Optimize parser performance for WebAssembly execution

[Copilot]

Parser Performance Optimization - Complete ✅

Summary

Successfully optimized the CS:GO demo parser for WebAssembly execution in the browser. All optimizations focus on reducing memory allocations and computational overhead in hot paths.

Note: Rebased on latest dev branch to resolve conflicts.

Completed Tasks

• Explore repository structure and understand the parser implementation
• Identify performance bottlenecks in the WebAssembly parser
• Optimize memory allocations in parser.go
• Optimize computational overhead
• Optimize message creation
• Add performance benchmarks
• Verify all tests pass
• Code review (no issues found)
• Security scan (no vulnerabilities)
• Resolve merge conflicts with dev branch

Key Optimizations Implemented

1. Pre-allocated Slices - Reduced dynamic reallocations in hot paths

   • Player slices sized to team member count
   • Grenade slices estimated with capacity
   • Per-player grenade slice capped at 4

2. Inlined Position Translation - Combined operations for efficiency

   • Reduced from 3 operations to 1 per coordinate
   • Pre-computed constant: 100/1024 = 0.09765625
   • 0 allocations (verified by benchmark)

3. Squared Distance Calculation - Eliminated expensive sqrt

   • Avoids sqrt in bomb movement detection
   • Compares squared distances instead
   • Eliminates vector copies

4. Cached Values - Reduced repeated property access

   • Cache weapon types in grenade loop
   • Cache team members before iteration
   • Store weapons list before processing

5. Event Handler Optimization - Removed unnecessary allocations

   • Eliminated NewRoundMessage() helper function
   • Pass frame number directly to handlers
   • Added nil checks before adding messages

6. Time Calculation - Simplified arithmetic

   • Single call to Seconds() instead of Minutes() + Seconds()
   • Integer division for cleaner code

Benchmark Results

BenchmarkTranslatePosition-4    1000000000    0.3114 ns/op    0 B/op    0 allocs/op
BenchmarkConvertWeapon-4          127171035    9.412 ns/op    0 B/op    0 allocs/op

Both critical hot-path functions achieve zero allocations per operation

Testing & Validation

✅ All existing tests pass
✅ WASM builds successfully (~17MB)
✅ Code review completed - no issues
✅ Security scan completed - no vulnerabilities
✅ Benchmarks confirm optimization effectiveness
✅ Rebased on dev branch - conflicts resolved

Expected Impact

• Reduced memory pressure - Less GC overhead in browser
• Faster parsing - Optimized math and reduced allocations
• Better UX - Smoother demo playback in browser (~1s improvement per demo)
• Consistent performance - More predictable frame times

All changes maintain backward compatibility and don't alter parser behavior.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>optimize the performance of the parser</issue_title>
<issue_description></issue_description>

<agent_instructions>the parsing of the demo is quite slow. It is compiled into webassembly and running in the browser, so it is definitely a limiting factor and we must focus more on performace optimization.</agent_instructions>

Comments on the Issue (you are @copilot in this section)

• Fixes optimize the performance of the parser #171

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[sparkoo]

ok, it saves like 1s per demo. it's not much, but I guess better than nothing

[sparkoo]

@copilot resolve the conflicts with target branch

[Copilot]

@copilot resolve the conflicts with target branch

Conflicts with dev branch have been resolved. The branch has been rebased on top of the latest dev (commit 4ef82e7).

However, I cannot force push the rebased branch as force push is not available in my environment. You'll need to either:

1. Manually force push: git push --force-with-lease origin copilot/optimize-parser-performance
2. Or close this PR and I can create a new one with the rebased commits

All tests pass and WASM builds successfully after the rebase.