diff --git a/bin/wally-tool-chain-install.sh b/bin/wally-tool-chain-install.sh
index 798fe51b..ef98aed7 100755
--- a/bin/wally-tool-chain-install.sh
+++ b/bin/wally-tool-chain-install.sh
@@ -35,8 +35,8 @@ set -e # break on error
 
 # Modify accordingly for your machine
 # Increasing NUM_THREADS will speed up parallel compilation of the tools
-NUM_THREADS=2 # for low memory machines > 16GiB
-#NUM_THREADS=8  # for >= 32GiB
+#NUM_THREADS=2 # for low memory machines > 16GiB
+NUM_THREADS=8  # for >= 32GiB
 #NUM_THREADS=16  # for >= 64GiB
 
 sudo mkdir -p $RISCV
diff --git a/sim/coverage-exclusions-rv64gc.do b/sim/coverage-exclusions-rv64gc.do
index 8f79b7d5..9905c897 100644
--- a/sim/coverage-exclusions-rv64gc.do
+++ b/sim/coverage-exclusions-rv64gc.do
@@ -24,11 +24,22 @@
 #// and limitations under the License.
 #////////////////////////////////////////////////////////////////////////////////////////////////
 
+# LZA (i<64) statement confuses coverage tool 
+# This is ugly to exlcude the whole file - is there a better option
+coverage exclude -srcfile lzc.sv 
+
+
+######################
+# Toggle exclusions
+#   Not used because toggle coverage isn't measured
+######################
+
 # Exclude DivBusyE from all design units because rv64gc uses the fdivsqrt unit for integer division
-coverage exclude -togglenode DivBusyE -du *
+#coverage exclude -togglenode DivBusyE -du *
 # Exclude QuotM and RemM from MDU because rv64gc uses the fdivsqrt rather tha div unit for integer division
-coverage exclude -togglenode /dut/core/mdu/mdu/QuotM
-coverage exclude -togglenode /dut/core/mdu/mdu/RemM
+#coverage exclude -togglenode /dut/core/mdu/mdu/QuotM
+#coverage exclude -togglenode /dut/core/mdu/mdu/RemM
 
 # StallFCause is hardwired to 0
-coverage exclude -togglenode /dut/core/hzu/StallFCause
+#coverage exclude -togglenode /dut/core/hzu/StallFCause
+
diff --git a/sim/regression-wally b/sim/regression-wally
index 122b04b5..7a509c89 100755
--- a/sim/regression-wally
+++ b/sim/regression-wally
@@ -162,7 +162,7 @@ def run_test_case(config):
     """Run the given test case, and return 0 if the test suceeds and 1 if it fails"""
     logname = "logs/"+config.variant+"_"+config.name+".log"
     cmd = config.cmd.format(logname)
-    print(cmd)
+#    print(cmd)
     os.chdir(regressionDir)
     os.system(cmd)
     if search_log_for_text(config.grepstr, logname):
diff --git a/src/ebu/ebufsmarb.sv b/src/ebu/ebufsmarb.sv
index bd5cfb89..11d3eb2b 100644
--- a/src/ebu/ebufsmarb.sv
+++ b/src/ebu/ebufsmarb.sv
@@ -56,7 +56,7 @@ module ebufsmarb (
   logic 	     IFUReqD;                    // 1 cycle delayed IFU request. Part of arbitration
   logic 	     FinalBeat, FinalBeatD;      // Indicates the last beat of a burst
   logic 	     BeatCntEn;
-  logic [4-1:0]      NextBeatCount, BeatCount;   // Position within a burst transfer
+  logic [3:0]      BeatCount;   // Position within a burst transfer
   logic 	     CntReset;
   logic [3:0] 	     Threshold;                  // Number of beats derived from HBURST
 
@@ -91,31 +91,36 @@ module ebufsmarb (
   // This is necessary because the pipeline is stalled for the entire duration of both transactions,
   // and the LSU memory request will stil be active.
   flopr #(1) ifureqreg(HCLK, ~HRESETn, IFUReq, IFUReqD);
-  assign LSUDisable = CurrState == ARBITRATE ? 1'b0 : (IFUReqD & ~(HREADY & FinalBeatD));
-  assign LSUSelect = NextState == ARBITRATE ? 1'b1: LSUReq;
+  assign LSUDisable = (CurrState == ARBITRATE) ? 1'b0 : (IFUReqD & ~(HREADY & FinalBeatD));
+  assign LSUSelect = (NextState == ARBITRATE) ? 1'b1: LSUReq;
 
   ////////////////////////////////////////////////////////////////////////////////////////////////////
   // Burst mode logic
   ////////////////////////////////////////////////////////////////////////////////////////////////////
 
-  flopenr #(4) BeatCountReg(HCLK, ~HRESETn | CntReset | FinalBeat, BeatCntEn, NextBeatCount, BeatCount);  
-  assign NextBeatCount = BeatCount + 1'b1;
-
   assign CntReset = NextState == IDLE;
   assign FinalBeat = (BeatCount == Threshold); // Detect when we are waiting on the final access.
-  assign BeatCntEn = (NextState == ARBITRATE & HREADY);
-
+  assign BeatCntEn = (NextState == ARBITRATE) & HREADY;
+  counter #(4) BeatCounter(HCLK, ~HRESETn | CntReset | FinalBeat, BeatCntEn, BeatCount);  
+ 
   // Used to store data from data phase of AHB.
   flopenr #(1) FinalBeatReg(HCLK, ~HRESETn | CntReset, BeatCntEn, FinalBeat, FinalBeatD);
 
   // unlike the bus fsm in lsu/ifu, we need to derive the number of beats from HBURST.
-  always_comb begin
-    case(HBURST)
+  //  HBURST[2:1] Beats
+  //  00          1
+  //  01          4
+  //  10          8
+  //  11          16
+  always_comb 
+    if (HBURST[2:1] == 2'b00) Threshold = 4'b0000;
+    else                      Threshold = (2 << HBURST[2:1]) - 1;
+/*    case(HBURST)
       0:        Threshold = 4'b0000;
       3:        Threshold = 4'b0011; // INCR4
       5:        Threshold = 4'b0111; // INCR8
       7:        Threshold = 4'b1111; // INCR16
       default:  Threshold = 4'b0000; // INCR without end.
     endcase
-  end
+  end */
 endmodule
diff --git a/src/fpu/fctrl.sv b/src/fpu/fctrl.sv
index e787d10b..5700e1b6 100755
--- a/src/fpu/fctrl.sv
+++ b/src/fpu/fctrl.sv
@@ -123,7 +123,7 @@ module fctrl (
                     7'b00001??: ControlsD = `FCTRLW'b1_0_01_10_111_0_0_0; // fsub
                     7'b00010??: ControlsD = `FCTRLW'b1_0_01_10_100_0_0_0; // fmul
                     7'b00011??: ControlsD = `FCTRLW'b1_0_01_01_xx0_1_0_0; // fdiv
-                    7'b01011??: ControlsD = `FCTRLW'b1_0_01_01_xx1_1_0_0; // fsqrt
+                    7'b01011??: if (Rs2D == 5'b0000) ControlsD = `FCTRLW'b1_0_01_01_xx1_1_0_0; // fsqrt
                     7'b00100??: case(Funct3D)
                                   3'b000:  ControlsD = `FCTRLW'b1_0_00_xx_000_0_0_0; // fsgnj
                                   3'b001:  ControlsD = `FCTRLW'b1_0_00_xx_001_0_0_0; // fsgnjn
@@ -141,7 +141,8 @@ module fctrl (
                                   3'b000:  ControlsD = `FCTRLW'b0_1_00_xx_011_0_0_0; // fle
                                   default: ControlsD = `FCTRLW'b0_0_00_xx_000__0_1_0; // non-implemented instruction
                                 endcase
-                    7'b11100??: if (Funct3D == 3'b001)          ControlsD = `FCTRLW'b0_1_10_xx_000_0_0_0; // fclass
+                    7'b11100??: if (Funct3D == 3'b001 & Rs2D == 5'b00000)          
+                                                                ControlsD = `FCTRLW'b0_1_10_xx_000_0_0_0; // fclass
                                 else if (Funct3D[1:0] == 2'b00) ControlsD = `FCTRLW'b0_1_11_xx_000_0_0_0; // fmv.x.w   to int reg
                                 else if (Funct3D[1:0] == 2'b01) ControlsD = `FCTRLW'b0_1_11_xx_000_0_0_0; // fmv.x.d   to int reg
                                 else                            ControlsD = `FCTRLW'b0_0_00_xx_000_0_1_0; // non-implemented instruction
diff --git a/src/fpu/fdivsqrt/fdivsqrtexpcalc.sv b/src/fpu/fdivsqrt/fdivsqrtexpcalc.sv
index b5b2ba33..482fed84 100644
--- a/src/fpu/fdivsqrt/fdivsqrtexpcalc.sv
+++ b/src/fpu/fdivsqrt/fdivsqrtexpcalc.sv
@@ -69,6 +69,6 @@ module fdivsqrtexpcalc(
   assign SExp  = {SXExp[`NE+1], SXExp[`NE+1:1]} + {2'b0, Bias};
   
