feat(tb): add Vivado XSIM Verilog testbenches for all 10 sync modules

Add file-based vector testbenches ( + ) for:
- mod_add_sync, rng_sync, poly_arith_sync, comp_decomp_sync
- s_bram/sd_bram, sha3_chain_top
- ntt_core, poly_mul_sync
- sample_cbd_sync, sample_ntt_sync

Each module includes:
- tb_<module>_xsim.v: Vivado XSIM testbench
- gen_vectors.py: Python vector generator (stdlib only)
- vectors/<module>_input.hex: test input vectors
- xsim_run.tcl: compile + elaborate + simulate script
This commit is contained in:
2026-06-25 20:48:38 +08:00
parent ae5f0ca048
commit d4c3fc86fc
42 changed files with 7745 additions and 0 deletions

View File

@@ -0,0 +1,254 @@
// tb_poly_arith_xsim.v - Standard Verilog testbench for poly_arith_sync targeting Vivado xsim
//
// Reads test vectors from a hex file using $readmemh.
// Each line is a 40-bit hex value (10 hex chars, no spaces):
// bits[39:28] = expected[11:0]
// bits[27:16] = coeff_b_in[11:0]
// bits[15:4] = coeff_a_in[11:0]
// bit[3] = mode (0=add, 1=sub)
// bits[2:0] = padding
//
// Drives poly_arith_sync, waits for valid_o, compares coeff_out with expected,
// and reports pass/fail.
//
// Parameters:
// VECTOR_FILE - path to input hex file (default: "sync_rtl/poly_arith/TB/vectors/poly_arith_input.hex")
// RESULT_FILE - path to output file (default: "sync_rtl/poly_arith/TB/vectors/poly_arith_result.hex")
//
// Usage with xsim_run.tcl or manual:
// xvlog -sv sync_rtl/common/pipeline_reg.v sync_rtl/poly_arith/poly_arith_sync.v tb_poly_arith_xsim.v
// xelab tb_poly_arith_xsim -s tb_poly_arith_xsim
// xsim tb_poly_arith_xsim -R
`timescale 1ns / 1ps
module tb_poly_arith_xsim;
// ================================================================
// Parameters
// ================================================================
parameter VECTOR_FILE = "sync_rtl/poly_arith/TB/vectors/poly_arith_input.hex";
parameter RESULT_FILE = "sync_rtl/poly_arith/TB/vectors/poly_arith_result.hex";
parameter MAX_VECTORS = 256;
parameter TIMEOUT_CYCLES = 10000;
parameter Q = 3329;
// ================================================================
// DUT signals
// ================================================================
reg clk;
reg rst_n;
reg [11:0] coeff_a_in;
reg [11:0] coeff_b_in;
reg mode;
reg valid_i;
wire ready_o;
wire [11:0] coeff_out;
wire valid_o;
reg ready_i;
// ================================================================
// DUT instantiation (named ports)
// ================================================================
poly_arith_sync u_dut (
.clk (clk),
.rst_n (rst_n),
.coeff_a_in (coeff_a_in),
.coeff_b_in (coeff_b_in),
.mode (mode),
.valid_i (valid_i),
.ready_o (ready_o),
.coeff_out (coeff_out),
.valid_o (valid_o),
.ready_i (ready_i)
);
// ================================================================
// Clock generation: 100 MHz (10 ns period)
// ================================================================
initial clk = 1'b0;
always #5 clk = ~clk;
// ================================================================
// Vector memory (loaded by $readmemh)
// 40 bits per word:
// bits[39:28] = expected
// bits[27:16] = coeff_b_in
// bits[15:4] = coeff_a_in
// bit[3] = mode
// bits[2:0] = padding
// ================================================================
reg [39:0] vector_mem [0:MAX_VECTORS-1];
integer vec_count;
integer idx;
integer cycle_count;
integer result_fd;
// Test result tracking
integer pass_count;
integer fail_count;
// ================================================================
// Hex-to-ASCII conversion helper
// ================================================================
function [7:0] nibble_to_ascii;
input [3:0] nibble;
begin
if (nibble < 4'd10)
nibble_to_ascii = 8'h30 + {4'd0, nibble}; // '0'-'9'
else
nibble_to_ascii = 8'h41 + ({4'd0, nibble} - 4'd10); // 'A'-'F'
end
endfunction
// ================================================================
// Main test sequence
// ================================================================
initial begin
// Count loaded vectors
vec_count = 0;
// Load vectors from hex file
