From 2ba2587fbc156b9f2f1af17bef4a4b6a33abbb7b Mon Sep 17 00:00:00 2001 From: "k.koide" Date: Tue, 2 Apr 2024 16:28:43 +0900 Subject: [PATCH] fix typo --- BENCHMARK.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/BENCHMARK.md b/BENCHMARK.md index 9cd667f..ab1f1e0 100644 --- a/BENCHMARK.md +++ b/BENCHMARK.md @@ -72,7 +72,7 @@ python3 plot_kdtree.py ``` - Multi-threaded implementation (TBB and OMP) can be up to **4x faster** than the single-threaded one (All the implementations are based on nanoflann). -- Basically the processing speed get faster as the number of threads increases, but the speed gain is not monotonic sometimes (because of the scheduling algorithm or some CPU(AMD 5995WX)-specific issues?). +- The processing speed gets faster as the number of threads increases, but the speed gain is not monotonic sometimes (because of the scheduling algorithm or some CPU(AMD 5995WX)-specific issues?). - This benchmark only compares the construction time (query time is not included). ![kdtree_time](docs/assets/kdtree_time.png) @@ -87,7 +87,7 @@ python3 plot_odometry.py - Single-thread `small_gicp::GICP` is about **2.4x and 1.9x faster** than `pcl::GICP` and `fast_gicp::GICP`, respectively. - `small_gicp::(GICP|VGICP)` shows a better multi-thread scalability compared to `fast_gicp::(GICP|VGICP)`. -- `small_gicp::GICP` parallelized with [TBB flow graph](src/odometry_benchmark_small_gicp_tbb_flow.cpp) shows an excellent scalablity to many-threads situations (**~128 threads**) but with latency degradation. +- `small_gicp::GICP` parallelized with [TBB flow graph](src/odometry_benchmark_small_gicp_tbb_flow.cpp) shows an excellent scalability to many-threads situations (**~128 threads**) but with latency degradation. ![odometry_time](docs/assets/odometry_time.png)