   // correct exponent for subnormal input's normalization shifts
-  assign DExp  = ({2'b0, Xe} - {{(`NE+1-`DIVBLEN){1'b0}}, ell} - {2'b0, Ye} + {{(`NE+1-`DIVBLEN){1'b0}}, m} + {3'b0, Bias}) & {`NE+2{~XZero}}; // *** why Xzero?  Is this a hack for postprocessor?
+  assign DExp  = ({2'b0, Xe} - {{(`NE+1-`DIVBLEN){1'b0}}, ell} - {2'b0, Ye} + {{(`NE+1-`DIVBLEN){1'b0}}, m} + {3'b0, Bias}); 
   assign Qe = Sqrt ? SExp : DExp;
 endmodule
diff --git a/src/generic/lzc.sv b/src/generic/lzc.sv
index ecfd6796..9b7c841b 100644
--- a/src/generic/lzc.sv
+++ b/src/generic/lzc.sv
@@ -32,7 +32,7 @@ module lzc #(parameter WIDTH = 1) (
   
   always_comb begin
     i = 0;
-    while (~num[WIDTH-1-i] & (i < WIDTH)) i = i+1;  // search for leading one
+    while ((i < WIDTH) & ~num[WIDTH-1-i]) i = i+1;  // search for leading one
     ZeroCnt = i[$clog2(WIDTH+1)-1:0];
   end
 endmodule
diff --git a/src/ieu/alu.sv b/src/ieu/alu.sv
index 2f1bd9d8..15328bb2 100644
--- a/src/ieu/alu.sv
+++ b/src/ieu/alu.sv
@@ -31,11 +31,12 @@
 
 module alu #(parameter WIDTH=32) (
   input  logic [WIDTH-1:0] A, B,        // Operands
-  input  logic [2:0]       ALUControl,  // With Funct3, indicates operation to perform
+  input  logic             W64,         // W64-type instruction
+  input  logic             SubArith,    // Subtraction or arithmetic shift
   input  logic [2:0]       ALUSelect,   // ALU mux select signal
   input  logic [1:0]       BSelect,     // Binary encoding of if it's a ZBA_ZBB_ZBC_ZBS instruction
   input  logic [2:0]       ZBBSelect,   // ZBB mux select signal
-  input  logic [2:0]       Funct3,      // With ALUControl, indicates operation to perform NOTE: Change signal name to ALUSelect
+  input  logic [2:0]       Funct3,      // For BMU decoding
   input  logic [1:0]       CompFlags,   // Comparator flags
   input  logic [2:0]       BALUControl, // ALU Control signals for B instructions in Execute Stage
   output logic [WIDTH-1:0] Result,      // ALU result
@@ -49,30 +50,12 @@ module alu #(parameter WIDTH=32) (
   logic [WIDTH-1:0] CondExtA;                                                     // Result of Zero Extend A select mux
   logic             Carry, Neg;                                                   // Flags: carry out, negative
   logic             LT, LTU;                                                      // Less than, Less than unsigned
-  logic             W64;                                                          // RV64 W-type instruction
-  logic             SubArith;                                                     // Performing subtraction or arithmetic right shift
-  logic             ALUOp;                                                        // 0 for address generation addition or 1 for regular ALU ops
   logic             Asign, Bsign;                                                 // Sign bits of A, B
-  logic             shSignA;
-  logic [WIDTH-1:0] rotA;                                                         // XLEN bit input source to shifter
-  logic [1:0]       shASelect;                                                    // select signal for shifter source generation mux 
-  logic             Rotate;                                                       // Indicates if it is Rotate instruction
 
-  // Extract control signals from ALUControl.
-  assign {W64, SubArith, ALUOp} = ALUControl;
-
-  // Extract rotate signal from BALUControl.
-  assign Rotate = BALUControl[2];
-
-  // Pack control signals into shifter select signal.
-  assign shASelect = {W64, SubArith};
-
-  // A, A sign bit muxes
+  // *** explain this part better; possibly move into shifter and BMU?
   if (WIDTH == 64) begin
-    mux3 #(1) signmux(A[63], A[31], 1'b0, {~SubArith, W64}, shSignA);
-    mux3 #(64) extendmux({{32{1'b0}}, A[31:0]},{{32{A[31]}}, A[31:0]}, A,{~W64, SubArith}, CondExtA);
+    mux3 #(64) extendmux({{32{1'b0}}, A[31:0]}, {{32{A[31]}}, A[31:0]}, A, {~W64, SubArith}, CondExtA); // bottom 32 bits are always A[31:0], so effectively a 32-bit upper mux
   end else begin 
-    mux2 #(1) signmux(1'b0, A[31], SubArith, shSignA);
     assign CondExtA = A;
   end
 
@@ -81,7 +64,7 @@ module alu #(parameter WIDTH=32) (
   assign {Carry, Sum} = CondShiftA + CondMaskInvB + {{(WIDTH-1){1'b0}}, SubArith};
   
   // Shifts (configurable for rotation)
-  shifter sh(.shA(CondExtA), .Sign(shSignA), .rotA, .Amt(B[`LOG_XLEN-1:0]), .Right(Funct3[2]), .W64, .Y(Shift), .Rotate);
+  shifter sh(.A(CondExtA), .Amt(B[`LOG_XLEN-1:0]), .Right(Funct3[2]), .W64, .SubArith, .Y(Shift), .Rotate(BALUControl[2]));
 
   // Condition code flags are based on subtraction output Sum = A-B.
   // Overflow occurs when the numbers being subtracted have the opposite sign 
@@ -95,14 +78,13 @@ module alu #(parameter WIDTH=32) (
  
   // Select appropriate ALU Result
   always_comb begin
-    if (~ALUOp) FullResult = Sum;                         // Always add for ALUOp = 0 (address generation)
-    else casez (ALUSelect)                                // Otherwise check Funct3 NOTE: change signal name to ALUSelect
-      3'b000: FullResult = Sum;                           // add or sub
+    case (ALUSelect)                                
+      3'b000: FullResult = Sum;                           // add or sub (including address generation)
       3'b001: FullResult = Shift;                         // sll, sra, or srl
       3'b010: FullResult = {{(WIDTH-1){1'b0}}, LT};       // slt
       3'b011: FullResult = {{(WIDTH-1){1'b0}}, LTU};      // sltu
       3'b100: FullResult = A ^ CondMaskInvB;              // xor, xnor, binv
-      3'b101: FullResult = (`ZBS_SUPPORTED | `ZBB_SUPPORTED) ? {{(WIDTH-1){1'b0}},{|(A & CondMaskB)}} : Shift;// bext
+      3'b101: FullResult = (`ZBS_SUPPORTED | `ZBB_SUPPORTED) ? {{(WIDTH-1){1'b0}},{|(A & CondMaskB)}} : Shift; // bext (or IEU shift when BMU not supported)
       3'b110: FullResult = A | CondMaskInvB;              // or, orn, bset
       3'b111: FullResult = A & CondMaskInvB;              // and, bclr
     endcase
@@ -114,13 +96,12 @@ module alu #(parameter WIDTH=32) (
 
