The existing C++ algorithm for sorting a list of five items took around 6.91 nanoseconds on a typical Intel Skylake chip. AlphaDev’s took 2.01 nanoseconds, around 70% faster. ...

As a reference, the algorithm in Fig 1 (using float without modeling fixed-point effects) ran in 3.5s (less than 2× faster than ac_fixed which models fixed-point effects). The runtimes presented in ...

Called SmartHLS, the tool allows C++ algorithms to be directly translated to FPGA-optimised RTL (register transfer level) code. It is based on the open-source Eclipse integrated development ...

Overall, AlphaDev’s new C++ sorting algorithms are 1.7 percent more efficient than the prior methods when sorting long sequences of numbers, and up to 70 percent faster for five-item sequences.

In a recently published white paper, we examine how SLX FPGA is used to take a MATLAB Embedded Coder generated C/C++ algorithm, in this case a Kalman filter, and optimize the C/C++ code for HLS. In ...

An artificial intelligence (AI) system based on Google DeepMind’s AlphaZero AI created algorithms that, when translated into the standard programming language C++, can sort data up to three ...