apache · Omega359 · May 29, 2026
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q01.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q01.benchmark
@@ -0,0 +1,20 @@
+subgroup groupby
+
+name Q01
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} groupby ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_groupby_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT id1, SUM(v1) AS v1
+FROM x
+GROUP BY id1;
+
+result sql_benchmarks/h2o/results/groupby/${H2O_BENCH_SIZE:-small}/q01.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q02.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q02.benchmark
@@ -0,0 +1,20 @@
+subgroup groupby
+
+name Q02
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} groupby ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_groupby_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT id1, id2, SUM(v1) AS v1
+FROM x
+GROUP BY id1, id2;
+
+result sql_benchmarks/h2o/results/groupby/${H2O_BENCH_SIZE:-small}/q02.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q03.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q03.benchmark
@@ -0,0 +1,20 @@
+subgroup groupby
+
+name Q03
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} groupby ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_groupby_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT id3, SUM(v1) AS v1, AVG(v3) AS v3
+FROM x
+GROUP BY id3;
+
+result sql_benchmarks/h2o/results/groupby/${H2O_BENCH_SIZE:-small}/q03.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q04.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q04.benchmark
@@ -0,0 +1,20 @@
+subgroup groupby
+
+name Q04
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} groupby ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_groupby_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT id4, AVG(v1) AS v1, AVG(v2) AS v2, AVG(v3) AS v3
+FROM x
+GROUP BY id4;
+
+result sql_benchmarks/h2o/results/groupby/${H2O_BENCH_SIZE:-small}/q04.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q05.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q05.benchmark
@@ -0,0 +1,20 @@
+subgroup groupby
+
+name Q05
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} groupby ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_groupby_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT id6, SUM(v1) AS v1, SUM(v2) AS v2, SUM(v3) AS v3
+FROM x
+GROUP BY id6;
+
+result sql_benchmarks/h2o/results/groupby/${H2O_BENCH_SIZE:-small}/q05.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q06.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q06.benchmark
@@ -0,0 +1,20 @@
+subgroup groupby
+
+name Q06
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} groupby ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_groupby_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT id4, id5, MEDIAN(v3) AS median_v3, STDDEV(v3) AS sd_v3
+FROM x
+GROUP BY id4, id5;
+
+result sql_benchmarks/h2o/results/groupby/${H2O_BENCH_SIZE:-small}/q06.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q07.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q07.benchmark
@@ -0,0 +1,20 @@
+subgroup groupby
+
+name Q07
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} groupby ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_groupby_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT id3, MAX(v1) - MIN(v2) AS range_v1_v2
+FROM x
+GROUP BY id3;
+
+result sql_benchmarks/h2o/results/groupby/${H2O_BENCH_SIZE:-small}/q07.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q08.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q08.benchmark
@@ -0,0 +1,22 @@
+subgroup groupby
+
+name Q08
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} groupby ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_groupby_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT id6, largest2_v3 FROM 
+   (
+        SELECT id6, v3 AS largest2_v3, ROW_NUMBER() OVER (PARTITION BY id6 ORDER BY v3 DESC) AS order_v3 
+        FROM x WHERE v3 IS NOT NULL
+   ) sub_query WHERE order_v3 <= 2;
+
+result sql_benchmarks/h2o/results/groupby/${H2O_BENCH_SIZE:-small}/q08.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q09.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q09.benchmark
@@ -0,0 +1,20 @@
+subgroup groupby
+
+name Q09
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} groupby ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_groupby_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT id2, id4, POWER(CORR(v1, v2), 2) AS r2
+FROM x
+GROUP BY id2, id4;
+
+result sql_benchmarks/h2o/results/groupby/${H2O_BENCH_SIZE:-small}/q09.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q10.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/groupby/q10.benchmark
