[all-commits] [llvm/llvm-project] b5d35f: [X86] X86FixupVectorConstants - load+sign-extend v...

Simon Pilgrim via All-commits all-commits at lists.llvm.org
Fri Feb 2 03:29:10 PST 2024


  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: b5d35feacb7246573c6a4ab2bddc4919a4228ed5
      https://github.com/llvm/llvm-project/commit/b5d35feacb7246573c6a4ab2bddc4919a4228ed5
  Author: Simon Pilgrim <RKSimon at users.noreply.github.com>
  Date:   2024-02-02 (Fri, 02 Feb 2024)

  Changed paths:
    M llvm/lib/Target/X86/X86FixupVectorConstants.cpp
    M llvm/lib/Target/X86/X86MCInstLower.cpp
    M llvm/test/CodeGen/X86/any_extend_vector_inreg_of_broadcast.ll
    M llvm/test/CodeGen/X86/any_extend_vector_inreg_of_broadcast_from_memory.ll
    M llvm/test/CodeGen/X86/avg.ll
    M llvm/test/CodeGen/X86/avx-vperm2x128.ll
    M llvm/test/CodeGen/X86/avx2-arith.ll
    M llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll
    M llvm/test/CodeGen/X86/avx2-vector-shifts.ll
    M llvm/test/CodeGen/X86/avx512-arith.ll
    M llvm/test/CodeGen/X86/avx512-intrinsics.ll
    M llvm/test/CodeGen/X86/avx512-shuffles/partial_permute.ll
    M llvm/test/CodeGen/X86/avx512-shuffles/permute.ll
    M llvm/test/CodeGen/X86/avx512bw-intrinsics.ll
    M llvm/test/CodeGen/X86/avx512bwvl-intrinsics.ll
    M llvm/test/CodeGen/X86/avx512vl-intrinsics-upgrade.ll
    M llvm/test/CodeGen/X86/bitcast-int-to-vector-bool-sext.ll
    M llvm/test/CodeGen/X86/bitcast-int-to-vector-bool-zext.ll
    M llvm/test/CodeGen/X86/bitcast-int-to-vector-bool.ll
    M llvm/test/CodeGen/X86/broadcast-elm-cross-splat-vec.ll
    M llvm/test/CodeGen/X86/combine-add.ll
    M llvm/test/CodeGen/X86/combine-addo.ll
    M llvm/test/CodeGen/X86/combine-and.ll
    M llvm/test/CodeGen/X86/combine-bitselect.ll
    M llvm/test/CodeGen/X86/combine-mul.ll
    M llvm/test/CodeGen/X86/combine-pavg.ll
    M llvm/test/CodeGen/X86/combine-pmuldq.ll
    M llvm/test/CodeGen/X86/combine-sdiv.ll
    M llvm/test/CodeGen/X86/combine-shl.ll
    M llvm/test/CodeGen/X86/combine-sra.ll
    M llvm/test/CodeGen/X86/combine-srem.ll
    M llvm/test/CodeGen/X86/combine-srl.ll
    M llvm/test/CodeGen/X86/combine-sub-usat.ll
    M llvm/test/CodeGen/X86/combine-sub.ll
    M llvm/test/CodeGen/X86/combine-udiv.ll
    M llvm/test/CodeGen/X86/combine-urem.ll
    M llvm/test/CodeGen/X86/expand-vp-int-intrinsics.ll
    M llvm/test/CodeGen/X86/extract-concat.ll
    M llvm/test/CodeGen/X86/fold-int-pow2-with-fmul-or-fdiv.ll
    M llvm/test/CodeGen/X86/fpclamptosat_vec.ll
    M llvm/test/CodeGen/X86/i64-to-float.ll
    M llvm/test/CodeGen/X86/icmp-abs-C-vec.ll
    M llvm/test/CodeGen/X86/icmp-pow2-diff.ll
    M llvm/test/CodeGen/X86/insert-into-constant-vector.ll
    M llvm/test/CodeGen/X86/insertelement-shuffle.ll
    M llvm/test/CodeGen/X86/known-signbits-vector.ll
    M llvm/test/CodeGen/X86/masked_load.ll
    M llvm/test/CodeGen/X86/masked_store.ll
    M llvm/test/CodeGen/X86/masked_store_trunc.ll
    M llvm/test/CodeGen/X86/masked_store_trunc_ssat.ll
    M llvm/test/CodeGen/X86/masked_store_trunc_usat.ll
    M llvm/test/CodeGen/X86/midpoint-int-vec-128.ll
    M llvm/test/CodeGen/X86/midpoint-int-vec-256.ll
    M llvm/test/CodeGen/X86/min-legal-vector-width.ll
    M llvm/test/CodeGen/X86/movmsk-cmp.ll
    M llvm/test/CodeGen/X86/oddshuffles.ll
    M llvm/test/CodeGen/X86/packus.ll
    M llvm/test/CodeGen/X86/paddus.ll
    M llvm/test/CodeGen/X86/pmul.ll
    M llvm/test/CodeGen/X86/pmulh.ll
    M llvm/test/CodeGen/X86/pr48215.ll
    M llvm/test/CodeGen/X86/pr57340.ll
    M llvm/test/CodeGen/X86/pr61964.ll
    M llvm/test/CodeGen/X86/pr62014.ll
    M llvm/test/CodeGen/X86/pr63507.ll
    M llvm/test/CodeGen/X86/pr74736.ll
    M llvm/test/CodeGen/X86/pr77459.ll
    M llvm/test/CodeGen/X86/prefer-avx256-mask-shuffle.ll
    M llvm/test/CodeGen/X86/psubus.ll
    M llvm/test/CodeGen/X86/sat-add.ll
    M llvm/test/CodeGen/X86/setcc-non-simple-type.ll
    M llvm/test/CodeGen/X86/sext-vsetcc.ll
    M llvm/test/CodeGen/X86/shuffle-strided-with-offset-512.ll
    M llvm/test/CodeGen/X86/shuffle-vs-trunc-256.ll
    M llvm/test/CodeGen/X86/shuffle-vs-trunc-512.ll
    M llvm/test/CodeGen/X86/slow-pmulld.ll
    M llvm/test/CodeGen/X86/srem-seteq-illegal-types.ll
    M llvm/test/CodeGen/X86/srem-seteq-vec-nonsplat.ll
    M llvm/test/CodeGen/X86/srem-vector-lkk.ll
