Searched hist:2010 (Results 526 - 550 of 929) sorted by relevance

<<21222324252627282930>>

/gem5/src/arch/x86/
H A Dvtophys.ccdiff 7087:fb8d5786ff30 Mon May 24 01:44:00 EDT 2010 Nathan Binkert <nate@binkert.org> copyright: Change HP copyright on x86 code to be more friendly
H A Disa_traits.hhdiff 7623:072f8b921599 Mon Aug 23 12:44:00 EDT 2010 Gabe Black <gblack@eecs.umich.edu> X86: Define a noop ExtMachInst.
diff 7580:6f77f379a594 Mon Aug 23 12:18:00 EDT 2010 Ali Saidi <Ali.Saidi@arm.com> Loader: Make the load address mask be a parameter of the system rather than a constant.

This allows one two different OS requirements for the same ISA to be handled.
Some OSes are compiled for a virtual address and need to be loaded into physical
memory that starts at address 0, while other bare metal tools generate
images that start at address 0.
diff 7087:fb8d5786ff30 Mon May 24 01:44:00 EDT 2010 Nathan Binkert <nate@binkert.org> copyright: Change HP copyright on x86 code to be more friendly
diff 6974:4d4903a3e7c5 Fri Feb 12 14:53:00 EST 2010 Timothy M. Jones <tjones1@inf.ed.ac.uk> 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.
/gem5/src/arch/x86/regs/
H A Dmisc.hh7629:0f0c231e3e97 Mon Aug 23 19:14:00 EDT 2010 Gabe Black <gblack@eecs.umich.edu> 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.
/gem5/src/arch/arm/isa/templates/
H A Dbranch.isa7150:b276b5afd927 Wed Jun 02 01:58:00 EDT 2010 Gabe Black <gblack@eecs.umich.edu> ARM: Add new templates for branch instructions.
/gem5/util/m5/
H A DMakefile.thumb7732:a2c660de7787 Mon Nov 08 14:58:00 EST 2010 Ali Saidi <Ali.Saidi@ARM.com> ARM: Add support for M5 ops in the ARM ISA
/gem5/src/arch/mips/
H A Dutility.hhdiff 7720:65d338a8dba4 Sun Oct 31 03:07:00 EDT 2010 Gabe Black <gblack@eecs.umich.edu> 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.
diff 7707:e5b6f1157be3 Sat Oct 16 02:57:00 EDT 2010 Gabe Black <gblack@eecs.umich.edu> GetArgument: Rework getArgument so that X86_FS compiles again.

When no size is specified for an argument, push the decision about what size
to use into the ISA by passing a size of -1.
diff 7693:f1db1000d957 Fri Oct 01 17:02:00 EDT 2010 Ali Saidi <Ali.Saidi@ARM.com> 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.
diff 7627:3b0c4b819651 Mon Aug 23 19:14:00 EDT 2010 Gabe Black <gblack@eecs.umich.edu> ISA: Get rid of old, unused utility functions cluttering up the ISAs.
/gem5/src/arch/power/linux/
H A Dprocess.hhdiff 7532:3f6413fc37a2 Tue Aug 17 08:17:00 EDT 2010 Steve Reinhardt <steve.reinhardt@amd.com> sim: revamp unserialization procedure

Replace direct call to unserialize() on each SimObject with a pair of
calls for better control over initialization in both ckpt and non-ckpt
cases.

If restoring from a checkpoint, loadState(ckpt) is called on each
SimObject. The default implementation simply calls unserialize() if
there is a corresponding checkpoint section, so we get backward
compatibility for existing objects. However, objects can override
loadState() to get other behaviors, e.g., doing other programmed
initializations after unserialize(), or complaining if no checkpoint
section is found. (Note that the default warning for a missing
checkpoint section is now gone.)

If not restoring from a checkpoint, we call the new initState() method
on each SimObject instead. This provides a hook for state
initializations that are only required when *not* restoring from a
checkpoint.

Given this new framework, do some cleanup of LiveProcess subclasses
and X86System, which were (in some cases) emulating initState()
behavior in startup via a local flag or (in other cases) erroneously
doing initializations in startup() that clobbered state loaded earlier
by unserialize().
/gem5/src/arch/sparc/
H A DSparcSystem.pydiff 7580:6f77f379a594 Mon Aug 23 12:18:00 EDT 2010 Ali Saidi <Ali.Saidi@arm.com> Loader: Make the load address mask be a parameter of the system rather than a constant.

