diff --git a/DataFormats/L1THGCal/interface/HGCalCluster.h b/DataFormats/L1THGCal/interface/HGCalCluster.h
index 2c132916bf024..49bef63790446 100644
--- a/DataFormats/L1THGCal/interface/HGCalCluster.h
+++ b/DataFormats/L1THGCal/interface/HGCalCluster.h
@@ -20,8 +20,20 @@ namespace l1t {
     void setModule(uint32_t module) { module_ = module; }
     uint32_t module() const { return module_; }
 
+    void setColumn(int column) { column_ = column; }
+    int column() const { return column_; }
+
+    void setFrame(unsigned frame) { frame_ = frame; }
+    unsigned frame() const { return frame_; }
+
+    void setChannel(unsigned channel) { channel_ = channel; }
+    unsigned channel() const { return channel_; }
+
   private:
     uint32_t module_;
+    unsigned channel_;
+    unsigned frame_;
+    int column_;
   };
 
   typedef BXVector<HGCalCluster> HGCalClusterBxCollection;
diff --git a/DataFormats/L1THGCal/interface/HGCalTriggerCell.h b/DataFormats/L1THGCal/interface/HGCalTriggerCell.h
index b65fb11316047..5bbaa7ce4f290 100644
--- a/DataFormats/L1THGCal/interface/HGCalTriggerCell.h
+++ b/DataFormats/L1THGCal/interface/HGCalTriggerCell.h
@@ -36,6 +36,9 @@ namespace l1t {
     void setCompressedCharge(uint32_t value) { compressedCharge_ = value; }
     uint32_t compressedCharge() const { return compressedCharge_; }
 
+    void setModuleId(uint32_t value) { moduleId_ = value; }
+    uint32_t moduleId() { return moduleId_; }
+
     void setPt(double pT);
 
   private:
@@ -46,6 +49,7 @@ namespace l1t {
 
     uint32_t uncompressedCharge_{0};
     uint32_t compressedCharge_{0};
+    uint32_t moduleId_{0};
   };
 
 }  // namespace l1t
diff --git a/DataFormats/L1THGCal/src/classes_def.xml b/DataFormats/L1THGCal/src/classes_def.xml
index 0a8c4378d7bc8..5ec643aafe1cf 100644
--- a/DataFormats/L1THGCal/src/classes_def.xml
+++ b/DataFormats/L1THGCal/src/classes_def.xml
@@ -30,7 +30,8 @@
 
   <class name="l1t::HGCalClusterT<l1t::HGCalTriggerCell>" />
   <class name="l1t::HGCalClusterT<l1t::HGCalTriggerSums>" />
-  <class name="l1t::HGCalCluster" ClassVersion="19">
+  <class name="l1t::HGCalCluster" ClassVersion="20">
+   <version ClassVersion="20" checksum="3312252455"/>
    <version ClassVersion="19" checksum="214410871"/>
    <version ClassVersion="18" checksum="3346067797"/>
    <version ClassVersion="17" checksum="2841504063"/>
@@ -67,7 +68,8 @@
   <class name="l1t::HGCalMulticlusterBxCollection"/>
   <class name="edm::Wrapper<l1t::HGCalMulticlusterBxCollection>"/>
 
-  <class name="l1t::HGCalTriggerCell" ClassVersion="12">
+  <class name="l1t::HGCalTriggerCell" ClassVersion="13">
+   <version ClassVersion="13" checksum="990350208"/>
    <version ClassVersion="12" checksum="3538848072"/>
    <version ClassVersion="11" checksum="646735227"/>
     <version ClassVersion="10" checksum="1275348814"/>
diff --git a/L1Trigger/L1THGCal/interface/HGCalAlgoWrapperBase.h b/L1Trigger/L1THGCal/interface/HGCalAlgoWrapperBase.h
index 2d73948b04630..0e91755520026 100644
--- a/L1Trigger/L1THGCal/interface/HGCalAlgoWrapperBase.h
+++ b/L1Trigger/L1THGCal/interface/HGCalAlgoWrapperBase.h
@@ -31,6 +31,11 @@ typedef HGCalAlgoWrapperBaseT<std::vector<edm::Ptr<l1t::HGCalTriggerCell>>,
                               std::tuple<const HGCalTriggerGeometryBase* const, const unsigned&, const uint32_t&>>
     HGCalLayer1TruncationWrapperBase;
 
+typedef HGCalAlgoWrapperBaseT<std::vector<edm::Ptr<l1t::HGCalTriggerCell>>,
+                              l1t::HGCalClusterBxCollection,
+                              std::tuple<const HGCalTriggerGeometryBase* const, const unsigned&, const uint32_t&>>
+    HGCalLayer1PhiOrderWrapperBase;
+
 #include "FWCore/PluginManager/interface/PluginFactory.h"
 typedef edmplugin::PluginFactory<HGCalHistoClusteringWrapperBase*(const edm::ParameterSet&)>
     HGCalHistoClusteringWrapperBaseFactory;
@@ -39,5 +44,7 @@ typedef edmplugin::PluginFactory<HGCalStage2FilteringWrapperBase*(const edm::Par
     HGCalStage2FilteringWrapperBaseFactory;
 typedef edmplugin::PluginFactory<HGCalLayer1TruncationWrapperBase*(const edm::ParameterSet&)>
     HGCalLayer1TruncationWrapperBaseFactory;
+typedef edmplugin::PluginFactory<HGCalLayer1PhiOrderWrapperBase*(const edm::ParameterSet&)>
+    HGCalLayer1PhiOrderWrapperBaseFactory;
 
 #endif
diff --git a/L1Trigger/L1THGCal/interface/HGCalTriggerTools.h b/L1Trigger/L1THGCal/interface/HGCalTriggerTools.h
index 60b4f4e1f1fa0..0b4a4b6636528 100644
--- a/L1Trigger/L1THGCal/interface/HGCalTriggerTools.h
+++ b/L1Trigger/L1THGCal/interface/HGCalTriggerTools.h
@@ -68,6 +68,8 @@ class HGCalTriggerTools {
   float getTCPhi(const DetId& id) const;
   float getTCPt(const DetId& id, const float& hitEnergy, const float& vertex_z = 0.) const;
 
