6 papers
The Quick and the Dead: Estimating Sparse-Matrix Permanents with Adaptive Work Filtering
Deniz Elbek, Yiğit Manafi, Zeynep Gürdal +2
Rasmussen's permanent estimator is a simple and unbiased estimator for the permanent of a binary matrix, but its practical performance can be limited by trajectories that terminate…
Graph Traversal on Tensor Cores: A BFS Framework for Modern GPUs
Deniz Elbek, Kamer Kaya
Modern GPUs have Tensor Cores (TCs) capable of extremely high-throughput matrix operations, yet graph algorithms remain difficult to accelerate because of their irregular and data-…
Diagonal Packing for Efficient Homomorphic Sparse Matrix-Vector Multiplication
Kemal Mutluergil, Deniz Elbek, Kamer Kaya +1
Homomorphic encryption (HE) enables computation over encrypted data but incurs a substantial overhead. For sparse matrix-vector multiplication, the widely used Halevi-Shoup scheme…
BLEST: Blazingly Efficient BFS using Tensor Cores
Deniz Elbek, Kamer Kaya
Breadth-First Search (BFS) is a fundamental graph kernel that underpins a wide range of applications. While modern GPUs provide specialised Matrix-Multiply-Accumulate (MMA) units,…
SUperman: Efficient Permanent Computation on GPUs
Deniz Elbek, Fatih Taşyaran, Bora Uçar +1
The permanent is a function, defined for a square matrix, with applications in various domains including quantum computing, statistical physics, complexity theory, combinatorics, a…
Fully-Automated Code Generation for Efficient Computation of Sparse Matrix Permanents on GPUs
Deniz Elbek, Kamer Kaya
Registers are the fastest memory components within the GPU's complex memory hierarchy, accessed by names rather than addresses. They are managed entirely by the compiler through a…