New compute efficiency data shows GPUs with a clear edge over CPUs, but the gap is narrowing as CPUs adopt wide vectors (e.g. AVX). Surprisingly, a throughput CPU is the most energy efficient processor, offering hope for future architectures. Our data also shows some advantages of AMD’s Bulldozer, and the overhead associated with highly scalable server CPUs.
Highlights of the upcoming 2012 ISSCC include the first 22nm disclosures from Intel and several SoC papers from AMD, Cavium Networks and Oracle. Looking out further to the future, the clear focus is power consumption. There are several papers from Intel on low-power logic, one from IBM discussing 3D integration of embedded DRAM and a third from Fujitsu on system level power for the K supercomputer.
Hot Chips 21 is nearly upon us, and with it comes updates from the major processor vendors and players in the PC industry and beyond. Key themes this year include CPUs, chipsets, FPGA and GPU co-processors and academic parallelism research. Our preview will briefly discuss and analyze some of the more interesting topics, with CPU highlights including AMD’s Magny Cours, Fujitsu’s SPARC64-VIIIfx, IBM’s POWER7, Intel’s trifecta of Moorestown, Beckton/Nehalem-EX and Westmere, and Rainbow Falls from Sun. In the broader ecosystem, there will be presentations on OpenCL, Ion from Nvidia, TI’s OMAP SOC for mobile phones, and three major parallelism labs – Berkeley, Illinois and Stanford.
David Wang provides an overview of disclosures at IEDM 2007, including presentations from TSMC, Fujitsu, IBM, Toshiba, Sony, AMD, NEC on their 45nm immersion lithography processes and Intel’s 45nm high-K and metal gate process which relies on dry lithography.