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 +1,85 @@
#!/usr/bin/env python3
"""gen_vectors.py — Generate SHA3-512 test vectors for tb_sha3_chain_xsim.v
Computes expected rho and sigma values for sha3_chain_top (ML-KEM G function).
The RTL computes: SHA3-512(d_in || 0x02)
- d_in: 256-bit input (32 bytes, big-endian)
- 0x02: single byte appended (k=2 parameter for ML-KEM)
- G(d || 0x02) uses SHA3-512 mode (rate=576, suffix=01)
- rho = hash[255:0] (first 256 bits of hash)
- sigma = hash[511:256] (next 256 bits of hash)
Output:
vectors/sha3_chain_input.hex — 256-bit d_in values (64 hex chars per line)
Usage:
python3 gen_vectors.py
"""
import hashlib
import os
VECTORS_DIR = os.path.join(os.path.dirname(__file__), "vectors")
OUTPUT_FILE = os.path.join(VECTORS_DIR, "sha3_chain_input.hex")
# Test vectors: (label, d_in value)
TEST_VECTORS = [
("all-zeros", 0x0000000000000000000000000000000000000000000000000000000000000000),
("all-ones", 0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF),
("lsb-one", 0x0000000000000000000000000000000000000000000000000000000000000001),
("msb-one", 0x8000000000000000000000000000000000000000000000000000000000000000),
("pattern-aa", 0xAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA),
("pattern-55", 0x5555555555555555555555555555555555555555555555555555555555555555),
("random-1", 0x1A2B3C4D5E6F708192A3B4C5D6E7F8091A2B3C4D5E6F708192A3B4C5D6E7F80),
("random-2", 0xF0E1D2C3B4A5968778695A4B3C2D1E0FF0E1D2C3B4A5968778695A4B3C2D1E0F),
]
def sha3_512_g(d_in: int) -> tuple:
"""Compute rho, sigma = G(d_in || 0x02) using SHA3-512.
Returns (rho, sigma) as 256-bit integers.
"""
# d_in as 32 bytes, big-endian (MSB first)
d_bytes = d_in.to_bytes(32, "big")
# Append k=2 as single byte 0x02
message = d_bytes + b"\x02"
# SHA3-512 hash → 64 bytes
h = hashlib.sha3_512(message).digest()
# rho = first 256 bits, sigma = next 256 bits
rho = int.from_bytes(h[0:32], "big")
sigma = int.from_bytes(h[32:64], "big")
return rho, sigma
def main():
os.makedirs(VECTORS_DIR, exist_ok=True)
d_in_values = []
print("// Expected values computed by gen_vectors.py")
print("// SHA3-512(d_in || 0x02)")
print("//" + "=" * 72)
with open(OUTPUT_FILE, "w") as f:
for label, d_in in TEST_VECTORS:
# Write d_in to hex file (256 bits = 64 hex chars)
f.write(f"{d_in:064X}\n")
d_in_values.append(d_in)
# Compute expected values
rho, sigma = sha3_512_g(d_in)
print(f"// {label}")
print(f"// d_in = 0x{d_in:064x}")
print(f"// rho = 0x{rho:064x}")
print(f"// sigma = 0x{sigma:064x}")
print()
print(f"Generated {len(TEST_VECTORS)} vectors → {OUTPUT_FILE}")
print()
print("// Copy the expected values above into tb_sha3_chain_xsim.v")
print("// as hardcoded parameters/initial blocks.")
if __name__ == "__main__":
main()

