llvm/test/CodeGen/RISCV/rvv/vscale-vw-web-simplification.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+v -verify-machineinstrs %s -o - --riscv-lower-ext-max-web-size=1 | FileCheck %s --check-prefixes=NO_FOLDING,RV32
; RUN: llc -mtriple=riscv32 -mattr=+v -verify-machineinstrs %s -o - --riscv-lower-ext-max-web-size=2 | FileCheck %s --check-prefixes=NO_FOLDING,RV32
; RUN: llc -mtriple=riscv32 -mattr=+v -verify-machineinstrs %s -o - --riscv-lower-ext-max-web-size=3 | FileCheck %s --check-prefixes=FOLDING,RV32
; RUN: llc -mtriple=riscv64 -mattr=+v -verify-machineinstrs %s -o - --riscv-lower-ext-max-web-size=1 | FileCheck %s --check-prefixes=NO_FOLDING,RV64
; RUN: llc -mtriple=riscv64 -mattr=+v -verify-machineinstrs %s -o - --riscv-lower-ext-max-web-size=2 | FileCheck %s --check-prefixes=NO_FOLDING,RV64
; RUN: llc -mtriple=riscv64 -mattr=+v -verify-machineinstrs %s -o - --riscv-lower-ext-max-web-size=3 | FileCheck %s --check-prefixes=FOLDING,RV64
; Check that the default value enables the web folding and
; that it is bigger than 3.
; RUN: llc -mtriple=riscv32 -mattr=+v -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=FOLDING,RV32
; RUN: llc -mtriple=riscv64 -mattr=+v -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=FOLDING,RV64

; Check that the scalable vector add/sub/mul operations are all promoted into their
; vw counterpart when the folding of the web size is increased to 3.
; We need the web size to be at least 3 for the folding to happen, because
; %c has 3 uses.
; see https://github.com/llvm/llvm-project/pull/72340

define <vscale x 2 x i16> @vwop_vscale_sext_i8i16_multiple_users(ptr %x, ptr %y, ptr %z) {
; NO_FOLDING-LABEL: vwop_vscale_sext_i8i16_multiple_users:
; NO_FOLDING:       # %bb.0:
; NO_FOLDING-NEXT:    vsetvli a3, zero, e16, mf2, ta, ma
; NO_FOLDING-NEXT:    vle8.v v8, (a0)
; NO_FOLDING-NEXT:    vle8.v v9, (a1)
; NO_FOLDING-NEXT:    vle8.v v10, (a2)
; NO_FOLDING-NEXT:    vsext.vf2 v11, v8
; NO_FOLDING-NEXT:    vsext.vf2 v8, v9
; NO_FOLDING-NEXT:    vsext.vf2 v9, v10
; NO_FOLDING-NEXT:    vmul.vv v8, v11, v8
; NO_FOLDING-NEXT:    vadd.vv v10, v11, v9
; NO_FOLDING-NEXT:    vsub.vv v9, v11, v9
; NO_FOLDING-NEXT:    vor.vv v8, v8, v10
; NO_FOLDING-NEXT:    vor.vv v8, v8, v9
; NO_FOLDING-NEXT:    ret
;
; FOLDING-LABEL: vwop_vscale_sext_i8i16_multiple_users:
; FOLDING:       # %bb.0:
; FOLDING-NEXT:    vsetvli a3, zero, e8, mf4, ta, ma
; FOLDING-NEXT:    vle8.v v8, (a0)
; FOLDING-NEXT:    vle8.v v9, (a1)
; FOLDING-NEXT:    vle8.v v10, (a2)
; FOLDING-NEXT:    vwmul.vv v11, v8, v9
; FOLDING-NEXT:    vwadd.vv v9, v8, v10
; FOLDING-NEXT:    vwsub.vv v12, v8, v10
; FOLDING-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
; FOLDING-NEXT:    vor.vv v8, v11, v9
; FOLDING-NEXT:    vor.vv v8, v8, v12
; FOLDING-NEXT:    ret
  %a = load <vscale x 2 x i8>, ptr %x
  %b = load <vscale x 2 x i8>, ptr %y
  %b2 = load <vscale x 2 x i8>, ptr %z
  %c = sext <vscale x 2 x i8> %a to <vscale x 2 x i16>
