iris: FrameReport CPU/GPU split, force-gles backend switch, iris-scroll.sh rig

Splits each frame sample at queue.submit into redraw-to-submit (iris's own
CPU work) and submit-to-after-present (driver/GPU wait), so RUST.md's I5
"where does iris's frame time go" question can be answered with a number
per half instead of a single total. Adds a force-gles Cargo feature that
switches the Android wgpu::Instance from Backends::PRIMARY to Backends::GL
at compile time (no runtime env-var path exists into an already-launched
Android process on this machine), for isolating SwiftShader-Vulkan vs.
GLES/virgl as the software-mode gap's cause. app/iris-scroll.sh extracts
transcript-bench.sh's exact 24-swipe/6-cycle gesture loop for iris's own
demo app, which transcript-bench.sh cannot drive directly since it opens a
session through the Compose app's own UI.

Verification (this pass, on a disk-pressure-limited host running low on
space): cargo fmt --all clean, no diff. cargo clippy --workspace
--all-targets: no warnings from this diff (pre-existing future-incompat
notices from wgpu/winit/naga only). cargo test --workspace and cargo ndk
for iris-android-app --features transcript-screen were verified clean by
the previous pass on this identical diff (fmt/clippy/test/ndk all clean,
per that pass's own report); not re-run here because the host's disk was
93% full and a concurrent ai-server rebuild (stable toolchain moved to
1.98.1, rebuilding aws-lc-sys from scratch) had driven I/O pressure to
~60%, so a repeat cargo test --workspace sat 50+ minutes doing no useful
work and was stopped rather than left to make the disk situation worse.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

iris/core/src/render/frame_report.rs

@@ -35,6 +35,12 @@ const RING_CAPACITY: usize = 4096;
 /// ever called from a button tap, not once per frame.
 pub struct FrameReport {
     ring: Box<[Duration; RING_CAPACITY]>,
+    /// The `submit_to_present` half of each sample in `ring`, same index,
+    /// same lifetime -- kept as a second ring rather than a ring of pairs so
+    /// the existing `ring`/percentile code above is untouched (RUST.md's I5
+    /// "Where iris's frame time goes" CPU/GPU split, added 2026-09-05).
+    /// `ring[i] - submit_ring[i]` is that frame's `redraw_to_submit` half.
+    submit_ring: Box<[Duration; RING_CAPACITY]>,
     /// How many of `ring`'s slots hold a real sample -- saturates at
     /// `RING_CAPACITY`, unlike `total_frames` below which keeps counting.
     len: usize,
@@ -56,6 +62,20 @@ pub struct FrameStats {
     pub p90: Duration,
     pub p99: Duration,
     pub worst: Duration,
+    /// Median of `redraw_to_submit` -- iris's own CPU work (layout, text,
+    /// primitive building) up to and including building the `queue.submit`
+    /// call, per frame. RUST.md's I5 "Where iris's frame time goes" split,
+    /// added 2026-09-05 to answer "CPU or GPU?" with a number rather than a
+    /// guess.
+    pub cpu_p50: Duration,
+    /// Median of `submit_to_present` -- the `queue.submit` call itself plus
+    /// `present()`, i.e. wherever the driver/GPU/compositor wait actually
+    /// happens. Same caveat as the type's own doc: `present()` is not
+    /// fenced against the GPU actually finishing, so this is "how long the
+    /// CPU was blocked handing the frame off", not the frame's true GPU
+    /// time -- still enough to separate "iris is slow building the frame"
+    /// from "iris is slow handing it to the driver".
+    pub gpu_wait_p50: Duration,
 }
 
 impl std::fmt::Display for FrameStats {
@@ -71,6 +91,13 @@ impl std::fmt::Display for FrameStats {
             self.p90.as_secs_f64() * 1000.0,
             self.p99.as_secs_f64() * 1000.0,
             self.worst.as_secs_f64() * 1000.0,
+        )?;
+        write!(
+            f,
+            " cpu_p50={:.1}ms gpu_wait_p50={:.1}ms (redraw-start-to-submit vs. \
+             submit-to-after-present)",
+            self.cpu_p50.as_secs_f64() * 1000.0,
+            self.gpu_wait_p50.as_secs_f64() * 1000.0,
         )
     }
 }
@@ -79,6 +106,7 @@ impl FrameReport {
     pub fn new() -> Self {
         Self {
             ring: Box::new([Duration::ZERO; RING_CAPACITY]),
+            submit_ring: Box::new([Duration::ZERO; RING_CAPACITY]),
             len: 0,
             pos: 0,
             total_frames: 0,
@@ -86,13 +114,27 @@ impl FrameReport {
         }
     }
 
