1
0
Commit Graph

26 Commits

Author SHA1 Message Date
Henry Styles
5498468743 FPU : simplify pipeline register generation in FMA 2017-10-05 15:18:19 -07:00
Henry Styles
7a46715cbc FPU : to assist retiming move upto first 2 register stages of into FMA 2017-10-05 15:18:04 -07:00
Henry Cook
9c0bfbd500 tile: remove global Field ResetVectorBits
Reset vector width is determined by systemBus.busView.
Also move some defs from HasCoreParameters to HasTileParameters.
2017-09-08 14:50:59 -07:00
Andrew Waterman
a3358f34a0 Fix priority inversion for two back-to-back divides (#948)
If the first one is killed for some unrelated reason (e.g. write port
hazard), the second one will still issue to the div-sqrt unit.  While
it will itself later be killed, the fact that the later instruction
acquires a resource needed by the former instruction leads to deadlock.
2017-08-10 17:12:09 -07:00
Henry Cook
4c595d175c Refactor package hierarchy and remove legacy bus protocol implementations (#845)
* Refactors package hierarchy.

Additionally:
  - Removes legacy ground tests and configs
  - Removes legacy bus protocol implementations
  - Removes NTiles
  - Adds devices package
  - Adds more functions to util package
2017-07-07 10:48:16 -07:00
Andrew Waterman
76af15a6ff Fix FPU control bug for div/sqrt
I was examining a WB-stage control signal instead of a MEM-stage control
signal.  I refactored the code to group the signals together, so that this
sort of bug is less likely going forward.
2017-06-09 15:51:06 -07:00
Andrew Waterman
5a4daebbcc minNum -> minimumNumber (#766) 2017-06-08 11:12:52 -07:00
Andrew Waterman
8cb250cfe6 Fix FMUL sign, again (#789) 2017-06-08 01:50:00 -07:00
Andrew Waterman
07ad9203ff Fix FMUL sign of zero 2017-06-05 17:35:42 -07:00
Andrew Waterman
8229bdee03 Remove FP unboxing from FMA critical path 2017-06-02 20:44:52 -07:00
Andrew Waterman
7504b47bbe Improve code quality in FP->FP and Int->FP units 2017-06-02 20:44:52 -07:00
Andrew Waterman
84c4ae775f Improve QoR for FP->Int conversions 2017-06-02 20:44:52 -07:00
Andrew Waterman
07968df183 Refactor FP Classify 2017-06-02 20:44:52 -07:00
Andrew Waterman
6ecd58a977 Incorporate new div/sqrt unit 2017-06-02 20:44:15 -07:00
Andrew Waterman
3a1a37d41b Support PutPartial in ScratchpadSlavePort 2017-05-02 03:07:02 -07:00
Andrew Waterman
3b2c15b648 Use tininess-after-rounding in FPU 2017-04-24 02:01:15 -07:00
Andrew Waterman
34d45b4fb0 Fix whitespace error 2017-04-14 01:03:11 -07:00
Andrew Waterman
9a983c12a3 Implement new FP encoding proposal
https://groups.google.com/a/groups.riscv.org/d/msg/isa-dev/_r7hBlzsEd8/cWPyJKMzCQAJ
2017-04-10 22:38:25 -07:00
Andrew Waterman
0e2b780089 Bump hardfloat, giving us the 5th rounding mode finally! 2017-03-26 14:20:16 -07:00
Andrew Waterman
e710e32f10 Implement new FP encoding proposal
Single-precision values are stored in the regfile as double-precision,
so that FSD on a single-precision value stores a proper double and
FLD restores it as either a double or a single.
2017-03-26 14:20:16 -07:00
Andrew Waterman
bb42f3bf3b WIP on FPU subword recoding 2017-03-26 14:20:16 -07:00
Andrew Waterman
24a2278fc4 Perform all illegal-instruction detection in ID stage
This is simpler, reduces what would have become a critical path in
the commit stage, and will make it easier to support the mbadinst
CSR if it is implemented.
2017-03-09 11:29:51 -08:00
Andrew Waterman
603b8af2eb Don't canonicalize 32-bit FP results in the various pipelines
It's redundant with the new scheme, so just adds HW for no reason.
2017-03-07 20:51:32 -08:00
Andrew Waterman
f505aba1ac Use sNaN value for flw, like other single-precision ops 2017-03-07 20:51:32 -08:00
Andrew Waterman
cc389bea90 Fix in-register representation of fdiv.s/fsqrt.s result
We were zero-extending it, which is a double-precision zero in the recoded
format.  So, when spilled and reloaded with fsd/fld, the original value
was destroyed.  Instead, set the MSBs so that it represents sNaN.  When
spilled, the single-precision number will be preserved as the NaN payload.
2017-03-07 20:51:32 -08:00
Henry Cook
e8c8d2af71 Heterogeneous Tiles (#550)
Fundamental new features:

* Added tile package: This package is intended to hold components re-usable across different types of tile. Will be the future location of TL2-RoCC accelerators and new diplomatic versions of intra-tile interfaces.
* Adopted [ModuleName]Params convention: Code base was very inconsistent about what to name case classes that provide parameters to modules. Settled on calling them [ModuleName]Params to distinguish them from config.Parameters and config.Config. So far applied mostly only to case classes defined within rocket and tile.
* Defined RocketTileParams: A nested case class containing case classes for all the components of a tile (L1 caches and core). Allows all such parameters to vary per-tile.
* Defined RocketCoreParams: All the parameters that can be varied per-core.
* Defined L1CacheParams: A trait defining the parameters common to L1 caches, made concrete in different derived case classes.
* Defined RocketTilesKey: A sequence of RocketTileParams, one for every tile to be created.
* Provided HeterogeneousDualCoreConfig: An example of making a heterogeneous chip with two cores, one big and one little.
* Changes to legacy code: ReplacementPolicy moved to package util. L1Metadata moved to package tile. Legacy L2 cache agent removed because it can no longer share the metadata array implementation with the L1. Legacy GroundTests on life support.

Additional changes that got rolled in along the way:

* rocket: 	Fix critical path through BTB for I$ index bits > pgIdxBits
* coreplex: tiles connected via :=*
* groundtest: updated to use TileParams
* tilelink: cache cork requirements are relaxed to allow more cacheless masters
2017-02-09 13:59:09 -08:00