Ross Thompson
2fc8080102
Got the srams parameterized correctly now.
2023-06-15 13:42:24 -05:00
Ross Thompson
e431f90cf3
Found a whole bunch of files still using the old `define configurations.
2023-06-15 13:09:07 -05:00
Ross Thompson
6bb5f32eb9
Improved simulation speed by gating bitmanip zbc's clmul's X and Y inputs with BSelect != 11. Reduced simulation time from 3m45s to 2m35s.
2023-06-14 15:28:58 -05:00
Ross Thompson
9a1042b0b1
This parameterizes the testbench but does not use the verilator updates or the new testbench.
2023-06-12 11:00:30 -05:00
Ross Thompson
9bae203d1c
Updated parameterization types. Modelsim version 2022.1 did requires defaults to a 32 bit integer. The base and ranges for the address decoder need to be larger.
2023-06-09 09:28:24 -05:00
David Harris
62a8332c8f
Merge pull request #313 from ross144/main
...
Fix extraneous force in testbench which keep btb in reset.
2023-06-06 08:41:34 -07:00
David Harris
df212ce7d8
Merge pull request #312 from ross144/main
...
Fixed typo in coremark makefile.
2023-06-06 05:44:22 -07:00
Ross Thompson
822e60bd3d
Found the coremark performance issue. The testbench was continuously forcing the BTB to all zeros. Once fixed it resolved the performance problem.
2023-06-05 15:42:05 -05:00
James Stine
51d77b0414
Update some spacing to make it look better
2023-06-05 11:03:06 -05:00
Ross Thompson
e56497101a
Updated source code to be compatible with verilator 5.011 for lint only.
2023-05-31 10:44:23 -05:00
Ross Thompson
ab91fe7436
Cleanup parameterization for verilator 5.010.
2023-05-31 10:02:34 -05:00
Ross Thompson
3c94c186db
Possible fix for Linux bug and bug 203. ImperasDV mismatches in linux boot around 571M instructions after the login prompt.
...
This bug occurs when there are back to back HPTW requests and the first generates an access fault during the walk. The old implementation uses a delayed version of the fault to prevent the HTPW fsm from transitioning out of the IDLE state. Because the first request generates the fault and the second request is pipelined the second request appears as if it also faults so the FSM does not perform the walk.
The new implementation adds a FAULT state. When the HPTW generates an access fault it transitions to this state removes the HPTWStall and then transitions to IDLE. There may still be a remaining bug here if the pipeline is stalled for another reason. However I don't think it is possible by construction. The only possible sources of stalls at this point would be IFU and LSU stalls and both are required to make this condition happen.
2023-05-30 15:20:24 -05:00
Ross Thompson
903f2f9063
Merge branch 'param-lim-merge'
2023-05-26 16:25:35 -05:00
Ross Thompson
b8474b208e
Uncore is now parameterized.
2023-05-26 16:24:12 -05:00
Ross Thompson
340aac0934
Got the branch predictor parameterized using Lim's method. Also had to add a global enum included in both cvw.sv and the configs which defines the branch predictor types. This should be synthesizable, but I'll need to double check.
2023-05-26 16:00:14 -05:00
Ross Thompson
e6d25b7f70
Finished fpu parameterization using Lim's method.
2023-05-26 14:40:06 -05:00
Ross Thompson
ef2bb7df93
fdiv is now parameterized using Lim's method.
2023-05-26 14:25:14 -05:00
Ross Thompson
c76eb315bc
Parameterized fpu's unpack and fma using Lim's method.
2023-05-26 14:12:25 -05:00
Ross Thompson
923c00b928
I think I've solved the slow down issue. Parameters can't be mixed with cvw_t and other types.
2023-05-26 13:56:51 -05:00
Ross Thompson
8aba897386
Update top level parameterized. Simulation slowed down to 4.5 minutes.
2023-05-26 12:13:11 -05:00
Ross Thompson
d47951fb51
The privileged unit is parameterized using Lim's method.
2023-05-26 12:03:46 -05:00
Ross Thompson
dd7c7f0a39
Completed LSU parameterization based on Lim's changes.
