diff --git a/ChaCha20_Poly1305_64/sim/poly1305_friendly_modular_mult.py b/ChaCha20_Poly1305_64/sim/poly1305_friendly_modular_mult.py
index f521981..5eb40d7 100644
--- a/ChaCha20_Poly1305_64/sim/poly1305_friendly_modular_mult.py
+++ b/ChaCha20_Poly1305_64/sim/poly1305_friendly_modular_mult.py
@@ -78,7 +78,7 @@ async def test_sanity(dut):
 
     await tb.cycle_reset()
 
-    count = 16
+    count = 1024
 
     for _ in range(count):
         await tb.write_input(random.randint(1,2**128-1), random.randint(0, 2**130-6))
@@ -93,6 +93,4 @@ async def test_sanity(dut):
             tb.log.info(f"{sim_val:x} -> {dut_val:x}")
             fail = True
 
-    # assert not fail
-
-    await Timer(1, "us")
\ No newline at end of file
+    assert not fail
\ No newline at end of file
diff --git a/ChaCha20_Poly1305_64/sim/poly1305_friendly_modulo.py b/ChaCha20_Poly1305_64/sim/poly1305_friendly_modulo.py
index 0294d5f..e96c1da 100644
--- a/ChaCha20_Poly1305_64/sim/poly1305_friendly_modulo.py
+++ b/ChaCha20_Poly1305_64/sim/poly1305_friendly_modulo.py
@@ -88,4 +88,23 @@ async def test_sanity(dut):
             tb.log.info(f"{sim_val:x} -> {dut_val:x}")
             fail = True
 
+    assert not fail
+
+@cocotb.test
+async def test_directed(dut):
+    tb = TB(dut)
+
+    await tb.cycle_reset()
+
+    await tb.write_input(0x14C0D69391E7116E057E7AD833B00B706AA2390C, 4)
+
+    fail = False
+
+    sim_val = await tb.expected_queue.get()
+    dut_val = await tb.output_queue.get()
+
+    if sim_val != dut_val:
+        tb.log.info(f"{sim_val:x} -> {dut_val:x}")
+        fail = True
+
     assert not fail
\ No newline at end of file
diff --git a/ChaCha20_Poly1305_64/src/poly1305_friendly_modular_mult.sv b/ChaCha20_Poly1305_64/src/poly1305_friendly_modular_mult.sv
index 7b50b51..3f6e51a 100644
--- a/ChaCha20_Poly1305_64/src/poly1305_friendly_modular_mult.sv
+++ b/ChaCha20_Poly1305_64/src/poly1305_friendly_modular_mult.sv
@@ -1,5 +1,5 @@
 module poly1305_friendly_modular_mult #(
-    parameter DATA_WIDTH = 128,
+    parameter DATA_WIDTH = 131,
     parameter ACC_WIDTH = 130
 ) (
     input  logic                    i_clk,
@@ -14,24 +14,25 @@ module poly1305_friendly_modular_mult #(
     output logic [ACC_WIDTH-1:0]    o_result
 );
 
+localparam INT_ACC_WIDTH = ACC_WIDTH + 3; // $clog2(8)
+
 localparam [129:0] PRIME = (1 << 130) - 5;
 
 logic [2:0] state_counter, state_counter_next;
 
-logic [2:0] state_counter_p [4];
+logic [2:0] state_counter_p [5];
 
-logic [ACC_WIDTH-1:0] accumulator, accumulator_next;    // accumulator is outgoing
-logic [ACC_WIDTH:0] accumulator_intermediate;
+logic [INT_ACC_WIDTH-1:0] accumulator, accumulator_next;    // accumulator is outgoing
+logic [INT_ACC_WIDTH+1:0] accumulator_intermediate;
 
 logic [DATA_WIDTH-1:0] data, data_next;
-logic [ACC_WIDTH-1:0] h, h_next;    // h is incoming
+logic [INT_ACC_WIDTH-1:0] h, h_next;    // h is incoming
 
 logic [DATA_WIDTH+26-1:0] mult_product, mult_product_next;
 
 logic [ACC_WIDTH-1:0] modulo_result;
 
 assign o_ready = state_counter >= 3'h4;
-assign o_result = accumulator;
 
 always_ff @(posedge i_clk) begin
     if (i_rst) begin
@@ -46,9 +47,7 @@ always_ff @(posedge i_clk) begin
 
         state_counter_p[0] <= state_counter;
 
-        o_valid <= state_counter_p[3] == 3'h4;
-
-        for (int i = 1; i < 4; i++) begin
+        for (int i = 1; i < 5; i++) begin
             state_counter_p[i] <= state_counter_p[i-1];
         end
     end
@@ -72,25 +71,19 @@ always_comb begin
 
     if (state_counter >= 3'h4 && i_valid) begin
         data_next = i_data;
-        h_next = i_accumulator;
+        h_next = (INT_ACC_WIDTH)'(i_accumulator);
         state_counter_next = '0;
     end
 
     if (state_counter_p[3] == '0) begin
-        accumulator_next = modulo_result;
+        accumulator_next = (INT_ACC_WIDTH)'(modulo_result);
     end else begin
-        accumulator_intermediate = accumulator + modulo_result;
-        if (accumulator_intermediate[130]) begin
-            // if we wrapped around, we need to add 5
-            accumulator_next = accumulator_intermediate[129:0] + 5;
-        end else begin
-            accumulator_next = accumulator_intermediate[129:0];
-        end
+        accumulator_next = accumulator + (INT_ACC_WIDTH)'(modulo_result);
     end
 
 end
 
-poly1305_friendly_modulo u_modulo (
+poly1305_friendly_modulo u_mult_modulo (
     .i_clk          (i_clk),
     .i_rst          (i_rst),
 
@@ -102,4 +95,16 @@ poly1305_friendly_modulo u_modulo (
     .o_result       (modulo_result)
 );
 
+poly1305_friendly_modulo u_sum_modulo (
+    .i_clk          (i_clk),
+    .i_rst          (i_rst),
+
+    .i_valid        (state_counter_p[4] == 3'h4),
+    .i_val          ({127'b0, accumulator}),
+    .i_shift_amount ('0),
+
+    .o_valid        (o_valid),
+    .o_result       (o_result)
+);
+
 endmodule
\ No newline at end of file
diff --git a/ChaCha20_Poly1305_64/src/poly1305_friendly_modulo.sv b/ChaCha20_Poly1305_64/src/poly1305_friendly_modulo.sv
index 5e398be..7182ee0 100644
--- a/ChaCha20_Poly1305_64/src/poly1305_friendly_modulo.sv
+++ b/ChaCha20_Poly1305_64/src/poly1305_friendly_modulo.sv
@@ -36,7 +36,7 @@ assign o_valid = valid_sr[2];
 always_ff @(posedge i_clk) begin
     valid_sr <= {valid_sr[1:0], i_valid};
 
-    high_part_1 <= WIDTH'({3'b0, i_val} >> (130 - (i_shift_amount*SHIFT_SIZE))) * MDIFF;
+    high_part_1 <= WIDE_WIDTH'({3'b0, i_val} >> (130 - (i_shift_amount*SHIFT_SIZE))) * MDIFF;
     low_part_1 <= WIDTH'(i_val << (i_shift_amount*SHIFT_SIZE));
 
     high_part_2 <= (intermediate_val >> WIDTH) * 5;