; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3 ; RUN: llc < %s -mtriple=riscv32 -mattr=+v,+zvfh -verify-machineinstrs | FileCheck %s -check-prefixes=CHECK,RV32 ; RUN: llc < %s -mtriple=riscv64 -mattr=+v,+zvfh -verify-machineinstrs | FileCheck %s -check-prefixes=CHECK,RV64 define @match_nxv16i8_v1i8( %op1, <1 x i8> %op2, %mask) { ; CHECK-LABEL: match_nxv16i8_v1i8: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, ma ; CHECK-NEXT: vrgather.vi v12, v10, 0 ; CHECK-NEXT: vmseq.vv v10, v8, v12 ; CHECK-NEXT: vmand.mm v0, v10, v0 ; CHECK-NEXT: ret %r = tail call @llvm.experimental.vector.match( %op1, <1 x i8> %op2, %mask) ret %r } define @match_nxv16i8_v2i8( %op1, <2 x i8> %op2, %mask) { ; CHECK-LABEL: match_nxv16i8_v2i8: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, ma ; CHECK-NEXT: vrgather.vi v12, v10, 1 ; CHECK-NEXT: vmseq.vv v14, v8, v12 ; CHECK-NEXT: vrgather.vi v12, v10, 0 ; CHECK-NEXT: vmseq.vv v10, v8, v12 ; CHECK-NEXT: vmor.mm v8, v10, v14 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call @llvm.experimental.vector.match( %op1, <2 x i8> %op2, %mask) ret %r } define @match_nxv16i8_v4i8( %op1, <4 x i8> %op2, %mask) { ; CHECK-LABEL: match_nxv16i8_v4i8: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, ma ; CHECK-NEXT: vrgather.vi v12, v10, 1 ; CHECK-NEXT: vmseq.vv v14, v8, v12 ; CHECK-NEXT: vrgather.vi v12, v10, 0 ; CHECK-NEXT: vmseq.vv v15, v8, v12 ; CHECK-NEXT: vmor.mm v12, v15, v14 ; CHECK-NEXT: vrgather.vi v14, v10, 2 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vrgather.vi v14, v10, 3 ; CHECK-NEXT: vmor.mm v10, v12, v13 ; CHECK-NEXT: vmseq.vv v11, v8, v14 ; CHECK-NEXT: vmor.mm v8, v10, v11 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call @llvm.experimental.vector.match( %op1, <4 x i8> %op2, %mask) ret %r } define @match_nxv16i8_v8i8( %op1, <8 x i8> %op2, %mask) { ; CHECK-LABEL: match_nxv16i8_v8i8: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, ma ; CHECK-NEXT: vrgather.vi v12, v10, 1 ; CHECK-NEXT: vmseq.vv v14, v8, v12 ; CHECK-NEXT: vrgather.vi v12, v10, 0 ; CHECK-NEXT: vmseq.vv v15, v8, v12 ; CHECK-NEXT: vmor.mm v12, v15, v14 ; CHECK-NEXT: vrgather.vi v14, v10, 2 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 3 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 4 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 5 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 6 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vrgather.vi v14, v10, 7 ; CHECK-NEXT: vmor.mm v10, v12, v13 ; CHECK-NEXT: vmseq.vv v11, v8, v14 ; CHECK-NEXT: vmor.mm v8, v10, v11 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call @llvm.experimental.vector.match( %op1, <8 x i8> %op2, %mask) ret %r } define @match_nxv16i8_v16i8( %op1, <16 x i8> %op2, %mask) { ; CHECK-LABEL: match_nxv16i8_v16i8: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, ma ; CHECK-NEXT: vrgather.vi v12, v10, 1 ; CHECK-NEXT: vmseq.vv v14, v8, v12 ; CHECK-NEXT: vrgather.vi v12, v10, 0 ; CHECK-NEXT: vmseq.vv v15, v8, v12 ; CHECK-NEXT: vmor.mm v12, v15, v14 ; CHECK-NEXT: vrgather.vi v14, v10, 2 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 3 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 4 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 5 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 6 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 7 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 8 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 9 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 10 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 11 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 12 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 13 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 14 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vrgather.vi v14, v10, 15 ; CHECK-NEXT: vmor.mm v10, v12, v13 ; CHECK-NEXT: vmseq.vv v11, v8, v14 ; CHECK-NEXT: vmor.mm v8, v10, v11 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call @llvm.experimental.vector.match( %op1, <16 x i8> %op2, %mask) ret %r } define <16 x i1> @match_v16i8_v1i8(<16 x i8> %op1, <1 x i8> %op2, <16 x i1> %mask) { ; CHECK-LABEL: match_v16i8_v1i8: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli a0, zero, e8, m1, ta, ma ; CHECK-NEXT: vrgather.vi v10, v9, 0 ; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma ; CHECK-NEXT: vmseq.vv v8, v8, v10 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call <16 x i1> @llvm.experimental.vector.match(<16 x i8> %op1, <1 x i8> %op2, <16 x i1> %mask) ret <16 x i1> %r } define <16 x i1> @match_v16i8_v2i8(<16 x i8> %op1, <2 x i8> %op2, <16 x i1> %mask) { ; CHECK-LABEL: match_v16i8_v2i8: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma ; CHECK-NEXT: vrgather.vi v10, v9, 1 ; CHECK-NEXT: vrgather.vi v11, v9, 0 ; CHECK-NEXT: vmseq.vv v9, v8, v10 ; CHECK-NEXT: vmseq.vv v8, v8, v11 ; CHECK-NEXT: vmor.mm v8, v8, v9 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call <16 x i1> @llvm.experimental.vector.match(<16 x i8> %op1, <2 x i8> %op2, <16 x i1> %mask) ret <16 x i1> %r } define <16 x i1> @match_v16i8_v4i8(<16 x i8> %op1, <4 x i8> %op2, <16 x i1> %mask) { ; CHECK-LABEL: match_v16i8_v4i8: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma ; CHECK-NEXT: vrgather.vi v10, v9, 1 ; CHECK-NEXT: vrgather.vi v11, v9, 0 ; CHECK-NEXT: vmseq.vv v10, v8, v10 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v11, v10 ; CHECK-NEXT: vrgather.vi v11, v9, 2 ; CHECK-NEXT: vrgather.vi v12, v9, 3 ; CHECK-NEXT: vmseq.vv v9, v8, v11 ; CHECK-NEXT: vmor.mm v9, v10, v9 ; CHECK-NEXT: vmseq.vv v8, v8, v12 ; CHECK-NEXT: vmor.mm v8, v9, v8 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call <16 x