# Apache Spark (including Amazon EMR, Synapse Spark, and Google Cloud Dataproc) Revision 1 (11 October 2026) · Modeled snapshot · through 8 October 2026. All figures are research-informed estimates of analytical activity. Significant errors may remain; decimal places do not imply measurement precision. Layer: compute. Values cover the years in which this category appears in the public timeline. Absence is not proof of zero use. ## Names and inspection notes ### 2010: Spark (independent deployments) Spark’s first public release arrived in early 2010, with datasets cached in memory across machines for repeated use. This 0.05% slice represents early batch processing, before Spark SQL arrived in 2014; its size is illustrative, not measured. ### 2011–2012: Spark (independent deployments) This category is shown in the compute layer. ### 2013–2014: Apache Spark (independent deployments) This category is shown in the compute layer. ### 2015: Apache Spark (including Amazon EMR and Google Cloud Dataproc) Includes Spark workloads on Amazon EMR and Google Cloud Dataproc, alongside other hosted and self-managed Spark deployments. EMR workloads using Hadoop/Hive and Presto are counted with those engines. Databricks has a separate box. Google Cloud Dataproc was in public beta in 2015; general availability followed in February 2016. ### 2016–2019: Apache Spark (including Amazon EMR and Google Cloud Dataproc) Includes Spark workloads on Amazon EMR and Google Cloud Dataproc, alongside other hosted and self-managed Spark deployments. EMR workloads using Hadoop/Hive and Presto are counted with those engines. Databricks has a separate box. ### 2020: Apache Spark (including Amazon EMR, Synapse Spark, and Google Cloud Dataproc) Includes Spark workloads on Amazon EMR, Synapse Spark, and Google Cloud Dataproc, alongside other hosted and self-managed Spark deployments. EMR workloads using Hadoop/Hive and Presto are counted with those engines. Databricks has a separate box. ### 2021–2022: Apache Spark (including Amazon EMR, Synapse Spark, and Google Cloud Dataproc) Includes Spark workloads on Amazon EMR, Synapse Spark, and Google Cloud Dataproc, alongside other hosted and self-managed Spark deployments. EMR workloads using Hadoop/Hive, Presto, and Trino are counted with those engines. Databricks has a separate box. ### 2023–2026: Apache Spark (including Amazon EMR, Synapse Spark, and Google Cloud Dataproc) Includes Spark workloads on Amazon EMR, Synapse Spark, and Google Cloud Dataproc, alongside other hosted and self-managed Spark deployments. EMR workloads using Hadoop/Hive, Presto, and Trino are counted with those engines. Databricks and Fabric LH (Spark) have separate boxes. Spark Connect, introduced in Spark 3.4 in 2023, counts as direct Arrow access because it streams results to clients as Arrow batches. Internal Arrow use within other Spark workflows does not by itself put them in that category. ## Annual estimates | Year | Name in this year | Share of full compute layer | Connections and details | | --- | --- | --- | --- | | [2010](https://history.columnar.tech/years/2010.md) | Spark (independent deployments) | 0.05% | [Inspect](https://history.columnar.tech/connections/2010/compute/spark.md) | | [2011](https://history.columnar.tech/years/2011.md) | Spark (independent deployments) | 1% | [Inspect](https://history.columnar.tech/connections/2011/compute/spark.md) | | [2012](https://history.columnar.tech/years/2012.md) | Spark (independent deployments) | 2% | [Inspect](https://history.columnar.tech/connections/2012/compute/spark.md) | | [2013](https://history.columnar.tech/years/2013.md) | Apache Spark (independent deployments) | 3% | [Inspect](https://history.columnar.tech/connections/2013/compute/spark.md) | | [2014](https://history.columnar.tech/years/2014.md) | Apache Spark (independent deployments) | 4% | [Inspect](https://history.columnar.tech/connections/2014/compute/spark.md) | | [2015](https://history.columnar.tech/years/2015.md) | Apache Spark (including Amazon EMR and Google Cloud Dataproc) | 5% | [Inspect](https://history.columnar.tech/connections/2015/compute/spark.md) | | [2016](https://history.columnar.tech/years/2016.md) | Apache Spark (including Amazon EMR and Google Cloud Dataproc) | 5.5% | [Inspect](https://history.columnar.tech/connections/2016/compute/spark.md) | | [2017](https://history.columnar.tech/years/2017.md) | Apache Spark (including Amazon EMR and Google Cloud Dataproc) | 6% | [Inspect](https://history.columnar.tech/connections/2017/compute/spark.md) | | [2018](https://history.columnar.tech/years/2018.md) | Apache Spark (including Amazon EMR and Google Cloud Dataproc) | 6.5% | [Inspect](https://history.columnar.tech/connections/2018/compute/spark.md) | | [2019](https://history.columnar.tech/years/2019.md) | Apache Spark (including Amazon EMR and Google Cloud Dataproc) | 6.95% | [Inspect](https://history.columnar.tech/connections/2019/compute/spark.md) | | [2020](https://history.columnar.tech/years/2020.md) | Apache Spark (including Amazon EMR, Synapse Spark, and Google Cloud Dataproc) | 7.4% | [Inspect](https://history.columnar.tech/connections/2020/compute/spark.md) | | [2021](https://history.columnar.tech/years/2021.md) | Apache Spark (including Amazon EMR, Synapse Spark, and Google Cloud Dataproc) | 7.35% | [Inspect](https://history.columnar.tech/connections/2021/compute/spark.md) | | [2022](https://history.columnar.tech/years/2022.md) | Apache Spark (including Amazon EMR, Synapse Spark, and Google Cloud Dataproc) | 7.3% | [Inspect](https://history.columnar.tech/connections/2022/compute/spark.md) | | [2023](https://history.columnar.tech/years/2023.md) | Apache Spark (including Amazon EMR, Synapse Spark, and Google Cloud Dataproc) | 7.25% | [Inspect](https://history.columnar.tech/connections/2023/compute/spark.md) | | [2024](https://history.columnar.tech/years/2024.md) | Apache Spark (including Amazon EMR, Synapse Spark, and Google Cloud Dataproc) | 6.65% | [Inspect](https://history.columnar.tech/connections/2024/compute/spark.md) | | [2025](https://history.columnar.tech/years/2025.md) | Apache Spark (including Amazon EMR, Synapse Spark, and Google Cloud Dataproc) | 6.6% | [Inspect](https://history.columnar.tech/connections/2025/compute/spark.md) | | [2026](https://history.columnar.tech/years/2026.md) | Apache Spark (including Amazon EMR, Synapse Spark, and Google Cloud Dataproc) | 6% | [Inspect](https://history.columnar.tech/connections/2026/compute/spark.md) | --- [Markdown overview](https://history.columnar.tech/index.md) · [Interactive visualization](https://history.columnar.tech/) · [Methodology](https://history.columnar.tech/methodology.md) · [Terms of use](https://history.columnar.tech/terms.md) © 2026 Columnar Technologies Inc.