Ch443c: per-frame scanout diagnostic + frame-restart latency fix
The Ch443 board A+B diagnostic captured a WARM-UP miss, not a displayed-
frame miss: the line-buffer reader is enabled by video_src_emif
immediately, but the HDMI mux only switches to it at the next vsync, and
the diagnostic (cleared only on !enable) froze that pre-display capture.
scan_y=32/nf=32 was the expected pre-display warm-up, and line_valid is
sticky so it only meant SOME row had loaded, not that row 32 was valid.
Two fixes (all accepted Ch443 timing repairs kept: AW buffer, F_SETTLE +
drain multicycle, tile max-skew, monolithic tex_mem):
1. Per-frame diagnostic: clear diag_valid_q on fs_edge_v as well as
!enable (mirrors underflow_v). Discards the warm-up capture and
records the first miss, if any, AFTER the real frame boundary.
2. Frame-restart latency: in L_R, after the single-beat response is
accepted, if fs_pending || fs_edge_e, abandon the remainder of the
obsolete row -- no beat commit, no next old-row AR, no publish/
increment -- and return to L_IDLE, which restarts at V_SOURCE_START.
Protocol-safe (the accepted AXI transaction is complete); removes up
to a full row of restart latency during vertical blanking, so the
restarted prefetch leads the first displayed row.
New tb_gs_scanout_restart proves: mid-fetch frame-start accepts the
in-flight response, issues NO further old-row AR, restarts at row 32,
loads rows 32/33 before active consumption, and no post-restart
underflow. Regressions green: scanout_lb {,_binomial,_hstretch,
_psm32_256,_fb}, scanout_diag (per-frame), ps2_hps_bridge, and the
complete f52 replay BYTE-IDENTICAL (Z 0/307200, COLOR 0/245760).
Also commits the previously-untracked Ch443 board A+B evidence
(docs/hardware/ch443_board_validation/: verdict, 3-session raw, board
FB, RBF sha). No Quartus/board/push from here.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -1280,6 +1280,15 @@ tb_gs_scanout_diag: dirs
|
||||
@echo "=== run tb_gs_scanout_diag ==="
|
||||
@cd $(TRACE_DIR) && $(VVP) $(BUILD_DIR)/tb_gs_scanout_diag.vvp
|
||||
|
||||
tb_gs_scanout_restart: dirs
|
||||
@echo "=== build tb_gs_scanout_restart ==="
|
||||
$(IVERILOG) $(IVERILOG_FLGS) \
|
||||
-o $(BUILD_DIR)/tb_gs_scanout_restart.vvp \
|
||||
-s tb_gs_scanout_restart \
|
||||
$(RTL_SRCS) $(TB_ROOT)/gif_gs/tb_gs_scanout_restart.sv
|
||||
@echo "=== run tb_gs_scanout_restart ==="
|
||||
@cd $(TRACE_DIR) && $(VVP) $(BUILD_DIR)/tb_gs_scanout_restart.vvp
|
||||
|
||||
tb_gs_texture_cache: dirs
|
||||
@echo "=== build tb_gs_texture_cache ==="
|
||||
$(IVERILOG) $(IVERILOG_FLGS) \
|
||||
|
||||
@@ -0,0 +1,146 @@
|
||||
// retroDE_ps2 — tb_gs_scanout_restart (Ch443c)
|
||||
//
|
||||
// Focused test for the frame-restart latency repair in gs_lpddr_scanout_lb's AXI
|
||||
// prefetch FSM. On a vsync (frame_start) that lands MID-ROW, the FSM must, after the
|
||||
// current single-beat response is accepted, abandon the remainder of the now-obsolete
|
||||
// row (no next old-row AR, no publish/increment) and restart the prefetch at
|
||||
// V_SOURCE_START. Proves:
|
||||
// (1) the in-flight response is accepted normally (no deadlock);
|
||||
// (2) NO further old-row AR issues after the restart trigger;
|
||||
// (3) the restart's first AR targets row V_SOURCE_START (=32);
|
||||
// (4) rows 32 and 33 become resident before the first active (in_window) consumption;
|
||||
// (5) no post-restart underflow on the displayed frame.