  %d = sext <vscale x 2 x i8> %b to <vscale x 2 x i16>
  %d2 = sext <vscale x 2 x i8> %b2 to <vscale x 2 x i16>
  %e = mul <vscale x 2 x i16> %c, %d
  %f = add <vscale x 2 x i16> %c, %d2
  %g = sub <vscale x 2 x i16> %c, %d2
  %h = or <vscale x 2 x i16> %e, %f
  %i = or <vscale x 2 x i16> %h, %g
  ret <vscale x 2 x i16> %i
}

define <vscale x 2 x i32> @vwop_vscale_sext_i16i32_multiple_users(ptr %x, ptr %y, ptr %z) {
; NO_FOLDING-LABEL: vwop_vscale_sext_i16i32_multiple_users:
; NO_FOLDING:       # %bb.0:
; NO_FOLDING-NEXT:    vsetvli a3, zero, e32, m1, ta, ma
; NO_FOLDING-NEXT:    vle16.v v8, (a0)
; NO_FOLDING-NEXT:    vle16.v v9, (a1)
; NO_FOLDING-NEXT:    vle16.v v10, (a2)
; NO_FOLDING-NEXT:    vsext.vf2 v11, v8
; NO_FOLDING-NEXT:    vsext.vf2 v8, v9
; NO_FOLDING-NEXT:    vsext.vf2 v9, v10
; NO_FOLDING-NEXT:    vmul.vv v8, v11, v8
; NO_FOLDING-NEXT:    vadd.vv v10, v11, v9
; NO_FOLDING-NEXT:    vsub.vv v9, v11, v9
; NO_FOLDING-NEXT:    vor.vv v8, v8, v10
; NO_FOLDING-NEXT:    vor.vv v8, v8, v9
; NO_FOLDING-NEXT:    ret
;
; FOLDING-LABEL: vwop_vscale_sext_i16i32_multiple_users:
; FOLDING:       # %bb.0:
; FOLDING-NEXT:    vsetvli a3, zero, e16, mf2, ta, ma
; FOLDING-NEXT:    vle16.v v8, (a0)
; FOLDING-NEXT:    vle16.v v9, (a1)
; FOLDING-NEXT:    vle16.v v10, (a2)
; FOLDING-NEXT:    vwmul.vv v11, v8, v9
; FOLDING-NEXT:    vwadd.vv v9, v8, v10
; FOLDING-NEXT:    vwsub.vv v12, v8, v10
; FOLDING-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
; FOLDING-NEXT:    vor.vv v8, v11, v9
; FOLDING-NEXT:    vor.vv v8, v8, v12
; FOLDING-NEXT:    ret
  %a = load <vscale x 2 x i16>, ptr %x
  %b = load <vscale x 2 x i16>, ptr %y
  %b2 = load <vscale x 2 x i16>, ptr %z
  %c = sext <vscale x 2 x i16> %a to <vscale x 2 x i32>
  %d = sext <vscale x 2 x i16> %b to <vscale x 2 x i32>
  %d2 = sext <vscale x 2 x i16> %b2 to <vscale x 2 x i32>
  %e = mul <vscale x 2 x i32> %c, %d
  %f = add <vscale x 2 x i32> %c, %d2
  %g = sub <vscale x 2 x i32> %c, %d2
  %h = or <vscale x 2 x i32> %e, %f
  %i = or <vscale x 2 x i32> %h, %g
  ret <vscale x 2 x i32> %i
}

define <vscale x 2 x i64> @vwop_vscale_sext_i32i64_multiple_users(ptr %x, ptr %y, ptr %z) {
; NO_FOLDING-LABEL: vwop_vscale_sext_i32i64_multiple_users:
; NO_FOLDING:       # %bb.0:
; NO_FOLDING-NEXT:    vl1re32.v v10, (a0)
; NO_FOLDING-NEXT:    vl1re32.v v12, (a1)
; NO_FOLDING-NEXT:    vl1re32.v v14, (a2)
; NO_FOLDING-NEXT:    vsetvli a0, zero, e64, m2, ta, ma
; NO_FOLDING-NEXT:    vsext.vf2 v8, v10
; NO_FOLDING-NEXT:    vsext.vf2 v10, v12
; NO_FOLDING-NEXT:    vsext.vf2 v12, v14
; NO_FOLDING-NEXT:    vmul.vv v10, v8, v10
; NO_FOLDING-NEXT:    vadd.vv v14, v8, v12
; NO_FOLDING-NEXT:    vsub.vv v8, v8, v12
; NO_FOLDING-NEXT:    vor.vv v10, v10, v14
; NO_FOLDING-NEXT:    vor.vv v8, v10, v8
; NO_FOLDING-NEXT:    ret
;
; FOLDING-LABEL: vwop_vscale_sext_i32i64_multiple_users:
; FOLDING:       # %bb.0:
; FOLDING-NEXT:    vl1re32.v v14, (a0)
; FOLDING-NEXT:    vl1re32.v v10, (a1)
; FOLDING-NEXT:    vl1re32.v v15, (a2)
