The relentless march of process technology brings more integration and performance. IBM’s System z processor leads the charge at ISSCC 2013 clocking in at 5.7GHz and with 2.75B transistors.
The chip complexity chart below shows the trend in transistor integration on a single chip over the past two decades. While the 1 billion transistor integration mark was achieved some years ago, we now commonly see processors with beyond 2B transistors on a die.
Leveraging sophisticated strategies to lower leakage and manage voltage, variability and aging, has bolstered the continuing reduction in total power dissipation. This is helping rein in the increase in energy demands from PCs, servers, and similar systems. As power reduction becomes mandatory in every application, the trend towards maintaining near-constant clock frequencies also continues as shown below in frequency trends plot. This will yield solutions with less cost and cooling demands, resulting in greener products in the future.
Processors are choosing to trade off performance by lowering supply voltage. The performance loss of reduced voltage and clock frequency is compensated by further increased parallelism. Processors with more than eight cores are now commonplace. This year at ISSCC 2013, a 24-core processor from Fudan University will be presented as noted in the core count trend chart below.
In addition to the trend to integrate more cores on a single chip, multiple die within a single package are appearing. In ISSCC 2013, IBM will present a multi-chip module with six CPUs and two embedded DRAM cache chips. As well, dedicated co-processing units for graphics and communications are now commonly integrated on these complex systems-on-chip. Design of these SoCs requires broad collaboration across multiple disciplines including circuits, architecture, graphics, process technology, package, system design, energy efficiency and software. New performance and power-efficient computing techniques continue to be introduced at targeted, critical applications such as floating point and SIMD.
As technology continues to scale to finer dimensions, large caches are being integrated into microprocessor die.
Methods to communicate within-die as well as cross-die are becoming increasingly important. This is being driven by two trends: (1) 3D integration continues to grow in interest and (2) intra-die communications become more challenging with process scaling due increases in delay per unit interconnect length. Work on bringing package-level inter-chip transport onto the die has been gaining in popularity and we see this trend continuing.
This and other related topics will be discussed at length at ISSCC 2013, the foremost global forum for new developments in the integrated-circuit industry. ISSCC, the International Solid-State Circuits Conference, will be held on February 17-21, 2013, at the San Francisco Marriott Marquis Hotel.