diff options
Diffstat (limited to 'ggml.c')
| -rw-r--r-- | ggml.c | 76 |
1 files changed, 65 insertions, 11 deletions
@@ -1,5 +1,5 @@ -// Defines CLOCK_MONOTONIC on Linux -#define _POSIX_C_SOURCE 199309L +// Defines CLOCK_MONOTONIC and asprintf on Linux +#define _GNU_SOURCE #include "ggml.h" @@ -10,6 +10,7 @@ #endif #include <assert.h> +#include <errno.h> #include <time.h> #include <math.h> #include <stdlib.h> @@ -31,7 +32,6 @@ #else // ref: https://github.com/ggerganov/whisper.cpp/issues/168 #include <windows.h> -#include <errno.h> #endif typedef volatile LONG atomic_int; @@ -83,6 +83,17 @@ typedef void* thread_ret_t; #define static_assert(cond, msg) _Static_assert(cond, msg) #endif +#define GGML_MLOCK_SUPPORT 0 + +#ifdef __has_include + #if __has_include(<sys/mman.h>) + #undef GGML_MLOCK_SUPPORT + #define GGML_MLOCK_SUPPORT 1 + #include <sys/mman.h> + #endif +#endif + + /*#define GGML_PERF*/ #define GGML_DEBUG 0 #define GGML_GELU_FP16 @@ -2344,6 +2355,7 @@ struct ggml_context { size_t mem_size; void * mem_buffer; bool mem_buffer_owned; + bool mem_buffer_mlocked; int n_objects; @@ -2619,16 +2631,19 @@ struct ggml_context * ggml_init(struct ggml_init_params params) { } *ctx = (struct ggml_context) { - /*.mem_size =*/ params.mem_size, - /*.mem_buffer =*/ params.mem_buffer ? params.mem_buffer : malloc(params.mem_size), - /*.mem_buffer_owned =*/ params.mem_buffer ? false : true, - /*.n_objects =*/ 0, - /*.objects_begin =*/ NULL, - /*.objects_end =*/ NULL, - /*.scratch =*/ { 0, 0, NULL, }, - /*.scratch_save =*/ { 0, 0, NULL, }, + /*.mem_size =*/ params.mem_size, + /*.mem_buffer =*/ params.mem_buffer ? params.mem_buffer : malloc(params.mem_size), + /*.mem_buffer_owned =*/ params.mem_buffer ? false : true, + /*.mem_buffer_mlocked =*/ false, + /*.n_objects =*/ 0, + /*.objects_begin =*/ NULL, + /*.objects_end =*/ NULL, + /*.scratch =*/ { 0, 0, NULL, }, + /*.scratch_save =*/ { 0, 0, NULL, }, }; + GGML_ASSERT(ctx->mem_buffer != NULL); // check for allocation failure + ggml_assert_aligned(ctx->mem_buffer); GGML_PRINT_DEBUG("%s: context initialized\n", __func__); @@ -2651,6 +2666,14 @@ void ggml_free(struct ggml_context * ctx) { GGML_PRINT_DEBUG("%s: context %d with %d objects has been freed. memory used = %zu\n", __func__, i, ctx->n_objects, ctx->objects_end->offs + ctx->objects_end->size); +#if GGML_MLOCK_SUPPORT + if (ctx->mem_buffer_mlocked) { + if (munlock(ctx->mem_buffer, ctx->mem_size)) { + fprintf(stderr, "%s: failed to munlock buffer: %s\n", __func__, strerror(errno)); + } + } +#endif + if (ctx->mem_buffer_owned) { free(ctx->mem_buffer); } @@ -2679,6 +2702,37 @@ size_t ggml_set_scratch(struct ggml_context * ctx, struct ggml_scratch scratch) return result; } +bool ggml_mlock_supported(void) { + return GGML_MLOCK_SUPPORT; +} + +#if GGML_MLOCK_SUPPORT +#ifdef __APPLE__ + #define MLOCK_SUGGESTION "Try increasing the sysctl values 'vm.user_wire_limit' and 'vm.global_user_wire_limit' and/or\n" \ + "decreasing 'vm.global_no_user_wire_amount'. Also try increasing RLIMIT_MLOCK (ulimit -l)." +#else + #define MLOCK_SUGGESTION "Try increasing RLIMIT_MLOCK (ulimit -l)." +#endif +bool ggml_mlock(struct ggml_context * ctx, char ** err_p) { + if (ctx->mem_buffer_mlocked) { + return true; + } + if (mlock(ctx->mem_buffer, ctx->mem_size)) { + int ret = asprintf(err_p, "failed to mlock %zu-byte buffer: %s\n" MLOCK_SUGGESTION, + ctx->mem_size, strerror(errno)); + GGML_ASSERT(ret >= 0); + return false; + } + ctx->mem_buffer_mlocked = true; + return true; +} +#else // GGML_MLOCK_SUPPORT +bool ggml_mlock(struct ggml_context * ctx, char ** err_p) { + *err_p = strdup("can't mlock because it's not supported on this system"); + return false; +} +#endif // GGML_MLOCK_SUPPORT + //////////////////////////////////////////////////////////////////////////////// struct ggml_tensor * ggml_new_tensor_impl( |