Auto merge of #139011 - Zoxc:no-rayon-iters, r=oli-obk

Remove the use of Rayon iterators

This removes the use of Rayon iterators and the use of the `rustc-rayon` crate.  `rustc-rayon-core` is still used however.

In parallel loops, instead of a Rayon iterator a serial iterator are used to collect items into a `Vec` and we use a parallel loop over its elements using the new `par_slice` function which is built on `rustc-rayon-core`'s `join`.

This change makes it easier to bring `rustc-rayon-core` in-tree.

Tests using 7 threads:
<table><tr><td rowspan="2">Benchmark</td><td colspan="1"><b>Before</b></th><td colspan="2"><b>After</b></th><td colspan="1"><b>Before</b></th><td colspan="2"><b>After</b></th><td colspan="1"><b>Before</b></th><td colspan="2"><b>After</b></th></tr><tr><td align="right">Time</td><td align="right">Time</td><td align="right">%</th><td align="right">Physical Memory</td><td align="right">Physical Memory</td><td align="right">%</th><td align="right">Committed Memory</td><td align="right">Committed Memory</td><td align="right">%</th></tr><tr><td>🟣 <b>clap</b>:check</td><td align="right">0.4827s</td><td align="right">0.4828s</td><td align="right"> 0.02%</td><td align="right">201.23 MiB</td><td align="right">201.31 MiB</td><td align="right"> 0.04%</td><td align="right">279.03 MiB</td><td align="right">279.46 MiB</td><td align="right"> 0.15%</td></tr><tr><td>🟣 <b>hyper</b>:check</td><td align="right">0.1443s</td><td align="right">0.1401s</td><td align="right">💚  -2.91%</td><td align="right">126.42 MiB</td><td align="right">126.70 MiB</td><td align="right"> 0.22%</td><td align="right">199.79 MiB</td><td align="right">199.99 MiB</td><td align="right"> 0.10%</td></tr><tr><td>🟣 <b>regex</b>:check</td><td align="right">0.3252s</td><td align="right">0.3065s</td><td align="right">💚  -5.78%</td><td align="right">161.87 MiB</td><td align="right">161.78 MiB</td><td align="right"> -0.05%</td><td align="right">229.59 MiB</td><td align="right">230.23 MiB</td><td align="right"> 0.28%</td></tr><tr><td>🟣 <b>syn</b>:check</td><td align="right">0.5845s</td><td align="right">0.5876s</td><td align="right"> 0.53%</td><td align="right">197.01 MiB</td><td align="right">196.89 MiB</td><td align="right"> -0.06%</td><td align="right">267.62 MiB</td><td align="right">267.47 MiB</td><td align="right"> -0.06%</td></tr><tr><td>Total</td><td align="right">1.5367s</td><td align="right">1.5169s</td><td align="right">💚  -1.29%</td><td align="right">686.53 MiB</td><td align="right">686.68 MiB</td><td align="right"> 0.02%</td><td align="right">976.04 MiB</td><td align="right">977.14 MiB</td><td align="right"> 0.11%</td></tr><tr><td>Summary</td><td align="right">1.0000s</td><td align="right">0.9796s</td><td align="right">💚  -2.04%</td><td align="right">1 byte</td><td align="right">1.00 bytes</td><td align="right"> 0.04%</td><td align="right">1 byte</td><td align="right">1.00 bytes</td><td align="right"> 0.12%</td></tr></table>

