Add TENSOR_QUANT8_ASYMM_SIGNED support for more ops

Updated:
  CONCATENATION
  REDUCE_MIN
  REDUCE_MAX
  STRIDED_SLICE
  RESHAPE
  SQUEEZE
  MEAN

Bug: 143934554
Bug: 143935314
Bug: 143934726
Bug: 143934771
Bug: 143934557
Bug: 143934306
Bug: 143935140
Test: quantization coupling tests in CTS and VTS
Change-Id: Ie73d070fd6f0a27185c1f26561710635b6e03b26
Merged-In: Ie73d070fd6f0a27185c1f26561710635b6e03b26
(cherry picked from commit 91134e7fb9cd0b6830d5fdbd6f640f631f283c25)
diff --git a/current.txt b/current.txt
index 7074f22..9c554e8 100644
--- a/current.txt
+++ b/current.txt
@@ -575,10 +575,10 @@
 b69a7615c508acf5c5201efd1bfa3262167874fc3594e2db5a3ff93addd8ac75 android.hardware.keymaster@4.0::IKeymasterDevice
 eb2fa0c883c2185d514be0b84c179b283753ef0c1b77b45b4f359bd23bba8b75 android.hardware.neuralnetworks@1.0::IPreparedModel
 f1109cbb10297b7429a11fab42afa912710b303c9bf20bd5cdb8bd57b9c84186 android.hardware.neuralnetworks@1.0::types
-9d8ee57c490ffeaa28f702eaea8d198cb510e4bbfb99e6cb5f63e73341057c7c android.hardware.neuralnetworks@1.1::types
+5f6d3097ba84cb63c430787123f4de1b31c11f90b531b98eae9a8623a5ae962a android.hardware.neuralnetworks@1.1::types
 fb382e986c10b8fbb797a8546e8f9ea6d1107bfe6f3fb7e57f6bbbf1f807a906 android.hardware.neuralnetworks@1.2::IDevice
 40e71cd693de5b832325c5d8f081f2ff20a7ba2b89d401cee5b4b3eb0e241681 android.hardware.neuralnetworks@1.2::IPreparedModel
-b40eb9dc491e3b203be2edca330ccd0417e9ca77b1b1b0f4c628a5fd269764a2 android.hardware.neuralnetworks@1.2::types
+2d5483fbf59d5fd2de94665a6df05da5c3d09de67561d0db5e9f09e59e9aea46 android.hardware.neuralnetworks@1.2::types
 a785a57447a81e9c130eef6904c3a5c256076c6a04588c40620ebd6fa2660d77 android.hardware.radio@1.2::types
 1a6e2bd289f22931c526b21916910f1d4c436b7acb9556e4243de4ce8e6cc2e4 android.hardware.soundtrigger@2.0::ISoundTriggerHwCallback
 fd65298e1e09e0e3c781ab18305920d757dbe55a3b459ce17814ec5cf6dfee99 android.hardware.wifi@1.0::IWifiP2pIface
@@ -597,7 +597,7 @@
 9e59fffceed0dd72a9799e04505db5f777bbbea1af0695ba4107ef6d967c6fda android.hardware.neuralnetworks@1.3::IDevice
 4a6c3b3556da951b4def21ba579a227c022980fe4465df6cdfbe20628fa75f5a android.hardware.neuralnetworks@1.3::IPreparedModel
 94e803236398bed1febb11cc21051bc42ec003700139b099d6c479e02a7ca3c3 android.hardware.neuralnetworks@1.3::IPreparedModelCallback
-8900b3a4ef6c0be540821fad0ad8b58b3654b70cfa38df662c640b88ea486d9f android.hardware.neuralnetworks@1.3::types
+cf1d55e8c68300090747ab90b94c22e4c859b29c84ced68a317c595bb115eab2 android.hardware.neuralnetworks@1.3::types
 3e01d4446cd69fd1c48f8572efd97487bc179564b32bd795800b97bbe10be37b android.hardware.wifi@1.4::IWifi
 a64467bae843569f0d465c5be7f0c7a5b987985b55a3ef4794dd5afc68538650 android.hardware.wifi.supplicant@1.3::ISupplicant
 44445b8a03d7b9e68b2fbd954672c18a8fce9e32851b0692f4f4ab3407f86ecb android.hardware.wifi.supplicant@1.3::ISupplicantStaIface
diff --git a/neuralnetworks/1.1/types.hal b/neuralnetworks/1.1/types.hal
index 3d78fb6..da7ba78 100644
--- a/neuralnetworks/1.1/types.hal
+++ b/neuralnetworks/1.1/types.hal
@@ -125,7 +125,7 @@
      * Outputs:
      * * 0: A tensor of the same {@link OperandType} as input0.
