; 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: 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: 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: 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, -1
; 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: 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, -1
; 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: 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, -1
; 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: 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: addi a0, a0, -1
; 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: 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 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: 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, -1
; 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: 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, -1
; 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
}
define <vscale x 1 x i8> @splice_nxv1i8_offset_negone(<vscale x 1 x i8> %a, <vscale x 1 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv1i8_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e8, mf8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, mf8, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; 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 -1)
ret <vscale x 1 x i8> %res
}
define <vscale x 1 x i8> @splice_nxv1i8_offset_min(<vscale x 1 x i8> %a, <vscale x 1 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv1i8_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -2
; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, mf8, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 2
; 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 -2)
ret <vscale x 1 x i8> %res
}
define <vscale x 1 x i8> @splice_nxv1i8_offset_max(<vscale x 1 x i8> %a, <vscale x 1 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv1i8_offset_max:
; CHECK: # %bb.0:
; 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 v8, v8, 1
; CHECK-NEXT: vsetvli a1, zero, e8, mf8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; 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 1)
ret <vscale x 1 x i8> %res
}
declare <vscale x 2 x i8> @llvm.experimental.vector.splice.nxv2i8(<vscale x 2 x i8>, <vscale x 2 x i8>, i32)
define <vscale x 2 x i8> @splice_nxv2i8_offset_zero(<vscale x 2 x i8> %a, <vscale x 2 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv2i8_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 2 x i8> @llvm.experimental.vector.splice.nxv2i8(<vscale x 2 x i8> %a, <vscale x 2 x i8> %b, i32 0)
ret <vscale x 2 x i8> %res
}
define <vscale x 2 x i8> @splice_nxv2i8_offset_negone(<vscale x 2 x i8> %a, <vscale x 2 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv2i8_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e8, mf4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, mf4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 2 x i8> @llvm.experimental.vector.splice.nxv2i8(<vscale x 2 x i8> %a, <vscale x 2 x i8> %b, i32 -1)
ret <vscale x 2 x i8> %res
}
define <vscale x 2 x i8> @splice_nxv2i8_offset_min(<vscale x 2 x i8> %a, <vscale x 2 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv2i8_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -4
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, mf4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 4
; CHECK-NEXT: ret
%res = call <vscale x 2 x i8> @llvm.experimental.vector.splice.nxv2i8(<vscale x 2 x i8> %a, <vscale x 2 x i8> %b, i32 -4)
ret <vscale x 2 x i8> %res
}
define <vscale x 2 x i8> @splice_nxv2i8_offset_max(<vscale x 2 x i8> %a, <vscale x 2 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv2i8_offset_max:
; CHECK: # %bb.0:
; 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 v8, v8, 3
; CHECK-NEXT: vsetvli a1, zero, e8, mf4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 2 x i8> @llvm.experimental.vector.splice.nxv2i8(<vscale x 2 x i8> %a, <vscale x 2 x i8> %b, i32 3)
ret <vscale x 2 x i8> %res
}
declare <vscale x 4 x i8> @llvm.experimental.vector.splice.nxv4i8(<vscale x 4 x i8>, <vscale x 4 x i8>, i32)
define <vscale x 4 x i8> @splice_nxv4i8_offset_zero(<vscale x 4 x i8> %a, <vscale x 4 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv4i8_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 4 x i8> @llvm.experimental.vector.splice.nxv4i8(<vscale x 4 x i8> %a, <vscale x 4 x i8> %b, i32 0)
