@@ -32,6 +32,10 @@ rte_ml_io_type_size_get(enum rte_ml_io_type type)
return sizeof(int32_t);
case RTE_ML_IO_TYPE_UINT32:
return sizeof(uint32_t);
+ case RTE_ML_IO_TYPE_INT64:
+ return sizeof(int64_t);
+ case RTE_ML_IO_TYPE_UINT64:
+ return sizeof(uint64_t);
case RTE_ML_IO_TYPE_FP8:
return sizeof(uint8_t);
case RTE_ML_IO_TYPE_FP16:
@@ -328,6 +328,98 @@ __rte_internal
int
rte_ml_io_uint32_to_float32(float scale, uint64_t nb_elements, void *input, void *output);
+/**
+ * @internal
+ *
+ * Convert a buffer containing numbers in single precision floating format (float32) to signed
+ * 64-bit integer format (INT64).
+ *
+ * @param[in] scale
+ * Scale factor for conversion.
+ * @param[in] nb_elements
+ * Number of elements in the buffer.
+ * @param[in] input
+ * Input buffer containing float32 numbers. Size of buffer is equal to (nb_elements * 4) bytes.
+ * @param[out] output
+ * Output buffer to store INT64 numbers. Size of buffer is equal to (nb_elements * 8) bytes.
+ *
+ * @return
+ * - 0, Success.
+ * - < 0, Error code on failure.
+ */
+__rte_internal
+int
+rte_ml_io_float32_to_int64(float scale, uint64_t nb_elements, void *input, void *output);
+
+/**
+ * @internal
+ *
+ * Convert a buffer containing numbers in signed 64-bit integer format (INT64) to single precision
+ * floating format (float32).
+ *
+ * @param[in] scale
+ * Scale factor for conversion.
+ * @param[in] nb_elements
+ * Number of elements in the buffer.
+ * @param[in] input
+ * Input buffer containing INT64 numbers. Size of buffer is equal to (nb_elements * 8) bytes.
+ * @param[out] output
+ * Output buffer to store float32 numbers. Size of buffer is equal to (nb_elements * 4) bytes.
+ *
+ * @return
+ * - 0, Success.
+ * - < 0, Error code on failure.
+ */
+__rte_internal
+int
+rte_ml_io_int64_to_float32(float scale, uint64_t nb_elements, void *input, void *output);
+
+/**
+ * @internal
+ *
+ * Convert a buffer containing numbers in single precision floating format (float32) to unsigned
+ * 64-bit integer format (UINT64).
+ *
+ * @param[in] scale
+ * Scale factor for conversion.
+ * @param[in] nb_elements
+ * Number of elements in the buffer.
+ * @param[in] input
+ * Input buffer containing float32 numbers. Size of buffer is equal to (nb_elements * 4) bytes.
+ * @param[out] output
+ * Output buffer to store UINT64 numbers. Size of buffer is equal to (nb_elements * 8) bytes.
+ *
+ * @return
+ * - 0, Success.
+ * - < 0, Error code on failure.
+ */
+__rte_internal
+int
+rte_ml_io_float32_to_uint64(float scale, uint64_t nb_elements, void *input, void *output);
+
+/**
+ * @internal
+ *
+ * Convert a buffer containing numbers in unsigned 64-bit integer format (UINT64) to single
+ * precision floating format (float32).
+ *
+ * @param[in] scale
+ * Scale factor for conversion.
+ * @param[in] nb_elements
+ * Number of elements in the buffer.
+ * @param[in] input
+ * Input buffer containing UINT64 numbers. Size of buffer is equal to (nb_elements * 8) bytes.
+ * @param[out] output
+ * Output buffer to store float32 numbers. Size of buffer is equal to (nb_elements * 4) bytes.
+ *
+ * @return
+ * - 0, Success.
+ * - < 0, Error code on failure.
