Signed-off-by: Knute <56927209+klingaard@users.noreply.github.com>

This PR adds issue queue modeling to Olympia, by allowing users to
define the number of issue queues, which execution units map to which
issue queues, and which target pipes are supported for each execution
unit.

Regressions will fail until we merge [scoreboard
fix](https://github.com/sparcians/map/pull/468

) in Sparta.
Old flow:
dispatch -> executepipe->execute

New flow:
dispatch -> issue queue -> executepipe -> execute

---------

Signed-off-by: Aaron Chan <achn357@gmail.com>

This SHA is an example of how to generate PEvents (Performance Events)
typically used for correlation
efforts between a perf model and hardware.

PEvents are a more "compact" form of the pipeout collection pairs,
allowing a modeler to specify more direct items
for collection. Pipeout pairs can be more elaborate/detailed. However,
with some clever coding, there can be
reuse -- it's not done here.

To generate performance events, use the command line parameter
`--pevents <filename> <pevent1,pevent2,...|all>`.

Examples:
```
# All pevents
./olympia traces/dhry_riscv.zstf --pevents retire.out all -i100

# Just RETIRE pevent
./olympia traces/dhry_riscv.zstf --pevents retire.out RETIRE -i100

# RETIRE and COMPLETE pevent
./olympia traces/dhry_riscv.zstf --pevents retire.out COMPLETE,RETIRE -i100
```

While I was at it, I removed the generated annotation for pipeline
collection for LoadStore/MemoryAccess classes -- uses NVP which
generates faster, as well as creates smaller pipeouts.

---------

Signed-off-by: Knute <56927209+klingaard@users.noreply.github.com>

Signed-off-by: Lehua Ding <lehua.ding@rivai.ai>

Signed-off-by: Knute Lingaard <knute.lingaard@sifive.com>

Signed-off-by: Knute Lingaard <knute.lingaard@sifive.com>

Updated README with corrected build instructions.

Signed-off-by: Knute Lingaard <knute.lingaard@sifive.com>

Signed-off-by: Knute <56927209+klingaard@users.noreply.github.com>

Signed-off-by: Suraj Shirvankar <surajshirvankar@gmail.com>

This fixes #35 and tracks the changes in Sparta
[PR397(https://github.com/sparcians/map/pull/397

), which are merges into Sparta main already. 

---------

Signed-off-by: Peter Debacker <peter-d@users.noreply.github.com>
Signed-off-by: Knute Lingaard <knute.lingaard@sifive.com>
Co-authored-by: Peter Debacker <pdback@imec.be>
Co-authored-by: Knute Lingaard <Knute.Lingaard@sifive.com>
Co-authored-by: Knute Lingaard <klingaard@gmail.com>

Added directions to checkout map_v1.1.0

Signed-off-by: Knute Lingaard <knute.lingaard@sifive.com>

First commit of using GitHub actions

Signed-off-by: Knute Lingaard <knute.lingaard@sifive.com>

---------

Signed-off-by: Knute Lingaard <knute.lingaard@sifive.com>
Co-authored-by: bdutro <brett.dutro@gmail.com>

Added link to instructions to install required STF library packages

Signed-off-by: Knute Lingaard <knute.lingaard@sifive.com>

Signed-off-by: Knute Lingaard <knute.lingaard@sifive.com>

In this PR, Execute is now it's own node and dynamically creates
execution pipes based on extensions listed in the
config files:
```
top.cpu.core0.extension.core_extensions:
  execution_topology:
  [["alu", "6"],
   ["fpu", "2"],
   ["br",  "2"]]
```

Work done;
- Added new class `Dispatcher` that is dynamically created by `Dispatch`
for each execution pipe defined in the `execution_topology` extension
- Added new class `Execute` that is a node created for the sole purpose
of dynamically creating the `ExecutePipe` objects based on the
`execution_topology` extension
- Cleaned up old code
- Reduced the `CPUTopology` structure to just static components like
Fetch, Decode, Rename, Dispatch, Execute, LS/etc, and Retire
- Updated the arches to include a small, medium, and big core. Dhrystone
trace improves with each architecture, but is limited by LS.

Signed-off-by: Knute Lingaard <knute.lingaard@sifive.com>
Co-authored-by: Zhen Wei <zhen.wei@sifive.com>

Fix typo

Signed-off-by: avinash mehta <avinash.mehta@imgtec.com>

Thanks, Pete!

Signed-off-by: Knute <56927209+klingaard@users.noreply.github.com>

Fixed README commands that were out of date
Fixed total_insts_executed stat
Fixed error where --no-run still required a workload

Signed-off-by: Knute <56927209+klingaard@users.noreply.github.com>

Signed-off-by: Knute <56927209+klingaard@users.noreply.github.com>

Signed-off-by: Knute <56927209+klingaard@users.noreply.github.com>

* First cut of adding stf library
* Fixed warnings from llvm on Mac
* Added directions and README to generate traces
* More documentation updates
* Moved mavis sha
* Regression is running again

Co-authored-by: Knute Lingaard <Knute.Lingaard@sifive.com>

* Mavis added as a submodule

* Mavis is installed and compiling!  Not used yet

* Mavis instantiated; complains about no uarch files: good!

* Updated mavis to gcc branch fixes

* Mavis is now installed and loading arch files

* Workload added and passed to Fetch

* Now have json files running

* Olympia can now run json traces

* Updated documentation -- still more work to do

* Updated documentation -- still more work to do

* Updated documentation -- still more work to do

* Declare InstPtr type within olympia namespace

* Removed outdated fetch param; tests still failing

* Added json test in regress

* Fixed LLVM compilation warnings

* Fixed conflicts

Co-authored-by: Knute Lingaard <Knute.Lingaard@sifive.com>
Co-authored-by: zen <zhen.wei@sifive.com>

* Added Argos layouts
* Added core 80 layout
* Added plotting support and updated README
* Fixed report; changed inst state to simple enum

* First cut olympia: a copy of sparta_core_example with a lot of cleanup and some speed enhancements
* Shaved 10% off of the simulation time