Howard Mao
693a4ae00e
fix some more memory system bugs
2015-10-20 23:29:59 -07:00
Howard Mao
c311c9938e
nitpicky declaration move
2015-10-20 21:10:54 -07:00
Henry Cook
62765e9609
L2 rowBits param bugfix
2015-10-20 18:57:19 -07:00
Henry Cook
3fc630405b
Vectorize RoCC and Tile memory interfaces (bump uncore, rocket, zscale)
2015-10-20 15:05:12 -07:00
Howard Mao
4346111d2a
fix remaining vsim harness typo
2015-10-19 20:20:14 -07:00
Howard Mao
896aa892d1
bump uncore for TL -> NASTI converter fix
2015-10-19 15:31:59 -07:00
Henry Cook
8c3370c2e3
L2 AMOALU bugfix and simpler TileLinkParameters (bump rocket, uncore, zscale)
2015-10-16 19:15:47 -07:00
Howard Mao
c4117eb9a2
make sure TL parameters change properly throughout
...
* Outermost TL parameters should have the width set to be the same as the
MIF data width.
* Broadcast Hub and Narrower, which use different sets of TL parameters
should use the proper set of parameters at each interface
2015-10-14 18:03:39 -07:00
Henry Cook
4270fd78a5
Merge branch 'param-refactor-tl'
2015-10-14 12:16:22 -07:00
Henry Cook
dd5052888d
refactor tilelink params, compiles but ExampleSmallConfig fails
2015-10-13 23:44:05 -07:00
Howard Mao
a44e054c77
add support for different TileLink and MIF data widths
2015-10-13 12:46:23 -07:00
Henry Cook
9d11b64c75
added HasAddrMapParameters and GlobalAddrMap
2015-10-06 18:24:08 -07:00
Henry Cook
1c489d75c1
inject params at top-level for MemDessert
2015-10-06 16:26:58 -07:00
Henry Cook
c4eadbda57
Removed all traces of params
2015-10-06 11:42:06 -07:00
Henry Cook
38ae2707a3
refactor MemIO to not use params
2015-10-06 11:41:48 -07:00
Henry Cook
3d10a89907
refactor NASTI to not use param; new AddrMap class
2015-10-06 11:41:47 -07:00
Andrew Waterman
c2ad0b7dd4
Unfuck fpga-zynq submodule pointer
...
Sorry, Scott.
2015-10-01 15:00:35 -07:00
Andrew Waterman
996670a4a6
Point to correct Chisel commit
2015-10-01 10:31:29 -07:00
Howard Mao
a76f0bf8fb
fix involuntary release bug in rocket ProbeUnit
2015-09-30 17:26:48 -07:00
Andrew Waterman
8da7be3211
More Chisel3 compatibility fixes
2015-09-30 14:37:40 -07:00
Andrew Waterman
79cdf6efc0
Make perf counters optional
2015-09-28 13:56:08 -07:00
Howard Mao
353b00c8a1
revert some Chisel3-related changes and fix tlb bugs
2015-09-26 22:08:06 -07:00
Howard Mao
c517d9f6e3
fix htif emulator constructor in vcs_main
2015-09-25 17:21:09 -07:00
Howard Mao
7b0167b92e
make sure SCR and PCR data width matches xLen
2015-09-25 12:13:22 -07:00
Howard Mao
0e67d824b4
fix NASTI interconnect bug
2015-09-25 12:12:34 -07:00
Howard Mao
0d763524ef
make sure conf address map scales with number of cores
2015-09-25 09:41:19 -07:00
Howard Mao
5e3f9115d3
make sure HTIF mem_mb doesn't exceed MMIOBase
2015-09-25 09:02:35 -07:00
Schuyler Eldridge
f200d0947a
Force C++ emulator to always use 1GB for MEM_SIZE
...
Fixes #17
2015-09-24 23:56:41 -04:00
Howard Mao
c20ed350a0
even more Chisel3 compatability changes
2015-09-24 17:55:41 -07:00
Howard Mao
1c0111cc70
uncore merge commit
2015-09-24 17:10:45 -07:00
Howard Mao
8d4d8680bf
replace NASTIMasterIO and NASTISlaveIO with NASTIIO
2015-09-24 16:59:13 -07:00
Howard Mao
4a85c5a510
pull in hardfloat fixes
2015-09-24 16:58:49 -07:00
Scott Beamer
fbc6e695d3
remove bugs from float_fix
2015-09-23 16:11:47 -07:00
Scott Beamer
56daea793a
allow float_fix to take stdin (for piping)
2015-09-23 16:09:09 -07:00
Howard Mao
38a9b23ce7
add a flag to only log and dump after a certain number of cycles
2015-09-22 10:32:31 -07:00
Howard Mao
4496e8d4e2
make sure htif_emulator properly sets memory size
2015-09-22 10:32:31 -07:00
Howard Mao
56ecdff52d
Implement NASTI-based Mem/IO interconnect
2015-09-22 10:32:31 -07:00
Andrew Waterman
c6bcc832a1
Chisel3: Don't use Vec.fill for IOs
2015-09-20 13:43:56 -07:00
Andrew Waterman
fd58c52250
Update to latest chisel
2015-09-20 13:37:53 -07:00
Colin Schmidt
6f85ed191e
Add rocketchip_addons to the list of chisel srcs requiring rebuild
2015-09-16 12:28:03 -07:00
Colin Schmidt
7ecb936bf5
Remove -j from "make run-bmark-tests" in travis
...
+currently causes inconsistency in build success
+unclear what root cause is
2015-09-16 12:27:05 -07:00
Scott Beamer
de81762f7c
faster and more conservative float_fix
2015-09-15 17:19:29 -07:00
Scott Beamer
7e25b1ce03
cleaner/faster comlog without linear search
2015-09-15 17:19:29 -07:00
Christopher Celio
754c47bdd1
Removed "make debug" test from travis
...
- currently causes gcc4.8 to crash
- likely due to high memory requirements in compiling generated c++
code for debug/vcd output
2015-09-14 15:45:50 -07:00
Colin Schmidt
d355d81633
regression script bump for new torture that can produce waveforms
2015-09-14 13:00:54 -07:00
Scott Beamer
3eed7ff238
make float_fix more conservative with replacement
2015-09-12 11:00:00 -07:00
Scott Beamer
a12cd13190
tool to unrecode single floats from commit logs
2015-09-11 20:19:18 -07:00
Christopher Celio
c2344ee2bc
Added generated-src-debug to make clean target
2015-09-11 19:07:33 -07:00
Christopher Celio
c9d89226fb
Generated *.d file of tests now kept in order
...
-Changed Set to LinkedHashSet in Testing.scala
2015-09-11 18:36:04 -07:00
Christopher Celio
c8a7deb950
Added a commitlog post-processor for Rocket
...
- Useful for taking Rocket's out-of-order writebacks and generating an
in-order commit log.
- Resulting commit log can be diffed against Spike's commit log.
2015-09-11 16:06:01 -07:00