Rest of TPCH

bench-vortex/benches/tpch_benchmark.rs

@@ -1,5 +1,4 @@
 use bench_vortex::tpch::dbgen::{DBGen, DBGenOptions};
-use bench_vortex::tpch::query::Q1;
 use bench_vortex::tpch::{load_datasets, Format};
 use criterion::{criterion_group, criterion_main, Criterion};
 use tokio::runtime::Builder;
@@ -10,50 +9,76 @@ fn benchmark(c: &mut Criterion) {
     // Run TPC-H data gen.
     let data_dir = DBGen::new(DBGenOptions::default()).generate().unwrap();
 
-    let mut group = c.benchmark_group("tpch q1");
-    group.sample_size(10);
-
-    let ctx = runtime
+    let vortex_no_pushdown_ctx = runtime
         .block_on(load_datasets(
             &data_dir,
             Format::Vortex {
                 disable_pushdown: false,
             },
         ))
         .unwrap();
-    group.bench_function("vortex-pushdown", |b| {
-        b.to_async(&runtime)
-            .iter(|| async { ctx.sql(Q1).await.unwrap().collect().await.unwrap() })
-    });
-
-    let ctx = runtime
+    let vortex_ctx = runtime
         .block_on(load_datasets(
             &data_dir,
             Format::Vortex {
                 disable_pushdown: true,
             },
         ))
         .unwrap();
-    group.bench_function("vortex-nopushdown", |b| {
-        b.to_async(&runtime)
-            .iter(|| async { ctx.sql(Q1).await.unwrap().collect().await.unwrap() })
-    });
-
-    let ctx = runtime
+    let csv_ctx = runtime
         .block_on(load_datasets(&data_dir, Format::Csv))
         .unwrap();
-    group.bench_function("csv", |b| {
-        b.to_async(&runtime)
-            .iter(|| async { ctx.sql(Q1).await.unwrap().collect().await.unwrap() })
-    });
-
-    let ctx = runtime
+    let arrow_ctx = runtime
         .block_on(load_datasets(&data_dir, Format::Arrow))
         .unwrap();
-    group.bench_function("arrow", |b| {
-        b.to_async(&runtime)
-            .iter(|| async { ctx.sql(Q1).await.unwrap().collect().await.unwrap() })
-    });
+
+    for q in 1..=22 {
+        let query = bench_vortex::tpch::tpch_query(q);
+
+        let mut group = c.benchmark_group(format!("tpch_q{q}"));
+        group.sample_size(10);
+
+        group.bench_function("vortex-pushdown", |b| {
+            b.to_async(&runtime).iter(|| async {
+                vortex_ctx
+                    .sql(&query)
+                    .await
+                    .unwrap()
+                    .collect()
+                    .await
+                    .unwrap()
+            })
+        });
+
+        group.bench_function("vortex-nopushdown", |b| {
+            b.to_async(&runtime).iter(|| async {
+                vortex_no_pushdown_ctx
+                    .sql(&query)
+                    .await
+                    .unwrap()
+                    .collect()
+                    .await
+                    .unwrap()
+            })
+        });
+
+        group.bench_function("csv", |b| {
+            b.to_async(&runtime)
+                .iter(|| async { csv_ctx.sql(&query).await.unwrap().collect().await.unwrap() })
+        });
+
+        group.bench_function("arrow", |b| {
+            b.to_async(&runtime).iter(|| async {
+                arrow_ctx
+                    .sql(&query)
+                    .await
+                    .unwrap()
+                    .collect()
+                    .await
+                    .unwrap()
+            })
+        });
+    }
 }
 
 criterion_group!(benches, benchmark);

bench-vortex/src/bin/tpch_benchmark.rs

@@ -2,17 +2,17 @@
 use std::path::PathBuf;
 use std::time::SystemTime;
 
