Real 32-bit DDR3 widening (2x MT41J128M16JT-125:K chips ganged in parallel, user's own MIG wizard session). Full RTL adaptation across the shared ctrl bus (16-bit word -> 32-bit word, BURST_LEN=8 unchanged, burst payload 128->256 bits): - mig_native_adapter.v: app_wdf_data/app_rd_data 64->128 bits (real, confirmed against the regenerated MIG wrapper), beat count unchanged. - act_tile_fetch.v: real logic change - burst now holds 4 tiles instead of 2 (sel_lat extended to 2 registered bits, 4-way case mux instead of 2-way ternary, same request-time-registered-select discipline as EXP-0081). Not a further bytes/MAC reduction, just what's needed to keep 100% packing utilization at the larger burst. - host_mem_bridge.v: real addressing redesign - host-facing 16-bit-word contract kept unchanged (ESP32 firmware unaffected), internally translated onto the new 32-bit-native ctrl bus. - sdram_arbiter_n.v, layer_prefetch_ctrl.v, packed_slot.v, ddr_prefetch_mgr.v, n2_system_ddr3_top.v: mechanical width bump plus doubled ddr3_dq/dqs/dm pins and the real differential sys_clk/clk_ref top-level ports the regenerated MIG now requires. New burst_mem_model32.v: explicitly synthetic 32-bit test-only burst memory (the real 16-bit SDR model is genuinely fixed-width, shared by 20+ other tests, correctly not touched). Found and fixed a real address-aliasing bug in it during bring-up (MEM_ADDR_BITS=16 silently wrapped a real 0x10000 test address to 0). Real verification: all isolated testbenches re-verified (10/10, 33/33, 32/32, 7/7, 9/9 PASS), plus real xsim against the real 2-chip DDR3 model (tb_mig_native_adapter.v 12/12 PASS, tb_n2_system_ddr3.v 8/8 PASS, both chips visibly returning different real data). Real P&R: 5 real bugs found and fixed across iterations (stale single-ended MIG clock ports, a real VCCO conflict between the flash SPI bus and the differential reference clock in bank 14 - fixed by moving flash to bank 16, a stale imported XDC - same bug class as EXP-0078 but for constraints this time, missing IOSTANDARDs, and two previously-silently-broken XDC property bugs). Route completes 100%, but real timing does NOT close: WNS -0.618ns, 213 failing endpoints. Honest root cause: the violation is inside neural_processor_packed.v's own packed-MAC accumulation tree, unchanged since EXP-0059 - it has real margin at the old 155.039MHz ui_clk but not at the new 172.414MHz the paired clock-period change produced. This is NOT caused by the 32-bit width change itself. Width alone, even at the old clock, already delivers the full intended 2x bandwidth gain (1.24 -> ~2.48 GB/s) - width and clock rate are separable levers. Current trustworthy timing signoff remains EXP-0083 (16-bit, +0.073ns) until the clock period is reverted toward 3225ps (keeping Data Width=32) in one more real, user-gated MIG wizard session. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01MUG92aM9m68TRc4rG55BcC
278 lines
12 KiB
Verilog
278 lines
12 KiB
Verilog
`timescale 1ps/100fs
|
|
|
|
// ============================================================
|
|
// First real verification of mig_native_adapter.v against the REAL,
|
|
// vendor-provided DDR3 behavioral model (ddr3_model.sv, shipped with
|
|
// this project's own generated mig_7series_0 IP) -- not a stand-in,
|
|
// the actual JEDEC-timed model MIG itself ships for exactly this
|
|
// purpose. Confirms the app_cmd encoding, burst/beat sequencing, and
|
|
// address unit assumed by mig_native_adapter.v's own header comment
|
|
// are correct by real write-then-read-back comparison, not by
|
|
// documentation archaeology alone.
|
|
//
|
|
// Instantiates mig_7series_0_mig (the inner module, NOT the public
|
|
// mig_7series_0.v wrapper) directly, with SIM_BYPASS_INIT_CAL="FAST"
|
|
// overridden -- mig_7series_0.v's own wrapper hardcodes "OFF" (full
|
|
// real calibration, impractically slow for simulation) and does not
|
|
// expose this parameter; mig_7series_0_mig.v does. All other
|
|
// parameters are left at their defaults, which already ARE this
|
|
// project's real generated configuration (EXP-0084: DQ_WIDTH=32 now,
|
|
// two MT41J128M16 components ganged in parallel -- MEM_DENSITY=2Gb,
|
|
// MEM_SPEEDGRADE=125, MEM_ADDR_ORDER=BANK_ROW_COLUMN unchanged) --
|
|
// not generic MIG defaults.
