test(runner-shared): search artifacts of up to 100M events in the module event bench

With frames decoded in parallel, CI-sized artifacts are fast enough to
benchmark again: add the 10M and 100M event sizes the streamed decoder was
too slow for. The 100M artifact with stacks is about 5 GB on disk and is
mapped, not held in memory.

Author: not-matthias

crates/runner-shared/benches/memtrack_reader.rs

@@ -19,9 +19,9 @@ fn main() {
     divan::main();
 }
 
-/// Artifact sizes in events. CI-sized artifacts take minutes per case with the
-/// streamed decoder under the simulation instrument.
-const SIZES: &[usize] = &[1_000_000];
+/// Artifact sizes in events, up to a CI-sized artifact with enough frames to
+/// show how the parallel frame scan scales.
+const SIZES: &[usize] = &[1_000_000, 10_000_000, 100_000_000];
 
 /// Under the simulation and memory instruments, generating and searching
 /// larger artifacts outlasts the CI job, so these modes only search the