Operator argument consistency improvement.

Add values attribute to CONST operator.
Remove stale references to input tensor 0 and 1.
Remove out_t types where in and out are guaranteed
to be the same type.

Signed-off-by: Eric Kunze <eric.kunze@arm.com>
Change-Id: I75a8eb4dee67afbee3652d9e937aa0b82318dbd0

5 files changed, 174 insertions, 156 deletions

diff --git a/chapters/data_layout.adoc b/chapters/data_layout.adoc
index 4e6d24d..e764be9 100644
--- a/chapters/data_layout.adoc
+++ b/chapters/data_layout.adoc
@@ -20,7 +20,7 @@ Concatenate two tensors along a given axis. No data conversion happens during a
 |Input|in_t*|input1|shape1|Input tensor with rank from 1 to 4
 |Input|in_t*|input2|shape2|Input tensor with rank matching input1
 |Attribute|int|axis|-|Axis along which concatenation is to occur.
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Operation Function:*
@@ -30,7 +30,7 @@ Concatenate two tensors along a given axis. No data conversion happens during a
 for_each (index1 in shape) {
     index2 = index1
     index2[axis] = index1[axis] - shape1[axis]
-    value = (index2[axis] < 0) ?
+    in_t value = (index2[axis] < 0) ?
         tensor_read<in_t>(input1, shape1, index1) :
         tensor_read<in_t>(input2, shape2, index2) ;
     tensor_write<in_t>(output, shape, index1, value);
@@ -40,13 +40,13 @@ for_each (index1 in shape) {
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|Any|Boolean|bool|bool
-|Any|signed 8|int8/aint8|int8/aint8
-|Any|signed 16|int16|int16
-|Any|signed 32|int32|int32
-|MI, MT|float|float|float
+|Any|Boolean|bool
+|Any|signed 8|int8/aint8
+|Any|signed 16|int16
+|Any|signed 32|int32
+|MI, MT|float|float
 |===
 
 ==== PAD
@@ -60,7 +60,7 @@ Zero-pads a tensor along borders of each dimension.
 
 |Input|in_t*|input1|shape1|Input tensor
 |Attribute|int|padding|[rank(input1),2]|Amount of padding to be done
-|Output|out_t*|output|shape|Output tensor of same type as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type as the input tensor
 |===
 
 *Quantization Parameters:*
@@ -80,7 +80,7 @@ for_each (index in shape) {
     for (i=0; i<rank(shape); i++) {
         index1[i] = index1[i] - padding[i,0]
     }
-    value = tensor_read<in_t>(input1, shape1, index1, input1_zp, padding)
+    in_t value = tensor_read<in_t>(input1, shape1, index1, input1_zp, padding)
     tensor_write<in_t>(output, shape, index, value + input1_zp);
 }
 ----
@@ -88,13 +88,13 @@ for_each (index in shape) {
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|Any|Boolean|bool|bool
-|Any|signed 8|int8/aint8|int8/aint8
-|Any|signed 16|int16|int16
-|Any|signed 32|int32|int32
-|MI, MT|float|float|float
+|Any|Boolean|bool
+|Any|signed 8|int8/aint8
+|Any|signed 16|int16
+|Any|signed 32|int32
+|MI, MT|float|float
 |===
 
 ==== RESHAPE
@@ -108,7 +108,7 @@ Returns a tensor with the same type/values as the input, with a new shape specif
 
 |Input|in_t*|input1|shape1|Input tensor
 |Attribute|int|new_shape|[rank(output)]|List of values, with each element giving the size of the result tensor for the given dimension. At most one dimension may be given as-1 to automatically calculate the dimension size.
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Operation Function:*
@@ -124,13 +124,13 @@ for (i=0; i<tensor_size(shape); i++) {
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|Any|Boolean|bool|bool
-|Any|signed 8|int8/aint8|int8/aint8
-|Any|signed 16|int16|int16
-|Any|signed 32|int32|int32
-|MI, MT|float|float|float
+|Any|Boolean|bool
+|Any|signed 8|int8/aint8
+|Any|signed 16|int16
+|Any|signed 32|int32
+|MI, MT|float|float
 |===
 
