[RISCV] Change VECTOR_SPLICE mask operation from expand to promote

[Jimerlife]

Summary

Before this patch, vector_splice mask operation go through expandVectorSplice. But if Imm >= 0 in vector_splice, tests will crash when it go through expandVectorSplice.
So, I change expand vector_splice mask operation to promote. This patch D94708 has implemented vector_splice promote.

[reames]

Please land the new tests, and then rebase so that code changes are visible. (Unless this is fixing a crash, and then please clarify the commit message.)

[Jimerlife]

In D128717#3616747, @reames wrote:

Please land the new tests, and then rebase so that code changes are visible. (Unless this is fixing a crash, and then please clarify the commit message.)

I created D128778 for precommit test, but I set Imm = -1 in all precommit tests. If Imm >= 0, tests will crash. After precommit test land, I will rebase it and update this patch.

[Jimerlife]

rebase main

[craig.topper]

LGTM

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

for (MVT VT : BoolVecVTs) {
         setLoadExtAction({ISD::EXTLOAD, ISD::SEXTLOAD, ISD::ZEXTLOAD}, OtherVT,
                          VT, Expand);
       }
 
       setOperationAction(
           {ISD::VP_FPTOSI, ISD::VP_FPTOUI, ISD::VP_TRUNCATE, ISD::VP_SETCC}, VT,
           Custom);
       setOperationAction(ISD::VECTOR_REVERSE, VT, Custom);
+
+      setOperationPromotedToType(
+          ISD::VECTOR_SPLICE, VT,
+          MVT::getVectorVT(MVT::i8, VT.getVectorElementCount()));
     }
 
     for (MVT VT : IntVecVTs) {
       if (!isTypeLegal(VT))
         continue;
 
       setOperationAction(ISD::SPLAT_VECTOR, VT, Legal);
       setOperationAction(ISD::SPLAT_VECTOR_PARTS, VT, Custom);

llvm/test/CodeGen/RISCV/rvv/vector-splice.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple riscv32 -mattr=+m,+f,+d,+v,+zfh,+experimental-zvfh < %s | FileCheck %s
 ; RUN: llc -mtriple riscv64 -mattr=+m,+f,+d,+v,+zfh,+experimental-zvfh < %s | FileCheck %s
 
 ; Tests assume VLEN=128 or vscale_range_min=2.
 
 declare <vscale x 1 x i1> @llvm.experimental.vector.splice.nxv1i1(<vscale x 1 x i1>, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x i1> @splice_nxv1i1_offset_negone(<vscale x 1 x i1> %a, <vscale x 1 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv1i1_offset_negone:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf8, ta, mu
+; CHECK-NEXT:    vmv.v.i v9, 0
+; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vsetvli a1, zero, e8, mf8, ta, mu
-; CHECK-NEXT:    vsm.v v0, (a0)
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    srli a1, a1, 3
-; CHECK-NEXT:    add a0, a0, a1
-; CHECK-NEXT:    vsm.v v8, (a0)
+; CHECK-NEXT:    srli a0, a0, 3
 ; CHECK-NEXT:    addi a0, a0, -1
-; CHECK-NEXT:    vlm.v v0, (a0)
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    vsetivli zero, 1, e8, mf8, ta, mu
+; CHECK-NEXT:    vslidedown.vx v10, v10, a0
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, mu
+; CHECK-NEXT:    vslideup.vi v10, v8, 1
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, ta, mu
+; CHECK-NEXT:    vand.vi v8, v10, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 1 x i1> @llvm.experimental.vector.splice.nxv1i1(<vscale x 1 x i1> %a, <vscale x 1 x i1> %b, i32 -1)
   ret <vscale x 1 x i1> %res
 }
 
