Merge pull request ClickHouse#340 from acking-you/datafusion-issue-15465

[datafusion] Remove unnecessary type conversions

Author: rschu1ze

datafusion/benchmark.sh

@@ -1,33 +1,29 @@
 #!/bin/bash
 
-# Install Rust
+echo "Install Rust"
 curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs > rust-init.sh
 bash rust-init.sh -y
 source ~/.cargo/env
 
+echo "Install Dependencies"
+sudo apt-get update
+sudo apt-get install --yes gcc
 
-# Install Dependencies
-sudo yum update -y
-sudo yum install gcc -y
-
-
-# Install DataFusion main branch
+echo "Install DataFusion main branch"
 git clone https://github.com/apache/arrow-datafusion.git
 cd arrow-datafusion/datafusion-cli
 git checkout 45.0.0
 CARGO_PROFILE_RELEASE_LTO=true RUSTFLAGS="-C codegen-units=1" cargo build --release
 export PATH="`pwd`/target/release:$PATH"
 cd ../..
 
-
-# Download benchmark target data, single file
+echo "Download benchmark target data, single file"
 wget --continue https://datasets.clickhouse.com/hits_compatible/hits.parquet
 
-# Download benchmark target data, partitioned
+echo "Download benchmark target data, partitioned"
 mkdir -p partitioned
 seq 0 99 | xargs -P100 -I{} bash -c 'wget --directory-prefix partitioned --continue https://datasets.clickhouse.com/hits_compatible/athena_partitioned/hits_{}.parquet'
 
-# Run benchmarks for single parquet and partitioned
+echo "Run benchmarks for single parquet and partitioned"
 ./run.sh single
 ./run.sh partitioned
-

