Abstract: Apparatuses, systems, and techniques to cause a first tensor to be translated into a second tensor according to a tensor map without storing information about a memory transaction corresponding to the translation. In at least one embodiment, one or more circuits are to perform an application programming interface (API) to cause a first tensor to be translated into a second tensor according to a tensor map without storing information about one or more memory transactions corresponding to the translation.

Abstract: Apparatuses, systems, and techniques to perform a tensor prefetch instruction to cause one or more tensors to be transformed and stored into one or more caches. In at least one embodiment, one or more circuits of a GPU are to perform a tensor prefetch instruction to cause one or more tensors to be transformed and stored into one or more GPU caches.

Abstract: Apparatuses, systems, and techniques to perform a tensor prefetch instruction to cause one or more tensors to be stored into one or more caches. In at least one embodiment, one or more circuits of a GPU are to perform a tensor prefetch instruction to cause one or more tensors to be stored into one or more GPU caches.

Abstract: Apparatuses, systems, and techniques to perform a matrix multiplication using parallel processing. In at least one embodiment, a matrix multiplication is divided into a set of tiles, with each tile processed with a prolog task, a calculation task, and an epilog task. The prolog tasks are performed by a dedicated set of threads, with the remaining tasks performed in an interleaved manner using two or more thread groups.

Abstract: Matrix multiplication operations can be implemented, at least in part, on one or more tensor cores of a parallel processing unit. An efficiency of the matrix multiplication operations can be improved in cases where one of the input operands or the output operand of the matrix multiplication operation is a square matrix having a triangular data pattern. In such cases, the number of computations performed by the tensor cores of the parallel processing unit can be reduced by dropping computations and/or masking out elements of the square matrix input operand on one side of the main diagonal of the square matrix. In other cases where the output operand exhibits the triangular data pattern, computations can be dropped or masked out for the invalid side of the main diagonal of the square matrix. In an embodiment, a library implementing the matrix multiplication operations is provided.

Abstract: A parallel processing unit comprises a plurality of processors each being coupled to a memory access hardware circuitry. Each memory access hardware circuitry is configured to receive, from the coupled processor, a memory access request specifying a coordinate of a multidimensional data structure, wherein the memory access hardware circuit is one of a plurality of memory access circuitry each coupled to a respective one of the processors; and, in response to the memory access request, translate the coordinate of the multidimensional data structure into plural memory addresses for the multidimensional data structure and using the plural memory addresses, asynchronously transfer at least a portion of the multidimensional data structure for processing by at least the coupled processor. The memory locations may be in the shared memory of the coupled processor and/or an external memory.

Abstract: Apparatuses, systems, and techniques to perform a matrix multiplication using parallel processing. In at least one embodiment, a matrix multiplication is divided into a set of tiles, with each tile processed with a prolog task, a calculation task, and an epilog task. The prolog tasks are performed by a dedicated set of threads, with the remaining tasks performed in an interleaved manner using two or more thread groups.

Abstract: Apparatuses, systems, and techniques to perform a matrix multiplication using parallel processing. In at least one embodiment, a matrix multiplication is divided into a set of tiles, with each tile processed with a prolog task, a calculation task, and an epilog task. The prolog tasks are performed by a dedicated set of threads, with the remaining tasks performed in an interleaved manner using two or more thread groups.

Abstract: A parallel processing unit comprises a plurality of processors each being coupled to a memory access hardware circuitry. Each memory access hardware circuitry is configured to receive, from the coupled processor, a memory access request specifying a coordinate of a multidimensional data structure, wherein the memory access hardware circuit is one of a plurality of memory access circuitry each coupled to a respective one of the processors; and, in response to the memory access request, translate the coordinate of the multidimensional data structure into plural memory addresses for the multidimensional data structure and using the plural memory addresses, asynchronously transfer at least a portion of the multidimensional data structure for processing by at least the coupled processor. The memory locations may be in the shared memory of the coupled processor and/or an external memory.

Abstract: Apparatuses, systems, and techniques to perform computational operations in response to one or more compute uniform device architecture (CUDA) programs. In at least one embodiment, one or more computational operations are to cause one or more other computational operations to wait until a portion of matrix multiply-accumulate (MMA) operations have been performed.

Abstract: Apparatuses, systems, and techniques to perform computational operations in response to one or more compute uniform device architecture (CUDA) programs. In at least one embodiment, one or more computational operations are to cause one or more other computational operations to wait until a portion of matrix multiply-accumulate (MMA) operations have been performed.

Abstract: A parallel processing unit comprises a plurality of processors each being coupled to a memory access hardware circuitry. Each memory access hardware circuitry is configured to receive, from the coupled processor, a memory access request specifying a coordinate of a multidimensional data structure, wherein the memory access hardware circuit is one of a plurality of memory access circuitry each coupled to a respective one of the processors; and, in response to the memory access request, translate the coordinate of the multidimensional data structure into plural memory addresses for the multidimensional data structure and using the plural memory addresses, asynchronously transfer at least a portion of the multidimensional data structure for processing by at least the coupled processor. The memory locations may be in the shared memory of the coupled processor and/or an external memory.

Abstract: Apparatuses, systems, and techniques to perform computational operations in response to one or more compute uniform device architecture (CUDA) programs. In at least one embodiment, one or more computational operations are to cause one or more other computational operations to wait until a portion of matrix multiply-accumulate (MMA) operations have been performed.

Abstract: Apparatuses, systems, and techniques to perform a graphics processing unit (GPU) prefetch instruction to cause a variable amount of information to be stored into one or more GPU caches. In at least one embodiment, one or more circuits of a GPU are to perform a GPU prefetch instruction to cause a variable amount of information to be stored into one or more GPU caches.

Abstract: Apparatuses, systems, and techniques to perform a tensor prefetch instruction to cause one or more tensors to be stored into one or more caches. In at least one embodiment, one or more circuits of a GPU are to perform a tensor prefetch instruction to cause one or more tensors to be stored into one or more GPU caches.

Abstract: Apparatuses, systems, and techniques to generate a tensor mapping. In at least one embodiment, one or more circuits are to perform an application programming interface (API) to cause a mapping from a first tensor to a second tensor to be generated.

Abstract: Apparatuses, systems, and techniques to perform computational operations in response to one or more compute uniform device architecture (CUDA) programs. In at least one embodiment, one or more computational operations are to cause one or more other computational operations to wait until matrix multiply-accumulate (MMA) memory transactions are performed.

Abstract: Apparatuses, systems, and techniques to perform computational operations in response to one or more compute uniform device architecture (CUDA) programs. In at least one embodiment, one or more computational operations are to indicate whether matrix multiply-accumulate (MMA) memory operations are complete.

Abstract: Apparatuses, systems, and techniques to cause a first tensor to be translated into a second tensor according to a tensor map. In at least one embodiment, one or more circuits are to perform an application programming interface (API) to cause a first tensor to be translated into a second tensor according to a tensor map.

Abstract: Apparatuses, systems, and techniques to transform information corresponding to one or more memory transactions. In at least one embodiment, one or more circuits are to perform an application programming interface (API) to cause information corresponding to one or more memory transactions resulting from performance of the API to be transformed.