RFR: 8308103: Massive (up to ~30x) increase in C2 compilation time since JDK 17

[Tobias Hartmann]

On Fri, 30 Jun 2023 13:23:38 GMT, Roland Westrelin <roland at openjdk.org> wrote:

> A long chain of nodes are sunk out of a loop. Every time a node is
> moved out of the loop, a cast is created to pin the node out of the
> loop. When its input is next sunk, the cast is removed (the cast is
> replaced by its input) and a new cast is created. Some nodes on the
> chain have 2 other nodes in the chain as uses. When such a node is
> sunk, 2 cast nodes are created, one for each use. So as the compiler
> moves forward in the chain, the number of cast to remove grows. From
> some profiling, removing those casts is what takes a lot of time.
> 
> The fix I propose is, when a node is processed, to check whether a
> cast at the out of loop control was already created for that node and
> to reuse it.
> 
> The test case takes 6 minutes when I run it without the fix and 3
> seconds with it.

The fix looks good to me but I still have a hard time to comprehend that this leads to a 30x increase in compilation time. And I'm worried that we have similar issues in other code. As a follow-up, could we have `PhaseIdealLoop::register_new_node` check the hash and return an existing node?

-------------

Marked as reviewed by thartmann (Reviewer).

PR Review: https://git.openjdk.org/jdk/pull/14732#pullrequestreview-1525540555