datafusion/queries.sql

@@ -21,10 +21,10 @@ SELECT "UserID" FROM hits WHERE "UserID" = 435090932899640449;
 SELECT COUNT(*) FROM hits WHERE "URL" LIKE '%google%';
 SELECT "SearchPhrase", MIN("URL"), COUNT(*) AS c FROM hits WHERE "URL" LIKE '%google%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
 SELECT "SearchPhrase", MIN("URL"), MIN("Title"), COUNT(*) AS c, COUNT(DISTINCT "UserID") FROM hits WHERE "Title" LIKE '%Google%' AND "URL" NOT LIKE '%.google.%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
-SELECT * FROM hits WHERE "URL" LIKE '%google%' ORDER BY to_timestamp_seconds("EventTime") LIMIT 10;
-SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY to_timestamp_seconds("EventTime") LIMIT 10;
+SELECT * FROM hits WHERE "URL" LIKE '%google%' ORDER BY "EventTime" LIMIT 10;
+SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "EventTime" LIMIT 10;
 SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "SearchPhrase" LIMIT 10;
-SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY to_timestamp_seconds("EventTime"), "SearchPhrase" LIMIT 10;
+SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "EventTime", "SearchPhrase" LIMIT 10;
 SELECT "CounterID", AVG(length("URL")) AS l, COUNT(*) AS c FROM hits WHERE "URL" <> '' GROUP BY "CounterID" HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
 SELECT REGEXP_REPLACE("Referer", '^https?://(?:www\\.)?([^/]+)/.*$', '\\1') AS k, AVG(length("Referer")) AS l, COUNT(*) AS c, MIN("Referer") FROM hits WHERE "Referer" <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
 SELECT SUM("ResolutionWidth"), SUM("ResolutionWidth" + 1), SUM("ResolutionWidth" + 2), SUM("ResolutionWidth" + 3), SUM("ResolutionWidth" + 4), SUM("ResolutionWidth" + 5), SUM("ResolutionWidth" + 6), SUM("ResolutionWidth" + 7), SUM("ResolutionWidth" + 8), SUM("ResolutionWidth" + 9), SUM("ResolutionWidth" + 10), SUM("ResolutionWidth" + 11), SUM("ResolutionWidth" + 12), SUM("ResolutionWidth" + 13), SUM("ResolutionWidth" + 14), SUM("ResolutionWidth" + 15), SUM("ResolutionWidth" + 16), SUM("ResolutionWidth" + 17), SUM("ResolutionWidth" + 18), SUM("ResolutionWidth" + 19), SUM("ResolutionWidth" + 20), SUM("ResolutionWidth" + 21), SUM("ResolutionWidth" + 22), SUM("ResolutionWidth" + 23), SUM("ResolutionWidth" + 24), SUM("ResolutionWidth" + 25), SUM("ResolutionWidth" + 26), SUM("ResolutionWidth" + 27), SUM("ResolutionWidth" + 28), SUM("ResolutionWidth" + 29), SUM("ResolutionWidth" + 30), SUM("ResolutionWidth" + 31), SUM("ResolutionWidth" + 32), SUM("ResolutionWidth" + 33), SUM("ResolutionWidth" + 34), SUM("ResolutionWidth" + 35), SUM("ResolutionWidth" + 36), SUM("ResolutionWidth" + 37), SUM("ResolutionWidth" + 38), SUM("ResolutionWidth" + 39), SUM("ResolutionWidth" + 40), SUM("ResolutionWidth" + 41), SUM("ResolutionWidth" + 42), SUM("ResolutionWidth" + 43), SUM("ResolutionWidth" + 44), SUM("ResolutionWidth" + 45), SUM("ResolutionWidth" + 46), SUM("ResolutionWidth" + 47), SUM("ResolutionWidth" + 48), SUM("ResolutionWidth" + 49), SUM("ResolutionWidth" + 50), SUM("ResolutionWidth" + 51), SUM("ResolutionWidth" + 52), SUM("ResolutionWidth" + 53), SUM("ResolutionWidth" + 54), SUM("ResolutionWidth" + 55), SUM("ResolutionWidth" + 56), SUM("ResolutionWidth" + 57), SUM("ResolutionWidth" + 58), SUM("ResolutionWidth" + 59), SUM("ResolutionWidth" + 60), SUM("ResolutionWidth" + 61), SUM("ResolutionWidth" + 62), SUM("ResolutionWidth" + 63), SUM("ResolutionWidth" + 64), SUM("ResolutionWidth" + 65), SUM("ResolutionWidth" + 66), SUM("ResolutionWidth" + 67), SUM("ResolutionWidth" + 68), SUM("ResolutionWidth" + 69), SUM("ResolutionWidth" + 70), SUM("ResolutionWidth" + 71), SUM("ResolutionWidth" + 72), SUM("ResolutionWidth" + 73), SUM("ResolutionWidth" + 74), SUM("ResolutionWidth" + 75), SUM("ResolutionWidth" + 76), SUM("ResolutionWidth" + 77), SUM("ResolutionWidth" + 78), SUM("ResolutionWidth" + 79), SUM("ResolutionWidth" + 80), SUM("ResolutionWidth" + 81), SUM("ResolutionWidth" + 82), SUM("ResolutionWidth" + 83), SUM("ResolutionWidth" + 84), SUM("ResolutionWidth" + 85), SUM("ResolutionWidth" + 86), SUM("ResolutionWidth" + 87), SUM("ResolutionWidth" + 88), SUM("ResolutionWidth" + 89) FROM hits;