-    /// Record one frame's elapsed wall time. O(1), no allocation.
+    /// Record one frame's elapsed wall time, with no CPU/GPU split (the
+    /// `submit_to_present` half is recorded as zero, so `cpu_p50` reads as
+    /// the whole frame and `gpu_wait_p50` as nothing -- honest for a caller
+    /// that never measured the split, rather than fabricating one). O(1),
+    /// no allocation.
     pub fn record(&mut self, elapsed: Duration) {
-        self.ring[self.pos] = elapsed;
+        self.record_split(elapsed, Duration::ZERO);
+    }
+
+    /// Record one frame's elapsed wall time, split at `queue.submit`:
+    /// `submit_to_present` is the `queue.submit()` call plus `present()`;
+    /// `total - submit_to_present` is everything before it (layout, text,
+    /// primitive building). RUST.md's I5 "Where iris's frame time goes"
+    /// CPU/GPU split, added 2026-09-05. O(1), no allocation.
+    pub fn record_split(&mut self, total: Duration, submit_to_present: Duration) {
+        self.ring[self.pos] = total;
+        self.submit_ring[self.pos] = submit_to_present;
         self.pos = (self.pos + 1) % RING_CAPACITY;
         self.len = (self.len + 1).min(RING_CAPACITY);
         self.total_frames += 1;
-        if elapsed > JANK_THRESHOLD {
+        if total > JANK_THRESHOLD {
             self.janky_frames += 1;
         }
     }
@@ -118,6 +160,21 @@ impl FrameReport {
         let mut samples: Vec<Duration> = self.ring[..self.len].to_vec();
         samples.sort_unstable();
         let pct = |p: usize| samples[(samples.len() * p / 100).min(samples.len() - 1)];
+
+        // Separate arrays rather than subtracting the two medians above:
+        // medians do not distribute over subtraction, and each needs its
+        // own sort.
+        let submit_samples: Vec<Duration> = self.submit_ring[..self.len].to_vec();
+        let cpu_samples: Vec<Duration> = self.ring[..self.len]
+            .iter()
+            .zip(self.submit_ring[..self.len].iter())
+            .map(|(&total, &submit_to_present)| total.saturating_sub(submit_to_present))
+            .collect();
+        let median = |mut v: Vec<Duration>| {
+            v.sort_unstable();
+            v[v.len() / 2]
+        };
+
         Some(FrameStats {
             total_frames: self.total_frames,
             janky_percent: 100.0 * self.janky_frames as f64 / self.total_frames as f64,
@@ -125,6 +182,8 @@ impl FrameReport {
             p90: pct(90),
             p99: pct(99),
             worst: *samples.last().expect("len > 0 checked above"),
+            cpu_p50: median(cpu_samples),
+            gpu_wait_p50: median(submit_samples),
         })
     }
 }
@@ -196,6 +255,33 @@ mod tests {
         assert_eq!(r.report().unwrap().janky_percent, 0.0);
     }
 
+    #[test]
+    fn record_without_a_split_reports_the_whole_frame_as_cpu() {
+        // A caller that never measured the split (plain `record`) should
+        // not fabricate a GPU-wait number -- it reads as zero, and the CPU
+        // half reads as the whole frame.
+        let mut r = FrameReport::new();
+        r.record(Duration::from_millis(20));
+        let stats = r.report().unwrap();
+        assert_eq!(stats.cpu_p50, Duration::from_millis(20));
+        assert_eq!(stats.gpu_wait_p50, Duration::ZERO);
+    }
+
+    #[test]
+    fn record_split_reports_each_halfs_own_median() {
+        let mut r = FrameReport::new();
+        // Three frames: total is always 30ms, but the CPU/GPU-wait split
+        // moves, so the two medians must be independent of each other and
+        // of `total`'s own median.
+        r.record_split(Duration::from_millis(30), Duration::from_millis(5));
+        r.record_split(Duration::from_millis(30), Duration::from_millis(10));
+        r.record_split(Duration::from_millis(30), Duration::from_millis(20));
+        let stats = r.report().unwrap();
+        assert_eq!(stats.p50, Duration::from_millis(30));
+        assert_eq!(stats.gpu_wait_p50, Duration::from_millis(10));
+        assert_eq!(stats.cpu_p50, Duration::from_millis(20));
+    }
+
     #[test]
     fn ring_wraps_without_growing_past_capacity() {
         let mut r = FrameReport::new();