2023-05-26 11:26:09 -05:00
Ross Thompson
0c2a54540b
Subwordread now parameterized.
2023-05-26 11:22:44 -05:00
Ross Thompson
3765ebfb9f
PMA checker's address decoder is now parameterized. I did not see bit slicing in Lim's code. I'm not sure how they got around this issue.
2023-05-26 11:06:48 -05:00
Ross Thompson
60bcd3d21a
Progress on LSU.
2023-05-26 10:47:09 -05:00
Ross Thompson
7c364d5a77
Updated mmu's tlb and hptw to use Lim's parameterization.
2023-05-24 18:02:22 -05:00
Ross Thompson
438c955d1c
PM(P/A) checkers parameterized based on Lim's work.
2023-05-24 17:20:55 -05:00
Ross Thompson
febb2442db
Partial parameterization into mmu.
2023-05-24 16:12:41 -05:00
Ross Thompson
7fc53226ac
MDU and hazard unit now also parameterized. Based on Lim's work. Again I want to clarify this their work. Not mine. I'm just doing this because the merge had an issue.
2023-05-24 15:01:35 -05:00
Ross Thompson
8f9151b125
More parameterization. Based on Lim's work. EBU, IFU (except bpred), and IEU done.
2023-05-24 14:56:02 -05:00
Ross Thompson
e33db7f9a7
More parameterization. Copied Lim. Still no slow down.
2023-05-24 14:49:22 -05:00
Ross Thompson
d3123fc00a
Updated a large number of the source files to use parameters rather than `defines. Based on Lim's work. So far there is no simulation slow down.
2023-05-24 14:05:44 -05:00
Ross Thompson
3de3a42f97
Merged changes.
2023-05-24 13:15:52 -05:00
Ross Thompson
b28a75f32a
Updated headers to local branch history predictors.
2023-05-24 12:52:42 -05:00
Ross Thompson
c5aeb08e5c
Trying to figure out why the parameterization slowed down modelsim so much.
2023-05-24 12:44:42 -05:00
Ross Thompson
6163fc29e1
Adds local history predictor.
...
Fixes performance counters, but not coremark.
2023-05-23 18:53:46 -05:00
Ross Thompson
1dc7fb567b
Merge branch 'localhistory'
...
Repair to wave file.
Created implementations of local history. Part of my Ph.D. research.
2023-05-22 10:13:31 -05:00
Ross Thompson
81b33fb48e
Fixes load and store stall counters.
2023-05-22 10:08:49 -05:00
Ross Thompson
2612ca4062
Merge branch 'main' of https://github.com/openhwgroup/cvw
2023-05-11 14:56:53 -05:00
Ross Thompson
03823a9bc1
Partially working local history repair.
2023-05-11 14:56:26 -05:00
Ross Thompson
e34b25511a
Baseline localhistory with speculative repair built.
2023-05-05 15:23:45 -05:00
Ross Thompson
faf71294d6
Fixed bug in local history predictor.
2023-05-04 16:54:41 -05:00
Ross Thompson
e11d42b270
Almost working ahead pipelined local history predictor.
2023-05-04 16:17:31 -05:00
Ross Thompson
8da2b18543
Maybe I finally have the ahead pipelined local history predictor working.
2023-05-04 14:11:34 -05:00
Ross Thompson
afafa9718d
Ahead pipelining is not yet working. :(
2023-05-03 17:41:38 -05:00
Ross Thompson
35a59a1193
I think ahead pipelining is working for local history.
2023-05-03 12:52:32 -05:00
Ross Thompson
c4d6724867
Updated configs for local branch history `defines.
2023-05-02 11:11:04 -05:00
Ross Thompson
9ee6ba8964
Added comment explaining the difference between global history and local history basic implementations.
2023-05-02 11:01:46 -05:00
Ross Thompson
799c25cc60
Swapped the m and k parameters for local history predictor.
2023-05-02 10:52:41 -05:00
Ross Thompson
b9abb2a491
Maybe have the baseline local history predictor working.
2023-05-01 15:45:27 -05:00
