// Final row (i=7) wire [7:0] final_carry; generate for (j = 0; j < 7; j = j + 1) begin if (j == 0) ha ha_final (.a(pp[7][0]), .b(s[6][0]), .sum(s[7][j]), .carry(final_carry[j])); else fa fa_final (.a(pp[7][j]), .b(s[6][j]), .cin(final_carry[j-1]), .sum(s[7][j]), .cout(final_carry[j])); end assign s[7][7] = final_carry[6]; endgenerate
assign final_sum[7] = final_carry[6];
// Row 1: half adder at LSB, rest pass carry/sum assign sum[0][0] = pp[1][0]; assign carry[0][0] = 1'b0; // Not used
This work implements an using structural and dataflow modeling in Verilog. 2. Multiplication Algorithm Let the multiplicand be ( A = A_7A_6...A_0 ) and multiplier be ( B = B_7B_6...B_0 ). The product ( P = A \times B ) is computed as: 8 bit array multiplier verilog code
Abstract —This paper presents the design, implementation, and simulation of an 8-bit array multiplier using Verilog HDL. Array multipliers offer a regular structure suitable for VLSI implementation. The design utilizes full adders and half adders arranged in a systolic array to compute the product of two 8-bit unsigned numbers, resulting in a 16-bit output. The code is synthesized for generic digital design and validated through simulation testbenches. 1. Introduction Multiplication is a fundamental arithmetic operation in digital signal processing (DSP), microprocessors, and AI accelerators. While sequential multipliers save area, parallel array multipliers achieve high speed by computing partial products simultaneously. The array multiplier is particularly attractive due to its regular layout, making it easy to fabricate and pipeline.
[ P = \sum_i=0^7 (A \cdot B_i) \cdot 2^i ]
// Generate partial products: pp[i][j] = A[i] & B[j] genvar i, j; generate for (i = 0; i < 8; i = i + 1) begin : pp_gen for (j = 0; j < 8; j = j + 1) begin : bit_gen assign pp[i][j] = A[i] & B[j]; end end endgenerate // Final row (i=7) wire [7:0] final_carry; generate
// Middle columns (full adders) for (j = 1; j < 7; j = j + 1) begin : cols fa fa_inst ( .a (pp[k][j]), .b (sum[k-1][j-1]), .cin (carry[k][j-1]), .sum (sum[k][j]), .cout (carry[k][j]) ); end // Last column (just propagate carry from previous) assign sum[k][7] = carry[k][6]; end endgenerate
// Assign product bits assign P[1] = sum[0][0]; assign P[2] = sum[1][1]; assign P[3] = sum[2][2]; assign P[4] = sum[3][3]; assign P[5] = sum[4][4]; assign P[6] = sum[5][5]; assign P[7] = sum[6][6]; assign P[8] = final_sum[0]; assign P[9] = final_sum[1]; assign P[10] = final_sum[2]; assign P[11] = final_sum[3]; assign P[12] = final_sum[4]; assign P[13] = final_sum[5]; assign P[14] = final_sum[6]; assign P[15] = final_sum[7];
—Array multiplier, Verilog, digital design, parallel multiplication, full adder. The product ( P = A \times B
// Middle rows (i=1 to 6) genvar i; generate for (i = 1; i < 7; i = i + 1) begin // First bit of row i ha ha_i0 (.a(pp[i][0]), .b(s[i-1][0]), .sum(s[i][0]), .carry(c[i][0])); // Remaining bits for (j = 1; j < 7; j = j + 1) begin fa fa_ij (.a(pp[i][j]), .b(s[i-1][j]), .cin(c[i][j-1]), .sum(s[i][j]), .cout(c[i][j])); end // Last bit of row i assign s[i][7] = c[i][6]; end endgenerate
endmodule The above manual connection for final product is simplified. A cleaner implementation uses a 2D array of carry-save adders. Below is a more elegant version using generate loops. 4.4 Optimized Structured Version module array_multiplier_8bit_optimized ( input [7:0] A, B, output [15:0] P ); wire [7:0] pp [0:7]; wire [7:0] s [0:7]; // sum between rows wire [7:0] c [0:7]; // carry between rows // Partial product generation generate for (i = 0; i < 8; i = i + 1) begin for (j = 0; j < 8; j = j + 1) begin assign pp[i][j] = A[i] & B[j]; end end endgenerate
// Row 7: full adders for all but last column generate for (j = 0; j < 7; j = j + 1) begin : final_row if (j == 0) begin ha final_ha ( .a (pp[7][0]), .b (sum[6][j]), .sum (final_sum[j]), .carry(final_carry[j]) ); end else begin fa final_fa ( .a (pp[7][j]), .b (sum[6][j-1]), .cin (final_carry[j-1]), .sum (final_sum[j]), .cout (final_carry[j]) ); end end endgenerate