The interest in climbing and walking robots (CLAWAR) has intensified in recent years, and novel solutions for complex and very diverse applications have been anticipated by means of significant progress in this area o...
详细信息
ISBN:
(数字)9783540264156
ISBN:
(纸本)9783540264132;9783662500408
The interest in climbing and walking robots (CLAWAR) has intensified in recent years, and novel solutions for complex and very diverse applications have been anticipated by means of significant progress in this area of - botics. Moreover, the amalgamation of original ideas and related inno- tions, search for new potential applications and the use of state of the art support technologies permit to foresee an important step forward and a significant socio-economic impact of advanced robot technology in the - ture. This is leading to the creation and consolidation of a mobile service robotics sector where most of the robotics activities are foreseen in the - ture. The technology is now maturing to become of real benefit to society and methods of realizing this potential quickly are being eagerly explored. Robot standards and modularity are key to this and form key components of the research presented here. CLAWAR 2005 is the eighth in a series of international conferences - ganised annually since 1998 with the aim to report on latest research and development findings and to provide a forum for scientific discussion and debate within the mobile service robotics community. The series has grown in its popularity significantly over the years, and has attracted - searchers and developers from across the globe. The CLAWAR 2005 p- ceedings reports state of the art scientific and developmental findings p- sented during the CLAWAR 2005 conference in 131 technical presentations by authors from 27 countries covering the five continents.
Sparse matrix-vector semiring computation is a key operation in sparse matrix computations, with performance strongly dependent on both program design and the features of the sparse matrices. Given the diversity of sp...
Sparse matrix-vector semiring computation is a key operation in sparse matrix computations, with performance strongly dependent on both program design and the features of the sparse matrices. Given the diversity of sparse matrices, designing a tailored program for each matrix is challenging. To address this, we propose SRSparse1 an program generator that creates tailored programs by automatically combining program designing methods to fit specific input matrices. It provides two components: the problem definition configuration, which declares the computation, and the scheduling language, which can be leveraged by an auto-tuner to specify the program designs. The two are lowered to the intermediate representations of SRSparse, the Format IR and Kernel IR, which respectively generates format conversion routine and kernel code. We evaluate SRSparse on four representative sparse kernels and three format conversion routines. For sparse kernels, SRSparse achieves median speedups over handwritten programs: COO (3.50 ×), CSR-Adaptive (5.36 ×), CSR5 (2.06 ×), ELL (1.63 ×), Gunrock (1.57 ×), and GraphBLAST (1.96 ×); over an auto-tuner: AlphaSparse (1.16 ×); and over a compiler: TACO (1.71 ×). For format conversion routines, SRSparse achieves median speedups over handwritten implementations: Intel MKL (7.60 ×), SPARSKIT (2.61 ×), CUSP (2.77 ×), and Ginkgo (1.74 ×); and over a compiler: TACO (4.04 ×).
暂无评论