RFR: JDK-8287061: Support for rematerializing scalar replaced objects participating in allocation merges [v9]

[Vladimir Kozlov]

On Mon, 17 Apr 2023 16:17:30 GMT, Cesar Soares Lucas <cslucas at openjdk.org> wrote:

>> Can I please get reviews for this PR? 
>> 
>> The most common and frequent use of NonEscaping Phis merging object allocations is for debugging information. The two graphs below show numbers for Renaissance and DaCapo benchmarks - similar results are obtained for all other applications that I tested.
>> 
>> With what frequency does each IR node type occurs as an allocation merge user? I.e., if the same node type uses a Phi N times the counter is incremented by N:
>> 
>> ![image](https://user-images.githubusercontent.com/2249648/222280517-4dcf5871-2564-4207-b49e-22aee47fa49d.png)
>> 
>> What are the most common users of allocation merges? I.e., if the same node type uses a Phi N times the counter is incremented by 1:
>> 
>> ![image](https://user-images.githubusercontent.com/2249648/222280608-ca742a4e-1622-4e69-a778-e4db6805ea02.png)
>> 
>> This PR adds support scalar replacing allocations participating in merges used as debug information OR as a base for field loads. I plan to create subsequent PRs to enable scalar replacement of merges used by other node types (CmpP is next on the list) subsequently.
>> 
>> The approach I used for _rematerialization_ is pretty straightforward. It consists basically of the following. 1) New IR node (suggested by V. Kozlov), named SafePointScalarMergeNode, to represent a set of SafePointScalarObjectNode; 2) Each scalar replaceable input participating in a merge will get a SafePointScalarObjectNode like if it weren't part of a merge. 3) Add a new Class to support the rematerialization of SR objects that are part of a merge; 4) Patch HotSpot to be able to serialize and deserialize debug information related to allocation merges; 5) Patch C2 to generate unique types for SR objects participating in some allocation merges.
>> 
>> The approach I used for _enabling the scalar replacement of some of the inputs of the allocation merge_ is also pretty straightforward: call `MemNode::split_through_phi` to, well, split AddP->Load* through the merge which will render the Phi useless.
>> 
>> I tested this with JTREG tests tier 1-4 (Windows, Linux, and Mac) and didn't see regression. I also experimented with several applications and didn't see any failure. I also ran tests with "-ea -esa -Xbatch -Xcomp -XX:+UnlockExperimentalVMOptions -XX:-TieredCompilation -server -XX:+IgnoreUnrecognizedVMOptions -XX:+UnlockDiagnosticVMOptions -XX:+StressLCM -XX:+StressGCM -XX:+StressCCP" and didn't observe any related failures.
>
> Cesar Soares Lucas has updated the pull request incrementally with one additional commit since the last revision:
> 
>   Fix tests. Remember previous reducible Phis.

Again got failures in the test on Aarch64 running with -XX:-UseTLAB:

testCmpMergeWithNull(boolean,int,int):
- Failed comparison: [found] 0 = 2 [given]
testCmpMergeWithNull_Second(boolean,int,int)
- Failed comparison: [found] 0 = 1 [given]
testMergedAccessAfterCallNoWrite(boolean,int,int)
- Failed comparison: [found] 2 = 3 [given]
testMergedAccessAfterCallWithWrite(boolean,int,int)
- Failed comparison: [found] 2 = 3 [given]
testNestedObjectsArray(boolean,int,int)
- Failed comparison: [found] 2 = 4 [given]

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

PR Comment: https://git.openjdk.org/jdk/pull/12897#issuecomment-1515550553