+ */
+__rte_internal
+int
+rte_ml_io_uint64_to_float32(float scale, uint64_t nb_elements, void *input, void *output);
+
/**
* @internal
*
@@ -842,6 +842,330 @@ rte_ml_io_uint32_to_float32(float scale, uint64_t nb_elements, void *input, void
return 0;
}
+static inline void
+__float32_to_int64_neon_s64x2(float scale, float *input, int64_t *output)
+{
+ float32x2_t f32x2;
+ float64x2_t f64x2;
+ int64x2_t s64x2;
+
+ /* load 2 x float elements */
+ f32x2 = vld1_f32(input);
+
+ /* scale */
+ f32x2 = vmul_n_f32(f32x2, scale);
+
+ /* convert to float64x2_t */
+ f64x2 = vcvt_f64_f32(f32x2);
+
+ /* convert to int64x2_t */
+ s64x2 = vcvtaq_s64_f64(f64x2);
+
+ /* store 2 elements */
+ vst1q_s64(output, s64x2);
+}
+
+static inline void
+__float32_to_int64_neon_s64x1(float scale, float *input, int64_t *output)
+{
+ float32x2_t f32x2;
+ float64x2_t f64x2;
+ int64x2_t s64x2;
+
+ /* load 1 x float element */
+ f32x2 = vdup_n_f32(*input);
+
+ /* scale */
+ f32x2 = vmul_n_f32(f32x2, scale);
+
+ /* convert to float64x2_t */
+ f64x2 = vcvt_f64_f32(f32x2);
+
+ /* convert to int64x2_t */
+ s64x2 = vcvtaq_s64_f64(f64x2);
+
+ /* store lane 0 of int64x2_t */
+ vst1q_lane_s64(output, s64x2, 0);
+}
+
+int
+rte_ml_io_float32_to_int64(float scale, uint64_t nb_elements, void *input, void *output)
+{
+ float *input_buffer;
+ int64_t *output_buffer;
+ uint64_t nb_iterations;
+ uint32_t vlen;
+ uint64_t i;
+
+ if ((scale == 0) || (nb_elements == 0) || (input == NULL) || (output == NULL))
+ return -EINVAL;
+
+ input_buffer = (float *)input;
+ output_buffer = (int64_t *)output;
+ vlen = 4 * sizeof(float) / sizeof(int64_t);
+ nb_iterations = nb_elements / vlen;
+
+ /* convert vlen elements in each iteration */
+ for (i = 0; i < nb_iterations; i++) {
+ __float32_to_int64_neon_s64x2(scale, input_buffer, output_buffer);
+ input_buffer += vlen;
+ output_buffer += vlen;
+ }
+
+ /* convert leftover elements */
+ i = i * vlen;
+ for (; i < nb_elements; i++) {
+ __float32_to_int64_neon_s64x1(scale, input_buffer, output_buffer);
+ input_buffer++;
+ output_buffer++;
+ }
+
+ return 0;
+}
+
+static inline void
+__int64_to_float32_neon_f32x2(float scale, int64_t *input, float *output)
+{
+ int64x2_t s64x2;
+ float64x2_t f64x2;
+ float32x2_t f32x2;
+
+ /* load 2 x int64_t elements */
+ s64x2 = vld1q_s64(input);
+
+ /* convert int64x2_t to float64x2_t */
+ f64x2 = vcvtq_f64_s64(s64x2);
+
+ /* convert float64x2_t to float32x2_t */
+ f32x2 = vcvt_f32_f64(f64x2);
+
+ /* scale */
+ f32x2 = vmul_n_f32(f32x2, scale);
+
+ /* store float32x2_t */
+ vst1_f32(output, f32x2);
+}
+
+static inline void
+__int64_to_float32_neon_f32x1(float scale, int64_t *input, float *output)
+{
+ int64x2_t s64x2;
+ float64x2_t f64x2;
+ float32x2_t f32x2;
+
+ /* load 2 x int64_t elements */
+ s64x2 = vld1q_lane_s64(input, vdupq_n_s64(0), 0);
+
+ /* convert int64x2_t to float64x2_t */
+ f64x2 = vcvtq_f64_s64(s64x2);
+
+ /* convert float64x2_t to float32x2_t */
+ f32x2 = vcvt_f32_f64(f64x2);
+
+ /* scale */
+ f32x2 = vmul_n_f32(f32x2, scale);
+
+ /* store float32x2_t */
+ vst1_lane_f32(output, f32x2, 0);
+}
+
+int
+rte_ml_io_int64_to_float32(float scale, uint64_t nb_elements, void *input, void *output)
+{
+ int64_t *input_buffer;
+ float *output_buffer;
+ uint64_t nb_iterations;
+ uint32_t vlen;
+ uint64_t i;
+
+ if ((scale == 0) || (nb_elements == 0) || (input == NULL) || (output == NULL))
+ return -EINVAL;
+
+ input_buffer = (int64_t *)input;
+ output_buffer = (float *)output;
+ vlen = 4 * sizeof(float) / sizeof(int64_t);
+ nb_iterations = nb_elements / vlen;
+
+ /* convert vlen elements in each iteration */
