1 files changed, 25 insertions, 1 deletions

diff --git a/src/pardes/app.zig b/src/pardes/app.zig
index a83485a..23da203 100644
--- a/src/pardes/app.zig
+++ b/src/pardes/app.zig
@@ -37,6 +37,10 @@
 const std = @import("std");
 const soc = @import("soc");
 const config = @import("config");
+
+/// `-Dprof`: time the two phases of a keystroke on the board and print the cycle counts. A
+/// diagnostic, not a feature - see the loop.
+const prof = config.prof;
 const hal = @import("hal");
 const heapmod = @import("heap");
 const uart = @import("uart.zig");
@@ -203,16 +207,36 @@ export fn zig_main() noreturn {
 
     var in: [256]u8 = undefined;
     while (!pardes_p4_quit()) {
+        // ATTRIBUTION. The host can time a keystroke's round trip but cannot see what the firmware
+        // spent it on, and the two candidates - parsing and editing, versus rendering - want
+        // opposite fixes. `soc.cycles()` is the unprivileged cycle counter, so this costs two CSR
+        // reads per phase and quantises at one cycle, which is four orders of magnitude below the
+        // milliseconds being attributed. Gated on `prof` so the shipping build carries none of it.
         const n = uart.read(&in);
-        if (n > 0) pardes_p4_input(&in, n);
+        var input_cy: u64 = 0;
+        if (n > 0) {
+            const t0 = if (prof) soc.cycles() else 0;
+            pardes_p4_input(&in, n);
+            if (prof) input_cy = soc.cycles() - t0;
+        }
 
         pardes_p4_tick(nowMs());
 
         // Only when there is something to show. On a link this slow an unconditional repaint per
         // iteration would saturate the wire and starve input.
         if (pardes_p4_wants_frame()) {
+            const t0 = if (prof) soc.cycles() else 0;
             const err = pardes_p4_render();
             if (err != 0) soc.rom.print("MARK PARDES_RENDER_FAIL rc=%u\r\n", .{err});
+            if (prof) {
+                const render_cy = soc.cycles() - t0;
+                // Reported in cycles, not microseconds: the divisor is the CPU clock, which this
+                // firmware does not set and has only ever measured, so converting here would bake a
+                // guess into the data. `experiments/` divides by the clock it measured.
+                soc.rom.print("PROF in=%u render=%u\r\n", .{
+                    @as(u32, @intCast(input_cy)), @as(u32, @intCast(render_cy)),
+                });
+            }
         }
     }