This allows one two different OS requirements for the same ISA to be handled.
Some OSes are compiled for a virtual address and need to be loaded into physical
memory that starts at address 0, while other bare metal tools generate
images that start at address 0.
H A Dstacktrace.hhdiff 7741:340b6f01d69b Thu Nov 11 05:03:00 EST 2010 Gabe Black <gblack@eecs.umich.edu> SPARC: Clean up some historical style issues.
diff 7706:a7cb52c76262 Thu Oct 14 17:02:00 EDT 2010 Gabe Black <gblack@eecs.umich.edu> SPARC: Get rid of the copy/pasted StackTrace stolen from Alpha.
/gem5/src/arch/x86/insts/
H A Dmicromediaop.hhdiff 7620:3d8a23caa1ef Mon Aug 23 12:44:00 EDT 2010 Gabe Black <gblack@eecs.umich.edu> 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.
H A Dmacroop.hhdiff 7720:65d338a8dba4 Sun Oct 31 03:07:00 EDT 2010 Gabe Black <gblack@eecs.umich.edu> 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.
diff 7087:fb8d5786ff30 Mon May 24 01:44:00 EDT 2010 Nathan Binkert <nate@binkert.org> copyright: Change HP copyright on x86 code to be more friendly
/gem5/src/arch/x86/linux/
H A Dprocess.hhdiff 7087:fb8d5786ff30 Mon May 24 01:44:00 EDT 2010 Nathan Binkert <nate@binkert.org> copyright: Change HP copyright on x86 code to be more friendly
/gem5/src/cpu/o3/
H A DFuncUnitConfig.pydiff 7760:e93e7e0caae1 Mon Nov 15 15:04:00 EST 2010 Giacomo Gabrielli <Giacomo.Gabrielli@arm.com> CPU/ARM: Add SIMD op classes to CPU models and ARM ISA.
/gem5/tests/configs/
H A Drubytest-ruby.pydiff 7570:417ef5d444bd Fri Aug 20 20:44:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> regress: Regression tester updates

Regression tester updates required by the following patches:

brad/moved_python_protocol_files: config: moved python protocol config files
brad/ruby_options_movement: config: reorganized how ruby specifies command-line options
brad/config_token_bcast: ruby: added token broadcast config params to cmd options
brad/topology_name: config: Added the topology description to m5 config.ini
brad/ruby_system_names: config: Improve ruby simobject names
brad/consolidated_protocol_stats: slicc: Consolidated the protocol stats printing
brad/ruby_request_type_ostream_fix: ruby: Added ruby_request_type ostream def to libruby.hh
brad/memtest_dma_extension: memtest: Memtester support for DMA
brad/token_dma_lockdown_fix: MOESI_CMP_token: Fixed dma persistent lockdown bugs
brad/profile_generic_mach_type: ruby: Reincarnated the responding machine profiling
brad/network_msg_consolidated_stats: ruby: Added consolidated network msg stats
brad/bcast_msg_profiling: ruby: Added bcast msg profiling to hammer and token
brad/l2cache_profiling_fix: ruby: Fixed L2 cache miss profiling
brad/llsc_ruby_m5_fix: ruby: fix ruby llsc support to sync sc outcomes
brad/ruby_latency_fixes: ruby: Reduced ruby latencies
brad/hammer_l2_cache_latency: ruby: Updated MOESI_hammer L2 latency behavior
brad/deterministic_resurrection: ruby: Resurrected Ruby's deterministic tests
brad/token_dma_fixes: ruby: MOESI_CMP_token dma fixes
brad/ruby_cmd_options: config: added cmd options to control ruby debug
brad/token_owner_fixes: ruby: fixed token bugs associated with owner token counts
brad/ruby_remove_try_except: ruby: Improved try except blocks in ruby creation
brad/ruby_port_callback_fix: ruby: Fixed RubyPort sendTiming callbacks
brad/interrupt_drain_fix: devices: Fixed periodic interrupts to work with draining
brad/llsc_trace_profile: ruby: Added SC fail indication to trace profiling
brad/no_migrate_atomic: ruby: Disable migratory sharing for token and hammer
brad/ruby_start_time_fix: ruby: Reset ruby stats in RubySystem unserialize
brad/numa_bit_select_fix: ruby: fixed DirectoryMemory's numa_high_bit configuration
brad/hammer_probe_filter: ruby: added probe filter support to hammer
brad/miss_latency_detail_profile: MOESI_hammer: break down miss latency stalled cycles
brad/recycle_latency_fix: ruby: Recycle latency fix for hammer
brad/stall_and_wait: ruby: Stall and wait input messages instead of recycling
brad/rubytest_request_flag_fix: ruby: Fixed minor bug in ruby test for setting the request type
brad/hammer_merge_gets: ruby: Added merge GETS optimization to hammer
brad/regress_updates: regress: Regression tester updates
diff 7526:4bb5f5207617 Tue Aug 17 08:06:00 EDT 2010 Steve Reinhardt <steve.reinhardt@amd.com> sim: fail on implicit creation of orphans via ports
Orphan SimObjects (not in the config hierarchy) could get
created implicitly if they have a port connection to a SimObject
that is in the hierarchy. This means that there are objects on
the C++ SimObject list (created via the C++ SimObject
constructor call) that are unknown to Python and will get
skipped if we walk the hierarchy from the Python side (as we are
about to do). This patch detects this situation and prints an
error message.

