Choosing a Kernel Backend

TiGrIS plans are target-independent. The backend selected with tigris codegen chooses the kernels used by the generated integration code; it does not change the model or plan format.

For initial integration and host testing, use reference. For an int8 deployment, select esp-nn on ESP32-S3 or cmsis-nn on Cortex-M. Both accelerated backends fall back to TiGrIS’s portable int8 kernels when a vendor kernel cannot preserve the plan’s semantics.

At a glance

--backend	Intended target	Float32 plan	Int8 plan
reference	POSIX, tests, portable deployments	Portable C	Portable C
esp-nn	ESP32-S3	Portable C	ESP-NN with portable fallback
cmsis-nn	Arm Cortex-M	Portable C	CMSIS-NN with portable fallback

ESP-NN and CMSIS-NN accelerate int8 only. Selecting either for a float32 plan explicitly uses the portable float implementation.

Supported operators

The table covers operators that may remain after TiGrIS normalizes an ONNX graph. Native means the vendor library is normally used. Portable fallback remains supported but does not receive vendor acceleration.

Executable operators after graph normalization

Operator	Portable C	ESP-NN (int8)	CMSIS-NN (int8)
Conv	Float32 + int8	Native*	Native*
DepthwiseConv	Float32 + int8	Native*	Native*
Relu	Float32 + int8	Portable fallback	Portable fallback
Relu6	Float32 + int8	Portable fallback	Portable fallback
MaxPool	Float32 + int8	Portable fallback	Portable fallback
AveragePool	Float32 + int8	Native*	Native*
Add	Float32 + int8	Portable fallback	Portable fallback
Mul	Float32 + int8	Portable fallback	Portable fallback
Gemm	Float32 + int8	Native	Native
Softmax	Float32 + int8	Portable fallback	Portable fallback
Sigmoid	Float32 + int8	Portable fallback	Portable fallback
Concat	Float32 + int8	Portable fallback	Portable fallback
GlobalAveragePool	Float32 + int8	Portable fallback	Native*
Flatten	Float32 + int8	Portable fallback	Portable fallback
Reshape	Float32 + int8	Portable fallback	Portable fallback
Sub	Float32 + int8	Portable fallback	Portable fallback
Tanh	Float32 + int8	Portable fallback	Portable fallback
ConvTranspose	Float32 + int8	Portable fallback	Portable fallback
MatMul	Float32 + int8	Portable fallback	Portable fallback
ReduceMean	Float32 + int8	Portable fallback	Portable fallback
Transpose	Float32 + int8	Portable fallback	Portable fallback
Resize	Float32 + int8	Portable fallback	Portable fallback
GlobalMaxPool	Float32 + int8	Portable fallback	Portable fallback
Conv1D	Float32 + int8	Portable fallback	Portable fallback
LayerNormalization	Float32 + int8	Portable fallback	Portable fallback
Erf	Float32 + int8	Portable fallback	Portable fallback
Split	Float32 + int8	Portable fallback	Portable fallback
ResizeLinear	Float32 + int8	Portable fallback	Portable fallback
HardSwish	Float32 + int8	Portable fallback	Portable fallback

Important operator limits

The matrix uses the runtime’s NLC/NHWC layouts. For rank-3 and rank-4 ONNX activations, the channel axis becomes the runtime’s final dimension; this is the supported Softmax axis.

Operator	Implemented form
Relu	rank-3 pointwise length tiling on serialized axis 1
Relu6	rank-3 pointwise length tiling on serialized axis 1
MaxPool	explicit padding, floor output sizing, unit dilation, and no indices output
AveragePool	explicit padding, floor output sizing, unit dilation, and count_include_pad=0 wherever padding is non-zero
Add	a dynamic second operand has the first operand's shape or holds one value per channel, and a per-channel one runs untiled; a float constant operand is one value, one per channel, or one per element
Add	standalone rank-3 pointwise length tiling on serialized axis 1
Mul	a dynamic second operand has the first operand's shape or holds one value per channel, and a per-channel one runs untiled; a float constant operand is one value, one per channel, or one per element
Mul	standalone rank-3 pointwise length tiling on serialized axis 1
Softmax	final axis only; untiled execution
Sigmoid	rank-3 pointwise length tiling on serialized axis 1
Concat	rank-3 and rank-4 concatenation on the last stored axis; a constant part only as the leading operand of a float concatenation
GlobalAveragePool	untiled execution
Tanh	rank-3 pointwise length tiling on serialized axis 1
ReduceMean	rank-3 mean over serialized axis 1; untiled execution. A rank-4 mean over both spatial axes is rewritten to GlobalAveragePool instead
Transpose	a concrete, valid permutation is stored in schema 4+ plans
Resize	rank-4 nearest-neighbor integer H/W upscaling; height tiling as the stage's single spatial op, never in a chain
Conv1D	standalone rank-3 length tiling on serialized axis 1; may compose with shape-preserving unary pointwise operators
Split	contiguous parts along the outermost stored axis; untiled execution
ResizeLinear	rank-4 bilinear integer H/W upscaling with half-pixel or asymmetric coordinates; height tiling as the stage's single spatial op, never in a chain
HardSwish	rank-3 pointwise length tiling on serialized axis 1

When native acceleration falls back

An asterisk in the support table means the vendor adapter is used for the common case, while these variants deliberately take the portable int8 path:

Backend	Operator	Fallback condition
cmsis-nn	Conv	falls back for dilation other than 1
esp-nn	Conv	falls back for dilation other than 1; asymmetric padding falls back when its preparation-time workspace is insufficient
cmsis-nn	DepthwiseConv	falls back for dilation other than 1
esp-nn	DepthwiseConv	falls back for dilation other than 1
cmsis-nn	AveragePool	falls back when tiled or when input/output quantization differs
esp-nn	AveragePool	falls back when tiled or when input/output quantization differs
cmsis-nn	GlobalAveragePool	falls back when tiled or when input/output quantization differs

Operators not directly executable

These names have reserved plan opcodes but no kernel route. Normalization may fold or rewrite some of them; code generation rejects a plan if one remains:

Clip, Pad, Div, LeakyRelu, BatchNormalization, InstanceNormalization, Squeeze, Unsqueeze.

The compiler still validates each model’s shapes, attributes, quantization, tiling, and memory requirements. A listed operator does not imply support for every ONNX attribute combination.

Keeping this page accurate

These tables describe the currently released tigris-ml package. They are generated from its capability contract and automatically verified against the published package for every website release. Development CI separately checks the next documentation state against compiler and runtime develop.