From 58098a7b1ffcf41da759f862deb753c82fe5b4b0 Mon Sep 17 00:00:00 2001 From: Eric Kunze Date: Fri, 5 Aug 2022 15:40:12 -0700 Subject: Machine parsable specification This converts portions of the asciidoc specification into an xml document and schema. For the html and pdf outputs, the xml is converted to asciidoc files that are included into the existing specification. The xml allows future automated uses of the tosa specification while maintaining rough compatibility with the existing document. No significant functional changes are included in this change. Change-Id: I7f1f95c527638e270c157d58fcdec6a3510daea5 Signed-off-by: Eric Kunze --- chapters/tensor_ops.adoc | 285 +++-------------------------------------------- 1 file changed, 13 insertions(+), 272 deletions(-) (limited to 'chapters/tensor_ops.adoc') diff --git a/chapters/tensor_ops.adoc b/chapters/tensor_ops.adoc index fb657f7..4c9a25b 100644 --- a/chapters/tensor_ops.adoc +++ b/chapters/tensor_ops.adoc @@ -13,15 +13,7 @@ This returns the index with the largest value across the given axis of the input tensor. -*Arguments* - -|=== -|Argument|Type|Name|Shape|Description - -|Input|in_t*|input|shape1|Input tensor with rank from 1 to 4 -|Attribute|int32_t|axis|-|Axis in range from 0 to rank(shape1)-1 -|Output|out_t*|output|shape|Output tensor, with rank = rank(shape1)-1 -|=== +include::{generated}/operators/ARGMAX.adoc[] *Operation Function:* @@ -54,36 +46,13 @@ for_each(left_index in left_shape) { } ---- -*Supported Data Types:* - -|=== -|Profile|Mode|in_t|out_t - -|Any|signed 8|int8_t|int32_t -|Any|signed 16|int16_t|int32_t -|MI, MT|fp16|fp16_t|int32_t -|MI, MT|bf16|bf16_t|int32_t -|MI, MT|fp32|fp32_t|int32_t -|=== - ==== AVG_POOL2D This performs an average pooling over the given input tensor. A sliding window of size given by is passed over the input tensor, with the mean value being placed in the output tensor. When calculating the average, only the number of valid input tensor values, but not padding, are used to calculate the divisor. -*Arguments:* - -|=== -|Argument|Type|Name|Shape|Description -|Input|in_out_t*|input|[N,IH,IW,C]|Input tensor 4D -|Attribute|int32_t*|kernel|[2]|[kernel_y, kernel_x] -|Attribute|int32_t*|stride|[2]|[stride_y, stride_x] -|Attribute|int32_t*|pad|[4]|[pad_top, pad_bottom, pad_left, pad_right] -|Attribute|in_out_t|input_zp|-|Input tensor zero point. Must be zero for non-int8 types. -|Attribute|in_out_t|output_zp|-|Output tensor zero point. Must be zero for non-int8 types. -|Output|in_out_t*|output|[N,OH,OW,C]|Output tensor 4D -|=== +include::{generated}/operators/AVG_POOL2D.adoc[] *Operation Function:* @@ -130,37 +99,11 @@ for_each(0 <= n < N, 0 <= oy < OH, 0 <= ox < OW, 0 <= c < C ) { } ---- -*Supported Data Types:* -|=== -|Profile|Mode|in_out_t|acc_t - -|Any|signed 8|int8_t|int32_t -|Any|signed 16|int16_t|int32_t -|MI, MT|fp16 with fp16 accumulate|fp16_t|fp16_t -|MI, MT|fp16 with fp32 accumulate|fp16_t|fp32_t -|MI, MT|bf16 with fp32 accumulate|bf16_t|fp32_t -|MI, MT|fp32|fp32_t|fp32_t -|=== - ==== CONV2D Performs a 2D convolution over the given tensor input, using the weight tensor. -*Arguments:* - -|=== -|Argument|Type|Name|Shape|Description - -|Input|in_t*|input|[N,IH,IW,IC]|Input tensor -|Input (MT profile) Attribute (BI/MI profiles)|weight_t*|weight|[OC,KH,KW,IC]|Weight kernel size KH x KW -|Input (MT profile) Attribute (BI/MI profiles)|out_t*|bias|[OC]|Per output channel bias