\thispagestyle{plain}
\noindent
\begin{tikzpicture}
\node[fill=fnDark,text=white,rounded corners=2pt,inner sep=6pt,
      minimum width=\textwidth,anchor=west]
  {\large\bfseries FPGA-Neural --- General description and features};
\end{tikzpicture}

\vspace{6pt}
\noindent
{\small FPGA-Neural is a \textbf{parametric hardware accelerator for feed-forward
neural networks} contained entirely within the FPGA. Computation (multiplication,
accumulation, bias, activation, saturation) takes place entirely on-chip in INT8/INT32
integer arithmetic; the host system only provides configuration, weights, input data
and control through a simple SPI interface, without ever being part of the
computational datapath. A single bitstream serves any topology up to the build
maximum.}

\vspace{8pt}
\begin{multicols}{2}
{\color{fnDark}\large\bfseries Features}\\[2pt]
{\footnotesize
\begin{itemize}[leftmargin=1.1em]
\item \textbf{INT8 $\times$ INT8 $\to$ INT16 $\to$ INT32} datapath, 32-bit accumulation
      with sign extension.
\item \textbf{Balanced binary adder tree} ($O(\log_2 \text{PARALLEL})$) instead of
      linear reduction.
\item Configurable parallel MAC: \code{PARALLEL} simultaneous hardware MACs per neuron,
      mapped onto \code{MULT18X18D} DSPs.
\item Fully \textbf{parametric} architecture: \code{N\_INPUTS}, \code{N\_NEURONS},
      \code{PARALLEL}, \code{DATA\_WIDTH}, \code{ACC\_WIDTH}, \code{N\_LAYERS}.
\item \textbf{Runtime network width}: per-layer \code{n\_inputs\_real}/\code{n\_neurons\_real},
      a single bitstream for every topology up to the maximum.
\item Configurable activations: \code{ACT\_RELU} (default) and \code{ACT\_NONE} (linear
      with bilateral saturation), with INT8 saturation.
\item \textbf{Two network types}: classic multi-layer dense (\code{layer\_sequencer},
      ping-pong buffers) and \textbf{arbitrary sparse graph} (\code{graph\_engine} +
      activation buffer in \code{DP16KD} block RAM), selectable at runtime.
\item \textbf{Dedicated memory} subsystem: byte$\leftrightarrow$word interface,
      asynchronous parallel PSRAM controller with \textbf{page mode} (70~ns random
      access, 20~ns page burst), 8~MB addressable (23~bit).
\item \textbf{SPI Mode 0} MSB-first host interface, \code{SET\_NET\_TYPE}+dispatch, \code{STATUS.done}
      sticky/clear-on-read, runtime \code{READ\_CONFIG}.
\item \textbf{Flash subsystem} for boot/persistence: FPGA-exclusive access to a
      \code{W25Q128JV} SPI NOR (16~MB) via a dedicated SPI master, a
      flash$\leftrightarrow$PSRAM copy engine, and a 16-slot catalog with CRC32,
      8 host opcodes.
\item Verified in \textbf{simulation} (Icarus Verilog) and \textbf{real synthesis}
      (Yosys + nextpnr-ecp5 + ecppack).
\end{itemize}}

\columnbreak

{\color{fnDark}\large\bfseries Applications}\\[2pt]
{\footnotesize
\begin{itemize}[leftmargin=1.1em]
\item Deterministic low-latency inference as a peripheral of a
      Linux SoC, Raspberry-Pi-like board, ESP32, microcontrollers.
\item Reusable hardware block integrable into heterogeneous projects
      (a platform, not a single network).
\item Edge AI on compact dense INT8-quantized networks.
\item Off-loading the neural workload from the host CPU to dedicated
      hardware with predictable throughput.
\end{itemize}}

\vspace{4pt}
{\color{fnDark}\large\bfseries Target \& toolchain}\\[2pt]
{\footnotesize
\begin{itemize}[leftmargin=1.1em]
\item FPGA: Lattice ECP5 \code{LFE5U-45F-8BG381C} ($-8$, CABGA381).
\item Synthesis: Yosys; place\&route: nextpnr-ecp5; bitstream: Project~Trellis
      (\code{ecppack}).
\item Simulation: Icarus Verilog (\code{-g2012}).
\item PSRAM: ISSI \code{IS66WVE4M16EBLL-70BLI} (64\,Mb, 4M$\times$16).
\end{itemize}}
\end{multicols}

\vspace{2pt}
% --- key parameter table ---
\noindent
{\small\color{fnDark}\bfseries Key parameters (characterized baseline configuration)}
\vspace{2pt}

\noindent
\begin{tabularx}{\textwidth}{L{3.2cm}L{3.6cm}Y}
\toprule
\rowh \thd{Quantity} & \thd{Value} & \thd{Notes} \\
\midrule
Data precision & INT8 (signed) & \code{DATA\_WIDTH}=8 \\
\rowa Accumulator & INT32 (signed) & \code{ACC\_WIDTH}=32 \\
Inputs / neurons & 256 / 4 & datapath benchmark baseline \\
\rowa Simultaneous MACs & $2\ldots64$ & $=$\code{PARALLEL}$\times$\code{N\_NEURONS} \\
Activations & ReLU, linear & \code{ACT\_RELU} / \code{ACT\_NONE} \\
\rowa Fmax (P=2, datapath) & 87.88~MHz & isolated datapath benchmark \\
Fmax (P=2, integrated system) & 67.91~MHz & full system incl. flash subsystem, real place\&route \\
MAC throughput (P=16) & $\approx$3.34~G\,MAC/s & theoretical, datapath only \\
\rowa Working memory & 8~MB PSRAM & 16-bit parallel bus, 70~ns / 20~ns page mode \\
Address space & 23~bit (byte) & \code{ADDR\_WIDTH}=23 \\
\bottomrule
\end{tabularx}

\vspace{8pt}
\noindent
{\small\color{fnDark}\bfseries System block diagram}
\begin{center}
\begin{tikzpicture}[node distance=6mm and 10mm,font=\footnotesize]
  \node[fnblockD,minimum width=26mm,minimum height=13mm] (host){HOST\\{\scriptsize configures / trains / controls}};
  \node[fnblockT,right=16mm of host,minimum width=52mm,minimum height=22mm] (eng){};
  \node[anchor=north,font=\footnotesize\bfseries,text=fnDark] at (eng.north){FPGA -- Neural Network Engine};
  \node[fnreg,fill=white] (spi) at ([yshift=-2mm]eng.center){\code{spi\_slave} + \code{spi\_engine}};
  \node[fnreg,fill=white,below=2.5mm of spi] (arb){\code{mem\_arbiter} + \code{layer\_sequencer}};
  \node[fnreg,fill=white,above=2.5mm of spi] (core){\code{neuron\_memory} $\to$ \code{neuron\_parallel} $\to$ \code{mac8}};
  \node[fnblock,right=16mm of eng,minimum width=24mm,minimum height=13mm] (ram){PSRAM 8\,MB\\{\scriptsize \code{psram\_controller}}};
  \draw[fnbus] (host) -- node[fnlbl,above]{SPI} (eng.west|-host);
  \draw[fnbus] (eng.east|-ram) -- node[fnlbl,above]{16-bit async} (ram);
\end{tikzpicture}
\end{center}
\begin{center}\footnotesize\itshape\color{fnGrey}
The neural datapath is entirely inside the FPGA; the host does not take part in the
individual MAC operations.\end{center}