diff --git a/mlir/lib/Transforms/Inliner.cpp b/mlir/lib/Transforms/Inliner.cpp
--- a/mlir/lib/Transforms/Inliner.cpp
+++ b/mlir/lib/Transforms/Inliner.cpp
@@ -663,7 +663,7 @@
 
   // Optimize each of the nodes within the SCC in parallel.
   if (failed(optimizeSCCAsync(nodesToVisit, context)))
-      return failure();
+    return failure();
 
   // Recompute the uses held by each of the nodes.
   for (CallGraphNode *node : nodesToVisit)
@@ -678,7 +678,11 @@
   // parallel. Note: The number of pass managers here needs to remain constant
   // to prevent issues with pass instrumentations that rely on having the same
   // pass manager for the main thread.
-  size_t numThreads = llvm::hardware_concurrency().compute_thread_count();
+  // Note that this lining up is dependent on failableParallelForEach using
+  // the context thread pool under the covers (the thread count must be
+  // consistent).
+  llvm::ThreadPool &threadPool = ctx->getThreadPool();
+  size_t numThreads = threadPool.getThreadCount();
   if (opPipelines.size() < numThreads) {
     // Reserve before resizing so that we can use a reference to the first
     // element.
@@ -700,6 +704,8 @@
       bool expectedInactive = false;
       return isActive.compare_exchange_strong(expectedInactive, true);
     });
+    assert(it != activePMs.end() &&
+           "could not find active pass manager for thread");
     unsigned pmIndex = it - activePMs.begin();
 
     // Optimize this callable node.