ret <vscale x 4 x i8> %res
}
define <vscale x 4 x i8> @splice_nxv4i8_offset_negone(<vscale x 4 x i8> %a, <vscale x 4 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv4i8_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e8, mf2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, mf2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 4 x i8> @llvm.experimental.vector.splice.nxv4i8(<vscale x 4 x i8> %a, <vscale x 4 x i8> %b, i32 -1)
ret <vscale x 4 x i8> %res
}
define <vscale x 4 x i8> @splice_nxv4i8_offset_min(<vscale x 4 x i8> %a, <vscale x 4 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv4i8_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -8
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, mf2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 8
; CHECK-NEXT: ret
%res = call <vscale x 4 x i8> @llvm.experimental.vector.splice.nxv4i8(<vscale x 4 x i8> %a, <vscale x 4 x i8> %b, i32 -8)
ret <vscale x 4 x i8> %res
}
define <vscale x 4 x i8> @splice_nxv4i8_offset_max(<vscale x 4 x i8> %a, <vscale x 4 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv4i8_offset_max:
; CHECK: # %bb.0:
; 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 v8, v8, 7
; CHECK-NEXT: vsetvli a1, zero, e8, mf2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 4 x i8> @llvm.experimental.vector.splice.nxv4i8(<vscale x 4 x i8> %a, <vscale x 4 x i8> %b, i32 7)
ret <vscale x 4 x i8> %res
}
declare <vscale x 8 x i8> @llvm.experimental.vector.splice.nxv8i8(<vscale x 8 x i8>, <vscale x 8 x i8>, i32)
define <vscale x 8 x i8> @splice_nxv8i8_offset_zero(<vscale x 8 x i8> %a, <vscale x 8 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv8i8_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 8 x i8> @llvm.experimental.vector.splice.nxv8i8(<vscale x 8 x i8> %a, <vscale x 8 x i8> %b, i32 0)
ret <vscale x 8 x i8> %res
}
define <vscale x 8 x i8> @splice_nxv8i8_offset_negone(<vscale x 8 x i8> %a, <vscale x 8 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv8i8_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e8, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 8 x i8> @llvm.experimental.vector.splice.nxv8i8(<vscale x 8 x i8> %a, <vscale x 8 x i8> %b, i32 -1)
ret <vscale x 8 x i8> %res
}
define <vscale x 8 x i8> @splice_nxv8i8_offset_min(<vscale x 8 x i8> %a, <vscale x 8 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv8i8_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -16
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 16
; CHECK-NEXT: ret
%res = call <vscale x 8 x i8> @llvm.experimental.vector.splice.nxv8i8(<vscale x 8 x i8> %a, <vscale x 8 x i8> %b, i32 -16)
ret <vscale x 8 x i8> %res
}
define <vscale x 8 x i8> @splice_nxv8i8_offset_max(<vscale x 8 x i8> %a, <vscale x 8 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv8i8_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -15
; CHECK-NEXT: vsetvli zero, a0, e8, m1, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 15
; CHECK-NEXT: vsetvli a1, zero, e8, m1, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 8 x i8> @llvm.experimental.vector.splice.nxv8i8(<vscale x 8 x i8> %a, <vscale x 8 x i8> %b, i32 15)
ret <vscale x 8 x i8> %res
}
declare <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, i32)
define <vscale x 16 x i8> @splice_nxv16i8_offset_zero(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv16i8_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, i32 0)
ret <vscale x 16 x i8> %res
}
define <vscale x 16 x i8> @splice_nxv16i8_offset_negone(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv16i8_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e8, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 1
; CHECK-NEXT: ret
%res = call <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, i32 -1)
ret <vscale x 16 x i8> %res
}
define <vscale x 16 x i8> @splice_nxv16i8_offset_min(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv16i8_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -32
; CHECK-NEXT: li a1, 32
; CHECK-NEXT: vsetvli zero, a1, e8, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, m2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v10, a1
; CHECK-NEXT: ret
%res = call <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, i32 -32)
ret <vscale x 16 x i8> %res
}
define <vscale x 16 x i8> @splice_nxv16i8_offset_max(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv16i8_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -31