+  uint32_t getModuleId(const DetId& id) const;
+
   inline const HGCalTriggerGeometryBase* getTriggerGeometry() const { return geom_; };
 
   float getLayerZ(const unsigned& layerWithOffset) const;
@@ -93,6 +95,8 @@ class HGCalTriggerTools {
   };
   SubDetectorType getSubDetectorType(const DetId& id) const;
 
+  double rotatePhiToSectorZero(double phi, unsigned sector) const;
+
 private:
   const HGCalTriggerGeometryBase* geom_;
   unsigned eeLayers_;
diff --git a/L1Trigger/L1THGCal/interface/backend/HGCalBackendLayer1ProcessorPhiOrderFw.h b/L1Trigger/L1THGCal/interface/backend/HGCalBackendLayer1ProcessorPhiOrderFw.h
new file mode 100644
index 0000000000000..856885c0d24a2
--- /dev/null
+++ b/L1Trigger/L1THGCal/interface/backend/HGCalBackendLayer1ProcessorPhiOrderFw.h
@@ -0,0 +1,26 @@
+#ifndef __L1Trigger_L1THGCal_HGCalBackendLayer1ProcessorPhiOrderFw_h__
+#define __L1Trigger_L1THGCal_HGCalBackendLayer1ProcessorPhiOrderFw_h__
+
+#include "L1Trigger/L1THGCal/interface/HGCalProcessorBase.h"
+#include "L1Trigger/L1THGCal/interface/HGCalAlgoWrapperBase.h"
+
+#include "DataFormats/L1THGCal/interface/HGCalTriggerCell.h"
+#include "DataFormats/L1THGCal/interface/HGCalCluster.h"
+
+#include "L1Trigger/L1THGCal/interface/backend_emulator/HGCalLayer1PhiOrderFwImpl.h"
+#include "L1Trigger/L1THGCal/interface/backend/HGCalClusteringDummyImpl.h"
+
+class HGCalBackendLayer1ProcessorPhiOrderFw : public HGCalBackendLayer1ProcessorBase {
+public:
+  HGCalBackendLayer1ProcessorPhiOrderFw(const edm::ParameterSet& conf);
+
+  void run(const std::pair<uint32_t, std::vector<edm::Ptr<l1t::HGCalTriggerCell>>>& fpga_id_tcs,
+           l1t::HGCalClusterBxCollection& clusters) override;
+
+private:
+  std::unique_ptr<HGCalClusteringDummyImpl> clusteringDummy_;
+  std::unique_ptr<HGCalLayer1PhiOrderWrapperBase> PhiOrderWrapper_;
+  const edm::ParameterSet conf_;
+};
+
+#endif
\ No newline at end of file
diff --git a/L1Trigger/L1THGCal/interface/backend_emulator/HGCalLayer1PhiOrderFwConfig.h b/L1Trigger/L1THGCal/interface/backend_emulator/HGCalLayer1PhiOrderFwConfig.h
new file mode 100644
index 0000000000000..032c6f5c3bf29
--- /dev/null
+++ b/L1Trigger/L1THGCal/interface/backend_emulator/HGCalLayer1PhiOrderFwConfig.h
@@ -0,0 +1,60 @@
+#ifndef __L1Trigger_L1THGCal_HGCalLayer1PhiOrderFwConfig_h__
+#define __L1Trigger_L1THGCal_HGCalLayer1PhiOrderFwConfig_h__
+
+#include <vector>
+#include <cstdint>  // uint32_t
+#include <unordered_map>
+
+namespace l1thgcfirmware {
+
+  class HGCalLayer1PhiOrderFwConfig {
+  public:
+    HGCalLayer1PhiOrderFwConfig() {}
+
+    void setSector120(const unsigned sector) { sector120_ = sector; }
+    void setFPGAID(const uint32_t fpga_id) { fpga_id_ = fpga_id; }
+
+    void
+    configureMappingInfo() {  //creates a map between column number and a vector of pairs containing the available (channel,frame) combinations. Each frame accepts 4 TCs, so each (channel,frame) combination appears 4 times in the vector. We could optionally add a unique "slot" index to this vector, but it is not strictly necessary. The function also creates a vector of pairs between column number and number of TCs the column can accept.
+      for (unsigned i = 0; i < 20; ++i) {
+        //std::pair<unsigned, int> mod_col_pair = std::make_pair(dummyModId_,i);//
+        for (unsigned j = 0; j < 2; ++j) {
+          for (unsigned k = 0; k < 4; ++k) {  //number of slots per frame
+            chn_frame_slots_per_mod_and_col_[dummyModId_][i].push_back(std::make_pair(i + 3, j));
+          }
+          for (unsigned k = 0; k < 4; ++k) {  //number of slots per frame
+            chn_frame_slots_per_mod_and_col_[dummyModId_][i].push_back(std::make_pair(i + 4, j));
+          }
+        }
+        max_tcs_per_module_and_column_[dummyModId_].push_back(
+            std::make_pair(i, chn_frame_slots_per_mod_and_col_[dummyModId_][i].size()));
+      }
+    }
+
+    unsigned phiSector() const { return sector120_; }
+    uint32_t fpgaID() const { return fpga_id_; }
+    unsigned getColBudgetAtIndex(unsigned moduleId, unsigned theColumnIndex) const {
+      return max_tcs_per_module_and_column_.at(dummyModId_).at(theColumnIndex).second;
+    }  //Get TC budget for column at index theColumnIndex in the vector
+    int getColFromBudgetMapAtIndex(unsigned moduleId, unsigned theColumnIndex) const {
+      return max_tcs_per_module_and_column_.at(dummyModId_).at(theColumnIndex).first;
+    }  //Get column number at index theColumnIndex in the vector
+    unsigned getChannelAtIndex(unsigned moduleId, int theColumn, unsigned theChnFrameIndex) const {
+      return chn_frame_slots_per_mod_and_col_.at(dummyModId_).at(theColumn).at(theChnFrameIndex).first;
+    }  //Extract channel number for colnr theColumn, at given channel+frame index in the vector
+    unsigned getFrameAtIndex(unsigned moduleId, int theColumn, unsigned theChnFrameIndex) const {
+      return chn_frame_slots_per_mod_and_col_.at(dummyModId_).at(theColumn).at(theChnFrameIndex).second;
+    }  //Extract frame number for colnr theColumn, at given channel+frame index in the vector
+
+  private:
+    unsigned sector120_;
+    uint32_t fpga_id_;
+    std::unordered_map<unsigned, std::vector<std::pair<int, unsigned>>> max_tcs_per_module_and_column_;
+    std::unordered_map<unsigned, std::unordered_map<int, std::vector<std::pair<unsigned, unsigned>>>>
+        chn_frame_slots_per_mod_and_col_;
+    const uint32_t dummyModId_ = 1879048191;  // Just to avoid filling maps for random module ID values. Temporary!!
+  };
+
+}  // namespace l1thgcfirmware
+
+#endif
diff --git a/L1Trigger/L1THGCal/interface/backend_emulator/HGCalLayer1PhiOrderFwImpl.h b/L1Trigger/L1THGCal/interface/backend_emulator/HGCalLayer1PhiOrderFwImpl.h
new file mode 100644
index 0000000000000..d928991b97bca
--- /dev/null
+++ b/L1Trigger/L1THGCal/interface/backend_emulator/HGCalLayer1PhiOrderFwImpl.h
@@ -0,0 +1,46 @@
+#ifndef __L1Trigger_L1THGCal_HGCalLayer1PhiOrderFwImpl_h__
+#define __L1Trigger_L1THGCal_HGCalLayer1PhiOrderFwImpl_h__
+
+#include "L1Trigger/L1THGCal/interface/backend_emulator/HGCalTriggerCell_SA.h"
+#include "L1Trigger/L1THGCal/interface/backend_emulator/HGCalLayer1PhiOrderFwConfig.h"
+#include "L1Trigger/L1THGCal/interface/backend_emulator/BatcherSorter.h"
+
+#include <vector>
+#include <cstdint>        // uint32_t, unsigned
+#include <unordered_map>  // std::unordered_map
+
+namespace l1thgcfirmware {
+
+  class HGCalLayer1PhiOrderFwImpl {
+  public:
+    HGCalLayer1PhiOrderFwImpl();
+    ~HGCalLayer1PhiOrderFwImpl() {}
+
+    void runAlgorithm() const;
+
+    unsigned run(const l1thgcfirmware::HGCalTriggerCellSACollection& tcs_in,
+                 const l1thgcfirmware::HGCalLayer1PhiOrderFwConfig& theConf,
+                 l1thgcfirmware::HGCalTriggerCellSACollection& tcs_out) const;
+
+  private:
+    const int columnMask_ = 0x1F;  //5 bits
+    const int columnOffset_ = 11;  //7 bits frame, 4 bits channel
+    const int channelMask_ = 0xF;  //4 bits for channel
+    const int channelOffset_ = 7;  //Frame has 7 bits (to fit 108 frames)
+    const int frameMask_ = 0x7F;   //7 bits for frame
+    const int frameOffset_ = 0;
+
+    int packColChnFrame(int column, unsigned channel, unsigned frame) const;
+    void unpackColChnFrame(int packedbin, int& column, unsigned& channel, unsigned& frame) const;
+
+    std::vector<std::pair<l1thgcfirmware::HGCalTriggerCell, int>> assignTCToCol(
+        const l1thgcfirmware::HGCalLayer1PhiOrderFwConfig& theConf,
+        std::vector<l1thgcfirmware::HGCalTriggerCell> tcs) const;
+    std::vector<std::pair<l1thgcfirmware::HGCalTriggerCell, int>> assignTCToChnAndFrame(
+        const l1thgcfirmware::HGCalLayer1PhiOrderFwConfig& theConf,
+        std::vector<std::pair<l1thgcfirmware::HGCalTriggerCell, int>> ord_tcs) const;
+  };
+
+}  // namespace l1thgcfirmware
+
+#endif
diff --git a/L1Trigger/L1THGCal/interface/backend_emulator/HGCalTriggerCell_SA.h b/L1Trigger/L1THGCal/interface/backend_emulator/HGCalTriggerCell_SA.h
index a8b0dd71180df..27b789d55eeae 100644
--- a/L1Trigger/L1THGCal/interface/backend_emulator/HGCalTriggerCell_SA.h
+++ b/L1Trigger/L1THGCal/interface/backend_emulator/HGCalTriggerCell_SA.h
@@ -36,6 +36,10 @@ namespace l1thgcfirmware {
     void setY(const unsigned int Y) { Y_ = Y; }
     void setDeltaR2(const unsigned int deltaR2) { deltaR2_ = deltaR2; }
     void setCmsswIndex(const std::pair<int, int> index) { index_cmssw_ = index; }
+    void setModuleId(const unsigned int moduleid) { moduleId_ = moduleid; }
+    void setColumn(const int column) { column_ = column; }
+    void setFrame(const unsigned frame) { frame_ = frame; }
+    void setChannel(const unsigned channel) { channel_ = channel; }
 
