The fused multiply-add instruction leads to algorithms for extended-precision floating point: applications to java and high-performance computing.
Fred G. GustavsonJosé E. MoreiraRobert F. EnenkelPublished in: CASCON (1999)
Keyphrases
- floating point
- high performance computing
- instruction set
- sparse matrices
- fixed point
- graphics processing units
- massively parallel
- artificial intelligence
- image segmentation
- computer architecture
- computational science
- floating point arithmetic
- probabilistic model
- fault tolerant
- parallel computing
- scientific computing