; CHECK-NEXT: vsetvli zero, a0, e8, m2, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 31
; CHECK-NEXT: vsetvli a1, zero, e8, m2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v10, a0
; CHECK-NEXT: ret
%res = call <vscale x 16 x i8> @llvm.experimental.vector.splice.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b, i32 31)
ret <vscale x 16 x i8> %res
}
declare <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8>, <vscale x 32 x i8>, i32)
define <vscale x 32 x i8> @splice_nxv32i8_offset_zero(<vscale x 32 x i8> %a, <vscale x 32 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv32i8_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8> %a, <vscale x 32 x i8> %b, i32 0)
ret <vscale x 32 x i8> %res
}
define <vscale x 32 x i8> @splice_nxv32i8_offset_negone(<vscale x 32 x i8> %a, <vscale x 32 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv32i8_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e8, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, m4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v12, 1
; CHECK-NEXT: ret
%res = call <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8> %a, <vscale x 32 x i8> %b, i32 -1)
ret <vscale x 32 x i8> %res
}
define <vscale x 32 x i8> @splice_nxv32i8_offset_min(<vscale x 32 x i8> %a, <vscale x 32 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv32i8_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -64
; CHECK-NEXT: li a1, 64
; CHECK-NEXT: vsetvli zero, a1, e8, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, m4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v12, a1
; CHECK-NEXT: ret
%res = call <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8> %a, <vscale x 32 x i8> %b, i32 -64)
ret <vscale x 32 x i8> %res
}
define <vscale x 32 x i8> @splice_nxv32i8_offset_max(<vscale x 32 x i8> %a, <vscale x 32 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv32i8_offset_max:
; CHECK: # %bb.0:
; 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 v8, v8, a1
; CHECK-NEXT: vsetvli a1, zero, e8, m4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v12, a0
; CHECK-NEXT: ret
%res = call <vscale x 32 x i8> @llvm.experimental.vector.splice.nxv32i8(<vscale x 32 x i8> %a, <vscale x 32 x i8> %b, i32 63)
ret <vscale x 32 x i8> %res
}
declare <vscale x 64 x i8> @llvm.experimental.vector.splice.nxv64i8(<vscale x 64 x i8>, <vscale x 64 x i8>, i32)
define <vscale x 64 x i8> @splice_nxv64i8_offset_zero(<vscale x 64 x i8> %a, <vscale x 64 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv64i8_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 64 x i8> @llvm.experimental.vector.splice.nxv64i8(<vscale x 64 x i8> %a, <vscale x 64 x i8> %b, i32 0)
ret <vscale x 64 x i8> %res
}
define <vscale x 64 x i8> @splice_nxv64i8_offset_negone(<vscale x 64 x i8> %a, <vscale x 64 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv64i8_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e8, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, m8, tu, mu
; CHECK-NEXT: vslideup.vi v8, v16, 1
; CHECK-NEXT: ret
%res = call <vscale x 64 x i8> @llvm.experimental.vector.splice.nxv64i8(<vscale x 64 x i8> %a, <vscale x 64 x i8> %b, i32 -1)
ret <vscale x 64 x i8> %res
}
define <vscale x 64 x i8> @splice_nxv64i8_offset_min(<vscale x 64 x i8> %a, <vscale x 64 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv64i8_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -128
; CHECK-NEXT: li a1, 128
; CHECK-NEXT: vsetvli zero, a1, e8, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e8, m8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v16, a1
; CHECK-NEXT: ret
%res = call <vscale x 64 x i8> @llvm.experimental.vector.splice.nxv64i8(<vscale x 64 x i8> %a, <vscale x 64 x i8> %b, i32 -128)
ret <vscale x 64 x i8> %res
}
define <vscale x 64 x i8> @splice_nxv64i8_offset_max(<vscale x 64 x i8> %a, <vscale x 64 x i8> %b) #0 {
; CHECK-LABEL: splice_nxv64i8_offset_max:
; CHECK: # %bb.0:
; 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 v8, v8, a1
; CHECK-NEXT: vsetvli a1, zero, e8, m8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v16, a0
; CHECK-NEXT: ret
%res = call <vscale x 64 x i8> @llvm.experimental.vector.splice.nxv64i8(<vscale x 64 x i8> %a, <vscale x 64 x i8> %b, i32 127)
ret <vscale x 64 x i8> %res
}
declare <vscale x 1 x i16> @llvm.experimental.vector.splice.nxv1i16(<vscale x 1 x i16>, <vscale x 1 x i16>, i32)
