Boris Grot

Boris Grot

Auto-generated profile, based on publicly available information

Boris Grot

University of Edinburgh, Edinburgh, United Kingdom

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 October 2016
Verified
Conference Paper
Open access
PDF file
SNStanko Novakovic
Stanko Novakovic
ADAlexandros Daglis
Alexandros Daglis
EBEdouard Bugnion
Edouard Bugnion
BFBabak Falsafi
Babak Falsafi
BGBoris Grot
Boris Grot
To provide low latency and high throughput guarantees, most large key-value stores keep the data in the memory of many servers. Despite the natural parallelism across lookups, the load imbalance, introduced by heavy skew in the popularity distribution of keys, limits performance. To avoid violating tail latency service-level objectives, systems tend to keep server utilization low and organize the data in micro-shards, which provides units of migration and replication for the purpose of load balancing. These techniques reduce the skew, but incur additional monitoring, data replication and consistency maintenance overheads. In this work, we introduce RackOut, a memory pooling technique that leverages the one-sided remote read primitive of emerging rack-scale systems to mitigate load imbalance while respecting service-level objectives. In RackOut, the data is aggregated at rack-scale granularity, with all of the participating servers in the rack jointly servicing all of the rack's micro-shards. We develop a queuing model to evaluate the impact of RackOut at the datacenter scale. In addition, we implement a RackOut proof-of-concept key-value store, evaluate it on two experimental platforms based on RDMA and Scale-Out NUMA, and use these results to validate the model. Our results show that RackOut can increase throughput up to 6x for RDMA and 8.6x for Scale-Out NUMA compared to a scale-out deployment, while respecting tight tail latency service-level objectives.

13 June 2015
Verified
Conference Paper
Open access
ADAlexandros Daglis
Alexandros Daglis
SNStanko Novaković
Stanko Novaković
EBEdouard Bugnion
Edouard Bugnion
BFBabak Falsafi
Babak Falsafi
BGBoris Grot
Boris Grot
Datacenter operators rely on low-cost, high-density technologies to maximize throughput for data-intensive services with tight tail latencies. In-memory rack-scale computing is emerging as a promising paradigm in scale-out datacenters capitalizing on commodity SoCs, low-latency and high-bandwidth communication fabrics and a remote memory access model to enable aggregation of a rack's memory for critical data-intensive applications such as graph processing or key-value stores. Low latency and high bandwidth not only dictate eliminating communication bottlenecks in the software protocols and off-chip fabrics but also a careful on-chip integration of network interfaces. The latter is a key challenge especially in architectures with RDMA-inspired one-sided operations that aim to achieve low latency and high bandwidth through on-chip Network Interface (NI) support. This paper proposes and evaluates network interface architectures for tiled manycore SoCs for in-memory rack-scale computing. Our results indicate that a careful splitting of NI functionality per chip tile and at the chip's edge along a NOC dimension enables a rack-scale architecture to optimize for both latency and bandwidth. Our best manycore NI architecture achieves latencies within 3% of an idealized hardware NUMA and efficiently uses the full bisection bandwidth of the NOC, without changing the on-chip coherence protocol or the core's microarchitecture.

23 October 2023
Verified
Conference Paper
Open access
DUDmitrii Ustiugov
Dmitrii Ustiugov
DPDohyun Park
Dohyun Park
LCLazar Cvetković
Lazar Cvetković
MDMihajlo Djokic
Mihajlo Djokic
HHHongyu Hè
Hongyu Hè
AKAna Klimovic
Ana Klimovic
Serverless is an increasingly popular cloud computing paradigm that has stimulated new systems research opportunities. However, developing and evaluating serverless systems in a research setting (i.e., "in-vitro", without access to a large-scale production cluster and real workloads) is challenging yet vital for innovation. Recently, several serverless providers have released production traces consisting of large sets of functions with their invocation inter-arrival time, execution time, and memory footprint distributions. However, executing the workload synthesized from these traces requires a massive cluster, making experiments expensive and time-consuming. In this work, we show how to use the data available in production traces to construct workload summaries of configurable scales that remain highly representative of the original trace characteristics and can be used to evaluate serverless systems in-vitro. Compared to random sampling of functions from the original trace, our method can generate summaries of up to 10X higher representativity, measured as the average of the Wasserstein distances of the distributions of interest (e.g., function execution time and invocation inter-arrival time) from the respective distributions in the original trace. We release our toolchain that enables researchers to synthesize representative workload summaries and show how it can be used to evaluate the performance of serverless systems at diverse load scale factors.

