| Age | Commit message (Collapse) | Author |
|---|
|
the GPUExecContext context currently stores a reference to its parent WF's
GPUISA object, however there are some special instructions that do not have
an associated WF. when these objects are constructed they set their WF pointer
to null, which causes the GPUExecContext to segfault when trying to
dereference
the WF pointer to get at the WF's GPUISA object. here we change the GPUISA
reference in the GPUExecContext class to a pointer so that it may be set to
null.
|
|
valid field for GpuTlbEntry is not set in the default ctor, which can
lead to strange behavior, and is also flagged by UBSAN.
|
|
not all uses of MachineID initialize its fields, so here we add a default
ctor.
|
|
UBSAN flags this operation because it detects that arg is being cast directly
to an unsigned type, argBits. this patch fixes this by first casting the
value to a signed int type, then reintrepreting the raw bits of the signed
int into argBits.
|
|
SequencerMsg is autogenerated by slicc scripts and the MessageSizeType is
initialized to the max enume value by default. The DMASequencer pushes this
message to the mandatory queue and since the MessageSizeType is unitialized,
string_to_MessageSizeType() function used by traces to print the message fails
with a panic. This patch avoids this problem by initializing MessageSizeType
of SequencerMsg to Request_Control.
|
|
|
|
No one appears to be using it, and it is causing build issues
and increases the development and maintenance effort.
|
|
fixes to appease clang++. tested on:
Ubuntu clang version 3.5.0-4ubuntu2~trusty2
(tags/RELEASE_350/final) (based on LLVM 3.5.0)
Ubuntu clang version 3.6.0-2ubuntu1~trusty1
(tags/RELEASE_360/final) (based on LLVM 3.6.0)
the fixes address the following five issues:
1) the exec continuations in gpu_static_inst.hh were marked
as protected when they should be public. here we mark
them as public
2) the Abs instruction uses std::abs() in its execute method.
because Abs is templated, it can also operate on U32 and U64,
types, which cause Abs::execute() to pass uint32_t and uint64_t
types to std::abs() respectively. this triggers a warning
because std::abs() has no effect in this case. to rememdy this
we add template specialization for the execute() method of Abs
when its template paramter is U32 or U64.
3) Some potocols that utilize the code in cprintf.hh were missing
includes to BoolVec.hh, which defines operator<< for the BoolVec
type. This would cause issues when the generated code would try
to pass a BoolVec type to a method in cprintf.hh that used
operator<< on an instance of a BoolVec.
4) Surprise, clang doesn't like it when you clobber all the bits
in a newly allocated object. I.e., this code:
tlb = new GpuTlbEntry\[size\];
std::memset(tlb, 0, sizeof(GpuTlbEntry) \* size);
Let's use std::vector to track the TLB entries in the GpuTlb now...
5) There were a few variables used only in DPRINTFs, so we mark them
with M5_VAR_USED.
|
|
This patch adds the ability for an application to request dist-gem5 to begin/
end synchronization using an m5 op. When toggling on sync, all nodes agree
on the next sync point based on the maximum of all nodes' ticks. CPUs are
suspended until the sync point to avoid sending network messages until sync has
been enabled. Toggling off sync acts like a global execution barrier, where
all CPUs are disabled until every node reaches the toggle off point. This
avoids tricky situations such as one node hitting a toggle off followed by a
toggle on before the other nodes hit the first toggle off.
|
|
DMA sequencers and protocols can currently only issue one DMA access at
a time. This patch implements the necessary functionality to support
multiple outstanding DMA requests in Ruby.
|
|
Currently, all the network devices create a 16K buffer for the 'data' field
in EthPacketData, and use 'length' to keep track of the size of the packet
in the buffer. This patch introduces the 'simLength' parameter to
EthPacketData, which is used to hold the effective length of the packet used
for all timing calulations in the simulator. Serialization is performed using
only the useful data in the packet ('length') and not necessarily the entire
original buffer.
|
|
this patch adds an ordered response buffer to the GM pipeline
to ensure in-order data delivery. the buffer is implemented as
a stl ordered map, which sorts the request in program order by
using their sequence ID. when requests return to the GM pipeline
they are marked as done. only the oldest request may be serviced
from the ordered buffer, and only if is marked as done.
the FIFO response buffers are kept and used in OoO delivery mode
|
|
for HSAIL an operand's indices into the register files may be calculated
trivially, because the operands are always read from a register file, or are
an immediate.
for machine ISA, however, an op selector may specify special registers, or
may specify special SGPRs with an alias op selector value. the location of
some of the special registers values are dependent on the size of the RF
in some cases. here we add a way for the underlying getRegisterIndex()
method to know about the size of the RFs, so that it may find the relative
positions of the special register values.
|
|
|
|
currently the PC is incremented on an instruction granularity, and not as an
instruction's byte address. machine ISA instructions assume the PC is a byte
address, and is incremented accordingly. here we make the GPU model, and the
HSAIL instructions treat the PC as a byte address as well.
|
|
the GPUISA class is meant to encapsulate any ISA-specific behavior - special
register accesses, isa-specific WF/kernel state, etc. - in a generic enough
way so that it may be used in ISA-agnostic code.
