SYCL: Avoid using with SYCL-Graph for unsupported nodes (#13587)

Currently on a CUDA backend to SYCL when running
`GGML_SYCL_DISABLE_GRAPH=0 ./bin/test-backend-ops -b SYCL0` there
are two operations that throw an exception from the blocking
waits during queue recording.

* `-o CONCAT` : Use of blocking waits on a queue that's being recorded https://github.com/ggml-org/llama.cpp/blob/master/ggml/src/ggml-sycl/concat.cpp#L185-L187
* `-o MUL_MAT_ID`: Blocking wait on a recording queue for a copy to host memory https://github.com/ggml-org/llama.cpp/blob/master/ggml/src/ggml-sycl/ggml-sycl.cpp#L3072-L3074

We've noticed that `ggml-cuda.cu` has the
[check_node_graph_compatibility_and_refresh_copy_ops](https://github.com/ggml-org/llama.cpp/blob/39e73ae0d69f882d7e29cecc6dd8f5052fca6731/ggml/src/ggml-cuda/ggml-cuda.cu#L2458-L2458)
method for checking if a graph can be used, even if enabled. I've taken a
similar approach in this PR by adding a method to `ggml-sycl.cpp` for checking
if a graph can be used for the operations even if a user has asked for it to be
enabled.

diff --git a/ggml/src/ggml-sycl/ggml-sycl.cpp b/ggml/src/ggml-sycl/ggml-sycl.cpp
index d05919781e7be5f3e459db9fe5e3234fb610a7c1..c2eb618e8914f9d7a977b65a46a81afc0d1302c5 100644 (file)
--- a/ggml/src/ggml-sycl/ggml-sycl.cpp
+++ b/ggml/src/ggml-sycl/ggml-sycl.cpp
@@ -3809,11 +3809,43 @@ static void ggml_backend_sycl_graph_compute_impl(ggml_backend_sycl_context * syc
     }
 }
 
+#ifdef GGML_SYCL_GRAPH
+static bool check_graph_compatibility(ggml_cgraph * cgraph) {
+    if (ggml_sycl_info().device_count > 1) {
+        // A sycl_ex::command_graph object can only be created for a single device
+        GGML_LOG_INFO("%s: disabling SYCL graphs due to multiple devices\n", __func__);
+        return false;
+    }
+
+    for (int i = 0; i < cgraph->n_nodes; i++) {
+        const ggml_op node_op = cgraph->nodes[i]->op;
+        switch (node_op) {
+            default:
+                break;
+            case GGML_OP_CONCAT:
+                // ggml_sycl_op_concat() does a blocking host wait after memcpy operations,
+                // but wait() can't be called on the events returned by a queue recording
+                // to a graph.
+                [[fallthrough]];
+            case GGML_OP_MUL_MAT_ID:
+                // ggml_sycl_mul_mat_id() does a blocking host wait on the sycl queue after
+                // submitting a memcpy operation, but wait() can't be called on a queue that
+                // is recording to a graph.
+                GGML_LOG_INFO("%s: disabling SYCL graphs due to unsupported node type %s\n", __func__,
+                              ggml_op_name(node_op));
+                return false;
+        }
+    }
+    return true;
+}
+#endif
+
 static ggml_status ggml_backend_sycl_graph_compute(ggml_backend_t backend, ggml_cgraph * cgraph) {
     auto * sycl_ctx = static_cast<ggml_backend_sycl_context *>(backend->context);
 
 #ifdef GGML_SYCL_GRAPH
-    if (!g_ggml_sycl_disable_graph) {
+    bool use_sycl_graph = !g_ggml_sycl_disable_graph && check_graph_compatibility(cgraph);
+    if (use_sycl_graph) {
         const bool graph_support = dpct::get_device(sycl_ctx->device).has(sycl::aspect::ext_oneapi_limited_graph);
         if (!graph_support) {
             GGML_SYCL_DEBUG("[SYCL-GRAPH] can not use graphs on device:%d\n", sycl_ctx->device);