<table><tr><td rowspan="2">Benchmark</td><td colspan="1"><b>Before</b></th><td colspan="2"><b>After</b></th><td colspan="1"><b>Before</b></th><td colspan="2"><b>After</b></th><td colspan="1"><b>Before</b></th><td colspan="2"><b>After</b></th></tr><tr><td align="right">Time</td><td align="right">Time</td><td align="right">%</th><td align="right">Physical Memory</td><td align="right">Physical Memory</td><td align="right">%</th><td align="right">Committed Memory</td><td align="right">Committed Memory</td><td align="right">%</th></tr><tr><td>🟠 <b>clap</b>:debug</td><td align="right">1.6371s</td><td align="right">1.6529s</td><td align="right"> 0.96%</td><td align="right">395.58 MiB</td><td align="right">396.21 MiB</td><td align="right"> 0.16%</td><td align="right">460.98 MiB</td><td align="right">461.52 MiB</td><td align="right"> 0.12%</td></tr><tr><td>🟠 <b>hyper</b>:debug</td><td align="right">0.3248s</td><td align="right">0.3210s</td><td align="right">💚  -1.16%</td><td align="right">155.16 MiB</td><td align="right">155.19 MiB</td><td align="right"> 0.02%</td><td align="right">219.21 MiB</td><td align="right">219.30 MiB</td><td align="right"> 0.04%</td></tr><tr><td>🟠 <b>regex</b>:debug</td><td align="right">1.0148s</td><td align="right">0.9929s</td><td align="right">💚  -2.16%</td><td align="right">297.96 MiB</td><td align="right">295.07 MiB</td><td align="right"> -0.97%</td><td align="right">354.53 MiB</td><td align="right">351.58 MiB</td><td align="right"> -0.83%</td></tr><tr><td>🟠 <b>syn</b>:debug</td><td align="right">1.3614s</td><td align="right">1.3717s</td><td align="right"> 0.76%</td><td align="right">319.10 MiB</td><td align="right">321.19 MiB</td><td align="right"> 0.65%</td><td align="right">378.90 MiB</td><td align="right">381.27 MiB</td><td align="right"> 0.62%</td></tr><tr><td>Total</td><td align="right">4.3381s</td><td align="right">4.3386s</td><td align="right"> 0.01%</td><td align="right">1.14 GiB</td><td align="right">1.14 GiB</td><td align="right"> -0.01%</td><td align="right">1.38 GiB</td><td align="right">1.38 GiB</td><td align="right"> 0.00%</td></tr><tr><td>Summary</td><td align="right">1.0000s</td><td align="right">0.9960s</td><td align="right"> -0.40%</td><td align="right">1 byte</td><td align="right">1.00 bytes</td><td align="right"> -0.03%</td><td align="right">1 byte</td><td align="right">1.00 bytes</td><td align="right"> -0.01%</td></tr></table>

1 files changed, 15 insertions, 14 deletions

diff --git a/compiler/rustc_codegen_cranelift/src/driver/aot.rs b/compiler/rustc_codegen_cranelift/src/driver/aot.rs
index 444dc441286..b1bc7e1707e 100644
--- a/compiler/rustc_codegen_cranelift/src/driver/aot.rs
+++ b/compiler/rustc_codegen_cranelift/src/driver/aot.rs
@@ -728,26 +728,27 @@ pub(crate) fn run_aot(
 
     let concurrency_limiter = IntoDynSyncSend(ConcurrencyLimiter::new(todo_cgus.len()));
 
-    let modules = tcx.sess.time("codegen mono items", || {
-        let mut modules: Vec<_> = par_map(todo_cgus, |(_, cgu)| {
-            let dep_node = cgu.codegen_dep_node(tcx);
-            tcx.dep_graph
-                .with_task(
+    let modules: Vec<_> =
+        tcx.sess.time("codegen mono items", || {
+            let modules: Vec<_> = par_map(todo_cgus, |(_, cgu)| {
+                let dep_node = cgu.codegen_dep_node(tcx);
+                let (module, _) = tcx.dep_graph.with_task(
                     dep_node,
                     tcx,
                     (global_asm_config.clone(), cgu.name(), concurrency_limiter.acquire(tcx.dcx())),
                     module_codegen,
                     Some(rustc_middle::dep_graph::hash_result),
-                )
-                .0
-        });
-        modules.extend(
-            done_cgus
+                );
+                IntoDynSyncSend(module)
+            });
+            modules
                 .into_iter()
-                .map(|(_, cgu)| OngoingModuleCodegen::Sync(reuse_workproduct_for_cgu(tcx, cgu))),
-        );
-        modules
-    });
+                .map(|module| module.0)
+                .chain(done_cgus.into_iter().map(|(_, cgu)| {
+                    OngoingModuleCodegen::Sync(reuse_workproduct_for_cgu(tcx, cgu))
+                }))
+                .collect()
+        });
 
     let allocator_module = emit_allocator_module(tcx);