; FOLDING-NEXT:    vsetvli a0, zero, e32, m1, ta, ma
; FOLDING-NEXT:    vwmul.vv v8, v14, v10
; FOLDING-NEXT:    vwadd.vv v10, v14, v15
; FOLDING-NEXT:    vwsub.vv v12, v14, v15
; FOLDING-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
; FOLDING-NEXT:    vor.vv v8, v8, v10
; FOLDING-NEXT:    vor.vv v8, v8, v12
; FOLDING-NEXT:    ret
  %a = load <vscale x 2 x i32>, ptr %x
  %b = load <vscale x 2 x i32>, ptr %y
  %b2 = load <vscale x 2 x i32>, ptr %z
  %c = sext <vscale x 2 x i32> %a to <vscale x 2 x i64>
  %d = sext <vscale x 2 x i32> %b to <vscale x 2 x i64>
  %d2 = sext <vscale x 2 x i32> %b2 to <vscale x 2 x i64>
  %e = mul <vscale x 2 x i64> %c, %d
  %f = add <vscale x 2 x i64> %c, %d2
  %g = sub <vscale x 2 x i64> %c, %d2
  %h = or <vscale x 2 x i64> %e, %f
  %i = or <vscale x 2 x i64> %h, %g
  ret <vscale x 2 x i64> %i
}

define <vscale x 2 x i32> @vwop_vscale_sext_i1i32_multiple_users(ptr %x, ptr %y, ptr %z) {
; NO_FOLDING-LABEL: vwop_vscale_sext_i1i32_multiple_users:
; NO_FOLDING:       # %bb.0:
; NO_FOLDING-NEXT:    vsetvli a3, zero, e32, m1, ta, mu
; NO_FOLDING-NEXT:    vlm.v v8, (a0)
; NO_FOLDING-NEXT:    vlm.v v9, (a1)
; NO_FOLDING-NEXT:    vlm.v v10, (a2)
; NO_FOLDING-NEXT:    vmv.v.i v11, 0
; NO_FOLDING-NEXT:    vmv.v.v v0, v8
; NO_FOLDING-NEXT:    vmerge.vim v12, v11, -1, v0
; NO_FOLDING-NEXT:    vmv.v.v v0, v9
; NO_FOLDING-NEXT:    vmerge.vim v9, v11, -1, v0
; NO_FOLDING-NEXT:    vmv.v.v v0, v10
; NO_FOLDING-NEXT:    vmerge.vim v10, v11, -1, v0
; NO_FOLDING-NEXT:    vmul.vv v9, v12, v9
; NO_FOLDING-NEXT:    vsub.vv v11, v12, v10
; NO_FOLDING-NEXT:    vmv.v.v v0, v8
; NO_FOLDING-NEXT:    vadd.vi v10, v10, -1, v0.t
; NO_FOLDING-NEXT:    vor.vv v8, v9, v10
; NO_FOLDING-NEXT:    vor.vv v8, v8, v11
; NO_FOLDING-NEXT:    ret
;
; FOLDING-LABEL: vwop_vscale_sext_i1i32_multiple_users:
; FOLDING:       # %bb.0:
; FOLDING-NEXT:    vsetvli a3, zero, e32, m1, ta, mu
; FOLDING-NEXT:    vlm.v v8, (a0)
; FOLDING-NEXT:    vlm.v v9, (a1)
; FOLDING-NEXT:    vlm.v v10, (a2)
; FOLDING-NEXT:    vmv.v.i v11, 0
; FOLDING-NEXT:    vmv.v.v v0, v8
; FOLDING-NEXT:    vmerge.vim v12, v11, -1, v0
; FOLDING-NEXT:    vmv.v.v v0, v9
; FOLDING-NEXT:    vmerge.vim v9, v11, -1, v0
; FOLDING-NEXT:    vmv.v.v v0, v10
; FOLDING-NEXT:    vmerge.vim v10, v11, -1, v0
; FOLDING-NEXT:    vmul.vv v9, v12, v9
; FOLDING-NEXT:    vsub.vv v11, v12, v10
; FOLDING-NEXT:    vmv.v.v v0, v8
; FOLDING-NEXT:    vadd.vi v10, v10, -1, v0.t
; FOLDING-NEXT:    vor.vv v8, v9, v10
; FOLDING-NEXT:    vor.vv v8, v8, v11
; FOLDING-NEXT:    ret
  %a = load <vscale x 2 x i1>, ptr %x
  %b = load <vscale x 2 x i1>, ptr %y
  %b2 = load <vscale x 2 x i1>, ptr %z
  %c = sext <vscale x 2 x i1> %a to <vscale x 2 x i32>
  %d = sext <vscale x 2 x i1> %b to <vscale x 2 x i32>
  %d2 = sext <vscale x 2 x i1> %b2 to <vscale x 2 x i32>
  %e = mul <vscale x 2 x i32> %c, %d
  %f = add <vscale x 2 x i32> %c, %d2
  %g = sub <vscale x 2 x i32> %c, %d2
  %h = or <vscale x 2 x i32> %e, %f
  %i = or <vscale x 2 x i32> %h, %g
