gem5/cpu/beta_cpu/rob_impl.hh
Kevin Lim 61d95de4c8 Large update of several parts of my code. The most notable change is the inclusion of a full-fledged load/store queue. At the moment it still has some issues running, but most of the code is hopefully close to the final version.
SConscript:
arch/isa_parser.py:
cpu/base_dyn_inst.cc:
    Remove OOO CPU stuff.
arch/alpha/faults.hh:
    Add fake memory fault.  This will be removed eventually.
arch/alpha/isa_desc:
    Change EA comp and Mem accessor to be const StaticInstPtrs.
cpu/base_dyn_inst.hh:
    Update read/write calls to use load queue and store queue indices.
cpu/beta_cpu/alpha_dyn_inst.hh:
    Change to const StaticInst in the register accessors.
cpu/beta_cpu/alpha_dyn_inst_impl.hh:
    Update syscall code with thread numbers.
cpu/beta_cpu/alpha_full_cpu.hh:
    Alter some of the full system code so it will compile without errors.
cpu/beta_cpu/alpha_full_cpu_builder.cc:
    Created a DerivAlphaFullCPU class so I can instantiate different CPUs that have different template parameters.
cpu/beta_cpu/alpha_full_cpu_impl.hh:
    Update some of the full system code so it compiles.
cpu/beta_cpu/alpha_params.hh:
cpu/beta_cpu/fetch_impl.hh:
    Remove asid.
cpu/beta_cpu/comm.hh:
    Remove global history field.
cpu/beta_cpu/commit.hh:
    Comment out rename map.
cpu/beta_cpu/commit_impl.hh:
    Update some of the full system code so it compiles.  Also change it so that it handles memory instructions properly.
cpu/beta_cpu/cpu_policy.hh:
    Removed IQ from the IEW template parameter to make it more uniform.
cpu/beta_cpu/decode.hh:
    Add debug function.
cpu/beta_cpu/decode_impl.hh:
    Slight updates for decode in the case where it causes a squash.
cpu/beta_cpu/fetch.hh:
cpu/beta_cpu/rob.hh:
    Comment out unneccessary code.
cpu/beta_cpu/full_cpu.cc:
    Changed some of the full system code so it compiles.  Updated exec contexts and so forth to hopefully make multithreading easier.
cpu/beta_cpu/full_cpu.hh:
    Updated some of the full system code to make it compile.
cpu/beta_cpu/iew.cc:
    Removed IQ from template parameter to IEW.
cpu/beta_cpu/iew.hh:
    Removed IQ from template parameter to IEW. Updated IEW to recognize the Load/Store queue.
cpu/beta_cpu/iew_impl.hh:
    New handling of memory instructions through the Load/Store queue.
cpu/beta_cpu/inst_queue.hh:
    Updated comment.
cpu/beta_cpu/inst_queue_impl.hh:
    Slightly different handling of memory instructions due to Load/Store queue.
cpu/beta_cpu/regfile.hh:
    Updated full system code so it compiles.
cpu/beta_cpu/rob_impl.hh:
    Moved some code around; no major functional changes.
cpu/ooo_cpu/ooo_cpu.hh:
    Slight updates to OOO CPU; still does not work.
cpu/static_inst.hh:
    Remove OOO CPU stuff.  Change ea comp and mem acc to return const StaticInst.
kern/kernel_stats.hh:
    Extra forward declares added due to compile error.

--HG--
extra : convert_revision : 594a7cdbe57f6c2bda7d08856fcd864604a6238e
2005-05-03 10:56:47 -04:00

