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
319 lines
7.0 KiB
Verilog
319 lines
7.0 KiB
Verilog
`timescale 1ns/1ps
|
|
|
|
module memory_interface_tb;
|
|
|
|
parameter ADDR_WIDTH = 23;
|
|
parameter DATA_WIDTH = 16;
|
|
|
|
reg clk;
|
|
reg rst;
|
|
|
|
// Host side
|
|
reg req;
|
|
reg wr;
|
|
reg [ADDR_WIDTH-1:0] addr;
|
|
reg [DATA_WIDTH-1:0] wdata;
|
|
|
|
wire [DATA_WIDTH-1:0] rdata;
|
|
wire ready;
|
|
|
|
// Memory side
|
|
wire mem_req;
|
|
wire mem_wr;
|
|
wire [ADDR_WIDTH-1:0] mem_addr;
|
|
wire [DATA_WIDTH-1:0] mem_wdata;
|
|
|
|
wire [DATA_WIDTH-1:0] mem_rdata;
|
|
wire mem_ready;
|
|
|
|
// ------------------------------------------------------------
|
|
// Clock
|
|
// ------------------------------------------------------------
|
|
|
|
initial begin
|
|
clk = 1'b0;
|
|
|
|
forever #5 clk = ~clk;
|
|
end
|
|
|
|
// ------------------------------------------------------------
|
|
// DUT: Memory Interface
|
|
// ------------------------------------------------------------
|
|
|
|
memory_interface #(
|
|
.ADDR_WIDTH(ADDR_WIDTH),
|
|
.DATA_WIDTH(DATA_WIDTH)
|
|
) dut (
|
|
.clk(clk),
|
|
.rst(rst),
|
|
|
|
.req(req),
|
|
.wr(wr),
|
|
.addr(addr),
|
|
.wdata(wdata),
|
|
|
|
.rdata(rdata),
|
|
.ready(ready),
|
|
|
|
.mem_req(mem_req),
|
|
.mem_wr(mem_wr),
|
|
.mem_addr(mem_addr),
|
|
.mem_wdata(mem_wdata),
|
|
|
|
.mem_rdata(mem_rdata),
|
|
.mem_ready(mem_ready)
|
|
);
|
|
|
|
// ------------------------------------------------------------
|
|
// Memory model
|
|
// ------------------------------------------------------------
|
|
|
|
memory_model #(
|
|
.ADDR_WIDTH(ADDR_WIDTH),
|
|
.DATA_WIDTH(DATA_WIDTH),
|
|
.DEPTH(4096),
|
|
.READ_LATENCY(2)
|
|
) memory (
|
|
.clk(clk),
|
|
.rst(rst),
|
|
|
|
.req(mem_req),
|
|
.wr(mem_wr),
|
|
.addr(mem_addr),
|
|
.wdata(mem_wdata),
|
|
|
|
.rdata(mem_rdata),
|
|
.ready(mem_ready)
|
|
);
|
|
|
|
// ------------------------------------------------------------
|
|
// Test utilities
|
|
// ------------------------------------------------------------
|
|
|
|
task write_mem;
|
|
input [ADDR_WIDTH-1:0] address;
|
|
input [DATA_WIDTH-1:0] data;
|
|
begin
|
|
@(posedge clk);
|
|
|
|
addr <= address;
|
|
wdata <= data;
|
|
wr <= 1'b1;
|
|
req <= 1'b1;
|
|
|
|
@(posedge clk);
|
|
|
|
req <= 1'b0;
|
|
|
|
wait (ready);
|
|
|
|
@(posedge clk);
|
|
|
|
$display(
|
|
"WRITE addr=0x%08h data=0x%04h PASS",
|
|
address,
|
|
data
|
|
);
|
|
end
|
|
endtask
|
|
|
|
task read_mem;
|
|
input [ADDR_WIDTH-1:0] address;
|
|
input [DATA_WIDTH-1:0] expected;
|
|
|
|
reg [DATA_WIDTH-1:0] received;
|
|
|
|
begin
|
|
@(posedge clk);
|
|
|
|
addr <= address;
|
|
wr <= 1'b0;
|
|
req <= 1'b1;
|
|
|
|
@(posedge clk);
|
|
|
|
req <= 1'b0;
|
|
|
|
wait (ready);
|
|
|
|
received = rdata;
|
|
|
|
@(posedge clk);
|
|
|
|
if (received === expected) begin
|
|
$display(
|
|
"READ addr=0x%08h data=0x%04h PASS",
|
|
address,
|
|
received
|
|
);
|
|
end else begin
|
|
$display(
|
|
"READ addr=0x%08h got=0x%04h expected=0x%04h FAIL",
|
|
address,
|
|
received,
|
|
expected
|
|
);
|
|
|
|
$fatal;
|
|
end
|
|
end
|
|
endtask
|
|
|
|