 ==== REVERSE
@@ -144,7 +144,7 @@ Returns a tensor with the same type/values as the input, with the data reversed
 
 |Input|in_t*|input|shape|Input tensor from 1 to 4 dims
 |Attribute|int|axis|-|Axis to reverse
-|Output|out_t*|output|shape|Output tensor. Same shape as input tensor.
+|Output|in_t*|output|shape|Output tensor. Same shape as input tensor.
 |===
 
 *Operation Function:*
@@ -155,7 +155,7 @@ assert(0<=axis && axis<rank(shape))
 for_each (index in shape) {
     tmp_index = index;
     tmp_index[axis] = shape[axis]-1-index[axis];
-    value = tensor_read<in_t>(input, shape, tmp_index);
+    in_t value = tensor_read<in_t>(input, shape, tmp_index);
     tensor_write<in_t>(output, shape, index, value);
 }
 ----
@@ -163,27 +163,27 @@ for_each (index in shape) {
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|Any|Boolean|bool|bool
-|Any|signed 8|int8/aint8|int8/aint8
-|Any|signed 16|int16|int16
-|Any|signed 32|int32|int32
-|MI, MT|float|float|float
+|Any|Boolean|bool
+|Any|signed 8|int8/aint8
+|Any|signed 16|int16
+|Any|signed 32|int32
+|MI, MT|float|float
 |===
 
 ==== SLICE
 
-Extracts a slice of the input tensor 0 on the given axis, beginning at the start coordinates, and extending for size elements in each direction. No data conversion happens during a slice operation.
+Extracts a slice of the input1 on the given axis, beginning at the start coordinates, and extending for size elements in each direction. No data conversion happens during a slice operation.
 
 *Arguments:*
 |===
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape1|Input tensor with rank from 1 to 4
-|Attribute|int|start|[rank(input1)]|List of integer coordinates, of length equal to the rank of input 0. Start coordinate for slicing.
-|Attribute|int|size|[rank(input1)]|List of integer size values, of length equal to the rank of input 0. Size of the input to be used.
-|Output|out_t*|output|shape|Output tensor of same type as the input tensor
+|Attribute|int|start|[rank(input1)]|List of integer coordinates, of length equal to the rank of input1. Start coordinate for slicing.
+|Attribute|int|size|[rank(input1)]|List of integer size values, of length equal to the rank of input1. Size of the input to be used.
+|Output|in_t*|output|shape|Output tensor of same type as the input tensor
 |===
 
 *Operation Function:*
@@ -195,7 +195,7 @@ for_each (index in shape) {
     for (i=0; i<rank(shape); i++) {
        tmp_index[i] = index[i] + start[i];
     }
-    value = tensor_read<in_t>(input, shape1, tmp_index);
+    in_t value = tensor_read<in_t>(input, shape1, tmp_index);
     tensor_write<in_t>(output, shape, index, value);
 }
 ----
@@ -203,18 +203,18 @@ for_each (index in shape) {
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|Any|Boolean|bool|bool
-|Any|signed 8|int8/aint8|int8/aint8
-|Any|signed 16|int16|int16
-|Any|signed 32|int32|int32
-|MI, MT|float|float|float
+|Any|Boolean|bool
+|Any|signed 8|int8/aint8
+|Any|signed 16|int16
+|Any|signed 32|int32
+|MI, MT|float|float
 |===
 
 ==== TILE
 
-Replicates input 0 multiplies times along each dimension.
+Replicates input1 multiplies times along each dimension.
 