     // Getters
     unsigned int clock() const { return clock_; }
@@ -50,7 +54,11 @@ namespace l1thgcfirmware {
     unsigned int Y() const { return Y_; }
     bool frameValid() const { return frameValid_; }
     bool dataValid() const { return dataValid_; }
+    unsigned int moduleId() const { return moduleId_; }
     const std::pair<int, int>& cmsswIndex() const { return index_cmssw_; }
+    int column() const { return column_; }
+    unsigned frame() const { return frame_; }
+    unsigned channel() const { return channel_; }
 
     // Operators
     bool operator==(const HGCalTriggerCell& rhs) const;
@@ -69,7 +77,11 @@ namespace l1thgcfirmware {
     unsigned int Y_;
     bool frameValid_;
     bool dataValid_;
+    unsigned int moduleId_;
     std::pair<int, int> index_cmssw_;
+    int column_;
+    unsigned frame_;
+    unsigned channel_;
   };
 
   typedef std::vector<HGCalTriggerCell> HGCalTriggerCellSACollection;
diff --git a/L1Trigger/L1THGCal/plugins/backend/HGCalBackendLayer1ProcessorPhiOrderFw.cc b/L1Trigger/L1THGCal/plugins/backend/HGCalBackendLayer1ProcessorPhiOrderFw.cc
new file mode 100644
index 0000000000000..116ee88d6b468
--- /dev/null
+++ b/L1Trigger/L1THGCal/plugins/backend/HGCalBackendLayer1ProcessorPhiOrderFw.cc
@@ -0,0 +1,29 @@
+#include "L1Trigger/L1THGCal/interface/backend/HGCalBackendLayer1ProcessorPhiOrderFw.h"
+#include "DataFormats/ForwardDetId/interface/HGCalTriggerBackendDetId.h"
+
+DEFINE_EDM_PLUGIN(HGCalBackendLayer1Factory,
+                  HGCalBackendLayer1ProcessorPhiOrderFw,
+                  "HGCalBackendLayer1ProcessorPhiOrderFw");
+
+HGCalBackendLayer1ProcessorPhiOrderFw::HGCalBackendLayer1ProcessorPhiOrderFw(const edm::ParameterSet& conf)
+    : HGCalBackendLayer1ProcessorBase(conf), conf_(conf) {
+  const edm::ParameterSet& PhiOrderParamConfig = conf.getParameterSet("phiorder_parameters");
+  const std::string& PhiOrderWrapperName = PhiOrderParamConfig.getParameter<std::string>("AlgoName");
+
+  PhiOrderWrapper_ = std::unique_ptr<HGCalLayer1PhiOrderWrapperBase>{
+      HGCalLayer1PhiOrderWrapperBaseFactory::get()->create(PhiOrderWrapperName, PhiOrderParamConfig)};
+}
+
+void HGCalBackendLayer1ProcessorPhiOrderFw::run(
+    const std::pair<uint32_t, std::vector<edm::Ptr<l1t::HGCalTriggerCell>>>& fpga_id_tcs,
+    l1t::HGCalClusterBxCollection& clusters) {
+  const unsigned sector120 = HGCalTriggerBackendDetId(fpga_id_tcs.first).sector();
+  const uint32_t fpga_id = fpga_id_tcs.first;
+
+  // Configuration
+  const std::tuple<const HGCalTriggerGeometryBase* const, unsigned, uint32_t> configuration{
+      geometry(), sector120, fpga_id};
+  PhiOrderWrapper_->configure(configuration);
+
+  PhiOrderWrapper_->process(fpga_id_tcs.second, clusters);
+}
diff --git a/L1Trigger/L1THGCal/plugins/backend/HGCalLayer1PhiOrderWrapper.cc b/L1Trigger/L1THGCal/plugins/backend/HGCalLayer1PhiOrderWrapper.cc
new file mode 100644
index 0000000000000..8b5b90788a4de
--- /dev/null
+++ b/L1Trigger/L1THGCal/plugins/backend/HGCalLayer1PhiOrderWrapper.cc
@@ -0,0 +1,112 @@
+#include "L1Trigger/L1THGCal/interface/HGCalAlgoWrapperBase.h"
+
+#include "DataFormats/L1THGCal/interface/HGCalTriggerCell.h"
+#include "L1Trigger/L1THGCal/interface/backend_emulator/HGCalTriggerCell_SA.h"
+#include "L1Trigger/L1THGCal/interface/backend_emulator/HGCalLayer1PhiOrderFwImpl.h"
+#include "L1Trigger/L1THGCal/interface/backend_emulator/HGCalLayer1PhiOrderFwConfig.h"
+
+#include "L1Trigger/L1THGCal/interface/HGCalTriggerTools.h"
+
+class HGCalLayer1PhiOrderWrapper : public HGCalLayer1PhiOrderWrapperBase {
+public:
+  HGCalLayer1PhiOrderWrapper(const edm::ParameterSet& conf);
+  ~HGCalLayer1PhiOrderWrapper() override = default;
+
+  void configure(
+      const std::tuple<const HGCalTriggerGeometryBase* const, const unsigned&, const uint32_t&>& configuration) override;
+
+  void process(const std::vector<edm::Ptr<l1t::HGCalTriggerCell>>& fpga_tcs,
+               l1t::HGCalClusterBxCollection& clusters) const override;
+
+private:
+  void convertCMSSWInputs(const std::vector<edm::Ptr<l1t::HGCalTriggerCell>>& fpga_tcs,
+                          l1thgcfirmware::HGCalTriggerCellSACollection& fpga_tcs_SA) const;
+
+  void convertAlgorithmOutputs(const l1thgcfirmware::HGCalTriggerCellSACollection& fpga_tcs_out,
+                               const std::vector<edm::Ptr<l1t::HGCalTriggerCell>>& fpga_tcs_original,