Also fix the rubytester config script which happened to rely on
this behavior.
diff 7034:6bf327b128c6 Mon Mar 22 00:22:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Regression updates for new ruby config locations
6928:5bd33f7c26ea Fri Jan 29 23:29:00 EST 2010 Brad Beckmann <Brad.Beckmann@amd.com> m5: Regression Tester Update

This patch includes the necessary regression updates to test the new ruby
configuration system. The patch includes support for multiple ruby protocols
and adds the ruby random tester. The patch removes atomic mode test for
ruby since ruby does not support atomic mode acceses. These tests can be
added back in when ruby supports atomic mode for real.
H A Dsimple-timing-ruby.pydiff 7570:417ef5d444bd Fri Aug 20 20:44:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> regress: Regression tester updates

Regression tester updates required by the following patches:

brad/moved_python_protocol_files: config: moved python protocol config files
brad/ruby_options_movement: config: reorganized how ruby specifies command-line options
brad/config_token_bcast: ruby: added token broadcast config params to cmd options
brad/topology_name: config: Added the topology description to m5 config.ini
brad/ruby_system_names: config: Improve ruby simobject names
brad/consolidated_protocol_stats: slicc: Consolidated the protocol stats printing
brad/ruby_request_type_ostream_fix: ruby: Added ruby_request_type ostream def to libruby.hh
brad/memtest_dma_extension: memtest: Memtester support for DMA
brad/token_dma_lockdown_fix: MOESI_CMP_token: Fixed dma persistent lockdown bugs
brad/profile_generic_mach_type: ruby: Reincarnated the responding machine profiling
brad/network_msg_consolidated_stats: ruby: Added consolidated network msg stats
brad/bcast_msg_profiling: ruby: Added bcast msg profiling to hammer and token
brad/l2cache_profiling_fix: ruby: Fixed L2 cache miss profiling
brad/llsc_ruby_m5_fix: ruby: fix ruby llsc support to sync sc outcomes
brad/ruby_latency_fixes: ruby: Reduced ruby latencies
brad/hammer_l2_cache_latency: ruby: Updated MOESI_hammer L2 latency behavior
brad/deterministic_resurrection: ruby: Resurrected Ruby's deterministic tests
brad/token_dma_fixes: ruby: MOESI_CMP_token dma fixes
brad/ruby_cmd_options: config: added cmd options to control ruby debug
brad/token_owner_fixes: ruby: fixed token bugs associated with owner token counts
brad/ruby_remove_try_except: ruby: Improved try except blocks in ruby creation
brad/ruby_port_callback_fix: ruby: Fixed RubyPort sendTiming callbacks
brad/interrupt_drain_fix: devices: Fixed periodic interrupts to work with draining
brad/llsc_trace_profile: ruby: Added SC fail indication to trace profiling
brad/no_migrate_atomic: ruby: Disable migratory sharing for token and hammer
brad/ruby_start_time_fix: ruby: Reset ruby stats in RubySystem unserialize
brad/numa_bit_select_fix: ruby: fixed DirectoryMemory's numa_high_bit configuration
brad/hammer_probe_filter: ruby: added probe filter support to hammer
brad/miss_latency_detail_profile: MOESI_hammer: break down miss latency stalled cycles
brad/recycle_latency_fix: ruby: Recycle latency fix for hammer
brad/stall_and_wait: ruby: Stall and wait input messages instead of recycling
brad/rubytest_request_flag_fix: ruby: Fixed minor bug in ruby test for setting the request type
brad/hammer_merge_gets: ruby: Added merge GETS optimization to hammer
brad/regress_updates: regress: Regression tester updates
diff 7034:6bf327b128c6 Mon Mar 22 00:22:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Regression updates for new ruby config locations
diff 6928:5bd33f7c26ea Fri Jan 29 23:29:00 EST 2010 Brad Beckmann <Brad.Beckmann@amd.com> m5: Regression Tester Update

