[rwstauner]

Add a new optimization pass that deduplicates PatchPoint instructions
asserting the same invariant within a basic block when no intervening
instruction could invalidate it.

This is common in practice — e.g., 1 + 2 + 3 produces two identical
PatchPoint MethodRedefined(Integer, +, cme) because each + call
inserts one. The second is redundant since nothing between them can
redefine Integer#+.

The approach adds a PatchPoint leaf to the abstract heap DAG so the
effect system can distinguish instructions that could invalidate
invariants (writes to PatchPoint, e.g. Send/CCall) from those that
cannot (e.g. IncrCounter, Const). The pass maintains a HashSet of
seen invariants per block and skips duplicates, clearing the set when
an instruction writes to the PatchPoint heap.

Removed PatchPoints' orphaned Snapshot dependencies are cleaned up by
the subsequent DCE pass.

I added a new test with snapshots to zjit/src/hir/tests.rs in the first commit
so that you can see how the change affects it in the second commit:
88cf26b#diff-38be021d8d0035cca77d3eab5ccc530109e7832f4711a5beb4dfced7001787ae

closes Shopify#779

[tekknolagi]

This looks great! Thank you. Is there an ARM code size reduction?

[rwstauner]

With a quick lobsters run I'm seeing

$ ./run_benchmarks.rb --chruby 'a::ruby-mdev --zjit-stats' --chruby 'b::ruby-claude --zjit-stats' lobsters --warmup 30 --bench 10 --out-path data/zjit-ab.json
$ misc/zjit_diff.rb data/zjit-ab.json/output_002.json -a| grep -E 'size|bytes'
    side_exit_size                          9,783,408 →      9,397,028 ▼   -3.9%
    code_region_bytes                      29,343,744 →     28,753,920 ▼   -2.0%
    total_mem_bytes                        79,537,171 →     78,347,249 ▼   -1.5%
    zjit_alloc_bytes                       50,193,427 →     49,593,329 ▼   -1.2%