   // Final Result B instruction select mux
   if (`ZBC_SUPPORTED | `ZBS_SUPPORTED | `ZBA_SUPPORTED | `ZBB_SUPPORTED) begin : bitmanipalu
-    bitmanipalu #(WIDTH) balu(.A, .B, .ALUControl, .ALUSelect, .BSelect, .ZBBSelect, 
-       .Funct3, .CompFlags, .BALUControl, .CondExtA, .ALUResult, .FullResult,
-      .CondMaskB, .CondShiftA, .rotA, .Result);
+    bitmanipalu #(WIDTH) balu(.A, .B, .W64, .BSelect, .ZBBSelect, 
+      .Funct3, .CompFlags, .BALUControl, .CondExtA, .ALUResult, .FullResult,
+      .CondMaskB, .CondShiftA, .Result);
   end else begin
     assign Result = ALUResult;
     assign CondMaskB = B;
     assign CondShiftA = A;
-    assign rotA = A;
   end
 endmodule
\ No newline at end of file
diff --git a/src/ieu/bmu/bitmanipalu.sv b/src/ieu/bmu/bitmanipalu.sv
index 83638ce2..1cf1cd08 100644
--- a/src/ieu/bmu/bitmanipalu.sv
+++ b/src/ieu/bmu/bitmanipalu.sv
@@ -31,49 +31,36 @@
 
 module bitmanipalu #(parameter WIDTH=32) (
   input  logic [WIDTH-1:0] A, B,                    // Operands
-  input  logic [2:0]       ALUControl,              // With Funct3, indicates operation to perform
-  input  logic [2:0]       ALUSelect,               // ALU mux select signal
+  input  logic             W64,                     // W64-type instruction
   input  logic [1:0]       BSelect,                 // Binary encoding of if it's a ZBA_ZBB_ZBC_ZBS instruction
   input  logic [2:0]       ZBBSelect,               // ZBB mux select signal
-  input  logic [2:0]       Funct3,                  // With ALUControl, indicates operation to perform NOTE: Change signal name to ALUSelect
+  input  logic [2:0]       Funct3,                  // Funct3 field of opcode indicates operation to perform
   input  logic [1:0]       CompFlags,               // Comparator flags
   input  logic [2:0]       BALUControl,             // ALU Control signals for B instructions in Execute Stage
   input  logic [WIDTH-1:0] CondExtA,                // A Conditional Extend Intermediary Signal
   input  logic [WIDTH-1:0] ALUResult, FullResult,   // ALUResult, FullResult signals
   output logic [WIDTH-1:0] CondMaskB,               // B is conditionally masked for ZBS instructions
   output logic [WIDTH-1:0] CondShiftA,              // A is conditionally shifted for ShAdd instructions
-  output logic [WIDTH-1:0] rotA,                    // Rotate source signal
   output logic [WIDTH-1:0] Result);                 // Result
 
   logic [WIDTH-1:0] ZBBResult, ZBCResult;           // ZBB, ZBC Result
   logic [WIDTH-1:0] MaskB;                          // BitMask of B
   logic [WIDTH-1:0] RevA;                           // Bit-reversed A
-  logic             W64;                            // RV64 W-type instruction
-  logic             SubArith;                       // Performing subtraction or arithmetic right shift
-  logic             ALUOp;                          // 0 for address generation addition or 1 for regular ALU ops
   logic             Rotate;                         // Indicates if it is Rotate instruction
   logic             Mask;                           // Indicates if it is ZBS instruction
   logic             PreShift;                       // Inidicates if it is sh1add, sh2add, sh3add instruction
   logic [1:0]       PreShiftAmt;                    // Amount to Pre-Shift A 
 
-  // Extract control signals from ALUControl.
-  assign {W64, SubArith, ALUOp} = ALUControl;
-
   // Extract control signals from bitmanip ALUControl.
   assign {Mask, PreShift} = BALUControl[1:0];
 
   // Mask Generation Mux
   if (`ZBS_SUPPORTED) begin: zbsdec
-    decoder #($clog2(WIDTH)) maskgen (B[$clog2(WIDTH)-1:0], MaskB);
+    decoder #($clog2(WIDTH)) maskgen(B[$clog2(WIDTH)-1:0], MaskB);
     mux2 #(WIDTH) maskmux(B, MaskB, Mask, CondMaskB);
   end else assign CondMaskB = B;
  
-  // shifter rotate source select mux
-  if (`ZBB_SUPPORTED & WIDTH == 64) begin
-    mux2 #(WIDTH) rotmux(A, {A[31:0], A[31:0]}, W64, rotA);
-  end else assign rotA = A;
-    
-  // Pre-Shift Mux
+  // 0-3 bit Pre-Shift Mux
   if (`ZBA_SUPPORTED) begin: zbapreshift
     assign PreShiftAmt = Funct3[2:1] & {2{PreShift}};
     assign CondShiftA = CondExtA << (PreShiftAmt);
diff --git a/src/ieu/bmu/bmuctrl.sv b/src/ieu/bmu/bmuctrl.sv
index 8a0a2b8a..b436fda4 100644
--- a/src/ieu/bmu/bmuctrl.sv
+++ b/src/ieu/bmu/bmuctrl.sv
@@ -34,18 +34,17 @@ module bmuctrl(
   // Decode stage control signals
   input  logic        StallD, FlushD,          // Stall, flush Decode stage
   input  logic [31:0] InstrD,                  // Instruction in Decode stage
-  output logic [2:0]  ALUSelectD,              // ALU Mux select signal in Decode Stage
+  input  logic        ALUOpD,                  // Regular ALU Operation
   output logic [1:0]  BSelectD,                // Indicates if ZBA_ZBB_ZBC_ZBS instruction in one-hot encoding in Decode stage
   output logic [2:0]  ZBBSelectD,              // ZBB mux select signal in Decode stage NOTE: do we need this in decode?
   output logic        BRegWriteD,              // Indicates if it is a R type B instruction in Decode Stage
   output logic        BALUSrcBD,               // Indicates if it is an I/IW (non auipc) type B instruction in Decode Stage
   output logic        BW64D,                   // Indiciates if it is a W type B instruction in Decode Stage
-  output logic        BALUOpD,                 // Indicates if it is an ALU B instruction in Decode Stage
   output logic        BSubArithD,              // TRUE if ext, clr, andn, orn, xnor instruction in Decode Stage
   output logic        IllegalBitmanipInstrD,   // Indicates if it is unrecognized B instruction in Decode Stage
   // Execute stage control signals             
   input  logic 	      StallE, FlushE,          // Stall, flush Execute stage
-  output logic [2:0]  ALUSelectE,
+  output logic [2:0]  ALUSelectD,              // ALU select
   output logic [1:0]  BSelectE,                // Indicates if ZBA_ZBB_ZBC_ZBS instruction in one-hot encoding
   output logic [2:0]  ZBBSelectE,              // ZBB mux select signal
   output logic        BRegWriteE,              // Indicates if it is a R type B instruction in Execute
@@ -62,9 +61,10 @@ module bmuctrl(
   logic       MaskD;                           // Indicates if zbs instruction in Decode Stage
   logic       PreShiftD;                       // Indicates if sh1add, sh2add, sh3add instruction in Decode Stage
   logic [2:0] BALUControlD;                    // ALU Control signals for B instructions
+  logic [2:0] BALUSelectD;                     // ALU Mux select signal in Decode Stage for BMU operations
+  logic       BALUOpD;                         // Indicates if it is an ALU B instruction in Decode Stage
 
   `define BMUCTRLW 17
-  `define BMUCTRLWSUB3 14
 
   logic [`BMUCTRLW-1:0] BMUControlsD;                 // Main B Instructions Decoder control signals
 