i1> @llvm.experimental.vector.match(<16 x i8> %op1, <4 x i8> %op2, <16 x i1> %mask) ret <16 x i1> %r } define <16 x i1> @match_v16i8_v8i8(<16 x i8> %op1, <8 x i8> %op2, <16 x i1> %mask) { ; CHECK-LABEL: match_v16i8_v8i8: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma ; CHECK-NEXT: vrgather.vi v10, v9, 1 ; CHECK-NEXT: vrgather.vi v11, v9, 0 ; CHECK-NEXT: vmseq.vv v10, v8, v10 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v11, v10 ; CHECK-NEXT: vrgather.vi v11, v9, 2 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 3 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 4 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 5 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 6 ; CHECK-NEXT: vrgather.vi v12, v9, 7 ; CHECK-NEXT: vmseq.vv v9, v8, v11 ; CHECK-NEXT: vmor.mm v9, v10, v9 ; CHECK-NEXT: vmseq.vv v8, v8, v12 ; CHECK-NEXT: vmor.mm v8, v9, v8 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call <16 x i1> @llvm.experimental.vector.match(<16 x i8> %op1, <8 x i8> %op2, <16 x i1> %mask) ret <16 x i1> %r } define <16 x i1> @match_v16i8_v16i8(<16 x i8> %op1, <16 x i8> %op2, <16 x i1> %mask) { ; CHECK-LABEL: match_v16i8_v16i8: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, ma ; CHECK-NEXT: vrgather.vi v10, v9, 1 ; CHECK-NEXT: vrgather.vi v11, v9, 0 ; CHECK-NEXT: vmseq.vv v10, v8, v10 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v11, v10 ; CHECK-NEXT: vrgather.vi v11, v9, 2 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 3 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 4 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 5 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 6 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 7 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 8 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 9 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 10 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 11 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 12 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 13 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 14 ; CHECK-NEXT: vrgather.vi v12, v9, 15 ; CHECK-NEXT: vmseq.vv v9, v8, v11 ; CHECK-NEXT: vmor.mm v9, v10, v9 ; CHECK-NEXT: vmseq.vv v8, v8, v12 ; CHECK-NEXT: vmor.mm v8, v9, v8 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call <16 x i1> @llvm.experimental.vector.match(<16 x i8> %op1, <16 x i8> %op2, <16 x i1> %mask) ret <16 x i1> %r } define <8 x i1> @match_v8i8_v8i8(<8 x i8> %op1, <8 x i8> %op2, <8 x i1> %mask) { ; CHECK-LABEL: match_v8i8_v8i8: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma ; CHECK-NEXT: vrgather.vi v10, v9, 1 ; CHECK-NEXT: vrgather.vi v11, v9, 0 ; CHECK-NEXT: vmseq.vv v10, v8, v10 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v11, v10 ; CHECK-NEXT: vrgather.vi v11, v9, 2 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 3 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 4 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 5 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 6 ; CHECK-NEXT: vrgather.vi v12, v9, 7 ; CHECK-NEXT: vmseq.vv v9, v8, v11 ; CHECK-NEXT: vmor.mm v9, v10, v9 ; CHECK-NEXT: vmseq.vv v8, v8, v12 ; CHECK-NEXT: vmor.mm v8, v9, v8 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call <8 x i1> @llvm.experimental.vector.match(<8 x i8> %op1, <8 x i8> %op2, <8 x i1> %mask) ret <8 x i1> %r } define @match_nxv8i16_v8i16( %op1, <8 x i16> %op2, %mask) { ; CHECK-LABEL: match_nxv8i16_v8i16: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli a0, zero, e16, m2, ta, ma ; CHECK-NEXT: vrgather.vi v12, v10, 1 ; CHECK-NEXT: vmseq.vv v14, v8, v12 ; CHECK-NEXT: vrgather.vi v12, v10, 0 ; CHECK-NEXT: vmseq.vv v15, v8, v12 ; CHECK-NEXT: vmor.mm v12, v15, v14 ; CHECK-NEXT: vrgather.vi v14, v10, 2 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 3 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 4 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 5 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vmor.mm v12, v12, v13 ; CHECK-NEXT: vrgather.vi v14, v10, 6 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vrgather.vi v14, v10, 7 ; CHECK-NEXT: vmor.mm v10, v12, v13 ; CHECK-NEXT: vmseq.vv v11, v8, v14 ; CHECK-NEXT: vmor.mm v8, v10, v11 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call @llvm.experimental.vector.match( %op1, <8 x i16> %op2, %mask) ret %r } define <8 x i1> @match_v8i16(<8 x i16> %op1, <8 x i16> %op2, <8 x i1> %mask) { ; CHECK-LABEL: match_v8i16: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, ma ; CHECK-NEXT: vrgather.vi v10, v9, 1 ; CHECK-NEXT: vrgather.vi v11, v9, 0 ; CHECK-NEXT: vmseq.vv v10, v8, v10 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v11, v10 ; CHECK-NEXT: vrgather.vi v11, v9, 2 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 3 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 4 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 5 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vrgather.vi v11, v9, 6 ; CHECK-NEXT: vrgather.vi v12, v9, 7 ; CHECK-NEXT: vmseq.vv v9, v8, v11 ; CHECK-NEXT: vmor.mm v9, v10, v9 ; CHECK-NEXT: vmseq.vv v8, v8, v12 ; CHECK-NEXT: vmor.mm v8, v9, v8 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call <8 x i1> @llvm.experimental.vector.match(<8 x i16> %op1, <8 x i16> %op2, <8 x i1> %mask) ret <8 x i1> %r } ; Cases where op2 has more elements than op1. define <8 x i1> @match_v8i8_v16i8(<8 x i8> %op1, <16 x i8> %op2, <8 x i1> %mask) { ; CHECK-LABEL: match_v8i8_v16i8: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, ma ; CHECK-NEXT: vmv.x.s a0, v9 ; CHECK-NEXT: vslidedown.vi v10, v9, 1 ; CHECK-NEXT: vslidedown.vi v11, v9, 2 ; CHECK-NEXT: vmv.x.s a1, v10 ; CHECK-NEXT: vslidedown.vi v10, v9, 3 ; CHECK-NEXT: vmv.x.s a2, v11 ; CHECK-NEXT: vslidedown.vi v11, v9, 4 ; CHECK-NEXT: vmv.x.s a3, v10 ; CHECK-NEXT: vslidedown.vi v10, v9, 5 ; CHECK-NEXT: vmv.x.s a4, v11 ; CHECK-NEXT: vslidedown.vi v11, v9, 6 ; CHECK-NEXT: vmv.x.s a5, v10 ; CHECK-NEXT: vslidedown.vi v10, v9, 7 ; CHECK-NEXT: vmv.x.s a6, v11 ; CHECK-NEXT: vslidedown.vi v11, v9, 8 ; CHECK-NEXT: vmv.x.s a7, v10 ; CHECK-NEXT: vslidedown.vi v10, v9, 9 ; CHECK-NEXT: vmv.x.s t0, v11 ; CHECK-NEXT: vslidedown.vi v11, v9, 10 ; CHECK-NEXT: vmv.x.s t1, v10 ; CHECK-NEXT: vslidedown.vi v10, v9, 11 ; CHECK-NEXT: vmv.x.s t2, v11 ; CHECK-NEXT: vslidedown.vi v11, v9, 12 ; CHECK-NEXT: vmv.x.s t3, v10 ; CHECK-NEXT: vslidedown.vi v10, v9, 13 ; CHECK-NEXT: vmv.x.s t4, v11 ; CHECK-NEXT: vslidedown.vi v11, v9, 14 ; CHECK-NEXT: vslidedown.vi v9, v9, 15 ; CHECK-NEXT: vmv.x.s t5, v10 ; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, ma ; CHECK-NEXT: vmseq.vx v10, v8, a0 ; CHECK-NEXT: vmv.x.s a0, v11 ; CHECK-NEXT: vmseq.vx v11, v8, a1 ; CHECK-NEXT: vmv.x.s a1, v9 ; CHECK-NEXT: vmseq.vx v9, v8, a2 ; CHECK-NEXT: vmor.mm v10, v10, v11 ; CHECK-NEXT: vmseq.vx v11, v8, a3 ; CHECK-NEXT: vmor.mm v9, v10, v9 ; CHECK-NEXT: vmseq.vx v10, v8, a4 ; CHECK-NEXT: vmor.mm v9, v9, v11 ; CHECK-NEXT: vmseq.vx v11, v8, a5 ; CHECK-NEXT: vmor.mm v9, v9, v10 ; CHECK-NEXT: vmseq.vx v10, v8, a6 ; CHECK-NEXT: vmor.mm v9, v9, v11 ; CHECK-NEXT: vmseq.vx v11, v8, a7 ; CHECK-NEXT: vmor.mm v9, v9, v10 ; CHECK-NEXT: vmseq.vx v10, v8, t0 ; CHECK-NEXT: vmor.mm v9, v9, v11 ; CHECK-NEXT: vmseq.vx v11, v8, t1 ; CHECK-NEXT: vmor.mm v9, v9, v10 ; CHECK-NEXT: vmseq.vx v10, v8, t2 ; CHECK-NEXT: vmor.mm v9, v9, v11 ; CHECK-NEXT: vmseq.vx v11, v8, t3 ; CHECK-NEXT: vmor.mm v9, v9, v10 ; CHECK-NEXT: vmseq.vx v10, v8, t4 ; CHECK-NEXT: vmor.mm v9, v9, v11 ; CHECK-NEXT: vmseq.vx v11, v8, t5 ; CHECK-NEXT: vmor.mm v9, v9, v10 ; CHECK-NEXT: vmseq.vx v10, v8, a0 ; CHECK-NEXT: vmor.mm v9, v9, v11 ; CHECK-NEXT: vmor.mm v9, v9, v10 ; CHECK-NEXT: vmseq.vx v8, v8, a1 ; CHECK-NEXT: vmor.mm v8, v9, v8 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call <8 x i1> @llvm.experimental.vector.match(<8 x i8> %op1, <16 x i8> %op2, <8 x i1> %mask) ret <8 x i1> %r } define @match_nxv16i8_v32i8( %op1, <32 x i8> %op2, %mask) { ; RV32-LABEL: match_nxv16i8_v32i8: ; RV32: # %bb.0: ; RV32-NEXT: addi sp, sp, -64 ; RV32-NEXT: .cfi_def_cfa_offset 64 ; RV32-NEXT: sw ra, 60(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s0, 56(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s1, 52(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s2, 48(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s3, 44(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s4, 40(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s5, 36(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s6, 32(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s7, 28(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s8, 24(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s9, 20(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s10, 16(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s11, 12(sp) # 4-byte Folded Spill ; RV32-NEXT: .cfi_offset ra, -4 ; RV32-NEXT: .cfi_offset s0, -8 ; RV32-NEXT: .cfi_offset s1, -12 ; RV32-NEXT: .cfi_offset s2, -16 ; RV32-NEXT: .cfi_offset s3, -20 ; RV32-NEXT: .cfi_offset s4, -24 ; RV32-NEXT: .cfi_offset s5, -28 ; RV32-NEXT: .cfi_offset s6, -32 ; RV32-NEXT: .cfi_offset s7, -36 ; RV32-NEXT: .cfi_offset s8, -40 ; RV32-NEXT: .cfi_offset s9, -44 ; RV32-NEXT: .cfi_offset s10, -48 ; RV32-NEXT: .cfi_offset s11, -52 ; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma ; RV32-NEXT: vmv.x.s a0, v10 ; RV32-NEXT: sw a0, 8(sp) # 4-byte Folded Spill ; RV32-NEXT: vslidedown.vi v12, v10, 1 ; RV32-NEXT: vslidedown.vi v13, v10, 2 ; RV32-NEXT: vslidedown.vi v14, v10, 3 ; RV32-NEXT: vslidedown.vi v15, v10, 4 ; RV32-NEXT: vslidedown.vi v16, v10, 5 ; RV32-NEXT: vslidedown.vi v17, v10, 6 ; RV32-NEXT: vslidedown.vi v18, v10, 7 ; RV32-NEXT: vslidedown.vi v19, v10, 8 ; RV32-NEXT: vslidedown.vi v20, v10, 9 ; RV32-NEXT: vslidedown.vi v21, v10, 10 ; RV32-NEXT: vslidedown.vi v22, v10, 11 ; RV32-NEXT: vslidedown.vi v23, v10, 12 ; RV32-NEXT: vsetivli zero, 1, e8, m2, ta, ma ; RV32-NEXT: vslidedown.vi v24, v10, 16 ; RV32-NEXT: vmv.x.s a1, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 17 ; RV32-NEXT: vmv.x.s a2, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 18 ; RV32-NEXT: vmv.x.s a3, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 19 ; RV32-NEXT: vmv.x.s a4, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 20 ; RV32-NEXT: vmv.x.s a5, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 21 ; RV32-NEXT: vmv.x.s a6, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 22 ; RV32-NEXT: vmv.x.s a7, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 23 ; RV32-NEXT: vmv.x.s t0, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 24 ; RV32-NEXT: vmv.x.s t1, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 25 ; RV32-NEXT: vmv.x.s t2, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 26 ; RV32-NEXT: vmv.x.s t3, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 27 ; RV32-NEXT: vmv.x.s t4, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 28 ; RV32-NEXT: vmv.x.s t5, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 29 ; RV32-NEXT: vmv.x.s t6, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 30 ; RV32-NEXT: vmv.x.s s0, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 31 ; RV32-NEXT: vmv.x.s s1, v24 ; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma ; RV32-NEXT: vslidedown.vi v11, v10, 13 ; RV32-NEXT: vslidedown.vi v24, v10, 14 ; RV32-NEXT: vslidedown.vi