Pipeline ML-KEM datapath bottlenecks

sync_rtl/sha3/sha3_top.v

@@ -100,6 +100,16 @@ module sha3_top (
     reg           mb_last_r;         // captured last-block flag
     reg  [255:0]  mb_digest_r;       // latched 256-bit digest (sticky in MB_DONE)
 
+    // ================================================================
+    // Keccak core
+    // ================================================================
+    wire              kc_valid_i;
+    /* verilator lint_off UNUSEDSIGNAL */
+    wire [1599:0]     kc_state_o;
+    wire              kc_ready_o;
+    /* verilator lint_on UNUSEDSIGNAL */
+    wire              kc_valid_o;
+
     // XOR the incoming block into the low 1088 bits (rate) of the state.
     wire [1599:0] mb_xored;
     assign mb_xored = mb_state_r ^ {{(1600-1088){1'b0}}, mb_block_i};
@@ -119,16 +129,6 @@ module sha3_top (
         endcase
     end
 
-    // ================================================================
-    // Keccak core
-    // ================================================================
-    wire              kc_valid_i;
-    /* verilator lint_off UNUSEDSIGNAL */
-    wire [1599:0]     kc_state_o;
-    wire              kc_ready_o;
-    /* verilator lint_on UNUSEDSIGNAL */
-    wire              kc_valid_o;
-
     // Keccak input: multi-block xored state when mb_en, else single-block absorb.
     wire [1599:0] kc_state_i_mux;
     assign kc_state_i_mux = mb_en ? mb_xored : absorb_state;