This patch includes the necessary regression updates to test the new ruby
configuration system. The patch includes support for multiple ruby protocols
and adds the ruby random tester. The patch removes atomic mode test for
ruby since ruby does not support atomic mode acceses. These tests can be
added back in when ruby supports atomic mode for real.
diff 6870:5707ef3691b5 Mon Jan 25 12:51:00 EST 2010 Derek Hower <drh5@cs.wisc.edu> config: changed default ruby config file for regression
H A Dsimple-timing-mp-ruby.pydiff 7570:417ef5d444bd Fri Aug 20 20:44:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> regress: Regression tester updates

Regression tester updates required by the following patches:

brad/moved_python_protocol_files: config: moved python protocol config files
brad/ruby_options_movement: config: reorganized how ruby specifies command-line options
brad/config_token_bcast: ruby: added token broadcast config params to cmd options
brad/topology_name: config: Added the topology description to m5 config.ini
brad/ruby_system_names: config: Improve ruby simobject names
brad/consolidated_protocol_stats: slicc: Consolidated the protocol stats printing
brad/ruby_request_type_ostream_fix: ruby: Added ruby_request_type ostream def to libruby.hh
brad/memtest_dma_extension: memtest: Memtester support for DMA
brad/token_dma_lockdown_fix: MOESI_CMP_token: Fixed dma persistent lockdown bugs
brad/profile_generic_mach_type: ruby: Reincarnated the responding machine profiling
brad/network_msg_consolidated_stats: ruby: Added consolidated network msg stats
brad/bcast_msg_profiling: ruby: Added bcast msg profiling to hammer and token
brad/l2cache_profiling_fix: ruby: Fixed L2 cache miss profiling
brad/llsc_ruby_m5_fix: ruby: fix ruby llsc support to sync sc outcomes
brad/ruby_latency_fixes: ruby: Reduced ruby latencies
brad/hammer_l2_cache_latency: ruby: Updated MOESI_hammer L2 latency behavior
brad/deterministic_resurrection: ruby: Resurrected Ruby's deterministic tests
brad/token_dma_fixes: ruby: MOESI_CMP_token dma fixes
brad/ruby_cmd_options: config: added cmd options to control ruby debug
brad/token_owner_fixes: ruby: fixed token bugs associated with owner token counts
brad/ruby_remove_try_except: ruby: Improved try except blocks in ruby creation
brad/ruby_port_callback_fix: ruby: Fixed RubyPort sendTiming callbacks
brad/interrupt_drain_fix: devices: Fixed periodic interrupts to work with draining
brad/llsc_trace_profile: ruby: Added SC fail indication to trace profiling
brad/no_migrate_atomic: ruby: Disable migratory sharing for token and hammer
brad/ruby_start_time_fix: ruby: Reset ruby stats in RubySystem unserialize
brad/numa_bit_select_fix: ruby: fixed DirectoryMemory's numa_high_bit configuration
brad/hammer_probe_filter: ruby: added probe filter support to hammer
brad/miss_latency_detail_profile: MOESI_hammer: break down miss latency stalled cycles
brad/recycle_latency_fix: ruby: Recycle latency fix for hammer
brad/stall_and_wait: ruby: Stall and wait input messages instead of recycling
brad/rubytest_request_flag_fix: ruby: Fixed minor bug in ruby test for setting the request type
brad/hammer_merge_gets: ruby: Added merge GETS optimization to hammer
brad/regress_updates: regress: Regression tester updates
diff 7034:6bf327b128c6 Mon Mar 22 00:22:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Regression updates for new ruby config locations
diff 6928:5bd33f7c26ea Fri Jan 29 23:29:00 EST 2010 Brad Beckmann <Brad.Beckmann@amd.com> m5: Regression Tester Update

