diff --git a/pipelined/src/ieu/clmul.sv b/pipelined/src/ieu/clmul.sv
index 4fa8dda5a..5557283f9 100644
--- a/pipelined/src/ieu/clmul.sv
+++ b/pipelined/src/ieu/clmul.sv
@@ -31,23 +31,22 @@
 
 module clmul #(parameter WIDTH=32) (
   input  logic [WIDTH-1:0] A, B,       // Operands
-  output logic [WIDTH-1:0] Result);     // ZBS result
+  output logic [WIDTH-1:0] ClmulResult);     // ZBS result
 
   logic [WIDTH-1:0] pp [WIDTH-1:0]; //partial AND products
-  logic [WIDTH-1:0] sop; //sum of partial products
 
   genvar i,j;
-  for (i=1; i<WIDTH;i+=WIDTH) begin:outer //loop fills partial product array
-    for (j=0;j<i;j++) begin: inner
+  for (i=1; i<WIDTH;i++) begin:outer //loop fills partial product array
+    for (j=0;j<=i;j++) begin: inner
       assign pp[i][j] = A[i]&B[j];
     end
   end
 
   for (i=1;i<WIDTH;i++) begin:xortree
-    assign result[i] = ^pp[i][i:0];
+    assign result[i] = ^pp[i:0][i];
   end
 
-  assign result[0] = A[0]&B[0];
+  assign ClmulResult[0] = A[0]&B[0];
 
 
 endmodule
diff --git a/pipelined/src/ieu/zbc.sv b/pipelined/src/ieu/zbc.sv
index 14cc2b889..9e73eba1b 100644
--- a/pipelined/src/ieu/zbc.sv
+++ b/pipelined/src/ieu/zbc.sv
@@ -29,13 +29,50 @@
 
 `include "wally-config.vh"
 
-module zbs #(parameter WIDTH=32) (
+module zbc #(parameter WIDTH=32) (
   input  logic [WIDTH-1:0] A, B,       // Operands
-  //input  logic [2:0]       ALUControl, // With Funct3, indicates operation to perform
-  input  logic [6:0]       Funct7,
-  input  logic [2:0]       Funct3,     // With ***Control, indicates operation to perform
-  output logic [WIDTH-1:0] ZBCResult);     // ZBC result
+  input  logic [2:0]       Funct3,     // Indicates operation to perform
+  output logic [WIDTH-1:0] ZBCResult); // ZBC result
 
+  logic [WIDTH-1:0] ClmulResult, RevClmulResult;
+  logic [WIDTH-1:0] RevA, RevB;
+  logic [WIDTH-1:0] X,Y;
+
+
+  genvar i;
+  
+
+  bitreverse brA(.a(A), .b(RevA));
+  bitreverse brB(.a(B), .b(RevB));
+   
+  //NOTE: Is it better to mux in input to a SINGLE clmul or to instantiate 3 clmul and MUX the result?
+  //current implementation CP goes MUX -> CLMUL -> MUX -> RESULT
+  //alternate could have CLMUL * 3 -> MUX -> MUX
+  always_comb begin
+    casez (Funct3)
+      3'b001: begin //clmul
+        X = A;
+        Y = B;
+      end
+      3'b011: begin //clmulh
+        X = {RevA[WIDTH-2:0], {1'b0}};
+        Y = {{1'b0}, RevB[WIDTH-2:0]};
+      end
+      3'b010: begin //clmulr
+        X = {A[WIDTH-2:0], {1'b0}};
+        Y = B;
+      end
+      default: begin
+        X = 0;
+        Y = 0;
+      end
+    endcase
+    
+  end
+  clmul clm(.A(X), .B(Y), .ClmulResult(ClmulResult));
+  bitreverse brClmulResult(.a(ClmulResult), .b(RevClmulResult));
+
+  assign ZBCResult = (Funct3 == 3'b011) ? RevClmulResult : ClmulResult;
 
 
 endmodule
\ No newline at end of file