Add a callgrind measure

README.md

@@ -195,19 +195,33 @@ note that measuring using CPU cycles alone can be problematic (e.g., CPU
 frequency changes, context switches, etc.).
 
 Several _measures_ can be configured using the `--measure` option:
-- `cycles`: the number of CPU cycles elapsed
-- `perf-counters`: a selection of common `perf` counters (CPU cycles,
-  instructions retired, cache accesses, cache misses); only available on Linux
-- `vtune`: record each phase as a VTune task for analysis; see [this help
-  documentation](docs/vtune.md) for more details
-- `noop`: no measurement is performed
+
+- `cycles`: The number of CPU cycles elapsed.
+
+- `perf-counters`: A selection of common `perf` counters (CPU cycles,
+  instructions retired, cache accesses, cache misses); only available on Linux.
+
+- `callgrind`: Uses Valgrind's Callgrind to count instructions retired and
+  simulate caches and branch prediction. Mostly deterministic and very low
+  noise. Only available on Linux and when built with `--features callgrind`.
+
+- `vtune`: Record each phase as a VTune task for analysis; see [this help
+  documentation](docs/vtune.md) for more details.
+
+- `noop`: No measurement is performed.
 
 For example, run:
 
 ```
 $ cargo run -- benchmark --measure perf-counters ...
 ```
 
+For `callgrind`, Sightglass runs benchmark children under `setarch -R valgrind`
+with a fixed cache model and forces single-threaded Wasmtime compilation with
+`RAYON_NUM_THREADS=1` so results stay stable across machines. Use the same
+Valgrind version when comparing data recorded on different machines for best
+results.
+
 ### Getting Raw JSON or CSV Results
 
 If you don't want the results to be summarized and displayed in a human-readable

crates/cli/Cargo.toml

@@ -4,6 +4,10 @@ version = "0.1.0"
 authors = ["Sightglass Project Developers"]
 edition = "2021"
 
+[features]
+default = ["callgrind"]
+callgrind = ["sightglass-recorder/callgrind"]
+
 [dependencies]
 anyhow = "1.0"
 libloading = "0.9"
@@ -24,10 +28,10 @@ csv = "1.1.6"
 regex = "1.5.4"
 vega_lite_4 = { git = "https://github.com/procyon-rs/vega_lite_4.rs" }
 minijinja = "2.10"
+tempfile = "3.2.0"
 
 [dev-dependencies]
 assert_cmd = "1.0.4"
 env_logger = "0.8.3"
 predicates = "1.0.8"
-tempfile = "3.2.0"
 scraper = "0.24"