tom's Hardware on MSN3mon
AI engineers claim new algorithm reduces AI power consumption by 95% — replaces complex floating-point multiplication with integer addition
Engineers from BitEnergy AI, a firm specializing in AI inference technology, has developed a means of artificial intelligence ...
Computing3mon
Meet the engineer who believes he can reduce AI’s energy consumption by up to 30%
Replacing computationally complex floating-point tensor multiplication with the much simpler integer addition is 20 times more efficient. Together with incoming hardware improvements this promises ...
Design-Reuse7y
How to Reduce FPGA Logic Cell Usage by >x5 for Floating-Point FFTs
These DSP blocks provide several basic floating-point primitives: multiplication, accumulation and addition. Centar’s architecture focuses on doing exactly this in that it consists of an array of ...