I’ve been away from Julia for several months, and have been rerunning GPU code from this past summer on a new installation of Jula 1.5.3 and CUDA.jl (previously I used the separate CUDA packages). My subset sum program now runs much slower (3 1/3 sec compared to 159 ms): julia> s = rand(1:10000000,…

OK, that looks like a bug then, please file an issue (with a fully reproducible example, etc). You could always try to reduce some more or profile individual operations to see where the issue is.

Performance regression with GPUArrays subset sum

Specific Domains GPU

eaubanel December 9, 2020, 7:20pm 10

Thanks for prompting me, I just did submit an issue

Topic		Replies	Views
Performance of view with cuArrays GPU	11	2705	November 11, 2018
Is there a way to guarantee 0 allocations when accessing an array? General Usage	18	4359	June 1, 2017
Dot-product of CuArray views is slow GPU performance , memory-allocation , views	10	1567	May 11, 2021
Array views becoming dominant source of memory allocation Performance	31	5264	November 14, 2018
Puzzled by the difference in performance when summing an array in different ways Performance array , memory-allocation	4	898	July 19, 2019

Performance regression with GPUArrays subset sum

Related topics