 *Arguments:*
 
@@ -223,7 +223,7 @@ Replicates input 0 multiplies times along each dimension.
 
 |Input|in_t*|input1|shape1|Input tensor with rank from 1 to 4
 |Attribute|int|multiplies|[rank(shape1)]|Number of times to replicate input1 in each dimension
-|Output|out_t*|output|shape|Output tensor of same type, rank as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, rank as the input tensor
 |===
 
 *Operation Function:*
@@ -236,7 +236,7 @@ for_each (index in shape) {
         assert(shape1[i] * multiplies[i] == shape[i])
         tmp_index[i] = index[i] % shape1[i]
     }
-    value = tensor_read<in_t>(input, shape1, tmp_index);
+    in_t value = tensor_read<in_t>(input, shape1, tmp_index);
     tensor_write<in_t>(output, shape, index, value);
 }
 ----
@@ -244,13 +244,13 @@ for_each (index in shape) {
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|Any|Boolean|bool|bool
-|Any|signed 8|int8/aint8|int8/aint8
-|Any|signed 16|int16|int16
-|Any|signed 32|int32|int32
-|MI, MT|float|float|float
+|Any|Boolean|bool
+|Any|signed 8|int8/aint8
+|Any|signed 16|int16
+|Any|signed 32|int32
+|MI, MT|float|float
 |===
 
 ==== TRANSPOSE
@@ -264,7 +264,7 @@ Permutes the dimensions based on perm.
 
 |Input|in_t*|input1|shape1|Input tensor with rank from 1 to 4
 |Attribute|int|perms|[rank(input1)]|List of integers of length equal to the rank of input1.
-|Output|out_t*|output|shape|Output tensor of same type, rank as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, rank as the input tensor
 |===
 
 *Operation Function:*
@@ -277,7 +277,7 @@ for_each (index in shape) {
         assert(shape1[perm[i]] == shape[i])
         tmp_index[perm[i]] = index[i]
     }
-    value = tensor_read<in_t>(input, shape1, tmp_index);
+    in_t value = tensor_read<in_t>(input, shape1, tmp_index);
     tensor_write<in_t>(output, shape, index, value);
 }
 ----
@@ -285,11 +285,11 @@ for_each (index in shape) {
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|Any|Boolean|bool|bool
-|Any|signed 8|int8/aint8|int8/aint8
-|Any|signed 16|int16|int16
-|Any|signed 32|int32|int32
-|MI, MT|float|float|float
+|Any|Boolean|bool
+|Any|signed 8|int8/aint8
+|Any|signed 16|int16
+|Any|signed 32|int32
+|MI, MT|float|float
 |===
diff --git a/chapters/data_nodes.adoc b/chapters/data_nodes.adoc
index ba38ef9..6164a95 100644
--- a/chapters/data_nodes.adoc
+++ b/chapters/data_nodes.adoc
@@ -18,6 +18,7 @@ A node containing constant data for use as the input to an operation. May hold d
 |===
 |Argument|Type|Name|Shape|Description
 
+|Attribute|out_t*|values|shape|Constant values
 |Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
@@ -43,19 +44,19 @@ Returns a tensor with the same shape, type, and contents as the input.
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t|input1|shape|Input tensor
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|Any|Boolean|bool|bool
-|Any|signed 8|int8/aint8|int8/aint8
-|Any|signed 16|int16|int16
-|Any|signed 32|int32|int32
-|MI, MT|float|float|float
+|Any|Boolean|bool
+|Any|signed 8|int8/aint8
+|Any|signed 16|int16
+|Any|signed 32|int32
+|MI, MT|float|float
 |===
 
 ==== IDENTITYN
@@ -68,19 +69,19 @@ Returns a list of tensors with the same shape, type, and contents as the input l
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t|input1|[shape1, shape2, …]|List of input tensors
-|Output|out_t*|output|[shape1, shape2, …]|List of output tensors of same type, size as the input tensors
+|Output|in_t*|output|[shape1, shape2, …]|List of output tensors of same type, size as the input tensors
 |===
 
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|Any|Boolean|bool|bool
-|Any|signed 8|int8/aint8|int8/aint8
-|Any|signed 16|int16|int16
-|Any|signed 32|int32|int32
-|MI, MT|float|float|float
+|Any|Boolean|bool
+|Any|signed 8|int8/aint8
+|Any|signed 16|int16
+|Any|signed 32|int32
+|MI, MT|float|float
 |===
 