|
|
//
|
|
// Clock/reset generation and DDR3 pin wiring (WireDelay pass-through,
|
|
// zero propagation delay) mirror this project's own vendor-shipped
|
|
// example_design/sim/sim_tb_top.v exactly, per its own real, proven
|
|
// pattern -- not re-derived from scratch. EXP-0084: the real vendor
|
|
// pattern instantiates NUM_COMP=DQ_WIDTH/16 real ddr3_model.sv
|
|
// components for a >16-bit aggregate width, each wired to its own
|
|
// 16-bit dq / 2-bit dqs / 2-bit dm slice -- confirmed by reading the
|
|
// real regenerated sim_tb_top.v (not assumed), replicated exactly
|
|
// below for DQ_WIDTH=32 (NUM_COMP=2).
|
|
// ============================================================
|
|
module tb;
|
|
localparam CLKIN_PERIOD = 2900; // ps, matches this project's real MIG config (EXP-0084)
|
|
localparam REFCLK_FREQ = 200.0; // MHz
|
|
localparam real REFCLK_PERIOD = (1000000.0/(2*REFCLK_FREQ));
|
|
localparam RESET_PERIOD = 200000; // ps
|
|
|
|
localparam ADDR_WIDTH = 25; // this project's own word-address convention (BURST_LEN=8)
|
|
localparam BURST_LEN = 8;
|
|
|
|
reg sys_rst_n;
|
|
wire sys_rst = sys_rst_n; // Active Low, matches mig_7series_0_mig's own default polarity
|
|
|
|
// EXP-0084: both system clock AND reference clock are now real
|
|
// DIFFERENTIAL pairs on the inner mig_7series_0_mig module (the
|
|
// user's own wizard choice, "Differential" for both) -- confirmed
|
|
// against the real regenerated mig_7series_0_mig.v port list
|
|
// (sys_clk_p/n, clk_ref_p/n, no single-ended sys_clk_i/clk_ref_i
|
|
// ports exist any more). Same real vendor pattern as sim_tb_top.v:
|
|
// generate a single-ended internal clock, drive the P/N pair as
|
|
// true/complement of it.
|
|
reg sys_clk_i = 1'b0;
|
|
always #(CLKIN_PERIOD/2.0) sys_clk_i = ~sys_clk_i;
|
|
wire sys_clk_p = sys_clk_i;
|
|
wire sys_clk_n = ~sys_clk_i;
|
|
|
|
reg clk_ref_i = 1'b0;
|
|
always #REFCLK_PERIOD clk_ref_i = ~clk_ref_i;
|
|
wire clk_ref_p = clk_ref_i;
|
|
wire clk_ref_n = ~clk_ref_i;
|
|
|
|
initial begin
|
|
sys_rst_n = 1'b0;
|
|
#RESET_PERIOD sys_rst_n = 1'b1;
|
|
end
|
|
|
|
// ---- real DDR3 pins (dq/dqs/dm widths doubled since EXP-0084's
|
|
// real 32-bit widening -- two MT41J128M16 chips ganged in
|
|
// parallel, confirmed against the real regenerated
|
|
// mig_7series_0.v wrapper) ----
|
|
wire ddr3_reset_n;
|
|
wire [31:0] ddr3_dq_fpga;
|
|
wire [3:0] ddr3_dqs_p_fpga, ddr3_dqs_n_fpga;
|
|
wire [13:0] ddr3_addr_fpga;
|
|
wire [2:0] ddr3_ba_fpga;
|
|
wire ddr3_ras_n_fpga, ddr3_cas_n_fpga, ddr3_we_n_fpga;