datafusion/results/partitioned.json

@@ -1,58 +1,55 @@
 {
     "system": "DataFusion (Parquet, partitioned)",
-    "date": "2024-02-08",
+    "date": "2024-03-29",
     "machine": "c6a.4xlarge, 500gb gp2",
     "cluster_size": 1,
     "comment": "v45.0.0 (26058ac)",
-
     "tags": ["Rust", "column-oriented", "embedded", "stateless"],
-
     "load_time": 0,
     "data_size": 14779976446,
-
     "result": [
-[0.059, 0.020, 0.021],
-[0.103, 0.034, 0.032],
-[0.188, 0.081, 0.077],
-[0.387, 0.089, 0.081],
-[0.976, 0.790, 0.792],
-[0.982, 0.793, 0.801],
-[0.093, 0.031, 0.031],
-[0.118, 0.037, 0.038],
-[0.997, 0.869, 0.861],
-[1.313, 0.987, 0.985],
-[0.530, 0.241, 0.250],
-[0.607, 0.273, 0.273],
-[1.047, 0.849, 0.869],
-[2.534, 1.343, 1.203],
-[1.095, 0.816, 0.792],
-[1.038, 0.952, 0.942],
-[2.586, 1.690, 1.710],
-[2.500, 1.585, 1.585],
-[5.162, 3.475, 3.434],
-[0.288, 0.074, 0.073],
-[9.896, 1.061, 1.038],
-[11.254, 1.246, 1.283],
-[21.845, 2.537, 2.541],
-[55.438, 9.532, 9.583],
-[2.700, 0.436, 0.451],
-[0.811, 0.367, 0.355],
-[2.702, 0.519, 0.501],
-[9.636, 1.464, 1.437],
-[9.892, 9.399, 9.500],
-[0.521, 0.435, 0.436],
-[2.390, 0.751, 0.751],
-[5.944, 0.891, 0.890],
-[4.703, 3.474, 3.364],
-[10.206, 3.615, 3.636],
-[10.171, 3.663, 3.631],
-[1.289, 1.150, 1.158],
-[0.394, 0.188, 0.185],
-[0.215, 0.081, 0.080],
-[0.289, 0.109, 0.115],
-[0.633, 0.346, 0.344],
-[0.170, 0.044, 0.045],
-[0.159, 0.038, 0.042],
-[0.158, 0.052, 0.051]
+[0.062, 0.019, 0.021],
+[0.117, 0.036, 0.035],
+[0.206, 0.084, 0.081],
+[0.385, 0.087, 0.086],
+[1.077, 0.873, 0.843],
+[1.014, 0.860, 0.858],
+[0.102, 0.036, 0.033],
+[0.125, 0.037, 0.038],
+[1.116, 0.943, 0.962],
+[1.343, 1.068, 1.041],
+[0.509, 0.258, 0.253],
+[0.639, 0.287, 0.302],
+[1.081, 0.891, 0.901],
+[2.708, 1.370, 1.418],
+[1.104, 0.854, 0.864],
+[1.108, 1.021, 1.016],
+[2.679, 1.820, 1.858],
+[2.511, 1.684, 1.696],
+[5.435, 3.718, 3.841],
+[0.260, 0.076, 0.081],
+[9.906, 1.077, 1.101],
+[11.275, 1.294, 1.288],
+[21.902, 2.510, 2.573],
+[55.539, 9.451, 9.515],
+[2.685, 0.453, 0.445],
+[0.798, 0.358, 0.358],
+[2.709, 0.514, 0.504],
+[9.663, 1.479, 1.502],
+[10.040, 9.552, 9.835],
+[0.524, 0.423, 0.413],
+[2.376, 0.796, 0.805],
+[5.963, 0.945, 0.911],
+[4.713, 3.666, 3.668],
+[10.233, 3.811, 3.796],
+[10.265, 3.756, 3.773],
+[1.378, 1.277, 1.249],
+[0.406, 0.203, 0.203],
+[0.209, 0.098, 0.082],
+[0.309, 0.117, 0.121],
+[0.642, 0.384, 0.369],
+[0.181, 0.052, 0.051],
+[0.167, 0.046, 0.045],
+[0.178, 0.055, 0.054]
 ]
 }