 ==== PLACEHOLDER
diff --git a/chapters/ewise_binary.adoc b/chapters/ewise_binary.adoc
index a9787b3..f3c9fbe 100644
--- a/chapters/ewise_binary.adoc
+++ b/chapters/ewise_binary.adoc
@@ -11,7 +11,8 @@
 
 ==== ADD
 
-Elementwise addition of input1 and input2. Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
+Elementwise addition of input1 and input2.
+Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -48,7 +49,8 @@ for_each (index in shape) {
 
 ==== ARITHMETIC_RIGHT_SHIFT
 
-Elementwise arithmetic right shift of input1 by the amount specified in input2. Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
+Elementwise arithmetic right shift of input1 by the amount specified in input2.
+Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -92,7 +94,8 @@ for_each (index in shape) {
 
 ==== BITWISE_AND
 
-Elementwise bitwise AND of input tensor 0 and input tensor 1. Axis of size 1 will be broadcast as necessary. Rank of input tensors must match.
+Elementwise bitwise AND of input1 and input2.
+Axis of size 1 will be broadcast as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -130,7 +133,8 @@ for_each (index in shape) {
 
 ==== BITWISE_OR
 
-Elementwise bitwise OR of input1 and input2. Axis of size 1 will be broadcast as necessary. Rank of input tensors must match.
+Elementwise bitwise OR of input1 and input2.
+Axis of size 1 will be broadcast as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -168,7 +172,8 @@ for_each (index in shape) {
 
 ==== BITWISE_XOR
 
-Elementwise bitwise XOR of input1 and input2. Axis of size 1 will be broadcast as necessary. Rank of input tensors must match.
+Elementwise bitwise XOR of input1 and input2.
+Axis of size 1 will be broadcast as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -206,7 +211,8 @@ for_each (index in shape) {
 
 ==== LOGICAL_AND
 
-Elementwise logical AND of input1 and input2. Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
+Elementwise logical AND of input1 and input2.
+Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -246,7 +252,8 @@ for_each (index in shape) {
 
 ==== LOGICAL_LEFT_SHIFT
 
-Elementwise left shift of input1 and input2. Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
+Elementwise left shift of input1 and input2.
+Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -285,7 +292,8 @@ for_each (index in shape) {
 
 ==== LOGICAL_RIGHT_SHIFT
 
-Elementwise logical right shift of input1 by the amount specified in input2. Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
+Elementwise logical right shift of input1 by the amount specified in input2.
+Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -324,7 +332,8 @@ for_each (index in shape) {
 
 ==== LOGICAL_OR
 
-Elementwise logical OR of input1 and input2. Axis of size 1 will be broadcast as necessary. Rank of input tensors must match.
+Elementwise logical OR of input1 and input2.
+Axis of size 1 will be broadcast as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -360,7 +369,8 @@ for_each (index in shape) {
 
 ==== LOGICAL_XOR
 
-Elementwise logical XOR of input tensor 0 and input tensor 1. Axis of size 1 will be broadcast as necessary. Rank of input tensors must match.
+Elementwise logical XOR of input1 and input2.
+Axis of size 1 will be broadcast as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -368,7 +378,7 @@ Elementwise logical XOR of input tensor 0 and input tensor 1. Axis of size 1 wil
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape1|Input tensor from 1 to 4 dims
-|Input|in_t*|input2|shape2|Input tensor with the same rank as Input 0
+|Input|in_t*|input2|shape2|Input tensor with the same rank as input1
 |Output|in_t*|output|shape|Output tensor of same type as the input tensors, with broadcast shape if necessary
 |===
 
@@ -396,7 +406,8 @@ for_each (index in shape) {
 
 ==== MAXIMUM
 
-Elementwise max of input1 and input2. Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
+Elementwise max of input1 and input2.
+Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -433,7 +444,8 @@ for_each (index in shape) {
 