      *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
-     *      the scale and zeroPoint must be same as input0.
+     *      the scale and zeroPoint must be the same as input0.
      */
     MEAN = 31,
 
diff --git a/neuralnetworks/1.2/types.hal b/neuralnetworks/1.2/types.hal
index 65ee81c..b111d96 100644
--- a/neuralnetworks/1.2/types.hal
+++ b/neuralnetworks/1.2/types.hal
@@ -1954,7 +1954,7 @@
      * Outputs:
      * * 0: A tensor of the same {@link OperandType} as input0.
      *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
-     *      the scale and zeroPoint must be same as input0.
+     *      the scale and zeroPoint must be the same as input0.
      */
     MEAN = @1.1::OperationType:MEAN,
 
@@ -3141,8 +3141,8 @@
      *      {@link SymmPerChannelQuantParams}) must be set to 0.
      * * 2: A 1-D tensor, of shape [depth_out], specifying the bias. For input
      *      tensor of type {@link OperandType::TENSOR_FLOAT32} or
-     *      {@link OperandType::TENSOR_FLOAT16}, the bias must be of the same type.
-     *      For filter tensor of {@link OperandType::TENSOR_QUANT8_ASYMM},
+     *      {@link OperandType::TENSOR_FLOAT16}, the bias must be of the same
+     *      type. For filter tensor of {@link OperandType::TENSOR_QUANT8_ASYMM},
      *      the bias should be of {@link OperandType::TENSOR_INT32}, with zeroPoint
      *      of 0 and bias_scale == input_scale * filter_scale. For filter tensor
      *      of {@link OperandType::TENSOR_QUANT8_SYMM_PER_CHANNEL}, the bias
@@ -3181,8 +3181,7 @@
      * * 2: A 1-D tensor, of shape [depth_out], specifying the bias. For input
      *      tensor of type {@link OperandType::TENSOR_FLOAT32} or
      *      {@link OperandType::TENSOR_FLOAT16}, the bias must be of the same
-     *      {@link OperandType::TENSOR_FLOAT16}, the bias must be of the same type.
-     *      For filter tensor of {@link OperandType::TENSOR_QUANT8_ASYMM},
+     *      type. For filter tensor of {@link OperandType::TENSOR_QUANT8_ASYMM},
      *      the bias should be of {@link OperandType::TENSOR_INT32}, with zeroPoint
      *      of 0 and bias_scale == input_scale * filter_scale. For filter tensor
      *      of {@link OperandType::TENSOR_QUANT8_SYMM_PER_CHANNEL}, the bias
@@ -3669,17 +3668,14 @@
     /**
      * Quantizes the input tensor.
      *
-     * The formula for {@link OperandType::TENSOR_QUANT8_ASYMM} output tensor is:
+     * The formula is:
      *
      *     output = max(0, min(255, round(input / scale) + zeroPoint)
      *
-     * Supported input tensor {@link OperandType}:
+     * Supported tensor {@link OperandType}:
      * * {@link OperandType::TENSOR_FLOAT16}
      * * {@link OperandType::TENSOR_FLOAT32}
      *
-     * Supported output tensor {@link OperandType}:
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     *
      * Supported tensor rank: from 1
      *
      * Inputs:
diff --git a/neuralnetworks/1.3/types.hal b/neuralnetworks/1.3/types.hal
index 5fbf4e6..84c4813 100644
--- a/neuralnetworks/1.3/types.hal
+++ b/neuralnetworks/1.3/types.hal
@@ -228,6 +228,7 @@
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
      *   (full support since HAL version 1.2, see the input section)
+     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: up to 4
      *
@@ -237,6 +238,9 @@
      *            Before HAL version 1.2, all input tensors of
      *            {@link OperandType::TENSOR_QUANT8_ASYMM}
      *            must have the same scale and zeroPoint as the output tensor.
+     *            Input tensors of
+     *            {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED}
+     *            are allowed to have different scale and zeroPoint.
      *            Since HAL version 1.2, zero-sized tensors are supported.
      * * n: An {@link OperandType::INT32} scalar, specifying the
      *      concatenation axis.
@@ -247,6 +251,8 @@
      *      Since HAL version 1.2, for a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint values can be different from
      *      input tensors. Before HAL version 1.2 they have to be the same as for the input tensors.
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      the scale and zeroPoint values can be different from input tensors.
      */
     CONCATENATION = @1.2::OperationType:CONCATENATION,
 
@@ -563,7 +569,6 @@
      * * {@link OperandType::TENSOR_FLOAT16} (since HAL version 1.2)
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: 4, with "NHWC" or "NCHW" data layout.
