Mon, 23 Aug 2010 16:44:19 +0000 (09:44 -0700)]
X86: Get rid of the flagless microop constructor.
This will reduce clutter in the source and hopefully speed up compilation.
Gabe Black [Mon, 23 Aug 2010 16:44:19 +0000 (09:44 -0700)]
X86: Make the TLB fault instead of panic when something is unmapped in SE mode.
The fault object, if invoked, would then panic. This is a bit less direct, but
it means speculative execution won't panic the simulator.
Gabe Black [Mon, 23 Aug 2010 16:44:19 +0000 (09:44 -0700)]
X86: Make the x86 ExtMachInst serializable with (UN)SERIALIZE_SCALAR.
--HG--
rename : src/arch/x86/types.hh => src/arch/x86/types.cc
Gabe Black [Mon, 23 Aug 2010 16:44:19 +0000 (09:44 -0700)]
X86: Define a noop ExtMachInst.
Gabe Black [Mon, 23 Aug 2010 16:44:19 +0000 (09:44 -0700)]
X86: Mark serializing macroops and regular instructions as such.
Gabe Black [Mon, 23 Aug 2010 16:44:19 +0000 (09:44 -0700)]
X86: Add a .serializing directive that makes a macroop serializing.
This directive really just tells the macroop to set IsSerializing and
IsSerializeAfter on its final microop.
Gabe Black [Mon, 23 Aug 2010 16:44:19 +0000 (09:44 -0700)]
X86: Consolidate extra microop flags into one parameter.
This single parameter replaces the collection of bools that set up various
flavors of microops. A flag parameter also allows other flags to be set like
the serialize before/after flags, etc., without having to change the
constructor.
Gabe Black [Mon, 23 Aug 2010 16:44:19 +0000 (09:44 -0700)]
CPU: Make the constants for StaticInst flags visible outside the class.
Ali Saidi [Mon, 23 Aug 2010 16:18:42 +0000 (11:18 -0500)]
BUILD: GCC 4.4.1/2 have a bug in their auto-vectorizer that we trip on
Ali Saidi [Mon, 23 Aug 2010 16:18:42 +0000 (11:18 -0500)]
ALPHA: The previous O3 patch causes a slight stats change with fullsys.
Min Kyu Jeong [Mon, 23 Aug 2010 16:18:42 +0000 (11:18 -0500)]
O3: Skipping mem-order violation check for uncachable loads.
Uncachable load is not executed until it reaches the head of the ROB,
hence cannot cause one.
Min Kyu Jeong [Mon, 23 Aug 2010 16:18:42 +0000 (11:18 -0500)]
ARM: Improve printing of uop disassembly.
Min Kyu Jeong [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
ARM: Clean up flattening for SPSR adding
Gene Wu [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
ARM: Implement DBG instruction that doesn't do much for now.
Gene Wu [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
MEM: Make CLREX a first class request operation and clear locks in caches when it in received
Gene Wu [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
ARM: Make sure that software prefetch instructions can't change the state of the TLB
Gene Wu [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
ARM: Don't write tracedata on writes, it might have been freed already.
Gene Wu [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
ARM: Implement CLREX init/complete acc methods
Gene Wu [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
ARM: Fix Uncachable TLB requests and decoding of xn bit
Gene Wu [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
Devices: Allow a device to specify that a request is uncachable.
Gene Wu [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
ARM: For non-cachable accesses set the UNCACHABLE flag
Gene Wu [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
ARM: Implement DSB, DMB, ISB
Gene Wu [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
ARM: Get SCTLR TE bit from reset SCTLR
Gene Wu [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
ARM: Implement CLREX
Gene Wu [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
ARM: BX instruction can be contitional if last instruction in a IT block
Branches are allowed to be the last instuction in an IT block. Before it was
assumed that they could not. So Branches in thumb2 were Uncond.
Min Kyu Jeong [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
CPU: Print out flatten-out register index as with IntRegs/FloatRegs traceflag
Min Kyu Jeong [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
CPU: Make Exec trace to print predication result (if false) for memory instructions
Min Kyu Jeong [Mon, 23 Aug 2010 16:18:41 +0000 (11:18 -0500)]
ARM: mark msr/mrs instructions as SerializeBefore/After
Since miscellaneous registers bypass wakeup logic, force serialization
to resolve data dependencies through them
* * *
ARM: adding non-speculative/serialize flags for instructions change CPSR
Min Kyu Jeong [Mon, 23 Aug 2010 16:18:40 +0000 (11:18 -0500)]
O3: Handle loads when the destination is the PC.
For loads that PC is the destination, check if the load
was mispredicted again when the value being loaded returns from memory