Ross Thompson
050523487c
Changed names of lsu address signals.
2021-12-29 15:03:34 -06:00
Ross Thompson
b1116600fe
Added more generates around virtual memory and csrs in the lsu.
2021-12-29 14:48:09 -06:00
Ross Thompson
7fe70c3cc6
Removed the fault state from the hptw. Now writing TLB faults into the I/DTLBs. This has two advantages.
...
1: It simplifies the interactions between the caches and the hptw.
2: instruction page faults are fetched 3 times, caching them in the ITLB speeds up this process.
There are two downsides.
1: Pollute the TLBs with not very relavent translations
2: Have to compute the misalignment. This can be cached in the TLB which only costs 1 flip flop
for each TLB line.
2021-12-23 12:40:22 -06:00
Ross Thompson
f863bdc495
linux-wave.do changes.
2021-12-21 22:37:55 -06:00
Ross Thompson
50b307bc0e
Looks like rdtime was accidentally replaced with rrame from a find and replace.
2021-12-20 21:26:38 -06:00
Ross Thompson
8416cae3fe
Fixed Type 5b interaction between dcache and hptw.
...
This is a load concurrent with ITLBMiss.
2021-12-20 18:33:31 -06:00
Ross Thompson
d3c3422d12
Rename of SelPTW to SelHPTW.
2021-12-19 22:24:07 -06:00
Ross Thompson
225cd5a114
Renamed MemAdrM to IEUAdrM. This will free the name MemAdrm for use in the DCache.
2021-12-19 14:00:30 -06:00
David Harris
0f319b45c1
Do File cleanups
2021-12-17 17:45:26 -08:00
bbracker
f7b2d3b6df
fix recursive signal logging for graphical sims
2021-12-08 16:07:26 -08:00
bbracker
23194c0308
fix parseState.py to correctly take in PMPCFG
2021-11-24 16:52:51 -08:00
bbracker
4e96d0f1db
add checkpoints to regression
2021-11-20 19:42:53 -08:00
bbracker
0c7681b942
fix testbench interrupt timing
2021-11-02 21:19:12 -07:00
bbracker
66e53929ce
adapt testbench linux to use reset_ext
2021-10-25 13:26:44 -07:00
bbracker
13763b002a
switch linux graphical sim over to Ross's waves
2021-10-24 18:39:23 -07:00
bbracker
5d60a3a9df
update linux wave-do
2021-10-07 19:15:11 -04:00
David Harris
b3bded9e6c
Added more pipeline stage suffixes to divider
2021-10-02 22:54:01 -04:00
Ross Thompson
221dbe92b2
Fixed the amo on dcache miss cpu stall issue.
2021-09-17 22:15:03 -05:00
Ross Thompson
e16c27225b
Finished adding the d cache flush. Required ensuring the write data, address, and size are
...
correct when transmitting to AHBLite interface.
2021-09-17 13:03:04 -05:00
Ross Thompson
0b1e59d075
Updated Dcache to fully support flush. This appears to work.
...
Updated PCNextF so it points to the correct PC after icache invalidate.
Build root crashes with PCW mismatch and invalid register writes.
2021-09-17 10:25:21 -05:00
Ross Thompson
6a9fa2fae3
Fixed bugs I introduced to the icache.
2021-08-27 15:00:40 -05:00
Ross Thompson
983524e81b
Updated linux test bench documenation and scripts.
2021-08-25 10:54:47 -05:00
Ross Thompson
fe378f2692
Added function tracking to linux test bench.
2021-08-24 11:08:46 -05:00
Ross Thompson
6c57002d0e
Added logic to linux test bench to not stop simulation on csr write faults.
2021-08-15 11:13:32 -05:00
Ross Thompson
af2c6fd6ff
Updated linux-wave.do to have cursors at the timer interrupt problem.
2021-08-13 17:29:37 -05:00
Ross Thompson
55fda4de62
Switched ExceptionM to dcache to be just exceptions.
...
Added test bench logic to hold forces until the W stage is unstalled.
2021-08-13 15:53:50 -05:00
Ross Thompson
e141a00934
Cleaned up the linux testbench by removing old code and signals.
...
Added back in the csr checking logic.
Added code to force timer, external, and software interrupts by using the expected
values from qemu's (m/s)cause registers.
Still need to prevent wally's timer interrupt.
2021-08-13 14:39:05 -05:00
Ross Thompson
cce0571925
Fixed another bug with the atomic instrucitons implemention in the dcache.
2021-08-08 22:50:31 -05:00
Ross Thompson
d3be04b7de
Fixed another bug with AMO. If the CPU stalled as an AMO was finishing, the write to the
...
cache's SRAM would occur. Then in the next cycle the SRAM would be reread while stalled
providing the new update dated rather than the correct older value.
2021-08-08 11:42:10 -05:00
Ross Thompson
fc7016eea6
Fixed the AMO dcache bug. The subword write needs to occur before the AMO logic.
...
Fixed logic for trace update in the M and W stages. The M stage should not update if there
is an instruction fault.
2021-08-08 00:28:18 -05:00
Ross Thompson
0bfbcef8ab
Now past the CLINT issues.
2021-08-06 16:16:39 -05:00
Ross Thompson
9be10cdc8b
Partial conversion of the linux trace checking to read in the file in the Memory Stage so it is possible to overwrite registers, memory, and interrupts.
2021-08-06 16:06:50 -05:00
Ross Thompson
c749d08542
fixed the read timer issue but we still have problems with interrupts and i/o devices.
2021-08-06 10:16:06 -05:00
