IEEE Computer Architecture Letters 

Abstract: Recently, both industry and academia have proposed many different roadmaps for the future of DRAM. Consequently, there is a growing need for an extensible DRAM simulator, which can be easily modified to judge the merits of today's DRAM standards as well as those of tomorrow. In this paper, we present Ramulator , a fast and cycle-accurate DRAM simulator that is built from the ground up for extensibility. Unlike existing simulators, Ramulator is based on a generalized template for modeling a DRAM system, which is only later infused with the specific details of a DRAM standard. Thanks to such a decoupled and modular design, Ramulator is able to provide out-of-the-box support for a wide array of DRAM standards: DDR3/4, LPDDR3/4, GDDR5, WIO1/2, HBM, as well as some academic proposals (SALP, AL-DRAM, TL-DRAM, RowClone, and SARP). Importantly, Ramulator does not sacrifice simulation speed to gain extensibility: according to our evaluations, Ramulator is 2.5 $\times$ faster than the next fastest simulator. Ramulator is released under the permissive BSD license.

Abstract: Computer architects must determine how tomost effectively use finite computational resources whenrunning simulations to evaluate new architectural ideas.To facilitate efficient simulations with a range of benchmarkprograms, rn have developed the MinneSPEC inputset for the SPEC CPU 2000 benchmark suite. Thisnew workload allows computer architects to obtain simulationresults in a reasonable time using existing sirnulators.While the MinneSPEC workload is derived from thestandard SPEC CPU 2000 warklcad, it is a valid benchmarksuite in and of itself for simulation-based research.MinneSPEC also may be used to run Iarge numbers ofsimulations to find "sweet spots" in the evaluation parameterspace. This small number of promising designpoints subsequently may be investigated in more detailwith the full SPEC reference workload. In the processof developing the MinneSPEC datasets, we quantify itsdifferences in terms of function-level execution patterns,instruction mixes, and memory behaviors compared tothe SPEC programs when executed with the reference inputs.We find that for some programs, the MinneSPECprofiles match the SPEC reference dataset program behaviorvery closely. For other programs, however, theMinneSPEC inputs produce significantly different programbehavior. The MinneSPEC workload has been recognizedby SPEC and is distributed with Version 1.2 andhigher of the SPEC CPU 2000 benchmark suite.

Abstract: The numerical representation precision required by the computations performed by Deep Neural Networks (DNNs) varies across networks and between layers of a same network. This observation motivates a precision-based approach to acceleration which takes into account both the computational structure and the required numerical precision representation. This work presents Stripes ( STR ), a hardware accelerator that uses bit-serial computations to improve energy efficiency and performance. Experimental measurements over a set of state-of-the-art DNNs for image classification show that STR improves performance over a state-of-the-art accelerator from 1.35 $\times$ to 5.33 $\times$ and by 2.24 $\times$ on average. STR ’s area and power overhead are estimated at 5 percent and 12 percent respectively. STR is 2.00 $\times$ more energy efficient than the baseline.