feat: embed ggml-metal.metal

CMakeLists.txt

@@ -294,11 +294,18 @@ if (LLAMA_CUBLAS)
 endif()
 
 if (LLAMA_METAL)
+    add_executable(embedfile embedfile.c)
+
+    add_custom_command(
+      OUTPUT ggml_metal_file.c
+      COMMAND embedfile ggml_metal_file bin/ggml-metal.metal
+      DEPENDS ggml-metal.metal)
+
     find_library(FOUNDATION_LIBRARY         Foundation              REQUIRED)
     find_library(METAL_FRAMEWORK            Metal                   REQUIRED)
     find_library(METALKIT_FRAMEWORK         MetalKit                REQUIRED)
 
-    set(GGML_SOURCES_METAL ggml-metal.m ggml-metal.h)
+    set(GGML_SOURCES_METAL ggml_metal_file.c ggml-metal.m ggml-metal.h)
 
     add_compile_definitions(GGML_USE_METAL)
     #add_compile_definitions(GGML_METAL_NDEBUG)

embedfile.c

@@ -0,0 +1,52 @@
+#include <stdlib.h>
+#include <stdio.h>
+
+FILE* open_or_exit(const char* fname, const char* mode)
+{
+  FILE* f = fopen(fname, mode);
+  if (f == NULL) {
+    perror(fname);
+    exit(EXIT_FAILURE);
+  }
+  return f;
+}
+
+int main(int argc, char** argv)
+{
+  if (argc < 3) {
+    fprintf(stderr, "USAGE: %s {sym} {rsrc}\n\n"
+        "  Creates {sym}.c from the contents of {rsrc}\n",
+        argv[0]);
+    return EXIT_FAILURE;
+  }
+
+  const char* sym = argv[1];
+  FILE* in = open_or_exit(argv[2], "r");
+
+  char symfile[256];
+  snprintf(symfile, sizeof(symfile), "%s.c", sym);
+
+  FILE* out = open_or_exit(symfile,"w");
+  fprintf(out, "#include <stdlib.h>\n");
+  fprintf(out, "const char %s[] = {\n", sym);
+
+  unsigned char buf[256];
+  size_t nread = 0;
+  size_t linecount = 0;
+  do {
+    nread = fread(buf, 1, sizeof(buf), in);
+    size_t i;
+    for (i=0; i < nread; i++) {
+      fprintf(out, "0x%02x, ", buf[i]);
+      if (++linecount == 10) { fprintf(out, "\n"); linecount = 0; }
+    }
+  } while (nread > 0);
+  if (linecount > 0) fprintf(out, "\n");
+  fprintf(out, "};\n");
+  fprintf(out, "const size_t %s_len = sizeof(%s);\n\n",sym,sym);
+
+  fclose(in);
+  fclose(out);
+
+  return EXIT_SUCCESS;
+}

ggml-metal.m

@@ -102,6 +102,9 @@ struct ggml_metal_context {
 #undef GGML_METAL_DECL_KERNEL
 };
 
+const char ggml_metal_file[];
+const size_t ggml_metal_file_len;
+
 // MSL code
 // TODO: move the contents here when ready
 //       for now it is easier to work in a separate file
@@ -140,7 +143,8 @@ struct ggml_metal_context * ggml_metal_init(int n_cb) {
 
     ctx->d_queue = dispatch_queue_create("llama.cpp", DISPATCH_QUEUE_CONCURRENT);
 
-#if 0
+#if 1
+    NSString * const msl_library_source = [[NSString alloc] initWithBytes: ggml_metal_file length: ggml_metal_file_len encoding: NSASCIIStringEncoding];
     // compile from source string and show compile log
     {
         NSError * error = nil;
@@ -151,6 +155,7 @@ struct ggml_metal_context * ggml_metal_init(int n_cb) {
             return NULL;
         }
     }
+    [msl_library_source release];
 #else
     UNUSED(msl_library_source);