Hacker News Reader

Intel suggests we program their GPUs and FPGAs with OpenCL. So, in theory, programming FPGAs could be not much harder than GPUs.

View on HN

At some point we should be able to code these things in (a subset) of C++. Microsoft has made C++ AMP for GPU programming. Herb Sutter has said it or something similar has a good chance of being standardised in C++ at some point.

Some chatter along those lines:

http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2015/p006...

Good news then. There is no shortage of speedup when we stop considering all memory being equal.

Reply on news.ycombinator.com