+define <vscale x 1 x i1> @splice_nxv1i1_offset_max(<vscale x 1 x i1> %a, <vscale x 1 x i1> %b) #0 {
+; CHECK-LABEL: splice_nxv1i1_offset_max:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf8, ta, mu
+; CHECK-NEXT:    vmv.v.i v9, 0
+; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 3
+; CHECK-NEXT:    addi a0, a0, -1
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
+; CHECK-NEXT:    vslidedown.vi v10, v10, 1
+; CHECK-NEXT:    vsetvli a1, zero, e8, mf8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, tu, mu
+; CHECK-NEXT:    vslideup.vx v10, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf8, ta, mu
+; CHECK-NEXT:    vand.vi v8, v10, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
+; CHECK-NEXT:    ret
+  %res = call <vscale x 1 x i1> @llvm.experimental.vector.splice.nxv1i1(<vscale x 1 x i1> %a, <vscale x 1 x i1> %b, i32 1)
+  ret <vscale x 1 x i1> %res
+}
+
 declare <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, i32)
 
 define <vscale x 2 x i1> @splice_nxv2i1_offset_negone(<vscale x 2 x i1> %a, <vscale x 2 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv2i1_offset_negone:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf4, ta, mu
+; CHECK-NEXT:    vmv.v.i v9, 0
+; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vsetvli a1, zero, e8, mf4, ta, mu
-; CHECK-NEXT:    vsm.v v0, (a0)
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    srli a1, a1, 3
-; CHECK-NEXT:    add a0, a0, a1
-; CHECK-NEXT:    vsm.v v8, (a0)
+; CHECK-NEXT:    srli a0, a0, 2
 ; CHECK-NEXT:    addi a0, a0, -1
-; CHECK-NEXT:    vlm.v v0, (a0)
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    vsetivli zero, 1, e8, mf4, ta, mu
+; CHECK-NEXT:    vslidedown.vx v10, v10, a0
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf4, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, tu, mu
+; CHECK-NEXT:    vslideup.vi v10, v8, 1
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, ta, mu
+; CHECK-NEXT:    vand.vi v8, v10, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1> %a, <vscale x 2 x i1> %b, i32 -1)
   ret <vscale x 2 x i1> %res
 }
 
+define <vscale x 2 x i1> @splice_nxv2i1_offset_max(<vscale x 2 x i1> %a, <vscale x 2 x i1> %b) #0 {
+; CHECK-LABEL: splice_nxv2i1_offset_max:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf4, ta, mu
+; CHECK-NEXT:    vmv.v.i v9, 0
+; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 2
+; CHECK-NEXT:    addi a0, a0, -3
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
+; CHECK-NEXT:    vslidedown.vi v10, v10, 3
+; CHECK-NEXT:    vsetvli a1, zero, e8, mf4, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, tu, mu
+; CHECK-NEXT:    vslideup.vx v10, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf4, ta, mu
+; CHECK-NEXT:    vand.vi v8, v10, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
+; CHECK-NEXT:    ret
+  %res = call <vscale x 2 x i1> @llvm.experimental.vector.splice.nxv2i1(<vscale x 2 x i1> %a, <vscale x 2 x i1> %b, i32 3)
+  ret <vscale x 2 x i1> %res
+}
+
 declare <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, i32)
 
 define <vscale x 4 x i1> @splice_nxv4i1_offset_negone(<vscale x 4 x i1> %a, <vscale x 4 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv4i1_offset_negone:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf2, ta, mu
+; CHECK-NEXT:    vmv.v.i v9, 0
+; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vsetvli a1, zero, e8, mf2, ta, mu
-; CHECK-NEXT:    vsm.v v0, (a0)
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    srli a1, a1, 3
-; CHECK-NEXT:    add a0, a0, a1
-; CHECK-NEXT:    vsm.v v8, (a0)
+; CHECK-NEXT:    srli a0, a0, 1
 ; CHECK-NEXT:    addi a0, a0, -1
-; CHECK-NEXT:    vlm.v v0, (a0)
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    vsetivli zero, 1, e8, mf2, ta, mu
+; CHECK-NEXT:    vslidedown.vx v10, v10, a0
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, tu, mu
+; CHECK-NEXT:    vslideup.vi v10, v8, 1
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, ta, mu
+; CHECK-NEXT:    vand.vi v8, v10, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1> %a, <vscale x 4 x i1> %b, i32 -1)
   ret <vscale x 4 x i1> %res
 }
 