|
|
wire [0:0] ddr3_cke_fpga, ddr3_ck_p_fpga, ddr3_ck_n_fpga, ddr3_cs_n_fpga;
|
|
wire [3:0] ddr3_dm_fpga;
|
|
wire [0:0] ddr3_odt_fpga;
|
|
|
|
wire [31:0] ddr3_dq_sdram;
|
|
reg [13:0] ddr3_addr_sdram;
|
|
reg [2:0] ddr3_ba_sdram;
|
|
reg ddr3_ras_n_sdram, ddr3_cas_n_sdram, ddr3_we_n_sdram;
|
|
wire [0:0] ddr3_cs_n_sdram;
|
|
wire [0:0] ddr3_odt_sdram;
|
|
reg [0:0] ddr3_cke_sdram;
|
|
wire [3:0] ddr3_dm_sdram;
|
|
wire [3:0] ddr3_dqs_p_sdram, ddr3_dqs_n_sdram;
|
|
reg [0:0] ddr3_ck_p_sdram, ddr3_ck_n_sdram;
|
|
|
|
reg [0:0] ddr3_cs_n_sdram_tmp;
|
|
reg [3:0] ddr3_dm_sdram_tmp;
|
|
reg [0:0] ddr3_odt_sdram_tmp;
|
|
|
|
always @(*) begin
|
|
ddr3_ck_p_sdram <= ddr3_ck_p_fpga;
|
|
ddr3_ck_n_sdram <= ddr3_ck_n_fpga;
|
|
ddr3_addr_sdram <= ddr3_addr_fpga;
|
|
ddr3_ba_sdram <= ddr3_ba_fpga;
|
|
ddr3_ras_n_sdram <= ddr3_ras_n_fpga;
|
|
ddr3_cas_n_sdram <= ddr3_cas_n_fpga;
|
|
ddr3_we_n_sdram <= ddr3_we_n_fpga;
|
|
ddr3_cke_sdram <= ddr3_cke_fpga;
|
|
end
|
|
always @(*) ddr3_cs_n_sdram_tmp <= ddr3_cs_n_fpga;
|
|
assign ddr3_cs_n_sdram = ddr3_cs_n_sdram_tmp;
|
|
always @(*) ddr3_dm_sdram_tmp <= ddr3_dm_fpga;
|
|
assign ddr3_dm_sdram = ddr3_dm_sdram_tmp;
|
|
always @(*) ddr3_odt_sdram_tmp <= ddr3_odt_fpga;
|
|
assign ddr3_odt_sdram = ddr3_odt_sdram_tmp;
|
|
|
|
genvar dqwd;
|
|
generate
|
|
for (dqwd = 0; dqwd < 32; dqwd = dqwd + 1) begin : dq_delay
|
|
WireDelay #(.Delay_g(0.00), .Delay_rd(0.00), .ERR_INSERT("OFF")) u_delay_dq (
|
|
.A(ddr3_dq_fpga[dqwd]), .B(ddr3_dq_sdram[dqwd]),
|
|
.reset(sys_rst_n), .phy_init_done(init_calib_complete)
|
|
);
|
|
end
|
|
endgenerate
|
|
genvar dqswd;
|
|
generate
|
|
for (dqswd = 0; dqswd < 4; dqswd = dqswd + 1) begin : dqs_delay
|
|
WireDelay #(.Delay_g(0.00), .Delay_rd(0.00), .ERR_INSERT("OFF")) u_delay_dqs_p (
|
|
.A(ddr3_dqs_p_fpga[dqswd]), .B(ddr3_dqs_p_sdram[dqswd]),
|
|
.reset(sys_rst_n), .phy_init_done(init_calib_complete)
|
|
);
|
|
WireDelay #(.Delay_g(0.00), .Delay_rd(0.00), .ERR_INSERT("OFF")) u_delay_dqs_n (
|
|
.A(ddr3_dqs_n_fpga[dqswd]), .B(ddr3_dqs_n_sdram[dqswd]),
|
|
.reset(sys_rst_n), .phy_init_done(init_calib_complete)
|
|
);
|
|
end
|
|
endgenerate
|
|
|
|
// ---- real DDR3 behavioral model (EXP-0084: TWO components now,
|
|
// DQ_WIDTH=32 / 16 per component -- exact real pattern confirmed
|
|
// against the real regenerated sim_tb_top.v's own generate block,
|
|
// not assumed) ----
|
|
genvar ci;
|
|
generate
|
|
for (ci = 0; ci < 2; ci = ci + 1) begin : gen_mem
|
|
ddr3_model u_comp_ddr3 (
|
|
