double precision

(redirected from Double-precision)
Also found in: Acronyms, Wikipedia.

double precision

[¦dəb·əl prə′sizh·ən]
(computer science)
The use of two computer words to represent a double-length number.

double precision

Using two computer words instead of one to hold a number used for calculations, thus allowing twice as large a number for more arithmetic precision. Contrast with single precision.
References in periodicals archive ?
01 TFlops) double-precision performance, and supports 8GB of GDDR5 memory at a higher 320 GB/sec memory bandwidth.
AXI(TM) and AHB(TM) standard interfaces that are configurable for 32-bit or 64-bit transactions and an optional FPU that supports both single- and double-precision operations enable the HS processors to be implemented with the optimal combination of performance and energy consumption.
The chips will offer peak double-precision performance of 1 teraflop per second, and include 28.
Xserve G5, the most powerful Xserve yet, delivers over 15 gigaflops of peak double-precision processing power per system and features the same revolutionary PowerPC G5, 64-bit processor used in Virginia Tech's cluster of 1,100 Power Mac G5s,the world's third fastest supercomputer.
The MPC7400 supplements AltiVec with a more powerful floating point unit, which is fully pipelined for double-precision operations, not just the single precision pipelined by the G3, and there is also an internal memory bus that is 128 bits wide, twice that of the G3.
The first presentation of the first silicon of "Knights Corner" co-processor showed that Intel architecture is capable of delivering more than 1 TFLOPs of double precision floating point performance (as measured by the Double-precision, General Matrix-Matrix multiplication benchmark -- DGEMM*).
This architecture supports, on a block-by-block basis, various precisions per block, ranging from low resolution fixed point video up to single-precision floating point within a single DSP block, and even double-precision floating point with minimal external logic.
Graphics processors lead in their ability to deliver several teraflops of single-precision and roughly half a teraflop of double-precision performance while consuming around 200 watts of power (between 185 and 225 watts).
The Silicon Graphics 750 system with 292GB memory, 428GFLOPS peak performance for double-precision computations and 856GFLOPS peak performance for single-precision computations, follows the Pentium(R) III Xeon(TM) cluster that was operative at OSC for the past 18 months.
Ultra small size, a high-performance 500Mhz superscalar SH-4A core, a double-precision FPU, multiple serial interfaces, generous memory, 10/100 Ethernet and on-board 3.
The 1U SuperServer 6016GT-TF-FM207 provides up to 1 TeraFLOPS of double-precision performance, and the SuperServer 7046GT-TRF-FC407 comes loaded with four double-width NVIDIA Fermi C2070 GPU cards and supports three additional PCI-E add-on cards for high-bandwidth I/O.
As a result, anyone planning to use the current generation of graphics processors for scientific computation must consider the question "how important is single-precision compared to double-precision (64-bit) arithmetic for my application?