RFR: 8351016: RA support for EVEX to REX/REX2 demotion to optimize NDD instructions

Sandhya Viswanathan sviswanathan at openjdk.org
Tue Aug 26 23:39:43 UTC 2025


On Mon, 14 Jul 2025 02:36:24 GMT, Jatin Bhateja <jbhateja at openjdk.org> wrote:

> Currently, while choosing the colour (register) for a definition live range during the select phase of register allocation, we pick the first available colour that does not match with already allocated neighboring live ranges.
> 
> With Intel APX NDD ISA extension, several existing two-address arithmetic instructions can now have an explicit non-destructive destination operand; this, in general, saves additional spills for two-address instructions where the destination is also the first source operand, and where the source live range surpasses the current instruction.
> 
> All NDD instructions mandate extended EVEX encoding with a bulky 4-byte prefix, [JDK-8351994](https://github.com/openjdk/jdk/pull/24431) added logic for NDD to REX/REX2 demotion in the assembler layer, but due to the existing first color selection register allocation policy, the demotions are rare. This patch biases the allocation of NDD definition to the first source operand or the second source operand for the commutative class of operations.
> 
> Biasing is a compile-time hint to the allocator and is different from live range coalescing (aggressive/conservative), which merges the two live ranges using the union find algorithm.  Given that REX encoding needs a 1-byte prefix and REX2 encoding needs a 2-byte prefix, domotion saves considerable JIT code size.
> 
> The patch shows around 5-20% improvement in code size by facilitating NDD demotion.
> 
> For the following micro, the method JIT code size reduced from 136 to 120 bytes, which is around a 13% reduction in code size footprint.
>  
> **Micro:-**
> <img width="1344" height="315" alt="image" src="https://github.com/user-attachments/assets/9cbe9da8-d6af-4b1c-bb55-3e5d86eb2cf9" />
> 
> 
> **Baseline :-**
> <img width="1013" height="163" alt="image" src="https://github.com/user-attachments/assets/ff5d50c6-fdfa-40e8-b93d-5f117d5a1ac6" />
> 
> **With opt:-**
> <img width="940" height="160" alt="image" src="https://github.com/user-attachments/assets/bff425b0-f7bf-4ffd-a43d-18bdeb36b000" />
> 
> Thorough validations are underway using the latest [Intel Software Development Emulator version 9.58](https://www.intel.com/content/www/us/en/download/684897/intel-software-development-emulator.html).
> 
> Kindly review and share your feedback.
> 
> Best Regards,
> Jatin

@jatin-bhateja Thanks for looking into this.

src/hotspot/share/opto/chaitin.cpp line 1461:

> 1459: OptoReg::Name PhaseChaitin::select_bias_lrg_color(LRG& lrg, uint bias_lrg, int chunk) {
> 1460:   if (bias_lrg != 0) {
> 1461:     // If first bias lrg has a color.

There is no first or second here, I think you meant the comment to be:
// If bias lrg has a color

src/hotspot/share/opto/chaitin.cpp line 1655:

> 1653:     };
> 1654: 
> 1655:     if (X86_ONLY(UseAPX) NOT_X86(false)) {

The change looks to be generically applicable and not APX or X86 specific.

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

PR Review: https://git.openjdk.org/jdk/pull/26283#pullrequestreview-3157634419
PR Review Comment: https://git.openjdk.org/jdk/pull/26283#discussion_r2302382839
PR Review Comment: https://git.openjdk.org/jdk/pull/26283#discussion_r2302389647


More information about the hotspot-compiler-dev mailing list