fix(test,docs): remove dead xfft_32 files, update test infra for dual-16 FFT, add regression guide
- Remove xfft_32.v, tb_xfft_32.v, and fft_twiddle_32.mem (dead code since PR #33 moved Doppler to dual 16-pt FFT architecture) - Update run_regression.sh: xfft_16 in PROD_RTL, remove xfft_32 from EXTRA_RTL and all compile commands - Update tb_fft_engine.v to test with N=16 / fft_twiddle_16.mem - Update validate_mem_files.py: validate fft_twiddle_16.mem instead of 32 - Update testbenches and golden data from main_cleanup branch to match dual-16 architecture (tb_doppler_cosim, tb_doppler_realdata, tb_fullchain_realdata, tb_fullchain_mti_cfar_realdata, tb_system_e2e, radar_receiver_final, golden_doppler.mem) - Update CONTRIBUTING.md with full regression test instructions covering FPGA, MCU, GUI, co-simulation, and formal verification Regression: 23/23 FPGA, 20/20 MCU, 57/58 GUI, 56/56 mem validation, all co-sim scenarios PASS.
This commit is contained in:
Jason
@@ -1,11 +0,0 @@
|
||||
// Quarter-wave cosine ROM for 32-point FFT
|
||||
// 8 entries, 16-bit signed Q15 ($readmemh format)
|
||||
// cos(2*pi*k/32) for k = 0..7
|
||||
7FFF
|
||||
7D89
|
||||
7641
|
||||
6A6D
|
||||
5A82
|
||||
471C
|
||||
30FB
|
||||
18F9
|
||||
@@ -403,11 +403,12 @@ assign range_data_32bit = {mti_range_q, mti_range_i};
|
||||
assign range_data_valid = mti_range_valid;
|
||||
|
||||
// ========== DOPPLER PROCESSOR ==========
|
||||
doppler_processor_optimized #(
|
||||
.DOPPLER_FFT_SIZE(32),
|
||||
.RANGE_BINS(64),
|
||||
.CHIRPS_PER_FRAME(32) // MUST MATCH YOUR ACTUAL FRAME SIZE!
|
||||
) doppler_proc (
|
||||
doppler_processor_optimized #(
|
||||
.DOPPLER_FFT_SIZE(16),
|
||||
.RANGE_BINS(64),
|
||||
.CHIRPS_PER_FRAME(32),
|
||||
.CHIRPS_PER_SUBFRAME(16)
|
||||
) doppler_proc (
|
||||
.clk(clk),
|
||||
.reset_n(reset_n),
|
||||
.range_data(range_data_32bit),
|
||||
@@ -473,4 +474,4 @@ assign dbg_adc_i = adc_i_scaled;
|
||||
assign dbg_adc_q = adc_q_scaled;
|
||||
assign dbg_adc_valid = adc_valid_sync;
|
||||
|
||||
endmodule
|
||||
endmodule
|
||||
|
||||
@@ -67,7 +67,7 @@ PROD_RTL=(
|
||||
matched_filter_processing_chain.v
|
||||
range_bin_decimator.v
|
||||
doppler_processor.v
|
||||
xfft_32.v
|
||||
xfft_16.v
|
||||
fft_engine.v
|
||||
usb_data_interface.v
|
||||
edge_detector.v
|
||||
@@ -369,7 +369,7 @@ run_test "Chirp Contract" \
|
||||
|
||||
run_test "Doppler Processor (DSP48)" \
|
||||
tb/tb_doppler_reg.vvp \
|
||||
tb/tb_doppler_cosim.v doppler_processor.v xfft_32.v fft_engine.v
|
||||
tb/tb_doppler_cosim.v doppler_processor.v xfft_16.v fft_engine.v
|
||||
|
||||
run_test "Threshold Detector (detection bugs)" \
|
||||
tb/tb_threshold_detector.vvp \
|
||||
@@ -414,7 +414,7 @@ if [[ "$QUICK" -eq 0 ]]; then
|
||||
cdc_modules.v fir_lowpass.v ddc_input_interface.v \
|
||||
chirp_memory_loader_param.v latency_buffer.v \
|
||||
matched_filter_multi_segment.v matched_filter_processing_chain.v \
|
||||
range_bin_decimator.v doppler_processor.v xfft_32.v fft_engine.v \
|
||||
range_bin_decimator.v doppler_processor.v xfft_16.v fft_engine.v \
|
||||
rx_gain_control.v mti_canceller.v
|
||||
|
||||
# Golden compare
|
||||
@@ -426,7 +426,7 @@ if [[ "$QUICK" -eq 0 ]]; then
|
||||
cdc_modules.v fir_lowpass.v ddc_input_interface.v \
|
||||
chirp_memory_loader_param.v latency_buffer.v \
|
||||
matched_filter_multi_segment.v matched_filter_processing_chain.v \
|
||||
range_bin_decimator.v doppler_processor.v xfft_32.v fft_engine.v \
|
||||
range_bin_decimator.v doppler_processor.v xfft_16.v fft_engine.v \
|
||||
rx_gain_control.v mti_canceller.v
|
||||
|
||||
# Full system top (monitoring-only, legacy)
|
||||
@@ -439,7 +439,7 @@ if [[ "$QUICK" -eq 0 ]]; then
|
||||
cdc_modules.v fir_lowpass.v ddc_input_interface.v \
|
||||
chirp_memory_loader_param.v latency_buffer.v \
|
||||
matched_filter_multi_segment.v matched_filter_processing_chain.v \
|
||||
range_bin_decimator.v doppler_processor.v xfft_32.v fft_engine.v \
|
||||
range_bin_decimator.v doppler_processor.v xfft_16.v fft_engine.v \
|
||||
usb_data_interface.v edge_detector.v radar_mode_controller.v \
|
||||
rx_gain_control.v cfar_ca.v mti_canceller.v fpga_self_test.v
|
||||
|
||||
@@ -453,7 +453,7 @@ if [[ "$QUICK" -eq 0 ]]; then
|
||||
cdc_modules.v fir_lowpass.v ddc_input_interface.v \
|
||||
chirp_memory_loader_param.v latency_buffer.v \
|
||||
matched_filter_multi_segment.v matched_filter_processing_chain.v \
|
||||
range_bin_decimator.v doppler_processor.v xfft_32.v fft_engine.v \
|
||||
range_bin_decimator.v doppler_processor.v xfft_16.v fft_engine.v \
|
||||
usb_data_interface.v edge_detector.v radar_mode_controller.v \
|
||||
rx_gain_control.v cfar_ca.v mti_canceller.v fpga_self_test.v
|
||||
else
|
||||