v10, v10, 15 ; RV32-NEXT: vmv.x.s s2, v12 ; RV32-NEXT: vmv.x.s s3, v13 ; RV32-NEXT: vmv.x.s s4, v14 ; RV32-NEXT: vmv.x.s s5, v15 ; RV32-NEXT: vmv.x.s s6, v16 ; RV32-NEXT: vmv.x.s s7, v17 ; RV32-NEXT: vmv.x.s s8, v18 ; RV32-NEXT: vmv.x.s s9, v19 ; RV32-NEXT: vmv.x.s s10, v20 ; RV32-NEXT: vmv.x.s s11, v21 ; RV32-NEXT: vmv.x.s ra, v22 ; RV32-NEXT: vsetvli a0, zero, e8, m2, ta, ma ; RV32-NEXT: lw a0, 8(sp) # 4-byte Folded Reload ; RV32-NEXT: vmseq.vx v12, v8, a0 ; RV32-NEXT: vmv.x.s a0, v23 ; RV32-NEXT: vmseq.vx v13, v8, s2 ; RV32-NEXT: vmv.x.s s2, v11 ; RV32-NEXT: vmseq.vx v11, v8, s3 ; RV32-NEXT: vmv.x.s s3, v24 ; RV32-NEXT: vmseq.vx v14, v8, s4 ; RV32-NEXT: vmv.x.s s4, v10 ; RV32-NEXT: vmseq.vx v10, v8, s5 ; RV32-NEXT: vmor.mm v12, v12, v13 ; RV32-NEXT: vmseq.vx v13, v8, s6 ; RV32-NEXT: vmor.mm v11, v12, v11 ; RV32-NEXT: vmseq.vx v12, v8, s7 ; RV32-NEXT: vmor.mm v11, v11, v14 ; RV32-NEXT: vmseq.vx v14, v8, s8 ; RV32-NEXT: vmor.mm v10, v11, v10 ; RV32-NEXT: vmseq.vx v11, v8, s9 ; RV32-NEXT: vmor.mm v10, v10, v13 ; RV32-NEXT: vmseq.vx v13, v8, s10 ; RV32-NEXT: vmor.mm v10, v10, v12 ; RV32-NEXT: vmseq.vx v12, v8, s11 ; RV32-NEXT: vmor.mm v10, v10, v14 ; RV32-NEXT: vmseq.vx v14, v8, ra ; RV32-NEXT: vmor.mm v10, v10, v11 ; RV32-NEXT: vmseq.vx v11, v8, a0 ; RV32-NEXT: vmor.mm v10, v10, v13 ; RV32-NEXT: vmseq.vx v13, v8, s2 ; RV32-NEXT: vmor.mm v10, v10, v12 ; RV32-NEXT: vmseq.vx v12, v8, s3 ; RV32-NEXT: vmor.mm v10, v10, v14 ; RV32-NEXT: vmseq.vx v14, v8, s4 ; RV32-NEXT: vmor.mm v10, v10, v11 ; RV32-NEXT: vmseq.vx v11, v8, a1 ; RV32-NEXT: vmor.mm v10, v10, v13 ; RV32-NEXT: vmseq.vx v13, v8, a2 ; RV32-NEXT: vmor.mm v10, v10, v12 ; RV32-NEXT: vmseq.vx v12, v8, a3 ; RV32-NEXT: vmor.mm v10, v10, v14 ; RV32-NEXT: vmseq.vx v14, v8, a4 ; RV32-NEXT: vmor.mm v10, v10, v11 ; RV32-NEXT: vmseq.vx v11, v8, a5 ; RV32-NEXT: vmor.mm v10, v10, v13 ; RV32-NEXT: vmseq.vx v13, v8, a6 ; RV32-NEXT: vmor.mm v10, v10, v12 ; RV32-NEXT: vmseq.vx v12, v8, a7 ; RV32-NEXT: vmor.mm v10, v10, v14 ; RV32-NEXT: vmseq.vx v14, v8, t0 ; RV32-NEXT: vmor.mm v10, v10, v11 ; RV32-NEXT: vmseq.vx v11, v8, t1 ; RV32-NEXT: vmor.mm v10, v10, v13 ; RV32-NEXT: vmseq.vx v13, v8, t2 ; RV32-NEXT: vmor.mm v10, v10, v12 ; RV32-NEXT: vmseq.vx v12, v8, t3 ; RV32-NEXT: vmor.mm v10, v10, v14 ; RV32-NEXT: vmseq.vx v14, v8, t4 ; RV32-NEXT: vmor.mm v10, v10, v11 ; RV32-NEXT: vmseq.vx v11, v8, t5 ; RV32-NEXT: vmor.mm v10, v10, v13 ; RV32-NEXT: vmseq.vx v13, v8, t6 ; RV32-NEXT: vmor.mm v10, v10, v12 ; RV32-NEXT: vmseq.vx v12, v8, s0 ; RV32-NEXT: vmor.mm v10, v10, v14 ; RV32-NEXT: vmor.mm v10, v10, v11 ; RV32-NEXT: vmor.mm v10, v10, v13 ; RV32-NEXT: vmor.mm v10, v10, v12 ; RV32-NEXT: vmseq.vx v11, v8, s1 ; RV32-NEXT: vmor.mm v8, v10, v11 ; RV32-NEXT: vmand.mm v0, v8, v0 ; RV32-NEXT: lw ra, 60(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s0, 56(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s1, 52(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s2, 48(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s3, 44(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s4, 40(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s5, 36(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s6, 32(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s7, 28(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s8, 24(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s9, 20(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s10, 16(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s11, 12(sp) # 4-byte Folded Reload ; RV32-NEXT: .cfi_restore ra ; RV32-NEXT: .cfi_restore s0 ; RV32-NEXT: .cfi_restore s1 ; RV32-NEXT: .cfi_restore s2 ; RV32-NEXT: .cfi_restore s3 ; RV32-NEXT: .cfi_restore s4 ; RV32-NEXT: .cfi_restore s5 ; RV32-NEXT: .cfi_restore s6 ; RV32-NEXT: .cfi_restore s7 ; RV32-NEXT: .cfi_restore s8 ; RV32-NEXT: .cfi_restore s9 ; RV32-NEXT: .cfi_restore s10 ; RV32-NEXT: .cfi_restore s11 ; RV32-NEXT: addi sp, sp, 64 ; RV32-NEXT: .cfi_def_cfa_offset 0 ; RV32-NEXT: ret ; ; RV64-LABEL: match_nxv16i8_v32i8: ; RV64: # %bb.0: ; RV64-NEXT: addi sp, sp, -112 ; RV64-NEXT: .cfi_def_cfa_offset 112 ; RV64-NEXT: sd ra, 104(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s0, 96(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s1, 88(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s2, 80(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s3, 72(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s4, 64(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s5, 56(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s6, 48(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s7, 40(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s8, 32(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s9, 24(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s10, 16(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s11, 8(sp) # 8-byte Folded Spill ; RV64-NEXT: .cfi_offset ra, -8 ; RV64-NEXT: .cfi_offset s0, -16 ; RV64-NEXT: .cfi_offset s1, -24 ; RV64-NEXT: .cfi_offset s2, -32 ; RV64-NEXT: .cfi_offset s3, -40 ; RV64-NEXT: .cfi_offset s4, -48 ; RV64-NEXT: .cfi_offset s5, -56 ; RV64-NEXT: .cfi_offset s6, -64 ; RV64-NEXT: .cfi_offset s7, -72 ; RV64-NEXT: .cfi_offset s8, -80 ; RV64-NEXT: .cfi_offset s9, -88 ; RV64-NEXT: .cfi_offset s10, -96 ; RV64-NEXT: .cfi_offset s11, -104 ; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma ; RV64-NEXT: vmv.x.s a0, v10 ; RV64-NEXT: sd a0, 0(sp) # 8-byte Folded Spill ; RV64-NEXT: vslidedown.vi v12, v10, 1 ; RV64-NEXT: vslidedown.vi v13, v10, 2 ; RV64-NEXT: vslidedown.vi v14, v10, 3 ; RV64-NEXT: vslidedown.vi v15, v10, 4 ; RV64-NEXT: vslidedown.vi v16, v10, 5 ; RV64-NEXT: vslidedown.vi v17, v10, 6 ; RV64-NEXT: