- gen_vectors.py: parse kat_MLKEM_512.rsp, generate hex vectors - tb_mlkem_top_xsim.v: force-inject d/msg/z for KAT testing - mlkem_top_input.hex: 5 vectors (d + msg + z) - mlkem_top_expected.hex: 5 vectors (pk + sk + ct + ss) - xsim_run.tcl: full dependency chain compilation Known issue: mlkem_top FSM has combinational race on rng_valid_i - rng_valid_i driven by state_r (registered) causes rng_sync to miss valid_i pulse when state transitions at posedge - Fix: change rng_valid_i to use state_next pattern (same as sha3_top uses state_next for kc_valid_i)
188 lines
6.3 KiB
Tcl
188 lines
6.3 KiB
Tcl
# NOTE: On some systems, you may need:
|
||
# export LD_PRELOAD=/usr/lib64/libtinfo.so.5
|
||
# before running this script.
|
||
|
||
# xsim_run.tcl - Vivado xsim compilation and simulation for mlkem_top KAT testbench
|
||
#
|
||
# Compiles ALL RTL dependencies for mlkem_top plus the testbench.
|
||
# Run from the project root: ~/Dev/mlkem/
|
||
#
|
||
# Prerequisites:
|
||
# source /opt/Xilinx/Vivado/2019.2/settings64.sh
|
||
#
|
||
# Usage examples:
|
||
# # Run mlkem_top KAT testbench
|
||
# xsim tb_mlkem_top_xsim -R
|
||
#
|
||
# # Step-by-step:
|
||
# vivado -mode batch -source sync_rtl/top/TB/xsim_run.tcl
|
||
#
|
||
# # Or via run_tb.sh:
|
||
# ./run_tb.sh mlkem_top
|
||
|
||
# ================================================================
|
||
# Configuration
|
||
# ================================================================
|
||
set COMMON_DIR sync_rtl/common
|
||
set SHA3_DIR sync_rtl/sha3
|
||
set SHA3C_DIR sync_rtl/sha3_chain
|
||
set RNG_DIR sync_rtl/rng
|
||
set NTT_DIR sync_rtl/ntt
|
||
set PA_DIR sync_rtl/poly_arith
|
||
set PM_DIR sync_rtl/poly_mul
|
||
set CBD_DIR sync_rtl/sample_cbd
|
||
set SNT_DIR sync_rtl/sample_ntt
|
||
set CD_DIR sync_rtl/comp_decomp
|
||
set MA_DIR sync_rtl/mod_add
|
||
set STOR_DIR sync_rtl/storage
|
||
set TOP_DIR sync_rtl/top
|
||
set TB_DIR sync_rtl/top/TB
|
||
|
||
# ================================================================
|
||
# Step 1: Compile common infrastructure
|
||
# ================================================================
|
||
puts "=== Compiling common infrastructure ==="
|
||
|
||
# Pipeline register (used by many modules)
|
||
xvlog -sv -i . ${COMMON_DIR}/pipeline_reg.v
|
||
|
||
# Skid buffer (backpressure buffer)
|
||
xvlog -sv -i . ${COMMON_DIR}/skid_buffer.v
|
||
|
||
# ================================================================
|
||
# Step 2: Compile SHA3 / Keccak core
|
||
# ================================================================
|
||
puts "=== Compiling SHA3/Keccak core ==="
|
||
|
||
# Keccak round (combinational, θ/ρ/π/χ/ι)
|
||
xvlog -sv ${SHA3_DIR}/keccak_round.v
|
||
|
||
# Keccak core (24-round sequential keccak-f[1600])
|
||
xvlog -sv ${SHA3_DIR}/keccak_core.v
|
||
|
||
# SHA3 top wrapper (G/H/J modes, with internal keccak_core)
|
||
xvlog -sv -i . ${SHA3_DIR}/sha3_top.v
|
||
|
||
# ================================================================
|
||
# Step 3: Compile SHA3 chain (G function)
|
||
# ================================================================
|
||
puts "=== Compiling SHA3 chain ==="
|
||
|
||
# sha3_chain_top_shared (G: d → rho, sigma, with external keccak_core)
|
||
xvlog -sv -i . ${SHA3C_DIR}/sha3_chain_top_shared.v
|
||
|
||
# ================================================================
|
||
# Step 4: Compile RNG
|
||
# ================================================================
|
||
puts "=== Compiling RNG ==="
|
||
|
||
# rng_sync (256-bit Galois LFSR)
|
||
xvlog -sv ${RNG_DIR}/rng_sync.v
|
||
|
||
# ================================================================
|
||
# Step 5: Compile NTT core and dependencies
|
||
# ================================================================
|
||
puts "=== Compiling NTT core ==="
|
||
|
||
# Zeta ROM (twiddle factors, 128 × 12-bit)
|
||
xvlog -sv ${NTT_DIR}/zeta_rom.v
|
||
|