+                               l1t::HGCalClusterBxCollection& clusters) const;
+
+  void setGeometry(const HGCalTriggerGeometryBase* const geom) { triggerTools_.setGeometry(geom); }
+
+  HGCalTriggerTools triggerTools_;
+  l1thgcfirmware::HGCalLayer1PhiOrderFwImpl theAlgo_;
+  l1thgcfirmware::HGCalLayer1PhiOrderFwConfig theConfiguration_;
+
+  // Scale factor for quantities sent to emulator to keep floating point precision. Value is arbitrary and could be set to relevant value.
+  const unsigned int FWfactor_ = 10000;
+};
+
+HGCalLayer1PhiOrderWrapper::HGCalLayer1PhiOrderWrapper(const edm::ParameterSet& conf)
+    : HGCalLayer1PhiOrderWrapperBase(conf), theAlgo_(), theConfiguration_() {}
+
+void HGCalLayer1PhiOrderWrapper::convertCMSSWInputs(const std::vector<edm::Ptr<l1t::HGCalTriggerCell>>& fpga_tcs,
+                                                    l1thgcfirmware::HGCalTriggerCellSACollection& fpga_tcs_SA) const {
+  fpga_tcs_SA.clear();
+  fpga_tcs_SA.reserve(fpga_tcs.size());
+  unsigned int itc = 0;
+  for (auto& tc : fpga_tcs) {
+    double phi = triggerTools_.rotatePhiToSectorZero(tc->phi(), theConfiguration_.phiSector());
+    phi += (phi < 0) ? M_PI : 0;
+    unsigned int digi_phi = phi * FWfactor_;
+    unsigned int digi_energy = (tc->mipPt()) * FWfactor_;
+    fpga_tcs_SA.emplace_back(true,
+                             true,
+                             1,
+                             digi_phi,
+                             triggerTools_.layerWithOffset(tc->detId()),
+                             digi_energy);  //Assign dummy RoverZbin to not change the dataformat/creators.
+    fpga_tcs_SA.back().setModuleId(triggerTools_.getModuleId(tc->detId()));
+    fpga_tcs_SA.back().setCmsswIndex(std::make_pair(itc, 0));
+    ++itc;
+  }
+}
+
+void HGCalLayer1PhiOrderWrapper::convertAlgorithmOutputs(
+    const l1thgcfirmware::HGCalTriggerCellSACollection& fpga_tcs_out,
+    const std::vector<edm::Ptr<l1t::HGCalTriggerCell>>& fpga_tcs_original,
+    l1t::HGCalClusterBxCollection& clusters) const {
+  std::vector<l1t::HGCalCluster> clustersTmp;
+
+  //for (const auto& otc : fpga_tcs_original) {
+  for (std::vector<edm::Ptr<l1t::HGCalTriggerCell>>::const_iterator otc = fpga_tcs_original.begin();
+       otc != fpga_tcs_original.end();
+       ++otc) {
+    clustersTmp.emplace_back(*otc);
+  }
+
+  for (auto& tc : fpga_tcs_out) {
+    unsigned tc_cmssw_id = tc.cmsswIndex().first;
+    if (tc_cmssw_id < fpga_tcs_original.size()) {
+      clustersTmp.at(tc_cmssw_id).setColumn(tc.column());
+      clustersTmp.at(tc_cmssw_id).setFrame(tc.frame());
+      clustersTmp.at(tc_cmssw_id).setChannel(tc.channel());
+      clustersTmp.at(tc_cmssw_id).setModule(tc.moduleId());
+      clusters.push_back(0, clustersTmp.at(tc_cmssw_id));
+    }
+  }
+}
+
+void HGCalLayer1PhiOrderWrapper::process(const std::vector<edm::Ptr<l1t::HGCalTriggerCell>>& fpga_tcs,
+                                         l1t::HGCalClusterBxCollection& clusters) const {
+  l1thgcfirmware::HGCalTriggerCellSACollection fpga_tcs_SA;
+  convertCMSSWInputs(fpga_tcs, fpga_tcs_SA);
+
+  l1thgcfirmware::HGCalTriggerCellSACollection tcs_out_SA;
+  unsigned error_code = theAlgo_.run(fpga_tcs_SA, theConfiguration_, tcs_out_SA);
+
+  if (error_code == 1)
+    throw cms::Exception("HGCalLayer1PhiOrderFwImpl::Error") << " This shouldn't happen ";
+
+  convertAlgorithmOutputs(tcs_out_SA, fpga_tcs, clusters);
+}
+
+void HGCalLayer1PhiOrderWrapper::configure(
+    const std::tuple<const HGCalTriggerGeometryBase* const, const unsigned&, const uint32_t&>& configuration) {
+  setGeometry(std::get<0>(configuration));
+
+  theConfiguration_.setSector120(std::get<1>(configuration));
+  theConfiguration_.setFPGAID(std::get<2>(configuration));
+  theConfiguration_.configureMappingInfo();
+};
+
+DEFINE_EDM_PLUGIN(HGCalLayer1PhiOrderWrapperBaseFactory, HGCalLayer1PhiOrderWrapper, "HGCalLayer1PhiOrderWrapper");
diff --git a/L1Trigger/L1THGCal/plugins/backend/HGCalLayer1TruncationWrapper.cc b/L1Trigger/L1THGCal/plugins/backend/HGCalLayer1TruncationWrapper.cc
index f6ae43add7c70..3a2c8f88c0a77 100644
--- a/L1Trigger/L1THGCal/plugins/backend/HGCalLayer1TruncationWrapper.cc
+++ b/L1Trigger/L1THGCal/plugins/backend/HGCalLayer1TruncationWrapper.cc
@@ -28,7 +28,6 @@ class HGCalLayer1TruncationWrapper : public HGCalLayer1TruncationWrapperBase {
 
