Ang On-Chip SRAM: Isang Humihingang Ilaw na Nakaimbak sa Sariling Memorya ng Iyong Chip

// SPDX-License-Identifier: Apache-2.0
// Youblob silicon rung 5: the PWM dimmer plays a brightness pattern stored in the on-chip SRAM macro.
// Port list unchanged from wafer-space/gf180mcu-project-template src/chip_core.sv.

`default_nettype none

module chip_core #(
    parameter NUM_INPUT_PADS,
    parameter NUM_BIDIR_PADS,
    parameter NUM_ANALOG_PADS,
    parameter HOLD_LOG2 = 9        // each table entry lasts 2**HOLD_LOG2 PWM periods
    )(
    `ifdef USE_POWER_PINS
    inout  wire VDD,
    inout  wire VSS,
    `endif

    input  wire clk,       // clock
    input  wire rst_n,     // reset (active low)

    input  wire [NUM_INPUT_PADS-1:0] input_in,   // Input value
    output wire [NUM_INPUT_PADS-1:0] input_pu,   // Pull-up
    output wire [NUM_INPUT_PADS-1:0] input_pd,   // Pull-down

    input  wire [NUM_BIDIR_PADS-1:0] bidir_in,   // Input value
    output wire [NUM_BIDIR_PADS-1:0] bidir_out,  // Output value
    output wire [NUM_BIDIR_PADS-1:0] bidir_oe,   // Output enable
    output wire [NUM_BIDIR_PADS-1:0] bidir_cs,   // Input type (0=CMOS Buffer, 1=Schmitt Trigger)
    output wire [NUM_BIDIR_PADS-1:0] bidir_sl,   // Slew rate (0=fast, 1=slow)
    output wire [NUM_BIDIR_PADS-1:0] bidir_ie,   // Input enable
    output wire [NUM_BIDIR_PADS-1:0] bidir_pu,   // Pull-up
    output wire [NUM_BIDIR_PADS-1:0] bidir_pd,   // Pull-down

    inout  wire [NUM_ANALOG_PADS-1:0] analog  // Analog
);

    // Input pad 0: enable.  Input pad 1: LOAD mode.  Input pad 2: write strobe.
    // Bidir pads 0..7: the byte to store while loading.  Bidir pad 8: the PWM output.
    localparam DUTY_W = 8;
    localparam PWM_PAD = 8;

    assign input_pu = '0;
    assign input_pd = '0;
    assign bidir_oe = {{(NUM_BIDIR_PADS-DUTY_W){1'b1}}, {DUTY_W{1'b0}}};
    assign bidir_ie = ~bidir_oe;
    assign bidir_cs = {{(NUM_BIDIR_PADS-DUTY_W){1'b0}}, {DUTY_W{1'b1}}};
    assign bidir_sl = '0;
    assign bidir_pu = '0;
    assign bidir_pd = '0;

    wire enable = input_in[0];
    wire [DUTY_W-1:0] data_in = bidir_in[DUTY_W-1:0];

    // The mode and strobe pads change whenever the outside world likes, not in step with clk:
    // two flip-flops in a row (a synchroniser) before anything uses them.
    logic [1:0] load_s;
    logic [2:0] strobe_s;
    always_ff @(posedge clk) begin
        load_s   <= {load_s[0], input_in[1]};
        strobe_s <= {strobe_s[1:0], input_in[2]};
    end
    logic load_was;
    wire load        = load_s[1];
    wire load_start  = load & ~load_was;
    wire strobe_rise = strobe_s[1] & ~strobe_s[2];
    always_ff @(posedge clk) load_was <= load;

    // The SRAM wants its chip enable (CEN, active LOW) to go 1 -> 0 before it works:
    // hold it at 1 through reset, then 0.
    logic cen;
    always_ff @(posedge clk) cen <= !rst_n;

    // PWM counter and the "hold" counter that decides when to step to the next table entry.
    logic [DUTY_W-1:0] count;
    logic [HOLD_LOG2:0] hold;                   // one bit wider so HOLD_LOG2 = 0 still works
    wire period_end = (count == '1);
    localparam logic [HOLD_LOG2:0] HOLD_MASK = (1 << HOLD_LOG2) - 1;   // 0 when HOLD_LOG2 = 0
    wire step = period_end && ((hold & HOLD_MASK) == HOLD_MASK);

    logic [DUTY_W-1:0] addr;
    logic [DUTY_W-1:0] duty;
    wire  [DUTY_W-1:0] q;                       // SRAM read data: mem[addr], one clock after addr

    always_ff @(posedge clk) begin
        if (!rst_n) begin
            count <= '0;  hold <= '0;  addr <= '0;  duty <= '0;
        end else if (load) begin
            count <= '0;  hold <= '0;  duty <= '0;
            if (load_start)       addr <= '0;       // every load starts at entry 0
            else if (strobe_rise) addr <= addr + 1'b1;
        end else if (enable) begin
            count <= count + 1'b1;
            if (period_end) hold <= hold + 1'b1;
            if (step) begin
                duty <= q;                          // the entry that was being read
                addr <= addr + 1'b1;                // and move on to the next
            end
        end
    end