gpu-compute: use the GPUISA object to advance the PC
the GPU model treats the PC as a pointer to individual instruction objects -
which are store in a contiguous array - and not a byte address to be fetched
from the real memory system. this is ok for HSAIL because all instructions
are considered by the model to be the same size.
in machine ISA, however, instructions may be 32b or 64b, and branches are
calculated by advancing the PC by the number of words (4 byte chunks) it
needs to advance in the real instruction stream. because of this there is
a mismatch between the PC we use to index into the instruction array, and
the actual byte address PC the ISA expects. here we move the PC advance
calculation to the ISA so that differences in the instrucion sizes may be
accounted for in generic way.
|
|
|
|
because every taken branch causes fetch to be discarded, we move the call
to the WF to avoid to have to call it from each and every branch instruction
type.
|
|
we are removing doGmReturn from the GM pipe, and adding completeAcc()
implementations for the HSAIL mem ops. the behavior in doGmReturn is
dependent on HSAIL and HSAIL mem ops, however the completion phase
of memory ops in machine ISA can be very different, even amongst individual
machine ISA mem ops. so we remove this functionality from the pipeline and
allow it to be implemented by the individual instructions.
|
|
this patch removes the GPUStaticInst enums that were defined in GPU.py.
instead, a simple set of attribute flags that can be set in the base
instruction class are used. this will help unify the attributes of HSAIL
and machine ISA instructions within the model itself.
because the static instrution now carries the attributes, a GPUDynInst
must carry a pointer to a valid GPUStaticInst so a new static kernel launch
instruction is added, which carries the attributes needed to perform a
the kernel launch.
|
|
|
|
|
|
the RequestDesc was previously implemented as a std::pair, which made
the implementation overly complex and error prone. here we encapsulate the
packet, primary, and secondary types all in a single data structure with
all members properly intialized in a ctor
|
|
Improve PL011 console interactivity
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
|
|
Read() should not write anything when returning 0 (EOF).
This patch does not correct the same bug occuring for :
nbr_read=read(file, buf, nbytes)
When nbr_read<nbytes, nbytes bytes are copied into the virtual
RAM instead of nbr_read. If buf is smaller than nbytes, a
page fault occurs, even if buf is in fact bigger than nbr_read.
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
|
|
Modify the opClass assigned to AArch64 FP instructions from SimdFloat* to
Float*. Also create the FloatMemRead and FloatMemWrite opClasses, which
distinguishes writes to the INT and FP register banks.
Change the latency of (Simd)FloatMultAcc to 5, based on the Cortex-A72,
where the "latency" of FMADD is 3 if the next instruction is a FMADD and
has only the augend to destination dependency, otherwise it's 7 cycles.
Signed-off-by: Jason Lowe-Power <jason@lowepower.com>
|
|
ClockedObject was changed to require its regStats() to be called from every
child class. If you forget to do this, the error was indecipherable. This
patch makes the error more clear.
|
|
Change-Id: I763cffe0c69f5ebbbf6a6eb12bec5c13d5d0161d
Reviewed-by: Andreas Hansson <andreas.hansson@arm.com>
Reviewed-by: Radhika Jagtap <radhika.jagtap@arm.com>
|
|
Added power-down state transitions to the DRAM controller model.
Added per rank parameter, outstandingEvents, which tracks the number
of outstanding command events and is used to determine when the
controller should transition to a low power state.
The controller will only transition when there are no outstanding events
scheduled and the number of command entries for the given rank is 0.
The outstandingEvents parameter is incremented for every RD/WR burst,
PRE, and REF event scheduled. ACT is implicitly covered by RD/WR
since burst will always issue and complete after a required ACT.
The parameter is decremented when the event is serviced (completed).
The controller will automatically transition to ACT power down,
PRE power down, or SREF.
Transition to ACT power down state scheduled from:
1) The RespondEvent, where read data is received from the memory.
ACT power-down entry will be scheduled when one or more banks is
open, all commands for the rank have completed (no more commands
scheduled), and there are no commands in queue for the rank
Transition to PRE power down scheduled from:
1) respondEvent, when all banks are closed, all commands have
completed, and there are no commands in queue for the rank
2) prechargeEvent when all banks are closed, all commands have
completed, and there are no commands in queue for the rank
3) refreshEvent, after the refresh is complete when the previous
state was ACT power-down
4) refreshEvent, after the refresh is complete when the previous
state was PRE power-down and there are commands in the queue.
Transition to SREF will be scheduled from:
1) refreshEvent, after the refresh is completes when the previous
state was PRE power-down with no commands in queue
Power-down exit commands are scheduled from:
1) The refreshEvent, prior to issuing a refresh
2) doDRAMAccess, to wake-up the rank for RD/WR command issue.
Self-refresh exit commands are scheduled from:
1) The next request event, when the queue has commands for the rank
in the readQueue or there are commands for the rank in the
writeQueue and the bus state is WRITE.
Change-Id: I6103f660776e36c686655e71d92ec7b5b752050a
Reviewed-by: Radhika Jagtap <radhika.jagtap@arm.com>
|
|
The per rank statistics are periodically updated based on
state transition and refresh events.