@@ -472,10 +472,6 @@ run_test "FFT Engine" \
|
||||
tb/tb_fft_reg.vvp \
|
||||
tb/tb_fft_engine.v fft_engine.v
|
||||
|
||||
run_test "XFFT-32 Wrapper" \
|
||||
tb/tb_xfft_reg.vvp \
|
||||
tb/tb_xfft_32.v xfft_32.v fft_engine.v
|
||||
|
||||
run_test "NCO 400MHz" \
|
||||
tb/tb_nco_reg.vvp \
|
||||
tb/tb_nco_400m.v nco_400m_enhanced.v
|
||||
@@ -487,7 +483,7 @@ run_test "FIR Lowpass" \
|
||||
run_test "Matched Filter Chain" \
|
||||
tb/tb_mf_reg.vvp \
|
||||
tb/tb_matched_filter_processing_chain.v matched_filter_processing_chain.v \
|
||||
xfft_32.v fft_engine.v chirp_memory_loader_param.v
|
||||
fft_engine.v chirp_memory_loader_param.v
|
||||
|
||||
echo ""
|
||||
|
||||
|
||||
@@ -30,7 +30,7 @@ T_LONG_CHIRP = 30e-6 # 30 us long chirp
|
||||
T_SHORT_CHIRP = 0.5e-6 # 0.5 us short chirp
|
||||
CIC_DECIMATION = 4
|
||||
FFT_SIZE = 1024
|
||||
DOPPLER_FFT_SIZE = 32
|
||||
DOPPLER_FFT_SIZE = 16
|
||||
LONG_CHIRP_SAMPLES = int(T_LONG_CHIRP * FS_SYS) # 3000 at 100 MHz
|
||||
|
||||
# Overlap-save parameters
|
||||
@@ -84,7 +84,7 @@ def test_structural():
|
||||
expected = {
|
||||
# FFT twiddle files (quarter-wave cosine ROMs)
|
||||
'fft_twiddle_1024.mem': {'lines': 256, 'desc': '1024-pt FFT quarter-wave cos ROM'},
|
||||
'fft_twiddle_32.mem': {'lines': 8, 'desc': '32-pt FFT quarter-wave cos ROM'},
|
||||
'fft_twiddle_16.mem': {'lines': 4, 'desc': '16-pt FFT quarter-wave cos ROM'},
|
||||
# Long chirp segments (4 segments x 1024 samples each)
|
||||
'long_chirp_seg0_i.mem': {'lines': 1024, 'desc': 'Long chirp seg 0 I'},
|
||||
'long_chirp_seg0_q.mem': {'lines': 1024, 'desc': 'Long chirp seg 0 Q'},
|
||||
@@ -145,13 +145,13 @@ def test_twiddle_1024():
|
||||
print(f" Max twiddle error: {max_err} LSB across {len(vals)} entries")
|
||||
|
||||
|
||||
def test_twiddle_32():
|
||||
print("\n=== TEST 2b: FFT Twiddle 32 Validation ===")
|
||||
vals = read_mem_hex('fft_twiddle_32.mem')
|
||||
def test_twiddle_16():
|
||||
print("\n=== TEST 2b: FFT Twiddle 16 Validation ===")
|
||||
vals = read_mem_hex('fft_twiddle_16.mem')
|
||||
|
||||
max_err = 0
|
||||
for k in range(min(8, len(vals))):
|
||||
angle = 2.0 * math.pi * k / 32.0
|
||||
for k in range(min(4, len(vals))):
|
||||
angle = 2.0 * math.pi * k / 16.0
|
||||
expected = int(round(math.cos(angle) * 32767.0))
|
||||
expected = max(-32768, min(32767, expected))
|
||||
actual = vals[k]
|
||||
@@ -160,13 +160,13 @@ def test_twiddle_32():
|
||||
max_err = err
|
||||
|
||||
check(max_err <= 1,
|
||||
f"fft_twiddle_32.mem: max twiddle error = {max_err} LSB (tolerance: 1)")
|
||||
f"fft_twiddle_16.mem: max twiddle error = {max_err} LSB (tolerance: 1)")
|
||||
print(f" Max twiddle error: {max_err} LSB across {len(vals)} entries")
|
||||
|
||||
# Print all 8 entries for reference
|
||||
print(" Twiddle 32 entries:")
|
||||
for k in range(min(8, len(vals))):
|
||||
angle = 2.0 * math.pi * k / 32.0
|
||||
# Print all 4 entries for reference
|
||||
print(" Twiddle 16 entries:")
|
||||
for k in range(min(4, len(vals))):
|
||||
angle = 2.0 * math.pi * k / 16.0
|
||||
expected = int(round(math.cos(angle) * 32767.0))
|
||||
print(f" k={k}: file=0x{vals[k] & 0xFFFF:04x} ({vals[k]:6d}), "
|
||||
f"expected=0x{expected & 0xFFFF:04x} ({expected:6d}), "
|
||||
@@ -605,7 +605,7 @@ def main():
|
||||
|
||||
test_structural()
|
||||
test_twiddle_1024()
|
||||
test_twiddle_32()
|
||||
test_twiddle_16()
|
||||
test_long_chirp()
|
||||
test_short_chirp()
|
||||
test_chirp_vs_model()
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -6,8 +6,8 @@
|
||||
*
|
||||
* Tests the complete Doppler processing pipeline:
|
||||
* - Accumulates 32 chirps x 64 range bins into BRAM
|
||||
* - Processes each range bin: Hamming window -> 32-pt FFT
|
||||
* - Outputs 2048 samples (64 range bins x 32 Doppler bins)
|
||||
* - Processes each range bin: Hamming window -> dual 16-pt FFT (staggered PRF)
|
||||
* - Outputs 2048 samples (64 range bins x 32 packed Doppler bins)
|
||||
*
|
||||
* Validates:
|
||||
* 1. FSM state transitions (IDLE -> ACCUMULATE -> LOAD_FFT -> ... -> OUTPUT)
|
||||
@@ -20,10 +20,10 @@
|
||||
* RTL output written to: tb/cosim/rtl_doppler_<scenario>.csv
|
||||
* RTL FFT inputs written: tb/cosim/rtl_doppler_fft_in_<scenario>.csv
|
||||
*
|
||||
* Compile (SIMULATION branch — uses behavioral xfft_32/fft_engine):
|
||||
* Compile (SIMULATION branch — uses behavioral xfft_16/fft_engine):
|
||||
* iverilog -g2001 -DSIMULATION \
|
||||
* -o tb/tb_doppler_cosim.vvp \
|
||||
* tb/tb_doppler_cosim.v doppler_processor.v xfft_32.v fft_engine.v
|
||||
* tb/tb_doppler_cosim.v doppler_processor.v xfft_16.v fft_engine.v
|
||||
*
|
||||
* Scenarios (use -D flags):
|
||||
* default: stationary target
|
||||
@@ -37,7 +37,7 @@ module tb_doppler_cosim;
|
||||
