gigaflops


Also found in: Encyclopedia, Wikipedia.

gig·a·flops

 (gĭg′ə-flŏps′, jĭg′-) or gig·a·flop (-flŏp′)
n. pl. gigaflops
A measure of computing speed equal to one billion floating-point operations per second.

gig•a•flops

(ˈgɪg əˌflɒps, ˈdʒɪg-)
n.
a measure of computer speed, equal to one billion floating-point operations per second.
[1985–90; see flops]
Mentioned in ?
References in periodicals archive ?
It offers 1,011 gigaflops of peak double-precision performance, 30MB of cache and memory capacity of 8GB.
Tesla M2090, which has 512 CUDA parallel processing cores, delivers 665 gigaflops of peak double-precision performance, enabling application acceleration by up to 10 times, compared to using a processing unit (CPU) alone, Nvidia said.
This includes single-node Linpack performance of 563,2 GigaFLOPS, multi-node performance of 522 GigaFLOPS and DGEMM performance of 621 GigaFLOPS.
The company said that the card delivers 620 GigaFLOPS of computing power and GDDR5 memory and also has full support for Microsoft's DirectX 11.
Each processor node has a peak performance of 64 gigaflops and consists of 8 vector processors (each of which has a peak performance of 8 gigaflops).
3 GHz PowerPC G5 processors with over 35 gigaflops of processing power per system.
It is based on the Linpack benchmark, which measures a computer's floating-point rate of executing linear equations and is expressed in Gigaflops (Gflop/s) or billions of floating point operations per second.
According to Cupertino, California-based Apple, Xserve G5 is about 60% more powerful than its PowerPC G4-based Xserve predecessor, and delivers 30 gigaflops of processing power per 1U rack-mount server.
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.
Designed from the ground up for HPC, computational science and supercomputing, NVIDIA's Tesla M2090 GPUs provide 512 CUDA cores with 665 gigaflops of peak performance to accelerate even the most demanding computationally intensive workloads.
4 gigaflops per single core and processing performance of 839 teraflops.