Robert A. van de Geijn
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Robert A. van de Geijn has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Field G. Van Zee
The University of Texas at Austin, Austin, USA
2 shared publications Behnam Robatmili
The University of Texas at Austin, Austin, TX, USA
1 shared publication- Devangi N. Parikh
University of Texas at Austin
1 shared publication - Doug Burger
Microsoft, Redmond, WA, USA
1 shared publication Jeffrey R. Diamond
The University of Texas at Austin, Austin, TX, USA
1 shared publicationKazushige Goto
The University of Texas at Austin, Austin, TX, USA
1 shared publication
Latest Publications
- Open Access
- 21 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 111-121
Towards a Unified Implementation of GEMM in BLIS
Matrix libraries often focus on achieving high performance for problems considered to be either "small" or "large", as these two scenarios tend to respond best to different optimization strategies. We propose a unified technique for implementing matrix operations like general matrix multiplication (gemm) that can achieve high performance for both small and large problem sizes. The key is to fuse packing - an operation that copies data to a contiguous layout in memory and which is critical for large matrix performance - with the first computational "pass" over that data. This boosts performance across the problem size spectrum. As a result, tuning general-purpose libraries becomes simpler since it obviates the need to carefully express and parameterize logic that chooses between a "small matrix" strategy and a "large matrix" strategy. A prototype implementation of the technique built with the BLAS-like Library Instantiation Software (BLIS) framework is described and performance on a range of architectures is reported.
- 21 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 111-121
Open AccessTowards a Unified Implementation of GEMM in BLIS
Matrix libraries often focus on achieving high performance for problems considered to be either "small" or "large", as these two scenarios tend to respond best to different optimization strategies. We propose a unified technique for implementing matrix operations like general matrix multiplication (gemm) that can achieve high performance for both small and large problem sizes. The key is to fuse packing - an operation that copies data to a contiguous layout in memory and which is critical for large matrix performance - with the first computational "pass" over that data. This boosts performance across the problem size spectrum. As a result, tuning general-purpose libraries becomes simpler since it obviates the need to carefully express and parameterize logic that chooses between a "small matrix" strategy and a "large matrix" strategy. A prototype implementation of the technique built with the BLAS-like Library Instantiation Software (BLIS) framework is described and performance on a range of architectures is reported.
- Open Access
Supporting mixed-datatype matrix multiplication within the BLIS framework
We approach the problem of implementing mixed-datatype support within the general matrix multiplication (GEMM) operation of the BLIS framework, whereby each matrix operand A, B, and C may be stored as single- or double-precision real or complex values. Another factor of complexity, whereby the computation is allowed to take place in a precision different from the storage precisions of either A or B, is also included in the discussion. We first break the problem into mostly orthogonal dimensions, considering the mixing of domains separately from mixing precisions. Support for all combinations of matrix operands stored in either the real or complex domain is mapped out by enumerating the cases and describing an implementation approach for each. Supporting all combinations of storage and computation precisions is handled by typecasting the matrices at key stages of the computation---during packing and/or accumulation, as needed. Several optional optimizations are also documented. Performance results gathered on a 56-core Marvell ThunderX2 and a 52-core Intel Xeon Platinum demonstrate that high performance is mostly preserved, with modest slowdowns incurred from unavoidable typecast instructions. The mixed-datatype implementation confirms that combinatoric intractability is avoided, with the framework relying on only two assembly microkernels to implement 128 datatype combinations.
Open AccessSupporting mixed-datatype matrix multiplication within the BLIS framework
We approach the problem of implementing mixed-datatype support within the general matrix multiplication (GEMM) operation of the BLIS framework, whereby each matrix operand A, B, and C may be stored as single- or double-precision real or complex values. Another factor of complexity, whereby the computation is allowed to take place in a precision different from the storage precisions of either A or B, is also included in the discussion. We first break the problem into mostly orthogonal dimensions, considering the mixing of domains separately from mixing precisions. Support for all combinations of matrix operands stored in either the real or complex domain is mapped out by enumerating the cases and describing an implementation approach for each. Supporting all combinations of storage and computation precisions is handled by typecasting the matrices at key stages of the computation---during packing and/or accumulation, as needed. Several optional optimizations are also documented. Performance results gathered on a 56-core Marvell ThunderX2 and a 52-core Intel Xeon Platinum demonstrate that high performance is mostly preserved, with modest slowdowns incurred from unavoidable typecast instructions. The mixed-datatype implementation confirms that combinatoric intractability is avoided, with the framework relying on only two assembly microkernels to implement 128 datatype combinations.
- Open Access
- 20 February 2008
- Published by Association for Computing Machinery (ACM)
- p. 63-72
High performance dense linear algebra on a spatially distributed processor
- 20 February 2008
- Published by Association for Computing Machinery (ACM)
- p. 63-72
Open AccessHigh performance dense linear algebra on a spatially distributed processor