define <vscale x 1 x i16> @splice_nxv1i16_offset_zero(<vscale x 1 x i16> %a, <vscale x 1 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv1i16_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 1 x i16> @llvm.experimental.vector.splice.nxv1i16(<vscale x 1 x i16> %a, <vscale x 1 x i16> %b, i32 0)
ret <vscale x 1 x i16> %res
}
define <vscale x 1 x i16> @splice_nxv1i16_offset_negone(<vscale x 1 x i16> %a, <vscale x 1 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv1i16_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, mf4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 1 x i16> @llvm.experimental.vector.splice.nxv1i16(<vscale x 1 x i16> %a, <vscale x 1 x i16> %b, i32 -1)
ret <vscale x 1 x i16> %res
}
define <vscale x 1 x i16> @splice_nxv1i16_offset_min(<vscale x 1 x i16> %a, <vscale x 1 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv1i16_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -2
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, mf4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 2
; CHECK-NEXT: ret
%res = call <vscale x 1 x i16> @llvm.experimental.vector.splice.nxv1i16(<vscale x 1 x i16> %a, <vscale x 1 x i16> %b, i32 -2)
ret <vscale x 1 x i16> %res
}
define <vscale x 1 x i16> @splice_nxv1i16_offset_max(<vscale x 1 x i16> %a, <vscale x 1 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv1i16_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 1
; CHECK-NEXT: vsetvli a1, zero, e16, mf4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 1 x i16> @llvm.experimental.vector.splice.nxv1i16(<vscale x 1 x i16> %a, <vscale x 1 x i16> %b, i32 1)
ret <vscale x 1 x i16> %res
}
declare <vscale x 2 x i16> @llvm.experimental.vector.splice.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i16>, i32)
define <vscale x 2 x i16> @splice_nxv2i16_offset_zero(<vscale x 2 x i16> %a, <vscale x 2 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv2i16_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 2 x i16> @llvm.experimental.vector.splice.nxv2i16(<vscale x 2 x i16> %a, <vscale x 2 x i16> %b, i32 0)
ret <vscale x 2 x i16> %res
}
define <vscale x 2 x i16> @splice_nxv2i16_offset_negone(<vscale x 2 x i16> %a, <vscale x 2 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv2i16_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e16, mf2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, mf2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 2 x i16> @llvm.experimental.vector.splice.nxv2i16(<vscale x 2 x i16> %a, <vscale x 2 x i16> %b, i32 -1)
ret <vscale x 2 x i16> %res
}
define <vscale x 2 x i16> @splice_nxv2i16_offset_min(<vscale x 2 x i16> %a, <vscale x 2 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv2i16_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -4
; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, mf2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 4
; CHECK-NEXT: ret
%res = call <vscale x 2 x i16> @llvm.experimental.vector.splice.nxv2i16(<vscale x 2 x i16> %a, <vscale x 2 x i16> %b, i32 -4)
ret <vscale x 2 x i16> %res
}
define <vscale x 2 x i16> @splice_nxv2i16_offset_max(<vscale x 2 x i16> %a, <vscale x 2 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv2i16_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -3
; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 3
; CHECK-NEXT: vsetvli a1, zero, e16, mf2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 2 x i16> @llvm.experimental.vector.splice.nxv2i16(<vscale x 2 x i16> %a, <vscale x 2 x i16> %b, i32 3)
ret <vscale x 2 x i16> %res
}
declare <vscale x 4 x i16> @llvm.experimental.vector.splice.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i16>, i32)
define <vscale x 4 x i16> @splice_nxv4i16_offset_zero(<vscale x 4 x i16> %a, <vscale x 4 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv4i16_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 4 x i16> @llvm.experimental.vector.splice.nxv4i16(<vscale x 4 x i16> %a, <vscale x 4 x i16> %b, i32 0)
ret <vscale x 4 x i16> %res
}
define <vscale x 4 x i16> @splice_nxv4i16_offset_negone(<vscale x 4 x i16> %a, <vscale x 4 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv4i16_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 4 x i16> @llvm.experimental.vector.splice.nxv4i16(<vscale x 4 x i16> %a, <vscale x 4 x i16> %b, i32 -1)
ret <vscale x 4 x i16> %res
}
