The Tensor Algebra Compiler
8 572
15
Microsoft Research334 тыс
Следующее
22.12.17 – 1 1751:15:07Популярные
05.05.23 – 4 5101:32:25Опубликовано 22 декабря 2017, 21:18
Linear algebra is a work-horse of numerical computing. Tensor algebra is a generalization of linear algebra with applications in scientific computing, machine learning, and data analytics. Tensors are often sparse and compound operations must frequently be computed in a single kernel for performance and to save memory. Programmers are left to write kernels for every operation of interest on dense and sparse tensors in different formats. The combinations are infinite, which makes it impossible to manually implement and optimize them all. I will present the first compiler technique to automatically generate kernels for any compound linear and tensor algebra operation on dense and sparse tensors. The technique is implemented in a C++ library called taco. Its performance is competitive with best-in-class hand-optimized kernels in popular libraries, while supporting far more tensor operations. For more information, see tensor-compiler.org.
See more at microsoft.com/en-us/research/v...
See more at microsoft.com/en-us/research/v...
Свежие видео
2 дня – 2207:08
4 дня – 31 49810:32
10 дней – 17 34151:38
15 дней – 1 8370:53
16 дней – 171 88518:46
16 дней – 3 6160:28Случайные видео
54 дня – 4 4805:08
236 дней – 16 96716:55
237 дней – 253 4180:12
339 дней – 1 4930:51
24.10.20 – 2 643 5228:06
12.04.16 – 78 3445:59
9 дней – 1 4260:43
12 дней – 98 9852:58
13 дней – 1259:34
15 дней – 3 3700:19
19 дней – 30 2079:25
23 дня – 12 6638:17
1 день – 5250:40
2 дня – 2 5661:30