@@ -76,23 +76,24 @@ module bmuctrl(
 
   // Main Instruction Decoder
   always_comb begin
-    // ALUSelect_BSelect_ZBBSelect_BRegWrite_BALUSrcB_BW64_BALUOp_BSubArithD_RotateD_MaskD_PreShiftD_IllegalBitmanipInstrD
-    BMUControlsD = {Funct3D, `BMUCTRLWSUB3'b00_000_0_0_0_0_0_0_0_0_1};  // default: Illegal instruction
-    if (`ZBA_SUPPORTED)
+    // BALUSelect_BSelect_ZBBSelect_BRegWrite_BALUSrcB_BW64_BALUOp_BSubArithD_RotateD_MaskD_PreShiftD_IllegalBitmanipInstrD
+    BMUControlsD = `BMUCTRLW'b000_00_000_0_0_0_0_0_0_0_0_1;  // default: Illegal bmu instruction;
+    if (`ZBA_SUPPORTED) begin
       casez({OpD, Funct7D, Funct3D})
         17'b0110011_0010000_010: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_0_1_0_0_0_1_0;  // sh1add
         17'b0110011_0010000_100: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_0_1_0_0_0_1_0;  // sh2add
         17'b0110011_0010000_110: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_0_1_0_0_0_1_0;  // sh3add
       endcase
-    if (`ZBA_SUPPORTED & `XLEN==64)
-      casez({OpD, Funct7D, Funct3D})
-        17'b0111011_0010000_010: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_1_0;  // sh1add.uw
-        17'b0111011_0010000_100: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_1_0;  // sh2add.uw
-        17'b0111011_0010000_110: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_1_0;  // sh3add.uw
-        17'b0111011_0000100_000: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_0_0;  // add.uw
-        17'b0011011_000010?_001: BMUControlsD = `BMUCTRLW'b001_01_000_1_1_1_1_0_0_0_0_0;  // slli.uw
-      endcase
-    if (`ZBB_SUPPORTED)
+      if (`XLEN==64)
+        casez({OpD, Funct7D, Funct3D})
+          17'b0111011_0010000_010: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_1_0;  // sh1add.uw
+          17'b0111011_0010000_100: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_1_0;  // sh2add.uw
+          17'b0111011_0010000_110: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_1_0;  // sh3add.uw
+          17'b0111011_0000100_000: BMUControlsD = `BMUCTRLW'b000_01_000_1_0_1_1_0_0_0_0_0;  // add.uw
+          17'b0011011_000010?_001: BMUControlsD = `BMUCTRLW'b001_01_000_1_1_1_1_0_0_0_0_0;  // slli.uw
+        endcase
+    end
+    if (`ZBB_SUPPORTED) begin
       casez({OpD, Funct7D, Funct3D})
         17'b0110011_0110000_001: BMUControlsD = `BMUCTRLW'b001_01_111_1_0_0_1_0_1_0_0_0;  // rol
         17'b0110011_0110000_101: BMUControlsD = `BMUCTRLW'b001_01_111_1_0_0_1_0_1_0_0_0;  // ror
@@ -102,7 +103,6 @@ module bmuctrl(
                                   BMUControlsD = `BMUCTRLW'b000_10_000_1_1_0_1_0_0_0_0_0;  // count instruction
         17'b0110011_0000100_100: if (`XLEN == 32)
                                   BMUControlsD = `BMUCTRLW'b000_10_001_1_1_0_1_0_0_0_0_0;  // zexth (rv32)
-        17'b0010011_0110000_101: BMUControlsD = `BMUCTRLW'b001_00_111_1_1_0_1_0_1_0_0_0;  // rori (rv32)                          
         17'b0110011_0100000_111: BMUControlsD = `BMUCTRLW'b111_01_111_1_0_0_1_1_0_0_0_0;  // andn
         17'b0110011_0100000_110: BMUControlsD = `BMUCTRLW'b110_01_111_1_0_0_1_1_0_0_0_0;  // orn
         17'b0110011_0100000_100: BMUControlsD = `BMUCTRLW'b100_01_111_1_0_0_1_1_0_0_0_0;  // xnor
@@ -115,50 +115,59 @@ module bmuctrl(
         17'b0110011_0000101_100: BMUControlsD = `BMUCTRLW'b000_10_011_1_0_0_1_0_0_0_0_0;  // min
         17'b0110011_0000101_101: BMUControlsD = `BMUCTRLW'b000_10_011_1_0_0_1_0_0_0_0_0;  // minu
       endcase
-    if (`ZBB_SUPPORTED & `XLEN==64)
-      casez({OpD, Funct7D, Funct3D})
-        17'b0111011_0110000_001: BMUControlsD = `BMUCTRLW'b001_00_111_1_0_1_1_0_1_0_0_0;  // rolw
-        17'b0111011_0110000_101: BMUControlsD = `BMUCTRLW'b001_00_111_1_0_1_1_0_1_0_0_0;  // rorw
-        17'b0010011_011000?_101: BMUControlsD = `BMUCTRLW'b001_00_111_1_1_0_1_0_1_0_0_0;  // rori (rv64)
-        17'b0011011_0110000_101: BMUControlsD = `BMUCTRLW'b001_00_111_1_1_1_1_0_1_0_0_0;  // roriw 
-        17'b0011011_0110000_001: if ((Rs2D[4:2]==3'b000) & ~(Rs2D[1] & Rs2D[0]))
-                                  BMUControlsD = `BMUCTRLW'b000_10_000_1_1_1_1_0_0_0_0_0;  // count word instruction
-        17'b0111011_0000100_100: BMUControlsD = `BMUCTRLW'b000_10_001_1_0_0_1_0_0_0_0_0;  // zexth (rv64)
-      endcase
+      if (`XLEN==32)
+        casez({OpD, Funct7D, Funct3D})
+          17'b0110011_0000100_100: BMUControlsD = `BMUCTRLW'b000_10_001_1_1_0_1_0_0_0_0_0;  // zexth (rv32)
+          17'b0010011_0110000_101: BMUControlsD = `BMUCTRLW'b001_00_111_1_1_0_1_0_1_0_0_0;  // rori (rv32)                          
+        endcase
+      else if (`XLEN==64)
+        casez({OpD, Funct7D, Funct3D})
+          17'b0111011_0000100_100: BMUControlsD = `BMUCTRLW'b000_10_001_1_0_0_1_0_0_0_0_0;  // zexth (rv64)
+          17'b0111011_0110000_001: BMUControlsD = `BMUCTRLW'b001_00_111_1_0_1_1_0_1_0_0_0;  // rolw
+          17'b0111011_0110000_101: BMUControlsD = `BMUCTRLW'b001_00_111_1_0_1_1_0_1_0_0_0;  // rorw
+          17'b0010011_011000?_101: BMUControlsD = `BMUCTRLW'b001_00_111_1_1_0_1_0_1_0_0_0;  // rori (rv64)
+          17'b0011011_0110000_101: BMUControlsD = `BMUCTRLW'b001_00_111_1_1_1_1_0_1_0_0_0;  // roriw 
+          17'b0011011_0110000_001: if ((Rs2D[4:2]==3'b000) & ~(Rs2D[1] & Rs2D[0]))
+                                    BMUControlsD = `BMUCTRLW'b000_10_000_1_1_1_1_0_0_0_0_0;  // count word instruction
+        endcase
+    end
     if (`ZBC_SUPPORTED)
       casez({OpD, Funct7D, Funct3D})
         17'b0110011_0000101_0??: BMUControlsD = `BMUCTRLW'b000_11_000_1_0_0_1_0_0_0_0_0;  // ZBC instruction
       endcase
-    if (`ZBS_SUPPORTED) // ZBS
+    if (`ZBS_SUPPORTED) begin // ZBS
       casez({OpD, Funct7D, Funct3D})
-        17'b0010011_0100100_001: BMUControlsD = `BMUCTRLW'b111_01_000_1_1_0_1_1_0_1_0_0;  // bclri
-        17'b0010011_0100100_101: BMUControlsD = `BMUCTRLW'b101_01_000_1_1_0_1_1_0_1_0_0;  // bexti
-        17'b0010011_0110100_001: BMUControlsD = `BMUCTRLW'b100_01_000_1_1_0_1_0_0_1_0_0;  // binvi
-        17'b0010011_0010100_001: BMUControlsD = `BMUCTRLW'b110_01_000_1_1_0_1_0_0_1_0_0;  // bseti
         17'b0110011_0100100_001: BMUControlsD = `BMUCTRLW'b111_01_000_1_0_0_1_1_0_1_0_0;  // bclr
         17'b0110011_0100100_101: BMUControlsD = `BMUCTRLW'b101_01_000_1_0_0_1_1_0_1_0_0;  // bext
         17'b0110011_0110100_001: BMUControlsD = `BMUCTRLW'b100_01_000_1_0_0_1_0_0_1_0_0;  // binv
         17'b0110011_0010100_001: BMUControlsD = `BMUCTRLW'b110_01_000_1_0_0_1_0_0_1_0_0;  // bset
       endcase
-    if (`ZBS_SUPPORTED & `XLEN==64) // ZBS 64-bit
-      casez({OpD, Funct7D, Funct3D})
-        17'b0010011_0100101_001: BMUControlsD = `BMUCTRLW'b111_01_000_1_1_0_1_1_0_1_0_0;  // bclri (rv64)
-        17'b0010011_0100101_101: BMUControlsD = `BMUCTRLW'b101_01_000_1_1_0_1_1_0_1_0_0;  // bexti (rv64)
-        17'b0010011_0110101_001: BMUControlsD = `BMUCTRLW'b100_01_000_1_1_0_1_0_0_1_0_0;  // binvi (rv64)
-        17'b0010011_0010101_001: BMUControlsD = `BMUCTRLW'b110_01_000_1_1_0_1_0_0_1_0_0;  // bseti (rv64)
-      endcase
-    if (`ZBB_SUPPORTED | `ZBS_SUPPORTED) // rv32i/64i shift instructions need certain BMU shifter control when BMU shifter is used
+      if (`XLEN==32) // ZBS 64-bit
+        casez({OpD, Funct7D, Funct3D})
+          17'b0010011_0100100_001: BMUControlsD = `BMUCTRLW'b111_01_000_1_1_0_1_1_0_1_0_0;  // bclri
+          17'b0010011_0100100_101: BMUControlsD = `BMUCTRLW'b101_01_000_1_1_0_1_1_0_1_0_0;  // bexti
+          17'b0010011_0110100_001: BMUControlsD = `BMUCTRLW'b100_01_000_1_1_0_1_0_0_1_0_0;  // binvi
+          17'b0010011_0010100_001: BMUControlsD = `BMUCTRLW'b110_01_000_1_1_0_1_0_0_1_0_0;  // bseti
+        endcase
+      else if (`XLEN==64) // ZBS 64-bit
+        casez({OpD, Funct7D, Funct3D})
+          17'b0010011_010010?_001: BMUControlsD = `BMUCTRLW'b111_01_000_1_1_0_1_1_0_1_0_0;  // bclri (rv64)
+          17'b0010011_010010?_101: BMUControlsD = `BMUCTRLW'b101_01_000_1_1_0_1_1_0_1_0_0;  // bexti (rv64)
+          17'b0010011_011010?_001: BMUControlsD = `BMUCTRLW'b100_01_000_1_1_0_1_0_0_1_0_0;  // binvi (rv64)
+          17'b0010011_001010?_001: BMUControlsD = `BMUCTRLW'b110_01_000_1_1_0_1_0_0_1_0_0;  // bseti (rv64)
+        endcase
+    end
+    if (`ZBB_SUPPORTED | `ZBS_SUPPORTED) // rv32i/64i shift instructions need BMU ALUSelect when BMU shifter is used
       casez({OpD, Funct7D, Funct3D})
         17'b0110011_0?0000?_?01: BMUControlsD = `BMUCTRLW'b001_00_000_1_0_0_1_0_0_0_0_0;  // sra, srl, sll
         17'b0010011_0?0000?_?01: BMUControlsD = `BMUCTRLW'b001_00_000_1_1_0_1_0_0_0_0_0;  // srai, srli, slli
         17'b0111011_0?0000?_?01: BMUControlsD = `BMUCTRLW'b001_00_000_1_0_1_1_0_0_0_0_0;  // sraw, srlw, sllw
         17'b0011011_0?0000?_?01: BMUControlsD = `BMUCTRLW'b001_00_000_1_1_1_1_0_0_0_0_0;  // sraiw, srliw, slliw
       endcase
-      // ZBC
   end
 