+define <vscale x 4 x i1> @splice_nxv4i1_offset_max(<vscale x 4 x i1> %a, <vscale x 4 x i1> %b) #0 {
+; CHECK-LABEL: splice_nxv4i1_offset_max:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, mf2, ta, mu
+; CHECK-NEXT:    vmv.v.i v9, 0
+; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    srli a0, a0, 1
+; CHECK-NEXT:    addi a0, a0, -7
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
+; CHECK-NEXT:    vslidedown.vi v10, v10, 7
+; CHECK-NEXT:    vsetvli a1, zero, e8, mf2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, tu, mu
+; CHECK-NEXT:    vslideup.vx v10, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8, mf2, ta, mu
+; CHECK-NEXT:    vand.vi v8, v10, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
+; CHECK-NEXT:    ret
+  %res = call <vscale x 4 x i1> @llvm.experimental.vector.splice.nxv4i1(<vscale x 4 x i1> %a, <vscale x 4 x i1> %b, i32 7)
+  ret <vscale x 4 x i1> %res
+}
+
 declare <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x i1> @splice_nxv8i1_offset_negone(<vscale x 8 x i1> %a, <vscale x 8 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv8i1_offset_negone:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    vsetvli a0, zero, e8, m1, ta, mu
+; CHECK-NEXT:    vmv.v.i v9, 0
+; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, mu
-; CHECK-NEXT:    vsm.v v0, (a0)
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    srli a1, a1, 3
-; CHECK-NEXT:    add a0, a0, a1
-; CHECK-NEXT:    vsm.v v8, (a0)
 ; CHECK-NEXT:    addi a0, a0, -1
-; CHECK-NEXT:    vlm.v v0, (a0)
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    vsetivli zero, 1, e8, m1, ta, mu
+; CHECK-NEXT:    vslidedown.vx v10, v10, a0
+; CHECK-NEXT:    vsetvli a0, zero, e8, m1, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, tu, mu
+; CHECK-NEXT:    vslideup.vi v10, v8, 1
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, mu
+; CHECK-NEXT:    vand.vi v8, v10, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1> %a, <vscale x 8 x i1> %b, i32 -1)
   ret <vscale x 8 x i1> %res
 }
 
+define <vscale x 8 x i1> @splice_nxv8i1_offset_max(<vscale x 8 x i1> %a, <vscale x 8 x i1> %b) #0 {
+; CHECK-LABEL: splice_nxv8i1_offset_max:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, m1, ta, mu
+; CHECK-NEXT:    vmv.v.i v9, 0
+; CHECK-NEXT:    vmerge.vim v10, v9, 1, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    addi a0, a0, -15
+; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
+; CHECK-NEXT:    vslidedown.vi v10, v10, 15
+; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v9, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, tu, mu
+; CHECK-NEXT:    vslideup.vx v10, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m1, ta, mu
+; CHECK-NEXT:    vand.vi v8, v10, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
+; CHECK-NEXT:    ret
+  %res = call <vscale x 8 x i1> @llvm.experimental.vector.splice.nxv8i1(<vscale x 8 x i1> %a, <vscale x 8 x i1> %b, i32 15)
+  ret <vscale x 8 x i1> %res
+}
+
 declare <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, i32)
 
 define <vscale x 16 x i1> @splice_nxv16i1_offset_negone(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv16i1_offset_negone:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    vsetvli a0, zero, e8, m2, ta, mu
+; CHECK-NEXT:    vmv.v.i v10, 0
+; CHECK-NEXT:    vmerge.vim v12, v10, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vsetvli a1, zero, e8, m2, ta, mu
-; CHECK-NEXT:    vsm.v v0, (a0)
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    srli a1, a1, 2
-; CHECK-NEXT:    add a0, a0, a1
-; CHECK-NEXT:    vsm.v v8, (a0)
 ; CHECK-NEXT:    addi a0, a0, -1
-; CHECK-NEXT:    vlm.v v0, (a0)
+; CHECK-NEXT:    vsetivli zero, 1, e8, m2, ta, mu
+; CHECK-NEXT:    vslidedown.vx v12, v12, a0
+; CHECK-NEXT:    vsetvli a0, zero, e8, m2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v10, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m2, tu, mu
+; CHECK-NEXT:    vslideup.vi v12, v8, 1
+; CHECK-NEXT:    vsetvli zero, zero, e8, m2, ta, mu
+; CHECK-NEXT:    vand.vi v8, v12, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
+; CHECK-NEXT:    ret
+  %res = call <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b, i32 -1)
+  ret <vscale x 16 x i1> %res
+}
+
+define <vscale x 16 x i1> @splice_nxv16i1_offset_max(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b) #0 {
+; CHECK-LABEL: splice_nxv16i1_offset_max:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, m2, ta, mu
+; CHECK-NEXT:    vmv.v.i v10, 0
+; CHECK-NEXT:    vmerge.vim v12, v10, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
 ; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    addi a0, a0, -31
+; CHECK-NEXT:    vsetvli zero, a0, e8, m2, ta, mu
+; CHECK-NEXT:    vslidedown.vi v12, v12, 31
+; CHECK-NEXT:    vsetvli a1, zero, e8, m2, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v10, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m2, tu, mu
+; CHECK-NEXT:    vslideup.vx v12, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m2, ta, mu
+; CHECK-NEXT:    vand.vi v8, v12, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
-  %res = call <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b, i32 -1)
+  %res = call <vscale x 16 x i1> @llvm.experimental.vector.splice.nxv16i1(<vscale x 16 x i1> %a, <vscale x 16 x i1> %b, i32 31)
   ret <vscale x 16 x i1> %res
 }
 
