| Age | Commit message (Collapse) | Author |
|---|
|
This object encapsulates (or will eventually) the identity and characteristics
of the ISA in the CPU.
|
|
|
|
--HG--
rename : src/cpu/2bit_local_pred.cc => src/cpu/pred/2bit_local.cc
rename : src/cpu/o3/2bit_local_pred.hh => src/cpu/pred/2bit_local.hh
rename : src/cpu/btb.cc => src/cpu/pred/btb.cc
rename : src/cpu/o3/btb.hh => src/cpu/pred/btb.hh
rename : src/cpu/ras.cc => src/cpu/pred/ras.cc
rename : src/cpu/o3/ras.hh => src/cpu/pred/ras.hh
rename : src/cpu/tournament_pred.cc => src/cpu/pred/tournament.cc
rename : src/cpu/o3/tournament_pred.hh => src/cpu/pred/tournament.hh
|
|
|
|
|
|
--HG--
rename : src/sim/host.hh => src/base/types.hh
|
|
regressions need this so they build the model
|
|
make sure unrecognized events in the resource pool are deleted and also delete resource events in destructor
|
|
TLBUnit no longer used and we also get rid of memAccSize and memAccFlags functions added to ISA and StaticInst
since TLB is not a separate resource to acquire. Instead, TLB access is done before any read/write to memory
and the result is checked before it's sent out to memory.
* * *
|
|
TLB had a bug where if it was stalled and waiting , it would not squash all instructions older than squashed instruction correctly
* * *
|
|
|
|
|
|
inorder was incorrectly storing FP values and confusing the integer/fp storage view of floating point operations. A big issue was knowing trying to infer when were doing single or double precision access
because this lets you know the size of value to store (32-64 bits). This isnt exactly straightforward since alpha uses all 64-bit regs while mips/sparc uses a dual-reg view. by getting this value from
the actual floating point register file, the model can figure out what it needs to store
|
|
|
|
* * *
|
|
|
|
allow InOrder and O3CPU to be compiled at the same time: need to make branch prediction filed shared by both models
|
|
|
|
result-types for better tracing of these types of values
|
|
Remove subinstructions eaComp/memAcc since unused in CPU Models. Instead, create eaComp that is visible from StaticInst object. Gives InOrder model capability of generating address without actually initiating access
* * *
|
|
Changes so that InOrder can work for a non-delay-slot ISA like Alpha. Typically, changes have to do with handling misspeculated branches at different points in pipeline
|
|
Edit AlphaISA to support the inorder model. Mostly alternate constructor functions and also a few skeleton multithreaded support functions
* * *
Remove namespace from header file. Causes compiler issues that are hard to find
* * *
Separate the TLB from the CPU and allow it to live in the TLBUnit resource. Give CPU accessor functions for access and also bind at construction time
* * *
Expose memory access size and flags through instruction object
(temporarily memAccSize and memFlags to get TLB stuff working.)
|
|
this was double scheduling itself (once in constructor and once in cpu code). also add support for stopping / starting
progress events through repeatEvent flag and also changing the interval of the progress event as well
|
|
This code compiles, but there are no tests still
|
|
|
|
|
|
|
|
|
|
don't assert.
|
|
stage was not setting the predicted PC correctly or passing that information back to fetch correctly
|
|
For some reason o3 FS init() only called initCPU if the thread state
was Suspended, which was no longer the case. There's no apparent
reason to check, so I whacked the test completely rather than
changing the check to Halted.
The inorder init() was also updated to be symmetric, though the
previous code was just a fancy no-op.
|
|
This situation can arise now on the first fetch cycle after
the last active thread is halted. It seems easy enough to
deal with when it happens rather than trying to avoid it.
|
|
Register indices were not being calculated properly.
|
|
This provides a common initial status for all threads independent
of CPU model (unlike the prior situation where CPUs initialized
threads to inconsistent states).
This mostly matters for SE mode; in FS mode, ISA-specific startupCPU()
methods generally handle boot-time initialization of thread contexts
(since the right thing to do is ISA-dependent).
|
|
Basically merge it in with Halted.
Also had to get rid of a few other functions that
called ThreadContext::deallocate(), including:
- InOrderCPU's setThreadRescheduleCondition.
- ThreadContext::exit(). This function was there to avoid terminating
simulation when one thread out of a multi-thread workload exits, but we
need to find a better (non-cpu-centric) way.
|
|
|
|
|
|
(no functional change)
|
|
This generally requires providing a more meaningful name() function for a
class.
|
|
|
|
|
|
a way for the compiler to play *nice*)
|
|
'Resource' flag
|
|
|
|
(1)number from 0-n, not 1-n+1, (2) always check nextStageValid before a stageNum+1 and prevStageValid for a stageNum-1 reference (3) add skidSize() to get StageQueue size for all threads
|
|
required for M5 objects; Also, a # of values need to be reset to 0 (or the appropriate value) before we assume they are OK for use.
|
|
generic stages so w/o an ID there is no way to differentiate buffers when debugging
|
|
|
|
|
|
object.
|
