Machine Learning Accelerators documentation

Assignments:

• Assignment 01: Tensors and Einsum
• Assignment 02: GPU Architecture and cuTile
• Assignment 03: Matrix Multiplication with cuTile
• Assignment 04: Tensor Contractions on GPUs
• Assignment 05: Contraction Interface and L2 Optimization
• Assignment 06: Multi-Input Einsum Contraction
• Assignment 07: Inferring the VLIW ISA of XDNA2
• Assignment 08: XDNA GEMM Kernel
• Assignment 09: XDNA GEMM
• Assignment 10: Using the whole NPU

Submissions:

• Submission 01: Tensors and Einsum
• Submission 02: GPU Architecture and cuTile
• Submission 03: Matrix Multiplication with cuTile
• Submission 04: Tensor Contractions on GPUs
• Submission 05: Contraction Interface and L2 Optimization
• Submission 06: Multi-Input Einsum Contraction
• Submission 07: Inferring the VLIW ISA of XDNA2
• Submission 08: XDNA GEMM Kernel
• Submission 09: XDNA GEMM
• Submission 10: Using the whole NPU
• Group Specific Component: Un-fusing the MatMul kernel