diff mbox series

[v1,24/34] ml/cnxk: update internal info for TVM model

Message ID 20230830155927.3566-25-syalavarthi@marvell.com (mailing list archive)
State Superseded, archived
Delegated to: Thomas Monjalon
Headers
Series Implemenation of revised ml/cnxk driver |

Checks

Context Check Description
ci/checkpatch success coding style OK

Commit Message

Srikanth Yalavarthi Aug. 30, 2023, 3:59 p.m. UTC 
  Enabled updating internal IO info structures for TVM model.
Compute static fields related to the model I/O.

Signed-off-by: Srikanth Yalavarthi <syalavarthi@marvell.com>
---
 drivers/ml/cnxk/mvtvm_ml_model.c | 105 +++++++++++++++++++++++++++++++
 drivers/ml/cnxk/mvtvm_ml_model.h |   1 +
 drivers/ml/cnxk/mvtvm_ml_ops.c   |   3 +
 3 files changed, 109 insertions(+)
diff mbox series

Patch

diff --git a/drivers/ml/cnxk/mvtvm_ml_model.c b/drivers/ml/cnxk/mvtvm_ml_model.c
index 425a682209f..86f465a645f 100644
--- a/drivers/ml/cnxk/mvtvm_ml_model.c
+++ b/drivers/ml/cnxk/mvtvm_ml_model.c
@@ -7,10 +7,14 @@ 
 
 #include <rte_mldev.h>
 
+#include <mldev_utils.h>
+
 #include <roc_api.h>
 
 #include "mvtvm_ml_model.h"
 
+#include "cnxk_ml_model.h"
+
 /* Objects list */
 char mvtvm_object_list[ML_MVTVM_MODEL_OBJECT_MAX][RTE_ML_STR_MAX] = {"mod.so", "mod.json",
 								     "mod.params"};
@@ -71,3 +75,104 @@  mvtvm_ml_model_blob_parse(struct rte_ml_model_params *params, struct mvtvm_ml_mo
 
