Merge pull request 'phase1: bench_flush_frame substrate selector + IDCT-layer CPU vs QPU data' (#10) from noether/phase1-bench-substrate into main

Reviewed-on: #10

tests/bench_flush_frame.c

@@ -12,9 +12,19 @@
  * NOT a ctest — produces wall-time numbers, doesn't pass/fail.
  * Invoke manually after a build:
  *
- *   ./build/bench_flush_frame [width] [height] [iters] [warmup]
+ *   ./build/bench_flush_frame [width] [height] [iters] [warmup] [substrate]
  *
- * Defaults: 1920 1088 100 5
+ * Defaults: 1920 1088 100 5 auto
+ *
+ * The [substrate] argument selects the dispatch path:
+ *   auto — recipe table picks (V3D7 when available, else NEON)
+ *   cpu  — force NEON path
+ *   qpu  — force V3D7 path (fails on hosts without it)
+ *
+ * Run both to quantify the substrate gap.  The "QPU is default
+ * substrate" decree (2026-05-23, feedback_qpu_is_default_substrate.md)
+ * is a policy claim; this bench is how we measure whether the policy
+ * pays off for the IDCT layer specifically.
  *
  * The first `warmup` iterations are excluded from the timing
  * average because the daedalus-fourier shader pool needs to
@@ -70,6 +80,18 @@ int main(int argc, char **argv)
     int iters   = argc > 3 ? atoi(argv[3]) : 100;
     int warmup  = argc > 4 ? atoi(argv[4]) : 5;
 
+    daedalus_decoder_substrate sub = DAEDALUS_DECODER_SUBSTRATE_AUTO;
+    const char *sub_name = "auto";
+    if (argc > 5) {
+        if      (!strcmp(argv[5], "cpu"))  { sub = DAEDALUS_DECODER_SUBSTRATE_CPU;  sub_name = "cpu"; }
+        else if (!strcmp(argv[5], "qpu"))  { sub = DAEDALUS_DECODER_SUBSTRATE_QPU;  sub_name = "qpu"; }
+        else if (!strcmp(argv[5], "auto")) { /* default */ }
+        else {
+            fprintf(stderr, "unknown substrate '%s' (want auto/cpu/qpu)\n", argv[5]);
+            return 1;
+        }
+    }
+
     if (warmup >= iters) {
         fprintf(stderr, "warmup (%d) must be < iters (%d)\n", warmup, iters);
         return 1;
@@ -78,14 +100,18 @@ int main(int argc, char **argv)
     int mb_w = width  / 16;
     int mb_h = height / 16;
     int n_mbs = mb_w * mb_h;
-    printf("bench_flush_frame: %dx%d (%d MBs), %d iters (%d warmup)\n",
-           width, height, n_mbs, iters, warmup);
+    printf("bench_flush_frame: %dx%d (%d MBs), %d iters (%d warmup), substrate=%s\n",
+           width, height, n_mbs, iters, warmup, sub_name);
 
     daedalus_decoder *dec = daedalus_decoder_create(width, height);
     if (!dec) {
         fprintf(stderr, "SKIP: ctx create failed (Vulkan / V3D7 unavailable)\n");
         return 0;
     }
+    if (daedalus_decoder_set_substrate(dec, sub) != 0) {
+        fprintf(stderr, "set_substrate(%s) failed\n", sub_name);
+        return 1;
+    }
     printf("ctx has_qpu=%d\n", daedalus_decoder_has_qpu(dec));
 
     /* Pre-generate per-MB random coeffs once.  We re-append the same