1
0
Commit Graph

838 Commits

Author SHA1 Message Date
Andrew Waterman
2c875555a2 Separate exception return control from exception control 2015-03-17 00:14:32 -07:00
Andrew Waterman
e85c54cc4b New privileged ISA implementation 2015-03-14 02:49:07 -07:00
Yunsup Lee
ebbd14254c uncached port should be a HeaderlessUncachedTileLinkIO type 2015-03-13 02:12:23 -07:00
Henry Cook
51e4cd7616 Added UncachedTileLinkIO port to RocketTile, simplify arbitration 2015-03-12 16:30:04 -07:00
Yunsup Lee
ea018b3d84 stall rocket decode when not rocc ready 2015-03-11 22:33:03 -07:00
Colin Schmidt
e293d89035 fix decodelogic bug for bitwidths >= 64 s/1L/BigInt(1)/ 2015-03-10 10:28:05 -07:00
Henry Cook
95aa295c39 Use HeaderlessTileLinkIO to cut down on unconnected port errors in VCS 2015-03-09 16:34:43 -07:00
Henry Cook
b36d751250 sret bugfix: bypass arbiter 2015-03-05 13:14:16 -08:00
Henry Cook
35532420a8 Merge pull request #6 from ccelio/master
Clarified ptw/tlb/sret/cache I/O bundles
2015-03-03 18:01:26 -08:00
Christopher Celio
06dea3790a Removed sret from ptw; sret now comes thru io.cpu to dcache 2015-03-03 16:50:41 -08:00
Christopher Celio
5d07733057 Removed TLBPTWIO from the io.cpu bundle for icache/dcache 2015-03-03 16:40:39 -08:00
Henry Cook
1e0c16c557 new metadata api 2015-02-28 17:00:32 -08:00
Henry Cook
0b131173e6 WritebackUnit multibeat control logic bugfix 2015-02-16 10:59:57 -08:00
Henry Cook
aa46b8b72d Slightly refactor TLBResp 2015-02-03 19:32:37 -08:00
Stephen Twigg
3d35ccd401 Explicitely convert results of Bits Muxes to UInt
Chisel updated to emit SInt result instead of UInt so this commit addresses this change.
2015-02-03 18:10:54 -08:00
Henry Cook
741e6b77ad Rename some params, use refactored TileLink 2015-02-01 20:37:31 -08:00
Scott Beamer
00e074cdd9 fixes slight bug for non-power of 2 number of ras entries 2015-01-29 15:29:25 -08:00
Andrew Waterman
a98127c09e Merge branch 'ss-frontend' 2015-01-04 20:26:38 -08:00
Andrew Waterman
b70f7683d3 Merge branch 'master' into ss-frontend
Conflicts:
	src/main/scala/ctrl.scala
2015-01-04 19:59:18 -08:00
Andrew Waterman
87ad1a5703 More control cleanup 2015-01-04 19:46:01 -08:00
Andrew Waterman
2aee85cb11 Flush pipeline from MEM stage
This means we no longer have to rely on the instruction behind a serializing
instruction being valid, simplifying the control.  But we have to be a
little more cautious when flusing the I$/ITLB/BTB.
2015-01-04 16:40:16 -08:00
Andrew Waterman
94b75c7cb1 Continue refactoring control 2015-01-04 15:32:05 -08:00
Andrew Waterman
6181de4cc9 Much refactor, so control 2015-01-03 13:34:38 -08:00
Henry Cook
1cb65d5ec1 %s/master/manager/g 2014-12-29 22:56:18 -08:00
Henry Cook
77e5e6b561 refill bug 2014-12-17 19:29:28 -08:00
Henry Cook
08dcf4c6ca refactor cache params 2014-12-17 14:28:05 -08:00
Henry Cook
d29793d1f7 cleanup CoherenceMetadata and coherence params 2014-12-15 19:23:38 -08:00
Henry Cook
c9320862ae add l2 dmem signal to rocc 2014-12-12 16:55:08 -08:00
Henry Cook
72ea24283b multibeat TL; passes all tests 2014-12-12 16:54:33 -08:00
Christopher Celio
f19b3ca43e Deleted extra spaces at EOL in ctrl.scala 2014-11-16 22:04:33 -08:00
Christopher Celio
6749f67b7f Fixed BHT update error.
- separated out BTB/BHT update
   - BHT updates counters on every branch
   - BTB update only on mispredicted and taken branches
2014-11-16 22:02:27 -08:00
Henry Cook
b7b2923bff Cleanup MSHR internal bundles 2014-11-11 18:18:35 -08:00
Henry Cook
c9e7874818 Major tilelink revision for uncached message types 2014-11-11 17:36:48 -08:00
Christopher Celio
fea31d2167 Significant changes and fixes to BTB for superscalar fetch.
- BTBUpdate only occurs on mispredicts now.
   - RASUpdate broken out from BTBUpdate (allows RASUpdate to be performed in
      Decode).
   - Added optional 2nd CAM port to BTB for updates (for when updates to the
      BTB may occur out-of-order).
   - Fixed resp.mask bit logic.
2014-11-11 03:34:05 -08:00
Henry Cook
bf901e4bca Remove master_xact_id from Release 2014-11-06 12:09:45 -08:00
Christopher Celio
3be3cd7731 Fixed error with icache/btb resp mask. 2014-11-03 01:13:22 -08:00
Christopher Celio
08d2c13330 Fixed btb/icache bugs regarding resp mask, fw==1 2014-10-20 18:45:23 -07:00
Christopher Celio
91efdc379b Merge remote-tracking branch 'origin/master' into ss-frontend
Also fixed bridx logic and zero-width wire logic.

