[WIP]chore: Add TPCDS benchmarks

benchmarks/bench.sh

@@ -87,6 +87,9 @@ tpch10:                 TPCH inspired benchmark on Scale Factor (SF) 10 (~10GB),
 tpch_csv10:             TPCH inspired benchmark on Scale Factor (SF) 10 (~10GB), single csv file per table, hash join
 tpch_mem10:             TPCH inspired benchmark on Scale Factor (SF) 10 (~10GB), query from memory
 
+# TPC-DS Benchmarks
+tpcds:                  TPCDS inspired benchmark on Scale Factor (SF) 1 (~1GB), single parquet file per table, hash join
+
 # Extended TPC-H Benchmarks
 sort_tpch:              Benchmark of sorting speed for end-to-end sort queries on TPC-H dataset (SF=1)
 sort_tpch10:            Benchmark of sorting speed for end-to-end sort queries on TPC-H dataset (SF=10)
@@ -216,6 +219,9 @@ main() {
                     # same data as for tpch10
                     data_tpch "10"
                     ;;
+                tpcds)
+                    data_tpcds
+                    ;;
                 clickbench_1)
                     data_clickbench_1
                     ;;
@@ -384,6 +390,7 @@ main() {
                     run_external_aggr
                     run_nlj
                     run_hj
+                    run_tpcds
                     ;;
                 tpch)
                     run_tpch "1" "parquet"
@@ -403,6 +410,9 @@ main() {
                 tpch_mem10)
                     run_tpch_mem "10"
                     ;;
+                tpcds)
+                    run_tpcds
+                    ;;
                 cancellation)
                     run_cancellation
                     ;;
@@ -589,6 +599,14 @@ data_tpch() {
     fi
 }
 
+# Points to TPCDS data generation instructions
+data_tpcds() {
+    echo ""
+    echo "For TPC-DS data generation, please clone the datafusion-benchmarks repository:"
+    echo "  git clone https://github.com/apache/datafusion-benchmarks"
+    echo ""
+}
+
 # Runs the tpch benchmark
 run_tpch() {
     SCALE_FACTOR=$1
@@ -622,6 +640,27 @@ run_tpch_mem() {
     debug_run $CARGO_COMMAND --bin tpch -- benchmark datafusion --iterations 5 --path "${TPCH_DIR}" --prefer_hash_join "${PREFER_HASH_JOIN}" -m --format parquet -o "${RESULTS_FILE}" ${QUERY_ARG}
 }
 
+# Runs the tpcds benchmark
+run_tpcds() {
+    TPCDS_DIR="${DATA_DIR}"
+
+    # Check if TPCDS data directory exists
+    if [ ! -d "${TPCDS_DIR}" ]; then
+        echo "Error: TPC-DS data directory does not exist: ${TPCDS_DIR}"
+        echo ""
+        echo "Please prepare TPC-DS data first by running:"
+        echo "  ./bench.sh data tpcds"
+        echo ""
+        return 1
+    fi
+
+    RESULTS_FILE="${RESULTS_DIR}/tpcds_sf1.json"
+    echo "RESULTS_FILE: ${RESULTS_FILE}"
+    echo "Running tpcds benchmark..."
+
+    debug_run $CARGO_COMMAND --bin tpcds -- benchmark datafusion --iterations 5 --path "${TPCDS_DIR}" --query_path "${SCRIPT_DIR}/queries/tpcds" --prefer_hash_join "${PREFER_HASH_JOIN}" --format parquet -o "${RESULTS_FILE}" ${QUERY_ARG}
+}
+
 # Runs the compile profile benchmark helper
 run_compile_profile() {
     local profiles=("$@")

benchmarks/queries/tpcds/q1.sql

@@ -0,0 +1,26 @@
+-- SQLBench-DS query 1 derived from TPC-DS query 1 under the terms of the TPC Fair Use Policy.
+-- TPC-DS queries are Copyright 2021 Transaction Processing Performance Council.
+-- This query was generated at scale factor 1.
+with customer_total_return as
+(select sr_customer_sk as ctr_customer_sk
+,sr_store_sk as ctr_store_sk
+,sum(SR_RETURN_AMT_INC_TAX) as ctr_total_return
+from store_returns
+,date_dim
+where sr_returned_date_sk = d_date_sk
+and d_year =1999
+group by sr_customer_sk
+,sr_store_sk)
+ select  c_customer_id
+from customer_total_return ctr1
+,store
+,customer
+where ctr1.ctr_total_return > (select avg(ctr_total_return)*1.2
+from customer_total_return ctr2
+where ctr1.ctr_store_sk = ctr2.ctr_store_sk)
+and s_store_sk = ctr1.ctr_store_sk
+and s_state = 'TN'
+and ctr1.ctr_customer_sk = c_customer_sk
+order by c_customer_id
+ LIMIT 100;
+