$readmemh(VECTOR_FILE, vector_mem);
// Count non-X/non-Z entries to determine actual vector count
begin
integer found_end;
found_end = 0;
for (idx = 0; idx < MAX_VECTORS; idx = idx + 1) begin
if (!found_end && (vector_mem[idx] === 40'hx || vector_mem[idx] === 40'hz))
found_end = 1;
else if (!found_end)
vec_count = vec_count + 1;
end
end
if (vec_count == 0) begin
$display("ERROR: No vectors loaded from %s", VECTOR_FILE);
$display(" Check that the file exists and is in the correct format.");
$display(" Each line: <10 hex chars> = {expected[11:0], coeff_b[11:0], coeff_a[11:0], mode, 3'b0}");
$finish;
end
$display("INFO: Loaded %0d test vectors from %s", vec_count, VECTOR_FILE);
// Open result file
result_fd = $fopen(RESULT_FILE, "w");
if (result_fd == 0) begin
$display("ERROR: Cannot open result file: %s", RESULT_FILE);
$finish;
end
// Initialize DUT inputs
coeff_a_in <= 12'd0;
coeff_b_in <= 12'd0;
mode <= 1'b0;
valid_i <= 1'b0;
ready_i <= 1'b1; // always ready to accept output
// Reset sequence: rst_n low for 3 cycles, then high
rst_n <= 1'b0;
repeat (3) @(posedge clk);
rst_n <= 1'b1;
@(posedge clk);
pass_count = 0;
fail_count = 0;
// ============================================================
// Process each vector
// ============================================================
for (idx = 0; idx < vec_count; idx = idx + 1) begin
begin
reg [11:0] vec_expected;
reg [11:0] vec_coeff_b;
reg [11:0] vec_coeff_a;
reg vec_mode;
reg [11:0] captured_out;
// Extract fields from vector
vec_expected = vector_mem[idx][39:28];
vec_coeff_b = vector_mem[idx][27:16];
vec_coeff_a = vector_mem[idx][15:4];
vec_mode = vector_mem[idx][3];
$display("INFO: Vector %0d - a=%0d b=%0d mode=%s expected=%0d",
idx, vec_coeff_a, vec_coeff_b,
vec_mode ? "SUB" : "ADD", vec_expected);
// Drive DUT inputs
coeff_a_in <= vec_coeff_a;
coeff_b_in <= vec_coeff_b;
mode <= vec_mode;
valid_i <= 1'b1;
@(posedge clk);
valid_i <= 1'b0;
// Wait for valid_o assertion (1 pipeline stage latency)
cycle_count = 0;
while (!valid_o && cycle_count < TIMEOUT_CYCLES) begin
@(posedge clk);
cycle_count = cycle_count + 1;
end
if (cycle_count >= TIMEOUT_CYCLES) begin
$display("ERROR: Timeout waiting for valid_o on vector %0d", idx);
fail_count = fail_count + 1;
$fwrite(result_fd, "RESULT: VECTOR %0d TIMEOUT\n", idx);
end else begin
// Capture output (valid_o is high, coeff_out is valid)
captured_out = coeff_out;
// Compare with expected
if (captured_out == vec_expected) begin
pass_count = pass_count + 1;
$fwrite(result_fd, "PASS: %0d - mode=%s a=%03X b=%03X expected=%03X got=%03X\n",
idx, vec_mode ? "SUB" : "ADD",
vec_coeff_a, vec_coeff_b, vec_expected, captured_out);
end else begin
$display("FAIL: Vector %0d - mode=%s a=%0d b=%0d expected=%0d got=%0d",
idx, vec_mode ? "SUB" : "ADD",
vec_coeff_a, vec_coeff_b, vec_expected, captured_out);
fail_count = fail_count + 1;
$fwrite(result_fd, "FAIL: %0d - mode=%s a=%03X b=%03X expected=%03X got=%03X\n",
idx, vec_mode ? "SUB" : "ADD",
vec_coeff_a, vec_coeff_b, vec_expected, captured_out);
end
end
// One extra cycle for valid_o -> ready_i handshake (pipeline clears valid_o)
@(posedge clk);
end
end
// ============================================================
// Summary
// ============================================================
$fclose(result_fd);
$display("========================================");
$display("TEST COMPLETE");
$display(" Total vectors: %0d", vec_count);
$display(" Passed: %0d", pass_count);
$display(" Failed: %0d", fail_count);
$display(" Results written to: %s", RESULT_FILE);
if (fail_count == 0) begin
$display(" STATUS: ALL TESTS PASSED");
end else begin
$display(" STATUS: %0d FAILURE(S) DETECTED", fail_count);
end
$display("========================================");
$finish;
end
// ================================================================
// Timeout watchdog (TIMEOUT_CYCLES * 10ns * vectors * margin)
// ================================================================
initial begin
#(TIMEOUT_CYCLES * 10 * MAX_VECTORS * 2);
$display("FATAL: Global simulation timeout reached");
$finish;
end
endmodule