ggml_backend_sycl_buffer_context * ctx = ( ggml_backend_sycl_buffer_context *)buffer->context;
ggml_sycl_set_device(ctx->device);
auto stream = &(dpct::dev_mgr::instance().get_device(ctx->device).default_queue());
- SYCL_CHECK(
- CHECK_TRY_ERROR(dpct::dev_mgr::instance().get_device(ctx->device).queues_wait_and_throw()));
+ SYCL_CHECK(CHECK_TRY_ERROR(dpct::dev_mgr::instance().get_device(ctx->device).queues_wait_and_throw()));
+#ifndef _WIN32
// Note: Use host buffer to save the data from mmap(), then copy to device. It's workaround for mmap() issue on PVC GPU.
// This function will be called during load model from disk. Use memory buffer replace dynamic won't save more time and brings potential memory leak risk here.
- char* host_buf = (char*)malloc(size);
+ char * host_buf = (char *) malloc(size);
memcpy(host_buf, data, size);
- SYCL_CHECK(
- CHECK_TRY_ERROR((*stream).memcpy((char *)tensor->data + offset, host_buf, size)
- .wait()));
+ SYCL_CHECK(CHECK_TRY_ERROR((*stream).memcpy((char *) tensor->data + offset, host_buf, size).wait()));
free(host_buf);
+#else
+ SYCL_CHECK(CHECK_TRY_ERROR((*stream).memcpy((char *) tensor->data + offset, data, size).wait()));
+#endif
}
catch (sycl::exception const &exc) {
std::cerr << exc.what() << "Exception caught at file:" << __FILE__