micheleandClaude Sonnet 5
8e014d8d49
FASE #1 hardware freeze for FPGA-Neural V2, N4/P8, single external SDRAM (Alliance Memory AS4C4M16SA-6TIN) serving weights, activations, and results through one physical sdram_controller.v instance. Removes the PSRAM dependency (hardware/v1/rtl/psram_controller.v + memory_interface.v) from the V2 physical path entirely -- V1 itself remains fully unmodified, the golden reference. New RTL: sdram_unified_backend.v (2-way W/AR arbitration over one SDRAM controller, real per-byte DQM write masking added to sdram_controller.v for correct single-byte result writes with no read-modify-write), nms_neural_multiprocessor_sdram_unified.v (the frozen top-level). Two real bugs found and fixed via full-system testing before being accepted (ERR-0023): a deadlock and an off-by-one data-shift bug in the new arbitration logic. Real results: N=4 and N=2 D-Stress bit-exact (256/256 neurons), 40 real AUTO REFRESH events interleaved with zero corruption, real Yosys+nextpnr-ecp5 synthesis/P&R for LFE5U-45F-8CABGA381 (149/245 TRELLIS_IO, a real 45-pin reduction from the prior dual-memory design). Timing is MARGINAL (1/8 P&R seeds >=80MHz), reported honestly rather than masked by the best seed. Real, sourced ball-level pinout for the SDRAM bus + clk/rst (39/149 signals, P&R-verified) using the official Lattice ECP5U-45 pinout CSV found on disk during this step's own pre-commit review -- corrects an earlier draft that wrongly assumed no real pinout data was available. Chip readiness: NO. Real, disclosed blockers remain (no physical host interface exists yet -- the RTL's own reg_* ports are a 110-pin raw test-harness bus; clock source/PLL decision; power/configuration component selection) -- see hardware/v2/docs/{HARDWARE_FREEZE, CHIP_READINESS,OPEN_ITEMS}.md for the complete, itemized status. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013xXuuRUWZScuo1DeYJxs3v
54 lines
1.9 KiB
Verilog
54 lines
1.9 KiB
Verilog
// ================================================================
|
|
// SYNTHESIS-ONLY TIMING HARNESS -- NOT a functional deliverable.
|
|
// Same pattern as harness_nms_weight_direct.v, for nms_weight_packed.v.
|
|
// ================================================================
|
|
module harness_nms_weight_packed #(
|
|
parameter DATA_WIDTH = 8,
|
|
parameter P_IN = 8,
|
|
parameter N_SLOTS = 4,
|
|
parameter MAX_TILES = 16,
|
|
parameter TIW = (MAX_TILES <= 1) ? 1 : $clog2(MAX_TILES)
|
|
)(
|
|
input wire clk,
|
|
input wire rst,
|
|
input wire [7:0] seed,
|
|
output wire [7:0] checksum
|
|
);
|
|
|
|
reg [31:0] lfsr;
|
|
always @(posedge clk) begin
|
|
if (rst) lfsr <= {24'h0, seed} | 32'h1;
|
|
else lfsr <= {lfsr[30:0], lfsr[31] ^ lfsr[21] ^ lfsr[1] ^ lfsr[0]};
|
|
end
|
|
|
|
wire [N_SLOTS-1:0] fill_we = lfsr[N_SLOTS-1:0];
|
|
wire [N_SLOTS*TIW-1:0] fill_addr_flat = {(N_SLOTS*TIW/32+1){lfsr}};
|
|
wire [N_SLOTS*DATA_WIDTH*P_IN-1:0] fill_data_flat = {(N_SLOTS*DATA_WIDTH*P_IN/32+1){lfsr}};
|
|
wire [N_SLOTS-1:0] rd_en = lfsr[N_SLOTS-1:0];
|
|
wire [N_SLOTS*TIW-1:0] rd_addr_flat = {(N_SLOTS*TIW/32+1){lfsr}};
|
|
wire [N_SLOTS*DATA_WIDTH*P_IN-1:0] rd_data_flat;
|
|
|
|
nms_weight_packed #(
|
|
.DATA_WIDTH(DATA_WIDTH), .P_IN(P_IN), .N_SLOTS(N_SLOTS), .MAX_TILES(MAX_TILES)
|
|
) dut (
|
|
.clk(clk), .rst(rst),
|
|
.fill_we(fill_we), .fill_addr_flat(fill_addr_flat), .fill_data_flat(fill_data_flat),
|
|
.rd_en(rd_en), .rd_addr_flat(rd_addr_flat), .rd_data_flat(rd_data_flat)
|
|
);
|
|
|
|
integer k;
|
|
reg [7:0] chk, chk_next;
|
|
always @(posedge clk) begin
|
|
if (rst) begin
|
|
chk <= 8'h0;
|
|
end else begin
|
|
chk_next = chk;
|
|
for (k = 0; k < N_SLOTS; k = k + 1)
|
|
chk_next = chk_next ^ rd_data_flat[k*DATA_WIDTH*P_IN +: 8];
|
|
chk <= chk_next;
|
|
end
|
|
end
|
|
assign checksum = chk;
|
|
|
|
endmodule
|