// Parameters
|
||||
// ============================================================================
|
||||
localparam CLK_PERIOD = 10.0; // 100 MHz
|
||||
localparam DOPPLER_FFT = 32;
|
||||
localparam DOPPLER_FFT = 32; // Total packed Doppler bins (2 sub-frames x 16-pt FFT)
|
||||
localparam RANGE_BINS = 64;
|
||||
localparam CHIRPS = 32;
|
||||
localparam TOTAL_INPUTS = CHIRPS * RANGE_BINS; // 2048
|
||||
@@ -193,7 +193,7 @@ initial begin
|
||||
$display("Doppler Processor Co-Sim Testbench");
|
||||
$display("Scenario: %0s", SCENARIO);
|
||||
$display("Input samples: %0d (32 chirps x 64 range bins)", TOTAL_INPUTS);
|
||||
$display("Expected outputs: %0d (64 range bins x 32 doppler bins)",
|
||||
$display("Expected outputs: %0d (64 range bins x 32 packed Doppler bins, dual 16-pt FFT)",
|
||||
TOTAL_OUTPUTS);
|
||||
$display("============================================================");
|
||||
|
||||
|
||||
@@ -17,7 +17,7 @@
|
||||
* Compile:
|
||||
* iverilog -Wall -DSIMULATION -g2012 \
|
||||
* -o tb/tb_doppler_realdata.vvp \
|
||||
* tb/tb_doppler_realdata.v doppler_processor.v xfft_32.v fft_engine.v
|
||||
* tb/tb_doppler_realdata.v doppler_processor.v xfft_16.v fft_engine.v
|
||||
*
|
||||
* Run from: 9_Firmware/9_2_FPGA/
|
||||
* vvp tb/tb_doppler_realdata.vvp
|
||||
@@ -29,7 +29,7 @@ module tb_doppler_realdata;
|
||||
// PARAMETERS
|
||||
// ============================================================================
|
||||
localparam CLK_PERIOD = 10.0; // 100 MHz
|
||||
localparam DOPPLER_FFT = 32;
|
||||
localparam DOPPLER_FFT = 32; // Total packed Doppler bins (2 sub-frames x 16-pt FFT)
|
||||
localparam RANGE_BINS = 64;
|
||||
localparam CHIRPS = 32;
|
||||
localparam TOTAL_INPUTS = CHIRPS * RANGE_BINS; // 2048
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
* tb_fft_engine.v
|
||||
*
|
||||
* Testbench for the synthesizable FFT engine.
|
||||
* Tests with N=32 first (fast), then validates key properties.
|
||||
* Tests with N=16 (matching the dual-16 Doppler architecture).
|
||||
*
|
||||
* Test Groups:
|
||||
* 1. Impulse response: FFT of delta[0] should be all 1s
|
||||
@@ -19,10 +19,10 @@
|
||||
module tb_fft_engine;
|
||||
|
||||
// ============================================================================
|
||||
// PARAMETERS — test with 32-pt for speed
|
||||
// PARAMETERS — test with 16-pt to match dual-FFT Doppler architecture
|
||||
// ============================================================================
|
||||
localparam N = 32;
|
||||
localparam LOG2N = 5;
|
||||
localparam N = 16;
|
||||
localparam LOG2N = 4;
|
||||
localparam DATA_W = 16;
|
||||
localparam INT_W = 32;
|
||||
localparam TW_W = 16;
|
||||
@@ -47,7 +47,7 @@ fft_engine #(
|
||||
.DATA_W(DATA_W),
|
||||
.INTERNAL_W(INT_W),
|
||||
.TWIDDLE_W(TW_W),
|
||||
.TWIDDLE_FILE("fft_twiddle_32.mem")
|
||||
.TWIDDLE_FILE("fft_twiddle_16.mem")
|
||||
) dut (
|
||||
.clk(clk),
|
||||
.reset_n(reset_n),
|
||||
|
||||
@@ -9,7 +9,7 @@
|
||||
*
|
||||
* range_bin_decimator (peak detection, 1024->64)
|
||||
* -> mti_canceller (2-pulse, mti_enable=1)
|
||||
* -> doppler_processor_optimized (Hamming + 32-pt FFT)
|
||||
* -> doppler_processor_optimized (Hamming + dual 16-pt FFT)
|
||||
* -> DC notch filter (width=2, inline logic)
|
||||
* -> cfar_ca (CA mode, guard=2, train=8, alpha=0x30)
|
||||
*
|
||||
@@ -41,7 +41,7 @@
|
||||
* -o tb/tb_fullchain_mti_cfar_realdata.vvp \
|
||||
* tb/tb_fullchain_mti_cfar_realdata.v \
|
||||
* range_bin_decimator.v mti_canceller.v doppler_processor.v \
|
||||
* xfft_32.v fft_engine.v cfar_ca.v
|
||||
* xfft_16.v fft_engine.v cfar_ca.v
|
||||
*
|
||||
* Run from: 9_Firmware/9_2_FPGA/
|
||||
* vvp tb/tb_fullchain_mti_cfar_realdata.vvp
|
||||
@@ -375,7 +375,7 @@ initial begin
|
||||
$display(" Full-Chain Real-Data Co-Simulation (MTI + CFAR)");
|
||||
$display(" range_bin_decimator (peak, 1024->64)");
|
||||
$display(" -> mti_canceller (2-pulse, enable=1)");
|
||||
$display(" -> doppler_processor_optimized (Hamming + 32-pt FFT)");
|
||||
$display(" -> doppler_processor_optimized (Hamming + dual 16-pt FFT)");
|
||||
$display(" -> DC notch filter (width=%0d)", DC_NOTCH_WIDTH);
|
||||
$display(" -> cfar_ca (CA, guard=2, train=8, alpha=0x30)");
|
||||
$display(" ADI CN0566 Phaser 10.525 GHz X-band FMCW");
|
||||
|
||||
@@ -7,7 +7,7 @@
|
||||
* (post-range-FFT, 32 chirps x 1024 bins) through:
|
||||
*
|
||||
* range_bin_decimator (peak detection, 1024→64)
|
||||
* → doppler_processor_optimized (Hamming + 32-pt FFT)
|
||||
* → doppler_processor_optimized (Hamming + dual 16-pt FFT)
|
||||
*
|
||||
* and compares the Doppler output bit-for-bit against the Python golden
|
||||
* reference that models the same chain (golden_reference.py).