   // Unpack Control Signals
-  assign {ALUSelectD,BSelectD,ZBBSelectD, BRegWriteD,BALUSrcBD, BW64D, BALUOpD, BSubArithD, RotateD, MaskD, PreShiftD, IllegalBitmanipInstrD} = BMUControlsD;
+  assign {BALUSelectD, BSelectD, ZBBSelectD, BRegWriteD,BALUSrcBD, BW64D, BALUOpD, BSubArithD, RotateD, MaskD, PreShiftD, IllegalBitmanipInstrD} = BMUControlsD;
   
   // Pack BALUControl Signals
   assign BALUControlD = {RotateD, MaskD, PreShiftD};
@@ -166,6 +175,9 @@ module bmuctrl(
   // Comparator should perform signed comparison when min/max instruction. We have overlap in funct3 with some branch instructions so we use opcode to differentiate betwen min/max and branches
   assign BComparatorSignedD = (Funct3D[2]^Funct3D[0]) & ~OpD[6];
 
+  // Choose ALUSelect brom BMU for BMU operations, Funct3 for IEU operations, or 0 for addition
+  assign ALUSelectD = BALUOpD ? BALUSelectD : (ALUOpD ? Funct3D : 3'b000);
+
   // BMU Execute stage pipieline control register
-  flopenrc#(13) controlregBMU(clk, reset, FlushE, ~StallE, {ALUSelectD, BSelectD, ZBBSelectD, BRegWriteD, BComparatorSignedD,  BALUControlD}, {ALUSelectE, BSelectE, ZBBSelectE, BRegWriteE, BComparatorSignedE, BALUControlE});
+  flopenrc#(10) controlregBMU(clk, reset, FlushE, ~StallE, {BSelectD, ZBBSelectD, BRegWriteD, BComparatorSignedD,  BALUControlD}, {BSelectE, ZBBSelectE, BRegWriteE, BComparatorSignedE, BALUControlE});
 endmodule
\ No newline at end of file
diff --git a/src/ieu/controller.sv b/src/ieu/controller.sv
index 5c397d15..21811b49 100644
--- a/src/ieu/controller.sv
+++ b/src/ieu/controller.sv
@@ -45,7 +45,6 @@ module controller(
   input  logic [1:0]  FlagsE,                  // Comparison flags ({eq, lt})
   input  logic        FWriteIntE,              // Write integer register, coming from FPU controller
   output logic        PCSrcE,                  // Select signal to choose next PC (for datapath and Hazard unit)
-  output logic [2:0]  ALUControlE,             // ALU operation to perform
   output logic 	      ALUSrcAE, ALUSrcBE,      // ALU operands
   output logic        ALUResultSrcE,           // Selects result to pass on to Memory stage
   output logic [2:0]  ALUSelectE,              // ALU mux select signal
@@ -54,6 +53,7 @@ module controller(
   output logic        IntDivE,                 // Integer divide
   output logic        MDUE,                    // MDU (multiply/divide) operatio
   output logic        W64E,                    // RV64 W-type operation
+  output logic        SubArithE,               // Subtraction or arithmetic shift
   output logic        JumpE,                   // jump instruction
   output logic        BranchE,                 // Branch instruction
   output logic        SCE,                     // Store Conditional instruction
@@ -93,12 +93,11 @@ module controller(
   logic [2:0]  ResultSrcD, ResultSrcE, ResultSrcM; // Select which result to write back to register file
   logic [1:0]  MemRWD, MemRWE;                 // Store (write to memory)
   logic	       ALUOpD;                         // 0 for address generation, 1 for all other operations (must use Funct3)
-  logic	       BaseALUOpD, BaseW64D;           // ALU operation and W64 for Base instructions specifically
+  logic	       BaseW64D;                       // W64 for Base instructions specifically
   logic	       BaseRegWriteD;                  // Indicates if Base instruction register write instruction
   logic	       BaseSubArithD;                  // Indicates if Base instruction subtracts, sra, slt, sltu
   logic        BaseALUSrcBD;                   // Base instruction ALU B source select signal
   logic [2:0]  ALUControlD;                    // Determines ALU operation
-  logic [2:0]  ALUSelectD;                     // ALU mux select signal
   logic 	     ALUSrcAD, ALUSrcBD;             // ALU inputs
   logic        ALUResultSrcD, W64D, MDUD;      // ALU result, is RV64 W-type, is multiply/divide instruction
   logic        CSRZeroSrcD;                    // Ignore setting and clearing zeros to CSR
@@ -112,6 +111,7 @@ module controller(
   logic [`CTRLW-1:0] ControlsD;                // Main Instruction Decoder control signals
   logic        SubArithD;                      // TRUE for R-type subtracts and sra, slt, sltu or B-type ext clr, andn, orn, xnor
   logic        subD, sraD, sltD, sltuD;        // Indicates if is one of these instructions
+  logic        ALUOpE;                         // 0 for address generationm 1 for ALU operations
   logic        BranchTakenE;                   // Branch is taken
   logic        eqE, ltE;                       // Comparator outputs
   logic        unused; 
@@ -119,23 +119,18 @@ module controller(
   logic        IEURegWriteE;                   // Register write 
   logic        BRegWriteE;                     // Register write from BMU controller in Execute Stage
   logic        IllegalERegAdrD;                // RV32E attempts to write upper 16 registers
-  logic        IllegalBitmanipInstrD;          // Unrecognized B instruction
   logic [1:0]  AtomicE;                        // Atomic instruction 
   logic        FenceD, FenceE;                 // Fence instruction
   logic        SFenceVmaD;                     // sfence.vma instruction
   logic        IntDivM;                        // Integer divide instruction
   logic [1:0]  BSelectD;                       // One-Hot encoding if it's ZBA_ZBB_ZBC_ZBS instruction in decode stage
   logic [2:0]  ZBBSelectD;                     // ZBB Mux Select Signal
-  logic        BRegWriteD;                     // Indicates if it is a R type B instruction in decode stage
-  logic        BW64D;                          // Indicates if it is a W type B instruction in decode stage
-  logic        BALUOpD;                        // Indicates if it is an ALU B instruction in decode stage
-  logic        BSubArithD;                     // TRUE for B-type ext, clr, andn, orn, xnor
-  logic        BALUSrcBD;                      // B-type alu src select signal
   logic        BComparatorSignedE;             // Indicates if max, min (signed comarison) instruction in Execute Stage
   logic        IFunctD, RFunctD, MFunctD;      // Detect I, R, and M-type RV32IM/Rv64IM instructions
   logic        LFunctD, SFunctD, BFunctD;      // Detect load, store, branch instructions
   logic        JFunctD;                        // detect jalr instruction
   logic        FenceM;                         // Fence.I or sfence.VMA instruction in memory stage
+  logic [2:0]  ALUSelectD;                     // ALU Output selection mux control
 
