VkTensorTilingARM

Possible values of VkTensorCreateInfoARM::tiling, specifying the tiling arrangement of elements in the tensor, are:

typedef enum VkTensorTilingARM {
    VK_TENSOR_TILING_OPTIMAL_ARM = 0,
    VK_TENSOR_TILING_LINEAR_ARM = 1,
    // Provided by extensions
    VK_TENSOR_TILING_BRICK_16_WIDE_ARM = -999999000,
    VK_TENSOR_TILING_BRICK_8_WIDE_ARM = -999999001,
    VK_TENSOR_TILING_BRICK_4_WIDE_ARM = -999999002,
    VK_TENSOR_TILING_BLOCK_U_INTERLEAVED_ARM = -999999003,
    VK_TENSOR_TILING_BLOCK_U_INTERLEAVED_64K_ARM = -999999004,
} VkTensorTilingARM;

pub struct TensorTilingARM(u32);
impl TensorTilingARM {
    pub const OPTIMAL: Self = 0;
    pub const LINEAR: Self = 1;
    pub const BRICK_16_WIDE: Self = -999999000;
    pub const BRICK_8_WIDE: Self = -999999001;
    pub const BRICK_4_WIDE: Self = -999999002;
    pub const BLOCK_U_INTERLEAVED: Self = -999999003;
    pub const BLOCK_U_INTERLEAVED_64K: Self = -999999004;
}

• VK_TENSOR_TILING_OPTIMAL_ARM specifies optimal tiling (elements are laid out in an implementation-dependent arrangement, for more efficient memory access).
• VK_TENSOR_TILING_LINEAR_ARM specifies linear tiling (elements are laid out linearly and the offset between each element is determined by the strides of the tensor).
• VK_TENSOR_TILING_BRICK_16_WIDE_ARM specifies that the data is laid out in 64-byte blocks of 16 x N elements where N depends on the size of the elements in the tensor.
• VK_TENSOR_TILING_BRICK_8_WIDE_ARM specifies that the data is laid out in 64-byte blocks of 8 x N elements where N depends on the size of the elements in the tensor.
• VK_TENSOR_TILING_BRICK_4_WIDE_ARM specifies that the data is laid out in 64-byte blocks of 4 x N elements where N depends on the size of the elements in the tensor.
• VK_TENSOR_TILING_BLOCK_U_INTERLEAVED_ARM specifies that the data is laid out using blocks of size 16 x 16 x C where C is the size of the tensor along the innermost dimension.
• VK_TENSOR_TILING_BLOCK_U_INTERLEAVED_64K_ARM specifies that the data is laid out using 64kiB groups of blocks of size 16 x 16 x C, where C is the size of the tensor along the innermost dimension.