|
||||
@@ -27,7 +27,7 @@
|
||||
* iverilog -Wall -DSIMULATION -g2012 \
|
||||
* -o tb/tb_fullchain_realdata.vvp \
|
||||
* tb/tb_fullchain_realdata.v \
|
||||
* range_bin_decimator.v doppler_processor.v xfft_32.v fft_engine.v
|
||||
* range_bin_decimator.v doppler_processor.v xfft_16.v fft_engine.v
|
||||
*
|
||||
* Run from: 9_Firmware/9_2_FPGA/
|
||||
* vvp tb/tb_fullchain_realdata.vvp
|
||||
@@ -243,7 +243,7 @@ initial begin
|
||||
$display("============================================================");
|
||||
$display(" Full-Chain Real-Data Co-Simulation");
|
||||
$display(" range_bin_decimator (peak, 1024->64)");
|
||||
$display(" -> doppler_processor_optimized (Hamming + 32-pt FFT)");
|
||||
$display(" -> doppler_processor_optimized (Hamming + dual 16-pt FFT)");
|
||||
$display(" ADI CN0566 Phaser 10.525 GHz X-band FMCW");
|
||||
$display(" Input: %0d chirps x %0d range FFT bins = %0d samples",
|
||||
CHIRPS, INPUT_BINS, TOTAL_INPUT_SAMPLES);
|
||||
|
||||
@@ -34,7 +34,7 @@
|
||||
* cdc_modules.v fir_lowpass.v ddc_input_interface.v \
|
||||
* chirp_memory_loader_param.v latency_buffer.v \
|
||||
* matched_filter_multi_segment.v matched_filter_processing_chain.v \
|
||||
* range_bin_decimator.v doppler_processor.v xfft_32.v fft_engine.v \
|
||||
* range_bin_decimator.v doppler_processor.v xfft_16.v fft_engine.v \
|
||||
* usb_data_interface.v edge_detector.v radar_mode_controller.v
|
||||
*
|
||||
* Run:
|
||||
|
||||
@@ -1,355 +0,0 @@
|
||||
`timescale 1ns / 1ps
|
||||
|
||||
/**
|
||||
* tb_xfft_32.v
|
||||
*
|
||||
* Testbench for xfft_32 AXI-Stream FFT wrapper.
|
||||
* Verifies the wrapper correctly interfaces with fft_engine via AXI-Stream.
|
||||
*
|
||||
* Test Groups:
|
||||
* 1. Impulse response (all output bins = input amplitude)
|
||||
* 2. DC input (bin 0 = A*N, rest ~= 0)
|
||||
* 3. Single tone detection
|
||||
* 4. AXI-Stream handshake correctness (tvalid, tlast, tready)
|
||||
* 5. Back-to-back transforms (no state leakage)
|
||||
*/
|
||||
|
||||
module tb_xfft_32;
|
||||
|
||||
// ============================================================================
|
||||
// PARAMETERS
|
||||
// ============================================================================
|
||||
localparam N = 32;
|
||||
localparam CLK_PERIOD = 10;
|
||||
|
||||
// ============================================================================
|
||||
// SIGNALS
|
||||
// ============================================================================
|
||||
reg aclk, aresetn;
|
||||
reg [7:0] cfg_tdata;
|
||||
reg cfg_tvalid;
|
||||
wire cfg_tready;
|
||||
reg [31:0] din_tdata;
|
||||
reg din_tvalid;
|
||||
reg din_tlast;
|
||||
wire [31:0] dout_tdata;
|
||||
wire dout_tvalid;
|
||||
wire dout_tlast;
|
||||
reg dout_tready;
|
||||
|
||||
// ============================================================================
|
||||
// DUT
|
||||
// ============================================================================
|
||||
xfft_32 dut (
|
||||
.aclk(aclk),
|
||||
.aresetn(aresetn),
|
||||
.s_axis_config_tdata(cfg_tdata),
|
||||
.s_axis_config_tvalid(cfg_tvalid),
|
||||
.s_axis_config_tready(cfg_tready),
|
||||
.s_axis_data_tdata(din_tdata),
|
||||
.s_axis_data_tvalid(din_tvalid),
|
||||
.s_axis_data_tlast(din_tlast),
|
||||
.m_axis_data_tdata(dout_tdata),
|
||||
.m_axis_data_tvalid(dout_tvalid),
|
||||
.m_axis_data_tlast(dout_tlast),
|
||||
.m_axis_data_tready(dout_tready)
|
||||
);
|
||||
|
||||
// ============================================================================
|
||||
// CLOCK
|
||||
// ============================================================================
|
||||
initial aclk = 0;
|
||||
always #(CLK_PERIOD/2) aclk = ~aclk;
|
||||
|
||||
// ============================================================================
|
||||
// PASS/FAIL TRACKING
|
||||
// ============================================================================
|
||||
integer pass_count, fail_count;
|
||||
|
||||
task check;
|
||||
input cond;
|
||||
input [512*8-1:0] label;
|
||||
begin
|
||||
if (cond) begin
|
||||
$display(" [PASS] %0s", label);
|
||||
pass_count = pass_count + 1;
|
||||
end else begin
|
||||
$display(" [FAIL] %0s", label);
|
||||
fail_count = fail_count + 1;
|
||||
end
|
||||
end
|
||||
endtask
|
||||
|
||||
// ============================================================================
|
||||
// OUTPUT CAPTURE
|
||||
// ============================================================================
|
||||
