From 888db62c8070ca71f56026437a0a305c58b03ae2 Mon Sep 17 00:00:00 2001
From: Pavol Rusnak <pavol@rusnak.io>
Date: Mon, 3 Apr 2023 12:28:49 +0200
Subject: [PATCH] Advise the kernel to preload the mapped memory

---
 llama.cpp | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/llama.cpp b/llama.cpp
index 854bb8993fbc5..dad4f9fa1fc89 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -327,13 +327,24 @@ static void *mmap_file(const char *fname, uint64_t *mm_length) {
     void *addr = MapViewOfFile(hMapping, FILE_MAP_READ, 0, 0, 0);
     CloseHandle(hMapping);
     if (!addr) return 0;
+    // Advise the kernel to preload the mapped memory
+    WIN32_MEMORY_RANGE_ENTRY range;
+    range.VirtualAddress = addr;
+    range.NumberOfBytes = (SIZE_T)length;
+    PrefetchVirtualMemory(GetCurrentProcess(), 1, &range, 0);
 #else
     int fd = open(fname, O_RDONLY);
     if (fd == -1) return 0;
     int64_t length = lseek(fd, 0, SEEK_END);
+#ifdef __linux__
+    void *addr = mmap(NULL, length, PROT_READ, MAP_SHARED | MAP_POPULATE, fd, 0);
+#else // MAP_POPULATE is only supported on Linux
     void *addr = mmap(NULL, length, PROT_READ, MAP_SHARED, fd, 0);
+#endif
     close(fd);
     if (addr == MAP_FAILED) return 0;
+    // Advise the kernel to preload the mapped memory
+    madvise(addr, length, MADV_WILLNEED);
 #endif
     *mm_length = length;
     return addr;