define <vscale x 4 x i16> @splice_nxv4i16_offset_min(<vscale x 4 x i16> %a, <vscale x 4 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv4i16_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -8
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 8
; CHECK-NEXT: ret
%res = call <vscale x 4 x i16> @llvm.experimental.vector.splice.nxv4i16(<vscale x 4 x i16> %a, <vscale x 4 x i16> %b, i32 -8)
ret <vscale x 4 x i16> %res
}
define <vscale x 4 x i16> @splice_nxv4i16_offset_max(<vscale x 4 x i16> %a, <vscale x 4 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv4i16_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -7
; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 7
; CHECK-NEXT: vsetvli a1, zero, e16, m1, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 4 x i16> @llvm.experimental.vector.splice.nxv4i16(<vscale x 4 x i16> %a, <vscale x 4 x i16> %b, i32 7)
ret <vscale x 4 x i16> %res
}
declare <vscale x 8 x i16> @llvm.experimental.vector.splice.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, i32)
define <vscale x 8 x i16> @splice_nxv8i16_offset_zero(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv8i16_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 8 x i16> @llvm.experimental.vector.splice.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, i32 0)
ret <vscale x 8 x i16> %res
}
define <vscale x 8 x i16> @splice_nxv8i16_offset_negone(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv8i16_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e16, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 1
; CHECK-NEXT: ret
%res = call <vscale x 8 x i16> @llvm.experimental.vector.splice.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, i32 -1)
ret <vscale x 8 x i16> %res
}
define <vscale x 8 x i16> @splice_nxv8i16_offset_min(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv8i16_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -16
; CHECK-NEXT: vsetivli zero, 16, e16, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 16
; CHECK-NEXT: ret
%res = call <vscale x 8 x i16> @llvm.experimental.vector.splice.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, i32 -16)
ret <vscale x 8 x i16> %res
}
define <vscale x 8 x i16> @splice_nxv8i16_offset_max(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv8i16_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -15
; CHECK-NEXT: vsetvli zero, a0, e16, m2, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 15
; CHECK-NEXT: vsetvli a1, zero, e16, m2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v10, a0
; CHECK-NEXT: ret
%res = call <vscale x 8 x i16> @llvm.experimental.vector.splice.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b, i32 15)
ret <vscale x 8 x i16> %res
}
declare <vscale x 16 x i16> @llvm.experimental.vector.splice.nxv16i16(<vscale x 16 x i16>, <vscale x 16 x i16>, i32)
define <vscale x 16 x i16> @splice_nxv16i16_offset_zero(<vscale x 16 x i16> %a, <vscale x 16 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv16i16_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 16 x i16> @llvm.experimental.vector.splice.nxv16i16(<vscale x 16 x i16> %a, <vscale x 16 x i16> %b, i32 0)
ret <vscale x 16 x i16> %res
}
define <vscale x 16 x i16> @splice_nxv16i16_offset_negone(<vscale x 16 x i16> %a, <vscale x 16 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv16i16_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e16, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v12, 1
; CHECK-NEXT: ret
%res = call <vscale x 16 x i16> @llvm.experimental.vector.splice.nxv16i16(<vscale x 16 x i16> %a, <vscale x 16 x i16> %b, i32 -1)
ret <vscale x 16 x i16> %res
}
define <vscale x 16 x i16> @splice_nxv16i16_offset_min(<vscale x 16 x i16> %a, <vscale x 16 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv16i16_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -32
; CHECK-NEXT: li a1, 32
; CHECK-NEXT: vsetvli zero, a1, e16, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v12, a1
; CHECK-NEXT: ret
%res = call <vscale x 16 x i16> @llvm.experimental.vector.splice.nxv16i16(<vscale x 16 x i16> %a, <vscale x 16 x i16> %b, i32 -32)
ret <vscale x 16 x i16> %res
}
define <vscale x 16 x i16> @splice_nxv16i16_offset_max(<vscale x 16 x i16> %a, <vscale x 16 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv16i16_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -31
; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 31
; CHECK-NEXT: vsetvli a1, zero, e16, m4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v12, a0
