Documentation update

Author: n-shevko

docs/source/guide/guide_part_i.rst

@@ -288,8 +288,17 @@ For example, spikes can be stored efficiently using a sparse monitor:
         network.layers[layer], state_vars=["s"], time=int(time / dt), device=device, sparse=True
     )
 
-Note that using sparse tensors is advantageous only when the percentage of non-zero values is less than 4% of the total values.
-The table below compares memory consumption between sparse and dense tensors:
+
+Performance Considerations:
+
+
+While sparse tensors reduce memory usage when the percentage of non-zero values is below 4% (see table below),
+there is a trade-off in computational speed. Benchmarks on an RTX 3070 GPU show:
+
+* Sparse runtime: 1.2 seconds
+* Dense runtime: 0.5 seconds
+
+The dense implementation achieves 2x faster execution compared to sparse tensors in this configuration.
 
 ======================= ====================== ====================== ====================
 Sparse (megabytes used) Dense (megabytes used) Ratio (Sparse/Dense) % % of non zero values
@@ -315,9 +324,7 @@ Sparse (megabytes used) Dense (megabytes used) Ratio (Sparse/Dense) % % of non z
 283                     119                    238                    9.5
 ======================= ====================== ====================== ====================
 
-The tensor size does not affect the values in the third column.
-This table was generated by :code:`examples/benchmark/sparse_vs_dense_tensors.py`
-
+This table and performance metrics were generated by :code:`examples/benchmark/sparse_vs_dense_tensors.py`
 
 Running Simulations
 -------------------