A co-designed HW/SW approach to general purpose program acceleration using a programmable functional unit

Abstract

In this paper, we propose a novel programmable functional unit (PFU) to accelerate general purpose application execution on a modern out-of-order x86 processor in a complexity-effective way. Code is transformed and instructions are generated that run on the PFU using a co-designed virtual machine (Cd-VM). Groups of frequently executed micro-operations (micro-ops) are identified and fused into a macro-op (MOP) by the Cd-VM. The MOPs are executed on PFU. Results presented in this paper show that this HW/SW co-designed approach produces average speedups in performance of 17% in SPECFP and 10% in SPECINT, and up-to 33%, over modern out-of-order processor. Moreover, we also show that the proposed scheme not only out-performs dynamic vectorization using SIMD accelerators but also outperforms an 8-wide issue out-of-order processor.