Key concepts

In this puzzle, you’ll learn about:

• Working with 2D thread indices (thread_idx.x, thread_idx.y)
• Converting 2D coordinates to 1D memory indices
• Handling boundary checks in two dimensions

The key insight is understanding how to map from 2D thread coordinates \((i,j)\) to elements in a row-major matrix of size \(n \times n\), while ensuring thread indices are within bounds.

• 2D indexing: Each thread has a unique \((i,j)\) position
• Memory layout: Row-major ordering maps 2D to 1D memory
• Guard condition: Need bounds checking in both dimensions
• Thread bounds: More threads \((3 \times 3)\) than matrix elements \((2 \times 2)\)

Code to complete

alias SIZE = 2
alias BLOCKS_PER_GRID = 1
alias THREADS_PER_BLOCK = (3, 3)
alias dtype = DType.float32


fn add_10_2d(
    out: UnsafePointer[Scalar[dtype]],
    a: UnsafePointer[Scalar[dtype]],
    size: Int,
):
    local_i = thread_idx.x
    local_j = thread_idx.y
    # FILL ME IN (roughly 2 lines)

View full file: problems/p04/p04.mojo

Running the code

To test your solution, run the following command in your terminal:

magic run p04

Your output will look like this if the puzzle isn’t solved yet:

out: HostBuffer([0.0, 0.0, 0.0, 0.0])
expected: HostBuffer([10.0, 11.0, 12.0, 13.0])

Solution

fn add_10_2d(
    out: UnsafePointer[Scalar[dtype]],
    a: UnsafePointer[Scalar[dtype]],
    size: Int,
):
    local_i = thread_idx.x
    local_j = thread_idx.y
    if local_i < size and local_j < size:
        out[local_j * size + local_i] = a[local_j * size + local_i] + 10.0