Pre Merge pull request !1301 from shenwei41/r1.2

inc/external/acl/acl.h

@@ -26,9 +26,9 @@ extern "C" {
 #endif
 
 // Current version is 1.0.0
-#define ACL_MAJOR_VERSION 1
-#define ACL_MINOR_VERSION 0
-#define ACL_PATCH_VERSION 0
+#define ACL_MAJOR_VERSION    1
+#define ACL_MINOR_VERSION    0
+#define ACL_PATCH_VERSION    0
 
 /**
  * @ingroup AscendCL
@@ -70,4 +70,4 @@ ACL_FUNC_VISIBILITY aclError aclrtGetVersion(int32_t *majorVersion, int32_t *min
 }
 #endif
 
-#endif  // INC_EXTERNAL_ACL_ACL_H_
+#endif // INC_EXTERNAL_ACL_ACL_H_

third_party/fwkacllib/inc/ops/linalg_ops.h

@@ -82,6 +82,25 @@ REG_OP(Cholesky)
         DT_FLOAT16, DT_COMPLEX64, DT_COMPLEX128}))
     .OP_END_FACTORY_REG(Cholesky)
 
+/**
+*@brief Computes the outer product of two 1D vectors . \n
+
+*@par Inputs:
+*The input x and vec2 has to be a 1D vector.Inputs include:
+*@li x:A Tensor. Must be one of the following types: float16, float32. 
+Shape is [N] . \n
+*@li vec2:A Tensor. Must have the same type as x. Shape is [M] . \n
+
+*@par Outputs:
+*y:A Tensor. Has the same type as x . \n
+*/
+
+REG_OP(Ger)
+    .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT}))
+    .INPUT(vec2, TensorType({DT_FLOAT16, DT_FLOAT}))
+    .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT}))
+    .OP_END_FACTORY_REG(Ger)
+
 /**
 *@brief Computes the sign and the log of the absolute value of the determinant
 of one or more square matrices . \n

third_party/fwkacllib/inc/ops/nn_norm_ops.h

@@ -525,6 +525,31 @@ REG_OP(LayerNorm)
     .ATTR(epsilon, Float, 0.0000001)
     .OP_END_FACTORY_REG(LayerNorm)
 
+/**
+*@brief Returns a tensor where each sub-tensor of input along dimension 
+*       dim is normalized such that the p-norm of the sub-tensor is lower than the value maxnorm. \n
+
+*@par Inputs:
+*One input, including:
+* @li x: A Tensor. Must be one of the following types: float16, float32 . \n
+
+*@par Attributes:
+* @li p: Specify L_p norm, the type is float. 
+* @li dim: The processed dim, the type is int.
+* @li maxnorm: Threshold for comparison, the type is float.  \n
+
+*@par Outputs:
+*One outputs, including:
+* @li y: shape and dtype of output, should be same shape and type as input.
+*/
+REG_OP(Renorm)
+    .INPUT(x, TensorType::BasicType())
+    .OUTPUT(y, TensorType::BasicType())
+    .REQUIRED_ATTR(p, Float)
+    .REQUIRED_ATTR(dim, Int)
+    .REQUIRED_ATTR(maxnorm, Float)
+    .OP_END_FACTORY_REG(Renorm)
+
 /**
 *@brief LayerNormGrad operator interface implementation
 *  calculating: dy, x, variance, mean, gamma

third_party/fwkacllib/inc/ops/nn_pooling_ops.h

@@ -397,8 +397,8 @@ No default value.
 specifying the stride of the sliding window for each dimension of
 the input tensor. No default value.
 *@li padding: A required string type of float16.
-*@li pads: A list type of int32. Default value {0, 0, 0}.
-*@li dilation: A list type of int32. Default value {1, 1, 1}.
+*@li pads: A list type of int32. Default value {0,0,0,0,0,0}.
+*@li dilation: A list type of int32. Default value {1,1,1,1,1,1}.
 *@li ceil_mode: A ceil mode number of int32 . Default value 0.
 *@li data_format: An optional string. Defaults to "NDHWC" . \n
 
@@ -421,8 +421,8 @@ REG_OP(MaxPool3D)
     .REQUIRED_ATTR(ksize, ListInt)
     .REQUIRED_ATTR(strides, ListInt)
     .REQUIRED_ATTR(padding, String)
-    .ATTR(pads, ListInt, {0,0,0})
-    .ATTR(dilation, ListInt, {1,1,1})
+    .ATTR(pads, ListInt, {0,0,0,0,0,0})
+    .ATTR(dilation, ListInt, {1,1,1,1,1,1})
     .ATTR(ceil_mode, Int, 0)
     .ATTR(data_format, String, "NDHWC")
     .OP_END_FACTORY_REG(MaxPool3D)

third_party/fwkacllib/inc/ops/pad_ops.h

@@ -418,7 +418,7 @@ REG_OP(EmbeddingRankId)
 */
 REG_OP(FillV2)
     .INPUT(dims, TensorType({DT_INT16, DT_INT32, DT_INT64}))
-    .OUTPUT(y, TensorType({DT_FLOAT, DT_FLOAT, DT_DOUBLE, DT_INT8, DT_INT16, DT_INT32, DT_INT64}))
+    .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE, DT_INT8, DT_INT16, DT_INT32, DT_INT64}))
     .ATTR(value, Float, 0)
     .OP_END_FACTORY_REG(FillV2)
 
@@ -437,7 +437,7 @@ REG_OP(FillV2)
 * Compatible with the ONNX operator ConstantOfShape.
 */
 REG_OP(FillV2D)
-    .OUTPUT(y, TensorType({DT_FLOAT, DT_FLOAT, DT_DOUBLE, DT_INT8, DT_UINT8, DT_INT16, DT_INT32, DT_INT64}))
+    .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE, DT_INT8, DT_UINT8, DT_INT16, DT_INT32, DT_INT64}))
     .ATTR(value, Float, 0)
     .REQUIRED_ATTR(dims, ListInt)
     .OP_END_FACTORY_REG(FillV2D)