vslidedown.vi v18, v10, 7 ; RV64-NEXT: vslidedown.vi v19, v10, 8 ; RV64-NEXT: vslidedown.vi v20, v10, 9 ; RV64-NEXT: vslidedown.vi v21, v10, 10 ; RV64-NEXT: vslidedown.vi v22, v10, 11 ; RV64-NEXT: vslidedown.vi v23, v10, 12 ; RV64-NEXT: vsetivli zero, 1, e8, m2, ta, ma ; RV64-NEXT: vslidedown.vi v24, v10, 16 ; RV64-NEXT: vmv.x.s a1, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 17 ; RV64-NEXT: vmv.x.s a2, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 18 ; RV64-NEXT: vmv.x.s a3, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 19 ; RV64-NEXT: vmv.x.s a4, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 20 ; RV64-NEXT: vmv.x.s a5, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 21 ; RV64-NEXT: vmv.x.s a6, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 22 ; RV64-NEXT: vmv.x.s a7, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 23 ; RV64-NEXT: vmv.x.s t0, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 24 ; RV64-NEXT: vmv.x.s t1, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 25 ; RV64-NEXT: vmv.x.s t2, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 26 ; RV64-NEXT: vmv.x.s t3, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 27 ; RV64-NEXT: vmv.x.s t4, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 28 ; RV64-NEXT: vmv.x.s t5, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 29 ; RV64-NEXT: vmv.x.s t6, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 30 ; RV64-NEXT: vmv.x.s s0, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 31 ; RV64-NEXT: vmv.x.s s1, v24 ; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma ; RV64-NEXT: vslidedown.vi v11, v10, 13 ; RV64-NEXT: vslidedown.vi v24, v10, 14 ; RV64-NEXT: vslidedown.vi v10, v10, 15 ; RV64-NEXT: vmv.x.s s2, v12 ; RV64-NEXT: vmv.x.s s3, v13 ; RV64-NEXT: vmv.x.s s4, v14 ; RV64-NEXT: vmv.x.s s5, v15 ; RV64-NEXT: vmv.x.s s6, v16 ; RV64-NEXT: vmv.x.s s7, v17 ; RV64-NEXT: vmv.x.s s8, v18 ; RV64-NEXT: vmv.x.s s9, v19 ; RV64-NEXT: vmv.x.s s10, v20 ; RV64-NEXT: vmv.x.s s11, v21 ; RV64-NEXT: vmv.x.s ra, v22 ; RV64-NEXT: vsetvli a0, zero, e8, m2, ta, ma ; RV64-NEXT: ld a0, 0(sp) # 8-byte Folded Reload ; RV64-NEXT: vmseq.vx v12, v8, a0 ; RV64-NEXT: vmv.x.s a0, v23 ; RV64-NEXT: vmseq.vx v13, v8, s2 ; RV64-NEXT: vmv.x.s s2, v11 ; RV64-NEXT: vmseq.vx v11, v8, s3 ; RV64-NEXT: vmv.x.s s3, v24 ; RV64-NEXT: vmseq.vx v14, v8, s4 ; RV64-NEXT: vmv.x.s s4, v10 ; RV64-NEXT: vmseq.vx v10, v8, s5 ; RV64-NEXT: vmor.mm v12, v12, v13 ; RV64-NEXT: vmseq.vx v13, v8, s6 ; RV64-NEXT: vmor.mm v11, v12, v11 ; RV64-NEXT: vmseq.vx v12, v8, s7 ; RV64-NEXT: vmor.mm v11, v11, v14 ; RV64-NEXT: vmseq.vx v14, v8, s8 ; RV64-NEXT: vmor.mm v10, v11, v10 ; RV64-NEXT: vmseq.vx v11, v8, s9 ; RV64-NEXT: vmor.mm v10, v10, v13 ; RV64-NEXT: vmseq.vx v13, v8, s10 ; RV64-NEXT: vmor.mm v10, v10, v12 ; RV64-NEXT: vmseq.vx v12, v8, s11 ; RV64-NEXT: vmor.mm v10, v10, v14 ; RV64-NEXT: vmseq.vx v14, v8, ra ; RV64-NEXT: vmor.mm v10, v10, v11 ; RV64-NEXT: vmseq.vx v11, v8, a0 ; RV64-NEXT: vmor.mm v10, v10, v13 ; RV64-NEXT: vmseq.vx v13, v8, s2 ; RV64-NEXT: vmor.mm v10, v10, v12 ; RV64-NEXT: vmseq.vx v12, v8, s3 ; RV64-NEXT: vmor.mm v10, v10, v14 ; RV64-NEXT: vmseq.vx v14, v8, s4 ; RV64-NEXT: vmor.mm v10, v10, v11 ; RV64-NEXT: vmseq.vx v11, v8, a1 ; RV64-NEXT: vmor.mm v10, v10, v13 ; RV64-NEXT: vmseq.vx v13, v8, a2 ; RV64-NEXT: vmor.mm v10, v10, v12 ; RV64-NEXT: vmseq.vx v12, v8, a3 ; RV64-NEXT: vmor.mm v10, v10, v14 ; RV64-NEXT: vmseq.vx v14, v8, a4 ; RV64-NEXT: vmor.mm v10, v10, v11 ; RV64-NEXT: vmseq.vx v11, v8, a5 ; RV64-NEXT: vmor.mm v10, v10, v13 ; RV64-NEXT: vmseq.vx v13, v8, a6 ; RV64-NEXT: vmor.mm v10, v10, v12 ; RV64-NEXT: vmseq.vx v12, v8, a7 ; RV64-NEXT: vmor.mm v10, v10, v14 ; RV64-NEXT: vmseq.vx v14, v8, t0 ; RV64-NEXT: vmor.mm v10, v10, v11 ; RV64-NEXT: vmseq.vx v11, v8, t1 ; RV64-NEXT: vmor.mm v10, v10, v13 ; RV64-NEXT: vmseq.vx v13, v8, t2 ; RV64-NEXT: vmor.mm v10, v10, v12 ; RV64-NEXT: vmseq.vx v12, v8, t3 ; RV64-NEXT: vmor.mm v10, v10, v14 ; RV64-NEXT: vmseq.vx v14, v8, t4 ; RV64-NEXT: vmor.mm v10, v10, v11 ; RV64-NEXT: vmseq.vx v11, v8, t5 ; RV64-NEXT: vmor.mm v10, v10, v13 ; RV64-NEXT: vmseq.vx v13, v8, t6 ; RV64-NEXT: vmor.mm v10, v10, v12 ; RV64-NEXT: vmseq.vx v12, v8, s0 ; RV64-NEXT: vmor.mm v10, v10, v14 ; RV64-NEXT: vmor.mm v10, v10, v11 ; RV64-NEXT: vmor.mm v10, v10, v13 ; RV64-NEXT: vmor.mm v10, v10, v12 ; RV64-NEXT: vmseq.vx v11, v8, s1 ; RV64-NEXT: vmor.mm v8, v10, v11 ; RV64-NEXT: vmand.mm v0, v8, v0 ; RV64-NEXT: ld ra, 104(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s0, 96(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s1, 88(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s2, 80(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s3, 72(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s4, 64(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s5, 56(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s6, 48(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s7, 40(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s8, 32(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s9, 24(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s10, 16(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s11, 8(sp) # 8-byte Folded Reload ; RV64-NEXT: .cfi_restore ra ; RV64-NEXT: .cfi_restore s0 ; RV64-NEXT: .cfi_restore s1 ; RV64-NEXT: .cfi_restore s2 ; RV64-NEXT: .cfi_restore s3 ; RV64-NEXT: .cfi_restore s4 ; RV64-NEXT: .cfi_restore s5 ; RV64-NEXT: .cfi_restore s6 ; RV64-NEXT: .cfi_restore s7 ; RV64-NEXT: .cfi_restore s8 ; RV64-NEXT: .cfi_restore s9 ; RV64-NEXT: .cfi_restore s10 ; RV64-NEXT: .cfi_restore s11 ; RV64-NEXT: addi sp, sp, 112 ; RV64-NEXT: .cfi_def_cfa_offset 0 ; RV64-NEXT: ret %r = tail call @llvm.experimental.vector.match( %op1, <32 x i8> %op2, %mask) ret %r } define <16 x i1> @match_v16i8_v32i8(<16 x i8> %op1, <32 x i8> %op2, <16 x i1> %mask) { ; RV32-LABEL: match_v16i8_v32i8: ; RV32: # %bb.0: ; RV32-NEXT: addi sp, sp, -64 ; RV32-NEXT: .cfi_def_cfa_offset 64 ; RV32-NEXT: sw ra, 60(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s0, 56(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s1, 52(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s2, 48(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s3, 44(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s4, 40(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s5, 36(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s6, 32(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s7, 28(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s8, 24(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s9, 20(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s10, 16(sp) # 4-byte Folded Spill ; RV32-NEXT: sw s11, 12(sp) # 4-byte Folded Spill ; RV32-NEXT: .cfi_offset ra, -4 ; RV32-NEXT: .cfi_offset s0, -8 ; RV32-NEXT: .cfi_offset s1, -12 ; RV32-NEXT: .cfi_offset s2, -16 ; RV32-NEXT: .cfi_offset s3, -20 ; RV32-NEXT: .cfi_offset s4, -24 ; RV32-NEXT: .cfi_offset s5, -28 ; RV32-NEXT: .cfi_offset s6, -32 ; RV32-NEXT: .cfi_offset s7, -36 ; RV32-NEXT: .cfi_offset s8, -40 ; RV32-NEXT: .cfi_offset s9, -44 ; RV32-NEXT: .cfi_offset s10, -48 ; RV32-NEXT: .cfi_offset s11, -52 ; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma ; RV32-NEXT: vmv.x.s a0, v10 ; RV32-NEXT: vslidedown.vi v9, v10, 1 ; RV32-NEXT: vslidedown.vi v12, v10, 2 ; RV32-NEXT: vslidedown.vi v13, v10, 3 ; RV32-NEXT: vslidedown.vi v14, v10, 4 ; RV32-NEXT: vslidedown.vi v15, v10, 5 ; RV32-NEXT: vslidedown.vi v16, v10, 6 ; RV32-NEXT: vslidedown.vi v17, v10, 7 ; RV32-NEXT: vslidedown.vi v18, v10, 8 ; RV32-NEXT: vslidedown.vi v19, v10, 9 ; RV32-NEXT: vslidedown.vi v20, v10, 10 ; RV32-NEXT: vslidedown.vi v21, v10, 11 ; RV32-NEXT: vslidedown.vi v22, v10, 12 ; RV32-NEXT: vsetivli zero, 1, e8, m2, ta, ma ; RV32-NEXT: vslidedown.vi v24, v10, 16 ; RV32-NEXT: vmv.x.s a1, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 17 ; RV32-NEXT: vmv.x.s a2, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 18 ; RV32-NEXT: vmv.x.s a3, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 19 ; RV32-NEXT: vmv.x.s a4, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 20 ; RV32-NEXT: vmv.x.s a5, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 21 ; RV32-NEXT: vmv.x.s a6, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 22 ; RV32-NEXT: vmv.x.s a7, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 23 ; RV32-NEXT: vmv.x.s t0, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 24 ; RV32-NEXT: vmv.x.s t1, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 25 ; RV32-NEXT: vmv.x.s t2, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 26 ; RV32-NEXT: vmv.x.s t3, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 27 ; RV32-NEXT: vmv.x.s t4, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 28 ; RV32-NEXT: vmv.x.s t5, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 29 ; RV32-NEXT: vmv.x.s t6, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 30 ; RV32-NEXT: vmv.x.s s0, v24 ; RV32-NEXT: vslidedown.vi v24, v10, 31 ; RV32-NEXT: vmv.x.s s1, v24 ; RV32-NEXT: vsetivli zero, 16, e8, m1, ta, ma ; RV32-NEXT: vslidedown.vi v11, v10, 13 ; RV32-NEXT: vslidedown.vi v23, v10, 14 ; RV32-NEXT: vslidedown.vi v10, v10, 15 ; RV32-NEXT: vmv.x.s s2, v9 ; RV32-NEXT: vmv.x.s s3, v12 ; RV32-NEXT: vmv.x.s s4, v13 ; RV32-NEXT: vmv.x.s s5, v14 ; RV32-NEXT: vmv.x.s s6, v15 ; RV32-NEXT: vmv.x.s s7, v16 ; RV32-NEXT: vmv.x.s s8, v17 ; RV32-NEXT: vmv.x.s s9, v18 ; RV32-NEXT: vmv.x.s s10, v19 ; RV32-NEXT: vmv.x.s s11, v20 ; RV32-NEXT: vmv.x.s ra, v21 ; RV32-NEXT: vmseq.vx v9, v8, a0 ; RV32-NEXT: vmv.x.s a0, v22 ; RV32-NEXT: vmseq.vx v12, v8, s2 ; RV32-NEXT: vmv.x.s s2, v11 ; RV32-NEXT: vmseq.vx v11, v8, s3 ; RV32-NEXT: vmv.x.s s3, v23 ; RV32-NEXT: vmseq.vx v13, v8, s4 ; RV32-NEXT: vmv.x.s s4, v10 ; RV32-NEXT: vmseq.vx v10, v8, s5 ; RV32-NEXT: vmor.mm v9, v9, v12 ; RV32-NEXT: vmseq.vx v12, v8, s6 ; RV32-NEXT: vmor.mm v9, v9, v11 ; RV32-NEXT: vmseq.vx v11, v8, s7 ; RV32-NEXT: vmor.mm v9, v9, v13 ; RV32-NEXT: vmseq.vx v13, v8, s8 ; RV32-NEXT: vmor.mm v9, v9, v10 ; RV32-NEXT: vmseq.vx v10, v8, s9 ; RV32-NEXT: vmor.mm v9, v9, v12 ; RV32-NEXT: vmseq.vx v12, v8, s10 ; RV32-NEXT: vmor.mm v9, v9, v11 ; RV32-NEXT: vmseq.vx v11, v8, s11 ; RV32-NEXT: vmor.mm v9, v9, v13 ; RV32-NEXT: vmseq.vx v13, v8, ra ; RV32-NEXT: vmor.mm v9, v9, v10 ; RV32-NEXT: vmseq.vx v10, v8, a0 ; RV32-NEXT: vmor.mm v9, v9, v12 ; RV32-NEXT: vmseq.vx v12, v8, s2 ; RV32-NEXT: vmor.mm v9, v9, v11 ; RV32-NEXT: vmseq.vx v11, v8, s3 ; RV32-NEXT: vmor.mm v9, v9, v13 ; RV32-NEXT: vmseq.vx v13, v8, s4 ; RV32-NEXT: vmor.mm v9, v9, v10 ; RV32-NEXT: vmseq.vx v10, v8, a1 ; RV32-NEXT: vmor.mm v9, v9, v12 ; RV32-NEXT: vmseq.vx v12, v8, a2 ; RV32-NEXT: vmor.mm v9, v9, v11 ; RV32-NEXT: vmseq.vx v11, v8, a3 ; RV32-NEXT: vmor.mm v9, v9, v13 ; RV32-NEXT: vmseq.vx v13, v8, a4 ; RV32-NEXT: vmor.mm v9, v9, v10 ; RV32-NEXT: vmseq.vx v10, v8, a5 ; RV32-NEXT: vmor.mm v9, v9, v12 ; RV32-NEXT: vmseq.vx v12, v8, a6 ; RV32-NEXT: vmor.mm v9, v9, v11 ; RV32-NEXT: vmseq.vx v11, v8, a7 ; RV32-NEXT: vmor.mm v9, v9, v13 ; RV32-NEXT: vmseq.vx v13, v8, t0 ; RV32-NEXT: vmor.mm v9, v9, v10 ; RV32-NEXT: vmseq.vx v10, v8, t1 ; RV32-NEXT: vmor.mm v9, v9, v12 ; RV32-NEXT: vmseq.vx v12, v8, t2 ; RV32-NEXT: vmor.mm v9, v9, v11 ; RV32-NEXT: vmseq.vx v11, v8, t3 ; RV32-NEXT: vmor.mm v9, v9, v13 ; RV32-NEXT: vmseq.vx v13, v8, t4 ; RV32-NEXT: vmor.mm