View File

@@ -0,0 +1,287 @@
// tb_sha3_chain_xsim.v - Vivado xsim testbench for sha3_chain_top
//
// Tests the ML-KEM G function: SHA3-512(d_in || 0x02) {rho, sigma}.
// Uses $readmemh file-based test vectors for d_in values.
//
// Vector format (256 bits = 64 hex chars per line):
// Each line is a 256-bit d_in value (MSB-first hex).
//
// Expected rho/sigma values are hardcoded (computed by gen_vectors.py
// using hashlib.sha3_512).
//
// Protocol: start_i / done_o handshake
// 1. Drive d_in, assert start_i=1
// 2. Wait for done_o=1 (with timeout watchdog)
// 3. Capture rho_out, sigma_out
// 4. Compare with expected values
// 5. Deassert start_i (FSM returns to IDLE)
`timescale 1ns / 1ps
module tb_sha3_chain_xsim;
// ================================================================
// Parameters
// ================================================================
parameter VECTOR_FILE = "sync_rtl/sha3_chain/TB/vectors/sha3_chain_input.hex";
parameter RESULT_FILE = "sync_rtl/sha3_chain/TB/vectors/sha3_chain_result.hex";
parameter MAX_VECTORS = 256;
parameter TIMEOUT_CYCLES = 2000;
// ================================================================
// DUT signals
// ================================================================
reg clk;
reg rst_n;
reg [255:0] d_in;
reg start_i;
wire done_o;
wire [255:0] rho_out;
wire [255:0] sigma_out;
// ================================================================
// Expected values (computed by gen_vectors.py)
// 8 test vectors total
// ================================================================
reg [255:0] expected_rho [0:7];
reg [255:0] expected_sigma [0:7];
initial begin
// all-zeros
expected_rho[0] = 256'h6a0af64a85e909df8e2816605d20b4e382b30bbb61bf3a5f821a0b5dba9ad3e7;
expected_sigma[0] = 256'he367d3e9ab3b86b64230aa8bf8815d408ef819f9e9d956ce22bbc2f68eaa9e3a;
// all-ones
expected_rho[1] = 256'hf393670510fe33b5df9efb515bf1515c84bdf625e3c53154c10c7d2c92b7f234;
expected_sigma[1] = 256'h9fac853f1e61e8389a04fc710845963c18e48fbec11c66d7d6567f8e168160cc;
// lsb-one
expected_rho[2] = 256'h90ad3aafcc6bde61dc5014cf6cdee8065504733fc0caa8bddf3e1689a7b7b302;
expected_sigma[2] = 256'h3c8686e00e96619b07c7d56fa1effce7ec5597f94a9109ec40c2a6314f6e4ada;
// msb-one
expected_rho[3] = 256'h6c914803c353f4f3b4d8cc541b67019dd2d04cd0fb2ba51b8ebaba973d8f5cbe;
expected_sigma[3] = 256'h33d64b904e1afa541dbe72162021b54c7aef182125da38d88dd7d076636af6cf;
// pattern-aa
expected_rho[4] = 256'h561a98ff76434dc201ca8152cf2b97342090157a522354e299db35fec29690aa;
expected_sigma[4] = 256'hed57f5826ed6e77c756cf821244b350e6b34eb05f9639e227f9a5e130eca649f;
// pattern-55
expected_rho[5] = 256'hff31fe4fc62849226d9197992b1a2d0429c2c325011d2c7bb48860920c04636c;
expected_sigma[5] = 256'hdb5f9599ae43d39fa182896d0ab1d1af663f19355dfeb951fed7b1c8c94eb0d3;
// random-1
expected_rho[6] = 256'h4538916fc357ba9fe24033fa8c1e18cbfb14faf7e1771e0d7521c80cb0d4379f;
expected_sigma[6] = 256'h78565d212000aabb8086e3373ad82d45c07589bcca35409a3f5d9fd30623340e;
// random-2
expected_rho[7] = 256'h176c0b7e91b90ae50757b14bbec130a9e328d09d020466565829de47f6b387cd;
expected_sigma[7] = 256'h413f41c838828e079d5e06b06de61eed6b5bd5005b334e516be6e3b900da7938;
end
// ================================================================
// DUT instantiation
// ================================================================
sha3_chain_top u_dut (
.clk (clk),
.rst_n (rst_n),
.d_in (d_in),
.start_i (start_i),
.done_o (done_o),
.rho_out (rho_out),
.sigma_out(sigma_out)
);
// ================================================================
// Clock generation: 100 MHz (10 ns period)
// ================================================================
initial clk = 1'b0;
always #5 clk = ~clk;
// ================================================================
// Vector memory (loaded by $readmemh)
// ================================================================
reg [255:0] vector_mem [0:MAX_VECTORS-1];
integer vec_count;
integer idx;
integer cycle_count;
integer result_fd;
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};
else
nibble_to_ascii = 8'h41 + ({4'd0, nibble} - 4'd10);
end
endfunction
// ================================================================
// Main test sequence
// ================================================================
initial begin
vec_count = 0;
$readmemh(VECTOR_FILE, vector_mem);
// Count non-X entries
begin
integer found_end;
found_end = 0;
for (idx = 0; idx < MAX_VECTORS; idx = idx + 1) begin
if (!found_end && (vector_mem[idx] === 256'hx || vector_mem[idx] === 256'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.");
$display(" Format: 64 hex chars per line (256-bit d_in)");
$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
d_in <= 256'd0;
start_i <= 1'b0;
// 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_d_in;
reg [255:0] captured_rho;
reg [255:0] captured_sigma;
integer bit_idx;
reg [3:0] nib;
vec_d_in = vector_mem[idx];
$display("INFO: Vector %0d - d_in=0x%064h", idx, vec_d_in);
// Drive d_in and assert start_i
d_in <= vec_d_in;
start_i <= 1'b1;
@(posedge clk);
// Wait for done_o (with timeout)
cycle_count = 0;
while (!done_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 done_o on vector %0d", idx);
$fwrite(result_fd, "TIMEOUT: vector %0d d_in=0x%064h\n", idx, vec_d_in);
fail_count = fail_count + 1;
// Force reset the FSM
start_i <= 1'b0;
@(posedge clk);
end else begin
// Capture outputs (valid on cycle done_o=1)
captured_rho = rho_out;
captured_sigma = sigma_out;
// Deassert start_i (FSM returns to IDLE on next cycle)
start_i <= 1'b0;
// Check rho
if (captured_rho !== expected_rho[idx]) begin
$display("FAIL: Vector %0d RHO mismatch", idx);
$display(" expected = 0x%064h", expected_rho[idx]);
$display(" got = 0x%064h", captured_rho);
$fwrite(result_fd, "FAIL: vector %0d RHO expected=0x%064h got=0x%064h\n",
idx, expected_rho[idx], captured_rho);
fail_count = fail_count + 1;
end else begin
pass_count = pass_count + 1;
end
// Check sigma
if (captured_sigma !== expected_sigma[idx]) begin
$display("FAIL: Vector %0d SIGMA mismatch", idx);
$display(" expected = 0x%064h", expected_sigma[idx]);
$display(" got = 0x%064h", captured_sigma);
$fwrite(result_fd, "FAIL: vector %0d SIGMA expected=0x%064h got=0x%064h\n",
idx, expected_sigma[idx], captured_sigma);
fail_count = fail_count + 1;
end else begin
pass_count = pass_count + 1;
end
// Write results to output file
$fwrite(result_fd, "RESULT: %0d ", idx);
$fwrite(result_fd, "d_in=0x");
for (bit_idx = 63; bit_idx >= 0; bit_idx = bit_idx - 1) begin
nib = vec_d_in[(bit_idx*4)+:4];
$fwrite(result_fd, "%c", nibble_to_ascii(nib));
end
$fwrite(result_fd, " rho=0x");
for (bit_idx = 63; bit_idx >= 0; bit_idx = bit_idx - 1) begin
nib = captured_rho[(bit_idx*4)+:4];
$fwrite(result_fd, "%c", nibble_to_ascii(nib));
end
$fwrite(result_fd, " sigma=0x");
for (bit_idx = 63; bit_idx >= 0; bit_idx = bit_idx - 1) begin
nib = captured_sigma[(bit_idx*4)+:4];
$fwrite(result_fd, "%c", nibble_to_ascii(nib));
end
$fwrite(result_fd, "\n");
@(posedge clk);
end
end // inner begin block
end
// ============================================================
// Summary
// ============================================================
$fclose(result_fd);
$display("========================================");
$display("SHA3 CHAIN TEST COMPLETE");
$display(" Total vectors: %0d", vec_count);
$display(" Checks (rho+sigma): %0d", vec_count * 2);
$display(" Passed: %0d", pass_count);
$display(" Failed: %0d", fail_count);
$display(" Results written to: %s", RESULT_FILE);
if (fail_count == 0)
$display(" RESULT: ALL TESTS PASSED");
else
$display(" RESULT: SOME TESTS FAILED");
$display("========================================");
$finish;
end
// ================================================================
// Timeout watchdog
// ================================================================
initial begin
#(TIMEOUT_CYCLES * 10 * 100);
$display("FATAL: Global simulation timeout reached");
$finish;
end
endmodule

