Begins the V2 Neural Multiprocessor / Dataflow architecture per docs/v2-description.md, per explicit user request to freeze V1 and start V2 development, copying from V1 what's needed. Scaffold: - hardware/v1/: byte-exact, read-only copy of the current V1 codebase (rtl, testbenches, tools, constraints, a representative subset of synthesis results, and reference docs) -- verified identical via diff/cmp against the live top-level tree before being made filesystem-read-only. The live top-level tree is untouched and remains the project's "production" V1 (see hardware/v1/README.md and hardware/v2/logs/decisions.log DEC-0001 for why copy-not-move). - hardware/v2/: mandatory structure (rtl/sim/constraints/synthesis/ reports/scripts/logs/docs) plus the full logging system required by the spec (development/architecture/simulation/synthesis/timing/ benchmark/decisions/experiments/errors.log). M1 -- Neural Processor (hardware/v2/rtl/neural_processor.v): - 8-stage pipelined perceptron unit (P_IN=8): input align, 8 multipliers, 3-level adder tree, accumulator, bias+activation, INT8 saturation. Genuine 1-tile/cycle throughput, not just a wider combinational datapath. - 7-state FSM (NP_IDLE..NP_ERROR per docs/v2-description.md §6, with 4 baseline states merged into NP_WAIT_OPERANDS -- see decisions.log DEC-0002); valid/ready/data/last stream interfaces per §7. - Bit-exact vs the frozen hardware/v1/rtl/neuron_parallel.v + mac8.v + mac_unit.v: 7/7 tests pass (hardware/v2/sim/tb_neural_processor.v), covering regular/mixed-sign/extreme-INT8 vectors, both activations, a zero-idle-gap back-to-back-tiles throughput check, and an 8-tile job -- verified with Verilator (see below for why). - Real synthesis + place&route (Yosys + nextpnr-ecp5): 0 CHECK problems, Fmax 183.12 MHz at ACC_WIDTH=32 (PASS at 80MHz, ~3x V1's isolated PARALLEL=8 Fmax of 61.71 MHz) and 176.21 MHz at ACC_WIDTH=24 (a user-requested comparison experiment, also bit-exact-verified; see experiments.log EXP-0001/EXP-0002 and benchmark.log). Three real bugs found and resolved during M1 development (full diagnostic record in errors.log): - Two independent, reproducible Icarus Verilog v13.0 scheduling defects (ERR-0001, ERR-0002) that silently produced wrong simulation results for standard sequential Verilog -- confirmed via Verilator 5.050 giving correct results on the same minimal repros. Verilator is now the trusted simulator for hardware/v2/ (decisions.log DEC-0004); Icarus's affected protocol-violation check was removed from the RTL and deferred architecturally to the Neural Director (DEC-0003) rather than chased further. - One real RTL bug (ERR-0003): last0 wasn't gated like valid0, letting a "last tile" tag leak into the pipeline ahead of its actual valid tile on back-to-back jobs. Fixed and verified. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013xXuuRUWZScuo1DeYJxs3v
207 lines
6.8 KiB
Verilog
207 lines
6.8 KiB
Verilog
`timescale 1ns/1ps
|
|
|
|
// ================================================================
|
|
// SPI SLAVE - physical layer
|
|
//
|
|
// SPI Mode 0 (CPOL=0, CPHA=0), MSB-first, single SPI.
|
|
// Per docs/FPGA-NeuralNetwork-Engine.md §8.1: the FPGA is always
|
|
// SPI slave; one command per CS-low period.
|
|
//
|
|
// SCLK/MOSI/CS_N arrive from an external, clock-asynchronous SPI
|
|
// master, so they are double-flop synchronized into the `clk`
|
|
// domain before any edge detection. This module only implements
|
|
// the byte-level shift register and CS framing; opcode/protocol
|
|
// decoding lives in spi_engine.v.
|
|
//
|
|
// Mode 0 timing: MOSI is sampled on the RISING edge of SCLK; MISO
|
|
// is driven on the FALLING edge (so it is stable well before the
|
|
// master's next rising-edge sample).
|
|
// ================================================================
|
|
|
|
module spi_slave (
|
|
input wire clk,
|
|
input wire rst,
|
|
|
|
// ------------------------------------------------------------
|
|
// External SPI pins
|
|
// ------------------------------------------------------------
|
|
|
|
input wire sclk,
|
|
input wire mosi,
|
|
output reg miso,
|
|
input wire cs_n,
|
|
|
|
// ------------------------------------------------------------
|
|
// Byte-level interface to spi_engine
|
|
// ------------------------------------------------------------
|
|
|
|
output reg [7:0] rx_byte,
|
|
output reg rx_valid, // one clk pulse: rx_byte is valid
|
|
|
|
// IMPORTANT / load-bearing contract:
|
|
// tx_byte_req is a PREFETCH hint, not a "byte consumed" event.
|
|
// It fires once at cs_fell (to load byte 1) and once more after
|
|
// EVERY byte's last bit (to have the next byte ready in time
|
|
// for MISO, in case the master keeps clocking) -- including
|
|
// after the LAST byte of a transaction, since the slave cannot
|
|
// know in advance that no further byte will follow until CS
|
|
// actually deasserts. A consumer MUST NOT treat tx_byte_req as
|
|
// a destructive "advance/pop the next byte" trigger, or it will
|
|
// over-advance by exactly one byte on every transaction (e.g.
|
|
// over-incrementing a RAM read pointer). Use `rx_valid` instead
|
|
// to advance any stateful pointer: it pulses exactly once per
|
|
// REAL byte transferred, never an extra time, because it is
|
|
// driven purely by counted SCLK edges that actually happened.