Add a method to update these when a dump event occurs to
ensure they reflect accurate values.
Specifically, need to ensure that the low-power state
durations, power, and energy are logged correctly.
Change-Id: Ib642a6668340de8f494a608bb34982e58ba7f1eb
Reviewed-by: Radhika Jagtap <radhika.jagtap@arm.com>
|
|
Add constraint that all ranks have to be in PWR_IDLE
before signaling drain complete
This will ensure that the banks are all closed and the rank
has exited any low-power states.
On suspend, update the power stats to sync the DRAM power logic
The logic maintains the location of the signalDrainDone
method, which is still triggered from either:
1) Read response event
2) Next request event
This ensures that the drain will complete in the READ bus
state and minimizes the changes required.
Change-Id: If1476e631ea7d5999fe50a0c9379c5967a90e3d1
Reviewed-by: Radhika Jagtap <radhika.jagtap@arm.com>
|
|
Add local variable to stores commands to be issued.
These commands are in order within a single bank but will be out
of order across banks & ranks.
A new procedure, flushCmdList, sorts commands across banks / ranks,
and flushes the sorted list, up to curTick() to DRAMPower.
This is currently called in refresh, once all previous commands are
guaranteed to have completed. Could be called in other events like
the powerEvent as well.
By only flushing commands up to curTick(), will not get out of sync
when flushed at a periodic stats dump (done in subsequent patch).
Change-Id: I4ac65a52407f64270db1e16a1fb04cfe7f638851
Reviewed-by: Radhika Jagtap <radhika.jagtap@arm.com>
|
|
Change-Id: I8992ddc1664c3ed4b2d36d8a34e4ce8be113b9de
Reviewed-by: Radhika Jagtap <radhika.jagtap@arm.com>
|
|
|
|
|
|
This commit adds missing non-predicated, scalar floating point
instructions. Specifically VRINT* floating point integer rounding
instructions and VSEL* floating point conditional selects.
Change-Id: I23cbd1389f151389ac8beb28a7d18d5f93d000e7
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Nathanael Premillieu <nathanael.premillieu@arm.com>
|
|
The generic timer needs a pointer to an ArmSystem to wire itself to the
system register handler. This was previously specified as an instance
of System that was later cast to ArmSystem. Make this more robust by
specifying it as an ArmSystem in the Python interface and add a check
to make sure that it is non-NULL.
Change-Id: I989455e666f4ea324df28124edbbadfd094b0d02
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
This removes errors when building gem5.fast
|
|
Revamped version of garnet with more optimized single-cycle routers,
more configurability, and cleaner code.
|
|
Only garnet2.0 will be supported henceforth.
|
|
This patch adds port direction names to the links during topology
creation, which can be used for better printed names for the links
or for users to code up their own adaptive routing algorithms.
It also adds support for every router to have an independent latency
value to support heterogeneous topologies with the subsequent
garnet2.0 patch.
|
|
This patch makes the internal links within the network topology
unidirectional, thus allowing any deadlock-free routing algorithms to
be specified from the topology itself using weights.
This patch also renames Mesh.py and MeshDirCorners.py to
Mesh_XY.py and MeshDirCorners_XY.py (Mesh with XY routing).
It also adds a Mesh_westfirst.py and CrossbarGarnet.py topologies.
|
|
networktest is essentially a collection of synthetic traffic patterns
for the network. The protocol name and the tester having the same name
led to multiple python configuration files with the same name, adding
confusion. This patch renames networktest to garnet_synthetic_traffic,
and also adds more synthetic traffic patterns.
|
|
Over the past 6 years, we realized that the protocol is essentially used
to run the garnet network in a standalone manner, and feed standard synthetic
traffic patterns through it.
|
|
Adding details, e.g. rip, rsp etc. to the kvm pagefault exit when in SE mode.
|
|
Instead of scheduling another event, this patch adds a warning in case gdb
is attached multiple times and the first attachement event has not been
processed yet.
|
|
This patch adds a method to the Wavefront class to compute the actual workgroup
size. This can be different from the maximum workgroup size specified when
launching the kernel through the NDRange object. Current solution is still not
optimal, as we are computing these for each wavefront and the dispatcher also
needs to have this information and can't actually call
Wavefront::computeActuallWgSz before the wavefronts are being created. A long
term solution would be to have a Workgroup class that deals with all these
details.
|
|
When loading a checkpoint, it's sometimes desirable to be able to test
whether an entry within a secion exists. This is currently done
automatically in the UNSERIALIZE_OPT_SCALAR macro, but it isn't
possible to do for arrays, containers, or enums. Instead of adding
even more macros, add a helper function (CheckpointIn::entryExists())
that tests for the presence of an entry.
Change-Id: I4b4646b03276b889fd3916efefff3bd552317dbc
Signed-off-by: Andreas Sandberg <andreas.sandberg@arm.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
|
|
Fixed AbstractController::queueMemoryWritePartial to specify the
correct size for partial memory writes.
|
|
print number of bytes written as a decimal number, not hex
|