reg signed [15:0] out_re [0:N-1];
|
||||
reg signed [15:0] out_im [0:N-1];
|
||||
integer out_idx;
|
||||
reg got_tlast;
|
||||
integer tlast_count;
|
||||
|
||||
// ============================================================================
|
||||
// HELPER TASKS
|
||||
// ============================================================================
|
||||
|
||||
task do_reset;
|
||||
begin
|
||||
aresetn = 0;
|
||||
cfg_tdata = 0;
|
||||
cfg_tvalid = 0;
|
||||
din_tdata = 0;
|
||||
din_tvalid = 0;
|
||||
din_tlast = 0;
|
||||
dout_tready = 1;
|
||||
repeat(5) @(posedge aclk);
|
||||
aresetn = 1;
|
||||
repeat(2) @(posedge aclk);
|
||||
end
|
||||
endtask
|
||||
|
||||
// Send config (forward FFT: tdata[0]=1)
|
||||
// Waits for cfg_tready (wrapper in S_IDLE) before sending
|
||||
task send_config;
|
||||
input [7:0] cfg;
|
||||
integer wait_cnt;
|
||||
begin
|
||||
// Wait for wrapper to be ready (S_IDLE)
|
||||
wait_cnt = 0;
|
||||
while (!cfg_tready && wait_cnt < 5000) begin
|
||||
@(posedge aclk);
|
||||
wait_cnt = wait_cnt + 1;
|
||||
end
|
||||
cfg_tdata = cfg;
|
||||
cfg_tvalid = 1;
|
||||
@(posedge aclk);
|
||||
cfg_tvalid = 0;
|
||||
cfg_tdata = 0;
|
||||
end
|
||||
endtask
|
||||
|
||||
// Feed N samples: each sample is {im[15:0], re[15:0]}
|
||||
// in_re_arr and in_im_arr must be pre-loaded
|
||||
reg signed [15:0] feed_re [0:N-1];
|
||||
reg signed [15:0] feed_im [0:N-1];
|
||||
|
||||
task feed_data;
|
||||
integer i;
|
||||
begin
|
||||
for (i = 0; i < N; i = i + 1) begin
|
||||
din_tdata = {feed_im[i], feed_re[i]};
|
||||
din_tvalid = 1;
|
||||
din_tlast = (i == N - 1) ? 1 : 0;
|
||||
@(posedge aclk);
|
||||
end
|
||||
din_tvalid = 0;
|
||||
din_tlast = 0;
|
||||
din_tdata = 0;
|
||||
end
|
||||
endtask
|
||||
|
||||
// Capture N output samples
|
||||
task capture_output;
|
||||
integer timeout;
|
||||
begin
|
||||
out_idx = 0;
|
||||
got_tlast = 0;
|
||||
tlast_count = 0;
|
||||
timeout = 0;
|
||||
while (out_idx < N && timeout < 5000) begin
|
||||
@(posedge aclk);
|
||||
if (dout_tvalid && dout_tready) begin
|
||||
out_re[out_idx] = dout_tdata[15:0];
|
||||
out_im[out_idx] = dout_tdata[31:16];
|
||||
if (dout_tlast) begin
|
||||
got_tlast = 1;
|
||||
tlast_count = tlast_count + 1;
|
||||
end
|
||||
out_idx = out_idx + 1;
|
||||
end
|
||||
timeout = timeout + 1;
|
||||
end
|
||||
end
|
||||
endtask
|
||||
|
||||
// ============================================================================
|
||||
// VCD
|
||||
// ============================================================================
|
||||
initial begin
|
||||
$dumpfile("tb_xfft_32.vcd");
|
||||
$dumpvars(0, tb_xfft_32);
|
||||
end
|
||||
|
||||
// ============================================================================
|
||||
// MAIN TEST
|
||||
// ============================================================================
|
||||
integer i;
|
||||
reg signed [31:0] err;
|
||||
integer max_err;
|
||||
integer max_mag_bin;
|
||||
reg signed [31:0] max_mag, mag;
|
||||
real angle;
|
||||
|
||||
initial begin
|
||||
pass_count = 0;
|
||||
fail_count = 0;
|
||||
|
||||
$display("============================================================");
|
||||
$display(" xfft_32 AXI-Stream Wrapper Testbench");
|
||||
$display("============================================================");
|
||||
|
||||
do_reset;
|
||||
|
||||
// ================================================================
|
||||
// TEST 1: Impulse Response
|
||||
// ================================================================
|
||||
$display("");
|
||||
$display("--- Test 1: Impulse Response ---");
|
||||
|
||||
for (i = 0; i < N; i = i + 1) begin
|
||||
feed_re[i] = (i == 0) ? 16'sd1000 : 16'sd0;
|
||||
feed_im[i] = 16'sd0;
|
||||
end
|
||||
|
||||
send_config(8'h01); // Forward FFT
|
||||
feed_data;
|
||||
capture_output;
|
||||
|
||||
check(out_idx == N, "Received N output samples");
|
||||
check(got_tlast == 1, "Got tlast on output");
|
||||
|
||||
max_err = 0;
|
||||
for (i = 0; i < N; i = i + 1) begin
|
||||
err = out_re[i] - 1000;
|
||||
if (err < 0) err = -err;
|
||||
if (err > max_err) max_err = err;
|
||||
err = out_im[i];
|
||||
if (err < 0) err = -err;
|
||||
if (err > max_err) max_err = err;
|
||||
end
|
||||
$display(" Impulse max error: %0d", max_err);
|
||||
check(max_err < 10, "Impulse: all bins ~= 1000");
|
||||
|
||||
// ================================================================
|
||||
// TEST 2: DC Input
|
||||
// ================================================================
