ggml : add GGML_NO_REALLOC option to disable reallocations in ggml-alloc

Enabled in ggml-ci for testing.

Author: slaren

ci/run.sh

@@ -45,7 +45,7 @@ sd=`dirname $0`
 cd $sd/../
 SRC=`pwd`
 
-CMAKE_EXTRA="-DLLAMA_FATAL_WARNINGS=ON -DLLAMA_CURL=ON"
+CMAKE_EXTRA="-DLLAMA_FATAL_WARNINGS=ON -DLLAMA_CURL=ON -DGGML_NO_REALLOC=ON"
 
 if [ ! -z ${GG_BUILD_METAL} ]; then
     CMAKE_EXTRA="${CMAKE_EXTRA} -DGGML_METAL=ON"

ggml/CMakeLists.txt

@@ -182,6 +182,7 @@ endif()
 # ggml core
 set(GGML_SCHED_MAX_COPIES  "4" CACHE STRING "ggml: max input copies for pipeline parallelism")
 option(GGML_CPU                             "ggml: enable CPU backend"                        ON)
+option(GGML_NO_REALLOC                      "ggml: disallow reallocations in ggml-alloc (for debugging)" OFF)
 
 # 3rd party libs / backends
 option(GGML_ACCELERATE                      "ggml: enable Accelerate framework"               ON)

ggml/src/CMakeLists.txt

@@ -221,6 +221,10 @@ if (GGML_BACKEND_DL)
     target_compile_definitions(ggml-base PUBLIC GGML_BACKEND_DL)
 endif()
 
+if (GGML_NO_REALLOC)
+    target_compile_definitions(ggml-base PUBLIC GGML_NO_REALLOC)
+endif()
+
 add_library(ggml
             ggml-backend-reg.cpp)
 add_library(ggml::ggml ALIAS ggml)

ggml/src/ggml-alloc.c

@@ -921,8 +921,23 @@ bool ggml_gallocr_reserve_n(ggml_gallocr_t galloc, struct ggml_cgraph * graph, c
         }
         if (realloc) {
 #ifndef NDEBUG
-            size_t cur_size = galloc->buffers[i] ? ggml_vbuffer_size(galloc->buffers[i]) : 0;
-            GGML_LOG_DEBUG("%s: reallocating %s buffer from size %.02f MiB to %.02f MiB\n", __func__, ggml_backend_buft_name(galloc->bufts[i]), cur_size / 1024.0 / 1024.0, new_size / 1024.0 / 1024.0);
+            {
+                size_t cur_size = galloc->buffers[i] ? ggml_vbuffer_size(galloc->buffers[i]) : 0;
+                if (cur_size > 0) {
+                    GGML_LOG_DEBUG("%s: reallocating %s buffer from size %.02f MiB to %.02f MiB\n",
+                        __func__, ggml_backend_buft_name(galloc->bufts[i]),
+                        cur_size / 1024.0 / 1024.0, new_size / 1024.0 / 1024.0);
+                }
+            }
+#endif
+
+#ifdef GGML_NO_REALLOC
+            if (galloc->buffers[i] != NULL) {
+                size_t cur_size = galloc->buffers[i] ? ggml_vbuffer_size(galloc->buffers[i]) : 0;
+                GGML_ABORT("%s: reallocating %s buffer from size %.02f MiB to %.02f MiB not allowed with GGML_NO_REALLOC\n",
+                    __func__, ggml_backend_buft_name(galloc->bufts[i]),
+                    cur_size / 1024.0 / 1024.0, new_size / 1024.0 / 1024.0);
+            }
 #endif
 
             ggml_vbuffer_free(galloc->buffers[i]);

tests/CMakeLists.txt

@@ -196,7 +196,7 @@ if (NOT WIN32)
     llama_build_and_test(test-arg-parser.cpp)
 endif()
 
-if (NOT LLAMA_SANITIZE_ADDRESS)
+if (NOT LLAMA_SANITIZE_ADDRESS AND NOT GGML_NO_REALLOC)
   # TODO: repair known memory leaks
   llama_build_and_test(test-opt.cpp)
 endif()

tests/test-alloc.cpp

@@ -603,6 +603,8 @@ int main() {
     run("test_prefer_already_allocated_memory", test_prefer_already_allocated_memory);
     run("test_multiple_buffer_types", test_multiple_buffer_types);
     run("test_buffer_size_zero", test_buffer_size_zero);
+#ifndef GGML_NO_REALLOC
     run("test_reallocation", test_reallocation);
+#endif
     return 0;
 }