   void setGeometry(const HGCalTriggerGeometryBase* const geom) { triggerTools_.setGeometry(geom); }
 
-  double rotatedphi(double phi, unsigned sector) const;
   unsigned rozBin(double roverz, double rozmin, double rozmax, unsigned rozbins) const;
 
   HGCalTriggerTools triggerTools_;
@@ -62,7 +61,7 @@ void HGCalLayer1TruncationWrapper::convertCMSSWInputs(const std::vector<edm::Ptr
     double roverz = (std::sqrt(x * x + y * y) / std::abs(z));
     unsigned int rOverZbin =
         rozBin(roverz, theConfiguration_.rozMin(), theConfiguration_.rozMax(), theConfiguration_.rozBins());
-    double phi = rotatedphi(tc->phi(), theConfiguration_.phiSector());
+    double phi = triggerTools_.rotatePhiToSectorZero(tc->phi(), theConfiguration_.phiSector());
     phi += (phi < 0) ? M_PI : 0;
     unsigned int digi_phi = phi * FWfactor_;
     unsigned int digi_energy = (tc->mipPt()) * FWfactor_;
@@ -105,18 +104,6 @@ void HGCalLayer1TruncationWrapper::configure(
   theConfiguration_.setFPGAID(std::get<2>(configuration));
 };
 
-double HGCalLayer1TruncationWrapper::rotatedphi(double phi, unsigned sector) const {
-  if (sector == 1) {
-    if (phi < M_PI and phi > 0)
-      phi = phi - (2. * M_PI / 3.);
-    else
-      phi = phi + (4. * M_PI / 3.);
-  } else if (sector == 2) {
-    phi = phi + (2. * M_PI / 3.);
-  }
-  return phi;
-}
-
 unsigned HGCalLayer1TruncationWrapper::rozBin(double roverz, double rozmin, double rozmax, unsigned rozbins) const {
   constexpr double margin = 1.001;
   double roz_bin_size = (rozbins > 0 ? (rozmax - rozmin) * margin / double(rozbins) : 0.);
diff --git a/L1Trigger/L1THGCal/python/customLayer1.py b/L1Trigger/L1THGCal/python/customLayer1.py
index 2f10d34576bd9..a4b9d8f280ffa 100644
--- a/L1Trigger/L1THGCal/python/customLayer1.py
+++ b/L1Trigger/L1THGCal/python/customLayer1.py
@@ -1,5 +1,5 @@
 import FWCore.ParameterSet.Config as cms
-from L1Trigger.L1THGCal.l1tHGCalBackEndLayer1Producer_cfi import layer1truncation_proc, layer1truncationfw_proc, truncation_params, truncationfw_params
+from L1Trigger.L1THGCal.l1tHGCalBackEndLayer1Producer_cfi import layer1truncation_proc, layer1phiorderfw_proc, layer1truncationfw_proc, truncation_params, truncationfw_params
 
 def custom_layer1_truncation(process):
     parameters = layer1truncation_proc.clone()
@@ -17,5 +17,14 @@ def custom_layer1_truncationfw(process):
     process.l1tHGCalTowerProducer.InputTriggerCells = cms.InputTag('l1tHGCalBackEndLayer1Producer:HGCalBackendLayer1ProcessorTruncationFw')
     return process
 
