RFR: 8371603: C2: assert(_inputs.at(alias_idx) == nullptr || _inputs.at(alias_idx) == load->in(1)) failed

[Emanuel Peter]

On Thu, 4 Dec 2025 01:41:19 GMT, Xiaohong Gong <xgong at openjdk.org> wrote:

> **Problem:**
> 
> This issue occurs on a 256-bit SVE machine, caused by the following problematic pattern in `LoadVectorNode::Ideal()`:
> 
> 
> Node* LoadVectorNode::Ideal(PhaseGVN* phase, bool can_reshape) {
>   const TypeVect* vt = vect_type();
>   if (Matcher::vector_needs_partial_operations(this, vt)) {
>     return VectorNode::try_to_gen_masked_vector(phase, this, vt);
>   }
>   return LoadNode::Ideal(phase, can_reshape);
> }
> 
> 
> The condition `Matcher::vector_needs_partial_operations(this, vt)` returns true for `LoadVectorNode` with 256-bit vector size even when the vector size equals the maximum vector size on SVE. In such cases, when `VectorNode::try_to_gen_masked_vector()` returns `nullptr`, the method exits early without calling `LoadNode::Ideal()`. This results in missing crucial optimizations that would normally be applied by the superclass.
> 
> This code was introduced by https://bugs.openjdk.org/browse/JDK-8286941 to generate vector masks for partial vector operations, but it failed to ensure that the superclass `Ideal()` method is always invoked when no transformation is applied.
> 
> **Solution:**
> 
> This patch addresses the issue through two changes:
> 
> 1. Refine `Matcher::vector_needs_partial_operations()` to return true only when the vector node genuinely represents a partial vector operation that requires masking.
> 2. Modify `VectorNode::try_to_gen_masked_vector()` to never return `nullptr`, ensuring the superclass `Ideal()` method is always invoked when no transformation is applied.
> 
> **Testing:**
> 
> - Verified on different SVE platforms with different vector sizes (128|256|512 bits).
> - Verified on X86 platforms with different avx options (-XX:UseAVX=1|2|3).
> - Added two new IR tests to verify 1) previously missing optimizations for `LoadVector/StoreVector` are now applied, and 2) that mask and the correct IR patterns are generated for partial vector operations.

@XiaohongGong Thanks for taking this over from me and fixing this so quickly, much appreciated!

Thanks for adding my regression tests and for the attribution :)

I only have a minor comment below. Otherwise, the code looks good to me. But since I'm not an SVE specialist, it would be good if someone with deeper knowledge would do a deeper review of the specific SVE parts.

Once an SVE specialist gives the approval for the PR, I'l run some internal testing and approve from my side :)

Ah, and one more thing: you should change the PR title to be more descriptive of the issue. The assert that was hit is only a far removed symptom. I would suggest:

`C2 SVE: missing Ideal optimizations for load and store vectors`

src/hotspot/share/opto/vectornode.cpp line 1118:

> 1116:   if (Matcher::vector_needs_partial_operations(this, vt)) {
> 1117:     return VectorNode::gen_masked_vector(phase, this, vt);
> 1118:   }

I think it would still be good practice to expect that a `nullptr` could come from `gen_masked_vector`, and then continue with optimizations below, rather than just returning the `nullptr`.

Because: who knows what someone in the future might do inside `gen_masked_vector`, maybe they'll find some edge case and just return `nullptr` again, and then we are back to similar issues.

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

PR Review: https://git.openjdk.org/jdk/pull/28651#pullrequestreview-3538639579
PR Review Comment: https://git.openjdk.org/jdk/pull/28651#discussion_r2587987772