> ## Documentation Index > Fetch the complete documentation index at: https://sdk.cerebras.ai/llms.txt > Use this file to discover all available pages before exploring further. # SDK Code Examples > Tutorials and benchmarks from the Cerebras SDK examples repository. Example CSL programs, including tutorials and benchmarks that demonstrate individual language features and larger application kernels, live in the [SDK examples GitHub repository](https://github.com/Cerebras/sdk-examples). For step-by-step introductory tutorials that walk through the GEMV programs below, see [Build a GEMV Kernel](/csl/tutorials). ## GEMV Tutorial Series A progression of general matrix-vector product (GEMV) programs that introduce CSL features one at a time. First in a series; covers preliminaries of CSL syntax. A complete, runnable CSL program on a single PE. Use memory data structure descriptors (DSDs) for efficient tensor operations. Copy tensors between host and device with the `memcpy` functionality of `SdkRuntime`. Use compile-time parameters to specialize a program. Extend the program to run on multiple PEs. Use routes and colors to distribute a single GEMV across multiple PEs. More advanced routing across multiple PEs. Further extend the GEMV computation across a 2D grid. Alternative streaming version of the previous example. ## Topic Tutorials Focused examples illustrating specific language or library features. Pass and return arrays in compile-time functions. Use libraries bundled with the CSL compiler. Tasks activated in response to incoming wavelets. Efficiently stream only non-zero entries of sparse tensors. Use sentinels with routable colors. Fabric switches for limited runtime control of routes. Encode a special entry point with fabric switches. Fabric filters that let a PE selectively accept incoming wavelets. Buffer PE input/output with a FIFO DSD. The `@map` builtin for custom operations on data. Inter-PE communication with the `` library. Tracing via the `` library. Print values directly from the simulator. Color swap feature on WSE-2. Explicit microthread IDs on WSE-3. Flushing output queues on WSE-3 when multiple colors share a queue. ## Pipeline Tutorials Examples that build on wavelet-triggered tasks to process streaming data. Process one wavelet at a time with wavelet-triggered tasks. Use a FIFO to avoid stalls on large inputs. Reduce FIFO resource consumption with multiple pipelines. ## SDK Layout Tutorials Tutorials for the `SdkLayout` host API. Introduces the `SdkLayout` API. Define routes between code regions. Attach ports to code regions and wire them together. Connect ports to host-to-device and device-to-host streams. Put the pieces together in a full GEMV program. ## Benchmarks Programs that demonstrate more complex kernels on the Wafer-Scale Engine. GEMV using a checkerboard distribution across PEs. GEMV using the `` library. SUMMA matrix-multiply using the `` library. Compute a residual `r = b - Ax` on a 2 x 2 rectangle of PEs. Cholesky factorization of a symmetric positive-definite matrix. Time-marching 25-point stencil computation. Measure host-to-device and device-to-host WSE bandwidth. 7-point stencil sparse matrix-vector performance test. Power method on a sparse matrix. Conjugate Gradient (CG) solver on a sparse matrix. Preconditioned Conjugate Gradient solver. BiCGSTAB solver on a sparse matrix. Optimized matrix-vector products confined to single PEs. Row- and column-wise broadcasts across a PE rectangle. 3D Discrete Fourier Transform with a pencil decomposition. Conway's Game of Life on the WSE. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.