|
||||
`timescale 1ns/1ps
|
||||
|
||||
module tb_gs_scanout_restart;
|
||||
logic emif_clk = 0; always #2.5 emif_clk = ~emif_clk; // 200 MHz
|
||||
logic video_clk = 0; always #4 video_clk = ~video_clk; // 125 MHz
|
||||
logic rst_n;
|
||||
|
||||
localparam int N_ROWS = 48, VSS = 32, ROW_BEATS = 2, STRIDE = 64;
|
||||
localparam int ROW32_ADDR = VSS * STRIDE; // 2048
|
||||
localparam int ROW33_ADDR = (VSS+1) * STRIDE; // 2112
|
||||
|
||||
logic enable, frame_start, in_window;
|
||||
logic [11:0] pixel_x, pixel_y;
|
||||
logic [7:0] r,g,b; logic line_valid, underflow; logic [31:0] rd_errs;
|
||||
logic diag_rderr_nz, diag_valid; logic [29:0] diag_first; logic [6:0] diag_stat;
|
||||
logic [29:0] araddr; logic [1:0] arburst; logic [6:0] arid;
|
||||
logic [7:0] arlen; logic [2:0] arsize; logic arvalid, arready;
|
||||
logic [255:0] rdata; logic [1:0] rresp; logic rlast, rvalid, rready;
|
||||
|
||||
gs_lpddr_scanout_lb #(.FB_BASE(30'd0), .STRIDE_BYTES(STRIDE), .ROW_BEATS(ROW_BEATS),
|
||||
.N_ROWS(N_ROWS), .PSMCT32(1'b1), .V_SOURCE_START(VSS)) dut (
|
||||
.axi_clk(emif_clk), .axi_rst_n(rst_n), .enable(enable),
|
||||
.video_clk(video_clk), .frame_start(frame_start),
|
||||
.pixel_x(pixel_x), .pixel_y(pixel_y), .in_window(in_window),
|
||||
.r(r), .g(g), .b(b), .line_valid(line_valid), .underflow(underflow), .rd_errs(rd_errs),
|
||||
.diag_rderr_nz(diag_rderr_nz), .diag_valid(diag_valid), .diag_first(diag_first), .diag_stat(diag_stat),
|
||||
.araddr(araddr), .arburst(arburst), .arid(arid), .arlen(arlen), .arsize(arsize),
|
||||
.arvalid(arvalid), .arready(arready), .rdata(rdata), .rresp(rresp),
|
||||
.rlast(rlast), .rvalid(rvalid), .rready(rready)
|
||||
);
|
||||
|
||||
// behavioral EMIF responder: grant AR, return OKAY R one cycle later (fast).
|
||||
logic pend; logic [29:0] pend_addr;
|
||||
assign arready = arvalid && !pend && !rvalid;
|
||||
always_ff @(posedge emif_clk or negedge rst_n) begin
|
||||
if (!rst_n) begin pend<=0; rvalid<=0; rlast<=0; rresp<=0; rdata<=0; end
|
||||
else begin
|
||||
if (arready) begin pend<=1; pend_addr<=araddr; end
|
||||
if (pend && !rvalid) begin rvalid<=1; rlast<=1; rresp<=0; rdata<={8{2'b01,pend_addr}}; pend<=0; end
|
||||
else if (rvalid && rready) begin rvalid<=0; rlast<=0; end
|
||||
end
|
||||
end
|
||||
|
||||
int errors = 0;
|
||||
task automatic chk(input string s, input logic c);
|
||||
if (!c) begin $error("[restart] FAIL: %s", s); errors++; end
|
||||
else $display("[restart] ok : %s", s);
|
||||
endtask
|
||||
|
||||
// ---- monitors (emif domain) ----
|
||||
// capture, at the restart trigger, whether we were mid-fetch and which row.
|
||||
logic restart_seen, restart_midfetch;
|
||||
logic [$clog2(N_ROWS):0] row_at_restart;
|
||||
// track the FIRST araddr issued (arvalid rising) AFTER the restart trigger.
|
||||
logic arv_prev, armed_first_ar, got_first_ar;
|
||||
logic [29:0] first_ar_after_restart;
|
||||
// flag ANY old-row AR after restart (araddr not equal to a fresh row-32-onwards fetch
|
||||
// before we've seen the row-32 restart AR).
