Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
CPU pool: read the logical-processor layout when the pool is built
Niko1221e2b4464917d0
diff --git a/include/strata/kernels/cpu/pool.hpp b/include/strata/kernels/cpu/pool.hppindex 4f49a3a40..6c21d2d21 100644--- a/include/strata/kernels/cpu/pool.hpp+++ b/include/strata/kernels/cpu/pool.hpp@@ -302,6 +302,7 @@ private:int n_ = 0;bool explicit_cores_ = false;bool pinned_ = true;+ std::vector<LogicalCpuInfo> layout_; // the logical processors and their cores, read when the pool was built (the caller may be pinned later)const char* plan_limit_ = "";int plan_cores_ = 0;int plan_logical_ = 0;diff --git a/src/kernels/cpu/pool.cpp b/src/kernels/cpu/pool.cppindex bb7d24898..cdcc8d792 100644--- a/src/kernels/cpu/pool.cpp+++ b/src/kernels/cpu/pool.cpp@@ -744,6 +744,7 @@ ExpertPool::ExpertPool(int n_workers, bool pin, bool host_works, PoolAffinity af: tasks_(tasks), host_works_(host_works), affinity_(affinity), topo_(detect_cpu_topology(true, affinity)) {if (tasks < 0 || tasks > kMaxTasks) throw std::invalid_argument("expert pool tasks must be in 0..4096");pinned_ = pin;+ layout_ = logical_cpu_layout(); // now, before anything pins the caller (Linux reads the calling thread's allowed CPUs)if (const char* e = std::getenv("STRATA_POOL_SPIN_US")) // a test knob; see kSpinBeforeSleepspin_before_sleep_ = std::chrono::microseconds((std::max)(0, std::atoi(e)));// STRATA_NUMA_SPLIT, read here for the worker count (the split itself is decided below, once the count is known).@@ -762,7 +763,7 @@ ExpertPool::ExpertPool(int n_workers, bool pin, bool host_works, PoolAffinity af// --pool-cores (experimental, off by default): the person's own list of logical processors for the workers. The plan above// was made from the real topology; only the cores the workers are pinned to (and, by default, their count) come from the list.if (!pool_cores_setting().empty()) {- const PoolCoresCheck chk = check_pool_cores(pool_cores_setting(), logical_cpu_layout(), topo_.host_core);+ const PoolCoresCheck chk = check_pool_cores(pool_cores_setting(), layout_, topo_.host_core);static std::atomic<bool> told{false}; // (a throw-away pool of --pool-affinity measure builds the same list again)const bool say = !told.exchange(true);if (say)@@ -939,7 +940,7 @@ std::string ExpertPool::placement_line() const {if (!pinned_) return "CPU workers: " + std::to_string(n_) + " workers, not pinned to logical processors (the OS places them)";// a worker beyond the cores listed runs unpinned (more --pool-workers than --pool-cores entries)std::vector<int> on(topo_.worker_cores.begin(), topo_.worker_cores.begin() + (std::min)((size_t) n_, topo_.worker_cores.size()));- std::string s = describe_worker_placement(on, topo_.host_core, logical_cpu_layout(), explicit_cores_);+ std::string s = describe_worker_placement(on, topo_.host_core, layout_, explicit_cores_);if ((int) on.size() < n_) s += " (" + std::to_string(n_ - (int) on.size()) + " more workers run unpinned)";return s;}