@@ -0,0 +1,18 @@
+subgroup groupby
+
+name Q10
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} groupby ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_groupby_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT id1, id2, id3, id4, id5, id6, SUM(v3) AS v3, COUNT(*) AS count FROM x GROUP BY id1, id2, id3, id4, id5, id6;
+
+result sql_benchmarks/h2o/results/groupby/${H2O_BENCH_SIZE:-small}/q10.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/join/q01.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/join/q01.benchmark
@@ -0,0 +1,28 @@
+subgroup join
+
+name Q01
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} join ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_join_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT x.id1,
+       x.id2,
+       x.id3,
+       x.id4     as xid4,
+       small.id4 as smallid4,
+       x.id5,
+       x.id6,
+       x.v1,
+       small.v2
+FROM x
+INNER JOIN small ON x.id1 = small.id1;
+
+result sql_benchmarks/h2o/results/join/${H2O_BENCH_SIZE:-small}/q01.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/join/q02.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/join/q02.benchmark
@@ -0,0 +1,30 @@
+subgroup join
+
+name Q02
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} join ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_join_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT x.id1      as xid1,
+       medium.id1 as mediumid1,
+       x.id2,
+       x.id3,
+       x.id4      as xid4,
+       medium.id4 as mediumid4,
+       x.id5      as xid5,
+       medium.id5 as mediumid5,
+       x.id6,
+       x.v1,
+       medium.v2
+FROM x
+INNER JOIN medium ON x.id2 = medium.id2;
+
+result sql_benchmarks/h2o/results/join/${H2O_BENCH_SIZE:-small}/q02.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/join/q03.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/join/q03.benchmark
@@ -0,0 +1,30 @@
+subgroup join
+
+name Q03
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} join ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_join_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT x.id1      as xid1,
+       medium.id1 as mediumid1,
+       x.id2,
+       x.id3,
+       x.id4      as xid4,
+       medium.id4 as mediumid4,
+       x.id5      as xid5,
+       medium.id5 as mediumid5,
+       x.id6,
+       x.v1,
+       medium.v2
+FROM x
+LEFT JOIN medium ON x.id2 = medium.id2;
+
+result sql_benchmarks/h2o/results/join/${H2O_BENCH_SIZE:-small}/q03.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/join/q04.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/join/q04.benchmark
@@ -0,0 +1,30 @@
+subgroup join
+
+name Q04
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} join ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_join_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT x.id1      as xid1,
+       medium.id1 as mediumid1,
+       x.id2,
+       x.id3,
+       x.id4      as xid4,
+       medium.id4 as mediumid4,
+       x.id5      as xid5,
+       medium.id5 as mediumid5,
+       x.id6,
+       x.v1,
+       medium.v2
+FROM x
+JOIN medium ON x.id5 = medium.id5;
+
+result sql_benchmarks/h2o/results/join/${H2O_BENCH_SIZE:-small}/q04.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/join/q05.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/join/q05.benchmark
@@ -0,0 +1,32 @@
+subgroup join
+
+name Q05
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} join ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_join_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+SELECT x.id1     as xid1,
+       large.id1 as largeid1,
+       x.id2     as xid2,
+       large.id2 as largeid2,
+       x.id3,
+       x.id4     as xid4,
+       large.id4 as largeid4,
+       x.id5     as xid5,
+       large.id5 as largeid5,
+       x.id6     as xid6,
+       large.id6 as largeid6,
+       x.v1,
+       large.v2
+FROM x
+JOIN large ON x.id3 = large.id3;
+
+result sql_benchmarks/h2o/results/join/${H2O_BENCH_SIZE:-small}/q05.csv
diff --git a/benchmarks/sql_benchmarks/h2o/benchmarks/window/q01.benchmark b/benchmarks/sql_benchmarks/h2o/benchmarks/window/q01.benchmark
@@ -0,0 +1,25 @@
+subgroup window
+
+name Q01
+group h2o
+
+echo Loading ${H2O_BENCH_SIZE:-small} window ${H2O_FILE_TYPE:-csv} h2o data
+
+load sql_benchmarks/h2o/init/load_window_${H2O_BENCH_SIZE:-small}_${H2O_FILE_TYPE:-csv}.sql
+
+assert I
+SELECT COUNT(*) > 0 FROM x
+----
+true
+
+run
+-- Basic Window
+SELECT
+    id1,
+    id2,
+    id3,
+    v2,
+    sum(v2) OVER () AS window_basic
+FROM x;
+
+result sql_benchmarks/h2o/results/window/${H2O_BENCH_SIZE:-small}/q01.csv