benchmarks/queries/tpcds/q10.sql

@@ -0,0 +1,60 @@
+-- SQLBench-DS query 10 derived from TPC-DS query 10 under the terms of the TPC Fair Use Policy.
+-- TPC-DS queries are Copyright 2021 Transaction Processing Performance Council.
+-- This query was generated at scale factor 1.
+select  
+  cd_gender,
+  cd_marital_status,
+  cd_education_status,
+  count(*) cnt1,
+  cd_purchase_estimate,
+  count(*) cnt2,
+  cd_credit_rating,
+  count(*) cnt3,
+  cd_dep_count,
+  count(*) cnt4,
+  cd_dep_employed_count,
+  count(*) cnt5,
+  cd_dep_college_count,
+  count(*) cnt6
+ from
+  customer c,customer_address ca,customer_demographics
+ where
+  c.c_current_addr_sk = ca.ca_address_sk and
+  ca_county in ('Clinton County','Platte County','Franklin County','Louisa County','Harmon County') and
+  cd_demo_sk = c.c_current_cdemo_sk and 
+  exists (select *
+          from store_sales,date_dim
+          where c.c_customer_sk = ss_customer_sk and
+                ss_sold_date_sk = d_date_sk and
+                d_year = 2002 and
+                d_moy between 3 and 3+3) and
+   (exists (select *
+            from web_sales,date_dim
+            where c.c_customer_sk = ws_bill_customer_sk and
+                  ws_sold_date_sk = d_date_sk and
+                  d_year = 2002 and
+                  d_moy between 3 ANd 3+3) or 
+    exists (select * 
+            from catalog_sales,date_dim
+            where c.c_customer_sk = cs_ship_customer_sk and
+                  cs_sold_date_sk = d_date_sk and
+                  d_year = 2002 and
+                  d_moy between 3 and 3+3))
+ group by cd_gender,
+          cd_marital_status,
+          cd_education_status,
+          cd_purchase_estimate,
+          cd_credit_rating,
+          cd_dep_count,
+          cd_dep_employed_count,
+          cd_dep_college_count
+ order by cd_gender,
+          cd_marital_status,
+          cd_education_status,
+          cd_purchase_estimate,
+          cd_credit_rating,
+          cd_dep_count,
+          cd_dep_employed_count,
+          cd_dep_college_count
+ LIMIT 100;
+

benchmarks/queries/tpcds/q11.sql

@@ -0,0 +1,82 @@
+-- SQLBench-DS query 11 derived from TPC-DS query 11 under the terms of the TPC Fair Use Policy.
+-- TPC-DS queries are Copyright 2021 Transaction Processing Performance Council.
+-- This query was generated at scale factor 1.
+with year_total as (
+ select c_customer_id customer_id
+       ,c_first_name customer_first_name
+       ,c_last_name customer_last_name
+       ,c_preferred_cust_flag customer_preferred_cust_flag
+       ,c_birth_country customer_birth_country
+       ,c_login customer_login
+       ,c_email_address customer_email_address
+       ,d_year dyear
+       ,sum(ss_ext_list_price-ss_ext_discount_amt) year_total
+       ,'s' sale_type
+ from customer
+     ,store_sales
+     ,date_dim
+ where c_customer_sk = ss_customer_sk
+   and ss_sold_date_sk = d_date_sk
+ group by c_customer_id
+         ,c_first_name
+         ,c_last_name
+         ,c_preferred_cust_flag 
+         ,c_birth_country
+         ,c_login
+         ,c_email_address
+         ,d_year 
+ union all
+ select c_customer_id customer_id
+       ,c_first_name customer_first_name
+       ,c_last_name customer_last_name
+       ,c_preferred_cust_flag customer_preferred_cust_flag
+       ,c_birth_country customer_birth_country
+       ,c_login customer_login
+       ,c_email_address customer_email_address
+       ,d_year dyear
+       ,sum(ws_ext_list_price-ws_ext_discount_amt) year_total
+       ,'w' sale_type
+ from customer
+     ,web_sales
+     ,date_dim
+ where c_customer_sk = ws_bill_customer_sk
+   and ws_sold_date_sk = d_date_sk
+ group by c_customer_id
+         ,c_first_name
+         ,c_last_name
+         ,c_preferred_cust_flag 
+         ,c_birth_country
+         ,c_login
+         ,c_email_address
+         ,d_year
+         )
+  select  
+                  t_s_secyear.customer_id
+                 ,t_s_secyear.customer_first_name
+                 ,t_s_secyear.customer_last_name
+                 ,t_s_secyear.customer_email_address
+ from year_total t_s_firstyear
+     ,year_total t_s_secyear
+     ,year_total t_w_firstyear
+     ,year_total t_w_secyear
+ where t_s_secyear.customer_id = t_s_firstyear.customer_id
+         and t_s_firstyear.customer_id = t_w_secyear.customer_id
+         and t_s_firstyear.customer_id = t_w_firstyear.customer_id
+         and t_s_firstyear.sale_type = 's'
+         and t_w_firstyear.sale_type = 'w'
+         and t_s_secyear.sale_type = 's'
+         and t_w_secyear.sale_type = 'w'
+         and t_s_firstyear.dyear = 1999
+         and t_s_secyear.dyear = 1999+1
+         and t_w_firstyear.dyear = 1999
+         and t_w_secyear.dyear = 1999+1
+         and t_s_firstyear.year_total > 0
+         and t_w_firstyear.year_total > 0
+         and case when t_w_firstyear.year_total > 0 then t_w_secyear.year_total / t_w_firstyear.year_total else 0.0 end
+             > case when t_s_firstyear.year_total > 0 then t_s_secyear.year_total / t_s_firstyear.year_total else 0.0 end
+ order by t_s_secyear.customer_id
+         ,t_s_secyear.customer_first_name
+         ,t_s_secyear.customer_last_name
+         ,t_s_secyear.customer_email_address
+ LIMIT 100;
+