|
||||
$display("");
|
||||
$display("--- Test 2: DC Input ---");
|
||||
|
||||
for (i = 0; i < N; i = i + 1) begin
|
||||
feed_re[i] = 16'sd100;
|
||||
feed_im[i] = 16'sd0;
|
||||
end
|
||||
|
||||
send_config(8'h01);
|
||||
feed_data;
|
||||
capture_output;
|
||||
|
||||
$display(" DC bin[0] = %0d + j%0d (expect ~3200)", out_re[0], out_im[0]);
|
||||
check(out_re[0] >= 3100 && out_re[0] <= 3300, "DC: bin 0 ~= 3200 (5% tol)");
|
||||
|
||||
max_err = 0;
|
||||
for (i = 1; i < N; i = i + 1) begin
|
||||
err = out_re[i]; if (err < 0) err = -err;
|
||||
if (err > max_err) max_err = err;
|
||||
err = out_im[i]; if (err < 0) err = -err;
|
||||
if (err > max_err) max_err = err;
|
||||
end
|
||||
$display(" DC max non-DC: %0d", max_err);
|
||||
check(max_err < 25, "DC: non-DC bins ~= 0");
|
||||
|
||||
// ================================================================
|
||||
// TEST 3: Single Tone (bin 4)
|
||||
// ================================================================
|
||||
$display("");
|
||||
$display("--- Test 3: Single Tone (bin 4) ---");
|
||||
|
||||
for (i = 0; i < N; i = i + 1) begin
|
||||
angle = 6.28318530718 * 4.0 * i / 32.0;
|
||||
feed_re[i] = $rtoi($cos(angle) * 1000.0);
|
||||
feed_im[i] = 16'sd0;
|
||||
end
|
||||
|
||||
send_config(8'h01);
|
||||
feed_data;
|
||||
capture_output;
|
||||
|
||||
max_mag = 0;
|
||||
max_mag_bin = 0;
|
||||
for (i = 0; i < N; i = i + 1) begin
|
||||
mag = out_re[i] * out_re[i] + out_im[i] * out_im[i];
|
||||
if (mag > max_mag) begin
|
||||
max_mag = mag;
|
||||
max_mag_bin = i;
|
||||
end
|
||||
end
|
||||
$display(" Tone peak bin: %0d (expect 4 or 28)", max_mag_bin);
|
||||
check(max_mag_bin == 4 || max_mag_bin == 28, "Tone: peak at bin 4 or 28");
|
||||
|
||||
// ================================================================
|
||||
// TEST 4: Back-to-back transforms
|
||||
// ================================================================
|
||||
$display("");
|
||||
$display("--- Test 4: Back-to-Back Transforms ---");
|
||||
|
||||
// First: impulse
|
||||
for (i = 0; i < N; i = i + 1) begin
|
||||
feed_re[i] = (i == 0) ? 16'sd500 : 16'sd0;
|
||||
feed_im[i] = 16'sd0;
|
||||
end
|
||||
send_config(8'h01);
|
||||
feed_data;
|
||||
capture_output;
|
||||
check(out_idx == N, "Back-to-back 1st: got N outputs");
|
||||
|
||||
// Second: DC immediately after
|
||||
for (i = 0; i < N; i = i + 1) begin
|
||||
feed_re[i] = 16'sd50;
|
||||
feed_im[i] = 16'sd0;
|
||||
end
|
||||
send_config(8'h01);
|
||||
feed_data;
|
||||
capture_output;
|
||||
check(out_idx == N, "Back-to-back 2nd: got N outputs");
|
||||
$display(" 2nd transform bin[0] = %0d (expect ~1600)", out_re[0]);
|
||||
check(out_re[0] >= 1500 && out_re[0] <= 1700, "Back-to-back 2nd: bin 0 ~= 1600");
|
||||
|
||||
// ================================================================
|
||||
// TEST 5: Zero input
|
||||
// ================================================================
|
||||
$display("");
|
||||
$display("--- Test 5: Zero Input ---");
|
||||
|
||||
for (i = 0; i < N; i = i + 1) begin
|
||||
feed_re[i] = 16'sd0;
|
||||
feed_im[i] = 16'sd0;
|
||||
end
|
||||
send_config(8'h01);
|
||||
feed_data;
|
||||
capture_output;
|
||||
|
||||
max_err = 0;
|
||||
for (i = 0; i < N; i = i + 1) begin
|
||||
err = out_re[i]; if (err < 0) err = -err;
|
||||
if (err > max_err) max_err = err;
|
||||
err = out_im[i]; if (err < 0) err = -err;
|
||||
if (err > max_err) max_err = err;
|
||||
end
|
||||
check(max_err == 0, "Zero input: all outputs = 0");
|
||||
|
||||
// ================================================================
|
||||
// SUMMARY
|
||||
// ================================================================
|
||||
$display("");
|
||||
$display("============================================================");
|
||||
$display(" RESULTS: %0d/%0d passed", pass_count, pass_count + fail_count);
|
||||
if (fail_count == 0)
|
||||
$display(" ALL TESTS PASSED");
|
||||
else
|
||||
$display(" SOME TESTS FAILED");
|
||||
$display("============================================================");
|
||||
|
||||
$finish;
|
||||
end
|
||||
|
||||
endmodule
|
||||
@@ -5,7 +5,7 @@
|
||||
// Wraps the synthesizable fft_engine (radix-2 DIT) with the AXI-Stream port
|
||||
// interface expected by the doppler_processor dual-FFT architecture.
|
||||
//
|
||||
// Identical interface to xfft_32.v but with N=16.
|
||||
// Used by the doppler_processor dual-FFT architecture (2 x 16-pt sub-frames).
