Feature Scope

Propagation Directions and Data Types

**Table 1** Parameter data types of the forward direction
Propagation Direction	src Data Type	Weight Data Type	dst Data Type	Bias Data Type
dnnl_forward_training dnnl_forward_inference	f32	f32	f32	f32
	f16	f16	f16	f16
	bf16	bf16	bf16	bf16
	f16	f16	f32	f16
	bf16	bf16	f32	bf16

**Table 2** Parameter data types of the backward direction (dnnl_backward_data category)
Propagation Direction	src Data Type	Weight Data Type	dst Data Type	Bias Data Type
dnnl_backward_data	f32	f32	f32	f32
	f16	f16	f16	f16
	bf16	bf16	bf16	bf16
	f32	f16	f16	f32
	f32	bf16	bf16	f32

**Table 3** Parameter data types of the backward direction (dnnl_backward_weights category)
Propagation Direction	src Data Type	Weight Data Type	dst Data Type	Bias Data Type
dnnl_backward_weights	f32	f32	f32	f32
	f16	f16	f16	f16
	bf16	bf16	bf16	bf16
	f16	f32	f16	f16
	bf16	f32	bf16	bf16

Data Layout

2D convolution is supported. The input and output tensor dimension is 4D. The layout of src, weights, and dst data needs to meet the following requirements:

Tensor Dimension	src Data Layout	Weights Data Layout	dst Data Layout
4D	dnnl_abcd	dnnl_abcd	dnnl_abcd

Parameter Constraints

Propagation Direction	Variable Name	Variable Description	Constraint	Remarks
dnnl_forward_training dnnl_forward_inference	mb	batch	≥ 1	oh and ow can be left blank, automatically deduced by benchdnn, or set by the user. The following requirements must be met: $\text{[math]}$ [] represents rounding down to the nearest integer.
	ic	input channel	≥ 1
	ih	input height	≥ 1
	iw	input width	≥ 1
	oc	output channel	≥ 1
	kh	kernel height	≥ 1
	kw	kernel width	≥ 1
	oh	output height	≥ 1
	ow	output width	≥ 1
	sh	height-wise stride	≥ 1
	sw	width-wise stride	≥ 1
	dh	height-wise dilation	≥ 0
	dw	width-wise dilation	≥ 0
	ph	height padding	≥ 0
	pw	width padding	≥ 0
	DKH	kernel height with dilation	DKH = 1 + (kh-1) x (dh+1)
	DKW	kernel width with dilation	DKW = 1 + (kw-1) x (dw+1)
dnnl_backward_data	mb	batch	≥ 1	oh and ow can be left blank, automatically deduced by benchdnn, or set by the user. The following requirements must be met: $\text{[math]}$ [] represents rounding down to the nearest integer.
	ic	input channel	≥ 1
	ih	input height	≥ 1
	iw	input width	≥ 1
	oc	output channel	≥ 1
	kh	kernel height	≥ 1
	kw	kernel width	≥ 1
	oh	output height	≥ 1
	ow	output width	≥ 1
	sh	height-wise stride	≥ 1
	sw	width-wise stride	≥ 1
	dh	height-wise dilation	≥ 0
	dw	width-wise dilation	≥ 0
	ph	height padding	0<=ph<=(kh-1) x (dh+1)
	pw	width padding	0<=pw<=(kw-1) x (dw+1)
	DKH	kernel height with dilation	DKH = 1 + (kh-1) x (dh+1)
	DKW	kernel width with dilation	DKW = 1 + (kw-1) x (dw+1)
dnnl_backward_weights	mb	batch	≥ 1	$\text{[math]}$
	ic	input channel	≥ 1
	ih	input height	≥ 1
	iw	input width	≥ 1
	oc	output channel	≥ 1
	kh	kernel height	≥ 1
	kw	kernel width	≥ 1
	oh	output height	≥ 1
	ow	output width	≥ 1
	sh	height-wise stride	≥ 1
	sw	width-wise stride	≥ 1
	dh	height-wise dilation	≥ 0
	dw	width-wise dilation	≥ 0
	ph	height padding	≥ 0
	pw	width padding	≥ 0
	DKH	kernel height with dilation	DKH = 1 + (oh-1) x sh
	DKW	kernel width with dilation	DKW = 1 + (ow-1) x sw

Parent topic: Convolution