    M llvm/test/CodeGen/X86/sse-domains.ll
    M llvm/test/CodeGen/X86/subvector-broadcast.ll
    M llvm/test/CodeGen/X86/urem-seteq-illegal-types.ll
    M llvm/test/CodeGen/X86/urem-seteq-vec-nonsplat.ll
    M llvm/test/CodeGen/X86/urem-seteq-vec-splat.ll
    M llvm/test/CodeGen/X86/urem-seteq-vec-tautological.ll
    M llvm/test/CodeGen/X86/urem-vector-lkk.ll
    M llvm/test/CodeGen/X86/usub_sat_vec.ll
    M llvm/test/CodeGen/X86/var-permute-256.ll
    M llvm/test/CodeGen/X86/vec_int_to_fp.ll
    M llvm/test/CodeGen/X86/vec_setcc-2.ll
    M llvm/test/CodeGen/X86/vec_setcc.ll
    M llvm/test/CodeGen/X86/vec_shift6.ll
    M llvm/test/CodeGen/X86/vec_smulo.ll
    M llvm/test/CodeGen/X86/vec_umulo.ll
    M llvm/test/CodeGen/X86/vector-bo-select.ll
    M llvm/test/CodeGen/X86/vector-fshl-128.ll
    M llvm/test/CodeGen/X86/vector-fshl-256.ll
    M llvm/test/CodeGen/X86/vector-fshl-512.ll
    M llvm/test/CodeGen/X86/vector-fshl-rot-128.ll
    M llvm/test/CodeGen/X86/vector-fshl-rot-256.ll
    M llvm/test/CodeGen/X86/vector-fshl-rot-sub128.ll
    M llvm/test/CodeGen/X86/vector-fshl-sub128.ll
    M llvm/test/CodeGen/X86/vector-fshr-128.ll
    M llvm/test/CodeGen/X86/vector-fshr-256.ll
    M llvm/test/CodeGen/X86/vector-fshr-512.ll
    M llvm/test/CodeGen/X86/vector-fshr-rot-128.ll
    M llvm/test/CodeGen/X86/vector-fshr-rot-256.ll
    M llvm/test/CodeGen/X86/vector-fshr-rot-sub128.ll
    M llvm/test/CodeGen/X86/vector-fshr-sub128.ll
    M llvm/test/CodeGen/X86/vector-idiv-sdiv-128.ll
    M llvm/test/CodeGen/X86/vector-idiv-sdiv-512.ll
    M llvm/test/CodeGen/X86/vector-idiv-udiv-128.ll
    M llvm/test/CodeGen/X86/vector-idiv-udiv-512.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i16-stride-2.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i16-stride-3.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i16-stride-4.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i16-stride-5.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i16-stride-6.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i16-stride-7.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i16-stride-8.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i32-stride-2.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i32-stride-3.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i32-stride-4.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i32-stride-5.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i32-stride-6.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i32-stride-7.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i32-stride-8.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i64-stride-2.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i64-stride-3.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i64-stride-5.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i64-stride-6.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i64-stride-7.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i64-stride-8.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-2.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-3.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-4.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-5.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-6.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-7.ll
    M llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-8.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i16-stride-2.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i16-stride-3.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i16-stride-4.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i16-stride-5.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i16-stride-6.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i16-stride-7.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i16-stride-8.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-2.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-3.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-4.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-5.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-6.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-7.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-8.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-2.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-3.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-4.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-5.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-6.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-7.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-8.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-2.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-5.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-6.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-7.ll
