[prev in list] [next in list] [prev in thread] [next in thread] 

List:       openjdk-hotspot-compiler-dev
Subject:    Re: RFR: 8262355: Support for AVX-512 opmask register allocation. [v20]
From:       Jie Fu <jiefu () openjdk ! java ! net>
Date:       2021-11-30 23:37:52
Message-ID: drjK_9OwkvDglJbUyc-cPc8ERgMKHD2G7P2Fuhrlmak=.bc5048b8-cf34-4894-8103-d91f9c520888 () github ! com
[Download RAW message or body]

On Fri, 2 Apr 2021 13:16:53 GMT, Jatin Bhateja <jbhateja@openjdk.org> wrote:

> > AVX-512 added 8 new 64 bit opmask registers[1] . These registers allow \
> > conditional execution and efficient merging of destination operands. At present \
> > cross instruction mask propagation is being done either using a GPR (e.g. \
> > vmask_gen patterns in x86.ad) or a vector register (for propagating results of a \
> > vector comparison or vector load mask operations). 
> > This base patch extends the register allocator to support allocation of opmask \
> > registers. This will facilitate mask propagation across instructions and thus \
> > enable emitting efficient instruction sequence over X86 targets supporting \
> > AVX-512 feature. 
> > We intend to build a robust optimization framework[2] based on this patch to emit \
> > optimized instruction sequence for masked/predicated vector operation for X86 \
> > targets supporting AVX-512.  
> > Please review and share your feedback.
> > 
> > Summary of changes:
> > 
> > 1) AD side changes: New register definitions, register classes, allocation \
> > classes, operand definitions and spill code handling for opmask registers. 
> > 2) Runtime: Save/restoration for opmask registers in 32 and 64 bit JVM.
> > a) For 64 bit JVM we were anyways reserving the space in the frame layout but \
> > earlier were not saving and restoring at designated offset(1088), hence no extra \
> > space overhead apart from save/restore cost. b) For 32 bit JVM: Additional 64 \
> > byte are allocated apart from FXSTORE area on the lines of storage for ZMM(16-31) \
> > and YMM-Hi bank. There are few regressions due to extra space allocation which we \
> > are investigating. 
> > 3) Replacing all the hard-coded opmask references from macro-assembly routines: \
> > Pulling out the opmask occurrences all the way up to instruction pattern and \
> > adding an unbounded opmask operand for them. This exposes these operands to RA \
> > and scheduler; this will automatically facilitate spilling of live opmask \
> > registers across call sites. 
> > 4) Register class initializations related to Op_RegVMask during matcher startup.
> > 
> > 5) Handling for mask generating node:  Currently VectorMaskGen node uses a GPR to \
> > propagate mask across mask generating DEF instruction to its USER instructions. \
> > There are other mask generating nodes like VectorCmpMask, VectorLoadMask which \
> > are not handled as the part of this patch. Conditional overriding of two \
> > routines, ideal_reg and bottom_type for mask generating IDEAL nodes and modifying \
> > the instruction patterns to have new opmask operands enables instruction selector \
> > to associate opmask register class with USE/DEF operands  for such MachNodes. \
> > This will constrain  the allocation set for these operands to opmask \
> > registers(K1-K7). 
> > 6) Creation of a new concrete type TypeVectMask for mask generation nodes and a \
> > convivence routine Type::makemask which creates a regular vector types \
> > (TypeVect[SDXYZ]) for non-AVX-512 targets and TypeVectMask for a AVX-512 targets. \
> >  
> > 
> > [1] : Section 15.1.3 :  \
> > https://software.intel.com/content/www/us/en/develop/download/intel-64-and-ia-32-architectures-software-developers-manual-volume-1-basic-architecture.html
> >  [2] : http://cr.openjdk.java.net/~jbhateja/avx512_masked_operation_optimization/AVX-512_RA_Opmask_Support_VectorMask_Optimizations.pdf
> > 
> 
> Jatin Bhateja has updated the pull request with a new target base due to a merge or \
> a rebase. The pull request now contains 23 commits: 
> - 8262355: Rebasing patch, 32bit clean-up.
> - Merge http://github.com/openjdk/jdk into JDK-8262355
> - 8262355: Fix AARCH64 build issue
> - 8262355: Review comments resolutions.
> - Merge branch 'master' of http://github.com/openjdk/jdk into JDK-8262355
> - 8262355: Updating copywriter for edited files.
> - 8262355: Adding missed safety check.
> - 8262355: Review comments resolution.
> - 8262355: Extending Type::isa_vect and Type::is_vect routines to TypeVectMask \
>                 since its a valid vector type.
> - 8262355: Review comments resolution
> - ... and 13 more: https://git.openjdk.java.net/jdk/compare/7d0a0bad...b9810d20

Hi all,

There are still bugs for opmask register allocation on x86_32.
Could someone help to review it https://github.com/openjdk/jdk/pull/6535 ?

Thanks.
Best regards,
Jie

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

PR: https://git.openjdk.java.net/jdk/pull/2768


[prev in list] [next in list] [prev in thread] [next in thread]