||
# Barrett modular multiplier (a·b mod q)
|
||
xvlog -sv ${NTT_DIR}/barrett_mul.v
|
||
|
||
# Butterfly unit (CT/GS butterfly for NTT/INTT)
|
||
xvlog -sv ${NTT_DIR}/butterfly_unit.v
|
||
|
||
# NTT core (256-coeff NTT/INTT FSM)
|
||
xvlog -sv -i . ${NTT_DIR}/ntt_core.v
|
||
|
||
# ================================================================
|
||
# Step 6: Compile polynomial arithmetic
|
||
# ================================================================
|
||
puts "=== Compiling polynomial arithmetic ==="
|
||
|
||
# poly_arith_sync (element-wise poly add/sub)
|
||
xvlog -sv ${PA_DIR}/poly_arith_sync.v
|
||
|
||
# ================================================================
|
||
# Step 7: Compile polynomial multiplication
|
||
# ================================================================
|
||
puts "=== Compiling polynomial multiplication ==="
|
||
|
||
# Zeta ROM for poly_mul (degree-1 basecase)
|
||
xvlog -sv ${PM_DIR}/poly_mul_zeta_rom.v
|
||
|
||
# Basecase multiplier (degree-1 Karatsuba)
|
||
xvlog -sv ${PM_DIR}/basecase_mul.v
|
||
|
||
# poly_mul_sync (NTT-domain polynomial multiplier)
|
||
xvlog -sv -i . ${PM_DIR}/poly_mul_sync.v
|
||
|
||
# ================================================================
|
||
# Step 8: Compile sampling modules
|
||
# ================================================================
|
||
puts "=== Compiling sampling modules ==="
|
||
|
||
# sample_cbd_sync_shared (CBD sampling with external keccak)
|
||
xvlog -sv -i . ${CBD_DIR}/sample_cbd_sync_shared.v
|
||
|
||
# sample_ntt_sync_shared (SampleNTT with external keccak)
|
||
xvlog -sv -i . ${SNT_DIR}/sample_ntt_sync_shared.v
|
||
|
||
# ================================================================
|
||
# Step 9: Compile compression and modular arithmetic
|
||
# ================================================================
|
||
puts "=== Compiling compression and modular arithmetic ==="
|
||
|
||
# comp_decomp_sync (Compress_q / Decompress_q)
|
||
xvlog -sv ${CD_DIR}/comp_decomp_sync.v
|
||
|
||
# mod_add_sync ((a + b) mod q, streaming)
|
||
xvlog -sv ${MA_DIR}/mod_add_sync.v
|
||
|
||
# ================================================================
|
||
# Step 10: Compile storage (BRAM)
|
||
# ================================================================
|
||
puts "=== Compiling storage BRAMs ==="
|
||
|
||
# Single-port BRAM
|
||
xvlog -sv ${STOR_DIR}/s_bram.v
|
||
|
||
# Simple dual-port BRAM
|
||
xvlog -sv ${STOR_DIR}/sd_bram.v
|
||
|
||
# ================================================================
|
||
# Step 11: Compile top-level integration
|
||
# ================================================================
|
||
puts "=== Compiling top-level integration ==="
|
||
|
||
# keccak_arbiter (round-robin arbiter for shared keccak)
|
||
xvlog -sv -i . ${TOP_DIR}/keccak_arbiter.v
|
||
|
||
# mlkem_top (top-level KeyGen/Encaps/Decaps FSM)
|
||
xvlog -sv -i . ${TOP_DIR}/mlkem_top.v
|
||
|
||
# ================================================================
|
||
# Step 12: Compile testbench
|
||
# ================================================================
|
||
puts "=== Compiling testbench ==="
|
||
|
||
# tb_mlkem_top_xsim (KAT vector testbench)
|
||
xvlog -sv ${TB_DIR}/tb_mlkem_top_xsim.v
|
||
|
||
# ================================================================
|
||
# Step 13: Elaborate snapshot (xelab)
|
||
# ================================================================
|
||
puts "=== Elaborating snapshot ==="
|
||
xelab tb_mlkem_top_xsim -s tb_mlkem_top_xsim --timescale 1ns/1ps
|
||
|
||
# ================================================================
|
||
# Step 14: Run simulation
|
||
# ================================================================
|
||
puts ""
|
||
puts "=== Running mlkem_top KAT simulation ==="
|
||
xsim tb_mlkem_top_xsim -R
|
||
|
||
puts ""
|
||
puts "=== mlkem_top simulation complete ==="
|