 declare <vscale x 32 x i1> @llvm.experimental.vector.splice.nxv32i1(<vscale x 32 x i1>, <vscale x 32 x i1>, i32)
 
 define <vscale x 32 x i1> @splice_nxv32i1_offset_negone(<vscale x 32 x i1> %a, <vscale x 32 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv32i1_offset_negone:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    vsetvli a0, zero, e8, m4, ta, mu
+; CHECK-NEXT:    vmv.v.i v12, 0
+; CHECK-NEXT:    vmerge.vim v16, v12, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vsetvli a1, zero, e8, m4, ta, mu
-; CHECK-NEXT:    vsm.v v0, (a0)
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    srli a1, a1, 1
-; CHECK-NEXT:    add a0, a0, a1
-; CHECK-NEXT:    vsm.v v8, (a0)
+; CHECK-NEXT:    slli a0, a0, 2
 ; CHECK-NEXT:    addi a0, a0, -1
-; CHECK-NEXT:    vlm.v v0, (a0)
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    vsetivli zero, 1, e8, m4, ta, mu
+; CHECK-NEXT:    vslidedown.vx v16, v16, a0
+; CHECK-NEXT:    vsetvli a0, zero, e8, m4, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v12, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m4, tu, mu
+; CHECK-NEXT:    vslideup.vi v16, v8, 1
+; CHECK-NEXT:    vsetvli zero, zero, e8, m4, ta, mu
+; CHECK-NEXT:    vand.vi v8, v16, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 32 x i1> @llvm.experimental.vector.splice.nxv32i1(<vscale x 32 x i1> %a, <vscale x 32 x i1> %b, i32 -1)
   ret <vscale x 32 x i1> %res
 }
 
+define <vscale x 32 x i1> @splice_nxv32i1_offset_max(<vscale x 32 x i1> %a, <vscale x 32 x i1> %b) #0 {
+; CHECK-LABEL: splice_nxv32i1_offset_max:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, m4, ta, mu
+; CHECK-NEXT:    vmv.v.i v12, 0
+; CHECK-NEXT:    vmerge.vim v16, v12, 1, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 2
+; CHECK-NEXT:    addi a0, a0, -63
+; CHECK-NEXT:    li a1, 63
+; CHECK-NEXT:    vsetvli zero, a0, e8, m4, ta, mu
+; CHECK-NEXT:    vslidedown.vx v16, v16, a1
+; CHECK-NEXT:    vsetvli a1, zero, e8, m4, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v12, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m4, tu, mu
+; CHECK-NEXT:    vslideup.vx v16, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m4, ta, mu
+; CHECK-NEXT:    vand.vi v8, v16, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
+; CHECK-NEXT:    ret
+  %res = call <vscale x 32 x i1> @llvm.experimental.vector.splice.nxv32i1(<vscale x 32 x i1> %a, <vscale x 32 x i1> %b, i32 63)
+  ret <vscale x 32 x i1> %res
+}
+
 declare <vscale x 64 x i1> @llvm.experimental.vector.splice.nxv64i1(<vscale x 64 x i1>, <vscale x 64 x i1>, i32)
 