283 lines
7.2 KiB
C++

#ifndef __CPU_BETA_CPU_ROB_IMPL_HH__
#define __CPU_BETA_CPU_ROB_IMPL_HH__
#include "cpu/beta_cpu/rob.hh"
template <class Impl>
ROB<Impl>::ROB(unsigned _numEntries, unsigned _squashWidth)
: numEntries(_numEntries),
squashWidth(_squashWidth),
numInstsInROB(0),
squashedSeqNum(0)
{
doneSquashing = true;
}
template <class Impl>
void
ROB<Impl>::setCPU(FullCPU *cpu_ptr)
{
cpu = cpu_ptr;
// Set the tail to the beginning of the CPU instruction list so that
// upon the first instruction being inserted into the ROB, the tail
// iterator can simply be incremented.
tail = cpu->instList.begin();
// Set the squash iterator to the end of the instruction list.
squashIt = cpu->instList.end();
}
template <class Impl>
int
ROB<Impl>::countInsts()
{
// Start at 1; if the tail matches cpu->instList.begin(), then there is
// one inst in the ROB.
int return_val = 1;
// There are quite a few special cases. Do not use this function other
// than for debugging purposes.
if (cpu->instList.begin() == cpu->instList.end()) {
// In this case there are no instructions in the list. The ROB
// must be empty.
return 0;
} else if (tail == cpu->instList.end()) {
// In this case, the tail is not yet pointing to anything valid.
// The ROB must be empty.
return 0;
}
// Iterate through the ROB from the head to the tail, counting the
// entries.
for (InstIt_t i = cpu->instList.begin(); i != tail; ++i)
{
assert(i != cpu->instList.end());
++return_val;
}
return return_val;
// Because the head won't be tracked properly until the ROB gets the
// first instruction, and any time that the ROB is empty and has not
// yet gotten the instruction, this function doesn't work.
// return numInstsInROB;
}
template <class Impl>
void
ROB<Impl>::insertInst(DynInstPtr &inst)
{
// Make sure we have the right number of instructions.
assert(numInstsInROB == countInsts());
// Make sure the instruction is valid.
assert(inst);
DPRINTF(ROB, "ROB: Adding inst PC %#x to the ROB.\n", inst->readPC());
// If the ROB is full then exit.
assert(numInstsInROB != numEntries);
++numInstsInROB;
// Increment the tail iterator, moving it one instruction back.
// There is a special case if the ROB was empty prior to this insertion,
// in which case the tail will be pointing at instList.end(). If that
// happens, then reset the tail to the beginning of the list.
if (tail != cpu->instList.end()) {
++tail;
} else {
tail = cpu->instList.begin();
}
// Make sure the tail iterator is actually pointing at the instruction
// added.
assert((*tail) == inst);
DPRINTF(ROB, "ROB: Now has %d instructions.\n", numInstsInROB);
}
// Whatever calls this function needs to ensure that it properly frees up
// registers prior to this function.
template <class Impl>
void
ROB<Impl>::retireHead()
{
assert(numInstsInROB == countInsts());
assert(numInstsInROB > 0);
// Get the head ROB instruction.
DynInstPtr head_inst = cpu->instList.front();
// Make certain this can retire.
assert(head_inst->readyToCommit());
DPRINTF(ROB, "ROB: Retiring head instruction of the ROB, "
"instruction PC %#x, seq num %i\n", head_inst->readPC(),
head_inst->seqNum);
// Keep track of how many instructions are in the ROB.
--numInstsInROB;
// Tell CPU to remove the instruction from the list of instructions.
// A special case is needed if the instruction being retired is the
// only instruction in the ROB; otherwise the tail iterator will become
// invalidated.
cpu->removeFrontInst(head_inst);
if (numInstsInROB == 0) {
tail = cpu->instList.end();
}
}
template <class Impl>
bool
ROB<Impl>::isHeadReady()
{
if (numInstsInROB != 0) {
return cpu->instList.front()->readyToCommit();
}
return false;
}
template <class Impl>
unsigned
ROB<Impl>::numFreeEntries()
{
assert(numInstsInROB == countInsts());
return numEntries - numInstsInROB;
}
template <class Impl>
void
ROB<Impl>::doSquash()
{
DPRINTF(ROB, "ROB: Squashing instructions.\n");
assert(squashIt != cpu->instList.end());
for (int numSquashed = 0;
numSquashed < squashWidth && (*squashIt)->seqNum != squashedSeqNum;
++numSquashed)
{
// Ensure that the instruction is younger.
assert((*squashIt)->seqNum > squashedSeqNum);
DPRINTF(ROB, "ROB: Squashing instruction PC %#x, seq num %i.\n",
(*squashIt)->readPC(), (*squashIt)->seqNum);
// Mark the instruction as squashed, and ready to commit so that
// it can drain out of the pipeline.
(*squashIt)->setSquashed();
(*squashIt)->setCanCommit();
// Special case for when squashing due to a syscall. It's possible
// that the squash happened after the head instruction was already
// committed, meaning that (*squashIt)->seqNum != squashedSeqNum
// will never be false. Normally the squash would never be able
// to go past the head of the ROB; in this case it might, so it
// must be handled otherwise it will segfault.
#ifndef FULL_SYSTEM
if (squashIt == cpu->instList.begin()) {
DPRINTF(ROB, "ROB: Reached head of instruction list while "
"squashing.\n");
squashIt = cpu->instList.end();
doneSquashing = true;
return;
}
#endif
// Move the tail iterator to the next instruction.
squashIt--;
}
// Check if ROB is done squashing.
if ((*squashIt)->seqNum == squashedSeqNum) {
DPRINTF(ROB, "ROB: Done squashing instructions.\n");
squashIt = cpu->instList.end();
doneSquashing = true;
}
}
template <class Impl>
void
ROB<Impl>::squash(InstSeqNum squash_num)
{
DPRINTF(ROB, "ROB: Starting to squash within the ROB.\n");
doneSquashing = false;
squashedSeqNum = squash_num;
assert(tail != cpu->instList.end());
squashIt = tail;
doSquash();
}
template <class Impl>
uint64_t
ROB<Impl>::readHeadPC()
{
assert(numInstsInROB == countInsts());
DynInstPtr head_inst = cpu->instList.front();
return head_inst->readPC();
}
template <class Impl>
uint64_t
ROB<Impl>::readHeadNextPC()
{
assert(numInstsInROB == countInsts());
DynInstPtr head_inst = cpu->instList.front();
return head_inst->readNextPC();
}
template <class Impl>
InstSeqNum
ROB<Impl>::readHeadSeqNum()
{
// Return the last sequence number that has not been squashed. Other
// stages can use it to squash any instructions younger than the current
// tail.
DynInstPtr head_inst = cpu->instList.front();
return head_inst->seqNum;
}
template <class Impl>
uint64_t
ROB<Impl>::readTailPC()
{
assert(numInstsInROB == countInsts());
assert(tail != cpu->instList.end());
return (*tail)->readPC();
}
template <class Impl>
InstSeqNum
ROB<Impl>::readTailSeqNum()
{
// Return the last sequence number that has not been squashed. Other
// stages can use it to squash any instructions younger than the current
// tail.
return (*tail)->seqNum;
}
#endif // __CPU_BETA_CPU_ROB_IMPL_HH__