    `gf180mcu_xxx_ip_sram__sram512x8m8wm1 sram_0 (
        `ifdef USE_POWER_PINS
        .VDD  (VDD),
        .VSS  (VSS),
        `endif
        .CLK  (clk),
        .CEN  (cen),                                   // active low: 0 = on
        .GWEN (~(load && strobe_rise)),                // active low: 0 = write this clock
        .WEN  (8'b0),                                  // active low, per bit: write all eight
        .A    ({1'b0, addr}),                          // 256 of the 512 bytes
        .D    (data_in),
        .Q    (q)
    );

    logic pwm;
    always_ff @(posedge clk) begin
        if (!rst_n) pwm <= 1'b0;
        else        pwm <= enable && !load && (count < duty);
    end

    logic [NUM_BIDIR_PADS-1:0] out;
    always_comb begin
        out = '0;
        out[PWM_PAD] = pwm;
    end
    assign bidir_out = out;

    // Inputs this design does not read (keeps lint quiet, as the template does with _unused).
    logic _unused;
    assign _unused = &{1'b0, input_in[NUM_INPUT_PADS-1:3], bidir_in[NUM_BIDIR_PADS-1:DUTY_W], hold[HOLD_LOG2]};

endmodule

`default_nettype wire

# SPDX-License-Identifier: Apache-2.0
# cocotb testbench for the SRAM pattern player, with the PDK's own SRAM simulation model
# (gf180mcu_fd_ip_sram__sram512x8m8wm1, gf180mcuD, the commit the template pins).
import math
import os
from pathlib import Path

import cocotb
from cocotb.clock import Clock
from cocotb.triggers import ClockCycles, FallingEdge, RisingEdge
from cocotb_tools.runner import get_runner

PWM_PAD = 8
EN, LOAD, STROBE = 1, 2, 4                      # input pad bits
SRAM = Path(os.getenv("PDK_ROOT", "pdk")) / "gf180mcuD" / "libs.ref" / "gf180mcu_fd_ip_sram" / "verilog"


def breathing_table(n=256, gamma=2.2):
    """One slow breath: a raised sine, gamma-corrected so equal steps LOOK equal to the eye."""
    return [round(255 * ((1 - math.cos(2 * math.pi * i / n)) / 2) ** gamma) for i in range(n)]


async def start(dut):
    cocotb.start_soon(Clock(dut.clk, 40, unit="ns").start())   # 25 MHz, the template's CLOCK_PERIOD
    dut.input_in.value = 0
    dut.bidir_in.value = 0
    dut.rst_n.value = 0
    await ClockCycles(dut.clk, 5)
    dut.rst_n.value = 1
    await ClockCycles(dut.clk, 2)


async def load(dut, table):
    """What a microcontroller on the breakout does: LOAD high, then per byte set the data pads,
    raise the strobe, wait, lower it. The chip synchronises the strobe, so hold each for 4 clocks."""
    dut.input_in.value = LOAD
    await ClockCycles(dut.clk, 4)
    for b in table:
        dut.bidir_in.value = b
        await ClockCycles(dut.clk, 1)
        dut.input_in.value = LOAD | STROBE
        await ClockCycles(dut.clk, 4)
        dut.input_in.value = LOAD
        await ClockCycles(dut.clk, 4)
    dut.input_in.value = 0
    await ClockCycles(dut.clk, 4)


async def highs_per_period(dut, periods):
    """High clocks in each PWM period, counted from the core's own count = 0."""
    while int(dut.count.value) != 0:
        await RisingEdge(dut.clk)
    out = []
    for _ in range(periods):
        n = 0
        for _ in range(256):
            await FallingEdge(dut.clk)
            n += int(dut.bidir_out.value[PWM_PAD])
        out.append(n)
    return out


@cocotb.test()
async def test_plays_the_table(dut):
    """Load a 256-entry breathing table, play it: each period's high time is the next entry."""
    table = breathing_table()
    await start(dut)
    await load(dut, table)
    dut.input_in.value = EN
    got = await highs_per_period(dut, 600)
    # the output starts part-way through the table; find where, then demand every period match
    fits = [off for off in range(256) if all(got[j] == table[(j + off) % 256] for j in range(2, 600))]
    dut._log.info(f"first periods {got[:8]}, table aligns at offset {fits}")
    Path(__file__).resolve().parent.joinpath("pattern_trace.csv").write_text("\n".join(map(str, got)))
    assert len(fits) == 1, f"the output does not follow the table (offsets that fit: {fits})"


