LlamaWeb is a WebGPU backend for llama.cpp that uses static memory planning, tunable kernels, and templated multi-precision support to cut memory use by 29-33% and raise decode throughput by 45-69% versus prior browser frameworks on tested hardware.
A Metric for Performance Portability
3 Pith papers cite this work, alongside 44 external citations. Polarity classification is still indexing.
3
Pith papers citing it
44
external citations · Pith
abstract
The term "performance portability" has been informally used in computing to refer to a variety of notions which generally include: 1) the ability to run one application across multiple hardware platforms; and 2) achieving some notional level of performance on these platforms. However, there has been a noticeable lack of consensus on the precise meaning of the term, and authors' conclusions regarding their success (or failure) to achieve performance portability have thus been subjective. Comparing one approach to performance portability with another has generally been marked with vague claims and verbose, qualitative explanation of the comparison. This paper presents a concise definition for performance portability, along with a simple metric that accurately captures the performance and portability of an application across different platforms. The utility of this metric is then demonstrated with a retroactive application to previous work.
years
2026 3representative citing papers
OpenMP port of gPLUTO achieves comparable performance to OpenACC on NVIDIA but is 3x slower at application level and up to 10x at kernel level on AMD MI250X, driven by strided memory accesses, latency bounds, and C++ abstraction overheads.
A Kokkos-based C++ port of the SACRA numerical relativity code achieves ~10x speedup on GPU/APU over the Fortran CPU version while preserving waveform accuracy, pi-symmetry, and second-order convergence.
citing papers explorer
-
Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU
LlamaWeb is a WebGPU backend for llama.cpp that uses static memory planning, tunable kernels, and templated multi-precision support to cut memory use by 29-33% and raise decode throughput by 45-69% versus prior browser frameworks on tested hardware.
-
On the Limits of Performance Portability in Directive-Based GPU Programming
OpenMP port of gPLUTO achieves comparable performance to OpenACC on NVIDIA but is 3x slower at application level and up to 10x at kernel level on AMD MI250X, driven by strided memory accesses, latency bounds, and C++ abstraction overheads.
-
SACRA-K: A Performance-Portable Numerical Relativity Code with Kokkos
A Kokkos-based C++ port of the SACRA numerical relativity code achieves ~10x speedup on GPU/APU over the Fortran CPU version while preserving waveform accuracy, pi-symmetry, and second-order convergence.