From f21979ec3fbfb97ddab8ee465aadf8e98ad33e65 Mon Sep 17 00:00:00 2001 From: Muhammad Haseeb <14217455+mhaseeb123@users.noreply.github.com> Date: Mon, 9 Sep 2024 17:03:37 -0700 Subject: [PATCH] Extend the Parquet writer's dictionary encoding benchmark. (#16591) This PR extends the data cardinality and run length range for the existing parquet writer's encoding benchmark. Authors: - Muhammad Haseeb (https://github.com/mhaseeb123) Approvers: - Vukasin Milovanovic (https://github.com/vuule) - Karthikeyan (https://github.com/karthikeyann) URL: https://github.com/rapidsai/cudf/pull/16591 --- cpp/benchmarks/io/parquet/parquet_writer.cpp | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/cpp/benchmarks/io/parquet/parquet_writer.cpp b/cpp/benchmarks/io/parquet/parquet_writer.cpp index 46d2927a92b..256e50f0e64 100644 --- a/cpp/benchmarks/io/parquet/parquet_writer.cpp +++ b/cpp/benchmarks/io/parquet/parquet_writer.cpp @@ -202,8 +202,8 @@ NVBENCH_BENCH_TYPES(BM_parq_write_encode, NVBENCH_TYPE_AXES(d_type_list)) .set_name("parquet_write_encode") .set_type_axes_names({"data_type"}) .set_min_samples(4) - .add_int64_axis("cardinality", {0, 1000}) - .add_int64_axis("run_length", {1, 32}); + .add_int64_axis("cardinality", {0, 1000, 10'000, 100'000}) + .add_int64_axis("run_length", {1, 8, 32}); NVBENCH_BENCH_TYPES(BM_parq_write_io_compression, NVBENCH_TYPE_AXES(io_list, compression_list)) .set_name("parquet_write_io_compression")