 ==== MINIMUM
 
-Elementwise minimum of input tensor 0 and input tensor 1. Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
+Elementwise minimum of input1 and input2.
+Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -470,7 +482,8 @@ for_each (index in shape) {
 
 ==== MUL
 
-Elementwise multiplication (Hadamard product) of input tensor 0 and input tensor 1. Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
+Elementwise multiplication (Hadamard product) of input1 and input2.
+Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -478,7 +491,7 @@ Elementwise multiplication (Hadamard product) of input tensor 0 and input tensor
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape1|Input tensor
-|Input|in_t*|input2|shape2|Input tensor with the same rank as Input 0
+|Input|in_t*|input2|shape2|Input tensor with the same rank as input1
 |Input (MT profile) Attribute (BI/MI profiles)|uint6_t|shift|-|Result right shift (int32 data type only)
 |Output|out_t*|output|shape|Output tensor with broadcast shape if necessary
 |===
@@ -514,7 +527,8 @@ for_each (index in shape) {
 
 ==== POW
 
-Elementwise input tensor 0 value raised to the power of input 1 tensor. Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
+Elementwise input1 value raised to the power of input2.
+Axis of size 1 will be broadcast, as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -522,7 +536,7 @@ Elementwise input tensor 0 value raised to the power of input 1 tensor. Axis of
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape1|Input tensor from 1 to 4 dims
-|Input|in_t*|input2|shape2|Input tensor with the same rank as Input 0
+|Input|in_t*|input2|shape2|Input tensor with the same rank as input1
 |Output|in_t*|output|shape|Output tensor of same type as the input tensors, with broadcast shape if necessary
 |===
 
@@ -540,7 +554,8 @@ Only supported with floating point values.
 
 ==== SUB
 
-Elementwise subtraction of input tensor 0 and input tensor 1. Axis of size 1 will be broadcast as necessary. Rank of input tensors must match.
+Elementwise subtraction of input1 and input2.
+Axis of size 1 will be broadcast as necessary. Rank of input tensors must match.
 
 *Arguments:*
 
@@ -548,7 +563,7 @@ Elementwise subtraction of input tensor 0 and input tensor 1. Axis of size 1 wil
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape1|Input tensor
-|Input|in_t*|input2|shape2|Input tensor with the same rank as Input 0
+|Input|in_t*|input2|shape2|Input tensor with the same rank as input1
 |Output|in_t*|output|shape|Output tensor with broadcast shape if necessary
 |===
 
diff --git a/chapters/ewise_ternary.adoc b/chapters/ewise_ternary.adoc
index 1724777..8dc9172 100644
--- a/chapters/ewise_ternary.adoc
+++ b/chapters/ewise_ternary.adoc
@@ -18,10 +18,10 @@ Elementwise select of the output based on a condition.
 |===
 |Argument|Type|Name|Shape|Description
 
-|Input|bool_t|input1|shape1|
-|Input|in_t*|input2|shape2|Input tensor from 1 to 4 dims
-|Input|in_t*|input3|shape3|Input tensor with the same rank as Input 0
-|Output|out_t*|output|shape|Output tensor of same type, as the input tensors, with broadcast shape if necessary
+|Input|bool_t|input1|shape1|Input selector tensor
+|Input|in_t*|input2|shape2|Input value tensor if input1 is True
+|Input|in_t*|input3|shape3|Input value tensor if input1 is False
+|Output|in_t*|output|shape|Output tensor of same type as input2 and input3, with broadcast shape if necessary
 |===
 
 *Quantization Parameters:*
@@ -39,22 +39,23 @@ for_each (index in shape) {
     bool_t value1 = tensor_read<in_t>(input1, shape1, index1)
     in_t value2 = tensor_read<in_t>(input2, shape2, index2)
     in_t value3 = tensor_read<in_t>(input3, shape3, index3)
+    in_t acc = 0
     if (value1 == True){
-         in_t acc = value2
+         acc = value2
     } else {
-         in_t acc = value3
+         acc = value3
     }
-    tensor_write<out_t>(output, shape, index, acc)
+    tensor_write<in_t>(output, shape, index, acc)
 }
 ----
 