  ret <vscale x 2 x i32> %i
}

define <vscale x 2 x i8> @vwop_vscale_sext_i1i8_multiple_users(ptr %x, ptr %y, ptr %z) {
; NO_FOLDING-LABEL: vwop_vscale_sext_i1i8_multiple_users:
; NO_FOLDING:       # %bb.0:
; NO_FOLDING-NEXT:    vsetvli a3, zero, e8, mf4, ta, mu
; NO_FOLDING-NEXT:    vlm.v v8, (a0)
; NO_FOLDING-NEXT:    vlm.v v9, (a1)
; NO_FOLDING-NEXT:    vlm.v v10, (a2)
; NO_FOLDING-NEXT:    vmv.v.i v11, 0
; NO_FOLDING-NEXT:    vmv1r.v v0, v8
; NO_FOLDING-NEXT:    vmerge.vim v12, v11, -1, v0
; NO_FOLDING-NEXT:    vmv1r.v v0, v9
; NO_FOLDING-NEXT:    vmerge.vim v9, v11, -1, v0
; NO_FOLDING-NEXT:    vmv1r.v v0, v10
; NO_FOLDING-NEXT:    vmerge.vim v10, v11, -1, v0
; NO_FOLDING-NEXT:    vmul.vv v9, v12, v9
; NO_FOLDING-NEXT:    vsub.vv v11, v12, v10
; NO_FOLDING-NEXT:    vmv1r.v v0, v8
; NO_FOLDING-NEXT:    vadd.vi v10, v10, -1, v0.t
; NO_FOLDING-NEXT:    vor.vv v8, v9, v10
; NO_FOLDING-NEXT:    vor.vv v8, v8, v11
; NO_FOLDING-NEXT:    ret
;
; FOLDING-LABEL: vwop_vscale_sext_i1i8_multiple_users:
; FOLDING:       # %bb.0:
; FOLDING-NEXT:    vsetvli a3, zero, e8, mf4, ta, mu
; FOLDING-NEXT:    vlm.v v8, (a0)
; FOLDING-NEXT:    vlm.v v9, (a1)
; FOLDING-NEXT:    vlm.v v10, (a2)
; FOLDING-NEXT:    vmv.v.i v11, 0
; FOLDING-NEXT:    vmv1r.v v0, v8
; FOLDING-NEXT:    vmerge.vim v12, v11, -1, v0
; FOLDING-NEXT:    vmv1r.v v0, v9
; FOLDING-NEXT:    vmerge.vim v9, v11, -1, v0
; FOLDING-NEXT:    vmv1r.v v0, v10
; FOLDING-NEXT:    vmerge.vim v10, v11, -1, v0
; FOLDING-NEXT:    vmul.vv v9, v12, v9
; FOLDING-NEXT:    vsub.vv v11, v12, v10
; FOLDING-NEXT:    vmv1r.v v0, v8
; FOLDING-NEXT:    vadd.vi v10, v10, -1, v0.t
; FOLDING-NEXT:    vor.vv v8, v9, v10
; FOLDING-NEXT:    vor.vv v8, v8, v11
; FOLDING-NEXT:    ret
  %a = load <vscale x 2 x i1>, ptr %x
  %b = load <vscale x 2 x i1>, ptr %y
  %b2 = load <vscale x 2 x i1>, ptr %z
  %c = sext <vscale x 2 x i1> %a to <vscale x 2 x i8>
  %d = sext <vscale x 2 x i1> %b to <vscale x 2 x i8>
  %d2 = sext <vscale x 2 x i1> %b2 to <vscale x 2 x i8>
  %e = mul <vscale x 2 x i8> %c, %d
  %f = add <vscale x 2 x i8> %c, %d2
  %g = sub <vscale x 2 x i8> %c, %d2
  %h = or <vscale x 2 x i8> %e, %f
  %i = or <vscale x 2 x i8> %h, %g
  ret <vscale x 2 x i8> %i
}

define <vscale x 2 x i32> @vwop_vscale_sext_i8i32_multiple_users(ptr %x, ptr %y, ptr %z) {
; NO_FOLDING-LABEL: vwop_vscale_sext_i8i32_multiple_users:
; NO_FOLDING:       # %bb.0:
; NO_FOLDING-NEXT:    vsetvli a3, zero, e32, m1, ta, ma
; NO_FOLDING-NEXT:    vle8.v v8, (a0)
; NO_FOLDING-NEXT:    vle8.v v9, (a1)
; NO_FOLDING-NEXT:    vle8.v v10, (a2)
; NO_FOLDING-NEXT:    vsext.vf4 v11, v8
; NO_FOLDING-NEXT:    vsext.vf4 v8, v9
; NO_FOLDING-NEXT:    vsext.vf4 v9, v10
; NO_FOLDING-NEXT:    vmul.vv v8, v11, v8
; NO_FOLDING-NEXT:    vadd.vv v10, v11, v9
; NO_FOLDING-NEXT:    vsub.vv v9, v11, v9
; NO_FOLDING-NEXT:    vor.vv v8, v8, v10
; NO_FOLDING-NEXT:    vor.vv v8, v8, v9
; NO_FOLDING-NEXT:    ret
;
; FOLDING-LABEL: vwop_vscale_sext_i8i32_multiple_users:
; FOLDING:       # %bb.0:
; FOLDING-NEXT:    vsetvli a3, zero, e16, mf2, ta, ma
; FOLDING-NEXT:    vle8.v v8, (a0)
; FOLDING-NEXT:    vle8.v v9, (a1)
; FOLDING-NEXT:    vle8.v v10, (a2)
; FOLDING-NEXT:    vsext.vf2 v11, v8
; FOLDING-NEXT:    vsext.vf2 v8, v9
; FOLDING-NEXT:    vsext.vf2 v9, v10
; FOLDING-NEXT:    vwmul.vv v10, v11, v8
; FOLDING-NEXT:    vwadd.vv v8, v11, v9
; FOLDING-NEXT:    vwsub.vv v12, v11, v9
; FOLDING-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
; FOLDING-NEXT:    vor.vv v8, v10, v8
; FOLDING-NEXT:    vor.vv v8, v8, v12
; FOLDING-NEXT:    ret
  %a = load <vscale x 2 x i8>, ptr %x
  %b = load <vscale x 2 x i8>, ptr %y
  %b2 = load <vscale x 2 x i8>, ptr %z
  %c = sext <vscale x 2 x i8> %a to <vscale x 2 x i32>
  %d = sext <vscale x 2 x i8> %b to <vscale x 2 x i32>
  %d2 = sext <vscale x 2 x i8> %b2 to <vscale x 2 x i32>
  %e = mul <vscale x 2 x i32> %c, %d
  %f = add <vscale x 2 x i32> %c, %d2
  %g = sub <vscale x 2 x i32> %c, %d2
  %h = or <vscale x 2 x i32> %e, %f
  %i = or <vscale x 2 x i32> %h, %g
  ret <vscale x 2 x i32> %i
}

define <vscale x 2 x i16> @vwop_vscale_zext_i8i16_multiple_users(ptr %x, ptr %y, ptr %z) {
; NO_FOLDING-LABEL: vwop_vscale_zext_i8i16_multiple_users:
; NO_FOLDING:       # %bb.0:
; NO_FOLDING-NEXT:    vsetvli a3, zero, e16, mf2, ta, ma
; NO_FOLDING-NEXT:    vle8.v v8, (a0)
; NO_FOLDING-NEXT:    vle8.v v9, (a1)
; NO_FOLDING-NEXT:    vle8.v v10, (a2)
; NO_FOLDING-NEXT:    vzext.vf2 v11, v8
; NO_FOLDING-NEXT:    vzext.vf2 v8, v9
; NO_FOLDING-NEXT:    vzext.vf2 v9, v10
; NO_FOLDING-NEXT:    vmul.vv v8, v11, v8
; NO_FOLDING-NEXT:    vadd.vv v10, v11, v9
; NO_FOLDING-NEXT:    vsub.vv v9, v11, v9
; NO_FOLDING-NEXT:    vor.vv v8, v8, v10
; NO_FOLDING-NEXT:    vor.vv v8, v8, v9
; NO_FOLDING-NEXT:    ret
;
; FOLDING-LABEL: vwop_vscale_zext_i8i16_multiple_users:
; FOLDING:       # %bb.0:
; FOLDING-NEXT:    vsetvli a3, zero, e8, mf4, ta, ma
; FOLDING-NEXT:    vle8.v v8, (a0)
; FOLDING-NEXT:    vle8.v v9, (a1)
; FOLDING-NEXT:    vle8.v v10, (a2)
; FOLDING-NEXT:    vwmulu.vv v11, v8, v9
; FOLDING-NEXT:    vwaddu.vv v9, v8, v10
; FOLDING-NEXT:    vwsubu.vv v12, v8, v10
; FOLDING-NEXT:    vsetvli zero, zero, e16, mf2, ta, ma
; FOLDING-NEXT:    vor.vv v8, v11, v9
; FOLDING-NEXT:    vor.vv v8, v8, v12
; FOLDING-NEXT:    ret
  %a = load <vscale x 2 x i8>, ptr %x
  %b = load <vscale x 2 x i8>, ptr %y
  %b2 = load <vscale x 2 x i8>, ptr %z
  %c = zext <vscale x 2 x i8> %a to <vscale x 2 x i16>
  %d = zext <vscale x 2 x i8> %b to <vscale x 2 x i16>
  %d2 = zext <vscale x 2 x i8> %b2 to <vscale x 2 x i16>
  %e = mul <vscale x 2 x i16> %c, %d
  %f = add <vscale x 2 x i16> %c, %d2
  %g = sub <vscale x 2 x i16> %c, %d2
  %h = or <vscale x 2 x i16> %e, %f
  %i = or <vscale x 2 x i16> %h, %g
  ret <vscale x 2 x i16> %i
}

define <vscale x 2 x i32> @vwop_vscale_zext_i16i32_multiple_users(ptr %x, ptr %y, ptr %z) {
; NO_FOLDING-LABEL: vwop_vscale_zext_i16i32_multiple_users:
; NO_FOLDING:       # %bb.0:
; NO_FOLDING-NEXT:    vsetvli a3, zero, e32, m1, ta, ma
; NO_FOLDING-NEXT:    vle16.v v8, (a0)
; NO_FOLDING-NEXT:    vle16.v v9, (a1)
; NO_FOLDING-NEXT:    vle16.v v10, (a2)
; NO_FOLDING-NEXT:    vzext.vf2 v11, v8
; NO_FOLDING-NEXT:    vzext.vf2 v8, v9
; NO_FOLDING-NEXT:    vzext.vf2 v9, v10
; NO_FOLDING-NEXT:    vmul.vv v8, v11, v8
; NO_FOLDING-NEXT:    vadd.vv v10, v11, v9
; NO_FOLDING-NEXT:    vsub.vv v9, v11, v9
; NO_FOLDING-NEXT:    vor.vv v8, v8, v10
; NO_FOLDING-NEXT:    vor.vv v8, v8, v9
; NO_FOLDING-NEXT:    ret
;
; FOLDING-LABEL: vwop_vscale_zext_i16i32_multiple_users:
; FOLDING:       # %bb.0:
; FOLDING-NEXT:    vsetvli a3, zero, e16, mf2, ta, ma
; FOLDING-NEXT:    vle16.v v8, (a0)
; FOLDING-NEXT:    vle16.v v9, (a1)
; FOLDING-NEXT:    vle16.v v10, (a2)
; FOLDING-NEXT:    vwmulu.vv v11, v8, v9
; FOLDING-NEXT:    vwaddu.vv v9, v8, v10
; FOLDING-NEXT:    vwsubu.vv v12, v8, v10
; FOLDING-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
; FOLDING-NEXT:    vor.vv v8, v11, v9
; FOLDING-NEXT:    vor.vv v8, v8, v12
; FOLDING-NEXT:    ret
  %a = load <vscale x 2 x i16>, ptr %x
  %b = load <vscale x 2 x i16>, ptr %y
  %b2 = load <vscale x 2 x i16>, ptr %z
  %c = zext <vscale x 2 x i16> %a to <vscale x 2 x i32>
  %d = zext <vscale x 2 x i16> %b to <vscale x 2 x i32>
  %d2 = zext <vscale x 2 x i16> %b2 to <vscale x 2 x i32>
  %e = mul <vscale x 2 x i32> %c, %d
  %f = add <vscale x 2 x i32> %c, %d2
  %g = sub <vscale x 2 x i32> %c, %d2
  %h = or <vscale x 2 x i32> %e, %f
  %i = or <vscale x 2 x i32> %h, %g
  ret <vscale x 2 x i32> %i
}

define <vscale x 2 x i64> @vwop_vscale_zext_i32i64_multiple_users(ptr %x, ptr %y, ptr %z) {
; NO_FOLDING-LABEL: vwop_vscale_zext_i32i64_multiple_users:
; NO_FOLDING:       # %bb.0:
; NO_FOLDING-NEXT:    vl1re32.v v10, (a0)
; NO_FOLDING-NEXT:    vl1re32.v v12, (a1)
; NO_FOLDING-NEXT:    vl1re32.v v14, (a2)
; NO_FOLDING-NEXT:    vsetvli a0, zero, e64, m2, ta, ma
; NO_FOLDING-NEXT:    vzext.vf2 v8, v10
; NO_FOLDING-NEXT:    vzext.vf2 v10, v12
; NO_FOLDING-NEXT:    vzext.vf2 v12, v14
; NO_FOLDING-NEXT:    vmul.vv v10, v8, v10
; NO_FOLDING-NEXT:    vadd.vv v14, v8, v12
; NO_FOLDING-NEXT:    vsub.vv v8, v8, v12
; NO_FOLDING-NEXT:    vor.vv v10, v10, v14
; NO_FOLDING-NEXT:    vor.vv v8, v10, v8
; NO_FOLDING-NEXT:    ret
;
; FOLDING-LABEL: vwop_vscale_zext_i32i64_multiple_users:
; FOLDING:       # %bb.0:
; FOLDING-NEXT:    vl1re32.v v14, (a0)
; FOLDING-NEXT:    vl1re32.v v10, (a1)
; FOLDING-NEXT:    vl1re32.v v15, (a2)
; FOLDING-NEXT:    vsetvli a0, zero, e32, m1, ta, ma
; FOLDING-NEXT:    vwmulu.vv v8, v14, v10
; FOLDING-NEXT:    vwaddu.vv v10, v14, v15
; FOLDING-NEXT:    vwsubu.vv v12, v14, v15
; FOLDING-NEXT:    vsetvli zero, zero, e64, m2, ta, ma
; FOLDING-NEXT:    vor.vv v8, v8, v10
; FOLDING-NEXT:    vor.vv v8, v8, v12
; FOLDING-NEXT:    ret
  %a = load <vscale x 2 x i32>, ptr %x
  %b = load <vscale x 2 x i32>, ptr %y
  %b2 = load <vscale x 2 x i32>, ptr %z
  %c = zext <vscale x 2 x i32> %a to <vscale x 2 x i64>