.rst_n(ddr3_reset_n), .ck(ddr3_ck_p_sdram), .ck_n(ddr3_ck_n_sdram),
|
|
.cke(ddr3_cke_sdram[0]), .cs_n(ddr3_cs_n_sdram[0]),
|
|
.ras_n(ddr3_ras_n_sdram), .cas_n(ddr3_cas_n_sdram), .we_n(ddr3_we_n_sdram),
|
|
.dm_tdqs(ddr3_dm_sdram[2*ci +: 2]), .ba(ddr3_ba_sdram), .addr(ddr3_addr_sdram),
|
|
.dq(ddr3_dq_sdram[16*ci +: 16]),
|
|
.dqs(ddr3_dqs_p_sdram[2*ci +: 2]), .dqs_n(ddr3_dqs_n_sdram[2*ci +: 2]),
|
|
.tdqs_n(), .odt(ddr3_odt_sdram[0])
|
|
);
|
|
end
|
|
endgenerate
|
|
|
|
// ---- real MIG controller (inner module, SIM_BYPASS_INIT_CAL
|
|
// overridden for a real but fast simulation calibration) ----
|
|
wire [27:0] app_addr;
|
|
wire [2:0] app_cmd;
|
|
wire app_en, app_rdy;
|
|
wire [127:0] app_wdf_data;
|
|
wire app_wdf_end;
|
|
wire [15:0] app_wdf_mask;
|
|
wire app_wdf_wren, app_wdf_rdy;
|
|
wire [127:0] app_rd_data;
|
|
wire app_rd_data_end, app_rd_data_valid;
|
|
wire ui_clk, ui_clk_sync_rst, init_calib_complete;
|
|
|
|
mig_7series_0_mig #(
|
|
.SIM_BYPASS_INIT_CAL("FAST")
|
|
) u_mig (
|
|
.ddr3_dq(ddr3_dq_fpga), .ddr3_dqs_n(ddr3_dqs_n_fpga), .ddr3_dqs_p(ddr3_dqs_p_fpga),
|
|
.ddr3_addr(ddr3_addr_fpga), .ddr3_ba(ddr3_ba_fpga),
|
|
.ddr3_ras_n(ddr3_ras_n_fpga), .ddr3_cas_n(ddr3_cas_n_fpga), .ddr3_we_n(ddr3_we_n_fpga),
|
|
.ddr3_reset_n(ddr3_reset_n),
|
|
.ddr3_ck_p(ddr3_ck_p_fpga), .ddr3_ck_n(ddr3_ck_n_fpga),
|
|
.ddr3_cke(ddr3_cke_fpga), .ddr3_cs_n(ddr3_cs_n_fpga),
|
|
.ddr3_dm(ddr3_dm_fpga), .ddr3_odt(ddr3_odt_fpga),
|
|
.sys_clk_p(sys_clk_p), .sys_clk_n(sys_clk_n), .clk_ref_p(clk_ref_p), .clk_ref_n(clk_ref_n),
|
|
.app_addr(app_addr), .app_cmd(app_cmd), .app_en(app_en),
|
|
.app_wdf_data(app_wdf_data), .app_wdf_end(app_wdf_end),
|
|
.app_wdf_mask(app_wdf_mask), .app_wdf_wren(app_wdf_wren),
|
|
.app_rd_data(app_rd_data), .app_rd_data_end(app_rd_data_end),
|
|
.app_rd_data_valid(app_rd_data_valid), .app_rdy(app_rdy), .app_wdf_rdy(app_wdf_rdy),
|
|
.app_sr_req(1'b0), .app_ref_req(1'b0), .app_zq_req(1'b0),
|
|
.app_sr_active(), .app_ref_ack(), .app_zq_ack(),
|
|
.ui_clk(ui_clk), .ui_clk_sync_rst(ui_clk_sync_rst),
|
|
.init_calib_complete(init_calib_complete),
|
|
.device_temp(),
|
|
.sys_rst(sys_rst)
|
|
);
|
|
|
|
// ---- adapter under test ----
|
|
reg req, wr;
|
|
reg [ADDR_WIDTH-1:0] addr;
|
|
reg [32*BURST_LEN-1:0] wdata;
|
|
reg [4*BURST_LEN-1:0] wmask;
|
|
wire [32*BURST_LEN-1:0] rdata;
|
|
wire ready, busy;
|
|
|
|
mig_native_adapter #(.BURST_LEN(BURST_LEN), .ADDR_WIDTH(ADDR_WIDTH)) u_adapter (
|
|
.clk(ui_clk), .rst(ui_clk_sync_rst),
|
|
.req(req), .wr(wr), .addr(addr), .wdata(wdata), .wmask(wmask),
|
