Meet NVC++, the world's first compiler with GPU-accelerated C++17 parallel algorithms. I'm incredibly proud of my team - we've been building this for two years.https://twitter.com/NVIDIAHPCDev/status/1260941259541110784 …
-
0:18Show this thread -
Replying to @blelbach
How do we find out more? How does it compare to just CUDA
1 reply . 0 retweets 1 like
Replying to @HTT_WFT
Our C++17 parallel algorithms implementation is just as fast as Thrust/CUB. If you need to write your own optimized kernels, you will probably want to write them in CUDA C++. But many users can just use C++17 parallel algorithms.
5:32 pm - 15 May 2020
From Sunnyvale, CA
0 replies .
0 retweets
1 like
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.