 define <vscale x 64 x i1> @splice_nxv64i1_offset_negone(<vscale x 64 x i1> %a, <vscale x 64 x i1> %b) #0 {
 ; CHECK-LABEL: splice_nxv64i1_offset_negone:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi sp, sp, -16
-; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    vsetvli a0, zero, e8, m8, ta, mu
+; CHECK-NEXT:    vmv.v.i v16, 0
+; CHECK-NEXT:    vmerge.vim v24, v16, 1, v0
 ; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    sub sp, sp, a0
-; CHECK-NEXT:    addi a0, sp, 16
-; CHECK-NEXT:    vsetvli a1, zero, e8, m8, ta, mu
-; CHECK-NEXT:    vsm.v v0, (a0)
-; CHECK-NEXT:    csrr a1, vlenb
-; CHECK-NEXT:    add a0, a0, a1
-; CHECK-NEXT:    vsm.v v8, (a0)
+; CHECK-NEXT:    slli a0, a0, 3
 ; CHECK-NEXT:    addi a0, a0, -1
-; CHECK-NEXT:    vlm.v v0, (a0)
-; CHECK-NEXT:    csrr a0, vlenb
-; CHECK-NEXT:    slli a0, a0, 1
-; CHECK-NEXT:    add sp, sp, a0
-; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    vsetivli zero, 1, e8, m8, ta, mu
+; CHECK-NEXT:    vslidedown.vx v24, v24, a0
+; CHECK-NEXT:    vsetvli a0, zero, e8, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v16, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m8, tu, mu
+; CHECK-NEXT:    vslideup.vi v24, v8, 1
+; CHECK-NEXT:    vsetvli zero, zero, e8, m8, ta, mu
+; CHECK-NEXT:    vand.vi v8, v24, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
 ; CHECK-NEXT:    ret
   %res = call <vscale x 64 x i1> @llvm.experimental.vector.splice.nxv64i1(<vscale x 64 x i1> %a, <vscale x 64 x i1> %b, i32 -1)
   ret <vscale x 64 x i1> %res
 }
 
+define <vscale x 64 x i1> @splice_nxv64i1_offset_max(<vscale x 64 x i1> %a, <vscale x 64 x i1> %b) #0 {
+; CHECK-LABEL: splice_nxv64i1_offset_max:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli a0, zero, e8, m8, ta, mu
+; CHECK-NEXT:    vmv.v.i v16, 0
+; CHECK-NEXT:    vmerge.vim v24, v16, 1, v0
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    addi a0, a0, -127
+; CHECK-NEXT:    li a1, 127
+; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
+; CHECK-NEXT:    vslidedown.vx v24, v24, a1
+; CHECK-NEXT:    vsetvli a1, zero, e8, m8, ta, mu
+; CHECK-NEXT:    vmv1r.v v0, v8
+; CHECK-NEXT:    vmerge.vim v8, v16, 1, v0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m8, tu, mu
+; CHECK-NEXT:    vslideup.vx v24, v8, a0
+; CHECK-NEXT:    vsetvli zero, zero, e8, m8, ta, mu
+; CHECK-NEXT:    vand.vi v8, v24, 1
+; CHECK-NEXT:    vmsne.vi v0, v8, 0
+; CHECK-NEXT:    ret
+  %res = call <vscale x 64 x i1> @llvm.experimental.vector.splice.nxv64i1(<vscale x 64 x i1> %a, <vscale x 64 x i1> %b, i32 127)
+  ret <vscale x 64 x i1> %res
+}
+
 declare <vscale x 1 x i8> @llvm.experimental.vector.splice.nxv1i8(<vscale x 1 x i8>, <vscale x 1 x i8>, i32)
 
 define <vscale x 1 x i8> @splice_nxv1i8_offset_zero(<vscale x 1 x i8> %a, <vscale x 1 x i8> %b) #0 {
 ; CHECK-LABEL: splice_nxv1i8_offset_zero:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    ret
   %res = call <vscale x 1 x i8> @llvm.experimental.vector.splice.nxv1i8(<vscale x 1 x i8> %a, <vscale x 1 x i8> %b, i32 0)
   ret <vscale x 1 x i8> %res