Tile
A tile is a bounded block of elements from a larger array, matrix, or tensor that is treated as a unit of computation.
GPU Programming with Triton
A tile is a portion of a tensor processed by one Triton program instance.
- How it is used
- Organizes tensor work into blocks processed by parallel Triton program instances.
- How deep it goes
- Develops tile addressing, masking, data reuse, and a tiled matrix-multiplication kernel, initially without boundary or remainder handling.
- Examples
- Uses vector addition and a 4 × 4 matrix product distributed across four tiled programs.
- What you can do after
- Apply it via Triton to address tensor blocks and construct a tiled matrix-multiplication kernel.
CUDA for LLMs
A tile is a bounded subset of an array or matrix processed as a unit.
- How it is used
- Uses tiles to reduce memory traffic and distribute matrix multiplication and attention work across GPU execution units.
- How deep it goes
- Traces tile shapes, memory loads, accumulation, register reuse, and synchronization through CUDA kernels and a producer-consumer pipeline.
- Examples
- Works through a 128 × 128 GEMM output tile, 8 × 8 thread micro-tiles, and tiled Flash Attention.
- What you can do after
- Build a tiled CUDA matrix multiplication using shared-memory input tiles and register accumulation.
Grokking GPU Programming
A tile is a smaller rectangular block of elements taken from a larger matrix or other data structure.
- How it is used
- Uses tiles to stage matrix chunks in shared memory for reuse and efficient global-memory access.
- How deep it goes
- Explains tile ownership, partial sums, thread-to-slot mapping, synchronization, and padding, including consequences of mismatched block dimensions.
- Examples
- Uses a filing-cabinet and whiteboard analogy, tiled matrix multiplication, and a padded transpose kernel.
- What you can do after
- Diagnoses incorrect tile loading caused by mismatched thread-block and tile dimensions.
Also covered in
- Rearchitecting LLMsIn early access (MEAP)
What to know first
- matrix-matrix multiplicationMatrix multiplication is an operation on compatible matrices in which each entry of the product is the dot product of a row of the first matrix and a column of the second.
- float16float16 is a 16-bit floating-point format, commonly IEEE 754 binary16, with less precision and range than 32-bit floating-point formats.
- hardware registerA hardware register is a small, rapidly accessible storage location within a processor or processing device that holds data, addresses, or control information during execution.
- inner productAn inner product is a scalar-valued operation on two vectors that generalizes the dot product, which for real coordinate vectors is the sum of products of corresponding components.
Related concepts
- matrixpart of · A matrix is a rectangular two-dimensional array of elements arranged in rows and columns.
- CUTLASSused by · CUTLASS is NVIDIA’s collection of C++ templates for implementing high-performance linear algebra and tensor computations on GPUs.
- WMMA fragmenthas part · A WMMA fragment is a warp-distributed object that holds a portion of a matrix tile or accumulator across the threads of a warp.
- tile sizeconfigured by · Tile size specifies the dimensions or number of elements in a tile, a portion of data processed as a unit.
- shared memoryuses · Shared memory is a memory region accessible to multiple processes, threads, or other concurrent execution contexts for sharing data.
Questions about tile
What is tile?
A tile is a bounded block of elements from a larger array, matrix, or tensor that is treated as a unit of computation.
Which Manning books explain tile?
GPU Programming with Triton, CUDA for LLMs and Grokking GPU Programming.
What should I know before learning tile?
Manning books that teach tile usually introduce matrix-matrix multiplication, float16, hardware register and inner product first.
What is tile part of?
Tile is part of matrix. A matrix is a rectangular two-dimensional array of elements arranged in rows and columns.
What are the parts of tile?
Tile includes WMMA fragment and micro-tile.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.


