Update model metadata to v2301. Revised metadata introduces fields to support up to 32 inputs/outputs per model, scratch relocation and updates to names of existing fields. Update driver files to include changes in names of metadata fields.
Signed-off-by: Srikanth Yalavarthi <[email protected]> --- drivers/ml/cnxk/cn10k_ml_model.c | 111 ++++++++++++++++--------------- drivers/ml/cnxk/cn10k_ml_model.h | 36 +++++++--- drivers/ml/cnxk/cn10k_ml_ops.c | 50 +++++++------- 3 files changed, 106 insertions(+), 91 deletions(-) diff --git a/drivers/ml/cnxk/cn10k_ml_model.c b/drivers/ml/cnxk/cn10k_ml_model.c index c0b7b061f5..a15df700aa 100644 --- a/drivers/ml/cnxk/cn10k_ml_model.c +++ b/drivers/ml/cnxk/cn10k_ml_model.c @@ -83,11 +83,11 @@ cn10k_ml_model_metadata_check(uint8_t *buffer, uint64_t size) /* Header version */ rte_memcpy(version, metadata->header.version, 4 * sizeof(uint8_t)); - if (version[0] * 1000 + version[1] * 100 < MRVL_ML_MODEL_VERSION) { + if (version[0] * 1000 + version[1] * 100 != MRVL_ML_MODEL_VERSION_MIN) { plt_err("Metadata version = %u.%u.%u.%u (< %u.%u.%u.%u) not supported", version[0], - version[1], version[2], version[3], (MRVL_ML_MODEL_VERSION / 1000) % 10, - (MRVL_ML_MODEL_VERSION / 100) % 10, (MRVL_ML_MODEL_VERSION / 10) % 10, - MRVL_ML_MODEL_VERSION % 10); + version[1], version[2], version[3], (MRVL_ML_MODEL_VERSION_MIN / 1000) % 10, + (MRVL_ML_MODEL_VERSION_MIN / 100) % 10, + (MRVL_ML_MODEL_VERSION_MIN / 10) % 10, MRVL_ML_MODEL_VERSION_MIN % 10); return -ENOTSUP; } @@ -125,36 +125,36 @@ cn10k_ml_model_metadata_check(uint8_t *buffer, uint64_t size) } /* Check input count */ - if (metadata->model.num_input > MRVL_ML_INPUT_OUTPUT_SIZE) { + if (metadata->model.num_input > MRVL_ML_NUM_INPUT_OUTPUT_1) { plt_err("Invalid metadata, num_input = %u (> %u)", metadata->model.num_input, - MRVL_ML_INPUT_OUTPUT_SIZE); + MRVL_ML_NUM_INPUT_OUTPUT_1); return -EINVAL; } /* Check output count */ - if (metadata->model.num_output > MRVL_ML_INPUT_OUTPUT_SIZE) { + if (metadata->model.num_output > MRVL_ML_NUM_INPUT_OUTPUT_1) { plt_err("Invalid metadata, num_output = %u (> %u)", metadata->model.num_output, - MRVL_ML_INPUT_OUTPUT_SIZE); + MRVL_ML_NUM_INPUT_OUTPUT_1); return -EINVAL; } /* Inputs */ for (i = 0; i < metadata->model.num_input; i++) { - if (rte_ml_io_type_size_get(cn10k_ml_io_type_map(metadata->input[i].input_type)) <= + if (rte_ml_io_type_size_get(cn10k_ml_io_type_map(metadata->input1[i].input_type)) <= 0) { plt_err("Invalid metadata, input[%u] : input_type = %u", i, - metadata->input[i].input_type); + metadata->input1[i].input_type); return -EINVAL; } if (rte_ml_io_type_size_get( - cn10k_ml_io_type_map(metadata->input[i].model_input_type)) <= 0) { + cn10k_ml_io_type_map(metadata->input1[i].model_input_type)) <= 0) { plt_err("Invalid metadata, input[%u] : model_input_type = %u", i, - metadata->input[i].model_input_type); + metadata->input1[i].model_input_type); return -EINVAL; } - if (metadata->input[i].relocatable != 1) { + if (metadata->input1[i].relocatable != 1) { plt_err("Model not supported, non-relocatable