c069e66056
Modify the RoCC interface to include status in the command queue. ( #41 )
...
This addresses a bug in which changes in mstatus could
propagate to RoCCs before their time. Existing RoCCs that use
the status port will need to be modified to match this change.
This addresses the first half of #40 .
2016-07-18 17:40:50 -07:00
9eeb1112d4
fix Bufferless irel_vs_iacq_conflict signal
2016-07-18 17:38:20 -07:00
e5cccc0526
don't update xact_vol_irel if not a voluntary irel
2016-07-18 17:05:23 -07:00
2723b2f515
fix issues in SimpleHellaCacheIF and document the changes
2016-07-18 17:02:47 -07:00
40a146f625
HellaCacheArbiter passes through if n == 1
2016-07-18 17:01:29 -07:00
39a1ecbf3c
switch groundtest to merged master
2016-07-18 09:34:27 -07:00
359252fdc1
fix a width bug
2016-07-18 09:33:17 -07:00
6fc4236782
add atomic and prefetch drivers
2016-07-18 09:33:17 -07:00
2ec736ed67
reorder some code in the Nasti unit tests
2016-07-18 09:33:17 -07:00
3ea299b062
make unit test debug output more meaningful
2016-07-18 09:33:17 -07:00
def740406c
fix a few Driver bugs
2016-07-18 09:33:17 -07:00
8278a73e83
group unit tests by their tested interface
2016-07-18 09:33:17 -07:00
9c0fffdd1c
start constructing composable tilelink unit test drivers
2016-07-18 09:33:17 -07:00
c92732dcaa
rename MemoryTestDriver to NastiDriver
2016-07-18 09:33:16 -07:00
c906e6edde
some renaming
2016-07-18 09:33:16 -07:00
1c2bf6e938
make list of unit tests a a parameter
2016-07-18 09:33:16 -07:00
69eebaf362
factor out unit tests into separate package
2016-07-18 09:33:16 -07:00
4af6313288
TraceGen: Lookup -> MuxLookup
...
A recent commit to tracegen.scala introduced a call to BitPat() which
seems to mess up the subsequent call to Lookup(). (This function
seems undocumented so I'm not sure what's going on.) As a fix, I've
removed the call to BitPat() and replaced Lookup() with MuxLookup().
2016-07-17 22:28:18 +01:00
e08ec42bc0
refactor groundtest unittests into separate package
2016-07-16 23:19:55 -07:00
59d700bf66
fix combinational loop in NASTI -> HASTI converter
2016-07-15 18:45:37 -07:00
cff8de9814
Use new Mul/Div parameters vs UseFastMulDiv ( #48 )
...
* Use new Mul/Div parameters vs UseFastMulDiv
* Rename MulDivUnroll to MulUnroll
2016-07-15 15:41:20 -07:00
407bc95c42
Rename MulDivUnroll to MulUnroll
2016-07-15 15:40:17 -07:00
897e6ccf8a
fix Hasti and Smi converters
2016-07-15 15:39:00 -07:00
4c26a6bc96
Create seperate Mul/Div paramters instead of UseFastMulDiv
2016-07-15 14:40:37 -07:00
84098db81f
add a TileLinkTestRAM
2016-07-15 11:03:26 -07:00
7cf44f9b25
clean up WideCounter implementation
2016-07-15 00:51:01 -07:00
ba08255450
bump rocket
2016-07-14 22:11:19 -07:00
d78f1aacd0
Clean up some zero-width wire cases using UInt.extract
2016-07-14 22:08:01 -07:00
da512d4230
Explicitly discard BTB index LSBs
2016-07-14 17:10:27 -07:00
768403f8fa
Bump rocket; remove ICacheBufferWays parameter
2016-07-14 12:50:16 -07:00
e6aab368a4
Replace ICacheBufferWays parameter with I$ constructor argument
2016-07-14 12:38:54 -07:00
3d0b92afd7
Misc code cleanup
2016-07-14 12:09:34 -07:00
b8884e8143
Simplify frontend virtual address extension code
2016-07-14 12:05:09 -07:00
66b9c5ad05
fix up cloneType calls in clock crossers
2016-07-13 14:31:19 -07:00
eeae74e3fc
nasti: include convenient clock crossing helpers
2016-07-13 14:20:25 -07:00
c33c0944be
crossing: first clock crossing, the handshaker
2016-07-13 14:20:25 -07:00
18ea58c85f
remove unnecessary CAMs from converters
2016-07-13 12:42:50 -07:00
b122a54c32
don't allow more outer IDs than inner IDs
2016-07-13 12:42:28 -07:00
37fd11870c
fix up ReorderQueue CAM
2016-07-13 12:11:43 -07:00
de1e25f3d1
reduce usage of CAMs in converters
2016-07-13 11:20:50 -07:00
c0dc09b3a1
don't use CAM in ReorderQueue if not necessary
2016-07-13 11:08:15 -07:00
f3775df04d
fix the condition under which comparator error signal is set
2016-07-12 18:37:13 -07:00
4c79215fde
add a script for checking comparator trace
2016-07-12 14:42:04 -07:00
88dc0b983a
make sure Comparator logs correctly when prefetching off
2016-07-12 14:36:46 -07:00
676a536706
fix bugs from adding ComparatorSource backpressure
2016-07-12 13:50:34 -07:00
d435bb4185
reduce hardware usage of Comparator to allow it to synthesize
2016-07-12 10:54:18 -07:00
2f70136f90
Fix the Nasti to Smi Converter for single-word Nasti busses
...
There's a register that tracks what word within a Nasti transaction a
Smi response cooresponds to, since Smi itself doesn't have any
multi-word stuff. This breaks the single-word Nasti to Smi converter
due to what's essentially a 0-width wire bug: it ends up doing something
like
word_offset_into_nasti := nasti_address(3, 3)
when "word_offset_into_nasti" should really be a 0-bit register, but due
to some log2Up block size calculation logic it's actually a 1-bit
register. Thus, this expression ends up grabbing a bit of the address,
which causes odd addresses to get buffered incorrectly.
My fix is to just special-case the "Nasti bus width is the same as Smi
bus width" case.
2016-07-12 09:31:21 -07:00
90bcd3dbdc
make sure DirectGroundTest testers given correct TL settings
2016-07-11 18:11:01 -07:00
8f0fa11ce4
optionally export detailed status information in DirectGroundTest
2016-07-11 18:11:00 -07:00
b64998ec05
make sure dramsim reads and writes occur in the order they are received
2016-07-11 18:11:00 -07:00
