It's not necessary to use addr_beat to determine where to put the Grant
data. Just stripe it across all lanes.
This also gets rid of a dependence on addr_beat in Grant. If we move
towards a regime where TileLink is only narrowed, not widened, we may
be able to drop the field altogether.
To elide several races between reading and writing the metadata array for different types of transactions, all L2XactTrackers can now sink Voluntary Releases (writebacks from the L1 in the current implementation). These writebacks are merged with the ongoing transaction, and the merging tracker supplies an acknowledgment of the writeback in addition to its ongoing activities. This change involved another refactoring of the control logic for allocating new trackers and routing incoming Acquires and Releases. BroadcastHub uses the new routing logic, but still processes all voluntary releases through the VoluntaryReleaseTracker (not a problem because there are no metadata update races).
Closes#18Closes#20
This uses an reorder queue but doesn't check to ensure that the data it fetches
from the queue is actually in the queue before using it. It seems that during
correct operation this never breaks, but I'm trying to get the backup memory
port working again and this assertion fails with it enabled (without the
assertion the core just gets a bogus data beat dies).
Closes#16
Exposes new parameter field SplitMetadata to determine whether the metadata array in a particular cache is stored in a single SeqMem or with one SeqMem per way.
Closes#14
This was recently changed to write out physical addresses for SCR file entries,
but to bring up the chip we need SCR offsets so we can write the uncore SCR
file over HTIF. This changes the map generator to generate both.
Without this change things happened to work anyway because the high bits were
getting dropped by the SCR file.
