Outputs (7)

Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields (2023)
Presentation / Conference Contribution
Isaac-Medina, B., Willcocks, C., & Breckon, T. (2023, June). Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields. Presented at IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023, Vancouver, BC

Neural Radiance Fields (NeRF) have attracted significant attention due to their ability to synthesize novel scene views with great accuracy. However, inherent to their underlying formulation, the sampling of points along a ray with zero width may res... Read More about Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields.

Efficient GPU Offloading with OpenMP for a Hyperbolic Finite Volume Solver on Dynamically Adaptive Meshes (2023)
Presentation / Conference Contribution
Wille, M., Weinzierl, T., Brito Gadeschi, G., & Bader, M. (2023, December). Efficient GPU Offloading with OpenMP for a Hyperbolic Finite Volume Solver on Dynamically Adaptive Meshes. Presented at ISC High Performance 2023, Hamburg

We identify and show how to overcome an OpenMP bottleneck in the administration of GPU memory. It arises for a wave equation solver on dynamically adaptive block-structured Cartesian meshes, which keeps all CPU threads busy and allows all of them to... Read More about Efficient GPU Offloading with OpenMP for a Hyperbolic Finite Volume Solver on Dynamically Adaptive Meshes.

Upscaling ExaHyPE – on each and every core (2023)
Report
Li, B., Schulz, H., Tuft, A., Weinzierl, T., & Zhang, H. (2023). Upscaling ExaHyPE – on each and every core. ARCHER2

We study a MPI+multithreaded PDE solver for hyperbolic partial differential equations. Each thread per rank handles a subdomain of the computational domain identified by a segment of a space-filling curve. The threads spawn additional tasks which sho... Read More about Upscaling ExaHyPE – on each and every core.

Computational graphs for matrix functions (2023)
Journal Article
Jarlebring, E., Fasi, M., & Ringh, E. (2023). Computational graphs for matrix functions. ACM Transactions on Mathematical Software, 48(4), 1-35. https://doi.org/10.1145/3568991

Many numerical methods for evaluating matrix functions can be naturally viewed as computational graphs. Rephrasing these methods as directed acyclic graphs (DAGs) is a particularly effective approach to study existing techniques, improve them, and ev... Read More about Computational graphs for matrix functions.

CPFloat: A C library for simulating low-precision arithmetic (2023)
Journal Article
Fasi, M., & Mikaitis, M. (2023). CPFloat: A C library for simulating low-precision arithmetic. ACM Transactions on Mathematical Software, 49(2), 1-32. https://doi.org/10.1145/3585515

One can simulate low-precision floating-point arithmetic via software by executing each arithmetic operation in hardware and then rounding the result to the desired number of significant bits. For IEEE-compliant formats, rounding requires only standa... Read More about CPFloat: A C library for simulating low-precision arithmetic.

Matrix Multiplication in Multiword Arithmetic: Error Analysis and Application to GPU Tensor Cores (2023)
Journal Article
Fasi, M., Higham, N. J., Lopez, F., Mary, T., & Mikaitis, M. (2023). Matrix Multiplication in Multiword Arithmetic: Error Analysis and Application to GPU Tensor Cores. SIAM Journal on Scientific Computing, 45(1), https://doi.org/10.1137/21M1465032

In multiword arithmetic, a matrix is represented as the unevaluated sum of two or more lower precision matrices, and a matrix product is formed by multiplying the constituents in low precision. We investigate the use of multiword arithmetic for impro... Read More about Matrix Multiplication in Multiword Arithmetic: Error Analysis and Application to GPU Tensor Cores.

Dynamic Unary Convolution in Transformers (2023)
Journal Article
Duan, H., Long, Y., Wang, S., Zhang, H., Willcocks, C. G., & Shao, L. (2023). Dynamic Unary Convolution in Transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11), 12747 - 12759. https://doi.org/10.1109/tpami.2022.3233482

It is uncertain whether the power of transformer architectures can complement existing convolutional neural networks. A few recent attempts have combined convolution with transformer design through a range of structures in series, where the main cont... Read More about Dynamic Unary Convolution in Transformers.