-use bench_vortex::tpch;
 use bench_vortex::tpch::dbgen::{DBGen, DBGenOptions};
-use bench_vortex::tpch::{load_datasets, Format};
+use bench_vortex::tpch::{load_datasets, tpch_query, Format};
 
 async fn q1_csv(base_dir: &PathBuf) -> anyhow::Result<()> {
     let ctx = load_datasets(base_dir, Format::Csv).await?;
+    let q1 = tpch_query(1);
 
     println!("BEGIN: Q1(CSV)");
 
     let start = SystemTime::now();
-    ctx.sql(tpch::query::Q1).await?.show().await?;
+    ctx.sql(&q1).await?.show().await?;
     let elapsed = start.elapsed()?.as_millis();
     println!("END CSV: {elapsed}ms");
 
@@ -21,11 +21,12 @@ async fn q1_csv(base_dir: &PathBuf) -> anyhow::Result<()> {
 
 async fn q1_arrow(base_dir: &PathBuf) -> anyhow::Result<()> {
     let ctx = load_datasets(base_dir, Format::Arrow).await?;
+    let q1 = tpch_query(1);
 
     println!("BEGIN: Q1(ARROW)");
     let start = SystemTime::now();
 
-    ctx.sql(tpch::query::Q1).await?.show().await?;
+    ctx.sql(&q1).await?.show().await?;
     let elapsed = start.elapsed()?.as_millis();
 
     println!("END ARROW: {elapsed}ms");
@@ -41,11 +42,12 @@ async fn q1_vortex(base_dir: &PathBuf) -> anyhow::Result<()> {
         },
     )
     .await?;
+    let q1 = tpch_query(1);
 
     println!("BEGIN: Q1(VORTEX)");
     let start = SystemTime::now();
 
-    ctx.sql(tpch::query::Q1).await?.show().await?;
+    ctx.sql(&q1).await?.show().await?;
 
     let elapsed = start.elapsed()?.as_millis();
     println!("END VORTEX: {elapsed}ms");

bench-vortex/src/tpch/mod.rs

@@ -1,3 +1,4 @@
+use std::fs;
 use std::path::Path;
 use std::sync::Arc;
 
@@ -11,7 +12,6 @@ use vortex::{Array, ArrayDType, ArrayData, IntoArray};
 use vortex_datafusion::{SessionContextExt, VortexMemTableOptions};
 
 pub mod dbgen;
-pub mod query;
 pub mod schema;
 
 pub enum Format {
@@ -156,3 +156,10 @@ async fn register_vortex(
 
     Ok(())
 }
+
+pub fn tpch_query(query_idx: usize) -> String {
+    let manifest_dir = Path::new(env!("CARGO_MANIFEST_DIR"))
+        .join("tpch")
+        .join(format!("q{}.sql", query_idx));
+    fs::read_to_string(manifest_dir).unwrap()
+}

bench-vortex/tpch/q1.sql

@@ -0,0 +1,21 @@
+select
+    l_returnflag,
+    l_linestatus,
+    sum(l_quantity) as sum_qty,
+    sum(l_extendedprice) as sum_base_price,
+    sum(l_extendedprice * (1 - l_discount)) as sum_disc_price,
+    sum(l_extendedprice * (1 - l_discount) * (1 + l_tax)) as sum_charge,
+    avg(l_quantity) as avg_qty,
+    avg(l_extendedprice) as avg_price,
+    avg(l_discount) as avg_disc,
+    count(*) as count_order
+from
+    lineitem
+where
+        l_shipdate <= date '1998-09-02'
+group by
+    l_returnflag,
+    l_linestatus
+order by
+    l_returnflag,
+    l_linestatus;

