EXPLOITING IDLE FLOATING-POINT RESOURCES FOR INTEGER EXECUTION

In conventional superscalar microarchitectures with partitioned intege r and floating-point resources, all floating-point resources are idle during execution of integer programs. Palacharla and Smith [26] addres sed this drawback and proposed that the floating-point subsystem be au gmented to support integer operations. The hardware changes required a re expected to be fairly minimal. To exploit these idle floating resou rces, the compiler must identify integer code that can be profitably o ffloaded to the augmented floating-point subsystem. In this paper, we present two compiler algorithms to do this. The basic scheme offloads integer computation to the floating-point subsystem using existing pro gram loads/stores for inter-partition communication. For the SPECINT95 benchmarks, we show that this scheme offloads from 5% to 29% of the t otal dynamic instructions to the floating-point subsystem. The advance d scheme inserts copy instructions and duplicates some instructions to further offload computation. We evaluate the effectiveness of the two schemes using timing simulation. We show that the advanced scheme can offload from 9% to 41% of the total dynamic instructions to the float ing-point subsystem. In doing so, speedups from 3% to 23% are achieved over a conventional microarchitecture.