This patch includes the necessary regression updates to test the new ruby
configuration system. The patch includes support for multiple ruby protocols
and adds the ruby random tester. The patch removes atomic mode test for
ruby since ruby does not support atomic mode acceses. These tests can be
added back in when ruby supports atomic mode for real.
diff 6870:5707ef3691b5 Mon Jan 25 12:51:00 EST 2010 Derek Hower <drh5@cs.wisc.edu> config: changed default ruby config file for regression
/gem5/src/cpu/testers/directedtest/
H A DRubyDirectedTester.py7632:acf43d6bbc18 Tue Aug 24 03:07:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> 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.
/gem5/src/mem/ruby/network/
H A DNetwork.hhdiff 7454:3a3e8e8cce1b Fri Jun 11 02:17:00 EDT 2010 Nathan Binkert <nate@binkert.org> ruby: get rid of Vector and use STL
add a couple of helper functions to base for deleteing all pointers in
a container and outputting containers to a stream
diff 7055:4e24742201d7 Fri Apr 02 14:20:00 EDT 2010 Nathan Binkert <nate@binkert.org> ruby: get "using namespace" out of headers
In addition to obvious changes, this required a slight change to the slicc
grammar to allow types with :: in them. Otherwise slicc barfs on std::string
which we need for the headers that slicc generates.
diff 7054:7d6862b80049 Wed Mar 31 19:56:00 EDT 2010 Nathan Binkert <nate@binkert.org> style: another ruby style pass
diff 6876:a658c315512c Fri Jan 29 23:29:00 EST 2010 Steve Reinhardt <steve.reinhardt@amd.com> ruby: Convert most Ruby objects to M5 SimObjects.
The necessary companion conversion of Ruby objects generated by SLICC
are converted to M5 SimObjects in the following patch, so this patch
alone does not compile.
Conversion of Garnet network models is also handled in a separate
patch; that code is temporarily disabled from compiling to allow
testing of interim code.
/gem5/src/cpu/testers/rubytest/
H A DCheck.hh7632:acf43d6bbc18 Tue Aug 24 03:07:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> 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.
/gem5/configs/common/
H A DOptions.pydiff 7551:b10ee98aea91 Fri Aug 20 14:46:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Reduced ruby latencies

The previous slower ruby latencies created a mismatch between the faster M5
cpu models and the much slower ruby memory system. Specifically smp
interrupts were much slower and infrequent, as well as cpus moving in and out
of spin locks. The result was many cpus were idle for large periods of time.

These changes fix the latency mismatch.
diff 7538:5691b9dd51f4 Fri Aug 20 14:44:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> config: reorganized how ruby specifies command-line options
diff 7515:82453f1b46c5 Mon Aug 09 01:57:00 EDT 2010 Nathan Binkert <nate@binkert.org> None, not none
diff 7032:9f938aea1942 Mon Mar 22 00:22:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Reorganized Ruby topology and protocol files
diff 7027:46b02e79bf2c Mon Mar 22 00:22:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Adds configurable bit selection for numa mapping
diff 7025:9adf5b0ccc79 Mon Mar 22 00:22:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Ruby support for sparse memory