+def custom_layer1_phiorderfw(process):
+    parameters = layer1phiorderfw_proc.clone()
+    process.l1tHGCalBackEndLayer1Producer.ProcessorParameters = parameters
+    process.l1tHGCalBackEndLayer1Producer.BypassBackendMapping = cms.bool(False)
+    process.l1tHGCalBackEndLayer2Producer.InputCluster = cms.InputTag('l1tHGCalBackEndLayer1Producer:HGCalBackendLayer1ProcessorPhiOrderFw')
+    process.l1tHGCalTowerProducer.InputTriggerCells = cms.InputTag('l1tHGCalBackEndLayer1Producer:HGCalBackendLayer1ProcessorPhiOrderFw')
+    return process
+
+
 def custom_layer1_latestfw(process):
     return custom_layer1_truncationfw(process)
diff --git a/L1Trigger/L1THGCal/python/l1tHGCalBackEndLayer1Producer_cfi.py b/L1Trigger/L1THGCal/python/l1tHGCalBackEndLayer1Producer_cfi.py
index 32a1a89642de0..451e208c37b84 100644
--- a/L1Trigger/L1THGCal/python/l1tHGCalBackEndLayer1Producer_cfi.py
+++ b/L1Trigger/L1THGCal/python/l1tHGCalBackEndLayer1Producer_cfi.py
@@ -96,6 +96,15 @@
                    clustering_dummy_parameters = dummy_C2d_params.clone()
                    )
 
+phiorderfw_params = cms.PSet(AlgoName=cms.string('HGCalLayer1PhiOrderWrapper'))
+
+
+layer1phiorderfw_proc = cms.PSet(ProcessorName  = cms.string('HGCalBackendLayer1ProcessorPhiOrderFw'),
+                   phiorder_parameters = phiorderfw_params.clone(),
+                   clustering_dummy_parameters = dummy_C2d_params.clone()
+                   )
+
+
 clustering2d_proc = cms.PSet(ProcessorName  = cms.string('HGCalBackendLayer1Processor2DClustering'),
                    C2d_parameters = dummy_C2d_params.clone()
                    )
diff --git a/L1Trigger/L1THGCal/src/HGCalAlgoWrapperBase.cc b/L1Trigger/L1THGCal/src/HGCalAlgoWrapperBase.cc
index 547ad057550f6..3f5c625f61933 100644
--- a/L1Trigger/L1THGCal/src/HGCalAlgoWrapperBase.cc
+++ b/L1Trigger/L1THGCal/src/HGCalAlgoWrapperBase.cc
@@ -7,3 +7,5 @@ EDM_REGISTER_PLUGINFACTORY(HGCalTowerMapsWrapperBaseFactory, "HGCalTowerMapsWrap
 EDM_REGISTER_PLUGINFACTORY(HGCalStage2FilteringWrapperBaseFactory, "HGCalStage2FilteringWrapperBaseFactory");
 
 EDM_REGISTER_PLUGINFACTORY(HGCalLayer1TruncationWrapperBaseFactory, "HGCalLayer1TruncationWrapperBaseFactory");
+
+EDM_REGISTER_PLUGINFACTORY(HGCalLayer1PhiOrderWrapperBaseFactory, "HGCalLayer1PhiOrderWrapperBaseFactory");
diff --git a/L1Trigger/L1THGCal/src/HGCalTriggerTools.cc b/L1Trigger/L1THGCal/src/HGCalTriggerTools.cc
index 240ae9bb3c008..191aa6bedc31c 100644
--- a/L1Trigger/L1THGCal/src/HGCalTriggerTools.cc
+++ b/L1Trigger/L1THGCal/src/HGCalTriggerTools.cc
@@ -261,6 +261,8 @@ float HGCalTriggerTools::getTCPhi(const DetId& id) const {
   return getPhi(position);
 }
 
