Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Run micro-benchmark on GCP #464

Merged
merged 4 commits into from
Nov 7, 2024
Merged

Run micro-benchmark on GCP #464

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0238691
change data parh
YanxuanLiu Nov 5, 2024
cbb3173
change data path
YanxuanLiu Nov 5, 2024
db50e4a
save result to file
YanxuanLiu Nov 6, 2024
f040041
change format of output
YanxuanLiu Nov 6, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 12 additions & 10 deletions examples/SQL+DF-Examples/micro-benchmarks/notebooks/micro-benchmarks-gpu.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,9 @@
" total_time += round(end - start, 2)\n",
" count = count + 1\n",
" print(\"Retry times : {}, \".format(count) + appName + \" microbenchmark takes {} seconds\".format(round(end - start, 2)))\n",
" print(appName + \" microbenchmark takes average {} seconds after {} retries\".format(round(total_time/retryTimes),retryTimes))"
" print(appName + \" microbenchmark takes average {} seconds after {} retries\".format(round(total_time/retryTimes),retryTimes))\n",
" with open('result.txt', 'a') as file:\n",
" file.write(\"{},{},{}\\n\".format(appName, round(total_time/retryTimes), retryTimes))"
]
},
{
Expand Down Expand Up @@ -111,12 +113,12 @@
"# Load dataframe and create tempView\n",
"# You need to update data path to your real path!\n",
"dataRoot = os.getenv(\"DATA_ROOT\", \"/data\")\n",
"spark.read.parquet(dataRoot + \"/tpcds/customer\").createOrReplaceTempView(\"customer\")\n",
"spark.read.parquet(dataRoot + \"/tpcds/store_sales\").createOrReplaceTempView(\"store_sales\")\n",
"spark.read.parquet(dataRoot + \"/tpcds/catalog_sales\").createOrReplaceTempView(\"catalog_sales\")\n",
"spark.read.parquet(dataRoot + \"/tpcds/web_sales\").createOrReplaceTempView(\"web_sales\")\n",
"spark.read.parquet(dataRoot + \"/tpcds/item\").createOrReplaceTempView(\"item\")\n",
"spark.read.parquet(dataRoot + \"/tpcds/date_dim\").createOrReplaceTempView(\"date_dim\")\n",
"spark.read.parquet(dataRoot + \"/customer.dat\").createOrReplaceTempView(\"customer\")\n",
"spark.read.parquet(dataRoot + \"/store_sales.dat\").createOrReplaceTempView(\"store_sales\")\n",
"spark.read.parquet(dataRoot + \"/catalog_sales.dat\").createOrReplaceTempView(\"catalog_sales\")\n",
"spark.read.parquet(dataRoot + \"/web_sales.dat\").createOrReplaceTempView(\"web_sales\")\n",
"spark.read.parquet(dataRoot + \"/item.dat\").createOrReplaceTempView(\"item\")\n",
"spark.read.parquet(dataRoot + \"/date_dim.dat\").createOrReplaceTempView(\"date_dim\")\n",
"print(\"-\"*50)"
]
},
Expand Down Expand Up @@ -497,7 +499,7 @@
],
"source": [
"start = time() \n",
"spark.read.parquet(dataRoot + \"/tpcds/customer\").limit(1000000).write.format(\"parquet\").mode(\"overwrite\").save(\"/data/tmp/customer1m\")\n",
"spark.read.parquet(dataRoot + \"/customer.dat\").limit(1000000).write.format(\"parquet\").mode(\"overwrite\").save(\"/data/tmp/customer1m\")\n",
"end = time()\n",
"# Parquet file scanning and writing will be about 3 times faster running on GPU\n",
"print(\"scanning and writing parquet cost : {} seconds\".format(round(end - start, 2)))\n",
Expand Down Expand Up @@ -557,8 +559,8 @@
"metadata": {},
"outputs": [],
"source": [
"spark.read.parquet(dataRoot + \"/tpcds/store_sales\").createOrReplaceTempView(\"store_sales\")\n",
"spark.read.parquet(dataRoot + \"/tpcds/store_returns\").createOrReplaceTempView(\"store_returns\")\n",
"spark.read.parquet(dataRoot + \"/store_sales.dat\").createOrReplaceTempView(\"store_sales\")\n",
"spark.read.parquet(dataRoot + \"/store_returns.dat\").createOrReplaceTempView(\"store_returns\")\n",
"\n",
"print(\"-\"*50)\n",
"query = '''\n",
Expand Down