Files
FPGA-Neural/tools/netasm/cli.py
T
micheleandClaude Sonnet 5 55c827bedf feat: PSRAM page-mode reads + graph engine (Type #2) + real pinout/IRQ pins
PSRAM page-mode read burst support in psram_controller.v: enables the
ISSI IS66WVE4M16EBLL-70BLI's page mode via its configuration-register
software-access sequence at boot (disabled by default on the real
chip), then keeps CE#/OE# asserted after a read so a same-page
continuation only pays tAPA (20ns) instead of a full tAA (70ns)
random access, with automatic tCEM-safe session closing. Only a WRITE
closes the page -- byte-enable changes do not, since
int8_memory_access.v alternates them on nearly every access and an
early implementation attempt that treated them as a close condition
measured a real regression (53.25->61.25 cycles/edge) before being
corrected (53.25->37.53 cycles/edge, +42% gather bandwidth).
sim/psram_model.v gained independent tAPA/tAA and tCEM enforcement
(with a real Verilog same-timestep event-ordering race found and
fixed via a #0 sync) so the regression proves real timing compliance,
not just data correctness. New sim/psram_page_mode_tb.v; full 26-file
regression suite re-run clean. Real nextpnr-ecp5 Fmax re-measured on
the full spi_neuron_top system: 75.73MHz (P2, up from 55.59MHz) and
65.13MHz (P8) -- still under the 80MHz target but not regressed, with
the critical path confirmed (not assumed) to remain entirely inside
neuron_parallel's accumulate chain, never psram_controller.

Also includes this session's other already-validated work: the graph
engine (Type #2 sparse-graph network: act_buffer, graph_engine,
netasm host assembler), real CABGA381 pinout (.lpf, place&route
verified) and physical IRQ_N/DATA_READY_N pins, and Phase 7 timing
closure logs -- all previously uncommitted, documented in WORKLOG.md.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LH3jPeJ3eFMfF2v8SQhpkk
2026-09-03 17:12:05 +02:00

121 lines
4.3 KiB
Python

#!/usr/bin/env python3
"""
netasm CLI: compiles a .netasm source file (see parser.py's docstring
for the grammar) into an SPI load sequence + human-readable debug
dump. Host-side tool only -- see rtl/graph_engine.v / spi_engine.v
for the hardware side of this protocol.
Usage:
python3 -m tools.netasm.cli input.netasm -o out_prefix \\
[--parallel 8] [--max-conn 32] [--n-total 4096]
Produces:
out_prefix.frames.bin -- length-prefixed SPI transaction bytes
out_prefix.debug.txt -- human-readable id/address/byte dump
"""
from __future__ import annotations
import argparse
import sys
try:
from . import frames as F
from .assembler import (
NetasmError,
assemble_dense,
assemble_graph,
dump_dense_debug,
dump_graph_debug,
)
from .parser import DenseNet, GraphNet, NetasmSyntaxError, parse
except ImportError:
# Allow running this file directly (`python3 tools/netasm/cli.py`)
# without the package being importable as `tools.netasm` -- e.g.
# an unrelated `tools` namespace package earlier on PYTHONPATH
# shadowing this repo's tools/ directory.
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import frames as F
from assembler import (
NetasmError,
assemble_dense,
assemble_graph,
dump_dense_debug,
dump_graph_debug,
)
from parser import DenseNet, GraphNet, NetasmSyntaxError, parse
def main(argv=None) -> int:
ap = argparse.ArgumentParser(description=__doc__)
ap.add_argument("source", help="path to a .netasm source file")
ap.add_argument("-o", "--output", required=True, help="output file prefix")
ap.add_argument("--parallel", type=int, default=8, help="hardware PARALLEL (default 8)")
ap.add_argument("--max-conn", type=int, default=32, help="graph_engine's MAX_CONN (default 32)")
ap.add_argument("--n-total", type=int, default=4096, help="graph_engine's N_TOTAL (default 4096)")
ap.add_argument("--table-base", type=lambda s: int(s, 0), default=0x000000)
ap.add_argument("--edges-base", type=lambda s: int(s, 0), default=0x010000)
ap.add_argument("--x-base", type=lambda s: int(s, 0), default=0x000000)
ap.add_argument("--out-base", type=lambda s: int(s, 0), default=0x020000,
help="graph out_base / dense buf_a_base")
ap.add_argument("--buf-b-base", type=lambda s: int(s, 0), default=0x021000,
help="dense buf_b_base only")
ap.add_argument("--weights-base", type=lambda s: int(s, 0), default=0x010000,
help="dense weight/bias region base")
args = ap.parse_args(argv)
with open(args.source, "r") as f:
text = f.read()
try:
net = parse(text)
except NetasmSyntaxError as e:
print(f"{args.source}: syntax error: {e}", file=sys.stderr)
return 1
try:
if isinstance(net, GraphNet):
layout = assemble_graph(
net,
parallel=args.parallel,
max_conn=args.max_conn,
n_total=args.n_total,
table_base=args.table_base,
edges_base=args.edges_base,
x_base=args.x_base,
out_base=args.out_base,
)
debug = dump_graph_debug(layout)
frames = layout.frames
else:
assert isinstance(net, DenseNet)
layout = assemble_dense(
net,
parallel=args.parallel,
table_base=args.table_base,
weights_base=args.weights_base,
x_base=args.x_base,
buf_a_base=args.out_base,
buf_b_base=args.buf_b_base,
)
debug = dump_dense_debug(layout)
frames = layout.frames
except NetasmError as e:
print(f"{args.source}: assembly error: {e}", file=sys.stderr)
return 1
F.dump_frames(frames, args.output + ".frames.bin")
with open(args.output + ".debug.txt", "w") as f:
f.write(debug + "\n")
print(f"wrote {args.output}.frames.bin ({sum(len(fr.data) for fr in frames)} payload bytes, "
f"{len(frames)} SPI transactions)")
print(f"wrote {args.output}.debug.txt")
return 0
if __name__ == "__main__":
sys.exit(main())