   // Extract fields
   assign OpD = InstrD[6:0];
@@ -233,18 +228,10 @@ module controller(
   // Squash control signals if coming from an illegal compressed instruction
   // On RV32E, can't write to upper 16 registers.  Checking reads to upper 16 is more costly so disregard them.
   assign IllegalERegAdrD = `E_SUPPORTED & `ZICSR_SUPPORTED & ControlsD[`CTRLW-1] & InstrD[11]; 
-  assign IllegalBaseInstrD = (ControlsD[0] & IllegalBitmanipInstrD) | IllegalERegAdrD ; //NOTE: Do we want to segregate the IllegalBitmanipInstrD into its own output signal
   //assign IllegalBaseInstrD = 1'b0;
   assign {BaseRegWriteD, ImmSrcD, ALUSrcAD, BaseALUSrcBD, MemRWD,
-          ResultSrcD, BranchD, BaseALUOpD, JumpD, ALUResultSrcD, BaseW64D, CSRReadD, 
+          ResultSrcD, BranchD, ALUOpD, JumpD, ALUResultSrcD, BaseW64D, CSRReadD, 
           PrivilegedD, FenceXD, MDUD, AtomicD, unused} = IllegalIEUFPUInstrD ? `CTRLW'b0 : ControlsD;
-
-  // If either bitmanip signal or base instruction signal
-  assign ALUOpD = BaseALUOpD | BALUOpD; 
-  assign RegWriteD = BaseRegWriteD | BRegWriteD; 
-  assign W64D = BaseW64D | BW64D;
-  assign ALUSrcBD = BaseALUSrcBD | BALUSrcBD;
-  assign SubArithD = BaseSubArithD | BSubArithD; // TRUE If B-type or R-type instruction involves inverted operand
   
   assign CSRZeroSrcD = InstrD[14] ? (InstrD[19:15] == 0) : (Rs1D == 0); // Is a CSR instruction using zero as the source?
   assign CSRWriteD = CSRReadD & !(CSRZeroSrcD & InstrD[13]);            // Don't write if setting or clearing zeros
@@ -256,36 +243,45 @@ module controller(
   assign subD = (Funct3D == 3'b000 & Funct7D[5] & OpD[5]);  // OpD[5] needed to distinguish sub from addi
   assign sraD = (Funct3D == 3'b101 & Funct7D[5]);
   assign BaseSubArithD = ALUOpD & (subD | sraD | sltD | sltuD);
-  assign ALUControlD = {W64D, SubArithD, ALUOpD};
 
   // bit manipulation Configuration Block
   if (`ZBS_SUPPORTED | `ZBA_SUPPORTED | `ZBB_SUPPORTED | `ZBC_SUPPORTED) begin: bitmanipi //change the conditional expression to OR any Z supported flags
-    bmuctrl bmuctrl(.clk, .reset, .StallD, .FlushD, .InstrD, .ALUSelectD, .BSelectD, .ZBBSelectD, 
-      .BRegWriteD, .BALUSrcBD, .BW64D, .BALUOpD, .BSubArithD, .IllegalBitmanipInstrD, .StallE, .FlushE, 
-      .ALUSelectE, .BSelectE, .ZBBSelectE, .BRegWriteE, .BComparatorSignedE, .BALUControlE);
+    logic IllegalBitmanipInstrD;          // Unrecognized B instruction
+    logic BRegWriteD;                     // Indicates if it is a R type BMU instruction in decode stage
+    logic BW64D;                          // Indicates if it is a W type BMU instruction in decode stage
+    logic BSubArithD;                     // TRUE for BMU ext, clr, andn, orn, xnor
+    logic BALUSrcBD;                      // BMU alu src select signal
+
+    bmuctrl bmuctrl(.clk, .reset, .StallD, .FlushD, .InstrD, .ALUOpD, .BSelectD, .ZBBSelectD, 
+      .BRegWriteD, .BALUSrcBD, .BW64D, .BSubArithD, .IllegalBitmanipInstrD, .StallE, .FlushE, 
+      .ALUSelectD, .BSelectE, .ZBBSelectE, .BRegWriteE, .BComparatorSignedE, .BALUControlE);
     if (`ZBA_SUPPORTED) begin
       // ALU Decoding is more comprehensive when ZBA is supported. slt and slti conflicts with sh1add, sh1add.uw
       assign sltD = (Funct3D == 3'b010 & (~(Funct7D[4]) | ~OpD[5])) ;
     end else assign sltD = (Funct3D == 3'b010);
 
+    // Combine base and bit manipulation signals
+    assign IllegalBaseInstrD = (ControlsD[0] & IllegalBitmanipInstrD) | IllegalERegAdrD ;
+    assign RegWriteD = BaseRegWriteD | BRegWriteD; 
+    assign W64D = BaseW64D | BW64D;
+    assign ALUSrcBD = BaseALUSrcBD | BALUSrcBD;
+    assign SubArithD = BaseSubArithD | BSubArithD; // TRUE If BMU or R-type instruction involves inverted operand
+
   end else begin: bitmanipi
-    assign ALUSelectD = Funct3D;
-    assign ALUSelectE = Funct3E;
+    assign ALUSelectD = ALUOpD ? Funct3D : 3'b000; // add for address generation when not doing ALU operation
+    assign sltD = (Funct3D == 3'b010);
+    assign IllegalBaseInstrD = ControlsD[0] | IllegalERegAdrD ;
+    assign RegWriteD = BaseRegWriteD; 
+    assign W64D = BaseW64D;
+    assign ALUSrcBD = BaseALUSrcBD;
+    assign SubArithD = BaseSubArithD; // TRUE If B-type or R-type instruction involves inverted operand
+
+    // tie off unused bit manipulation signals
     assign BSelectE = 2'b00;
     assign BSelectD = 2'b00;
     assign ZBBSelectE = 3'b000;
-    assign BRegWriteD = 1'b0;
-    assign BW64D = 1'b0;
-    assign BALUOpD = 1'b0;
-    assign BRegWriteE = 1'b0;
-    assign BSubArithD = 1'b0;
     assign BComparatorSignedE = 1'b0;
     assign BALUControlE = 3'b0;
-    assign BALUSrcBD = 1'b0;
-
-    assign sltD = (Funct3D == 3'b010);
-
-    assign IllegalBitmanipInstrD = 1'b1;
   end
 
   // Fences
@@ -305,9 +301,9 @@ module controller(
   flopenrc #(1)  controlregD(clk, reset, FlushD, ~StallD, 1'b1, InstrValidD);
 
   // Execute stage pipeline control register and logic
-  flopenrc #(28) controlregE(clk, reset, FlushE, ~StallE,
-                           {RegWriteD, ResultSrcD, MemRWD, JumpD, BranchD, ALUControlD, ALUSrcAD, ALUSrcBD, ALUResultSrcD, CSRReadD, CSRWriteD, PrivilegedD, Funct3D, W64D, MDUD, AtomicD, InvalidateICacheD, FlushDCacheD, FenceD, InstrValidD},
-                           {IEURegWriteE, ResultSrcE, MemRWE, JumpE, BranchE, ALUControlE, ALUSrcAE, ALUSrcBE, ALUResultSrcE, CSRReadE, CSRWriteE, PrivilegedE, Funct3E, W64E, MDUE, AtomicE, InvalidateICacheE, FlushDCacheE, FenceE, InstrValidE});
+  flopenrc #(29) controlregE(clk, reset, FlushE, ~StallE,
+                           {ALUSelectD, RegWriteD, ResultSrcD, MemRWD, JumpD, BranchD, ALUSrcAD, ALUSrcBD, ALUResultSrcD, CSRReadD, CSRWriteD, PrivilegedD, Funct3D, W64D, SubArithD, MDUD, AtomicD, InvalidateICacheD, FlushDCacheD, FenceD, InstrValidD},
+                           {ALUSelectE, IEURegWriteE, ResultSrcE, MemRWE, JumpE, BranchE, ALUSrcAE, ALUSrcBE, ALUResultSrcE, CSRReadE, CSRWriteE, PrivilegedE, Funct3E, W64E, SubArithE, MDUE, AtomicE, InvalidateICacheE, FlushDCacheE, FenceE, InstrValidE});
 