|
||||
//
|
||||
// Data format: {Q[15:0], I[15:0]} packed 32-bit.
|
||||
// Config tdata[0]: 1 = forward FFT, 0 = inverse FFT.
|
||||
|
||||
@@ -1,278 +0,0 @@
|
||||
`timescale 1ns / 1ps
|
||||
// ============================================================================
|
||||
// xfft_32.v — 32-point FFT with AXI-Stream interface
|
||||
// ============================================================================
|
||||
// Wraps the synthesizable fft_engine (radix-2 DIT) with the AXI-Stream port
|
||||
// interface expected by doppler_processor.v.
|
||||
//
|
||||
// Port interface matches the Xilinx LogiCORE IP Fast Fourier Transform
|
||||
// (AXI-Stream variant) as instantiated in doppler_processor.v.
|
||||
//
|
||||
// Data format: {Q[15:0], I[15:0]} packed 32-bit.
|
||||
// Config tdata[0]: 1 = forward FFT, 0 = inverse FFT.
|
||||
// ============================================================================
|
||||
|
||||
module xfft_32 (
|
||||
input wire aclk,
|
||||
input wire aresetn,
|
||||
|
||||
// Configuration channel (AXI-Stream slave)
|
||||
input wire [7:0] s_axis_config_tdata,
|
||||
input wire s_axis_config_tvalid,
|
||||
output wire s_axis_config_tready,
|
||||
|
||||
// Data input channel (AXI-Stream slave)
|
||||
input wire [31:0] s_axis_data_tdata,
|
||||
input wire s_axis_data_tvalid,
|
||||
input wire s_axis_data_tlast,
|
||||
|
||||
// Data output channel (AXI-Stream master)
|
||||
output wire [31:0] m_axis_data_tdata,
|
||||
output wire m_axis_data_tvalid,
|
||||
output wire m_axis_data_tlast,
|
||||
input wire m_axis_data_tready
|
||||
);
|
||||
|
||||
// ============================================================================
|
||||
// PARAMETERS
|
||||
// ============================================================================
|
||||
localparam N = 32;
|
||||
localparam LOG2N = 5;
|
||||
|
||||
// ============================================================================
|
||||
// INTERNAL SIGNALS
|
||||
// ============================================================================
|
||||
|
||||
// FSM states
|
||||
localparam [2:0] S_IDLE = 3'd0,
|
||||
S_CONFIG = 3'd1, // Latch config (fwd/inv)
|
||||
S_FEED = 3'd2, // Feed input to FFT engine
|
||||
S_WAIT = 3'd3, // Wait for FFT to complete
|
||||
S_OUTPUT = 3'd4; // Stream output
|
||||
|
||||
reg [2:0] state;
|
||||
|
||||
// Configuration
|
||||
reg inverse_reg;
|
||||
|
||||
// Input buffering
|
||||
reg signed [15:0] in_buf_re [0:N-1];
|
||||
reg signed [15:0] in_buf_im [0:N-1];
|
||||
reg [5:0] in_count; // 0..31 for loading, extra bit for overflow check
|
||||
|
||||
// Output buffering
|
||||
reg signed [15:0] out_buf_re [0:N-1];
|
||||
reg signed [15:0] out_buf_im [0:N-1];
|
||||
reg [5:0] out_count;
|
||||
reg [5:0] out_total; // counts how many outputs captured from engine
|
||||
|
||||
// FFT engine interface
|
||||
reg fft_start;
|
||||
reg fft_inverse;
|
||||
reg signed [15:0] fft_din_re, fft_din_im;
|
||||
reg fft_din_valid;
|
||||
wire signed [15:0] fft_dout_re, fft_dout_im;
|
||||
wire fft_dout_valid;
|
||||
wire fft_busy;
|
||||
wire fft_done;
|
||||
|
||||
// Feed counter for streaming into engine
|
||||
reg [5:0] feed_count;
|
||||
|
||||
// ============================================================================
|
||||
// FFT ENGINE INSTANCE
|
||||
// ============================================================================
|
||||
fft_engine #(
|
||||
.N(N),
|
||||
.LOG2N(LOG2N),
|
||||
.DATA_W(16),
|
||||
.INTERNAL_W(32),
|
||||
.TWIDDLE_W(16),
|
||||
.TWIDDLE_FILE("fft_twiddle_32.mem")
|
||||
) fft_core (
|
||||
.clk(aclk),
|
||||
.reset_n(aresetn),
|
||||
.start(fft_start),
|
||||
.inverse(fft_inverse),
|
||||
.din_re(fft_din_re),
|
||||
.din_im(fft_din_im),
|
||||
.din_valid(fft_din_valid),
|
||||
.dout_re(fft_dout_re),
|
||||
.dout_im(fft_dout_im),
|
||||
.dout_valid(fft_dout_valid),
|
||||
.busy(fft_busy),
|
||||
.done(fft_done)
|
||||
);
|
||||
|
||||
// ============================================================================
|
||||
// AXI-STREAM OUTPUTS
|
||||
// ============================================================================
|
||||
|
||||
// Config is accepted when idle
|
||||
assign s_axis_config_tready = (state == S_IDLE);
|
||||
|
||||
// Output data: {Q, I} packed
|
||||
assign m_axis_data_tdata = {out_buf_im[out_count[4:0]], out_buf_re[out_count[4:0]]};
|
||||
assign m_axis_data_tvalid = (state == S_OUTPUT) && (out_count < N);
|
||||
assign m_axis_data_tlast = (state == S_OUTPUT) && (out_count == N - 1);
|
||||
|
||||
// ============================================================================
|
||||
// BUFFER WRITE LOGIC — separate always block, NO async reset
|
||||
// Allows Vivado to infer distributed RAM instead of dissolving into registers.
|
||||
// ============================================================================
|
||||
// Input buffer write enable
|
||||
reg in_buf_we;
|
||||
reg [4:0] in_buf_waddr;
|
||||
reg signed [15:0] in_buf_wdata_re, in_buf_wdata_im;
|
||||
|
||||
// Output buffer write enable
|
||||
reg out_buf_we;
|
||||
reg [4:0] out_buf_waddr;
|
||||
reg signed [15:0] out_buf_wdata_re, out_buf_wdata_im;
|
||||
|
||||
always @(posedge aclk) begin
|
||||
if (in_buf_we) begin
|
||||
in_buf_re[in_buf_waddr] <= in_buf_wdata_re;
|
||||
in_buf_im[in_buf_waddr] <= in_buf_wdata_im;
|
||||
end
|
||||
if (out_buf_we) begin
|
||||
out_buf_re[out_buf_waddr] <= out_buf_wdata_re;
|
||||
out_buf_im[out_buf_waddr] <= out_buf_wdata_im;
|
||||
end
|
||||
end
|
||||
|
||||
// ============================================================================
|
||||
// MAIN FSM
|
||||
// ============================================================================
|
||||
always @(posedge aclk or negedge aresetn) begin
|
||||
if (!aresetn) begin
|
||||
state <= S_IDLE;
|
||||
inverse_reg <= 1'b0;
|
||||
in_count <= 0;
|
||||
out_count <= 0;
|
||||
out_total <= 0;
|
||||
feed_count <= 0;
|
||||
fft_start <= 1'b0;
|
||||
fft_inverse <= 1'b0;
|
||||
fft_din_re <= 0;
|
||||
fft_din_im <= 0;
|
||||
fft_din_valid <= 1'b0;
|
||||
in_buf_we <= 1'b0;
|
||||
in_buf_waddr <= 0;
|
||||
in_buf_wdata_re <= 0;
|
||||
in_buf_wdata_im <= 0;
|
||||
out_buf_we <= 1'b0;
|
||||
out_buf_waddr <= 0;
|
||||
out_buf_wdata_re <= 0;
|
||||
out_buf_wdata_im <= 0;
|
||||
end else begin
|
||||
// Defaults
|
||||
fft_start <= 1'b0;
|
||||
fft_din_valid <= 1'b0;
|
||||
in_buf_we <= 1'b0;
|
||||
out_buf_we <= 1'b0;
|
||||
|
||||
case (state)
|
||||
|
||||
// ================================================================
|
||||
S_IDLE: begin
|
||||
in_count <= 0;
|
||||
if (s_axis_config_tvalid) begin
|
||||
// Config tdata[0]: 1=forward, 0=inverse
|
||||
// fft_engine: inverse=0 means forward, inverse=1 means inverse
|
||||
inverse_reg <= ~s_axis_config_tdata[0];
|
||||
state <= S_FEED;
|
||||
in_count <= 0;
|
||||
feed_count <= 0;
|
||||
end
|
||||
end
|
||||
|
||||
// ================================================================
|
||||
// S_FEED: Buffer all N inputs first, then start engine.
|
||||
// ================================================================
|
||||
S_FEED: begin
|
||||
if (in_count < N) begin
|
||||
// Still accepting input data
|
||||
if (s_axis_data_tvalid) begin
|
||||
in_buf_we <= 1'b1;
|
||||
in_buf_waddr <= in_count[4:0];
|
||||
in_buf_wdata_re <= s_axis_data_tdata[15:0];
|
||||
in_buf_wdata_im <= s_axis_data_tdata[31:16];
|
||||
in_count <= in_count + 1;
|
||||
end
|
||||
end else if (feed_count == 0) begin
|
||||
// All N inputs buffered, start the FFT engine
|
||||
fft_start <= 1'b1;
|
||||
fft_inverse <= inverse_reg;
|
||||
feed_count <= 0;
|
||||
state <= S_WAIT;
|
||||
out_total <= 0;
|
||||
end
|
||||
end
|
||||
|
||||
// ================================================================
|
||||
// S_WAIT: Feed buffered data to engine, then wait for output
|
||||
// ================================================================
|
||||
S_WAIT: begin
|
||||
if (feed_count < N) begin
|
||||
fft_din_re <= in_buf_re[feed_count[4:0]];
|
||||
fft_din_im <= in_buf_im[feed_count[4:0]];
|
||||
fft_din_valid <= 1'b1;
|
||||
feed_count <= feed_count + 1;
|
||||
end
|
||||
|
||||
// Capture engine outputs
|
||||
if (fft_dout_valid && out_total < N) begin
|
||||
out_buf_we <= 1'b1;
|
||||
out_buf_waddr <= out_total[4:0];
|
||||
out_buf_wdata_re <= fft_dout_re;
|
||||
out_buf_wdata_im <= fft_dout_im;
|
||||
out_total <= out_total + 1;
|
||||
end
|
||||
|
||||
// Engine done
|
||||
if (fft_done) begin
|
||||
state <= S_OUTPUT;
|
||||
out_count <= 0;
|
||||
end
|
||||
end
|
||||
|
||||
// ================================================================
|
||||
// S_OUTPUT: Stream buffered results via AXI-Stream master
|
||||
// ================================================================
|
||||
S_OUTPUT: begin
|
||||
if (m_axis_data_tready || !m_axis_data_tvalid) begin
|
||||
if (out_count < N) begin
|
||||
// m_axis_data_tdata driven combinationally from out_buf
|
||||
if (m_axis_data_tready) begin
|
||||
out_count <= out_count + 1;
|
||||
end
|
||||
end
|
||||
if (out_count >= N - 1 && m_axis_data_tready) begin
|
||||
state <= S_IDLE;
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
default: state <= S_IDLE;
|
||||
|
||||
endcase
|
||||
end
|
||||
end
|
||||
|
||||
// ============================================================================
|
||||
// MEMORY INIT (simulation only)
|
||||
// ============================================================================
|
||||
`ifdef SIMULATION
|
||||
integer init_k;
|
||||
initial begin
|
||||
for (init_k = 0; init_k < N; init_k = init_k + 1) begin
|
||||
in_buf_re[init_k] = 0;
|
||||
in_buf_im[init_k] = 0;
|
||||
out_buf_re[init_k] = 0;
|
||||
out_buf_im[init_k] = 0;
|
||||
end
|
||||
end
|
||||
`endif
|
||||
|
||||
endmodule
|
||||
Reference in New Issue
Block a user