Summary: In many parallel applications, network latency causes a dramatic loss in processor utilization. This paper presents KaHPF, an optimizing HPF compiler, that uses software controlled access pipelining to hide communication latency. Various benchmarks of common, but complex communication patterns demonstrate KaHPF’s performance improvement on a Cray T3E. KaHPF’s compiled code is faster than code that uses highly optimized shared-memory system functions by a factor of 1.2 to 3.2. In comparison to PGI’s HPF compiler KaHPF shows an improvement of 3.9 to 30.4.
For the entire collection see [Zbl 0936.00039].