@cocotb.test()
async def test_reload(dut):
    """Loading again replaces the pattern: a flat 64 gives 64 high clocks every period."""
    await start(dut)
    await load(dut, breathing_table())
    await load(dut, [64] * 256)
    dut.input_in.value = EN
    got = await highs_per_period(dut, 40)
    assert all(g == 64 for g in got[2:]), got


def test_runner():
    here = Path(__file__).resolve().parent
    defines = {"gf180mcu_xxx_ip_sram__sram512x8m8wm1": "gf180mcu_fd_ip_sram__sram512x8m8wm1"}
    runner = get_runner("icarus")
    runner.build(
        sources=[SRAM / "gf180mcu_fd_ip_sram__sram512x8m8wm1.v", here / "chip_core.sv"],
        hdl_toplevel="chip_core",
        parameters={"NUM_INPUT_PADS": 4, "NUM_BIDIR_PADS": 38, "NUM_ANALOG_PADS": 4, "HOLD_LOG2": 0},
        defines=defines,
        build_args=["-g2012"],
        timescale=("1ns", "1ps"),
        always=True,
    )
    runner.test(hdl_toplevel="chip_core", test_module="test_pattern")


if __name__ == "__main__":
    test_runner()

// SPDX-License-Identifier: Apache-2.0
// Load a breathing pattern into your chip's SRAM through its pads, then let the chip play it.
// Youblob silicon rung 5. The chip does the playing; this board only writes 256 bytes once.
//
// Wiring (ESP32 GPIO -> chip pad on your breakout):
//   D0..D7  GPIO 13,14,18,19,21,22,23,25 -> bidir[0..7]
//   LOAD    GPIO 26 -> input[1]
//   STROBE  GPIO 27 -> input[2]
//   EN      GPIO 32 -> input[0]
//   and a common ground. The chip's bidir[8] drives an LED through 330 ohm to ground.
// The ESP32 is a 3.3 V part: run the chip's I/O at 3.3 V, or put a level shifter between them.

#include <math.h>

const int DATA_PINS[8] = {13, 14, 18, 19, 21, 22, 23, 25};
const int PIN_LOAD = 26, PIN_STROBE = 27, PIN_EN = 32;

// The chip passes LOAD and STROBE through a two-flip-flop synchroniser and looks for the strobe's
// rising edge, so every level has to last a few of ITS clocks. 1 us is 25 clocks at 25 MHz.
const unsigned HOLD_US = 1;

uint8_t table[256];

void makeBreathingTable() {
  // a raised sine, gamma-corrected (2.2) so the brightness steps look even to the eye
  for (int i = 0; i < 256; i++) {
    float s = (1.0f - cosf(2.0f * PI * i / 256.0f)) / 2.0f;
    table[i] = (uint8_t)lroundf(255.0f * powf(s, 2.2f));
  }
}

void putByte(uint8_t b) {
  for (int bit = 0; bit < 8; bit++) digitalWrite(DATA_PINS[bit], (b >> bit) & 1);
  delayMicroseconds(HOLD_US);            // data settles before the strobe
  digitalWrite(PIN_STROBE, HIGH);        // the chip writes on the strobe's rising edge...
  delayMicroseconds(HOLD_US);            // ...a few of its clocks later, so hold the data
  digitalWrite(PIN_STROBE, LOW);
  delayMicroseconds(HOLD_US);
}

void loadTable() {
  digitalWrite(PIN_EN, LOW);
  digitalWrite(PIN_LOAD, HIGH);          // entering LOAD resets the chip's address to 0
  delayMicroseconds(HOLD_US);
  for (int i = 0; i < 256; i++) putByte(table[i]);
  digitalWrite(PIN_LOAD, LOW);
  delayMicroseconds(HOLD_US);
}

void setup() {
  Serial.begin(115200);
  for (int bit = 0; bit < 8; bit++) pinMode(DATA_PINS[bit], OUTPUT);
  pinMode(PIN_LOAD, OUTPUT);
  pinMode(PIN_STROBE, OUTPUT);
  pinMode(PIN_EN, OUTPUT);
  digitalWrite(PIN_STROBE, LOW);

  makeBreathingTable();
  loadTable();
  digitalWrite(PIN_EN, HIGH);            // play
  Serial.println("pattern loaded; the chip is playing it on its own");
  Serial.printf("table[0]=%u table[64]=%u table[128]=%u\n", table[0], table[64], table[128]);
}

void loop() {
  // Nothing to do: the pattern lives in the chip's SRAM now.
  // Send 'r' over serial to load it again (the SRAM loses it when the chip loses power).
  if (Serial.available() && Serial.read() == 'r') {
    loadTable();
    digitalWrite(PIN_EN, HIGH);
    Serial.println("reloaded");
  }
}