|
.rdata(rdata), .ready(ready), .busy(busy),
|
|
.app_addr(app_addr), .app_cmd(app_cmd), .app_en(app_en), .app_rdy(app_rdy),
|
|
.app_wdf_data(app_wdf_data), .app_wdf_end(app_wdf_end), .app_wdf_mask(app_wdf_mask),
|
|
.app_wdf_wren(app_wdf_wren), .app_wdf_rdy(app_wdf_rdy),
|
|
.app_rd_data(app_rd_data), .app_rd_data_end(app_rd_data_end), .app_rd_data_valid(app_rd_data_valid)
|
|
);
|
|
|
|
task automatic do_txn(
|
|
input t_wr,
|
|
input [ADDR_WIDTH-1:0] t_addr,
|
|
input [32*BURST_LEN-1:0] t_wdata,
|
|
output [32*BURST_LEN-1:0] t_rdata
|
|
);
|
|
begin
|
|
@(posedge ui_clk);
|
|
while (busy) @(posedge ui_clk);
|
|
req = 1'b1; wr = t_wr; addr = t_addr; wdata = t_wdata; wmask = {(4*BURST_LEN){1'b0}};
|
|
@(posedge ui_clk);
|
|
req = 1'b0;
|
|
while (!ready) @(posedge ui_clk);
|
|
t_rdata = rdata;
|
|
end
|
|
endtask
|
|
|
|
integer errors, tests;
|
|
reg [32*BURST_LEN-1:0] got, wpat;
|
|
integer k, i;
|
|
|
|
task automatic check_addr(input [ADDR_WIDTH-1:0] a, input [15:0] pattern);
|
|
begin
|
|
for (k = 0; k < BURST_LEN; k = k + 1)
|
|
wpat[k*32 +: 32] = {pattern, pattern + k[15:0]};
|
|
do_txn(1'b1, a, wpat, got);
|
|
do_txn(1'b0, a, {(32*BURST_LEN){1'b0}}, got);
|
|
tests = tests + 1;
|
|
if (got !== wpat) begin
|
|
$display("FAIL addr=%0d: got=%h expected=%h", a, got, wpat);
|
|
errors = errors + 1;
|
|
end else begin
|
|
$display("PASS addr=%0d: bit-exact %h", a, got);
|
|
end
|
|
end
|
|
endtask
|
|
|
|
initial begin
|
|
errors = 0; tests = 0;
|
|
req = 0; wr = 0; addr = 0; wdata = 0; wmask = 0;
|
|
|
|
$display("=== waiting for real DDR3 init_calib_complete (FAST sim calibration) ===");
|
|
wait (init_calib_complete);
|
|
$display("=== calibration done at time %0t, starting real write/read-back test ===", $time);
|
|
repeat (10) @(posedge ui_clk);
|
|
|
|
check_addr(25'd0, 16'hA5A5);
|
|
check_addr(25'd8, 16'h1000);
|
|
check_addr(25'd16, 16'h2000);
|
|
check_addr(25'd1024,16'h3000);
|
|
for (i = 0; i < 8; i = i + 1)
|
|
check_addr((25'd2048 + i*8), 16'h4000 + i);
|
|
|
|
$display("=== %0d/%0d tests, %0d errors ===", tests-errors, tests, errors);
|
|
if (errors == 0) $display("ALL TESTS PASSED (tb_mig_native_adapter, real ddr3_model.sv)");
|
|
else $display("SOME TESTS FAILED");
|
|
$finish;
|
|
end
|
|
|
|
initial begin
|
|
#200000000.0; // 200us watchdog
|
|
if (!init_calib_complete) $display("FAIL: calibration never completed within watchdog");
|
|
else $display("(watchdog fired after calibration already completed -- not a failure by itself)");
|
|
$finish;
|
|
end
|
|
endmodule
|