Ross Thompson
396f697d2f
Hacky fix to prevent ITLBMissF and TrapM bug.
2022-04-12 17:56:23 -05:00
Ross Thompson
9dce2a0679
Towards allowing dtim + bus.
2022-03-11 14:58:21 -06:00
Ross Thompson
6e24a807f6
mild cleanup.
2022-03-11 13:05:47 -06:00
Ross Thompson
b7a680ec2a
Moved subcachelineread inside the cache. There is some ugliness to still resolve.
2022-03-11 12:44:04 -06:00
Ross Thompson
a18f06c20b
Moved subcacheline read inside the cache.
2022-03-11 11:03:36 -06:00
Ross Thompson
52cc852600
removed unused parameter.
2022-03-11 10:43:54 -06:00
Ross Thompson
6d914def08
Name cleanup.
2022-03-10 18:44:50 -06:00
Ross Thompson
63b1ea88c9
Signal name cleanup.
2022-03-10 18:26:58 -06:00
Ross Thompson
7a129c75cd
Added byte write enables to cache SRAMs.
2022-03-10 15:48:31 -06:00
Ross Thompson
7b96b3f73c
Moved cacheable signal into cache.
2022-03-08 16:34:02 -06:00
David Harris
2cea3349ad
LSU/Cache code review notes
2022-03-04 00:07:31 +00:00
Ross Thompson
6076f90bbc
Cache mods to be consistant with diagrams.
2022-02-14 12:40:51 -06:00
Ross Thompson
e852cb8a31
Eliminated more ports in cacheway.
2022-02-13 15:53:46 -06:00
Ross Thompson
1d7949513d
More cache cleanup.
2022-02-13 15:47:27 -06:00
Ross Thompson
7ffbc6b2ab
Changed names of signals in cache.
2022-02-13 15:06:18 -06:00
Ross Thompson
a5ad4331ec
More cache cleanup.
2022-02-13 12:38:39 -06:00
Ross Thompson
dd944265aa
Formating improvements to cache.
2022-02-11 23:10:58 -06:00
Ross Thompson
16abe90a0d
Reduced seladr to 1 bit as second bit is same as selflush.
2022-02-11 22:41:36 -06:00
Ross Thompson
b11e9eca7b
Reduced complexity of the address selection during flush.
2022-02-11 22:27:27 -06:00
Ross Thompson
1255e82154
Removed redundant signals from cache.
2022-02-11 22:23:47 -06:00
Ross Thompson
f716cce832
Replacement policy cleanup.
2022-02-10 11:40:10 -06:00
Ross Thompson
fdb4f909fc
Cleanup + critical path optimizations.
2022-02-10 11:11:16 -06:00
Ross Thompson
88c7a94aa9
Cache name clarifications.
2022-02-10 10:50:17 -06:00
Ross Thompson
32eee5a06a
More cache cleanup.
2022-02-10 10:43:37 -06:00
Ross Thompson
7ff715f44f
More cache cleanup.
2022-02-09 19:29:15 -06:00
Ross Thompson
36ab78ef3b
Removed all possilbe paths to PreSelAdr from TrapM.
2022-02-09 19:20:10 -06:00
Ross Thompson
4a7ebb3757
Cache cleanup write enables.
2022-02-08 17:52:09 -06:00
Ross Thompson
e2191e3637
Preparing to make a major change to the cache's write enables.
2022-02-08 09:47:01 -06:00
Ross Thompson
5c9e23527d
cachefsm cleanup.
2022-02-07 22:09:56 -06:00
Ross Thompson
da2dca9816
Removed VDWriteEnable.
2022-02-07 21:59:18 -06:00
Ross Thompson
161f907cae
more partial cleanup of fsm and write enables.
2022-02-07 17:41:56 -06:00
Ross Thompson
359a23237d
Progress towards simplifying the cache's write enables.
2022-02-07 17:23:09 -06:00
Ross Thompson
d21be9d998
Added config to allow using the save/restore or replay implementation to handle sram clocked read delay.
2022-02-04 23:49:07 -06:00
Ross Thompson
ea84211ff9
Removed unused ports from caches and buses.
2022-02-04 22:52:51 -06:00
Ross Thompson
290430cda8
Moved the sub cache line read logic to lsu/ifu.
2022-02-04 20:42:53 -06:00
Ross Thompson
725852362e
Got separate module for the sub cache line read.
2022-02-04 20:23:09 -06:00
Ross Thompson
cdd599e340
Second optimization of save/restore.
2022-02-04 14:35:12 -06:00
Ross Thompson
459054900f
Optimization of cache save/restore.
2022-02-04 14:21:04 -06:00
Ross Thompson
7c1f7e335c
Working first cut of the cache changes moving the replay to a save/restore.
...
The current implementation is too expensive costing (tag+linelen)*numway flip flops and muxes.
2022-02-04 13:31:32 -06:00
David Harris
65f3bf4e0a
cacheway cleanup
2022-02-03 16:52:22 +00:00
David Harris
eef04eed84
cacheway cleanup
2022-02-03 16:33:01 +00:00
David Harris
a6708ed887
cache cleanup
2022-02-03 15:36:11 +00:00
David Harris
325724f556
LSU Cleanup
2022-01-15 01:11:17 +00:00
David Harris
120fb7863f
Reformatted MIT license to 95 characters
2022-01-07 12:58:40 +00:00
Ross Thompson
0fddceffa6
Modified the mmu to not mux the lower 12 bits of the physical address and instead directly
...
assign from the input non translated virtual address. Since the lower bits never change there is
no reason to place these lower bits on a longer critical path.
The cache and lsu were previously using the lower bits from the virtual address rather than
the physical address. This change will allow us to keep the shorter critical path and
reduce the complexity of the lsu, ifu, and cache drawings.
2022-01-06 23:19:09 -06:00
Ross Thompson
008ac20a43
Minor optimization to cache replacement.
2022-01-06 17:19:14 -06:00
Ross Thompson
e1db967417
Clean up of cachefsm.
2022-01-06 16:32:49 -06:00
Ross Thompson
365b2715ed
More name cleanup in cache.
2022-01-05 22:37:53 -06:00
Ross Thompson
77efcad15b
Changed names of address in caches.
...
Removed old cache files.
2022-01-05 22:19:36 -06:00
Ross Thompson
8d33bf0b4a
Slower but correct implementation of flush.
2022-01-05 16:57:22 -06:00