What is the next implementation fabric?

The semiconductor industry is caught on two horns of the economics dilemma. The first is technology scaling: subwavelength lithography, masks, and variability; the second is design productivity: turnaround time, and the reusability of design effort. Proliferation of semiconductors and their applications benefits from fast, cheap, and under-control ASIC-style implementation. The industry needs one or more implementation fabrics that support medium volume, low cost, low power, low nonrecurring engineering costs, and low design cost. To this end, each of the panelists has a different take on what the next implementation fabric will look like, and the application domains or cost-performance tradeoff points that such a fabric must support. IEEE Design & Test thanks the roundtable participants: moderator Andrew Kahng (University of California, San Diego), comoderator John Cohn (IBM), Ivo Bolsens (Xilinx), Bhusan Gupta (STMicroelectronics), Christopher Hamlin (LSI Logic), Zvi Or-Bach (eASIC), and Lawrence Pileggi (Carnegie Mellon Univ.). D&T also thanks Andy Broom (AMI Semiconductor) for his sidebar, and gratefully acknowledges the help of Kaushik Roy (Purdue University), our Roundtables Editor, who organized the event. Special thanks go to the IEEE Computer Society for sponsoring the roundtable.