How to implement the Gshare TAGE hybrid predictor combination on the RISC V BOOM core using Chisel

Question

I am working on implementing hybrid branch predictors listed below

1. Gshare + TAGE
2. TAGE + Alpha
3. Perceptron + TAGE
4. Gshare + Alpha
5. Perceptron + Gshare
6. Perceptron + Alpha
7. Perceptron + TAGE + Alpha

I understand that I have to create a class definition of the hybrid predictor in the config-mixins.scala file and create a class instance in the BOOMConfigs.scala file. When I try doing that, the results I get are the same as if I run the benchmark program without any branch predictor.

The idea is to replace the tagless base predictor (PC indexed 2-bit counter bimodal table) of TAGE with Gshare. I created a class definition of the hybrid predictor in the config-mixins.scala file and create a class instance in the BOOMConfigs.scala file. When I try doing that, the results I get are the same as if I run the benchmark programs (multiplication.riscv, qsort.riscv, and dhrystone.riscv) without any branch predictor. These are screenshots of what I did for the Gshare + TAGE hybrid combination.

Class Definition of Hybrid combination of Gshare and Tage in config-mixins.scala file

class WithHybridGshareTAGE extends Config((site, here, up) => {
  case TilesLocated(InSubsystem) => up(TilesLocated(InSubsystem), site) map {
    case tp: BoomTileAttachParams => tp.copy(tileParams = tp.tileParams.copy(core = tp.tileParams.core.copy(
      bpdMaxMetaLength = 120,
      globalHistoryLength = 64,
      localHistoryLength = 1,
      localHistoryNSets = 0,
      branchPredictor = ((resp_in: BranchPredictionBankResponse, p: Parameters) => {
        val loop = Module(new LoopBranchPredictorBank()(p))
        val tage = Module(new TageBranchPredictorBank()(p))
        val btb = Module(new BTBBranchPredictorBank()(p))
        val bim = Module(new BIMBranchPredictorBank()(p))
        val ubtb = Module(new FAMicroBTBBranchPredictorBank()(p))
        val gshare = Module(new TageBranchPredictorBank(
          BoomTageParams(tableInfo = Seq((256, 16, 7)))
        )(p))
        val preds = Seq(loop, tage, btb, ubtb, bim, gshare)
        preds.map(_.io := DontCare)
        gshare.io.resp_in(0) := resp_in
        ubtb.io.resp_in(0)  := gshare.io.resp
        bim.io.resp_in(0)   := ubtb.io.resp
        btb.io.resp_in(0)   := bim.io.resp
        tage.io.resp_in(0)  := btb.io.resp
        loop.io.resp_in(0)  := tage.io.resp
        
        (preds, loop.io.resp)
      })
    )))
    case other => other
  }
})

Class Instance of Hybrid combination of Gshare and Tage in BOOMConfigs.scala file

class ECE5504HybridGshareTAGESmallBoomConfig extends Config(
  new boom.common.WithNBoomPerfCounters(11) ++
  new boom.common.WithNSmallBooms(1) ++
  new boom.common.WithHybridGshareTAGE ++
  new chipyard.config.AbstractConfig)

The CPI I get for all three benchmark programs (multiplication.riscv, qsort.riscv, and dhrystone.riscv) with this hybrid combination is the same as the CPI for when I run the same benchmark programs with no branch predictor.