v9, v9, v10 ; RV32-NEXT: vmseq.vx v10, v8, t5 ; RV32-NEXT: vmor.mm v9, v9, v12 ; RV32-NEXT: vmseq.vx v12, v8, t6 ; RV32-NEXT: vmor.mm v9, v9, v11 ; RV32-NEXT: vmseq.vx v11, v8, s0 ; RV32-NEXT: vmor.mm v9, v9, v13 ; RV32-NEXT: vmor.mm v9, v9, v10 ; RV32-NEXT: vmor.mm v9, v9, v12 ; RV32-NEXT: vmor.mm v9, v9, v11 ; RV32-NEXT: vmseq.vx v8, v8, s1 ; RV32-NEXT: vmor.mm v8, v9, v8 ; RV32-NEXT: vmand.mm v0, v8, v0 ; RV32-NEXT: lw ra, 60(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s0, 56(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s1, 52(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s2, 48(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s3, 44(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s4, 40(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s5, 36(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s6, 32(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s7, 28(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s8, 24(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s9, 20(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s10, 16(sp) # 4-byte Folded Reload ; RV32-NEXT: lw s11, 12(sp) # 4-byte Folded Reload ; RV32-NEXT: .cfi_restore ra ; RV32-NEXT: .cfi_restore s0 ; RV32-NEXT: .cfi_restore s1 ; RV32-NEXT: .cfi_restore s2 ; RV32-NEXT: .cfi_restore s3 ; RV32-NEXT: .cfi_restore s4 ; RV32-NEXT: .cfi_restore s5 ; RV32-NEXT: .cfi_restore s6 ; RV32-NEXT: .cfi_restore s7 ; RV32-NEXT: .cfi_restore s8 ; RV32-NEXT: .cfi_restore s9 ; RV32-NEXT: .cfi_restore s10 ; RV32-NEXT: .cfi_restore s11 ; RV32-NEXT: addi sp, sp, 64 ; RV32-NEXT: .cfi_def_cfa_offset 0 ; RV32-NEXT: ret ; ; RV64-LABEL: match_v16i8_v32i8: ; RV64: # %bb.0: ; RV64-NEXT: addi sp, sp, -112 ; RV64-NEXT: .cfi_def_cfa_offset 112 ; RV64-NEXT: sd ra, 104(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s0, 96(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s1, 88(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s2, 80(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s3, 72(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s4, 64(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s5, 56(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s6, 48(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s7, 40(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s8, 32(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s9, 24(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s10, 16(sp) # 8-byte Folded Spill ; RV64-NEXT: sd s11, 8(sp) # 8-byte Folded Spill ; RV64-NEXT: .cfi_offset ra, -8 ; RV64-NEXT: .cfi_offset s0, -16 ; RV64-NEXT: .cfi_offset s1, -24 ; RV64-NEXT: .cfi_offset s2, -32 ; RV64-NEXT: .cfi_offset s3, -40 ; RV64-NEXT: .cfi_offset s4, -48 ; RV64-NEXT: .cfi_offset s5, -56 ; RV64-NEXT: .cfi_offset s6, -64 ; RV64-NEXT: .cfi_offset s7, -72 ; RV64-NEXT: .cfi_offset s8, -80 ; RV64-NEXT: .cfi_offset s9, -88 ; RV64-NEXT: .cfi_offset s10, -96 ; RV64-NEXT: .cfi_offset s11, -104 ; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma ; RV64-NEXT: vmv.x.s a0, v10 ; RV64-NEXT: vslidedown.vi v9, v10, 1 ; RV64-NEXT: vslidedown.vi v12, v10, 2 ; RV64-NEXT: vslidedown.vi v13, v10, 3 ; RV64-NEXT: vslidedown.vi v14, v10, 4 ; RV64-NEXT: vslidedown.vi v15, v10, 5 ; RV64-NEXT: vslidedown.vi v16, v10, 6 ; RV64-NEXT: vslidedown.vi v17, v10, 7 ; RV64-NEXT: vslidedown.vi v18, v10, 8 ; RV64-NEXT: vslidedown.vi v19, v10, 9 ; RV64-NEXT: vslidedown.vi v20, v10, 10 ; RV64-NEXT: vslidedown.vi v21, v10, 11 ; RV64-NEXT: vslidedown.vi v22, v10, 12 ; RV64-NEXT: vsetivli zero, 1, e8, m2, ta, ma ; RV64-NEXT: vslidedown.vi v24, v10, 16 ; RV64-NEXT: vmv.x.s a1, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 17 ; RV64-NEXT: vmv.x.s a2, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 18 ; RV64-NEXT: vmv.x.s a3, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 19 ; RV64-NEXT: vmv.x.s a4, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 20 ; RV64-NEXT: vmv.x.s a5, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 21 ; RV64-NEXT: vmv.x.s a6, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 22 ; RV64-NEXT: vmv.x.s a7, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 23 ; RV64-NEXT: vmv.x.s t0, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 24 ; RV64-NEXT: vmv.x.s t1, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 25 ; RV64-NEXT: vmv.x.s t2, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 26 ; RV64-NEXT: vmv.x.s t3, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 27 ; RV64-NEXT: vmv.x.s t4, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 28 ; RV64-NEXT: vmv.x.s t5, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 29 ; RV64-NEXT: vmv.x.s t6, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 30 ; RV64-NEXT: vmv.x.s s0, v24 ; RV64-NEXT: vslidedown.vi v24, v10, 31 ; RV64-NEXT: vmv.x.s s1, v24 ; RV64-NEXT: vsetivli zero, 16, e8, m1, ta, ma ; RV64-NEXT: vslidedown.vi v11, v10, 13 ; RV64-NEXT: vslidedown.vi v23, v10, 14 ; RV64-NEXT: vslidedown.vi v10, v10, 15 ; RV64-NEXT: vmv.x.s s2, v9 ; RV64-NEXT: vmv.x.s s3, v12 ; RV64-NEXT: vmv.x.s s4, v13 ; RV64-NEXT: vmv.x.s s5, v14 ; RV64-NEXT: vmv.x.s s6, v15 ; RV64-NEXT: vmv.x.s s7, v16 ; RV64-NEXT: vmv.x.s s8, v17 ; RV64-NEXT: vmv.x.s s9, v18 ; RV64-NEXT: vmv.x.s s10, v19 ; RV64-NEXT: vmv.x.s s11, v20 ; RV64-NEXT: vmv.x.s ra, v21 ; RV64-NEXT: vmseq.vx v9, v8, a0 ; RV64-NEXT: vmv.x.s a0, v22 ; RV64-NEXT: vmseq.vx v12, v8, s2 ; RV64-NEXT: vmv.x.s s2, v11 ; RV64-NEXT: vmseq.vx v11, v8, s3 ; RV64-NEXT: vmv.x.s s3, v23 ; RV64-NEXT: vmseq.vx v13, v8, s4 ; RV64-NEXT: vmv.x.s s4, v10 ; RV64-NEXT: vmseq.vx v10, v8, s5 ; RV64-NEXT: vmor.mm v9, v9, v12 ; RV64-NEXT: vmseq.vx v12, v8, s6 ; RV64-NEXT: vmor.mm v9, v9, v11 ; RV64-NEXT: vmseq.vx v11, v8, s7 ; RV64-NEXT: vmor.mm v9, v9, v13 ; RV64-NEXT: vmseq.vx v13, v8, s8 ; RV64-NEXT: vmor.mm v9, v9, v10 ; RV64-NEXT: vmseq.vx v10, v8, s9 ; RV64-NEXT: vmor.mm v9, v9, v12 ; RV64-NEXT: vmseq.vx v12, v8, s10 ; RV64-NEXT: vmor.mm v9, v9, v11 ; RV64-NEXT: vmseq.vx v11, v8, s11 ; RV64-NEXT: vmor.mm v9, v9, v13 ; RV64-NEXT: vmseq.vx v13, v8, ra ; RV64-NEXT: vmor.mm v9, v9, v10 ; RV64-NEXT: vmseq.vx v10, v8, a0 ; RV64-NEXT: vmor.mm v9, v9, v12 ; RV64-NEXT: vmseq.vx v12, v8, s2 ; RV64-NEXT: vmor.mm v9, v9, v11 ; RV64-NEXT: vmseq.vx v11, v8, s3 ; RV64-NEXT: vmor.mm v9, v9, v13 ; RV64-NEXT: vmseq.vx v13, v8, s4 ; RV64-NEXT: vmor.mm v9, v9, v10 ; RV64-NEXT: vmseq.vx v10, v8, a1 ; RV64-NEXT: vmor.mm v9, v9, v12 ; RV64-NEXT: vmseq.vx v12, v8, a2 ; RV64-NEXT: vmor.mm v9, v9, v11 ; RV64-NEXT: vmseq.vx v11, v8, a3 ; RV64-NEXT: vmor.mm v9, v9, v13 ; RV64-NEXT: vmseq.vx v13, v8, a4 ; RV64-NEXT: vmor.mm v9, v9, v10 ; RV64-NEXT: vmseq.vx v10, v8, a5 ; RV64-NEXT: vmor.mm v9, v9, v12 ; RV64-NEXT: vmseq.vx v12, v8, a6 ; RV64-NEXT: vmor.mm v9, v9, v11 ; RV64-NEXT: vmseq.vx v11, v8, a7 ; RV64-NEXT: vmor.mm v9, v9, v13 ; RV64-NEXT: vmseq.vx v13, v8, t0 ; RV64-NEXT: vmor.mm v9, v9, v10 ; RV64-NEXT: vmseq.vx v10, v8, t1 ; RV64-NEXT: vmor.mm v9, v9, v12 ; RV64-NEXT: vmseq.vx v12, v8, t2 ; RV64-NEXT: vmor.mm v9, v9, v11 ; RV64-NEXT: vmseq.vx v11, v8, t3 ; RV64-NEXT: vmor.mm v9, v9, v13 ; RV64-NEXT: vmseq.vx v13, v8, t4 ; RV64-NEXT: vmor.mm v9, v9, v10 ; RV64-NEXT: vmseq.vx v10, v8, t5 ; RV64-NEXT: vmor.mm v9, v9, v12 ; RV64-NEXT: vmseq.vx v12, v8, t6 ; RV64-NEXT: vmor.mm v9, v9, v11 ; RV64-NEXT: vmseq.vx v11, v8, s0 ; RV64-NEXT: vmor.mm v9, v9, v13 ; RV64-NEXT: vmor.mm v9, v9, v10 ; RV64-NEXT: vmor.mm v9, v9, v12 ; RV64-NEXT: vmor.mm v9, v9, v11 ; RV64-NEXT: vmseq.vx v8, v8, s1 ; RV64-NEXT: vmor.mm v8, v9, v8 ; RV64-NEXT: vmand.mm v0, v8, v0 ; RV64-NEXT: ld ra, 104(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s0, 96(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s1, 88(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s2, 80(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s3, 72(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s4, 64(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s5, 56(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s6, 48(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s7, 40(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s8, 32(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s9, 24(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s10, 16(sp) # 8-byte Folded Reload ; RV64-NEXT: ld s11, 8(sp) # 8-byte Folded Reload ; RV64-NEXT: .cfi_restore ra ; RV64-NEXT: .cfi_restore s0 ; RV64-NEXT: .cfi_restore s1 ; RV64-NEXT: .cfi_restore s2 ; RV64-NEXT: .cfi_restore s3 ; RV64-NEXT: .cfi_restore s4 ; RV64-NEXT: .cfi_restore s5 ; RV64-NEXT: .cfi_restore s6 ; RV64-NEXT: .cfi_restore s7 ; RV64-NEXT: .cfi_restore s8 ; RV64-NEXT: .cfi_restore s9 ; RV64-NEXT: .cfi_restore s10 ; RV64-NEXT: .cfi_restore s11 ; RV64-NEXT: addi sp, sp, 112 ; RV64-NEXT: .cfi_def_cfa_offset 0 ; RV64-NEXT: ret %r = tail call <16 x i1> @llvm.experimental.vector.match(<16 x i8> %op1, <32 x i8> %op2, <16 x i1> %mask) ret <16 x i1> %r } define @match_nxv4xi32_v4i32( %op1, <4 x i32> %op2, %mask) { ; CHECK-LABEL: match_nxv4xi32_v4i32: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli a0, zero, e32, m2, ta, ma ; CHECK-NEXT: vrgather.vi v12, v10, 1 ; CHECK-NEXT: vmseq.vv v14, v8, v12 ; CHECK-NEXT: vrgather.vi v12, v10, 0 ; CHECK-NEXT: vmseq.vv v15, v8, v12 ; CHECK-NEXT: vmor.mm v12, v15, v14 ; CHECK-NEXT: vrgather.vi v14, v10, 2 ; CHECK-NEXT: vmseq.vv v13, v8, v14 ; CHECK-NEXT: vrgather.vi v14, v10, 3 ; CHECK-NEXT: vmor.mm v10, v12, v13 ; CHECK-NEXT: vmseq.vv v11, v8, v14 ; CHECK-NEXT: vmor.mm v8, v10, v11 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call @llvm.experimental.vector.match( %op1, <4 x i32> %op2, %mask) ret %r } define @match_nxv2xi64_v2i64( %op1, <2 x i64> %op2, %mask) { ; CHECK-LABEL: match_nxv2xi64_v2i64: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetvli a0, zero, e64, m2, ta, ma ; CHECK-NEXT: vrgather.vi v12, v10, 1 ; CHECK-NEXT: vmseq.vv v14, v8, v12 ; CHECK-NEXT: vrgather.vi v12, v10, 0 ; CHECK-NEXT: vmseq.vv v10, v8, v12 ; CHECK-NEXT: vmor.mm v8, v10, v14 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call @llvm.experimental.vector.match( %op1, <2 x i64> %op2, %mask) ret %r } define <4 x i1> @match_v4xi32_v4i32(<4 x i32> %op1, <4 x i32> %op2, <4 x i1> %mask) { ; CHECK-LABEL: match_v4xi32_v4i32: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma ; CHECK-NEXT: vrgather.vi v10, v9, 1 ; CHECK-NEXT: vrgather.vi v11, v9, 0 ; CHECK-NEXT: vmseq.vv v10, v8, v10 ; CHECK-NEXT: vmseq.vv v11, v8, v11 ; CHECK-NEXT: vmor.mm v10, v11, v10 ; CHECK-NEXT: vrgather.vi v11, v9, 2 ; CHECK-NEXT: vrgather.vi v12, v9, 3 ; CHECK-NEXT: vmseq.vv v9, v8, v11 ; CHECK-NEXT: vmor.mm v9, v10, v9 ; CHECK-NEXT: vmseq.vv v8, v8, v12 ; CHECK-NEXT: vmor.mm v8, v9, v8 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call <4 x i1> @llvm.experimental.vector.match(<4 x i32> %op1, <4 x i32> %op2, <4 x i1> %mask) ret <4 x i1> %r } define <2 x i1> @match_v2xi64_v2i64(<2 x i64> %op1, <2 x i64> %op2, <2 x i1> %mask) { ; CHECK-LABEL: match_v2xi64_v2i64: ; CHECK: # %bb.0: ; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, ma ; CHECK-NEXT: vrgather.vi v10, v9, 1 ; CHECK-NEXT: vrgather.vi v11, v9, 0 ; CHECK-NEXT: vmseq.vv v9, v8, v10 ; CHECK-NEXT: vmseq.vv v8, v8, v11 ; CHECK-NEXT: vmor.mm v8, v8, v9 ; CHECK-NEXT: vmand.mm v0, v8, v0 ; CHECK-NEXT: ret %r = tail call <2 x i1> @llvm.experimental.vector.match(<2 x i64> %op1, <2 x i64> %op2, <2 x i1> %mask) ret <2 x i1> %r }