      * With the default data layout NHWC, the data is stored in the order of:
@@ -584,8 +589,7 @@
      * Outputs:
      * * 0: The output 4-D tensor, of shape [batch, height*block_size,
      *      width*block_size, depth/(block_size*block_size)].
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     DEPTH_TO_SPACE = @1.2::OperationType:DEPTH_TO_SPACE,
@@ -1469,6 +1473,7 @@
      * * {@link OperandType::TENSOR_FLOAT16} (since HAL version 1.2)
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: up to 4.
      *
@@ -1485,7 +1490,8 @@
      *
      * Outputs:
      * * 0: The output tensor, of shape specified by the input shape.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
+     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     RESHAPE = @1.2::OperationType:RESHAPE,
@@ -1501,7 +1507,6 @@
      * * {@link OperandType::TENSOR_FLOAT16} (since HAL version 1.2)
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM} (since HAL version 1.2)
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: 4, with "NHWC" or "NCHW" data layout.
      * With the default data layout NHWC, the data is stored in the order of:
@@ -1544,8 +1549,7 @@
      * Outputs:
      * * 0: The output 4-D tensor, of shape
      *      [batches, new_height, new_width, depth].
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     RESIZE_BILINEAR = @1.2::OperationType:RESIZE_BILINEAR,
@@ -1664,7 +1668,6 @@
      * * {@link OperandType::TENSOR_FLOAT16} (since HAL version 1.2)
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: 4, with "NHWC" or "NCHW" data layout.
      * With the default data layout NHWC, the data is stored in the order of:
@@ -1685,8 +1688,7 @@
      * Outputs:
      * * 0: The output 4-D tensor, of shape [batches, height/block_size,
      *      width/block_size, depth_in*block_size*block_size].
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     SPACE_TO_DEPTH = @1.2::OperationType:SPACE_TO_DEPTH,
@@ -1810,7 +1812,6 @@
      * * {@link OperandType::TENSOR_FLOAT16} (since HAL version 1.2)
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: 4, with "NHWC" or "NCHW" data layout.
      * With the default data layout NHWC, the data is stored in the order of:
@@ -1829,8 +1830,7 @@
      *
      * Outputs:
      * * 0: A tensor of the same {@link OperandType} as input0.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     BATCH_TO_SPACE_ND = @1.2::OperationType:BATCH_TO_SPACE_ND,
@@ -1890,6 +1890,7 @@
      * * {@link OperandType::TENSOR_FLOAT16} (since HAL version 1.2)
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: up to 4
      *
@@ -1909,8 +1910,9 @@
      *
      * Outputs:
      * * 0: A tensor of the same {@link OperandType} as input0.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
-     *      the scale and zeroPoint must be same as input0.
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
+     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      the scale and zeroPoint must be the same as input0.
      */
     MEAN = @1.2::OperationType:MEAN,
 
@@ -1923,7 +1925,6 @@
      * * {@link OperandType::TENSOR_FLOAT16} (since HAL version 1.2)
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *   (full support since HAL version 1.2, see the output section)
      *
      * Supported tensor rank: up to 4
@@ -1946,8 +1947,7 @@
      *      of the padding:
      *          output0.dimension[i] =
      *              padding[i, 0] + input0.dimension[i] + padding[i, 1]
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      *
      *      NOTE: Before HAL version 1.2, the pad value for
@@ -1971,7 +1971,6 @@
      * * {@link OperandType::TENSOR_FLOAT16} (since HAL version 1.2)
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *   (full support since HAL version 1.2, see the output section)
      *
      * Supported tensor rank: 4, with "NHWC" or "NCHW" data layout.