 *Supported Data Types:*
 |===
-|Profile|Mode|bool_t|in_t|out_t
+|Profile|Mode|bool_t|in_t
 
-|Any|Boolean|bool|bool|bool
-|Any|signed 8|bool|aint8/int8|aint8/int8
-|Any|signed 16|bool|int16|int16
-|Any|signed 32|bool|int32|int32
-|MI, MT|float|bool|float|float
+|Any|Boolean|bool|bool
+|Any|signed 8|bool|aint8/int8
+|Any|signed 16|bool|int16
+|Any|signed 32|bool|int32
+|MI, MT|float|bool|float
 |===
diff --git a/chapters/ewise_unary.adoc b/chapters/ewise_unary.adoc
index 34b64a9..7df32ba 100644
--- a/chapters/ewise_unary.adoc
+++ b/chapters/ewise_unary.adoc
@@ -19,7 +19,7 @@ Elementwise absolute value operation
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape|Input tensor
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Operation Function:*
@@ -27,10 +27,10 @@ Elementwise absolute value operation
 [source,c]
 ----
 for_each (index in shape) {
-    int32_t value1 = tensor_read<in_t>(input1, shape, index)
+    in_t value1 = tensor_read<in_t>(input1, shape, index)
     if (value1 < 0)
-        value1 = apply_sub<out_t>(0, value1)
-    tensor_write<out_t>(output, shape, index, value1)
+        value1 = apply_sub<in_t>(0, value1)
+    tensor_write<in_t>(output, shape, index, value1)
 }
 ----
 
@@ -39,8 +39,8 @@ for_each (index in shape) {
 |===
 |Profile|Mode|in_t|out_t
 
-|Any|signed 32|int32|int32
-|MI, MT|float|float|float
+|Any|signed 32|int32
+|MI, MT|float|float
 |===
 
 ==== BITWISE_NOT
@@ -53,7 +53,7 @@ Elementwise bitwise NOT of input tensor.
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape|Input tensor
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Quantization Parameters:*
@@ -65,20 +65,20 @@ None
 [source,c]
 ----
 for_each (index in shape) {
-    int32_t value1 = tensor_read<in_t>(input1, shape, index)
-    int32_t acc = ~value1
-    tensor_write<out_t>(output, shape, index, acc)
+    in_t value1 = tensor_read<in_t>(input1, shape, index)
+    in_t acc = ~value1
+    tensor_write<in_t>(output, shape, index, acc)
 }
 ----
 
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|Any|signed 8|aint8|aint8
-|Any|signed 16|int16|int16
-|Any|signed 32|int32|int32
+|Any|signed 8|aint8
+|Any|signed 16|int16
+|Any|signed 32|int32
 |===
 
 ==== CEIL
@@ -91,15 +91,15 @@ Elementwise ceiling operation
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape|Input tensor
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|MI, MT|float|float|float
+|MI, MT|float|float
 |===
 
 ==== CLZ
@@ -112,7 +112,7 @@ Elementwise count leading zeros operation
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape|Input tensor
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Operation Function:*
@@ -120,7 +120,8 @@ Elementwise count leading zeros operation
 [source,c]
 ----
 for_each (index in shape) {
-    int32_t value1 = tensor_read<in_t>(input1, shape, index)
+    in_t acc = 0
+    in_t value1 = tensor_read<in_t>(input1, shape, index)
     if (value1 == 0) {
          acc = 32 // input1_width
     }
@@ -132,15 +133,15 @@ for_each (index in shape) {
             acc = acc + 1
          }
     }
-    tensor_write<out_t>(output, shape, index, acc)
+    tensor_write<in_t>(output, shape, index, acc)
 }
 ----
 
 *Supported Data Types:*
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|Any|signed 32|int32|int32
+|Any|signed 32|int32
 |===
 
