feat(nightly): execution becomes faster

.github/workflows/benchmark-call.yml

@@ -107,7 +107,7 @@ on:
 env:
   S3_METRICS_PATH: s3://openvm-public-data-sandbox-us-east-1/benchmark/github/metrics
   S3_FLAMEGRAPHS_PATH: s3://openvm-public-data-sandbox-us-east-1/benchmark/github/flamegraphs
-  FEATURE_FLAGS: "metrics,parallel,nightly-features"
+  FEATURE_FLAGS: "metrics,parallel,nightly-features,tco"
   INPUT_ARGS: ""
   CARGO_NET_GIT_FETCH_WITH_CLI: "true"
 

.github/workflows/benchmarks-execute.yml

@@ -2,8 +2,7 @@ name: "Execution benchmarks"
 
 on:
   push:
-    # TODO(ayush): remove after feat/new-execution is merged
-    branches: ["main", "feat/new-execution"]
+    branches: ["main"]
   pull_request:
     types: [opened, synchronize, reopened, labeled]
     branches: ["**"]
@@ -28,6 +27,7 @@ env:
   CARGO_TERM_COLOR: always
   S3_FIXTURES_PATH: s3://openvm-public-data-sandbox-us-east-1/benchmark/fixtures
   JEMALLOC_SYS_WITH_MALLOC_CONF: "retain:true,background_thread:true,metadata_thp:always,thp:always,dirty_decay_ms:10000,muzzy_decay_ms:10000,abort_conf:true"
+  TOOLCHAIN: "+nightly-2025-08-19"
 
 jobs:
   codspeed-walltime-benchmarks:
@@ -66,12 +66,12 @@ jobs:
 
       - name: Build benchmarks
         working-directory: benchmarks/execute
-        run: cargo codspeed build --profile maxperf
+        run: cargo $TOOLCHAIN codspeed build --profile maxperf --features tco
       - name: Run benchmarks
         uses: CodSpeedHQ/action@v3
         with:
           working-directory: benchmarks/execute
-          run: cargo codspeed run
+          run: cargo $TOOLCHAIN codspeed run
           token: ${{ secrets.CODSPEED_TOKEN }}
 
   codspeed-instrumentation-benchmarks:
@@ -111,10 +111,10 @@ jobs:
 
       - name: Build benchmarks
         working-directory: benchmarks/execute
-        run: cargo codspeed build
+        run: cargo $TOOLCHAIN codspeed build --features tco
       - name: Run benchmarks
         uses: CodSpeedHQ/action@v3
         with:
           working-directory: benchmarks/execute
-          run: cargo codspeed run
+          run: cargo $TOOLCHAIN codspeed run
           token: ${{ secrets.CODSPEED_TOKEN }}

benchmarks/execute/Cargo.toml

@@ -46,6 +46,7 @@ divan = { package = "codspeed-divan-compat", version = "3.0.2" }
 
 [features]
 default = ["jemalloc"]
+tco = ["openvm-sdk/tco"]
 mimalloc = ["openvm-circuit/mimalloc"]
 jemalloc = ["openvm-circuit/jemalloc"]
 jemalloc-prof = ["openvm-circuit/jemalloc-prof"]

benchmarks/prove/Cargo.toml

@@ -33,8 +33,9 @@ metrics.workspace = true
 [dev-dependencies]
 
 [features]
-default = ["parallel", "jemalloc", "metrics", "evm"]
+default = ["parallel", "jemalloc", "metrics"]
 metrics = ["openvm-sdk/metrics"]
+tco = ["openvm-sdk/tco"]
 perf-metrics = ["openvm-sdk/perf-metrics", "metrics"]
 stark-debug = ["openvm-sdk/stark-debug"]
 # runs leaf aggregation benchmarks:

ci/scripts/bench.py

@@ -15,9 +15,12 @@ def run_cargo_command(
     kzg_params_dir,
     profile="release"
 ):
+    toolchain = "+1.86"
+    if "tco" in feature_flags:
+        toolchain = "+nightly-2025-08-19"
     # Command to run (for best performance but slower builds, use --profile maxperf)
     command = [
-        "cargo", "run", "--no-default-features", "-p", "openvm-benchmarks-prove", "--bin", bin_name, "--profile", profile, "--features", ",".join(feature_flags), "--"
+        "cargo", toolchain, "run", "--no-default-features", "-p", "openvm-benchmarks-prove", "--bin", bin_name, "--profile", profile, "--features", ",".join(feature_flags), "--"
     ]
 
     if app_log_blowup is not None:

crates/cli/Cargo.toml

@@ -45,6 +45,7 @@ default = ["parallel", "jemalloc", "evm-verify", "metrics"]
 evm-prove = ["openvm-sdk/evm-prove"]
 evm-verify = ["evm-prove", "openvm-sdk/evm-verify"]
 metrics = ["openvm-sdk/metrics"]
+tco = ["openvm-sdk/tco"]
 # for guest profiling:
 perf-metrics = ["openvm-sdk/perf-metrics", "metrics"]
 # performance features:

crates/cli/src/lib.rs

@@ -1,3 +1,6 @@
+#![cfg_attr(feature = "tco", allow(incomplete_features))]
+#![cfg_attr(feature = "tco", feature(explicit_tail_calls))]
+
 pub mod commands;
 pub mod default;
 pub mod input;

crates/sdk/Cargo.toml

@@ -79,6 +79,17 @@ metrics = [
     "openvm-native-recursion/metrics",
     "openvm-native-compiler/metrics",
 ]
+tco = [
+    "openvm-circuit/tco",
+    "openvm-rv32im-circuit/tco",
+    "openvm-native-circuit/tco",
+    "openvm-sha256-circuit/tco",
+    "openvm-keccak256-circuit/tco",
+    "openvm-bigint-circuit/tco",
+    "openvm-algebra-circuit/tco",
+    "openvm-ecc-circuit/tco",
+    "openvm-pairing-circuit/tco"
+]
 # for guest profiling:
 perf-metrics = ["openvm-circuit/perf-metrics", "openvm-transpiler/function-span"]
 # turns on stark-backend debugger in all proofs

crates/sdk/src/lib.rs

@@ -1,3 +1,5 @@
+#![cfg_attr(feature = "tco", allow(incomplete_features))]
+#![cfg_attr(feature = "tco", feature(explicit_tail_calls))]
 use std::{
     borrow::Borrow,
     fs::read,

crates/vm/Cargo.toml

@@ -68,6 +68,9 @@ basic-memory = []
 # turns on stark-backend debugger in all proofs
 stark-debug = []
 test-utils = ["openvm-stark-sdk"]
+# Tail call optimizations. This requires nightly for the `become` keyword (https://github.com/rust-lang/rust/pull/144232).
+# However tail call elimination is still an incomplete feature in Rust, so the `tco` feature remains experimental until then.
+tco = ["openvm-circuit-derive/tco"]
 # performance features:
 mimalloc = ["openvm-stark-backend/mimalloc"]
 jemalloc = ["openvm-stark-backend/jemalloc"]

crates/vm/derive/Cargo.toml

@@ -10,7 +10,10 @@ license.workspace = true
 proc-macro = true
 
 [dependencies]
-syn = { version = "2.0", features = ["parsing"] }
+syn = { version = "2.0", features = ["parsing", "full"] }
 quote = "1.0"
 proc-macro2 = "1.0"
 itertools = { workspace = true }
+
+[features]
+tco = []