data. -|Attribute|int32_t*|pad|[4]|[pad_top, pad_bottom, pad_left, pad_right] -|Attribute|int32_t*|stride|[2]|[stride_y, stride_x] -|Attribute|int32_t*|dilation|[2]|[dilation_y, dilation_x] -|Attribute|in_t|input_zp|-|Input tensor zero point. Must be zero for non-int8 types. -|Attribute|weight_t|weight_zp|-|Weight zero point. Must be zero for non-int8 types. -|Output|out_t*|output|[N,OH,OW,OC]|Output tensor -|=== +include::{generated}/operators/CONV2D.adoc[] *Operation Function* @@ -195,39 +138,11 @@ for_each(0 <= n < N, 0 <= oy < OH, 0 <= ox < OW; 0 <= oc < OC) { } ---- -*Supported Data Types:* - -|=== -|Profile|Mode|in_t|weight_t|out_t - -|Any|signed 8x8|int8_t|int8_t|int32_t -|Any|signed 8x4|int8_t|int4_t|int32_t -|Any|signed 16x8|int16_t|int8_t|int48_t -|MI, MT|fp16 with fp16 accumulate|fp16_t|fp16_t|fp16_t -|MI, MT|fp16 with fp32 accumulate|fp16_t|fp16_t|fp32_t -|MI, MT|bf16 with fp32 accumulate|bf16_t|bf16_t|fp32_t -|MI, MT|fp32|fp32_t|fp32_t|fp32_t -|=== - ==== CONV3D Performs a 3D convolution over the given input tensor. -*Arguments:* - -|=== -|Argument|Type|Name|Shape|Description - -|Input|in_t*|input|[N,ID,IH,IW,IC]|Input tensor -|Input (MT profile) Attribute (BI/MI profiles)|weight_t*|weight|[OC,KD,KH,KW,IC]|Weight kernel size KDxKHxKW -|Input (MT profile) Attribute (BI/MI profiles)|out_t*|bias|[OC]|Per output channel bias data. -|Attribute|int32_t*|pad|[6]|[pad_d0, pad_d1, pad_top, pad_bottom, pad_left, pad_right] -|Attribute|int32_t*|stride|[3]|[stride_d, stride_y, stride_x] -|Attribute|int32_t*|dilation|[3]|[dilation_d, dilation_y, dilation_x] -|Attribute|in_t|input_zp|-|Input tensor zero point. Must be zero for non-int8 types. -|Attribute|weight_t|weight_zp|-|Weight zero point. Must be zero for non-int8 types. -|Output|out_t*|output|[N,OD,OH,OW,OC]|Output tensor -|=== +include::{generated}/operators/CONV3D.adoc[] *Operation Function* @@ -265,40 +180,11 @@ for_each(0 <= n < N, 0 <= od < OD, 0 <= oy < OH, 0 <= ox < OW; 0 <= oc < OC) { } ---- -*Supported Data Types:* - -|=== -|Profile|Mode|in_t|weight_t|out_t - -|Any|signed 8x8|int8_t|int8_t|int32_t -|Any|signed 8x4|int8_t|int4_t|int32_t -|Any|signed 16x8|int16_t|int8_t|int48_t -|MI, MT|fp16 with fp16 accumulate|fp16_t|fp16_t|fp16_t -|MI, MT|fp16 with fp32 accumulate|fp16_t|fp16_t|fp32_t -|MI, MT|bf16 with fp32 accumulate|bf16_t|bf16_t|fp32_t -|MI, MT|fp32|fp32_t|fp32_t|fp32_t -|=== - - ==== DEPTHWISE_CONV2D Performs 2D convolutions separately over each channel of the given tensor input, using the weight tensor. -*Arguments:* - -|=== -|Argument|Type|Name|Shape|Description - -|Input|in_t*|input|[N,H,W,C]|Input tensor -|Input (MT profile) Attribute (BI/MI profiles)|weight_t*|weight|[KH,KW,C,M]|Weight kernel size KH x KW -|Input (MT profile) Attribute (BI/MI profiles)|out_t*|bias|[C*M]|Per output channel bias data. -|Attribute|int32_t*|pad|[4]|[pad_top, pad_bottom, pad_left, pad_right] -|Attribute|int32_t*|stride|[2]|[stride_y, stride_x] -|Attribute|int32_t*|dilation|[2]|[dilation_y, dilation_x] -|Attribute|in_t|input_zp|-|Input tensor zero point. Must be zero for non-int8 types. -|Attribute|weight_t|weight_zp|-|Weight zero point. Must be zero for non-int8 types. -|Output|out_t*|output|[N,OH,OW,C*M]|Output tensor -|=== +include::{generated}/operators/DEPTHWISE_CONV2D.adoc[] *Operation Function* @@ -333,20 +219,6 @@ for_each(0 <= n < N, 0 <= oy < OH, 0 <= ox < OW; 0 <= c < C, 0 <= m < M) { } ---- -*Supported Data Types:* - -|=== -|Profile|Mode|in_t|weight_t|out_t - -|Any|signed 8x8|int8_t|int8_t|int32_t -|Any|signed 8x4|int8_t|int4_t|int32_t -|Any|signed 16x8|int16_t|int8_t|int48_t -|MI, MT|fp16 with fp16 accumulate|fp16_t|fp16_t|fp16_t -|MI, MT|fp16 with fp32 accumulate|fp16_t|fp16_t|fp32_t -|MI, MT|bf16 with fp32 accumulate|bf16_t|bf16_t|fp32_t -|MI, MT|fp32|fp32_t|fp32_t|fp32_t -|=== - ==== FFT2D Performs a batched complex 2D Fast Fourier Transform over the input. @@ -364,17 +236,7 @@ image::forward_fft2d.svg["forward FFT definition", align="center"] .Calculation for the inverse FFT2D calculation (inverse=true) image::inverse_fft2d.svg["inverse FFT definition", align="center"] -*Arguments:* - -|=== -|Argument|Type|Name|Shape|Description - -|Input|in_out_t*|input_real|[N,H,W]|Real part of the complex input. H,W must be powers of two. -|Input|in_out_t*|input_imag|[N,H,W]|Imaginary part of the complex input. H,W must be powers of two. -|Attribute|bool_t|inverse|-|false for forward FFT, true for inverse FFT -|Output|in_out_t*|output_real|[N,H,W]|Real part of the complex output -|Output|in_out_t*|output_imag|[N,H,W]|Imaginary part of the complex output. -|=== +include::{generated}/operators/FFT2D.adoc[] *Operation Function* @@ -404,30 +266,11 @@ for_each(0 <= n < N, 0 <= oy < H, 0 <= ox < W) { } ---- -*Supported Data Types:* - -|=== -|Profile|Mode|in_out_t - -|MI,MT|fp32_t|fp32_t -|=== - ==== FULLY_CONNECTED Performs a fully connected network. -*Arguments:* - -|=== -|Argument|Type|Name|Shape|Description - -|Input|in_t*|input|[N,IC]|Input tensor -|Attribute|weight_t*|weight|[OC,IC]|Weights -|Attribute|out_t*|bias|[OC]|Per output channel bias data. -|Attribute|in_t|input_zp|-|Input tensor zero point. Must be zero for non-int8 types. -|Attribute|weight_t|weight_zp|-|Weight zero point. Must be zero for non-int8 types. -|Output|out_t*|output|[N,OC]|Output tensor -|=== +include::{generated}/operators/FULLY_CONNECTED.adoc[] *Operation Function* @@ -449,34 +292,11 @@ for_each(0 <= n < N, 0 <= oc < OC) { } ---- -*Supported Data Types:* - -|=== -|Profile|Mode|in_t|weight_t|out_t - -|Any|signed 8x8|int8_t|int8_t|int32_t -|Any|signed 8x4|int8_t|int4_t|int32_t -|Any|signed 16x8 |int16_t|int8_t|int48_t -|MI, MT|fp16 with fp16 accumulate|fp16_t|fp16_t|fp16_t -|MI, MT|fp16 with fp32 accumulate|fp16_t|fp16_t|fp32_t -|MI, MT|bf16 with fp32 accumulate|bf16_t|bf16_t|fp32_t -|MI, MT|fp32|fp32_t|fp32_t|fp32_t -|=== - ==== MATMUL -Performs two dimensional matrix multiplications. This allows both inputs to be activations, rather than reserving weights as an attribute in the FULLY_CONNECTED operator. - -*Arguments:* -|=== -|Argument|Type|Name|Shape|Description +Performs two dimensional matrix multiplications. This allows both inputs to be activations, rather than reserving weights as an attribute in the FULLY_CONNECTED operator. -|Input|in_t*|A|[N,H,C]|Input tensor A, N matrices of size HxC -|Input|in_t*|B|[N,C,W]|Input tensor B, N matrices of size CxW -|Attribute|in_t|A_zp|-|Input tensor A zero point. Must be zero for non-int8 types. -|Attribute|in_t|B_zp|-|Input tensor B zero point. Must be zero for non-int8 types. -|Output|out_t*|output|[N,H,W]|Output tensor, N matrices of size HxW -|=== +include::{generated}/operators/MATMUL.adoc[] *Operation Function* @@ -496,33 +316,11 @@ for_each(0 <= n < N, 0 <= h < H, 0 <= w < W) { } ---- -*Supported Data Types:* - -|=== -|Profile|Mode|in_t|out_t - -|Any|signed 8x8|int8_t|int32_t -|Any|signed 16x16|int16_t|int48_t -|MI, MT|fp16 with fp16 accumulate|fp16_t|fp16_t -|MI, MT|fp16 with fp32 