Struct cudnn::utils::ScalParams

pub struct ScalParams<T> {
    pub a: *const c_void,
    pub b: *const c_void,
    // some fields omitted
}

Provides a convenient interface for cuDNN's scaling parameters alpha and beta.

Scaling paramarters lend the source value with prior value in the destination tensor as follows: dstValue = alpha[0]*srcValue + beta[0]*priorDstValue. When beta[0] is zero, the output is not read and can contain any uninitialized data (including NaN). The storage data type for alpha[0], beta[0] is float for HALF and SINGLE tensors, and double for DOUBLE tensors. These parameters are passed using a host memory pointer.

For improved performance it is advised to use beta[0] = 0.0. Use a non-zero value for beta[0] only when blending with prior values stored in the output tensor is needed.

Fields

a: *const c_void

Alpha

b: *const c_void

Beta

Trait Implementations

impl Default for ScalParams<f32>

fn default() -> ScalParams<f32>

Provides default values for ScalParams.

impl Default for ScalParams<f64>

fn default() -> ScalParams<f64>

Provides default values for ScalParams.