    M llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-8.ll
    M llvm/test/CodeGen/X86/vector-mul.ll
    M llvm/test/CodeGen/X86/vector-pack-512.ll
    M llvm/test/CodeGen/X86/vector-popcnt-128-ult-ugt.ll
    M llvm/test/CodeGen/X86/vector-popcnt-256-ult-ugt.ll
    M llvm/test/CodeGen/X86/vector-reduce-add-mask.ll
    M llvm/test/CodeGen/X86/vector-reduce-ctpop.ll
    M llvm/test/CodeGen/X86/vector-reduce-xor-bool.ll
    M llvm/test/CodeGen/X86/vector-replicaton-i1-mask.ll
    M llvm/test/CodeGen/X86/vector-rotate-128.ll
    M llvm/test/CodeGen/X86/vector-rotate-256.ll
    M llvm/test/CodeGen/X86/vector-sext.ll
    M llvm/test/CodeGen/X86/vector-shift-ashr-128.ll
    M llvm/test/CodeGen/X86/vector-shift-ashr-256.ll
    M llvm/test/CodeGen/X86/vector-shift-ashr-512.ll
    M llvm/test/CodeGen/X86/vector-shift-ashr-sub128.ll
    M llvm/test/CodeGen/X86/vector-shift-lshr-128.ll
    M llvm/test/CodeGen/X86/vector-shift-lshr-256.ll
    M llvm/test/CodeGen/X86/vector-shift-lshr-sub128.ll
    M llvm/test/CodeGen/X86/vector-shift-shl-128.ll
    M llvm/test/CodeGen/X86/vector-shift-shl-256.ll
    M llvm/test/CodeGen/X86/vector-shift-shl-sub128.ll
    M llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll
    M llvm/test/CodeGen/X86/vector-shuffle-128-v8.ll
    M llvm/test/CodeGen/X86/vector-shuffle-256-v16.ll
    M llvm/test/CodeGen/X86/vector-shuffle-256-v32.ll
    M llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll
    M llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll
    M llvm/test/CodeGen/X86/vector-shuffle-512-v16.ll
    M llvm/test/CodeGen/X86/vector-shuffle-512-v32.ll
    M llvm/test/CodeGen/X86/vector-shuffle-512-v64.ll
    M llvm/test/CodeGen/X86/vector-shuffle-512-v8.ll
    M llvm/test/CodeGen/X86/vector-shuffle-combining-avx.ll
    M llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll
    M llvm/test/CodeGen/X86/vector-shuffle-combining-avx512bw.ll
    M llvm/test/CodeGen/X86/vector-shuffle-combining-avx512bwvl.ll
    M llvm/test/CodeGen/X86/vector-shuffle-combining-avx512f.ll
    M llvm/test/CodeGen/X86/vector-shuffle-combining-avx512vbmi.ll
    M llvm/test/CodeGen/X86/vector-shuffle-combining.ll
    M llvm/test/CodeGen/X86/vector-shuffle-v1.ll
    M llvm/test/CodeGen/X86/vector-shuffle-v192.ll
    M llvm/test/CodeGen/X86/vector-trunc-math.ll
    M llvm/test/CodeGen/X86/vector-trunc-packus.ll
    M llvm/test/CodeGen/X86/vector-trunc-ssat.ll
    M llvm/test/CodeGen/X86/vector-trunc-usat.ll
    M llvm/test/CodeGen/X86/vector-trunc.ll
    M llvm/test/CodeGen/X86/vector-tzcnt-128.ll
    M llvm/test/CodeGen/X86/vector-unsigned-cmp.ll
    M llvm/test/CodeGen/X86/vector-zext.ll
    M llvm/test/CodeGen/X86/vselect-constants.ll
    M llvm/test/CodeGen/X86/vselect-pcmp.ll
    M llvm/test/CodeGen/X86/vselect.ll
    M llvm/test/CodeGen/X86/widen_arith-5.ll
    M llvm/test/CodeGen/X86/x86-interleaved-access.ll
    M llvm/test/CodeGen/X86/zero_extend_vector_inreg.ll
    M llvm/test/CodeGen/X86/zero_extend_vector_inreg_of_broadcast.ll
    M llvm/test/CodeGen/X86/zero_extend_vector_inreg_of_broadcast_from_memory.ll

  Log Message:
  -----------
  [X86] X86FixupVectorConstants - load+sign-extend vector constants that can be stored in a truncated form (#79815)

Reduce the size of the vector constant by storing it in the constant pool in a truncated form, and sign-extend it as part of the load.

I've extended the existing FixupConstant functionality to support these sext constant rebuilds - we still select the smallest stored constant entry and prefer vzload/broadcast/vextload for same bitwidth to avoid domain flips.

I intend to add the matching load+zero-extend handling in a future PR, but that requires some alterations to the existing MC shuffle comments handling first.




More information about the All-commits mailing list