From 567d071c117184cc600102a4f92e43df5a8f0565 Mon Sep 17 00:00:00 2001
From: Tamim Ehsan <tamimehsan99@gmail.com>
Date: Wed, 26 Aug 2026 20:11:53 +0800
Subject: [PATCH] back the hnsw index arrays with transparent huge pages

---
 include/rabitqlib/index/hnsw/hnsw.hpp | 6 +++---
 include/rabitqlib/utils/memory.hpp    | 8 ++++++++
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/include/rabitqlib/index/hnsw/hnsw.hpp b/include/rabitqlib/index/hnsw/hnsw.hpp
index 7c8eaf4..71b59e6 100644
--- a/include/rabitqlib/index/hnsw/hnsw.hpp
+++ b/include/rabitqlib/index/hnsw/hnsw.hpp
@@ -423,7 +423,7 @@ inline HierarchicalNSW::HierarchicalNSW(
         offsetExData_ + size_ex_data_;  // (# of edges + edges) + (cluster_id) + (external
                                         // label) + (BinData) + (ExData)
     data_level0_memory_ =
-        reinterpret_cast<char*>(malloc(max_elements_ * size_data_per_element_));
+        memory::huge_page_allocate<char>(max_elements_ * size_data_per_element_);
     if (data_level0_memory_ == nullptr) {
         throw std::runtime_error("Not enough memory");
     }
@@ -549,7 +549,7 @@ inline void HierarchicalNSW::load(const char* filename) {
     input.read(reinterpret_cast<char*>(&ef_construction_), sizeof(size_t));
 
     const size_t centroids_bytes = num_cluster_ * padded_dim_ * sizeof(float);
-    centroids_memory_ = reinterpret_cast<char*>(malloc(centroids_bytes));
+    centroids_memory_ = memory::huge_page_allocate<char>(centroids_bytes);
     if (centroids_memory_ == nullptr) {
         throw std::runtime_error("Not enough memory: loadIndex failed to allocate centroids"
         );
@@ -561,7 +561,7 @@ inline void HierarchicalNSW::load(const char* filename) {
     );
 
     data_level0_memory_ =
-        reinterpret_cast<char*>(malloc(max_elements_ * size_data_per_element_));
+        memory::huge_page_allocate<char>(max_elements_ * size_data_per_element_);
 
     input.read(
         data_level0_memory_,
diff --git a/include/rabitqlib/utils/memory.hpp b/include/rabitqlib/utils/memory.hpp
index fb93ee1..8dced55 100644
--- a/include/rabitqlib/utils/memory.hpp
+++ b/include/rabitqlib/utils/memory.hpp
@@ -86,6 +86,14 @@ inline T* align_allocate(size_t nbytes) {
     return static_cast<T*>(ptr);
 }
 
+inline constexpr size_t kHugePageSize = 2UL << 20;
+
+// Allocate a large buffer backed by transparent huge pages.
+template <typename T>
+inline T* huge_page_allocate(size_t nbytes) {
+    return align_allocate<kHugePageSize, T, true>(nbytes);
+}
+
 static inline void prefetch_l1(const void* addr) {
 #if defined(__SSE2__)
     _mm_prefetch(addr, _MM_HINT_T0);