Benchmarking modern multiprocessors

1,129 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

CATalyst: Defeating last-level cache side channel attacks in cloud computing (2016, methodology): “We measure the impact on legacy applications using 22 SPEC CPU2006 [17] and 12 PARSEC [8] benchmarks.”
Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing (2012, background): “benchmarks [1] are one such example, with a focus on broad cov erage of characteristic workloads and parallelization patterns suitable for the shared-memory architecture of sy mmetric multiprocessors (SMPs) or chip multiprocessors (CMPs).”
Legion: Expressing locality and independence with logical regions (2012, methodology): “Our second experiment is a port of the fluidanimate benchmark from the PARSEC benchmark suite[8], which does a particle-based simulation of an incompressible fluid.”
Shenango: Achieving High CPU Efficiency for Latency-sensitive Datacenter Workloads (2019, methodology): “To support batch processing applications, we implemented a pthread shim layer for Shenango that enables it to run the entire PARSEC suite [19] without modifications.”
DAWG: A Defense Against Cache Timing Attacks in Speculative Execution Processors (2018, methodology): “We focus on read-only data in our evaluation, as benchmarks with low L1i MPKI like GAPBS, PARSEC, or SPECCPU are poorly suited to study code cache sensitivity.”