Conflicts:
	src/main/scala/btb.scala
2014-10-14 18:10:29 -07:00
Andrew Waterman
7bb7299018 Don't pollute BTB with PC+4 target predictions 2014-10-14 17:28:37 -07:00
Christopher Celio
59eb7d194d Finalize superscalar btb. 2014-10-03 16:08:08 -07:00
Andrew Waterman
cde7c9d869 simplify CSR decoding code 2014-10-03 14:31:26 -07:00
Christopher Celio
99614e37aa Merge remote-tracking branch 'origin/master' into ss-frontend
Conflicts:
	src/main/scala/btb.scala
	src/main/scala/core.scala
2014-10-03 04:22:58 -07:00
Andrew Waterman
655f9ae1af Merge pull request #2 from ccelio/master
Global history now updated (speculatively) in fetch.
2014-09-30 17:12:15 -07:00
Christopher Celio
9cc35dee9a Returned history update to fetch.
- Global history only contains branches.
   - Only update BHT and history on BTB hits.
   - Gate off speculative update on stall or icmiss.
   - Fixed bug where BHT updates were delayed a cycle.
2014-09-29 21:41:07 -07:00
Christopher Celio
8ccd07cfeb Moved updating global history from fetch to decode.
- No longer update global history in fetch stage.
   - Only update global history when instruction is a branch.
   - Does allow for the possibility of back-to-back branches to see
     slightly different histories on subsequent executions.
2014-09-28 05:16:36 -07:00
Christopher Celio
681b43f398 Bug fixes with global history register.
- Updated in fetch speculatively.
      * Updates gated off by cpu.resp.fire().
      * BTB direction factored into history update.
   - All branches update the BHT.
   - Each instruction carries history; index into BHT is recomputed by
     passing in mem_reg_pc.
2014-09-26 10:39:57 -07:00
Christopher Celio
a71bdbbc54 Update history register in fetch speculatively 2014-09-26 05:42:08 -07:00
Christopher Celio
f917810061 Removed RocketCoreParameters from use.
- The nbdache (among others?) use CoreParameters, which has nothing to do with RetireWidth requirements.
   - This conflicts with other cores which uses nbdcache.
   - RocketCoreParameters may be unneccessary, and the require() check can be moved deeper into Rocket.
2014-09-26 05:14:50 -07:00
Christopher Celio
868e747656 Factored out Rocket specifics from CoreParameters
- Added new RocketCoreParameters
   - Other cores using Rocket as a library will no longer conflict against
      Rocket's requires().
2014-09-25 18:52:58 -07:00
Henry Cook
8eb64205f5 bug fix for nbdcache s2_data 2014-09-25 12:00:20 -07:00