|
|
input wire [7:0] tx_byte, // next byte to shift out on MISO
|
|
output reg tx_byte_req, // one clk pulse: refresh tx_byte now (prefetch hint, see above)
|
|
|
|
output wire cs_active, // level: transaction in progress
|
|
output reg cs_start, // one clk pulse: CS just went low
|
|
output reg cs_end // one clk pulse: CS just went high
|
|
);
|
|
|
|
// ============================================================
|
|
// CDC SYNCHRONIZERS (double flip-flop)
|
|
// ============================================================
|
|
|
|
reg [2:0] sclk_sync;
|
|
reg [2:0] mosi_sync;
|
|
reg [2:0] cs_n_sync;
|
|
|
|
always @(posedge clk) begin
|
|
if (rst) begin
|
|
sclk_sync <= 3'b000;
|
|
mosi_sync <= 3'b000;
|
|
cs_n_sync <= 3'b111;
|
|
end else begin
|
|
sclk_sync <= {sclk_sync[1:0], sclk};
|
|
mosi_sync <= {mosi_sync[1:0], mosi};
|
|
cs_n_sync <= {cs_n_sync[1:0], cs_n};
|
|
end
|
|
end
|
|
|
|
wire sclk_s = sclk_sync[2];
|
|
wire mosi_s = mosi_sync[2];
|
|
wire cs_n_s = cs_n_sync[2];
|
|
|
|
// Edge detects on the synchronized (2-deep) signal using one
|
|
// extra history bit, so "rising"/"falling" mean the edge that
|
|
// just became visible to `clk`.
|
|
reg sclk_prev;
|
|
reg cs_n_prev;
|
|
|
|
always @(posedge clk) begin
|
|
if (rst) begin
|
|
sclk_prev <= 1'b0;
|
|
cs_n_prev <= 1'b1;
|
|
end else begin
|
|
sclk_prev <= sclk_s;
|
|
cs_n_prev <= cs_n_s;
|
|
end
|
|
end
|
|
|
|
wire sclk_rise = sclk_s & ~sclk_prev;
|
|
wire sclk_fall = ~sclk_s & sclk_prev;
|
|
|
|
wire cs_fell = ~cs_n_s & cs_n_prev; // CS just went active (low)
|
|
wire cs_rose = cs_n_s & ~cs_n_prev; // CS just went inactive (high)
|
|
|
|
assign cs_active = ~cs_n_s;
|
|
|
|
// ============================================================
|
|
// BIT COUNTER / SHIFT REGISTERS
|
|
// ============================================================
|
|
|
|
reg [2:0] bit_count; // 0..7, counts bits received/sent within a byte
|
|
reg [7:0] rx_shift;
|
|
reg [7:0] tx_shift;
|
|
|
|
always @(posedge clk) begin
|
|
|
|
if (rst) begin
|
|
|
|
bit_count <= 3'd0;
|
|
rx_shift <= 8'h00;
|
|
tx_shift <= 8'h00;
|
|
rx_byte <= 8'h00;
|
|
rx_valid <= 1'b0;
|
|
tx_byte_req <= 1'b0;
|
|
miso <= 1'b0;
|
|
cs_start <= 1'b0;
|
|
cs_end <= 1'b0;
|
|
|
|
end else begin
|
|
|
|
// ------------------------------------------------
|
|
// Default pulses
|
|
// ------------------------------------------------
|
|
rx_valid <= 1'b0;
|
|
tx_byte_req <= 1'b0;
|
|
cs_start <= 1'b0;
|
|
cs_end <= 1'b0;
|
|
|
|
if (cs_fell) begin
|
|
|
|
// New transaction: reset bit counter, arm the
|
|
// first tx byte load and pre-load MISO with its
|
|
// MSB so it is valid before the first SCLK rise.
|
|
bit_count <= 3'd0;
|
|
tx_shift <= tx_byte;
|
|
tx_byte_req <= 1'b1;
|
|
miso <= tx_byte[7];
|
|
cs_start <= 1'b1;
|
|
|
|
end else if (cs_rose) begin
|
|
|
|
cs_end <= 1'b1;
|
|
|
|
end else if (cs_active) begin
|
|
|
|
if (sclk_rise) begin
|
|
|
|
// Sample MOSI (mode 0: data valid on rising edge)
|
|
rx_shift <= {rx_shift[6:0], mosi_s};
|
|
|
|
if (bit_count == 3'd7) begin
|
|
|
|
bit_count <= 3'd0;
|
|
rx_byte <= {rx_shift[6:0], mosi_s};
|
|
rx_valid <= 1'b1;
|
|
|
|
end else begin
|
|
|
|
bit_count <= bit_count + 3'd1;
|
|
|
|
end
|
|
|
|
end else if (sclk_fall) begin
|
|
|
|
// Drive next MISO bit (mode 0: output changes
|
|
// on the falling edge, ahead of the next
|
|
// master-side rising-edge sample).
|
|
if (bit_count == 3'd0) begin
|
|
|
|
// A byte boundary just completed on the
|
|
// matching rising edge above; load the
|
|
// next tx byte now.
|
|
tx_shift <= tx_byte;
|
|
tx_byte_req <= 1'b1;
|
|
miso <= tx_byte[7];
|
|
|
|
end else begin
|
|
|
|
tx_shift <= {tx_shift[6:0], 1'b0};
|
|
miso <= tx_shift[6];
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
end
|
|
|
|
endmodule
|