datafusion/results/single.json

@@ -1,58 +1,55 @@
 {
     "system": "DataFusion (Parquet, single)",
-    "date": "2024-02-08",
+    "date": "2024-03-29",
     "machine": "c6a.4xlarge, 500gb gp2",
     "cluster_size": 1,
     "comment": "v45.0.0 (26058ac)",
-
     "tags": ["Rust", "column-oriented", "embedded", "stateless"],
-
     "load_time": 0,
     "data_size": 14779976446,
-
     "result": [
-[0.091, 0.059, 0.053],
-[0.145, 0.074, 0.067],
-[0.204, 0.115, 0.109],
-[0.353, 0.112, 0.113],
-[0.951, 0.851, 0.838],
-[1.033, 0.899, 0.901],
-[0.120, 0.066, 0.068],
-[0.141, 0.083, 0.077],
-[1.020, 0.901, 0.901],
-[1.288, 1.018, 1.046],
-[0.461, 0.266, 0.277],
-[0.545, 0.301, 0.308],
-[1.097, 0.931, 0.938],
-[2.596, 1.315, 1.314],
-[1.048, 0.891, 0.877],
-[1.090, 0.973, 0.974],
-[2.591, 1.797, 1.818],
-[2.503, 1.661, 1.668],
-[5.074, 3.473, 3.469],
-[0.270, 0.107, 0.110],
-[9.744, 1.121, 1.111],
-[11.237, 1.445, 1.423],
-[22.074, 3.566, 3.478],
-[55.972, 9.819, 9.872],
-[2.579, 0.567, 0.560],
-[0.814, 0.492, 0.493],
-[2.576, 0.659, 0.632],
-[9.598, 1.572, 1.552],
-[10.668, 10.012, 10.155],
-[0.562, 0.473, 0.465],
-[2.281, 0.860, 0.873],
-[5.695, 0.991, 0.946],
-[4.506, 3.428, 3.497],
-[10.139, 3.779, 3.859],
-[10.091, 3.804, 3.776],
-[1.315, 1.191, 1.235],
-[0.432, 0.234, 0.238],
-[0.275, 0.156, 0.156],
-[0.342, 0.155, 0.157],
-[0.667, 0.423, 0.405],
-[0.202, 0.080, 0.078],
-[0.186, 0.075, 0.076],
-[0.187, 0.099, 0.084]
+[0.106, 0.058, 0.070],
+[0.139, 0.077, 0.085],
+[0.217, 0.117, 0.127],
+[0.340, 0.121, 0.123],
+[1.029, 0.906, 0.900],
+[1.089, 0.950, 0.957],
+[0.123, 0.068, 0.077],
+[0.148, 0.085, 0.083],
+[1.134, 1.005, 0.977],
+[1.314, 1.095, 1.096],
+[0.484, 0.293, 0.290],
+[0.574, 0.313, 0.310],
+[1.141, 0.991, 0.971],
+[2.609, 1.554, 1.532],
+[1.086, 0.922, 0.941],
+[1.197, 1.056, 1.081],
+[2.676, 1.935, 1.930],
+[2.552, 1.805, 1.800],
+[5.212, 3.746, 3.798],
+[0.243, 0.117, 0.116],
+[9.731, 1.176, 1.139],
+[11.252, 1.439, 1.453],
+[22.124, 3.480, 3.546],
+[55.992, 9.964, 9.912],
+[2.588, 0.587, 0.563],
+[0.808, 0.507, 0.511],
+[2.584, 0.646, 0.640],
+[9.573, 1.607, 1.621],
+[10.865, 10.256, 10.331],
+[0.559, 0.454, 0.462],
+[2.281, 0.920, 0.936],
+[5.692, 1.004, 1.044],
+[4.539, 3.731, 3.757],
+[10.240, 3.861, 3.946],
+[10.201, 3.906, 3.870],
+[1.412, 1.288, 1.281],
+[0.421, 0.255, 0.243],
+[0.292, 0.154, 0.156],
+[0.360, 0.169, 0.189],
+[0.712, 0.413, 0.413],
+[0.211, 0.082, 0.087],
+[0.198, 0.091, 0.078],
+[0.199, 0.094, 0.089]
 ]
 }