; CHECK-NEXT: ret
%res = call <vscale x 16 x i16> @llvm.experimental.vector.splice.nxv16i16(<vscale x 16 x i16> %a, <vscale x 16 x i16> %b, i32 31)
ret <vscale x 16 x i16> %res
}
declare <vscale x 32 x i16> @llvm.experimental.vector.splice.nxv32i16(<vscale x 32 x i16>, <vscale x 32 x i16>, i32)
define <vscale x 32 x i16> @splice_nxv32i16_offset_zero(<vscale x 32 x i16> %a, <vscale x 32 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv32i16_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 32 x i16> @llvm.experimental.vector.splice.nxv32i16(<vscale x 32 x i16> %a, <vscale x 32 x i16> %b, i32 0)
ret <vscale x 32 x i16> %res
}
define <vscale x 32 x i16> @splice_nxv32i16_offset_negone(<vscale x 32 x i16> %a, <vscale x 32 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv32i16_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e16, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m8, tu, mu
; CHECK-NEXT: vslideup.vi v8, v16, 1
; CHECK-NEXT: ret
%res = call <vscale x 32 x i16> @llvm.experimental.vector.splice.nxv32i16(<vscale x 32 x i16> %a, <vscale x 32 x i16> %b, i32 -1)
ret <vscale x 32 x i16> %res
}
define <vscale x 32 x i16> @splice_nxv32i16_offset_min(<vscale x 32 x i16> %a, <vscale x 32 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv32i16_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -64
; CHECK-NEXT: li a1, 64
; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v16, a1
; CHECK-NEXT: ret
%res = call <vscale x 32 x i16> @llvm.experimental.vector.splice.nxv32i16(<vscale x 32 x i16> %a, <vscale x 32 x i16> %b, i32 -64)
ret <vscale x 32 x i16> %res
}
define <vscale x 32 x i16> @splice_nxv32i16_offset_max(<vscale x 32 x i16> %a, <vscale x 32 x i16> %b) #0 {
; CHECK-LABEL: splice_nxv32i16_offset_max:
; CHECK: # %bb.0:
; 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, e16, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a1
; CHECK-NEXT: vsetvli a1, zero, e16, m8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v16, a0
; CHECK-NEXT: ret
%res = call <vscale x 32 x i16> @llvm.experimental.vector.splice.nxv32i16(<vscale x 32 x i16> %a, <vscale x 32 x i16> %b, i32 63)
ret <vscale x 32 x i16> %res
}
declare <vscale x 1 x i32> @llvm.experimental.vector.splice.nxv1i32(<vscale x 1 x i32>, <vscale x 1 x i32>, i32)
define <vscale x 1 x i32> @splice_nxv1i32_offset_zero(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv1i32_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 1 x i32> @llvm.experimental.vector.splice.nxv1i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, i32 0)
ret <vscale x 1 x i32> %res
}
define <vscale x 1 x i32> @splice_nxv1i32_offset_negone(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv1i32_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, mf2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 1 x i32> @llvm.experimental.vector.splice.nxv1i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, i32 -1)
ret <vscale x 1 x i32> %res
}
define <vscale x 1 x i32> @splice_nxv1i32_offset_min(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv1i32_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -2
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, mf2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 2
; CHECK-NEXT: ret
%res = call <vscale x 1 x i32> @llvm.experimental.vector.splice.nxv1i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, i32 -2)
ret <vscale x 1 x i32> %res
}
define <vscale x 1 x i32> @splice_nxv1i32_offset_max(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv1i32_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 1
; CHECK-NEXT: vsetvli a1, zero, e32, mf2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 1 x i32> @llvm.experimental.vector.splice.nxv1i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, i32 1)
ret <vscale x 1 x i32> %res
}
declare <vscale x 2 x i32> @llvm.experimental.vector.splice.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i32>, i32)
define <vscale x 2 x i32> @splice_nxv2i32_offset_zero(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv2i32_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 2 x i32> @llvm.experimental.vector.splice.nxv2i32(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b, i32 0)
ret <vscale x 2 x i32> %res
}
define <vscale x 2 x i32> @splice_nxv2i32_offset_negone(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv2i32_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 2 x i32> @llvm.experimental.vector.splice.nxv2i32(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b, i32 -1)