The patch includes direct support for the MI example protocol.
diff 6918:9b57f0108bc8 Fri Jan 29 23:29:00 EST 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Converted Garnet to M5 configuration
diff 6916:a421f60f0e87 Fri Jan 29 23:29:00 EST 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Added a mesh topology
diff 6908:0e1d7624e641 Fri Jan 29 23:29:00 EST 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: MOESI_CMP_token updates to use the new config system
diff 6893:9cdf9b65d946 Fri Jan 29 23:29:00 EST 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: FS support using the new configuration system
/gem5/src/mem/ruby/system/
H A DRubyPort.ccdiff 7632:acf43d6bbc18 Tue Aug 24 03:07:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> 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.
diff 7558:6c3f81b176da Fri Aug 20 14:46:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Fixed RubyPort sendTiming callbacks

Fixed RubyPort schedSendTiming calls to match ruby frequency.
diff 7550:7d97cec15818 Fri Aug 20 14:46:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: fix ruby llsc support to sync sc outcomes

Added support so that ruby can determine the outcome of store conditional
operations and reflect that outcome to M5 physical memory and cpus.
diff 7039:bc0b6ea676b5 Mon Mar 22 21:43:00 EDT 2010 Nathan Binkert <nate@binkert.org> ruby: style pass
diff 7035:b78b3a9e205f Mon Mar 22 14:19:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: improved isReadWrite fix me comment
diff 7023:185ad61a4117 Mon Mar 22 00:22:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Ruby support for LLSC
diff 6922:1620cffaa3b6 Fri Jan 29 23:29:00 EST 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Removed static members in RubyPort including hitcallback
Removed static members in RubyPort and removed the ruby request unique id.
diff 6899:f8057af86bf7 Fri Jan 29 23:29:00 EST 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: added the GEMS ruby tester
diff 6893:9cdf9b65d946 Fri Jan 29 23:29:00 EST 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: FS support using the new configuration system
diff 6882:898047a3672c Fri Jan 29 23:29:00 EST 2010 Brad Beckmann <Brad.Beckmann@amd.com> ruby: Ruby changes required to use the python config system
This patch includes the necessary changes to connect ruby objects using
the python configuration system. Mainly it consists of removing
unnecessary ruby object pointers and connecting the necessary object
pointers using the generated param objects. This patch includes the
slicc changes necessary to connect generated ruby objects together using
the python configuraiton system.
/gem5/src/dev/alpha/
H A Dtsunami_io.hhdiff 7683:f81f5f27592b Thu Sep 16 23:24:00 EDT 2010 Steve Reinhardt <steve.reinhardt@amd.com> 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.
diff 7559:017baf09599f Fri Aug 20 14:46:00 EDT 2010 Brad Beckmann <Brad.Beckmann@amd.com> devices: Fixed periodic interrupts to work with draining

Added drain functions to the RTC and 8254 timer so that periodic interrupts
stop when the system is draining. This patch is needed to checkpoint in
timing mode. Otherwise under certain situations, the event queue will never
be completely empty.
/gem5/src/arch/power/insts/
H A Dbranch.ccdiff 7720:65d338a8dba4 Sun Oct 31 03:07:00 EDT 2010 Gabe Black <gblack@eecs.umich.edu> 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.
diff 7680:f4eda002333b Tue Sep 14 03:29:00 EDT 2010 Gabe Black <gblack@eecs.umich.edu> 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.
/gem5/src/dev/arm/
H A Drealview.ccdiff 7750:0731d632db76 Mon Nov 15 15:04:00 EST 2010 Ali Saidi <Ali.Saidi@ARM.com> ARM: Add support for a dumb IDE controller
7584:28ddf6d9e982 Mon Aug 23 12:18:00 EDT 2010 Ali Saidi <Ali.Saidi@arm.com> ARM: Add I/O devices for booting linux
/gem5/src/cpu/pred/
H A Dbtb.hhdiff 9480:d059f8a95a42 Thu Jan 24 01:28:00 EST 2013 Nilay Vaish <nilay@cs.wisc.edu>, Timothy Jones <timothy.jones@cl.cam.ac.uk> branch predictor: move out of o3 and inorder cpus
This patch moves the branch predictor files in the o3 and inorder directories
to src/cpu/pred. This allows sharing the branch predictor across different
cpu models.

This patch was originally posted by Timothy Jones in July 2010
but never made it to the repository.
diff 7720:65d338a8dba4 Sun Oct 31 03:07:00 EDT 2010 Gabe Black <gblack@eecs.umich.edu> 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.

Completed in 164 milliseconds

<<21222324252627282930>>