 	return -EINVAL;
 }
+
+static enum rte_ml_io_type
+mvtvm_ml_io_type_map(uint8_t type)
+{
+	switch (type) {
+	case kDLInt:
+		return RTE_ML_IO_TYPE_INT32;
+	case kDLUInt:
+		return RTE_ML_IO_TYPE_UINT32;
+	case kDLFloat:
+		return RTE_ML_IO_TYPE_FP32;
+	case kDLBfloat:
+		return RTE_ML_IO_TYPE_BFLOAT16;
+	}
+
+	return RTE_ML_IO_TYPE_UNKNOWN;
+}
+
+void
+mvtvm_ml_model_io_info_update(struct cnxk_ml_model *model)
+{
+	struct tvmdp_model_metadata *metadata;
+	int32_t i;
+	int32_t j;
+
+	if (model->subtype == ML_CNXK_MODEL_SUBTYPE_TVM_MRVL)
+		goto tvm_mrvl_model;
+
+	metadata = &model->mvtvm.metadata;
+
+	/* Inputs, set for layer_id = 0 */
+	model->mvtvm.info.nb_inputs = metadata->model.num_input;
+	model->mvtvm.info.total_input_sz_d = 0;
+	model->mvtvm.info.total_input_sz_q = 0;
+	for (i = 0; i < metadata->model.num_input; i++) {
+		strncpy(model->mvtvm.info.input[i].name, metadata->input[i].name,
+			TVMDP_NAME_STRLEN);
+		model->mvtvm.info.input[i].dtype =
+			mvtvm_ml_io_type_map(metadata->input[i].datatype.code);
+		model->mvtvm.info.input[i].qtype =
+			mvtvm_ml_io_type_map(metadata->input[i].model_datatype.code);
+		model->mvtvm.info.input[i].nb_dims = metadata->input[i].ndim;
+
+		model->mvtvm.info.input[i].nb_elements = 1;
+		for (j = 0; j < metadata->input[i].ndim; j++) {
+			model->mvtvm.info.input[i].shape[j] = metadata->input[i].shape[j];
+			model->mvtvm.info.input[i].nb_elements *= metadata->input[i].shape[j];
+		}
+
+		model->mvtvm.info.input[i].sz_d =
+			model->mvtvm.info.input[i].nb_elements *
+			rte_ml_io_type_size_get(model->mvtvm.info.input[i].dtype);
+		model->mvtvm.info.input[i].sz_q =
+			model->mvtvm.info.input[i].nb_elements *
+			rte_ml_io_type_size_get(model->mvtvm.info.input[i].qtype);
+
+		model->mvtvm.info.total_input_sz_d += model->mvtvm.info.input[i].sz_d;
+		model->mvtvm.info.total_input_sz_q += model->mvtvm.info.input[i].sz_q;
+
+		plt_ml_dbg("model_id = %u, input[%u] - sz_d = %u sz_q = %u", model->model_id, i,
+			   model->mvtvm.info.input[i].sz_d, model->mvtvm.info.input[i].sz_q);
+	}
+
+	/* Outputs, set for nb_layers - 1 */
+	model->mvtvm.info.nb_outputs = metadata->model.num_output;
+	model->mvtvm.info.total_output_sz_d = 0;
+	model->mvtvm.info.total_output_sz_q = 0;
+	for (i = 0; i < metadata->model.num_output; i++) {
+		strncpy(model->mvtvm.info.output[i].name, metadata->output[i].name,
+			TVMDP_NAME_STRLEN);
+		model->mvtvm.info.output[i].dtype =
+			mvtvm_ml_io_type_map(metadata->output[i].datatype.code);
+		model->mvtvm.info.output[i].qtype =
+			mvtvm_ml_io_type_map(metadata->output[i].model_datatype.code);
+		model->mvtvm.info.output[i].nb_dims = metadata->output[i].ndim;
+
+		model->mvtvm.info.output[i].nb_elements = 1;
+		for (j = 0; j < metadata->output[i].ndim; j++) {
+			model->mvtvm.info.output[i].shape[j] = metadata->output[i].shape[j];
+			model->mvtvm.info.output[i].nb_elements *= metadata->output[i].shape[j];
+		}
+
+		model->mvtvm.info.output[i].sz_d =
+			model->mvtvm.info.output[i].nb_elements *
+			rte_ml_io_type_size_get(model->mvtvm.info.output[i].dtype);
+		model->mvtvm.info.output[i].sz_q =
+			model->mvtvm.info.output[i].nb_elements *
+			rte_ml_io_type_size_get(model->mvtvm.info.output[i].qtype);
+
+		model->mvtvm.info.total_output_sz_d += model->mvtvm.info.output[i].sz_d;
+		model->mvtvm.info.total_output_sz_q += model->mvtvm.info.output[i].sz_q;
+
+		plt_ml_dbg("model_id = %u, output[%u] - sz_d = %u sz_q = %u", model->model_id, i,
+			   model->mvtvm.info.output[i].sz_d, model->mvtvm.info.output[i].sz_q);
+	}
+
+	return;
+
+tvm_mrvl_model:
+	cn10k_ml_layer_io_info_update(&model->mvtvm.info, &model->layer[0].glow.metadata);
+}
diff --git a/drivers/ml/cnxk/mvtvm_ml_model.h b/drivers/ml/cnxk/mvtvm_ml_model.h
index 6c38217c158..2b25a7b568e 100644
--- a/drivers/ml/cnxk/mvtvm_ml_model.h
+++ b/drivers/ml/cnxk/mvtvm_ml_model.h
@@ -47,5 +47,6 @@  struct mvtvm_ml_model_data {
 
 int mvtvm_ml_model_blob_parse(struct rte_ml_model_params *params,
 			      struct mvtvm_ml_model_object *object);
+void mvtvm_ml_model_io_info_update(struct cnxk_ml_model *model);
 
 #endif /* _MVTVM_ML_MODEL_H_ */
diff --git a/drivers/ml/cnxk/mvtvm_ml_ops.c b/drivers/ml/cnxk/mvtvm_ml_ops.c
index 5c30bbf6b89..a783e16e6eb 100644
--- a/drivers/ml/cnxk/mvtvm_ml_ops.c
+++ b/drivers/ml/cnxk/mvtvm_ml_ops.c
@@ -181,6 +181,9 @@  mvtvm_ml_model_load(struct cnxk_ml_dev *cnxk_mldev, struct rte_ml_model_params *
 		goto error;
 	}
 
+	/* Update model I/O data */
+	mvtvm_ml_model_io_info_update(model);
+
 	return 0;
 
 error: