Cargo.lock

@@ -299,6 +299,7 @@ dependencies = [
  "criterion",
  "getset",
  "itertools 0.12.0",
+ "ndarray",
  "num",
  "rand",
  "serde",
@@ -307,12 +308,35 @@ dependencies = [
  "thiserror",
 ]
 
+[[package]]
+name = "matrixmultiply"
+version = "0.3.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7574c1cf36da4798ab73da5b215bbf444f50718207754cb522201d78d1cd0ff2"
+dependencies = [
+ "autocfg",
+ "rawpointer",
+]
+
 [[package]]
 name = "memchr"
 version = "2.7.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "523dc4f511e55ab87b694dc30d0f820d60906ef06413f93d4d7a1385599cc149"
 
+[[package]]
+name = "ndarray"
+version = "0.15.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "adb12d4e967ec485a5f71c6311fe28158e9d6f4bc4a447b474184d0f91a8fa32"
+dependencies = [
+ "matrixmultiply",
+ "num-complex",
+ "num-integer",
+ "num-traits",
+ "rawpointer",
+]
+
 [[package]]
 name = "num"
 version = "0.4.1"
@@ -507,6 +531,12 @@ dependencies = [
  "getrandom",
 ]
 
+[[package]]
+name = "rawpointer"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "60a357793950651c4ed0f3f52338f53b2f809f32d83a07f72909fa13e4c6c1e3"
+
 [[package]]
 name = "rayon"
 version = "1.8.0"

Cargo.toml

@@ -6,10 +6,7 @@ license = "MIT/Apache-2.0"
 authors = ["Julius Koskela <julius.koskela@nordic-dev.net>"]
 
 description = """
-GDSL is a graph data-structure library including graph containers,
+Manifold is a Tensor library for Rust.
-connected node strutures and efficient algorithms on those structures.
-Nodes are independent of a graph container and can be used as connected
-smart pointers.
 """
 
 repository = "https://nordic-dev.net/julius/manifold"
@@ -23,10 +20,15 @@ getset = "0.1.2"
 itertools = "0.12.0"
 num = "0.4.1"
 serde = { version = "1.0.193", features = ["derive"] }
-serde_json = "1.0.108"
-static_assertions = "1.1.0"
 thiserror = "1.0.52"
 
 [dev-dependencies]
 rand = "0.8.5"
 criterion = "0.5.1"
+serde_json = "1.0.108"
+static_assertions = "1.1.0"
+ndarray = "0.15.6"
+
+[[bench]]
+name = "manifold_benchmark"
+harness = false

benches/manifold_benchmark.rs

@@ -0,0 +1,66 @@
+use criterion::Throughput;
+use criterion::{criterion_group, criterion_main, BenchmarkId, Criterion};
+use manifold::*;
+use rand::Rng;
+
+fn random_tensor_r2_manifold() -> Tensor<f64, 2> {
+    let mut rng = rand::thread_rng();
+    let mut tensor = tensor!([[0.0; 1000]; 1000]);
+    for i in 0..tensor.len() {
+        tensor[i] = rng.gen();
+    }
+    tensor
+}
+
+fn random_tensor_r2_ndarray() -> ndarray::Array2<f64> {
+    let mut rng = rand::thread_rng();
+    let (rows, cols) = (1000, 1000);
+    let mut tensor = ndarray::Array2::<f64>::zeros((rows, cols));
+    for i in 0..rows {
+        for j in 0..cols {
+            tensor[[i, j]] = rng.gen();
+        }
+    }
+    tensor
+}
+
+fn tensor_product(c: &mut Criterion) {
+    let b = 1000;
+
+    let mut group = c.benchmark_group("element-wise addition");
+
+    for (i, size) in [b].iter().enumerate() {
+        group.throughput(Throughput::Elements(*size as u64));
+
+        group.bench_with_input(
+            BenchmarkId::new("manifold", size),
+            &i,
+            |b, _| {
+                b.iter(|| {
+                    let a = random_tensor_r2_manifold();
+                    let b = random_tensor_r2_manifold();
+                    let c = a + b;
+                    assert!(c.shape().as_array() == &[1000, 1000]);
+                })
+            },
+        );
+
+        group.bench_with_input(
+            BenchmarkId::new("ndarray", size),
+            &i,
+            |b, _| {
+                b.iter(|| {
+                    let a = random_tensor_r2_ndarray();
+                    let b = random_tensor_r2_ndarray();
+                    let c = a + b;
+                    assert!(c.shape() == &[1000, 1000]);
+                })
+            },
+        );
+    }
+    group.finish();
+}
+
+criterion_group!(benches, tensor_product);
+
+criterion_main!(benches);

src/index.rs

@@ -1,8 +1,8 @@
 use super::*;
 use getset::{Getters, MutGetters};
 use std::{
-    ops::{Index, IndexMut, Add, Sub},
+    cmp::Ordering,
-	cmp::Ordering,
+    ops::{Add, Index, IndexMut, Sub},
 };
 
 #[derive(Clone, Copy, Debug, Getters, MutGetters)]
@@ -16,7 +16,6 @@ pub struct TensorIndex<const R: usize> {
 // ---- Construction and Initialization ---------------------------------------
 
 impl<const R: usize> TensorIndex<R> {
-
     pub fn new(shape: TensorShape<R>, indices: [usize; R]) -> Self {
         if !shape.check_indices(indices) {
             panic!("indices out of bounds");
@@ -65,10 +64,9 @@ impl<const R: usize> TensorIndex<R> {
         if self.indices()[0] >= self.shape().get(0) {
             return false;
         }
+        let shape = self.shape().as_array().clone();
         let mut carry = 1;
-        for (i, &dim_size) in
+        for (i, &dim_size) in self.indices.iter_mut().zip(&shape).rev() {
-            self.indices.iter_mut().zip(&self.shape.as_array()).rev()
-        {
             if carry == 1 {
                 *i += 1;
                 if *i >= dim_size {
@@ -158,9 +156,8 @@ impl<const R: usize> TensorIndex<R> {
         }
 
         let mut borrow = true;
-        for (i, &dim_size) in
+        let shape = self.shape().as_array().clone();
-            self.indices.iter_mut().zip(&self.shape.as_array()).rev()
+        for (i, &dim_size) in self.indices_mut().iter_mut().zip(&shape).rev() {
-        {
             if borrow {
                 if *i == 0 {
                     *i = dim_size - 1; // Wrap around to the maximum index of
@@ -271,7 +268,7 @@ impl<const R: usize> TensorIndex<R> {
     pub fn flat(&self) -> usize {
         self.indices()
             .iter()
-            .zip(&self.shape().as_array())
+            .zip(&self.shape().as_array().clone())
             .rev()
             .fold((0, 1), |(flat_index, product), (&idx, &dim_size)| {
                 (flat_index + idx * product, product * dim_size)
@@ -344,18 +341,14 @@ impl<const R: usize> IndexMut<usize> for TensorIndex<R> {
     }
 }
 
-impl<const R: usize> From<(TensorShape<R>, [usize; R])>
+impl<const R: usize> From<(TensorShape<R>, [usize; R])> for TensorIndex<R> {
-    for TensorIndex<R>
-{
     fn from((shape, indices): (TensorShape<R>, [usize; R])) -> Self {
         assert!(shape.check_indices(indices));
         Self::new(shape, indices)
     }
 }
 
-impl<const R: usize> From<(TensorShape<R>, usize)>
+impl<const R: usize> From<(TensorShape<R>, usize)> for TensorIndex<R> {
-    for TensorIndex<R>
-{
     fn from((shape, flat_index): (TensorShape<R>, usize)) -> Self {
         let indices = shape.index_from_flat(flat_index).indices;
         Self::new(shape, indices)
@@ -368,9 +361,7 @@ impl<const R: usize> From<TensorShape<R>> for TensorIndex<R> {
     }
 }
 
-impl<T: Value, const R: usize> From<Tensor<T, R>>
+impl<T: Value, const R: usize> From<Tensor<T, R>> for TensorIndex<R> {
-    for TensorIndex<R>
-{
     fn from(tensor: Tensor<T, R>) -> Self {
         Self::zero(tensor.shape().clone())
     }

src/lib.rs

@@ -9,7 +9,7 @@ pub mod shape;
 pub mod tensor;
 pub mod value;
 
-pub use {value::*, axis::*, error::*, index::*, shape::*, tensor::*};
+pub use {axis::*, error::*, index::*, shape::*, tensor::*, value::*};
 
 #[macro_export]
 macro_rules! tensor {
@@ -27,9 +27,9 @@ macro_rules! shape {
 
 #[macro_export]
 macro_rules! index {
-	($tensor:expr) => {
+    ($tensor:expr) => {
-		TensorIndex::zero($tensor.shape().clone())
+        TensorIndex::zero($tensor.shape().clone())
-	};
+    };
     ($tensor:expr, $indices:expr) => {
         TensorIndex::from(($tensor.shape().clone(), $indices))
     };

src/shape.rs

@@ -1,8 +1,8 @@
 use super::*;
+use core::result::Result as SerdeResult;
 use serde::de::{self, Deserialize, Deserializer, SeqAccess, Visitor};
 use serde::ser::{Serialize, SerializeTuple, Serializer};
-use std::fmt::{Result as FmtResult, Formatter};
+use std::fmt::{Formatter, Result as FmtResult};
-use core::result::Result as SerdeResult;
 
 #[derive(Clone, Copy, Debug)]
 pub struct TensorShape<const R: usize>([usize; R]);
@@ -24,8 +24,8 @@ impl<const R: usize> TensorShape<R> {
         new_shape
     }
 
-    pub const fn as_array(&self) -> [usize; R] {
+    pub const fn as_array(&self) -> &[usize; R] {
-        self.0
+        &self.0
     }
 
     pub const fn rank(&self) -> usize {

src/tensor.rs

@@ -4,7 +4,10 @@ use getset::{Getters, MutGetters};
 use serde::{Deserialize, Serialize};
 use std::{
     fmt::{Display, Formatter, Result as FmtResult},
-    ops::{Index, IndexMut},
+    ops::{
+        Add, AddAssign, Div, DivAssign, Index, IndexMut, Mul, MulAssign, Rem,
+        RemAssign, Sub, SubAssign,
+    },
 };
 
 /// A tensor is a multi-dimensional array of values. The rank of a tensor is the
@@ -35,7 +38,7 @@ impl<T: Value, const R: usize> Tensor<T, R> {
     /// use manifold::Tensor;
     ///
     /// let t = Tensor::<f64, 2>::new([3, 3].into());
-    /// assert_eq!(t.shape().as_array(), [3, 3]);
+    /// assert_eq!(t.shape().as_array(), &[3, 3]);
     /// ```
     pub fn new(shape: TensorShape<R>) -> Self {
         // Handle rank 0 tensor (scalar) as a special case
@@ -60,7 +63,7 @@ impl<T: Value, const R: usize> Tensor<T, R> {
     ///
     /// let buffer = vec![1, 2, 3, 4, 5, 6];
     /// let t = Tensor::<i32, 2>::new_with_buffer([2, 3].into(), buffer);
-    /// assert_eq!(t.shape().as_array(), [2, 3]);
+    /// assert_eq!(t.shape().as_array(), &[2, 3]);
     /// assert_eq!(t.buffer(), &[1, 2, 3, 4, 5, 6]);
     /// ```
     pub fn new_with_buffer(shape: TensorShape<R>, buffer: Vec<T>) -> Self {
@@ -413,6 +416,158 @@ impl<T: Value, const R: usize> Tensor<T, R> {
     }
 }
 
+// ---- Operations ------------------------------------------------------------
+
+impl<T: Value, const R: usize> Add for Tensor<T, R> {
+    type Output = Self;
+
+    fn add(self, other: Self) -> Self::Output {
+        if self.shape() != other.shape() {
+            todo!("Check for broadcasting");
+        }
+
+        let mut result = Self::new(self.shape().clone());
+
+        Self::ew_add(&self, &other, &mut result).unwrap();
+
+        result
+    }
+}
+
+impl<T: Value, const R: usize> Sub for Tensor<T, R> {
+    type Output = Self;
+
+    fn sub(self, other: Self) -> Self::Output {
+        if self.shape() != other.shape() {
+            todo!("Check for broadcasting");
+        }
+
+        let mut result = Self::new(self.shape().clone());
+
+        Self::ew_subtract(&self, &other, &mut result).unwrap();
+
+        result
+    }
+}
+
+impl<T: Value, const R: usize> Mul for Tensor<T, R> {
+    type Output = Self;
+
+    fn mul(self, other: Self) -> Self::Output {
+        if self.shape() != other.shape() {
+            todo!("Check for broadcasting");
+        }
+
+        let mut result = Self::new(self.shape().clone());
+
+        Self::ew_multiply(&self, &other, &mut result).unwrap();
+
+        result
+    }
+}
+
+impl<T: Value, const R: usize> Div for Tensor<T, R> {
+    type Output = Self;
+
+    fn div(self, other: Self) -> Self::Output {
+        if self.shape() != other.shape() {
+            todo!("Check for broadcasting");
+        }
+
+        let mut result = Self::new(self.shape().clone());
+
+        Self::ew_divide(&self, &other, &mut result).unwrap();
+
+        result
+    }
+}
+
+impl<T: Value, const R: usize> Rem for Tensor<T, R> {
+    type Output = Self;
+
+    fn rem(self, other: Self) -> Self::Output {
+        if self.shape() != other.shape() {
+            todo!("Check for broadcasting");
+        }
+
+        let mut result = Self::new(self.shape().clone());
+
+        Self::ew_modulo(&self, &other, &mut result).unwrap();
+
+        result
+    }
+}
+
+impl<T: Value, const R: usize> AddAssign for Tensor<T, R> {
+    fn add_assign(&mut self, other: Self) {
+        if self.shape() != other.shape() {
+            todo!("Check for broadcasting");
+        }
+
+        let mut result = Self::new(self.shape().clone());
+
+        Self::ew_add(&self, &other, &mut result).unwrap();
+
+        *self = result;
+    }
+}
+
+impl<T: Value, const R: usize> SubAssign for Tensor<T, R> {
+    fn sub_assign(&mut self, other: Self) {
+        if self.shape() != other.shape() {
+            todo!("Check for broadcasting");
+        }
+
+        let mut result = Self::new(self.shape().clone());
+
+        Self::ew_subtract(&self, &other, &mut result).unwrap();
+
+        *self = result;
+    }
+}
+
+impl<T: Value, const R: usize> MulAssign for Tensor<T, R> {
+    fn mul_assign(&mut self, other: Self) {
+        if self.shape() != other.shape() {
+            todo!("Check for broadcasting");
+        }
+
+        let mut result = Self::new(self.shape().clone());
+
+        Self::ew_multiply(&self, &other, &mut result).unwrap();
+
+        *self = result;
+    }
+}
+
+impl<T: Value, const R: usize> DivAssign for Tensor<T, R> {
+    fn div_assign(&mut self, other: Self) {
+        if self.shape() != other.shape() {
+            todo!("Check for broadcasting");
+        }
+
+        let mut result = Self::new(self.shape().clone());
+
+        Self::ew_divide(&self, &other, &mut result).unwrap();
+
+        *self = result;
+    }
+}
+
+impl<T: Value, const R: usize> RemAssign for Tensor<T, R> {
+    fn rem_assign(&mut self, other: Self) {
+        if self.shape() != other.shape() {
+            todo!("Check for broadcasting");
+        }
+
+        let mut result = Self::new(self.shape().clone());
+
+        Self::ew_modulo(&self, &other, &mut result).unwrap();
+
+        *self = result;
+    }
+}
+
 // ---- Indexing --------------------------------------------------------------
 
 impl<T: Value, const R: usize> Index<TensorIndex<R>> for Tensor<T, R> {
@@ -423,9 +578,7 @@ impl<T: Value, const R: usize> Index<TensorIndex<R>> for Tensor<T, R> {
     }
 }
 
-impl<T: Value, const R: usize> IndexMut<TensorIndex<R>>
+impl<T: Value, const R: usize> IndexMut<TensorIndex<R>> for Tensor<T, R> {
-    for Tensor<T, R>
-{
     fn index_mut(&mut self, index: TensorIndex<R>) -> &mut Self::Output {
         &mut self.buffer[index.flat()]
     }
@@ -479,7 +632,12 @@ where
     T: Display + Clone,
 {
     fn fmt(&self, f: &mut Formatter<'_>) -> FmtResult {
-        Tensor::<T, R>::fmt_helper(&self.buffer, &self.shape.as_array(), f, 1)
+        Tensor::<T, R>::fmt_helper(
+            &self.buffer,
+            &self.shape().as_array().clone(),
+            f,
+            1,
+        )
     }
 }
 

src/value.rs

@@ -1,9 +1,6 @@
 use num::{Num, One, Zero};
 use serde::{Deserialize, Serialize};
-use std::{
+use std::{fmt::Display, iter::Sum};
-	fmt::Display,
-	iter::Sum,
-};
 
 /// A trait for types that can be used as values in a tensor.
 pub trait Value:

tests/basic_tests.rs

@@ -0,0 +1,261 @@
+use manifold::*;
+
+use serde_json;
+
+#[test]
+fn test_serde_shape_serialization() {
+    // Create a shape instance
+    let shape: TensorShape<3> = [1, 2, 3].into();
+
+    // Serialize the shape to a JSON string
+    let serialized =
+        serde_json::to_string(&shape).expect("Failed to serialize");
+
+    // Deserialize the JSON string back into a shape
+    let deserialized: TensorShape<3> =
+        serde_json::from_str(&serialized).expect("Failed to deserialize");
+
+    // Check that the deserialized shape is equal to the original
+    assert_eq!(shape, deserialized);
+}
+
+#[test]
+fn test_tensor_serde_serialization() {
+    // Create an instance of Tensor
+    let tensor: Tensor<i32, 2> = Tensor::new(TensorShape::new([2, 2]));
+
+    // Serialize the Tensor to a JSON string
+    let serialized =
+        serde_json::to_string(&tensor).expect("Failed to serialize");
+
+    // Deserialize the JSON string back into a Tensor
+    let deserialized: Tensor<i32, 2> =
+        serde_json::from_str(&serialized).expect("Failed to deserialize");
+
+    // Check that the deserialized Tensor is equal to the original
+    assert_eq!(tensor.buffer(), deserialized.buffer());
+    assert_eq!(tensor.shape(), deserialized.shape());
+}
+
+#[test]
+fn test_iterating_3d_tensor() {
+    let shape = TensorShape::new([2, 2, 2]); // 3D tensor with shape 2x2x2
+    let mut tensor = Tensor::new(shape);
+    let mut num = 0;
+
+    // Fill the tensor with sequential numbers
+    for i in 0..2 {
+        for j in 0..2 {
+            for k in 0..2 {
+                tensor.buffer_mut()[i * 4 + j * 2 + k] = num;
+                num += 1;
+            }
+        }
+    }
+
+    println!("{}", tensor);
+
+    // Iterate over the tensor and check that the numbers are correct
+
+    let mut iter = TensorIterator::new(&tensor);
+
+    println!("{}", iter);
+
+    assert_eq!(iter.next(), Some(&0));
+
+    assert_eq!(iter.next(), Some(&1));
+    assert_eq!(iter.next(), Some(&2));
+    assert_eq!(iter.next(), Some(&3));
+    assert_eq!(iter.next(), Some(&4));
+    assert_eq!(iter.next(), Some(&5));
+    assert_eq!(iter.next(), Some(&6));
+    assert_eq!(iter.next(), Some(&7));
+    assert_eq!(iter.next(), None);
+    assert_eq!(iter.next(), None);
+}
+
+#[test]
+fn test_iterating_rank_4_tensor() {
+    // Define the shape of the rank-4 tensor (e.g., 2x2x2x2)
+    let shape = TensorShape::new([2, 2, 2, 2]);
+    let mut tensor = Tensor::new(shape);
+    let mut num = 0;
+
+    // Fill the tensor with sequential numbers
+    for i in 0..tensor.len() {
+        tensor.buffer_mut()[i] = num;
+        num += 1;
+    }
+
+    // Iterate over the tensor and check that the numbers are correct
+    let mut iter = TensorIterator::new(&tensor);
+    for expected_value in 0..tensor.len() {
+        assert_eq!(*iter.next().unwrap(), expected_value);
+    }
+
+    // Ensure the iterator is exhausted
+    assert!(iter.next().is_none());
+}
+
+#[test]
+fn test_index_dec_method() {
+    let shape = TensorShape::new([3, 3, 3]); // Example shape for a 3x3x3 tensor
+    let mut index = TensorIndex::zero(shape);
+
+    // Increment the index to the maximum
+    for _ in 0..26 {
+        // 3 * 3 * 3 - 1 = 26 increments to reach the end
+        index.inc();
+    }
+
+    // Check if the index is at the maximum
+    assert_eq!(index, TensorIndex::new(shape, [2, 2, 2]));
+
+    // Decrement step by step and check the index
+    let expected_indices = [
+        [2, 2, 2],
+        [2, 2, 1],
+        [2, 2, 0],
+        [2, 1, 2],
+        [2, 1, 1],
+        [2, 1, 0],
+        [2, 0, 2],
+        [2, 0, 1],
+        [2, 0, 0],
+        [1, 2, 2],
+        [1, 2, 1],
+        [1, 2, 0],
+        [1, 1, 2],
+        [1, 1, 1],
+        [1, 1, 0],
+        [1, 0, 2],
+        [1, 0, 1],
+        [1, 0, 0],
+        [0, 2, 2],
+        [0, 2, 1],
+        [0, 2, 0],
+        [0, 1, 2],
+        [0, 1, 1],
+        [0, 1, 0],
+        [0, 0, 2],
+        [0, 0, 1],
+        [0, 0, 0],
+    ];
+
+    for (i, &expected) in expected_indices.iter().enumerate() {
+        assert_eq!(
+            index,
+            TensorIndex::new(shape, expected),
+            "Failed at index {}",
+            i
+        );
+        index.dec();
+    }
+
+    // Finally, the index should reach [0, 0, 0]
+    index.dec();
+    assert_eq!(index, TensorIndex::zero(shape));
+}
+
+#[test]
+fn test_axis_iterator() {
+    // Creating a 2x2 Tensor for testing
+    let tensor = Tensor::from([[1.0, 2.0], [3.0, 4.0]]);
+
+    // Testing iteration over the first axis (axis = 0)
+    let axis = TensorAxis::new(&tensor, 0);
+
+    let mut axis_iter = axis.into_iter();
+
+    assert_eq!(axis_iter.next(), Some(&1.0));
+    assert_eq!(axis_iter.next(), Some(&2.0));
+    assert_eq!(axis_iter.next(), Some(&3.0));
+    assert_eq!(axis_iter.next(), Some(&4.0));
+
+    // Resetting the iterator for the second axis (axis = 1)
+    let axis = TensorAxis::new(&tensor, 1);
+
+    let mut axis_iter = axis.into_iter();
+
+    assert_eq!(axis_iter.next(), Some(&1.0));
+    assert_eq!(axis_iter.next(), Some(&3.0));
+    assert_eq!(axis_iter.next(), Some(&2.0));
+    assert_eq!(axis_iter.next(), Some(&4.0));
+
+    let shape = tensor.shape();
+
+    let mut a: TensorIndex<2> = (shape.clone(), [0, 0]).into();
+    let b: TensorIndex<2> = (shape.clone(), [1, 1]).into();
+
+    while a <= b {
+        println!("a: {}", a);
+        a.inc();
+    }
+}
+
+#[test]
+fn test_3d_tensor_axis_iteration() {
+    // Create a 3D Tensor with specific values
+    // Tensor shape is 2x2x2 for simplicity
+    let t = Tensor::from([[[1, 2], [3, 4]], [[5, 6], [7, 8]]]);
+
+    // 	TensorAxis 0 (Layer-wise):
+    //
+    // t[0][0][0] = 1
+    // t[0][0][1] = 2
+    // t[0][1][0] = 3
+    // t[0][1][1] = 4
+    // t[1][0][0] = 5
+    // t[1][0][1] = 6
+    // t[1][1][0] = 7
+    // t[1][1][1] = 8
+    // [1, 2, 3, 4, 5, 6, 7, 8]
+    //
+    // This order suggests that for each "layer" (first level of arrays),
+    // the iterator goes through all rows and columns. It first completes
+    // the entire first layer, then moves to the second.
+
+    let a0 = TensorAxis::new(&t, 0);
+    let a0_order = a0.into_iter().cloned().collect::<Vec<_>>();
+    assert_eq!(a0_order, [1, 2, 3, 4, 5, 6, 7, 8]);
+
+    // TensorAxis 1 (Row-wise within each layer):
+    //
+    // t[0][0][0] = 1
+    // t[0][0][1] = 2
+    // t[1][0][0] = 5
+    // t[1][0][1] = 6
+    // t[0][1][0] = 3
+    // t[0][1][1] = 4
+    // t[1][1][0] = 7
+    // t[1][1][1] = 8
+    // [1, 2, 5, 6, 3, 4, 7, 8]
+    //
+    // This indicates that within each "layer", the iterator first
+    // completes the first row across all layers, then the second row
+    // across all layers.
+
+    let a1 = TensorAxis::new(&t, 1);
+    let a1_order = a1.into_iter().cloned().collect::<Vec<_>>();
+    assert_eq!(a1_order, [1, 2, 5, 6, 3, 4, 7, 8]);
+
+    // TensorAxis 2 (Column-wise within each layer):
+    //
+    // t[0][0][0] = 1
+    // t[0][1][0] = 3
+    // t[1][0][0] = 5
+    // t[1][1][0] = 7
+    // t[0][0][1] = 2
+    // t[0][1][1] = 4
+    // t[1][0][1] = 6
+    // t[1][1][1] = 8
+    // [1, 3, 5, 7, 2, 4, 6, 8]
+    //
+    // This indicates that within each "layer", the iterator first
+    // completes the first column across all layers, then the second
+    // column across all layers.
+
+    let a2 = TensorAxis::new(&t, 2);
+    let a2_order = a2.into_iter().cloned().collect::<Vec<_>>();
+    assert_eq!(a2_order, [1, 3, 5, 7, 2, 4, 6, 8]);
+}

tests/mod.rs

@@ -0,0 +1 @@
+mod basic_tests;