@@ -1999,8 +1998,7 @@
      *
      * Outputs:
      * * 0: A tensor of the same {@link OperandType} as input0.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      *
      *      NOTE: Before HAL version 1.2, the pad value for
@@ -2021,6 +2019,7 @@
      * * {@link OperandType::TENSOR_FLOAT16} (since HAL version 1.2)
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: up to 4
      *
@@ -2036,7 +2035,8 @@
      * * 0: A tensor of the same {@link OperandType} as input0. Contains the
      *      same data as input, but has one or more dimensions of size 1
      *      removed.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
+     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     SQUEEZE = @1.2::OperationType:SQUEEZE,
@@ -2054,6 +2054,7 @@
      * * {@link OperandType::TENSOR_FLOAT16} (since HAL version 1.2)
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: up to 4
      *
@@ -2083,7 +2084,8 @@
      * Outputs:
      * * 0: A tensor of the same {@link OperandType} as input0 and rank (n - k),
      *      where k is the number of bits set in shrink_axis_mask.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
+     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     STRIDED_SLICE = @1.2::OperationType:STRIDED_SLICE,
@@ -2149,7 +2151,6 @@
      * * {@link OperandType::TENSOR_FLOAT16} (since HAL version 1.2)
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: up to 4
      *
@@ -2161,8 +2162,7 @@
      *
      * Outputs:
      * * 0: A tensor of the same {@link OperandType} as input0.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     TRANSPOSE = @1.2::OperationType:TRANSPOSE,
@@ -2708,7 +2708,6 @@
      * * {@link OperandType::TENSOR_FLOAT16}
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: up to 4
      *
@@ -2723,8 +2722,7 @@
      *
      * Outputs:
      * * 0: A tensor of the same {@link OperandType} and same shape as input0.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     CHANNEL_SHUFFLE = @1.2::OperationType:CHANNEL_SHUFFLE,
@@ -3083,23 +3081,12 @@
      * * * {@link OperandType::TENSOR_INT32} for bias (with scale set to
      * * * input.scale * filter.scale).
      *
-     * * Quantized signed (since HAL version 1.3):
-     * * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} for input, filter, and output.
-     * * * {@link OperandType::TENSOR_INT32} for bias (with scale set to
-     * * * input.scale * filter.scale).
-     *
      * * Quantized with symmetric per channel quantization for the filter:
      * * * {@link OperandType::TENSOR_QUANT8_ASYMM} for input, and output.
      * * * {@link OperandType::TENSOR_QUANT8_SYMM_PER_CHANNEL} for filter.
      * * * {@link OperandType::TENSOR_INT32} for bias (scale set to 0.0,
      * * * each value scaling is separate and equal to input.scale * filter.scales[channel]).
      *
-     * * Quantized signed with filter symmetric per channel quantization (since HAL version 1.3):
-     * * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} for input, and output.
-     * * * {@link OperandType::TENSOR_QUANT8_SYMM_PER_CHANNEL} for filter.
-     * * * {@link OperandType::TENSOR_INT32} for bias (scale set to 0.0,
-     * * * each value scaling is separate and equal to input.scale * filter.scales[channel]).
-     *
      * Supported tensor rank: 4, with "NHWC" or "NCHW" data layout.
      * With the default data layout NHWC, the data is stored in the order of:
      * [batch, height, width, channels]. Alternatively, the data layout could
@@ -3118,9 +3105,8 @@
      *      {@link SymmPerChannelQuantParams}) must be set to 0.
      * * 2: A 1-D tensor, of shape [depth_out], specifying the bias. For input
      *      tensor of type {@link OperandType::TENSOR_FLOAT32} or
-     *      {@link OperandType::TENSOR_FLOAT16}, the bias must be of the same type.
-     *      For filter tensor of {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED}
+     *      {@link OperandType::TENSOR_FLOAT16}, the bias must be of the same
+     *      type. For filter tensor of {@link OperandType::TENSOR_QUANT8_ASYMM},
      *      the bias should be of {@link OperandType::TENSOR_INT32}, with zeroPoint
      *      of 0 and bias_scale == input_scale * filter_scale. For filter tensor
      *      of {@link OperandType::TENSOR_QUANT8_SYMM_PER_CHANNEL}, the bias
@@ -3159,9 +3145,7 @@
      * * 2: A 1-D tensor, of shape [depth_out], specifying the bias. For input
      *      tensor of type {@link OperandType::TENSOR_FLOAT32} or
      *      {@link OperandType::TENSOR_FLOAT16}, the bias must be of the same
-     *      {@link OperandType::TENSOR_FLOAT16}, the bias must be of the same type.
-     *      For filter tensor of {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED}
+     *      type. For filter tensor of {@link OperandType::TENSOR_QUANT8_ASYMM},
      *      the bias should be of {@link OperandType::TENSOR_INT32}, with zeroPoint
      *      of 0 and bias_scale == input_scale * filter_scale. For filter tensor
      *      of {@link OperandType::TENSOR_QUANT8_SYMM_PER_CHANNEL}, the bias
@@ -3186,8 +3170,7 @@
      * Outputs:
      * * 0: The output 4-D tensor, of shape
      *      [batches, out_height, out_width, depth_out].
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint can be different from inputs' scale and zeroPoint.
      */
     GROUPED_CONV_2D = @1.2::OperationType:GROUPED_CONV_2D,
@@ -3543,7 +3526,6 @@
      * * {@link OperandType::TENSOR_FLOAT16}
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: up to 4
      *
@@ -3561,8 +3543,7 @@
      *      pad value must be of {@link OperandType::FLOAT16}.