 ==== EXP
@@ -153,15 +154,15 @@ Elementwise e to the x operation
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape|Input tensor
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Supported Data Types:*
 
 |===
-|Profile|Mode|Input 0|Output
+|Profile|Mode|in_t
 
-|Any|float|float|float
+|Any|float|float
 |===
 
 ==== FLOOR
@@ -174,15 +175,15 @@ Elementwise floor operation
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape|Input tensor
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|MI, MT|float|float|float
+|MI, MT|float|float
 |===
 
 ==== LOG
@@ -195,15 +196,15 @@ Elementwise natural logarithm operation
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape|Input tensor
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Supported Data Types:*
 
 |===
-|Profile|Mode|in_t|out_t
+|Profile|Mode|in_t
 
-|MI, MT|float|float|float
+|MI, MT|float|float
 |===
 
 ==== LOGICAL_NOT
@@ -216,7 +217,7 @@ Elementwise logical NOT of input.
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape|Input tensor
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Quantization Parameters:*
@@ -252,7 +253,7 @@ Elementwise negation operation
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape|Input tensor
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Quantization Parameters:*
@@ -261,7 +262,7 @@ Elementwise negation operation
 |Argument|Type|Name|Shape|Description
 
 |Attribute|in_t|input1_zp|-|Input 1 zero point
-|Attribute|out_t|output_zp|-|Output zero point
+|Attribute|in_t|output_zp|-|Output zero point
 |===
 
 *Operation Function:*
@@ -269,24 +270,24 @@ Elementwise negation operation
 [source,c]
 ----
 assert(in_t == aint8_t || input_zp == 0) // Zero point only for asymmetric int8
-assert(out_t == aint8_t || output_zp == 0) // Zero point only for asymmetric int8
+assert(in_t == aint8_t || output_zp == 0) // Zero point only for asymmetric int8
 for_each (index in shape) {
-    int32_t value1 = tensor_read<in_t>(input1, shape, index)
-    int32_t acc = appl_sub<int32_t>(0, value1 - input1_zp)
-    acc = apply_clip(acc, minimum<out_t>, maximum<out_t>)
-    tensor_write<out_t>(output + output_zp, shape, index, acc)
+    in_t value1 = tensor_read<in_t>(input1, shape, index)
+    in_t acc = appl_sub<in_t>(0, value1 - input1_zp)
+    acc = apply_clip(acc, minimum<in_t>, maximum<in_t>)
+    tensor_write<in_t>(output + output_zp, shape, index, acc)
 }
 ----
 
 *Supported Data Types:*
 
 |===
-|Profile|Mode|Input 0|Output
+|Profile|Mode|in_t
 
-|Any|signed 8|aint8|aint8
-|Any|signed 16|int16|int16
-|Any|signed 32|int32|int32
-|MI, MT|float|float|float
+|Any|signed 8|aint8
+|Any|signed 16|int16
+|Any|signed 32|int32
+|MI, MT|float|float
 |===
 
 ==== RECIPROCAL
@@ -299,15 +300,15 @@ Elementwise reciprocal operation. For integer operation, a TABLE should be used
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape|Input tensor
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Supported Data Types:*
 
 |===
-|Profile|Mode|Input 0|Output
+|Profile|Mode|in_t
 
-|MI, MT|float|float|float
+|MI, MT|float|float
 |===
 
 ==== RSQRT
@@ -320,13 +321,13 @@ Elementwise reciprocal square root operation. For integer operation, a TABLE sho
 |Argument|Type|Name|Shape|Description
 
 |Input|in_t*|input1|shape|Input tensor
-|Output|out_t*|output|shape|Output tensor of same type, size as the input tensor
+|Output|in_t*|output|shape|Output tensor of same type, size as the input tensor
 |===
 
 *Supported Data Types:*
 
 |===
-|Profile|Mode|Input 0|Output
+|Profile|Mode|in_t
 
-|MI, MT|float|float|float
-|===
\ No newline at end of file
+|MI, MT|float|float
+|===