input: %u", i); return -ENOTSUP; } @@ -163,20 +163,20 @@ cn10k_ml_model_metadata_check(uint8_t *buffer, uint64_t size) /* Outputs */ for (i = 0; i < metadata->model.num_output; i++) { if (rte_ml_io_type_size_get( - cn10k_ml_io_type_map(metadata->output[i].output_type)) <= 0) { + cn10k_ml_io_type_map(metadata->output1[i].output_type)) <= 0) { plt_err("Invalid metadata, output[%u] : output_type = %u", i, - metadata->output[i].output_type); + metadata->output1[i].output_type); return -EINVAL; } if (rte_ml_io_type_size_get( - cn10k_ml_io_type_map(metadata->output[i].model_output_type)) <= 0) { + cn10k_ml_io_type_map(metadata->output1[i].model_output_type)) <= 0) { plt_err("Invalid metadata, output[%u] : model_output_type = %u", i, - metadata->output[i].model_output_type); + metadata->output1[i].model_output_type); return -EINVAL; } - if (metadata->output[i].relocatable != 1) { + if (metadata->output1[i].relocatable != 1) { plt_err("Model not supported, non-relocatable output: %u", i); return -ENOTSUP; } @@ -191,28 +191,29 @@ cn10k_ml_model_metadata_update(struct cn10k_ml_model_metadata *metadata) uint8_t i; for (i = 0; i < metadata->model.num_input; i++) { - metadata->input[i].input_type = cn10k_ml_io_type_map(metadata->input[i].input_type); - metadata->input[i].model_input_type = - cn10k_ml_io_type_map(metadata->input[i].model_input_type); + metadata->input1[i].input_type = + cn10k_ml_io_type_map(metadata->input1[i].input_type); + metadata->input1[i].model_input_type = + cn10k_ml_io_type_map(metadata->input1[i].model_input_type); - if (metadata->input[i].shape.w == 0) - metadata->input[i].shape.w = 1; + if (metadata->input1[i].shape.w == 0) + metadata->input1[i].shape.w = 1; - if (metadata->input[i].shape.x == 0) - metadata->input[i].shape.x = 1; + if (metadata->input1[i].shape.x == 0) + metadata->input1[i].shape.x = 1; - if (metadata->input[i].shape.y == 0) - metadata->input[i].shape.y = 1; + if (metadata->input1[i].shape.y == 0) + metadata->input1[i].shape.y = 1; - if (metadata->input[i].shape.z == 0) - metadata->input[i].shape.z = 1; + if (metadata->input1[i].shape.z == 0) + metadata->input1[i].shape.z = 1; } for (i = 0; i < metadata->model.num_output; i++) { - metadata->output[i].output_type = - cn10k_ml_io_type_map(metadata->output[i].output_type); - metadata->output[i].model_output_type = - cn10k_ml_io_type_map(metadata->output[i].model_output_type); + metadata->output1[i].output_type = + cn10k_ml_io_type_map(metadata->output1[i].output_type); + metadata->output1[i].model_output_type = + cn10k_ml_io_type_map(metadata->output1[i].model_output_type); } } @@ -272,31 +273,31 @@ cn10k_ml_model_addr_update(struct cn10k_ml_model *model, uint8_t *buffer, uint8_ addr->total_input_sz_q = 0; for (i = 0; i < metadata->model.num_input; i++) { addr->input[i].nb_elements = - metadata->input[i].shape.w * metadata->input[i].shape.x * - metadata->input[i].shape.y * metadata->input[i].shape.z; + metadata->input1[i].shape.w * metadata->input1[i].shape.x * + metadata->input1[i].shape.y * metadata->input1[i].shape.z; addr->input[i].sz_d = addr->input[i].nb_elements * - rte_ml_io_type_size_get(metadata->input[i].input_type); + rte_ml_io_type_size_get(metadata->input1[i].input_type); addr->input[i].sz_q = addr->input[i].nb_elements * - rte_ml_io_type_size_get(metadata->input[i].model_input_type); + rte_ml_io_type_size_get(metadata->input1[i].model_input_type); addr->total_input_sz_d += addr->input[i].sz_d; addr->total_input_sz_q += addr->input[i].sz_q; plt_ml_dbg("model_id = %u, input[%u] - w:%u x:%u y:%u z:%u, sz_d = %u sz_q = %u", - model->model_id, i, metadata->input[i].shape.w, - metadata->input[i].shape.x, metadata->input[i].shape.y, - metadata->input[i].shape.z, addr->input[i].sz_d, addr->input[i].sz_q); + model->model_id, i, metadata->input1[i].shape.w, + metadata->input1[i].shape.x, metadata->input1[i].shape.y, + metadata->input1[i].shape.z, addr->input[i].sz_d, addr->input[i].sz_q); } /* Outputs */ addr->total_output_sz_q = 0; addr->total_output_sz_d = 0; for (i = 0; i < metadata->model.num_output; i++) { - addr->output[i].nb_elements = metadata->output[i].size; + addr->output[i].nb_elements = metadata->output1[i].size; addr->output[i].sz_d = addr->output[i].nb_elements * - rte_ml_io_type_size_get(metadata->output[i].output_type); + rte_ml_io_type_size_get(metadata->output1[i].output_type); addr->output[i].sz_q = addr->output[i].nb_elements * - rte_ml_io_type_size_get(metadata->output[i].model_output_type); + rte_ml_io_type_size_get(metadata->output1[i].model_output_type); addr->total_output_sz_q += addr->output[i].sz_q; addr->total_output_sz_d += addr->output[i].sz_d; @@ -388,24 +389,24 @@ cn10k_ml_model_info_set(struct rte_ml_dev *dev, struct cn10k_ml_model *model) /* Set input info */ for (i = 0; i < info->nb_inputs; i++) { - rte_memcpy(input[i].name, metadata->input[i].input_name, MRVL_ML_INPUT_NAME_LEN); - input[i].dtype = metadata->input[i].input_type; - input[i].qtype = metadata->input[i].model_input_type; - input[i].shape.format = metadata->input[i].shape.format; - input[i].shape.w = metadata->input[i].shape.w; - input[i].shape.x = metadata->input[i].shape.x; - input[i].shape.y = metadata->input[i].shape.y; - input[i].shape.z = metadata->input[i].shape.z; + rte_memcpy(input[i].name, metadata->input1[i].input_name, MRVL_ML_INPUT_NAME_LEN); + input[i].dtype = metadata->input1[i].input_type; + input[i].qtype = metadata->input1[i].model_input_type; + input[i].shape.format = metadata->input1[i].shape.format; + input[i].shape.w = metadata->input1[i].shape.w; + input[i].shape.x = metadata->input1[i].shape.x; + input[i].shape.y = metadata->input1[i].shape.y; + input[i].shape.z = metadata->input1[i].shape.z; } /* Set output info */ for (i = 0; i < info->nb_outputs; i++) { - rte_memcpy(output[i].name, metadata->output[i].output_name, + rte_memcpy(output[i].name, metadata->output1[i].output_name, MRVL_ML_OUTPUT_NAME_LEN); - output[i].dtype = metadata->output[i].output_type; - output[i].qtype = metadata->output[i].model_output_type; + output[i].dtype = metadata->output1[i].output_type; + output[i].qtype = metadata->output1[i].model_output_type; output[i].shape.format = RTE_ML_IO_FORMAT_1D; - output[i].shape.w = metadata->output[i].size; + output[i].shape.w = metadata->output1[i].size; output[i].shape.x = 1; output[i].shape.y = 1; output[i].shape.z = 1; diff --git a/drivers/ml/cnxk/cn10k_ml_model.h b/drivers/ml/cnxk/cn10k_ml_model.h index b30ad5a981..bd863a8c12 100644 --- a/drivers/ml/cnxk/cn10k_ml_model.h +++ b/drivers/ml/cnxk/cn10k_ml_model.h @@ -21,14 +21,15 @@ enum cn10k_ml_model_state { ML_CN10K_MODEL_STATE_UNKNOWN, }; -/* Model Metadata : v 2.1.0.2 */ +/* Model Metadata : v 2.3.0.1 */ #define MRVL_ML_MODEL_MAGIC_STRING "MRVL" #define MRVL_ML_MODEL_TARGET_ARCH 128 -#define MRVL_ML_MODEL_VERSION 2100 +#define MRVL_ML_MODEL_VERSION_MIN 2100 #define MRVL_ML_MODEL_NAME_LEN 64 #define MRVL_ML_INPUT_NAME_LEN 16 #define MRVL_ML_OUTPUT_NAME_LEN 16 -#define MRVL_ML_INPUT_OUTPUT_SIZE 8 +#define MRVL_ML_NUM_INPUT_OUTPUT_1 8 +#define MRVL_ML_NUM_INPUT_OUTPUT_2 24 /* Header (256-byte) */ struct cn10k_ml_model_metadata_header { @@ -101,10 +102,10 @@ struct cn10k_ml_model_metadata_model { /* Inference batch size */ uint8_t batch_size; - /* Number of input tensors (Max 8) */ + /* Number of input tensors (Max 32) */ uint8_t num_input; - /* Number of output tensors (Max 8) */ + /* Number of output tensors (Max 32) */ uint8_t num_output; uint8_t reserved_1; @@ -159,7 +160,14 @@ struct cn10k_ml_model_metadata_model { * 1 - Yes */ uint8_t supports_lower_batch_size_optimization; - uint8_t reserved_3[59]; + uint8_t reserved_3[3]; + + /* Relative DDR start address of scratch space */ + uint64_t ddr_scratch_range_start; + + /* Relative DDR end address of scratch space */ + uint64_t ddr_scratch_range_end; + uint8_t reserved_4[40]; }; /* Init section (64-byte) */ @@ -303,7 +311,7 @@ struct cn10k_ml_model_metadata_output_section { /* Model data */ struct cn10k_ml_model_metadata_data_section { - uint8_t reserved[4068]; + uint8_t reserved[996]; /* Beta: xx.xx.xx.xx, * Later: YYYYMM.xx.xx @@ -337,13 +345,19 @@ struct cn10k_ml_model_metadata { struct cn10k_ml_model_metadata_weights_bias_section weights_bias; /* Input (512-bytes, 64-byte per input) provisioned for 8 inputs */ - struct cn10k_ml_model_metadata_input_section input[MRVL_ML_INPUT_OUTPUT_SIZE]; + struct cn10k_ml_model_metadata_input_section input1[MRVL_ML_NUM_INPUT_OUTPUT_1]; /* Output (512-bytes, 64-byte per output) provisioned for 8 outputs */ - struct cn10k_ml_model_metadata_output_section output[MRVL_ML_INPUT_OUTPUT_SIZE]; + struct cn10k_ml_model_metadata_output_section output1[MRVL_ML_NUM_INPUT_OUTPUT_1]; uint8_t reserved_2[1792]; + /* Input (1536-bytes, 64-byte per input) provisioned for 24 inputs */ + struct cn10k_ml_model_metadata_input_section input2[MRVL_ML_NUM_INPUT_OUTPUT_2]; + + /* Output (1536-bytes, 64-byte per output) provisioned for 24 outputs */ + struct cn10k_ml_model_metadata_output_section output2[MRVL_ML_NUM_INPUT_OUTPUT_2]; + /* Model data */ struct cn10k_ml_model_metadata_data_section data; @@ -399,7 +413,7 @@ struct cn10k_ml_model_addr { /* Quantized input size */ uint32_t