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
103 lines
4.1 KiB
Python
103 lines
4.1 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Generates synth/ecp5/spi_neuron_top.lpf (LOCATE/IOBUF constraints) for
|
|
spi_neuron_top's SPI + PSRAM ports on the real LFE5U-45F-8BG381C part,
|
|
using Project Trellis's own device database as the source of ball/bank/
|
|
dual-function data (the same data nextpnr-ecp5 itself uses) -- not
|
|
invented numbers.
|
|
|
|
Requires prjtrellis installed (Homebrew: `brew install prjtrellis`) and
|
|
its iodb.json for LFE5U-45F. See docs/FPGA-Neural-Hardware-Design.md §7
|
|
for the full placement rationale (bank/die-edge geometry, why banks 2+3
|
|
hold the PSRAM bus and bank 7 holds SPI/clock/reset).
|
|
|
|
Re-run this whenever the port list of rtl/spi_neuron_top.v's top-level
|
|
SPI/PSRAM interface changes (ADDR_WIDTH, MEM_DATA_WIDTH, etc.) -- it does
|
|
NOT try to read the RTL; the port list/widths are hardcoded below and
|
|
must be kept in sync by hand.
|
|
"""
|
|
|
|
import json
|
|
import re
|
|
import glob
|
|
import sys
|
|
|
|
CLK_BALL = "H5" # GR_PCLK7_0, bank 7 -- dedicated global clock pad
|
|
ADDR_BITS = 23 # ADDR_WIDTH (byte address); only [21:0] carry real address, see §3
|
|
DATA_BITS = 16 # MEM_DATA_WIDTH
|
|
|
|
def find_iodb():
|
|
candidates = glob.glob(
|
|
"/opt/homebrew/Cellar/prjtrellis/*/share/trellis/database/ECP5/LFE5U-45F/iodb.json"
|
|
) + glob.glob(
|
|
"/usr/share/trellis/database/ECP5/LFE5U-45F/iodb.json"
|
|
)
|
|
if not candidates:
|
|
sys.exit("prjtrellis iodb.json not found -- install prjtrellis (brew install prjtrellis)")
|
|
return candidates[0]
|
|
|
|
|
|
def load_balls(iodb_path, package="CABGA381"):
|
|
d = json.load(open(iodb_path))
|
|
pkg = d["packages"][package]
|
|
meta_idx = {}
|
|
for m in d["pio_metadata"]:
|
|
meta_idx.setdefault((m["col"], m["row"], m["pio"]), []).append(m)
|
|
out = {}
|
|
for ball, info in pkg.items():
|
|
key = (info["col"], info["row"], info["pio"])
|
|
metas = meta_idx.get(key, [])
|
|
bank = metas[0]["bank"] if metas else None
|
|
funcs = sorted(set(m.get("function", "") for m in metas if m.get("function")))
|
|
out[ball] = dict(col=info["col"], row=info["row"], bank=bank, funcs=funcs)
|
|
return out
|
|
|
|
|
|
def bank_balls(rows, bank, exclude=()):
|
|
items = [(b, v) for b, v in rows.items() if v["bank"] == bank and b not in exclude]
|
|
plain = sorted((x for x in items if not x[1]["funcs"]), key=lambda x: (x[1]["row"], x[1]["col"], x[0]))
|
|
special = sorted((x for x in items if x[1]["funcs"]), key=lambda x: (x[1]["row"], x[1]["col"], x[0]))
|
|
return plain + special
|
|
|
|
|
|
def assign(rows):
|
|
psram_pool = bank_balls(rows, 2) + bank_balls(rows, 3)
|
|
ctrl_pool = bank_balls(rows, 7, exclude={CLK_BALL})
|
|
|
|
a = {}
|
|
for i, (ball, _) in enumerate(psram_pool[0:ADDR_BITS - 1]):
|
|
a[f"psram_a[{i}]"] = ball
|
|
for i, (ball, _) in enumerate(psram_pool[ADDR_BITS - 1:ADDR_BITS - 1 + DATA_BITS]):
|
|
a[f"psram_dq[{i}]"] = ball
|
|
ctrl_names = ["psram_ce_n", "psram_oe_n", "psram_we_n", "psram_lb_n", "psram_ub_n", "psram_zz_n"]
|
|
for name, (ball, _) in zip(ctrl_names, psram_pool[ADDR_BITS - 1 + DATA_BITS:ADDR_BITS - 1 + DATA_BITS + 6]):
|
|
a[name] = ball
|
|
a[f"psram_a[{ADDR_BITS - 1}]"] = psram_pool[ADDR_BITS - 1 + DATA_BITS + 6][0] # always-0 spare bit
|
|
|
|
# Application SPI + reset + host attention pins (irq_n/data_ready_n,
|
|
# added 2026-09-03), all in bank 7 alongside clk -- kept away from
|
|
# the PSRAM bus (banks 2+3) per the same "opposite edges" rationale
|
|
# as the SPI signals.
|
|
spi_names = ["sclk", "mosi", "miso", "cs_n", "rst", "irq_n", "data_ready_n"]
|
|
for name, (ball, _) in zip(spi_names, ctrl_pool[0:7]):
|
|
a[name] = ball
|
|
a["clk"] = CLK_BALL
|
|
return a
|
|
|
|
|
|
def write_lpf(assignment, path):
|
|
lines = ["BLOCK ASYNCPATHS;", "BLOCK RESETPATHS;", ""]
|
|
for sig, ball in sorted(assignment.items()):
|
|
lines.append(f'LOCATE COMP "{sig}" SITE "{ball}";')
|
|
lines.append(f'IOBUF PORT "{sig}" IO_TYPE=LVCMOS33;')
|
|
lines.append("")
|
|
open(path, "w").write("\n".join(lines))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
out_path = sys.argv[1] if len(sys.argv) > 1 else "synth/ecp5/spi_neuron_top.lpf"
|
|
rows = load_balls(find_iodb())
|
|
assignment = assign(rows)
|
|
write_lpf(assignment, out_path)
|
|
print(f"wrote {len(assignment)} signal constraints to {out_path}")
|