(r_∞, n_1/2 s_1/2) Measurements on the 2-CPU Cray X-MP

Summary

We report performance measurements made on the 2-CPU Cray X-MP at ECMWF, Reading. Vector (SIMD) performance on one CPU is interpreted by the two parameters (r_∞, n_1/2), and we find for dyadic operations using FORTRAN r_∞ = 70 Mflop/s, n_1/2 = 53 flop. All vector triadic operations produce r_∞ = 107 Mflop/s, n_1/2 = 45 flop; and a triadic operation with two vectors and one scalar gives r_∞ = 148 Mflop/s and n_1/2 = 60 flop. MIMD performance using both CPUs on one job is interpreted with the two parameters (r_∞, s_1/2),_1/2where s_1/2 is the amount of arithmetic that could have been done during the time taken to synchronize the two CPUs. We find, for dyadic operations using the TSKSTART and TSKWAIT synchronization primitives, that R_∞ = 130 Mflop/s and s_1/2 = 5700 flop. This means that a job must contain more than ∼6000 floating-point operations if it is to run more than 50% of the maximum performance when split between both CPUs by this method. Less expensive synchronization methods using LOCKS and EVENTS reduce s_1/2 to 4000 flop and 2000 flop respectively. A simplified form of LOCK synchronization written in CAL code further reduces s_1/2 to 220 flop. This is probably the minimum possible value for synchronization overhead on the Cray X-MP.