benchmarks/queries/tpcds/q12.sql

@@ -0,0 +1,35 @@
+-- SQLBench-DS query 12 derived from TPC-DS query 12 under the terms of the TPC Fair Use Policy.
+-- TPC-DS queries are Copyright 2021 Transaction Processing Performance Council.
+-- This query was generated at scale factor 1.
+select  i_item_id
+      ,i_item_desc 
+      ,i_category 
+      ,i_class 
+      ,i_current_price
+      ,sum(ws_ext_sales_price) as itemrevenue 
+      ,sum(ws_ext_sales_price)*100/sum(sum(ws_ext_sales_price)) over
+          (partition by i_class) as revenueratio
+from	
+	web_sales
+    	,item 
+    	,date_dim
+where 
+	ws_item_sk = i_item_sk 
+  	and i_category in ('Jewelry', 'Books', 'Women')
+  	and ws_sold_date_sk = d_date_sk
+	and d_date between cast('2002-03-22' as date) 
+				and (cast('2002-03-22' as date) + 30 days)
+group by 
+	i_item_id
+        ,i_item_desc 
+        ,i_category
+        ,i_class
+        ,i_current_price
+order by 
+	i_category
+        ,i_class
+        ,i_item_id
+        ,i_item_desc
+        ,revenueratio
+ LIMIT 100;
+

benchmarks/queries/tpcds/q13.sql

@@ -0,0 +1,53 @@
+-- SQLBench-DS query 13 derived from TPC-DS query 13 under the terms of the TPC Fair Use Policy.
+-- TPC-DS queries are Copyright 2021 Transaction Processing Performance Council.
+-- This query was generated at scale factor 1.
+select avg(ss_quantity)
+       ,avg(ss_ext_sales_price)
+       ,avg(ss_ext_wholesale_cost)
+       ,sum(ss_ext_wholesale_cost)
+ from store_sales
+     ,store
+     ,customer_demographics
+     ,household_demographics
+     ,customer_address
+     ,date_dim
+ where s_store_sk = ss_store_sk
+ and  ss_sold_date_sk = d_date_sk and d_year = 2001
+ and((ss_hdemo_sk=hd_demo_sk
+  and cd_demo_sk = ss_cdemo_sk
+  and cd_marital_status = 'U'
+  and cd_education_status = '4 yr Degree'
+  and ss_sales_price between 100.00 and 150.00
+  and hd_dep_count = 3   
+     )or
+     (ss_hdemo_sk=hd_demo_sk
+  and cd_demo_sk = ss_cdemo_sk
+  and cd_marital_status = 'S'
+  and cd_education_status = 'Unknown'
+  and ss_sales_price between 50.00 and 100.00   
+  and hd_dep_count = 1
+     ) or 
+     (ss_hdemo_sk=hd_demo_sk
+  and cd_demo_sk = ss_cdemo_sk
+  and cd_marital_status = 'D'
+  and cd_education_status = '2 yr Degree'
+  and ss_sales_price between 150.00 and 200.00 
+  and hd_dep_count = 1  
+     ))
+ and((ss_addr_sk = ca_address_sk
+  and ca_country = 'United States'
+  and ca_state in ('CO', 'MI', 'MN')
+  and ss_net_profit between 100 and 200  
+     ) or
+     (ss_addr_sk = ca_address_sk
+  and ca_country = 'United States'
+  and ca_state in ('NC', 'NY', 'TX')
+  and ss_net_profit between 150 and 300  
+     ) or
+     (ss_addr_sk = ca_address_sk
+  and ca_country = 'United States'
+  and ca_state in ('CA', 'NE', 'TN')
+  and ss_net_profit between 50 and 250  
+     ))
+;
+