refactor(bench): make latency statistics more compact

Changed from 8 lines to 2 lines:
- Line 1: Heading with input size
- Line 2: All measurements on one line

Before (8 lines):
📈 Latency Statistics (at 100K inputs):
   Min:    1.93μs
   p50:    1.93μs
   p95:    1.93μs
   p99:    1.93μs
   Max:    1.93μs
   Stddev: 0.00ns

After (2 lines):
📈 Latency Statistics (at 100K inputs):
   Min: 1.93μs  p50: 1.93μs  p95: 1.93μs  p99: 1.93μs  Max: 1.93μs  Stddev: 0.00ns

Author: claude

src/bin/bench_throughput.rs

@@ -539,14 +539,17 @@ fn print_template_results(template_name: &str, results: &[BenchmarkResult], deta
         }
 
         // Latency statistics for largest size
-        println!("\n📈 Latency Statistics (at {} inputs):", format_size(largest_result.input_size));
         let stats = &largest_result.latency_stats;
-        println!("   Min:    {}", format_duration(stats.min));
-        println!("   p50:    {}", format_duration(stats.p50));
-        println!("   p95:    {}", format_duration(stats.p95));
-        println!("   p99:    {}", format_duration(stats.p99));
-        println!("   Max:    {}", format_duration(stats.max));
-        println!("   Stddev: {:.2}ns", stats.stddev);
+        println!("\n📈 Latency Statistics (at {} inputs):", format_size(largest_result.input_size));
+        println!(
+            "   Min: {}  p50: {}  p95: {}  p99: {}  Max: {}  Stddev: {:.2}ns",
+            format_duration(stats.min),
+            format_duration(stats.p50),
+            format_duration(stats.p95),
+            format_duration(stats.p99),
+            format_duration(stats.max),
+            stats.stddev
+        );
     }
 }