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
157 lines
5.0 KiB
Verilog
157 lines
5.0 KiB
Verilog
`timescale 1ns/1ps
|
|
|
|
// ================================================================
|
|
// ACT_BUFFER TESTBENCH (Phase G1)
|
|
//
|
|
// Verifies:
|
|
// TEST 1 - write then read back (id 0, low end of range).
|
|
// TEST 2 - write then read back (id N_TOTAL-1, high end of range).
|
|
// TEST 3 - negative (signed) value round-trip.
|
|
// TEST 4 - read is REGISTERED: rd_data must NOT show the new value
|
|
// on the same cycle rd_addr changes, only one cycle later.
|
|
// TEST 5 - independent ports: write to addr X while reading addr Y
|
|
// in the same cycle does not disturb the read.
|
|
// TEST 6 - a burst of writes to many ids, then read them all back
|
|
// in a different order (models graph_engine's out-of-
|
|
// order gather pattern).
|
|
// ================================================================
|
|
|
|
module tb;
|
|
|
|
localparam N_TOTAL = 4096;
|
|
localparam DATA_WIDTH = 8;
|
|
localparam ADDR_WIDTH = $clog2(N_TOTAL);
|
|
localparam CLK_PERIOD = 10.0;
|
|
|
|
reg clk;
|
|
initial begin
|
|
clk = 1'b0;
|
|
forever #(CLK_PERIOD / 2.0) clk = ~clk;
|
|
end
|
|
|
|
reg wr_en;
|
|
reg [ADDR_WIDTH-1:0] wr_addr;
|
|
reg signed [DATA_WIDTH-1:0] wr_data;
|
|
|
|
reg [ADDR_WIDTH-1:0] rd_addr;
|
|
wire signed [DATA_WIDTH-1:0] rd_data;
|
|
|
|
act_buffer #(
|
|
.N_TOTAL(N_TOTAL),
|
|
.DATA_WIDTH(DATA_WIDTH)
|
|
) dut (
|
|
.clk(clk),
|
|
.wr_en(wr_en), .wr_addr(wr_addr), .wr_data(wr_data),
|
|
.rd_addr(rd_addr), .rd_data(rd_data)
|
|
);
|
|
|
|
integer errors;
|
|
|
|
task write_id(input [ADDR_WIDTH-1:0] addr, input signed [DATA_WIDTH-1:0] data);
|
|
begin
|
|
@(negedge clk);
|
|
wr_en = 1'b1;
|
|
wr_addr = addr;
|
|
wr_data = data;
|
|
@(negedge clk);
|
|
wr_en = 1'b0;
|
|
end
|
|
endtask
|
|
|
|
task check_read(input [ADDR_WIDTH-1:0] addr, input signed [DATA_WIDTH-1:0] expected, input [255:0] name);
|
|
begin
|
|
@(negedge clk);
|
|
rd_addr = addr;
|
|
@(negedge clk); // rd_data now reflects the address set above
|
|
if (rd_data !== expected) begin
|
|
$display("FAIL %0s: addr=%0d expected=%0d got=%0d", name, addr, expected, rd_data);
|
|
errors = errors + 1;
|
|
end else begin
|
|
$display("PASS %0s: addr=%0d data=%0d", name, addr, rd_data);
|
|
end
|
|
end
|
|
endtask
|
|
|
|
integer i;
|
|
|
|
initial begin
|
|
errors = 0;
|
|
wr_en = 1'b0;
|
|
wr_addr = 0;
|
|
wr_data = 0;
|
|
rd_addr = 0;
|
|
|
|
@(negedge clk);
|
|
|
|
// TEST 1 - low end of range
|
|
write_id(0, 8'sd42);
|
|
check_read(0, 8'sd42, "TEST1 id0");
|
|
|
|
// TEST 2 - high end of range
|
|
write_id(N_TOTAL-1, 8'sd100);
|
|
check_read(N_TOTAL-1, 8'sd100, "TEST2 id_max");
|
|
|
|
// TEST 3 - negative value round-trip
|
|
write_id(10, -8'sd77);
|
|
check_read(10, -8'sd77, "TEST3 negative");
|
|
|
|
// TEST 4 - read is registered (1-cycle latency), not
|
|
// combinational: changing rd_addr must not show the new
|
|
// value until the NEXT clock edge.
|
|
@(negedge clk);
|
|
rd_addr = 0; // id0 = 42
|
|
@(negedge clk);
|
|
if (rd_data !== 8'sd42) begin
|
|
$display("FAIL TEST4 setup: expected 42 got %0d", rd_data);
|
|
errors = errors + 1;
|
|
end
|
|
rd_addr = 10; // id10 = -77, but rd_data must still show id0's value THIS cycle
|
|
if (rd_data !== 8'sd42) begin
|
|
$display("FAIL TEST4 latency: rd_data changed same-cycle as rd_addr (got %0d, expected still 42)", rd_data);
|
|
errors = errors + 1;
|
|
end else begin
|
|
$display("PASS TEST4 latency: rd_data still 42 same-cycle as rd_addr change");
|
|
end
|
|
@(negedge clk);
|
|
if (rd_data !== -8'sd77) begin
|
|
$display("FAIL TEST4 next-cycle: expected -77 got %0d", rd_data);
|
|
errors = errors + 1;
|
|
end else begin
|
|
$display("PASS TEST4 next-cycle: rd_data=-77 one cycle after rd_addr=10");
|
|
end
|
|
|
|
// TEST 5 - independent ports: write addr 20 while reading addr 10
|
|
@(negedge clk);
|
|
rd_addr = 10;
|
|
wr_en = 1'b1;
|
|
wr_addr = 20;
|
|
wr_data = 8'sd55;
|
|
@(negedge clk);
|
|
wr_en = 1'b0;
|
|
if (rd_data !== -8'sd77) begin
|
|
$display("FAIL TEST5: concurrent write disturbed read (expected -77 got %0d)", rd_data);
|
|
errors = errors + 1;
|
|
end else begin
|
|
$display("PASS TEST5: concurrent write to a different address did not disturb read");
|
|
end
|
|
check_read(20, 8'sd55, "TEST5 followup id20");
|
|
|
|
// TEST 6 - burst write many ids, read back out of order
|
|
for (i = 0; i < 16; i = i + 1) begin
|
|
write_id(100 + i, i[7:0]);
|
|
end
|
|
for (i = 15; i >= 0; i = i - 1) begin
|
|
check_read(100 + i, i[7:0], "TEST6 burst reverse-order");
|
|
end
|
|
|
|
if (errors == 0) begin
|
|
$display("ALL TESTS PASSED");
|
|
end else begin
|
|
$display("%0d TEST(S) FAILED", errors);
|
|
end
|
|
|
|
$finish;
|
|
end
|
|
|
|
endmodule
|