View File

@@ -0,0 +1,8 @@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View File

@@ -0,0 +1,64 @@
# xsim_run.tcl - Vivado xsim compilation and simulation script
#
# Compiles sha3_chain_top with all SHA3 dependencies plus testbench.
# Run from the project root: ~/Dev/mlkem/
#
# Dependencies:
# sync_rtl/sha3/keccak_round.v (combinational Keccak round)
# sync_rtl/sha3/keccak_core.v (24-round Keccak core)
# sync_rtl/sha3/sha3_top.v (SHA3 G/H/J top wrapper)
# sync_rtl/sha3_chain/sha3_chain_top.v (ML-KEM G function)
#
# Prerequisites:
# source /opt/Xilinx/Vivado/2019.2/settings64.sh
#
# Usage:
# xsim -runall xsim_run.tcl
# vivado -mode batch -source xsim_run.tcl
# ================================================================
# Configuration
# ================================================================
set SHA3_DIR sync_rtl/sha3
set SHA3_CHAIN_DIR sync_rtl/sha3_chain
set TB_DIR sync_rtl/sha3_chain/TB
# ================================================================
# Step 1: Compile RTL sources (xvlog)
# ================================================================
puts "=== Compiling SHA3 RTL sources ==="
# Core Keccak module (combinational round)
xvlog -sv ${SHA3_DIR}/keccak_round.v
# Keccak core (24-round sequential core)
xvlog -sv ${SHA3_DIR}/keccak_core.v
# SHA3 top wrapper (G/H/J modes)
xvlog -sv ${SHA3_DIR}/sha3_top.v
# sha3_chain_top (ML-KEM G function)
xvlog -sv ${SHA3_CHAIN_DIR}/sha3_chain_top.v
# ================================================================
# Step 2: Compile testbench
# ================================================================
puts "=== Compiling testbench ==="
xvlog -sv ${TB_DIR}/tb_sha3_chain_xsim.v
# ================================================================
# Step 3: Elaborate snapshot (xelab)
# ================================================================
puts "=== Elaborating snapshot ==="
xelab tb_sha3_chain_xsim -s tb_sha3_chain_xsim
# ================================================================
# Step 4: Run simulation
# ================================================================
puts "=== Running sha3_chain test ==="
xsim tb_sha3_chain_xsim -R
puts ""
puts "=== sha3_chain simulation complete ==="