bench-vortex/tpch/q10.sql

@@ -0,0 +1,31 @@
+select
+    c_custkey,
+    c_name,
+    sum(l_extendedprice * (1 - l_discount)) as revenue,
+    c_acctbal,
+    n_name,
+    c_address,
+    c_phone,
+    c_comment
+from
+    customer,
+    orders,
+    lineitem,
+    nation
+where
+        c_custkey = o_custkey
+  and l_orderkey = o_orderkey
+  and o_orderdate >= date '1993-10-01'
+  and o_orderdate < date '1994-01-01'
+  and l_returnflag = 'R'
+  and c_nationkey = n_nationkey
+group by
+    c_custkey,
+    c_name,
+    c_acctbal,
+    c_phone,
+    n_name,
+    c_address,
+    c_comment
+order by
+    revenue desc;

bench-vortex/tpch/q11.sql

@@ -0,0 +1,27 @@
+select
+    ps_partkey,
+    sum(ps_supplycost * ps_availqty) as value
+from
+    partsupp,
+    supplier,
+    nation
+where
+    ps_suppkey = s_suppkey
+  and s_nationkey = n_nationkey
+  and n_name = 'GERMANY'
+group by
+    ps_partkey having
+    sum(ps_supplycost * ps_availqty) > (
+    select
+    sum(ps_supplycost * ps_availqty) * 0.0001
+    from
+    partsupp,
+    supplier,
+    nation
+    where
+    ps_suppkey = s_suppkey
+                  and s_nationkey = n_nationkey
+                  and n_name = 'GERMANY'
+    )
+order by
+    value desc;

bench-vortex/tpch/q12.sql

@@ -0,0 +1,30 @@
+select
+    l_shipmode,
+    sum(case
+            when o_orderpriority = '1-URGENT'
+                or o_orderpriority = '2-HIGH'
+                then 1
+            else 0
+        end) as high_line_count,
+    sum(case
+            when o_orderpriority <> '1-URGENT'
+                and o_orderpriority <> '2-HIGH'
+                then 1
+            else 0
+        end) as low_line_count
+from
+    lineitem
+        join
+    orders
+    on
+            l_orderkey = o_orderkey
+where
+        l_shipmode in ('MAIL', 'SHIP')
+  and l_commitdate < l_receiptdate
+  and l_shipdate < l_commitdate
+  and l_receiptdate >= date '1994-01-01'
+  and l_receiptdate < date '1995-01-01'
+group by
+    l_shipmode
+order by
+    l_shipmode;

bench-vortex/tpch/q13.sql

@@ -0,0 +1,20 @@
+select
+    c_count,
+    count(*) as custdist
+from
+    (
+        select
+            c_custkey,
+            count(o_orderkey)
+        from
+            customer left outer join orders on
+                        c_custkey = o_custkey
+                    and o_comment not like '%special%requests%'
+        group by
+            c_custkey
+    ) as c_orders (c_custkey, c_count)
+group by
+    c_count
+order by
+    custdist desc,
+    c_count desc;

bench-vortex/tpch/q14.sql

@@ -0,0 +1,13 @@
+select
+            100.00 * sum(case
+                             when p_type like 'PROMO%'
+                                 then l_extendedprice * (1 - l_discount)
+                             else 0
+            end) / sum(l_extendedprice * (1 - l_discount)) as promo_revenue
+from
+    lineitem,
+    part
+where
+        l_partkey = p_partkey
+  and l_shipdate >= date '1995-09-01'
+  and l_shipdate < date '1995-10-01';

bench-vortex/tpch/q15.sql

@@ -0,0 +1,34 @@
+create view revenue0 (supplier_no, total_revenue) as
+	select
+		l_suppkey,
+		sum(l_extendedprice * (1 - l_discount))
+	from
+		lineitem
+	where
+		l_shipdate >= date '1996-01-01'
+		and l_shipdate < date '1996-01-01' + interval '3' month
+	group by
+		l_suppkey;
+
+
+select
+	s_suppkey,
+	s_name,
+	s_address,
+	s_phone,
+	total_revenue
+from
+	supplier,
+	revenue0
+where
+	s_suppkey = supplier_no
+	and total_revenue = (
+		select
+			max(total_revenue)
+		from
+			revenue0
+	)
+order by
+	s_suppkey;
+
+drop view revenue0;