+ for (i = 0; i < nb_iterations; i++) {
+ __int64_to_float32_neon_f32x2(scale, input_buffer, output_buffer);
+ input_buffer += vlen;
+ output_buffer += vlen;
+ }
+
+ /* convert leftover elements */
+ i = i * vlen;
+ for (; i < nb_elements; i++) {
+ __int64_to_float32_neon_f32x1(scale, input_buffer, output_buffer);
+ input_buffer++;
+ output_buffer++;
+ }
+
+ return 0;
+}
+
+static inline void
+__float32_to_uint64_neon_u64x2(float scale, float *input, uint64_t *output)
+{
+ float32x2_t f32x2;
+ float64x2_t f64x2;
+ uint64x2_t u64x2;
+
+ /* load 2 x float elements */
+ f32x2 = vld1_f32(input);
+
+ /* scale */
+ f32x2 = vmul_n_f32(f32x2, scale);
+
+ /* convert to float64x2_t */
+ f64x2 = vcvt_f64_f32(f32x2);
+
+ /* convert to int64x2_t */
+ u64x2 = vcvtaq_u64_f64(f64x2);
+
+ /* store 2 elements */
+ vst1q_u64(output, u64x2);
+}
+
+static inline void
+__float32_to_uint64_neon_u64x1(float scale, float *input, uint64_t *output)
+{
+ float32x2_t f32x2;
+ float64x2_t f64x2;
+ uint64x2_t u64x2;
+
+ /* load 1 x float element */
+ f32x2 = vld1_lane_f32(input, vdup_n_f32(0), 0);
+
+ /* scale */
+ f32x2 = vmul_n_f32(f32x2, scale);
+
+ /* convert to float64x2_t */
+ f64x2 = vcvt_f64_f32(f32x2);
+
+ /* convert to int64x2_t */
+ u64x2 = vcvtaq_u64_f64(f64x2);
+
+ /* store 2 elements */
+ vst1q_lane_u64(output, u64x2, 0);
+}
+
+int
+rte_ml_io_float32_to_uint64(float scale, uint64_t nb_elements, void *input, void *output)
+{
+ float *input_buffer;
+ uint64_t *output_buffer;
+ uint64_t nb_iterations;
+ uint32_t vlen;
+ uint64_t i;
+
+ if ((scale == 0) || (nb_elements == 0) || (input == NULL) || (output == NULL))
+ return -EINVAL;
+
+ input_buffer = (float *)input;
+ output_buffer = (uint64_t *)output;
+ vlen = 4 * sizeof(float) / sizeof(uint64_t);
+ nb_iterations = nb_elements / vlen;
+
+ /* convert vlen elements in each iteration */
+ for (i = 0; i < nb_iterations; i++) {
+ __float32_to_uint64_neon_u64x2(scale, input_buffer, output_buffer);
+ input_buffer += vlen;
+ output_buffer += vlen;
+ }
+
+ /* convert leftover elements */
+ i = i * vlen;
+ for (; i < nb_elements; i++) {
+ __float32_to_uint64_neon_u64x1(scale, input_buffer, output_buffer);
+ input_buffer++;
+ output_buffer++;
+ }
+
+ return 0;
+}
+
+static inline void
+__uint64_to_float32_neon_f32x2(float scale, uint64_t *input, float *output)
+{
+ uint64x2_t u64x2;
+ float64x2_t f64x2;
+ float32x2_t f32x2;
+
+ /* load 2 x int64_t elements */
+ u64x2 = vld1q_u64(input);
+
+ /* convert int64x2_t to float64x2_t */
+ f64x2 = vcvtq_f64_u64(u64x2);
+
+ /* convert float64x2_t to float32x2_t */
+ f32x2 = vcvt_f32_f64(f64x2);
+
+ /* scale */
+ f32x2 = vmul_n_f32(f32x2, scale);
+
+ /* store float32x2_t */
+ vst1_f32(output, f32x2);
+}
+
+static inline void
+__uint64_to_float32_neon_f32x1(float scale, uint64_t *input, float *output)
+{
+ uint64x2_t u64x2;
+ float64x2_t f64x2;
+ float32x2_t f32x2;
+
+ /* load 2 x int64_t elements */
+ u64x2 = vld1q_lane_u64(input, vdupq_n_u64(0), 0);
+
+ /* convert int64x2_t to float64x2_t */
+ f64x2 = vcvtq_f64_u64(u64x2);
+
+ /* convert float64x2_t to float32x2_t */
+ f32x2 = vcvt_f32_f64(f64x2);
+
+ /* scale */
+ f32x2 = vmul_n_f32(f32x2, scale);
+
+ /* store float32x2_t */
+ vst1_lane_f32(output, f32x2, 0);
+}
+
+int
+rte_ml_io_uint64_to_float32(float scale, uint64_t nb_elements, void *input, void *output)
+{
+ uint64_t *input_buffer;
+ float *output_buffer;
+ uint64_t nb_iterations;
+ uint32_t vlen;
+ uint64_t i;
+
+ if ((scale == 0) || (nb_elements == 0) || (input == NULL) || (output == NULL))
+ return -EINVAL;
+
+ input_buffer = (uint64_t *)input;
