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 +1,265 @@
// tb_sample_ntt_xsim.v - Vivado xsim testbench for sample_ntt_sync
//
// Reads test vectors from a hex file using $readmemh.
// Each line is a packed hex word: {j_idx[1:0], i_idx[1:0], k_i[2:0], rho_i[255:0]}
// - rho_i[255:0] : 64 hex chars (LSB = rho_i[0])
// - k_i[2:0] : bits [258:256]
// - i_idx[1:0] : bits [260:259]
// - j_idx[1:0] : bits [262:261]
// - Total: 264 bits = 66 hex chars
//
// Drives sample_ntt_sync, waits for valid_o, collects 256 coefficients,
// and writes results to an output file.
//
// Usage:
// xvlog -sv sample_ntt_sync.v TB/tb_sample_ntt_xsim.v
// xelab tb_sample_ntt_xsim -s tb_sample_ntt_xsim
// xsim tb_sample_ntt_xsim -R
//
// Prerequisites:
// - Generate vectors: python3 TB/gen_vectors.py
// - Output file: vectors/sample_ntt_input.hex
`timescale 1ns / 1ps
module tb_sample_ntt_xsim;
// ================================================================
// Parameters
// ================================================================
parameter VECTOR_FILE = "sync_rtl/sample_ntt/TB/vectors/sample_ntt_input.hex";
parameter RESULT_FILE = "sync_rtl/sample_ntt/TB/vectors/sample_ntt_result.hex";
parameter EXPECT_FILE = "sync_rtl/sample_ntt/TB/vectors/sample_ntt_expected.hex";
parameter MAX_VECTORS = 32;
parameter TIMEOUT_CYCLES = 50000; // rejection sampling needs many cycles
parameter N_COEFFS = 256;
// ================================================================
// DUT signals
// ================================================================
reg clk;
reg rst_n;
reg [255:0] rho_i;
reg [2:0] k_i;
reg [1:0] i_idx;
reg [1:0] j_idx;
reg valid_i;
wire ready_o;
wire [11:0] coeff_o;
wire valid_o;
reg ready_i;
wire last_o;
// ================================================================
// DUT instantiation
// ================================================================
sample_ntt_sync u_dut (
.clk (clk),
.rst_n (rst_n),
.rho_i (rho_i),
.k_i (k_i),
.i_idx (i_idx),
.j_idx (j_idx),
.valid_i (valid_i),
.ready_o (ready_o),
.coeff_o (coeff_o),
.valid_o (valid_o),
.ready_i (ready_i),
.last_o (last_o)
);
// ================================================================
// Clock generation: 100 MHz (10 ns period)
// ================================================================
initial clk = 1'b0;
always #5 clk = ~clk;
// ================================================================
// Vector memory (loaded by $readmemh)
// 264 bits per word: {1'b0, j_idx[1:0], i_idx[1:0], k_i[2:0], rho_i[255:0]}
// Hex: 66 chars
// ================================================================
reg [263:0] vector_mem [0:MAX_VECTORS-1];
integer vec_count;
integer idx;
integer cycle_count;
integer result_fd;
integer coeff_idx;
// Test result tracking
integer pass_count;
integer fail_count;
// ================================================================
// Hex-to-ASCII conversion helper (for output file)
// ================================================================
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
vec_count = 0;
// Load vectors from hex file
$readmemh(VECTOR_FILE, vector_mem);
// Count non-zero/X 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] === {264{1'bx}} || vector_mem[idx] === {264{1'bz}}))
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: <66 hex chars> = {j, i, k, rho}");
$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
rho_i <= 256'd0;
k_i <= 3'd0;
i_idx <= 2'd0;
j_idx <= 2'd0;
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 [255:0] vec_rho;
reg [2:0] vec_k;
reg [1:0] vec_i;
reg [1:0] vec_j;
// Extract fields from packed vector_mem
// vector_mem[263:0] = {1'b0, j_idx, i_idx, k_i, rho_i}
vec_rho = vector_mem[idx][255:0];
vec_k = vector_mem[idx][258:256];
vec_i = vector_mem[idx][260:259];
vec_j = vector_mem[idx][262:261];
$display("INFO: Vector %0d - k=%0d, i=%0d, j=%0d, rho[0:31]=%0h...",
idx, vec_k, vec_i, vec_j, vec_rho[31:0]);
// Drive DUT with input
rho_i <= vec_rho;
k_i <= vec_k;
i_idx <= vec_i;
j_idx <= vec_j;
valid_i <= 1'b1;
@(posedge clk);
valid_i <= 1'b0;
// Wait for valid_o, then collect all 256 coefficients
// The DUT uses ready/valid handshake; we set ready_i=1
coeff_idx = 0;
cycle_count = 0;
// Write vector header to result file
$fwrite(result_fd, "# VECTOR_%0d k=%0d i=%0d j=%0d rho=0x%064h\n",
idx, vec_k, vec_i, vec_j, vec_rho);
while (coeff_idx < N_COEFFS && cycle_count < TIMEOUT_CYCLES) begin
@(posedge clk);
cycle_count = cycle_count + 1;
if (valid_o) begin
// Capture coefficient
begin
integer k;
reg [3:0] nib;
for (k = 2; k >= 0; k = k - 1) begin
nib = coeff_o[(k*4)+:4];
$fwrite(result_fd, "%c", nibble_to_ascii(nib));
end
end
coeff_idx = coeff_idx + 1;
if (last_o)
$fwrite(result_fd, " # last at coeff_idx=%0d", coeff_idx);
$fwrite(result_fd, "\n");
end
end
if (cycle_count >= TIMEOUT_CYCLES) begin
$display("ERROR: Timeout on vector %0d (got %0d/%0d coefficients)",
idx, coeff_idx, N_COEFFS);
fail_count = fail_count + 1;
end else if (coeff_idx != N_COEFFS) begin
$display("ERROR: Vector %0d incomplete (got %0d/%0d coefficients)",
idx, coeff_idx, N_COEFFS);
fail_count = fail_count + 1;
end else begin
$display("INFO: Vector %0d PASSED (%0d coefficients in %0d cycles)",
idx, coeff_idx, cycle_count);
pass_count = pass_count + 1;
end
// Wait for DUT to return to IDLE before next vector
// The DUT enters ST_DONE then ST_IDLE automatically
@(posedge clk);
end // inner begin block
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);
$display("========================================");
$finish;
end
// ================================================================
// Timeout watchdog (global)
// ================================================================
initial begin
#(TIMEOUT_CYCLES * 10 * 100); // TIMEOUT_CYCLES * 10ns * extra margin
$display("FATAL: Global simulation timeout reached");
$finish;
end
endmodule