+uint32_t HGCalTriggerTools::getModuleId(const DetId& id) const { return geom_->getModuleFromTriggerCell(id); }
+
 float HGCalTriggerTools::getPt(const GlobalPoint& position, const float& hitEnergy, const float& vertex_z) const {
   float eta = getEta(position, vertex_z);
   float pt = hitEnergy / cosh(eta);
@@ -308,3 +310,15 @@ DetId HGCalTriggerTools::simToReco(const DetId& simid, const HGCalTopology& topo
   }
   return recoid;
 }
+
+double HGCalTriggerTools::rotatePhiToSectorZero(double phi, unsigned sector) const {
+  if (sector == 1) {
+    if (phi < M_PI and phi > 0)
+      phi = phi - (2. * M_PI / 3.);
+    else
+      phi = phi + (4. * M_PI / 3.);
+  } else if (sector == 2) {
+    phi = phi + (2. * M_PI / 3.);
+  }
+  return phi;
+}
diff --git a/L1Trigger/L1THGCal/src/backend_emulator/HGCalLayer1PhiOrderFwImpl.cc b/L1Trigger/L1THGCal/src/backend_emulator/HGCalLayer1PhiOrderFwImpl.cc
new file mode 100644
index 0000000000000..11fadc814c1b6
--- /dev/null
+++ b/L1Trigger/L1THGCal/src/backend_emulator/HGCalLayer1PhiOrderFwImpl.cc
@@ -0,0 +1,111 @@
+#include "L1Trigger/L1THGCal/interface/backend_emulator/HGCalLayer1PhiOrderFwImpl.h"
+#include <cmath>
+#include <algorithm>
+
+using namespace l1thgcfirmware;
+
+HGCalLayer1PhiOrderFwImpl::HGCalLayer1PhiOrderFwImpl() {}
+
+struct {
+  bool operator()(l1thgcfirmware::HGCalTriggerCell a, l1thgcfirmware::HGCalTriggerCell b) const {
+    return a.phi() < b.phi();
+  }
+} sortByPhi;
+
+unsigned HGCalLayer1PhiOrderFwImpl::run(const l1thgcfirmware::HGCalTriggerCellSACollection& tcs_in,
+                                        const l1thgcfirmware::HGCalLayer1PhiOrderFwConfig& theConf,
+                                        l1thgcfirmware::HGCalTriggerCellSACollection& tcs_out) const {
+  std::unordered_map<unsigned, std::vector<l1thgcfirmware::HGCalTriggerCell>> tcs_per_bin;
+
+  // group TCs per unique module
+  for (const auto& tc : tcs_in) {
+    unsigned module_id = tc.moduleId();
+    tcs_per_bin[module_id].push_back(tc);
+  }
+
+  for (auto& bin_tcs : tcs_per_bin) {
+    std::vector<l1thgcfirmware::HGCalTriggerCell> sorted_tcs;
+
+    sorted_tcs = bin_tcs.second;
+
+    std::vector<std::pair<l1thgcfirmware::HGCalTriggerCell, int>> tcs_per_col = assignTCToCol(theConf, sorted_tcs);
+    std::vector<std::pair<l1thgcfirmware::HGCalTriggerCell, int>> tcs_with_ccf =
+        assignTCToChnAndFrame(theConf, tcs_per_col);
+
+    for (auto& tcobj : tcs_with_ccf) {
+      tcs_out.push_back(tcobj.first);
+      int col = 0;
+      unsigned ch = 0;
+      unsigned fr = 0;
+      unpackColChnFrame(tcobj.second, col, ch, fr);
+      tcs_out.back().setColumn(col);
+      tcs_out.back().setChannel(ch);
+      tcs_out.back().setFrame(fr);
+    }
+  }
+
+  return 0;
+}
+
+std::vector<std::pair<l1thgcfirmware::HGCalTriggerCell, int>> HGCalLayer1PhiOrderFwImpl::assignTCToCol(
+    const l1thgcfirmware::HGCalLayer1PhiOrderFwConfig& theConf,
+    std::vector<l1thgcfirmware::HGCalTriggerCell> tcs) const {
+  std::vector<std::pair<l1thgcfirmware::HGCalTriggerCell, int>> theOrderedTCs;
+  std::sort(tcs.begin(), tcs.end(), sortByPhi);
+  unsigned theColumnIndex =
+      0;  //start filling the first associated column. This assumes the columns are already ordered correctly! NB this is an index, not the column ID
+  unsigned nTCinColumn = 0;  //Number of TCs already in column
+  for (auto& tc : tcs) {
+    uint32_t theModuleId = tc.moduleId();
+    while (!(nTCinColumn < theConf.getColBudgetAtIndex(theModuleId, theColumnIndex))) {
+      theColumnIndex += 1;
+      nTCinColumn = 0;
+    }
+    theOrderedTCs.push_back(std::make_pair(tc, theConf.getColFromBudgetMapAtIndex(theModuleId, theColumnIndex)));
+    nTCinColumn += 1;
+  }
+  return theOrderedTCs;
+}
+
+std::vector<std::pair<l1thgcfirmware::HGCalTriggerCell, int>> HGCalLayer1PhiOrderFwImpl::assignTCToChnAndFrame(
+    const l1thgcfirmware::HGCalLayer1PhiOrderFwConfig& theConf,
+    std::vector<std::pair<l1thgcfirmware::HGCalTriggerCell, int>> ord_tcs) const {
+  std::vector<std::pair<l1thgcfirmware::HGCalTriggerCell, int>> theTCsWithChnFrame;
+  //std::unordered_map<int, std::pair<int,int>> chnAndFrameCounterForCol; //Need to track channel and frame counter for particular column.
+  //need map from column to index for that specific column. Index should be the index in a vector that already contains the possible combinations of chn,frame (could add the slot)
+  std::unordered_map<unsigned, std::unordered_map<int, unsigned>>
+      chnAndFrameCounterForCol;  //This will track the index 'per column', index is index in a vector of tuples;
+  for (auto& tc : ord_tcs) {
+    int theCol = tc.second;
+    uint32_t theModuleId = tc.first.moduleId();
+    if (chnAndFrameCounterForCol[theModuleId].count(theCol) == 0)
+      chnAndFrameCounterForCol[theModuleId][theCol] = 0;
+    unsigned theChnFrameIndex = chnAndFrameCounterForCol[theModuleId][theCol];
+    chnAndFrameCounterForCol[theModuleId][theCol] += 1;
+    int thePackedCCF = packColChnFrame(theCol,
+                                       theConf.getChannelAtIndex(theModuleId, theCol, theChnFrameIndex),
+                                       theConf.getFrameAtIndex(theModuleId, theCol, theChnFrameIndex));
+    theTCsWithChnFrame.push_back(std::make_pair(tc.first, thePackedCCF));
+  }
+  return theTCsWithChnFrame;
+}
+
+int HGCalLayer1PhiOrderFwImpl::packColChnFrame(int column, unsigned channel, unsigned frame) const {
+  int packed_bin = 0;
+  packed_bin |= (frame & frameMask_) << frameOffset_;
+  packed_bin |= (channel & channelMask_) << channelOffset_;
+  packed_bin |= (std::abs(column) & columnMask_) << columnOffset_;
+  if (column < 0)
+    packed_bin = -packed_bin;
+  return packed_bin;
+}
+
+void HGCalLayer1PhiOrderFwImpl::unpackColChnFrame(int packedBin, int& column, unsigned& channel, unsigned& frame) const {
+  int colsign = 1;
+  if (packedBin < 0)
+    colsign = -1;
+  frame = (std::abs(packedBin) >> frameOffset_) & frameMask_;
+  channel = (std::abs(packedBin) >> channelOffset_) & channelMask_;
+  column = (std::abs(packedBin) >> columnOffset_) & columnMask_;
+  column = colsign * column;
+}
diff --git a/L1Trigger/L1THGCalUtilities/python/customNtuples.py b/L1Trigger/L1THGCalUtilities/python/customNtuples.py
index e16ac829c92b2..808bfa651a220 100644
--- a/L1Trigger/L1THGCalUtilities/python/customNtuples.py
+++ b/L1Trigger/L1THGCalUtilities/python/customNtuples.py
@@ -18,8 +18,17 @@ def custom_ntuples_layer1_truncationfw(process):
             ntuple.Clusters = cms.InputTag('l1tHGCalBackEndLayer1Producer:HGCalBackendLayer1ProcessorTruncationFw')
     return process
 