+ output_buffer = (float *)output;
+ vlen = 4 * sizeof(float) / sizeof(uint64_t);
+ nb_iterations = nb_elements / vlen;
+
+ /* convert vlen elements in each iteration */
+ for (i = 0; i < nb_iterations; i++) {
+ __uint64_to_float32_neon_f32x2(scale, input_buffer, output_buffer);
+ input_buffer += vlen;
+ output_buffer += vlen;
+ }
+
+ /* convert leftover elements */
+ i = i * vlen;
+ for (; i < nb_elements; i++) {
+ __uint64_to_float32_neon_f32x1(scale, input_buffer, output_buffer);
+ input_buffer++;
+ output_buffer++;
+ }
+
+ return 0;
+}
+
static inline void
__float32_to_float16_neon_f16x4(float32_t *input, float16_t *output)
{
@@ -327,6 +327,104 @@ rte_ml_io_uint32_to_float32(float scale, uint64_t nb_elements, void *input, void
return 0;
}
+int
+rte_ml_io_float32_to_int64(float scale, uint64_t nb_elements, void *input, void *output)
+{
+ float *input_buffer;
+ int64_t *output_buffer;
+ uint64_t i;
+
+ if ((scale == 0) || (nb_elements == 0) || (input == NULL) || (output == NULL))
+ return -EINVAL;
+
+ input_buffer = (float *)input;
+ output_buffer = (int64_t *)output;
+
+ for (i = 0; i < nb_elements; i++) {
+ *output_buffer = (int64_t)round((*input_buffer) * scale);
+
+ input_buffer++;
+ output_buffer++;
+ }
+
+ return 0;
+}
+
+int
+rte_ml_io_int64_to_float32(float scale, uint64_t nb_elements, void *input, void *output)
+{
+ int64_t *input_buffer;
+ float *output_buffer;
+ uint64_t i;
+
+ if ((scale == 0) || (nb_elements == 0) || (input == NULL) || (output == NULL))
+ return -EINVAL;
+
+ input_buffer = (int64_t *)input;
+ output_buffer = (float *)output;
+
+ for (i = 0; i < nb_elements; i++) {
+ *output_buffer = scale * (float)(*input_buffer);
+
+ input_buffer++;
+ output_buffer++;
+ }
+
+ return 0;
+}
+
+int
+rte_ml_io_float32_to_uint64(float scale, uint64_t nb_elements, void *input, void *output)
+{
+ float *input_buffer;
+ uint64_t *output_buffer;
+ int64_t i64;
+ uint64_t i;
+
+ if ((scale == 0) || (nb_elements == 0) || (input == NULL) || (output == NULL))
+ return -EINVAL;
+
+ input_buffer = (float *)input;
+ output_buffer = (uint64_t *)output;
+
+ for (i = 0; i < nb_elements; i++) {
+ i64 = (int64_t)round((*input_buffer) * scale);
+
+ if (i64 < 0)
+ i64 = 0;
+
+ *output_buffer = (uint64_t)i64;
+
+ input_buffer++;
+ output_buffer++;
+ }
+
+ return 0;
+}
+
+int
+rte_ml_io_uint64_to_float32(float scale, uint64_t nb_elements, void *input, void *output)
+{
+ uint64_t *input_buffer;
+ float *output_buffer;
+ uint64_t i;
+
+ if ((scale == 0) || (nb_elements == 0) || (input == NULL) || (output == NULL))
+ return -EINVAL;
+
+ input_buffer = (uint64_t *)input;
+ output_buffer = (float *)output;
+
+ for (i = 0; i < nb_elements; i++) {
+ *output_buffer = scale * (float)(*input_buffer);
+
+ input_buffer++;
+ output_buffer++;
+ }
+
+ return 0;
+}
+
/* Convert a single precision floating point number (float32) into a half precision
* floating point number (float16) using round to nearest rounding mode.
*/
@@ -874,6 +874,10 @@ enum rte_ml_io_type {
/**< 32-bit integer */
RTE_ML_IO_TYPE_UINT32,
/**< 32-bit unsigned integer */
+ RTE_ML_IO_TYPE_INT64,
+ /**< 32-bit integer */
+ RTE_ML_IO_TYPE_UINT64,
+ /**< 32-bit unsigned integer */
RTE_ML_IO_TYPE_FP8,
/**< 8-bit floating point number */
RTE_ML_IO_TYPE_FP16,
@@ -61,6 +61,10 @@ INTERNAL {
rte_ml_io_int32_to_float32;
rte_ml_io_float32_to_uint32;
rte_ml_io_uint32_to_float32;
+ rte_ml_io_float32_to_int64;
+ rte_ml_io_int64_to_float32;
+ rte_ml_io_float32_to_uint64;
+ rte_ml_io_uint64_to_float32;
rte_ml_io_float32_to_float16;
rte_ml_io_float16_to_float32;
rte_ml_io_float32_to_bfloat16;