accumulate|fp16_t|fp32_t -|MI, MT|bf16 with fp32 accumulate|bf16_t|fp32_t -|MI, MT|fp32|fp32_t|fp32_t -|=== - ==== MAX_POOL2D -This performs a max pooling over the given input tensor. A sliding window of size given by is passed over the input tensor, with the maximum value being placed in the output tensor. - -*Arguments:* -|=== -|Argument|Type|Name|Shape|Description +This performs a max pooling over the given input tensor. A sliding window of size given by is passed over the input tensor, with the maximum value being placed in the output tensor. -|Input|in_out_t*|input|[N,IH,IW,C]|Input tensor 4D -|Attribute|int32_t*|kernel|[2]|[kernel_y, kernel_x] -|Attribute|int32_t*|stride|[2]|[stride_y, stride_x] -|Attribute|int32_t*|pad|[4]|[pad_top, pad_bottom, pad_left, pad_right] -|Output|in_out_t*|output|[N,OH,OW,C]|Output tensor 4D -|=== +include::{generated}/operators/MAX_POOL2D.adoc[] *Operation Function:* @@ -554,18 +352,6 @@ for_each(0 <= n < N, 0 <= oy < H, 0 <= ox < W, 0 <= c < C ) { } ---- -*Supported Data Types:* - -|=== -|Profile|Mode|in_out_t - -|Any|signed 8|int8_t -|Any|16-bit|int16_t -|MI, MT|fp16|fp16_t -|MI, MT|bf16|bf16_t -|MI, MT|fp32|fp32_t -|=== - ==== RFFT2D Performs a batched 2D real-valued Fast Fourier Transform over the input where the input tensor consists of real values producing complex valued output. @@ -575,15 +361,7 @@ Imaginary values with locations h=0,H/2 or w=0,W/2 are zero. image::forward_fft2d.svg["forward FFT definition", align="center"] -*Arguments:* - -|=== -|Argument|Type|Name|Shape|Description - -|Input|in_out_t*|input|[N,H,W]|Real input. H,W must be powers of two. -|Output|in_out_t*|output_real|[N,H/2 + 1,W/2 + 1]|Real part of the complex output -|Output|in_out_t*|output_imag|[N,H/2 + 1,W/2 + 1]|Imaginary part of the complex output. -|=== +include::{generated}/operators/RFFT2D.adoc[] *Operation Function* @@ -606,34 +384,11 @@ for_each(0 <= n < N, 0 <= oy < H/2 + 1, 0 <= ox < W/2 + 1) { } ---- -*Supported Data Types:* - -|=== -|Profile|Mode|in_out_t - -|MI,MT|fp32_t|fp32_t -|=== - - ==== TRANSPOSE_CONV2D Performs a 2D transposed convolution over the given tensor input, using the weights tensor. -*Arguments:* - -|=== -|Argument|Type|Name|Shape|Description - -|Input|in_t*|input|[N,IH,IW,IC]|Input tensor -|Input (MT profile) Attribute (BI/MI profiles)|weight_t*|weight|[OC,KH,KW,IC]|Weight kernel size KH x KW -|Input (MT profile) Attribute (BI/MI profiles)|out_t*|bias|[OC]|Per output channel bias data. -|Attribute|int32_t*|out_pad|[4]|[out_pad_top, out_pad_bottom, out_pad_left, out_pad_right] -|Attribute|int32_t*|stride|[2]|[stride_y, stride_x] -|Attribute|int32_t*|out_shape|[4]|[N,OH,OW,OC] -|Attribute|in_t|input_zp|-|Input tensor zero point. Must be zero for non-int8 types. -|Attribute|weight_t|weight_zp|-|Weight zero point. Must be zero for non-int8 types. -|Output|out_t*|output|[N,OH,OW,OC]|Output tensor -|=== +include::{generated}/operators/TRANSPOSE_CONV2D.adoc[] *Operation Function* @@ -665,17 +420,3 @@ for_each(0 <= n < N, 0 <= iy < IH, 0 <= ix < IW, 0 <= oc < OC, } } ---- - -*Supported Data Types:* - -|=== -|Profile|Mode|in_t|weight_t|out_t - -|Any|signed 8x8|int8_t|int8_t|int32_t -|Any|signed 8x4|int8_t|int4_t|int32_t -|Any|signed 16x8|int16_t|int8_t|int48_t -|MI, MT|fp16 with fp16 accumulate|fp16_t|fp16_t|fp16_t -|MI, MT|fp16 with fp32 accumulate|fp16_t|fp16_t|fp32_t -|MI, MT|bf16 with fp32 accumulate|bf16_t|bf16_t|fp32_t -|MI, MT|fp32|fp32_t|fp32_t|fp32_t -|=== -- cgit v1.2.1