+def custom_ntuples_layer1_phiorderfw(process):
+    ntuples = process.l1tHGCalTriggerNtuplizer.Ntuples
+    for ntuple in ntuples:
+        if ntuple.NtupleName=='HGCalTriggerNtupleHGCClusters' or \
+           ntuple.NtupleName=='HGCalTriggerNtupleHGCTriggerCells' or \
+           ntuple.NtupleName=='HGCalTriggerNtupleHGCMulticlusters':
+            ntuple.Clusters = cms.InputTag('l1tHGCalBackEndLayer1Producer:HGCalBackendLayer1ProcessorPhiOrderFw')
+    return process
+
 def custom_ntuples_layer1_latestfw(process):
-    return custom_ntuples_layer1_truncationfw(process)
+    return custom_ntuples_layer1_phiorderfw(process)
 
 def custom_ntuples_standalone_clustering(process):
     ntuples = process.l1tHGCalTriggerNtuplizer.Ntuples
diff --git a/L1Trigger/L1THGCalUtilities/test/ntuples/HGCalTriggerNtupleHGCClusters.cc b/L1Trigger/L1THGCalUtilities/test/ntuples/HGCalTriggerNtupleHGCClusters.cc
index 049a3b12e217a..6f6b012aadf9b 100644
--- a/L1Trigger/L1THGCalUtilities/test/ntuples/HGCalTriggerNtupleHGCClusters.cc
+++ b/L1Trigger/L1THGCalUtilities/test/ntuples/HGCalTriggerNtupleHGCClusters.cc
@@ -22,6 +22,7 @@ class HGCalTriggerNtupleHGCClusters : public HGCalTriggerNtupleBase {
 
   int cl_n_;
   std::vector<uint32_t> cl_id_;
+  std::vector<uint32_t> cl_module_id_;
   std::vector<float> cl_mipPt_;
   std::vector<float> cl_pt_;
   std::vector<float> cl_energy_;
@@ -33,6 +34,9 @@ class HGCalTriggerNtupleHGCClusters : public HGCalTriggerNtupleBase {
   std::vector<std::vector<uint32_t>> cl_cells_id_;
   std::vector<uint32_t> cl_multicluster_id_;
   std::vector<float> cl_multicluster_pt_;
+  std::vector<int> cl_column_;
+  std::vector<unsigned> cl_channel_;
+  std::vector<unsigned> cl_frame_;
 };
 
 DEFINE_EDM_PLUGIN(HGCalTriggerNtupleFactory, HGCalTriggerNtupleHGCClusters, "HGCalTriggerNtupleHGCClusters");
@@ -61,6 +65,7 @@ void HGCalTriggerNtupleHGCClusters::initialize(TTree& tree,
   // note: can't use withPrefix() twice within a same statement because bname gets overwritten
   tree.Branch(withPrefix("n"), &cl_n_, (prefix + "_n/I").c_str());
   tree.Branch(withPrefix("id"), &cl_id_);
+  tree.Branch(withPrefix("moduleId"), &cl_module_id_);
   tree.Branch(withPrefix("mipPt"), &cl_mipPt_);
   tree.Branch(withPrefix("pt"), &cl_pt_);
   tree.Branch(withPrefix("energy"), &cl_energy_);
@@ -72,6 +77,9 @@ void HGCalTriggerNtupleHGCClusters::initialize(TTree& tree,
   tree.Branch(withPrefix("cells_id"), &cl_cells_id_);
   tree.Branch(withPrefix("multicluster_id"), &cl_multicluster_id_);
   tree.Branch(withPrefix("multicluster_pt"), &cl_multicluster_pt_);
+  tree.Branch(withPrefix("column"), &cl_column_);
+  tree.Branch(withPrefix("channel"), &cl_channel_);
+  tree.Branch(withPrefix("frame"), &cl_frame_);
 }
 
 void HGCalTriggerNtupleHGCClusters::fill(const edm::Event& e, const HGCalTriggerNtupleEventSetup& es) {
@@ -110,9 +118,13 @@ void HGCalTriggerNtupleHGCClusters::fill(const edm::Event& e, const HGCalTrigger
     cl_phi_.emplace_back(cl_itr->phi());
 
     cl_id_.emplace_back(cl_itr->detId());
+    cl_module_id_.emplace_back(cl_itr->module());
     cl_layer_.emplace_back(triggerTools_.layerWithOffset(cl_itr->detId()));
     cl_subdet_.emplace_back(cl_itr->subdetId());
     cl_cells_n_.emplace_back(cl_itr->constituents().size());
+    cl_column_.emplace_back(cl_itr->column());
+    cl_frame_.emplace_back(cl_itr->frame());
+    cl_channel_.emplace_back(cl_itr->channel());
     // Retrieve indices of trigger cells inside cluster
     cl_cells_id_.emplace_back(cl_itr->constituents().size());
     std::transform(
@@ -128,6 +140,7 @@ void HGCalTriggerNtupleHGCClusters::fill(const edm::Event& e, const HGCalTrigger
 void HGCalTriggerNtupleHGCClusters::clear() {
   cl_n_ = 0;
   cl_id_.clear();
+  cl_module_id_.clear();
   cl_mipPt_.clear();
   cl_pt_.clear();
   cl_energy_.clear();
@@ -139,4 +152,7 @@ void HGCalTriggerNtupleHGCClusters::clear() {
   cl_cells_id_.clear();
   cl_multicluster_id_.clear();
   cl_multicluster_pt_.clear();
+  cl_column_.clear();
+  cl_frame_.clear();
+  cl_channel_.clear();
 }