sz_q; - } input[MRVL_ML_INPUT_OUTPUT_SIZE]; + } input[MRVL_ML_NUM_INPUT_OUTPUT_1]; /* Output address and size */ struct { @@ -411,7 +425,7 @@ struct cn10k_ml_model_addr { /* Quantized output size */ uint32_t sz_q; - } output[MRVL_ML_INPUT_OUTPUT_SIZE]; + } output[MRVL_ML_NUM_INPUT_OUTPUT_1]; /* Total size of quantized input */ uint32_t total_input_sz_q; diff --git a/drivers/ml/cnxk/cn10k_ml_ops.c b/drivers/ml/cnxk/cn10k_ml_ops.c index b5eaa24e83..aecc6e74ad 100644 --- a/drivers/ml/cnxk/cn10k_ml_ops.c +++ b/drivers/ml/cnxk/cn10k_ml_ops.c @@ -325,13 +325,13 @@ cn10k_ml_model_print(struct rte_ml_dev *dev, uint16_t model_id, FILE *fp) print_line(fp, LINE_LEN); for (i = 0; i < model->metadata.model.num_input; i++) { fprintf(fp, "%8u ", i); - fprintf(fp, "%*s ", 16, model->metadata.input[i].input_name); - rte_ml_io_type_to_str(model->metadata.input[i].input_type, str, STR_LEN); + fprintf(fp, "%*s ", 16, model->metadata.input1[i].input_name); + rte_ml_io_type_to_str(model->metadata.input1[i].input_type, str, STR_LEN); fprintf(fp, "%*s ", 12, str); - rte_ml_io_type_to_str(model->metadata.input[i].model_input_type, str, STR_LEN); + rte_ml_io_type_to_str(model->metadata.input1[i].model_input_type, str, STR_LEN); fprintf(fp, "%*s ", 18, str); - fprintf(fp, "%*s", 12, (model->metadata.input[i].quantize == 1 ? "Yes" : "No")); - rte_ml_io_format_to_str(model->metadata.input[i].shape.format, str, STR_LEN); + fprintf(fp, "%*s", 12, (model->metadata.input1[i].quantize == 1 ? "Yes" : "No")); + rte_ml_io_format_to_str(model->metadata.input1[i].shape.format, str, STR_LEN); fprintf(fp, "%*s", 16, str); fprintf(fp, "\n"); } @@ -343,12 +343,12 @@ cn10k_ml_model_print(struct rte_ml_dev *dev, uint16_t model_id, FILE *fp) print_line(fp, LINE_LEN); for (i = 0; i < model->metadata.model.num_output; i++) { fprintf(fp, "%8u ", i); - fprintf(fp, "%*s ", 16, model->metadata.output[i].output_name); - rte_ml_io_type_to_str(model->metadata.output[i].output_type, str, STR_LEN); + fprintf(fp, "%*s ", 16, model->metadata.output1[i].output_name); + rte_ml_io_type_to_str(model->metadata.output1[i].output_type, str, STR_LEN); fprintf(fp, "%*s ", 12, str); - rte_ml_io_type_to_str(model->metadata.output[i].model_output_type, str, STR_LEN); + rte_ml_io_type_to_str(model->metadata.output1[i].model_output_type, str, STR_LEN); fprintf(fp, "%*s ", 18, str); - fprintf(fp, "%*s", 12, (model->metadata.output[i].dequantize == 1 ? "Yes" : "No")); + fprintf(fp, "%*s", 12, (model->metadata.output1[i].dequantize == 1 ? "Yes" : "No")); fprintf(fp, "\n"); } fprintf(fp, "\n"); @@ -1882,28 +1882,28 @@ cn10k_ml_io_quantize(struct rte_ml_dev *dev, uint16_t model_id, uint16_t nb_batc next_batch: for (i = 0; i < model->metadata.model.num_input; i++) { - if (model->metadata.input[i].input_type == - model->metadata.input[i].model_input_type) { + if (model->metadata.input1[i].input_type == + model->metadata.input1[i].model_input_type) { rte_memcpy(lcl_qbuffer, lcl_dbuffer, model->addr.input[i].sz_d); } else { - switch (model->metadata.input[i].model_input_type) { + switch (model->metadata.input1[i].model_input_type) { case RTE_ML_IO_TYPE_INT8: - ret = rte_ml_io_float32_to_int8(model->metadata.input[i].qscale, + ret = rte_ml_io_float32_to_int8(model->metadata.input1[i].qscale, model->addr.input[i].nb_elements, lcl_dbuffer, lcl_qbuffer); break; case RTE_ML_IO_TYPE_UINT8: - ret = rte_ml_io_float32_to_uint8(model->metadata.input[i].qscale, + ret = rte_ml_io_float32_to_uint8(model->metadata.input1[i].qscale, model->addr.input[i].nb_elements, lcl_dbuffer, lcl_qbuffer); break; case RTE_ML_IO_TYPE_INT16: - ret = rte_ml_io_float32_to_int16(model->metadata.input[i].qscale, + ret = rte_ml_io_float32_to_int16(model->metadata.input1[i].qscale, model->addr.input[i].nb_elements, lcl_dbuffer, lcl_qbuffer); break; case RTE_ML_IO_TYPE_UINT16: - ret = rte_ml_io_float32_to_uint16(model->metadata.input[i].qscale, + ret = rte_ml_io_float32_to_uint16(model->metadata.input1[i].qscale, model->addr.input[i].nb_elements, lcl_dbuffer, lcl_qbuffer); break; @@ -1913,7 +1913,7 @@ cn10k_ml_io_quantize(struct rte_ml_dev *dev, uint16_t model_id, uint16_t nb_batc break; default: plt_err("Unsupported model_input_type[%u] : %u", i, - model->metadata.input[i].model_input_type); + model->metadata.input1[i].model_input_type); ret = -ENOTSUP; } if (ret < 0) @@ -1955,28 +1955,28 @@ cn10k_ml_io_dequantize(struct rte_ml_dev *dev, uint16_t model_id, uint16_t nb_ba next_batch: for (i = 0; i < model->metadata.model.num_output; i++) { - if (model->metadata.output[i].output_type == - model->metadata.output[i].model_output_type) { + if (model->metadata.output1[i].output_type == + model->metadata.output1[i].model_output_type) { rte_memcpy(lcl_dbuffer, lcl_qbuffer, model->addr.output[i].sz_q); } else { - switch (model->metadata.output[i].model_output_type) { + switch (model->metadata.output1[i].model_output_type) { case RTE_ML_IO_TYPE_INT8: - ret = rte_ml_io_int8_to_float32(model->metadata.output[i].dscale, + ret = rte_ml_io_int8_to_float32(model->metadata.output1[i].dscale, model->addr.output[i].nb_elements, lcl_qbuffer, lcl_dbuffer); break; case RTE_ML_IO_TYPE_UINT8: - ret = rte_ml_io_uint8_to_float32(model->metadata.output[i].dscale, + ret = rte_ml_io_uint8_to_float32(model->metadata.output1[i].dscale, model->addr.output[i].nb_elements, lcl_qbuffer, lcl_dbuffer); break; case RTE_ML_IO_TYPE_INT16: - ret = rte_ml_io_int16_to_float32(model->metadata.output[i].dscale, + ret = rte_ml_io_int16_to_float32(model->metadata.output1[i].dscale, model->addr.output[i].nb_elements, lcl_qbuffer, lcl_dbuffer); break; case RTE_ML_IO_TYPE_UINT16: - ret = rte_ml_io_uint16_to_float32(model->metadata.output[i].dscale, + ret = rte_ml_io_uint16_to_float32(model->metadata.output1[i].dscale, model->addr.output[i].nb_elements, lcl_qbuffer, lcl_dbuffer); break; @@ -1987,7 +1987,7 @@ cn10k_ml_io_dequantize(struct rte_ml_dev *dev, uint16_t model_id, uint16_t nb_ba break; default: plt_err("Unsupported model_output_type[%u] : %u", i, - model->metadata.output[i].model_output_type); + model->metadata.output1[i].model_output_type); ret = -ENOTSUP; } if (ret < 0) -- 2.17.1
