branch prediction, and makes memory dependence work properly.
SConscript:
Added return address stack, tournament predictor.
cpu/base_cpu.cc:
Added debug break and print statements.
cpu/base_dyn_inst.cc:
cpu/base_dyn_inst.hh:
Comment out possibly unneeded variables.
cpu/beta_cpu/2bit_local_pred.cc:
2bit predictor no longer speculatively updates itself.
cpu/beta_cpu/alpha_dyn_inst.hh:
Comment formatting.
cpu/beta_cpu/alpha_full_cpu.hh:
Formatting
cpu/beta_cpu/alpha_full_cpu_builder.cc:
Added new parameters for branch predictors, and IQ parameters.
cpu/beta_cpu/alpha_full_cpu_impl.hh:
Register stats.
cpu/beta_cpu/alpha_params.hh:
Added parameters for IQ, branch predictors, and store sets.
cpu/beta_cpu/bpred_unit.cc:
Removed one class.
cpu/beta_cpu/bpred_unit.hh:
Add in RAS, stats. Changed branch predictor unit functionality
so that it holds a history of past branches so it can update, and also
hold a proper history of the RAS so it can be restored on branch
mispredicts.
cpu/beta_cpu/bpred_unit_impl.hh:
Added in stats, history of branches, RAS. Now bpred unit actually
modifies the instruction's predicted next PC.
cpu/beta_cpu/btb.cc:
Add in sanity checks.
cpu/beta_cpu/comm.hh:
Add in communication where needed, remove it where it's not.
cpu/beta_cpu/commit.hh:
cpu/beta_cpu/rename.hh:
cpu/beta_cpu/rename_impl.hh:
Add in stats.
cpu/beta_cpu/commit_impl.hh:
Stats, update what is sent back on branch mispredict.
cpu/beta_cpu/cpu_policy.hh:
Change the bpred unit being used.
cpu/beta_cpu/decode.hh:
cpu/beta_cpu/decode_impl.hh:
Stats.
cpu/beta_cpu/fetch.hh:
Stats, change squash so it can handle squashes from decode differently
than squashes from commit.
cpu/beta_cpu/fetch_impl.hh:
Add in stats. Change how a cache line is fetched. Update to work with
caches. Also have separate functions for different behavior if squash
is coming from decode vs commit.
cpu/beta_cpu/free_list.hh:
Remove some old comments.
cpu/beta_cpu/full_cpu.cc:
cpu/beta_cpu/full_cpu.hh:
Added function to remove instructions from back of instruction list
until a certain sequence number.
cpu/beta_cpu/iew.hh:
Stats, separate squashing behavior due to branches vs memory.
cpu/beta_cpu/iew_impl.hh:
Stats, separate squashing behavior for branches vs memory.
cpu/beta_cpu/inst_queue.cc:
Debug stuff
cpu/beta_cpu/inst_queue.hh:
Stats, change how mem dep unit works, debug stuff
cpu/beta_cpu/inst_queue_impl.hh:
Stats, change how mem dep unit works, debug stuff. Also add in
parameters that used to be hardcoded.
cpu/beta_cpu/mem_dep_unit.hh:
cpu/beta_cpu/mem_dep_unit_impl.hh:
Add in stats, change how memory dependence unit works. It now holds
the memory instructions that are waiting for their memory dependences
to resolve. It provides which instructions are ready directly to the
IQ.
cpu/beta_cpu/regfile.hh:
Fix up sanity checks.
cpu/beta_cpu/rename_map.cc:
Fix loop variable type.
cpu/beta_cpu/rob_impl.hh:
Remove intermediate DynInstPtr
cpu/beta_cpu/store_set.cc:
Add in debugging statements.
cpu/beta_cpu/store_set.hh:
Reorder function arguments to match the rest of the calls.
--HG--
extra : convert_revision : aabf9b1fecd1d743265dfc3b174d6159937c6f44
273 lines
8.2 KiB
C++
273 lines
8.2 KiB
C++
/*
|
|
* Copyright (c) 2002-2004 The Regents of The University of Michigan
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions are
|
|
* met: redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions and the following disclaimer;
|
|
* redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution;
|
|
* neither the name of the copyright holders nor the names of its
|
|
* contributors may be used to endorse or promote products derived from
|
|
* this software without specific prior written permission.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
*/
|
|
|
|
#include <string>
|
|
#include <sstream>
|
|
#include <iostream>
|
|
|
|
#include "cpu/base_cpu.hh"
|
|
#include "base/cprintf.hh"
|
|
#include "cpu/exec_context.hh"
|
|
#include "base/misc.hh"
|
|
#include "sim/param.hh"
|
|
#include "sim/sim_events.hh"
|
|
|
|
#include "base/trace.hh"
|
|
|
|
using namespace std;
|
|
|
|
vector<BaseCPU *> BaseCPU::cpuList;
|
|
|
|
// This variable reflects the max number of threads in any CPU. Be
|
|
// careful to only use it once all the CPUs that you care about have
|
|
// been initialized
|
|
int maxThreadsPerCPU = 1;
|
|
|
|
extern void debug_break();
|
|
#ifdef FULL_SYSTEM
|
|
BaseCPU::BaseCPU(const string &_name, int _number_of_threads,
|
|
Counter max_insts_any_thread,
|
|
Counter max_insts_all_threads,
|
|
Counter max_loads_any_thread,
|
|
Counter max_loads_all_threads,
|
|
System *_system, Tick freq)
|
|
: SimObject(_name), frequency(freq),
|
|
number_of_threads(_number_of_threads), system(_system)
|
|
#else
|
|
BaseCPU::BaseCPU(const string &_name, int _number_of_threads,
|
|
Counter max_insts_any_thread,
|
|
Counter max_insts_all_threads,
|
|
Counter max_loads_any_thread,
|
|
Counter max_loads_all_threads)
|
|
: SimObject(_name), number_of_threads(_number_of_threads)
|
|
#endif
|
|
{
|
|
DPRINTF(FullCPU, "BaseCPU: Creating object, mem address %#x.\n", this);
|
|
|
|
debug_break();
|
|
|
|
// add self to global list of CPUs
|
|
cpuList.push_back(this);
|
|
|
|
DPRINTF(FullCPU, "BaseCPU: CPU added to cpuList, mem address %#x.\n",
|
|
this);
|
|
|
|
if (number_of_threads > maxThreadsPerCPU)
|
|
maxThreadsPerCPU = number_of_threads;
|
|
|
|
// allocate per-thread instruction-based event queues
|
|
comInstEventQueue = new (EventQueue *)[number_of_threads];
|
|
for (int i = 0; i < number_of_threads; ++i)
|
|
comInstEventQueue[i] = new EventQueue("instruction-based event queue");
|
|
|
|
//
|
|
// set up instruction-count-based termination events, if any
|
|
//
|
|
if (max_insts_any_thread != 0)
|
|
for (int i = 0; i < number_of_threads; ++i)
|
|
new SimExitEvent(comInstEventQueue[i], max_insts_any_thread,
|
|
"a thread reached the max instruction count");
|
|
|
|
if (max_insts_all_threads != 0) {
|
|
// allocate & initialize shared downcounter: each event will
|
|
// decrement this when triggered; simulation will terminate
|
|
// when counter reaches 0
|
|
int *counter = new int;
|
|
*counter = number_of_threads;
|
|
for (int i = 0; i < number_of_threads; ++i)
|
|
new CountedExitEvent(comInstEventQueue[i],
|
|
"all threads reached the max instruction count",
|
|
max_insts_all_threads, *counter);
|
|
}
|
|
|
|
// allocate per-thread load-based event queues
|
|
comLoadEventQueue = new (EventQueue *)[number_of_threads];
|
|
for (int i = 0; i < number_of_threads; ++i)
|
|
comLoadEventQueue[i] = new EventQueue("load-based event queue");
|
|
|
|
//
|
|
// set up instruction-count-based termination events, if any
|
|
//
|
|
if (max_loads_any_thread != 0)
|
|
for (int i = 0; i < number_of_threads; ++i)
|
|
new SimExitEvent(comLoadEventQueue[i], max_loads_any_thread,
|
|
"a thread reached the max load count");
|
|
|
|
if (max_loads_all_threads != 0) {
|
|
// allocate & initialize shared downcounter: each event will
|
|
// decrement this when triggered; simulation will terminate
|
|
// when counter reaches 0
|
|
int *counter = new int;
|
|
*counter = number_of_threads;
|
|
for (int i = 0; i < number_of_threads; ++i)
|
|
new CountedExitEvent(comLoadEventQueue[i],
|
|
"all threads reached the max load count",
|
|
max_loads_all_threads, *counter);
|
|
}
|
|
|
|
#ifdef FULL_SYSTEM
|
|
memset(interrupts, 0, sizeof(interrupts));
|
|
intstatus = 0;
|
|
#endif
|
|
}
|
|
|
|
|
|
void
|
|
BaseCPU::regStats()
|
|
{
|
|
using namespace Stats;
|
|
|
|
numCycles
|
|
.name(name() + ".numCycles")
|
|
.desc("number of cpu cycles simulated")
|
|
;
|
|
|
|
int size = execContexts.size();
|
|
if (size > 1) {
|
|
for (int i = 0; i < size; ++i) {
|
|
stringstream namestr;
|
|
ccprintf(namestr, "%s.ctx%d", name(), i);
|
|
execContexts[i]->regStats(namestr.str());
|
|
}
|
|
} else if (size == 1)
|
|
execContexts[0]->regStats(name());
|
|
}
|
|
|
|
|
|
void
|
|
BaseCPU::registerExecContexts()
|
|
{
|
|
for (int i = 0; i < execContexts.size(); ++i) {
|
|
ExecContext *xc = execContexts[i];
|
|
int cpu_id;
|
|
|
|
#ifdef FULL_SYSTEM
|
|
cpu_id = system->registerExecContext(xc);
|
|
#else
|
|
cpu_id = xc->process->registerExecContext(xc);
|
|
#endif
|
|
|
|
xc->cpu_id = cpu_id;
|
|
}
|
|
}
|
|
|
|
|
|
void
|
|
BaseCPU::switchOut()
|
|
{
|
|
// default: do nothing
|
|
}
|
|
|
|
void
|
|
BaseCPU::takeOverFrom(BaseCPU *oldCPU)
|
|
{
|
|
assert(execContexts.size() == oldCPU->execContexts.size());
|
|
|
|
for (int i = 0; i < execContexts.size(); ++i) {
|
|
ExecContext *newXC = execContexts[i];
|
|
ExecContext *oldXC = oldCPU->execContexts[i];
|
|
|
|
newXC->takeOverFrom(oldXC);
|
|
assert(newXC->cpu_id == oldXC->cpu_id);
|
|
#ifdef FULL_SYSTEM
|
|
system->replaceExecContext(newXC->cpu_id, newXC);
|
|
#else
|
|
assert(newXC->process == oldXC->process);
|
|
newXC->process->replaceExecContext(newXC->cpu_id, newXC);
|
|
#endif
|
|
}
|
|
|
|
#ifdef FULL_SYSTEM
|
|
for (int i = 0; i < NumInterruptLevels; ++i)
|
|
interrupts[i] = oldCPU->interrupts[i];
|
|
intstatus = oldCPU->intstatus;
|
|
#endif
|
|
}
|
|
|
|
|
|
#ifdef FULL_SYSTEM
|
|
void
|
|
BaseCPU::post_interrupt(int int_num, int index)
|
|
{
|
|
DPRINTF(Interrupt, "Interrupt %d:%d posted\n", int_num, index);
|
|
|
|
if (int_num < 0 || int_num >= NumInterruptLevels)
|
|
panic("int_num out of bounds\n");
|
|
|
|
if (index < 0 || index >= sizeof(uint64_t) * 8)
|
|
panic("int_num out of bounds\n");
|
|
|
|
AlphaISA::check_interrupts = 1;
|
|
interrupts[int_num] |= 1 << index;
|
|
intstatus |= (ULL(1) << int_num);
|
|
}
|
|
|
|
void
|
|
BaseCPU::clear_interrupt(int int_num, int index)
|
|
{
|
|
DPRINTF(Interrupt, "Interrupt %d:%d cleared\n", int_num, index);
|
|
|
|
if (int_num < 0 || int_num >= NumInterruptLevels)
|
|
panic("int_num out of bounds\n");
|
|
|
|
if (index < 0 || index >= sizeof(uint64_t) * 8)
|
|
panic("int_num out of bounds\n");
|
|
|
|
interrupts[int_num] &= ~(1 << index);
|
|
if (interrupts[int_num] == 0)
|
|
intstatus &= ~(ULL(1) << int_num);
|
|
}
|
|
|
|
void
|
|
BaseCPU::clear_interrupts()
|
|
{
|
|
DPRINTF(Interrupt, "Interrupts all cleared\n");
|
|
|
|
memset(interrupts, 0, sizeof(interrupts));
|
|
intstatus = 0;
|
|
}
|
|
|
|
|
|
void
|
|
BaseCPU::serialize(std::ostream &os)
|
|
{
|
|
SERIALIZE_ARRAY(interrupts, NumInterruptLevels);
|
|
SERIALIZE_SCALAR(intstatus);
|
|
}
|
|
|
|
void
|
|
BaseCPU::unserialize(Checkpoint *cp, const std::string §ion)
|
|
{
|
|
UNSERIALIZE_ARRAY(interrupts, NumInterruptLevels);
|
|
UNSERIALIZE_SCALAR(intstatus);
|
|
}
|
|
|
|
#endif // FULL_SYSTEM
|
|
|
|
DEFINE_SIM_OBJECT_CLASS_NAME("BaseCPU", BaseCPU)
|