Even in embedded processors, the accuracy in a branch prediction significantly affects the performance. In designing a branch predictor, in addition to accuracy, microarchitects should consider area, delay and power consumption. We propose two techniques to reduce the power consumption; these techniques do not requires any additional storage arrays, do not incur additional delay (except just one MUX delay) and never deteriorate accuracy. One is to look up two predictions at a time by increasing the width (decreasing the depth) of the PHT (Prediction History Table). The other is to reduce unnecessary accesses to the BTB (Branch Target Buffer) by accessing the PHT in advance. Analysis results with Samsung Memory Compiler show that the proposed techniques reduce the power consumption of the branch predictor by 15-52%.

This letter presents point diffusion clock network (PDCN) with local clock tree synthesis (CTS) scheme. The clock network is implemented with ten times wider metal line space than typical mesh networks for low power and utilized to nine times smaller area CTS execution for minimized clock skew amount. The measurement results show that skew amount of PDCN with local CTS is reduced to 36% and latency is shrunk to 45% of the amount in a 4.81 mm2 CortexA-8 core with 65 nm Samsung process.

This letter proposes a low-power tournament branch predictor, in which the number of accesses to the branch predictors (local predictor or global predictor) is reduced. Analysis results with Samsung Memory Compiler show that the proposed branch predictor reduces the power consumption by 24-45%, compared to the conventional tournament branch predictor, not requiring any additional storage arrays, not incurring any additional delay and never harming accuracy.