Sriram R. Vangal

The 48-core SCC Processor: the Programmer's View

The number of cores integrated onto a single die is expected to climb steadily in the foreseeable future. This move to many-core chips is driven by a need to optimize performance per watt. How best to connect these cores and how to program the resulting many-core processor, however, is an open research question. Designs vary from GPUs to cache-coherent shared memory multiprocessors to pure distributed memory chips. The 48-core SCC processor reported in this paper is an intermediate case, sharing traits of message passing and shared memory architectures. The hardware has been described elsewhere. In this paper, we describe the programmers view of this chip. In particular we describe RCCE: the native message passing model created for the SCC processor.

A 6.2-GFlops Floating-Point Multiply-Accumulator With Conditional Normalization

A pipelined single-precision floating-point multiply-accumulator (FPMAC) featuring a single-cycle accumulate loop using base 32 and internal carry-save arithmetic with delayed addition is described. A combination of algorithmic, logic, and circuit techniques enables multiply-accumulate operations at speeds exceeding 3 GHz with single-cycle throughput. The optimizations allow removal of the costly normalization step from the critical accumulate loop. This logic is conditionally powered down using dynamic sleep transistors on long accumulate operations, saving active and leakage power. In addition, an improved leading-zero anticipator (LZA) and overflow prediction logic applicable to carry-save format is presented. In a 90-nm seven-metal dual-VT CMOS process, the 2 mm2 custom design contains 230K transistors. The fully functional first silicon achieves 6.2 GFlops of performance while dissipating 1.2 W at 3.1 GHz, 1.3-V supply