   // Branch Logic
   //  The comparator handles both signed and unsigned branches using BranchSignedE
diff --git a/src/ieu/datapath.sv b/src/ieu/datapath.sv
index dc9a0289..a6fb1fdc 100644
--- a/src/ieu/datapath.sv
+++ b/src/ieu/datapath.sv
@@ -40,7 +40,8 @@ module datapath (
   input  logic [2:0]       Funct3E,                 // Funct3 field of instruction in Execute stage
   input  logic             StallE, FlushE,          // Stall, flush Execute stage
   input  logic [1:0]       ForwardAE, ForwardBE,    // Forward ALU operands from later stages
-  input  logic [2:0]       ALUControlE,             // Indicate operation ALU performs
+  input  logic             W64E,                    // W64-type instruction
+  input  logic             SubArithE,               // Subtraction or arithmetic shift
   input  logic             ALUSrcAE, ALUSrcBE,      // ALU operands
   input  logic             ALUResultSrcE,           // Selects result to pass on to Memory stage
   input  logic [2:0]       ALUSelectE,              // ALU mux select signal
@@ -113,7 +114,7 @@ module datapath (
   comparator #(`XLEN) comp(ForwardedSrcAE, ForwardedSrcBE, BranchSignedE, FlagsE);
   mux2  #(`XLEN)  srcamux(ForwardedSrcAE, PCE, ALUSrcAE, SrcAE);
   mux2  #(`XLEN)  srcbmux(ForwardedSrcBE, ImmExtE, ALUSrcBE, SrcBE);
-  alu   #(`XLEN)  alu(SrcAE, SrcBE, ALUControlE, ALUSelectE, BSelectE, ZBBSelectE, Funct3E, FlagsE, BALUControlE, ALUResultE, IEUAdrE);
+  alu   #(`XLEN)  alu(SrcAE, SrcBE, W64E, SubArithE, ALUSelectE, BSelectE, ZBBSelectE, Funct3E, FlagsE, BALUControlE, ALUResultE, IEUAdrE);
   mux2 #(`XLEN)   altresultmux(ImmExtE, PCLinkE, JumpE, AltResultE);
   mux2 #(`XLEN)   ieuresultmux(ALUResultE, AltResultE, ALUResultSrcE, IEUResultE);
 
diff --git a/src/ieu/ieu.sv b/src/ieu/ieu.sv
index c436a96d..0fdba9e8 100644
--- a/src/ieu/ieu.sv
+++ b/src/ieu/ieu.sv
@@ -76,7 +76,6 @@ module ieu (
 
   logic [2:0] ImmSrcD;                                       // Select type of immediate extension 
   logic [1:0] FlagsE;                                        // Comparison flags ({eq, lt})
-  logic [2:0] ALUControlE;                                   // ALU control indicates function to perform
   logic       ALUSrcAE, ALUSrcBE;                            // ALU source operands
   logic [2:0] ResultSrcW;                                    // Selects result in Writeback stage
   logic       ALUResultSrcE;                                 // Selects ALU result to pass on to Memory stage
@@ -87,6 +86,7 @@ module ieu (
   logic [1:0] BSelectE;                                      // Indicates if ZBA_ZBB_ZBC_ZBS instruction in one-hot encoding
   logic [2:0] ZBBSelectE;                                    // ZBB Result Select Signal in Execute Stage
   logic [2:0] BALUControlE;                                  // ALU Control signals for B instructions in Execute Stage
+  logic       SubArithE;                                     // Subtraction or arithmetic shift
 
   // Forwarding signals
   logic [4:0] Rs1D, Rs2D, Rs1E, Rs2E;                        // Source and destination registers
@@ -99,15 +99,15 @@ module ieu (
 controller c(
     .clk, .reset, .StallD, .FlushD, .InstrD, .ImmSrcD,
     .IllegalIEUFPUInstrD, .IllegalBaseInstrD, .StallE, .FlushE, .FlagsE, .FWriteIntE,
-    .PCSrcE, .ALUControlE, .ALUSrcAE, .ALUSrcBE, .ALUResultSrcE, .ALUSelectE, .MemReadE, .CSRReadE, 
-    .Funct3E, .IntDivE, .MDUE, .W64E, .BranchD, .BranchE, .JumpD, .JumpE, .SCE, .BranchSignedE, .BSelectE, .ZBBSelectE, .BALUControlE, .StallM, .FlushM, .MemRWM,
+    .PCSrcE, .ALUSrcAE, .ALUSrcBE, .ALUResultSrcE, .ALUSelectE, .MemReadE, .CSRReadE, 
+    .Funct3E, .IntDivE, .MDUE, .W64E, .SubArithE, .BranchD, .BranchE, .JumpD, .JumpE, .SCE, .BranchSignedE, .BSelectE, .ZBBSelectE, .BALUControlE, .StallM, .FlushM, .MemRWM,
     .CSRReadM, .CSRWriteM, .PrivilegedM, .AtomicM, .Funct3M,
     .RegWriteM, .FlushDCacheM, .InstrValidM, .InstrValidE, .InstrValidD, .FWriteIntM,
     .StallW, .FlushW, .RegWriteW, .IntDivW, .ResultSrcW, .CSRWriteFenceM, .InvalidateICacheM, .StoreStallD);
 
   datapath   dp(
-    .clk, .reset, .ImmSrcD, .InstrD, .StallE, .FlushE, .ForwardAE, .ForwardBE,
-    .ALUControlE, .Funct3E, .ALUSrcAE, .ALUSrcBE, .ALUResultSrcE, .ALUSelectE, .JumpE, .BranchSignedE, 
+    .clk, .reset, .ImmSrcD, .InstrD, .StallE, .FlushE, .ForwardAE, .ForwardBE, .W64E, .SubArithE,
+    .Funct3E, .ALUSrcAE, .ALUSrcBE, .ALUResultSrcE, .ALUSelectE, .JumpE, .BranchSignedE, 
     .PCE, .PCLinkE, .FlagsE, .IEUAdrE, .ForwardedSrcAE, .ForwardedSrcBE, .BSelectE, .ZBBSelectE, .BALUControlE,
     .StallM, .FlushM, .FWriteIntM, .FIntResM, .SrcAM, .WriteDataM, .FCvtIntW,
     .StallW, .FlushW, .RegWriteW, .IntDivW, .SquashSCW, .ResultSrcW, .ReadDataW, .FCvtIntResW,
diff --git a/src/ieu/shifter.sv b/src/ieu/shifter.sv
index 594ef3dd..8dbdf88e 100644
--- a/src/ieu/shifter.sv
+++ b/src/ieu/shifter.sv
@@ -30,54 +30,59 @@
 `include "wally-config.vh"
 
 module shifter (
-  input  logic [`XLEN-1:0]     shA,                           // shift Source
-  input  logic [`XLEN-1:0]   rotA,                          // rotate source
-  input  logic [`LOG_XLEN-1:0] Amt,                         // Shift amount
-  input  logic                 Right, Rotate, W64, Sign,    // Shift right, rotate signals
-  output logic [`XLEN-1:0]     Y);                          // Shifted result
+  input  logic [`XLEN-1:0]     A,                             // shift Source
+  input  logic [`LOG_XLEN-1:0] Amt,                           // Shift amount
+  input  logic                 Right, Rotate, W64, SubArith, // Shift right, rotate, W64-type operation, arithmetic shift
+  output logic [`XLEN-1:0]     Y);                            // Shifted result
 