3 September 2021 in IEEE Computer Architecture Letters
Verified
Journal Article
Closed access
TATruls Asheim
Truls Asheim
BGBoris Grot
Boris Grot
RKRakesh Kumar
Rakesh Kumar
Many contemporary applications feature multi-megabyte instruction footprints that overwhelm the capacity of branch target buffers (BTB) and instruction caches (L1-I), causing frequent front-end stalls that inevitably hurt performance. BTB is crucial for performance as it enables the front-end to accurately resolve the upcoming execution path and steer instruction fetch appropriately. Moreover, it also enables highly effective fetch-directed instruction prefetching that can eliminate many L1-I misses. For these reasons, commercial processors allocate vast amounts of storage capacity to BTBs. This letter aims to reduce BTB storage requirements by optimizing the organization of BTB entries. Our key insight is that today's BTBs store the full target address for each branch, yet the vast majority of dynamic branches have short offsets requiring just a handful of bits to encode. Based on this insight, we organize the BTB as an ensemble of smaller BTBs, each storing offsets within a particular range. Doing so enables a dramatic reduction in storage for target addresses. We also compress tags to reduce the tag storage cost. Our final design, called BTB-X, uses an ensemble of five BTBs with compressed tags that enables it to track 2.8x more branches than a conventional BTB with the same storage budget.

28 October 2023
Verified
Conference Paper
Open access
DSDavid Schall
David Schall
ASAndreas Sandberg
Andreas Sandberg
BGBoris Grot
Boris Grot
Serverless computing is a popular software deployment model for the cloud, in which applications are designed as a collection of stateless tasks. Developers are charged for the CPU time and memory footprint during the execution of each serverless function, which incentivizes them to reduce both runtime and memory usage. As a result, functions tend to be short (often on the order of a few milliseconds) and compact (128–256 MB). Cloud providers can pack thousands of such functions on a server, resulting in frequent context switches and a tremendous degree of interleaving. As a result, when a given memory-resident function is re-invoked, it commonly finds its on-chip microarchitectural state completely cold due to thrashing by other functions — a phenomenon termed lukewarm invocation. Our analysis shows that the cold microarchitectural state due to lukewarm invocations is highly detrimental to performance, which corroborates prior work. The main source of performance degradation is the front-end, composed of instruction delivery, branch identification via the BTB and the conditional branch prediction. State-of-the-art front-end prefetchers show only limited effectiveness on lukewarm invocations, falling considerably short of an ideal front-end. We demonstrate that the reason for this is the cold microarchitectural state of the branch identification and prediction units. In response, we introduce Ignite, a comprehensive restoration mechanism for front-end microarchitectural state targeting instructions, BTB and branch predictor via unified metadata. Ignite records an invocation’s control flow graph in compressed format and uses that to restore the front-end structures the next time the function is invoked. Ignite outperforms state-of-the-art front-end prefetchers, improving performance by an average of 43% by significantly reducing instruction, BTB and branch predictor MPKI.

30 March 2025
Verified
Conference Paper
Open access
TZTingji Zhang
Tingji Zhang
BGBoris Grot
Boris Grot
WHWenjian He
Wenjian He
YLYashuai Lv
Yashuai Lv
PQPeng Qu
Peng Qu
YZYouhui Zhang
Youhui Zhang