|
||||
always_ff @(posedge emif_clk or negedge rst_n) begin
|
||||
if (!rst_n) begin
|
||||
restart_seen<=0; restart_midfetch<=0; row_at_restart<=0;
|
||||
arv_prev<=0; armed_first_ar<=0; got_first_ar<=0; first_ar_after_restart<=0;
|
||||
end else begin
|
||||
arv_prev <= arvalid;
|
||||
// restart trigger = fs_edge_e inside the DUT
|
||||
// lstate_t = { L_IDLE=0, L_AR=1, L_R=2, L_C=3 }
|
||||
if (dut.fs_edge_e && !restart_seen) begin
|
||||
restart_seen <= 1'b1;
|
||||
restart_midfetch <= (dut.lst == 2'd1) || (dut.lst == 2'd2); // L_AR or L_R
|
||||
row_at_restart <= dut.cur_row;
|
||||
armed_first_ar <= 1'b1;
|
||||
end
|
||||
// first arvalid rising edge after the restart trigger
|
||||
if (armed_first_ar && arvalid && !arv_prev && !got_first_ar) begin
|
||||
got_first_ar <= 1'b1;
|
||||
first_ar_after_restart<= araddr;
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
task automatic pulse_fs();
|
||||
@(posedge video_clk) frame_start <= 1'b1;
|
||||
repeat (3) @(posedge video_clk); frame_start <= 1'b0;
|
||||
repeat (2) @(posedge video_clk);
|
||||
endtask
|
||||
|
||||
initial begin
|
||||
rst_n=0; enable=0; frame_start=0; in_window=0; pixel_x=0; pixel_y=VSS[11:0];
|
||||
repeat (8) @(posedge emif_clk); rst_n=1;
|
||||
repeat (6) @(posedge emif_clk);
|
||||
|
||||
// ---- warm the prefetch: enable, first frame, advance disp_row so rows load ----
|
||||
enable=1;
|
||||
pulse_fs();
|
||||
// climb pixel_y from VSS upward (in_window=0 -> no underflow) so the prefetch
|
||||
// actively fetches rows 32,33,34,... Inject the mid-row restart partway through.
|
||||
for (int y=VSS; y<VSS+8; y++) begin
|
||||
@(posedge video_clk) pixel_y <= y[11:0];
|
||||
repeat (6) @(posedge video_clk);
|
||||
if (y == VSS+4) begin
|
||||
// MID-ROW vsync: assert frame_start while the FSM is actively fetching.
|
||||
@(posedge video_clk) frame_start <= 1'b1;
|
||||
repeat (3) @(posedge video_clk); frame_start <= 1'b0;
|
||||
end
|
||||
end
|
||||
repeat (40) @(posedge emif_clk);
|
||||
|
||||
// ---- (1)+(2)+(3): restart abandoned the old row and re-fetched from row 32 ----
|
||||
chk("restart trigger observed", restart_seen === 1'b1);
|
||||
chk("restart landed mid-fetch (L_AR/L_R)", restart_midfetch === 1'b1);
|
||||
chk("first AR after restart = row 32", first_ar_after_restart === 30'(ROW32_ADDR));
|
||||
|
||||
// ---- (4): rows 32 and 33 resident before active consumption ----
|
||||
// advance disp_row to let the restarted prefetch reach next_fetch >= 34.
|
||||
for (int y=VSS; y<VSS+4; y++) begin
|
||||
@(posedge video_clk) pixel_y <= y[11:0];
|
||||
repeat (10) @(posedge video_clk);
|
||||
end
|
||||
repeat (40) @(posedge emif_clk);
|
||||
chk("next_fetch advanced past rows 32,33 (>=34)", dut.next_fetch >= ($clog2(N_ROWS)+1)'(VSS+2));
|
||||
chk("line_valid set (rows resident)", line_valid === 1'b1);
|
||||
|
||||
// ---- (5): now consume actively at row 32 -> NO underflow ----
|
||||
@(posedge video_clk) begin in_window <= 1'b1; pixel_y <= VSS[11:0]; pixel_x <= 12'd0; end
|
||||
repeat (60) @(posedge video_clk);
|
||||
chk("no post-restart underflow at row 32", underflow === 1'b0);
|
||||
|
||||
if (errors==0) $display("[tb_gs_scanout_restart] PASS");
|
||||
else $display("[tb_gs_scanout_restart] FAIL (%0d errors)", errors);
|
||||
$finish;
|
||||
end
|
||||
|
||||
initial begin #400000; $error("[tb_gs_scanout_restart] TIMEOUT"); $finish; end
|
||||
endmodule : tb_gs_scanout_restart
|
||||
Reference in New Issue
Block a user