  %d = zext <vscale x 2 x i32> %b to <vscale x 2 x i64>
  %d2 = zext <vscale x 2 x i32> %b2 to <vscale x 2 x i64>
  %e = mul <vscale x 2 x i64> %c, %d
  %f = add <vscale x 2 x i64> %c, %d2
  %g = sub <vscale x 2 x i64> %c, %d2
  %h = or <vscale x 2 x i64> %e, %f
  %i = or <vscale x 2 x i64> %h, %g
  ret <vscale x 2 x i64> %i
}

define <vscale x 2 x i32> @vwop_vscale_zext_i1i32_multiple_users(ptr %x, ptr %y, ptr %z) {
; NO_FOLDING-LABEL: vwop_vscale_zext_i1i32_multiple_users:
; NO_FOLDING:       # %bb.0:
; NO_FOLDING-NEXT:    vsetvli a3, zero, e32, m1, ta, mu
; NO_FOLDING-NEXT:    vlm.v v0, (a0)
; NO_FOLDING-NEXT:    vlm.v v8, (a2)
; NO_FOLDING-NEXT:    vlm.v v9, (a1)
; NO_FOLDING-NEXT:    vmv.v.i v10, 0
; NO_FOLDING-NEXT:    vmerge.vim v11, v10, 1, v0
; NO_FOLDING-NEXT:    vmv.v.v v0, v8
; NO_FOLDING-NEXT:    vmerge.vim v8, v10, 1, v0
; NO_FOLDING-NEXT:    vadd.vv v10, v11, v8
; NO_FOLDING-NEXT:    vsub.vv v8, v11, v8
; NO_FOLDING-NEXT:    vmv.v.v v0, v9
; NO_FOLDING-NEXT:    vor.vv v10, v10, v11, v0.t
; NO_FOLDING-NEXT:    vor.vv v8, v10, v8
; NO_FOLDING-NEXT:    ret
;
; FOLDING-LABEL: vwop_vscale_zext_i1i32_multiple_users:
; FOLDING:       # %bb.0:
; FOLDING-NEXT:    vsetvli a3, zero, e32, m1, ta, mu
; FOLDING-NEXT:    vlm.v v0, (a0)
; FOLDING-NEXT:    vlm.v v8, (a2)
; FOLDING-NEXT:    vlm.v v9, (a1)
; FOLDING-NEXT:    vmv.v.i v10, 0
; FOLDING-NEXT:    vmerge.vim v11, v10, 1, v0
; FOLDING-NEXT:    vmv.v.v v0, v8
; FOLDING-NEXT:    vmerge.vim v8, v10, 1, v0
; FOLDING-NEXT:    vadd.vv v10, v11, v8
; FOLDING-NEXT:    vsub.vv v8, v11, v8
; FOLDING-NEXT:    vmv.v.v v0, v9
; FOLDING-NEXT:    vor.vv v10, v10, v11, v0.t
; FOLDING-NEXT:    vor.vv v8, v10, v8
; FOLDING-NEXT:    ret
  %a = load <vscale x 2 x i1>, ptr %x
  %b = load <vscale x 2 x i1>, ptr %y
  %b2 = load <vscale x 2 x i1>, ptr %z
  %c = zext <vscale x 2 x i1> %a to <vscale x 2 x i32>
  %d = zext <vscale x 2 x i1> %b to <vscale x 2 x i32>
  %d2 = zext <vscale x 2 x i1> %b2 to <vscale x 2 x i32>
  %e = mul <vscale x 2 x i32> %c, %d
  %f = add <vscale x 2 x i32> %c, %d2
  %g = sub <vscale x 2 x i32> %c, %d2
  %h = or <vscale x 2 x i32> %e, %f
  %i = or <vscale x 2 x i32> %h, %g
  ret <vscale x 2 x i32> %i
}

define <vscale x 2 x i8> @vwop_vscale_zext_i1i8_multiple_users(ptr %x, ptr %y, ptr %z) {
; NO_FOLDING-LABEL: vwop_vscale_zext_i1i8_multiple_users:
; NO_FOLDING:       # %bb.0:
; NO_FOLDING-NEXT:    vsetvli a3, zero, e8, mf4, ta, mu
; NO_FOLDING-NEXT:    vlm.v v0, (a0)
; NO_FOLDING-NEXT:    vlm.v v8, (a2)
; NO_FOLDING-NEXT:    vlm.v v9, (a1)
; NO_FOLDING-NEXT:    vmv.v.i v10, 0
; NO_FOLDING-NEXT:    vmerge.vim v11, v10, 1, v0
; NO_FOLDING-NEXT:    vmv1r.v v0, v8
; NO_FOLDING-NEXT:    vmerge.vim v8, v10, 1, v0
; NO_FOLDING-NEXT:    vadd.vv v10, v11, v8
; NO_FOLDING-NEXT:    vsub.vv v8, v11, v8
; NO_FOLDING-NEXT:    vmv1r.v v0, v9
; NO_FOLDING-NEXT:    vor.vv v10, v10, v11, v0.t
; NO_FOLDING-NEXT:    vor.vv v8, v10, v8
; NO_FOLDING-NEXT:    ret
;
; FOLDING-LABEL: vwop_vscale_zext_i1i8_multiple_users:
; FOLDING:       # %bb.0:
; FOLDING-NEXT:    vsetvli a3, zero, e8, mf4, ta, mu
; FOLDING-NEXT:    vlm.v v0, (a0)
; FOLDING-NEXT:    vlm.v v8, (a2)
; FOLDING-NEXT:    vlm.v v9, (a1)
; FOLDING-NEXT:    vmv.v.i v10, 0
; FOLDING-NEXT:    vmerge.vim v11, v10, 1, v0
; FOLDING-NEXT:    vmv1r.v v0, v8
; FOLDING-NEXT:    vmerge.vim v8, v10, 1, v0
; FOLDING-NEXT:    vadd.vv v10, v11, v8
; FOLDING-NEXT:    vsub.vv v8, v11, v8
; FOLDING-NEXT:    vmv1r.v v0, v9
; FOLDING-NEXT:    vor.vv v10, v10, v11, v0.t
; FOLDING-NEXT:    vor.vv v8, v10, v8
; FOLDING-NEXT:    ret
  %a = load <vscale x 2 x i1>, ptr %x
  %b = load <vscale x 2 x i1>, ptr %y
  %b2 = load <vscale x 2 x i1>, ptr %z
  %c = zext <vscale x 2 x i1> %a to <vscale x 2 x i8>
  %d = zext <vscale x 2 x i1> %b to <vscale x 2 x i8>
  %d2 = zext <vscale x 2 x i1> %b2 to <vscale x 2 x i8>
  %e = mul <vscale x 2 x i8> %c, %d
  %f = add <vscale x 2 x i8> %c, %d2
  %g = sub <vscale x 2 x i8> %c, %d2
  %h = or <vscale x 2 x i8> %e, %f
  %i = or <vscale x 2 x i8> %h, %g
  ret <vscale x 2 x i8> %i
}

define <vscale x 2 x i32> @vwop_vscale_zext_i8i32_multiple_users(ptr %x, ptr %y, ptr %z) {
; NO_FOLDING-LABEL: vwop_vscale_zext_i8i32_multiple_users:
; NO_FOLDING:       # %bb.0:
; NO_FOLDING-NEXT:    vsetvli a3, zero, e32, m1, ta, ma
; NO_FOLDING-NEXT:    vle8.v v8, (a0)
; NO_FOLDING-NEXT:    vle8.v v9, (a1)
; NO_FOLDING-NEXT:    vle8.v v10, (a2)
; NO_FOLDING-NEXT:    vzext.vf4 v11, v8
; NO_FOLDING-NEXT:    vzext.vf4 v8, v9
; NO_FOLDING-NEXT:    vzext.vf4 v9, v10
; NO_FOLDING-NEXT:    vmul.vv v8, v11, v8
; NO_FOLDING-NEXT:    vadd.vv v10, v11, v9
; NO_FOLDING-NEXT:    vsub.vv v9, v11, v9
; NO_FOLDING-NEXT:    vor.vv v8, v8, v10
; NO_FOLDING-NEXT:    vor.vv v8, v8, v9
; NO_FOLDING-NEXT:    ret
;
; FOLDING-LABEL: vwop_vscale_zext_i8i32_multiple_users:
; FOLDING:       # %bb.0:
; FOLDING-NEXT:    vsetvli a3, zero, e16, mf2, ta, ma
; FOLDING-NEXT:    vle8.v v8, (a0)
; FOLDING-NEXT:    vle8.v v9, (a1)
; FOLDING-NEXT:    vle8.v v10, (a2)
; FOLDING-NEXT:    vzext.vf2 v11, v8
; FOLDING-NEXT:    vzext.vf2 v8, v9
; FOLDING-NEXT:    vzext.vf2 v9, v10
; FOLDING-NEXT:    vwmulu.vv v10, v11, v8
; FOLDING-NEXT:    vwaddu.vv v8, v11, v9
; FOLDING-NEXT:    vwsubu.vv v12, v11, v9
; FOLDING-NEXT:    vsetvli zero, zero, e32, m1, ta, ma
; FOLDING-NEXT:    vor.vv v8, v10, v8
; FOLDING-NEXT:    vor.vv v8, v8, v12
; FOLDING-NEXT:    ret
  %a = load <vscale x 2 x i8>, ptr %x
  %b = load <vscale x 2 x i8>, ptr %y
  %b2 = load <vscale x 2 x i8>, ptr %z
  %c = zext <vscale x 2 x i8> %a to <vscale x 2 x i32>
  %d = zext <vscale x 2 x i8> %b to <vscale x 2 x i32>
  %d2 = zext <vscale x 2 x i8> %b2 to <vscale x 2 x i32>
  %e = mul <vscale x 2 x i32> %c, %d
  %f = add <vscale x 2 x i32> %c, %d2
  %g = sub <vscale x 2 x i32> %c, %d2
  %h = or <vscale x 2 x i32> %e, %f
  %i = or <vscale x 2 x i32> %h, %g
  ret <vscale x 2 x i32> %i
}



;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; RV32: {{.*}}
; RV64: {{.*}}