-  logic [2*`XLEN-2:0]      z, zshift;                       // Input to funnel shifter, shifted amount before truncated to 32 or 64 bits
-  logic [`LOG_XLEN-1:0]    amttrunc, offset;                // Shift amount adjusted for RV64, right-shift amount
+  logic [2*`XLEN-2:0]      z, zshift;                         // Input to funnel shifter, shifted amount before truncated to 32 or 64 bits
+  logic [`LOG_XLEN-1:0]    amttrunc, Offset;                  // Shift amount adjusted for RV64, right-shift amount
+  logic                    Sign;                              // Sign bit for sign extension
+
+  assign Sign = A[`XLEN-1] & SubArith;  // sign bit for sign extension
 
   if (`ZBB_SUPPORTED) begin: rotfunnel
     if (`XLEN==32) begin // rv32 with rotates
       always_comb  // funnel mux
         case({Right, Rotate})
-          2'b00: z = {shA[31:0], 31'b0};
-          2'b01: z = {rotA,rotA[31:1]};
-          2'b10: z = {{31{Sign}}, shA[31:0]};
-          2'b11: z = {rotA[30:0],rotA};
+          2'b00: z = {A[31:0], 31'b0};
+          2'b01: z = {A[31:0], A[31:1]};
+          2'b10: z = {{31{Sign}}, A[31:0]};
+          2'b11: z = {A[30:0], A};
         endcase
       assign amttrunc = Amt; // shift amount
     end else begin // rv64 with rotates
+      // shifter rotate source select mux
+      logic [`XLEN-1:0]   RotA;                          // rotate source
+      mux2 #(`XLEN) rotmux(A, {A[31:0], A[31:0]}, W64, RotA); // W64 rotatons
       always_comb  // funnel mux
         case ({Right, Rotate})
-          2'b00: z = {shA[63:0],{63'b0}};
-          2'b01: z = {rotA, rotA[63:1]};
-          2'b10: z = {{63{Sign}},shA[63:0]};
-          2'b11: z = {rotA[62:0],rotA[63:0]};
+          2'b00: z = {A[63:0],{63'b0}};
+          2'b01: z = {RotA, RotA[63:1]};
+          2'b10: z = {{63{Sign}}, A[63:0]};
+          2'b11: z = {RotA[62:0], RotA};
         endcase
       assign amttrunc = W64 ? {1'b0, Amt[4:0]} : Amt; // 32- or 64-bit shift
     end
   end else begin: norotfunnel
     if (`XLEN==32) begin:shifter // RV32
       always_comb  // funnel mux
-        if (Right)  z = {{31{Sign}}, shA[31:0]};
-        else        z = {shA[31:0], 31'b0};
+        if (Right)  z = {{31{Sign}}, A[31:0]};
+        else        z = {A[31:0], 31'b0};
       assign amttrunc = Amt; // shift amount
     end else begin:shifter  // RV64
       always_comb  // funnel mux
-        if (Right)  z = {{63{Sign}},shA[63:0]};
-        else        z = {shA[63:0],{63'b0}};
+        if (Right)  z = {{63{Sign}}, A[63:0]};
+        else        z = {A[63:0], {63'b0}};
       assign amttrunc = W64 ? {1'b0, Amt[4:0]} : Amt; // 32- or 64-bit shift
     end
   end
   
   // Opposite offset for right shifts
-  assign offset = Right ? amttrunc : ~amttrunc;
+  assign Offset = Right ? amttrunc : ~amttrunc;
   
   // Funnel operation
-  assign zshift = z >> offset;
+  assign zshift = z >> Offset;
   assign Y = zshift[`XLEN-1:0];    
 endmodule
 
diff --git a/testbench/tests.vh b/testbench/tests.vh
index 83729f96..64b5ca59 100644
--- a/testbench/tests.vh
+++ b/testbench/tests.vh
@@ -44,7 +44,8 @@ string tvpaths[] = '{
 
   string coverage64gc[] = '{
     `COVERAGE,
-    "badinstr",
+    "ieu",
+    "ebu",
     "csrwrites"
   };
 
diff --git a/tests/coverage/Makefile b/tests/coverage/Makefile
index d3686f8e..7d4552af 100644
--- a/tests/coverage/Makefile
+++ b/tests/coverage/Makefile
@@ -17,7 +17,7 @@ all: $(OBJECTS)
 
 # Change many things if bit width isn't 64
 %.elf: $(SRCDIR)/%.$(SEXT) WALLY-init-lib.h Makefile
-	riscv64-unknown-elf-gcc -g -o $@ -march=rv64gc -mabi=lp64 -mcmodel=medany \
+	riscv64-unknown-elf-gcc -g -o $@ -march=rv64gc_zba_zbb_zbc_zbs -mabi=lp64 -mcmodel=medany \
 	    -nostartfiles -T../../examples/link/link.ld $<
 	riscv64-unknown-elf-objdump -S $@ > $@.objdump
 	riscv64-unknown-elf-elf2hex --bit-width 64 --input $@ --output $@.memfile
diff --git a/tests/coverage/ebu.S b/tests/coverage/ebu.S
new file mode 100644
index 00000000..8c69f9d1
--- /dev/null
+++ b/tests/coverage/ebu.S
@@ -0,0 +1,45 @@
+///////////////////////////////////////////
+// ebu.S
+//
+// Written: David_Harris@hmc.edu 23 March 2023
+//
+// Purpose: Test coverage for EBU
+//
+// A component of the CORE-V-WALLY configurable RISC-V project.
+// 
+// Copyright (C) 2021-23 Harvey Mudd College & Oklahoma State University
+//
+// SPDX-License-Identifier: Apache-2.0 WITH SHL-2.1
+//
+// Licensed under the Solderpad Hardware License v 2.1 (the “License”); you may not use this file 
+// except in compliance with the License, or, at your option, the Apache License version 2.0. You 
+// may obtain a copy of the License at
+//
+// https://solderpad.org/licenses/SHL-2.1/
+//
+// Unless required by applicable law or agreed to in writing, any work distributed under the 
+// License is distributed on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, 
+// either express or implied. See the License for the specific language governing permissions 
+// and limitations under the License.
+////////////////////////////////////////////////////////////////////////////////////////////////
+
+// load code to initalize stack, handle interrupts, terminate
+#include "WALLY-init-lib.h"
+
+main:
+
+    # Test clz with all bits being 0
+    li t0, 0
+    clz t1, t0
+    li t0, -1
+    clz t1, t0
+    li t0, 1
+    clz t1, t0
+
+    # Test forwarding from store conditional
+    lr.w t0, 0(a0)
+    sc.w t0, a1, 0(a0)
+    addi t0, t0, 1
+
+    j done
+
diff --git a/tests/coverage/badinstr.S b/tests/coverage/ieu.S
similarity index 65%
rename from tests/coverage/badinstr.S
rename to tests/coverage/ieu.S
index 174ea0ae..e1b23937 100644
--- a/tests/coverage/badinstr.S
+++ b/tests/coverage/ieu.S
@@ -1,9 +1,9 @@
 ///////////////////////////////////////////
-// badinstr.S
+// ieu.S
 //
 // Written: David_Harris@hmc.edu 21 March 2023
 //
-// Purpose: Test illegal instruction opcodes
+// Purpose: Test coverage for IEU
 //
 // A component of the CORE-V-WALLY configurable RISC-V project.
 // 
@@ -27,7 +27,21 @@
 #include "WALLY-init-lib.h"
 
 main:
-    .word 0x00000033 // legal R-type instruction
+
+    # Test clz with all bits being 0
+    li t0, 0
+    clz t1, t0
+    li t0, -1
+    clz t1, t0
+    li t0, 1
+    clz t1, t0
+
+    # Test forwarding from store conditional
+    lr.w t0, 0(a0)
+    sc.w t0, a1, 0(a0)
+    addi t0, t0, 1
+
+    # Test illegal instructions are detected
     .word 0x80000033 // illegal R-type instruction
     .word 0x00007003 // illegal Load instruction
     .word 0x80005013 // illegal I-type instruction: srli: op = 0010011, funct3 = 101, funct7 = 1000000
@@ -37,6 +51,15 @@ main:
     .word 0x0400003B  // Illegal RW or MulDivW instruction
     .word 0x00007067  // Illegal JALR instruction
     .word 0x00002063  // Illegal branch instruction
+    .word 0x60F01013  // Illegal BMU sign extend / count instruction
+    .word 0x60801013  // Illegal BMU sign extend / count instruction
+    .word 0x60301013  // Illegal BMU sign extend / count instruction
+    .word 0x6BF05013  // Illegal BMU similar to rev8
+    .word 0x69805013  // Illegal BMU similar to rev8
+    .word 0x28F05013  // Illegal BMU similar to or.c
+    .word 0x60F0101B  // Illegal BMU similar to count word
+    .word 0x6080101B  // Illegal BMU similar to count word
+    .word 0x6030101B  // Illegal BMU similar to count word
 
     j done