      *      For input tensor of {@link OperandType::TENSOR_FLOAT32}, the
      *      pad value must be of {@link OperandType::FLOAT32}.
-     *      For input tensor of {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED},
+     *      For input tensor of {@link OperandType::TENSOR_QUANT8_ASYMM},
      *      the pad value must be of {@link OperandType::INT32}. The
      *      scale and zeroPoint are assumed to be the same as in input0.
      *
@@ -3574,8 +3555,7 @@
      *      of the padding:
      *          output0.dimension[i] =
      *              padding[i, 0] + input0.dimension[i] + padding[i, 1]
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     PAD_V2 = @1.2::OperationType:PAD_V2,
@@ -3652,23 +3632,14 @@
     /**
      * Quantizes the input tensor.
      *
-     * The formula for {@link OperandType::TENSOR_QUANT8_ASYMM} output tensor is:
+     * The formula is:
      *
      *     output = max(0, min(255, round(input / scale) + zeroPoint)
      *
-     * The formula for {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} output
-     * tensor is:
-     *
-     *     output = max(-128, min(127, round(input / scale) + zeroPoint)
-     *
-     * Supported input tensor {@link OperandType}:
+     * Supported tensor {@link OperandType}:
      * * {@link OperandType::TENSOR_FLOAT16}
      * * {@link OperandType::TENSOR_FLOAT32}
      *
-     * Supported output tensor {@link OperandType}:
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
-     *
      * Supported tensor rank: from 1
      *
      * Inputs:
@@ -3676,8 +3647,7 @@
      *
      * Outputs:
      * * 0: The output tensor of same shape as input0, but with
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM} or.
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED}.
+     *      {@link OperandType::TENSOR_QUANT8_ASYMM}.
      */
     QUANTIZE = @1.2::OperationType:QUANTIZE,
 
@@ -3868,6 +3838,7 @@
      * * {@link OperandType::TENSOR_FLOAT16}
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: up to 4
      *
@@ -3880,7 +3851,8 @@
      *
      * Outputs:
      * * 0: A tensor of the same {@link OperandType} as input0.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
+     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     REDUCE_MAX = @1.2::OperationType:REDUCE_MAX,
@@ -3897,6 +3869,7 @@
      * * {@link OperandType::TENSOR_FLOAT16}
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
+     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: up to 4
      *
@@ -3909,7 +3882,8 @@
      *
      * Outputs:
      * * 0: A tensor of the same {@link OperandType} as input0.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
+     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     REDUCE_MIN = @1.2::OperationType:REDUCE_MIN,
@@ -4184,7 +4158,6 @@
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_INT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: from 1
      *
@@ -4197,8 +4170,7 @@
      *
      * Outputs:
      * * 0 ~ (num_splits - 1): Resulting subtensors.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     SPLIT = @1.2::OperationType:SPLIT,
@@ -4234,7 +4206,6 @@
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_INT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: from 1
      *
@@ -4245,8 +4216,7 @@
      *
      * Outputs:
      * * 0: A tiled tensor of the same {@link OperandType} and rank as `input`.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     TILE = @1.2::OperationType:TILE,
@@ -4262,7 +4232,6 @@
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_INT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: from 1
      *
@@ -4274,8 +4243,7 @@
      * Outputs:
      * * 0: An n-D tensor of the same type as the input, containing the k
      *      largest elements along each last dimensional slice.
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      * * 1: An n-D tensor of type {@link OperandType::TENSOR_INT32}
      *      containing the indices of values within the last dimension of input.
@@ -4571,7 +4539,6 @@
      * * {@link OperandType::TENSOR_FLOAT16}
      * * {@link OperandType::TENSOR_FLOAT32}
      * * {@link OperandType::TENSOR_QUANT8_ASYMM}
-     * * {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} (since HAL version 1.3)
      *
      * Supported tensor rank: 4, with "NHWC" or "NCHW" data layout.
      * With the default data layout NHWC, the data is stored in the order of:
@@ -4611,8 +4578,7 @@
      * Outputs:
      * * 0: The output 4-D tensor, of shape
      *      [batches, new_height, new_width, depth].
-     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} and
-     *      {@link OperandType::TENSOR_QUANT8_ASYMM_SIGNED} tensor,
+     *      For a {@link OperandType::TENSOR_QUANT8_ASYMM} tensor,
      *      the scale and zeroPoint must be the same as input0.
      */
     RESIZE_NEAREST_NEIGHBOR = @1.2::OperationType:RESIZE_NEAREST_NEIGHBOR,