// ------------------------------------------------------------
|
|
// Test sequence
|
|
// ------------------------------------------------------------
|
|
|
|
initial begin
|
|
|
|
// Defaults
|
|
rst = 1'b1;
|
|
|
|
req = 1'b0;
|
|
wr = 1'b0;
|
|
addr = {ADDR_WIDTH{1'b0}};
|
|
wdata = {DATA_WIDTH{1'b0}};
|
|
|
|
// Reset
|
|
repeat (3)
|
|
@(posedge clk);
|
|
|
|
rst = 1'b0;
|
|
|
|
$display("");
|
|
$display("========================================");
|
|
$display("MEMORY INTERFACE V1 TEST");
|
|
$display("ADDR_WIDTH = %0d", ADDR_WIDTH);
|
|
$display("DATA_WIDTH = %0d", DATA_WIDTH);
|
|
$display("========================================");
|
|
$display("");
|
|
|
|
// --------------------------------------------------------
|
|
// Test 1
|
|
// --------------------------------------------------------
|
|
|
|
write_mem(
|
|
22'h000001,
|
|
16'h1234
|
|
);
|
|
|
|
read_mem(
|
|
22'h000001,
|
|
16'h1234
|
|
);
|
|
|
|
// --------------------------------------------------------
|
|
// Test 2
|
|
// --------------------------------------------------------
|
|
|
|
write_mem(
|
|
22'h000010,
|
|
16'hABCD
|
|
);
|
|
|
|
read_mem(
|
|
22'h000010,
|
|
16'hABCD
|
|
);
|
|
|
|
// --------------------------------------------------------
|
|
// Test 3
|
|
// --------------------------------------------------------
|
|
|
|
write_mem(
|
|
22'h000100,
|
|
16'h55AA
|
|
);
|
|
|
|
read_mem(
|
|
22'h000100,
|
|
16'h55AA
|
|
);
|
|
|
|
// --------------------------------------------------------
|
|
// Test 4
|
|
// --------------------------------------------------------
|
|
// Consecutive different addresses
|
|
|
|
write_mem(
|
|
22'h000200,
|
|
16'h0001
|
|
);
|
|
|
|
write_mem(
|
|
22'h000201,
|
|
16'h0002
|
|
);
|
|
|
|
write_mem(
|
|
22'h000202,
|
|
16'h0003
|
|
);
|
|
|
|
read_mem(
|
|
22'h000200,
|
|
16'h0001
|
|
);
|
|
|
|
read_mem(
|
|
22'h000201,
|
|
16'h0002
|
|
);
|
|
|
|
read_mem(
|
|
22'h000202,
|
|
16'h0003
|
|
);
|
|
|
|
// --------------------------------------------------------
|
|
// Test 5
|
|
// --------------------------------------------------------
|
|
// Zero value
|
|
|
|
write_mem(
|
|
22'h000300,
|
|
16'h0000
|
|
);
|
|
|
|
read_mem(
|
|
22'h000300,
|
|
16'h0000
|
|
);
|
|
|
|
// --------------------------------------------------------
|
|
// Test 6
|
|
// --------------------------------------------------------
|
|
// Full 16-bit value
|
|
|
|
write_mem(
|
|
22'h000301,
|
|
16'hFFFF
|
|
);
|
|
|
|
read_mem(
|
|
22'h000301,
|
|
16'hFFFF
|
|
);
|
|
|
|
// --------------------------------------------------------
|
|
// Finished
|
|
// --------------------------------------------------------
|
|
|
|
$display("");
|
|
$display("========================================");
|
|
$display("MEMORY INTERFACE V1 TEST PASSED");
|
|
$display("========================================");
|
|
$display("");
|
|
|
|
$finish;
|
|
end
|
|
|
|
// ------------------------------------------------------------
|
|
// VCD
|
|
// ------------------------------------------------------------
|
|
|
|
initial begin
|
|
$dumpfile("sim/memory_interface.vcd");
|
|
$dumpvars(0, memory_interface_tb);
|
|
end
|
|
|
|
endmodule |