ret <vscale x 2 x i32> %res
}
define <vscale x 2 x i32> @splice_nxv2i32_offset_min(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv2i32_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -4
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 4
; CHECK-NEXT: ret
%res = call <vscale x 2 x i32> @llvm.experimental.vector.splice.nxv2i32(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b, i32 -4)
ret <vscale x 2 x i32> %res
}
define <vscale x 2 x i32> @splice_nxv2i32_offset_max(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv2i32_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -3
; CHECK-NEXT: vsetvli zero, a0, e32, m1, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 3
; CHECK-NEXT: vsetvli a1, zero, e32, m1, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 2 x i32> @llvm.experimental.vector.splice.nxv2i32(<vscale x 2 x i32> %a, <vscale x 2 x i32> %b, i32 3)
ret <vscale x 2 x i32> %res
}
declare <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, i32)
define <vscale x 4 x i32> @splice_nxv4i32_offset_zero(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv4i32_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, i32 0)
ret <vscale x 4 x i32> %res
}
define <vscale x 4 x i32> @splice_nxv4i32_offset_negone(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv4i32_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e32, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 1
; CHECK-NEXT: ret
%res = call <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, i32 -1)
ret <vscale x 4 x i32> %res
}
define <vscale x 4 x i32> @splice_nxv4i32_offset_min(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv4i32_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -8
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 8
; CHECK-NEXT: ret
%res = call <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, i32 -8)
ret <vscale x 4 x i32> %res
}
define <vscale x 4 x i32> @splice_nxv4i32_offset_max(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv4i32_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -7
; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 7
; CHECK-NEXT: vsetvli a1, zero, e32, m2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v10, a0
; CHECK-NEXT: ret
%res = call <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b, i32 7)
ret <vscale x 4 x i32> %res
}
declare <vscale x 8 x i32> @llvm.experimental.vector.splice.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i32>, i32)
define <vscale x 8 x i32> @splice_nxv8i32_offset_zero(<vscale x 8 x i32> %a, <vscale x 8 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv8i32_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 8 x i32> @llvm.experimental.vector.splice.nxv8i32(<vscale x 8 x i32> %a, <vscale x 8 x i32> %b, i32 0)
ret <vscale x 8 x i32> %res
}
define <vscale x 8 x i32> @splice_nxv8i32_offset_negone(<vscale x 8 x i32> %a, <vscale x 8 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv8i32_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e32, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v12, 1
; CHECK-NEXT: ret
%res = call <vscale x 8 x i32> @llvm.experimental.vector.splice.nxv8i32(<vscale x 8 x i32> %a, <vscale x 8 x i32> %b, i32 -1)
ret <vscale x 8 x i32> %res
}
define <vscale x 8 x i32> @splice_nxv8i32_offset_min(<vscale x 8 x i32> %a, <vscale x 8 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv8i32_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -16
; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v12, 16
; CHECK-NEXT: ret
%res = call <vscale x 8 x i32> @llvm.experimental.vector.splice.nxv8i32(<vscale x 8 x i32> %a, <vscale x 8 x i32> %b, i32 -16)
ret <vscale x 8 x i32> %res
}
define <vscale x 8 x i32> @splice_nxv8i32_offset_max(<vscale x 8 x i32> %a, <vscale x 8 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv8i32_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -15
; CHECK-NEXT: vsetvli zero, a0, e32, m4, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 15
; CHECK-NEXT: vsetvli a1, zero, e32, m4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v12, a0
; CHECK-NEXT: ret
%res = call <vscale x 8 x i32> @llvm.experimental.vector.splice.nxv8i32(<vscale x 8 x i32> %a, <vscale x 8 x i32> %b, i32 15)
ret <vscale x 8 x i32> %res
}
declare <vscale x 16 x i32> @llvm.experimental.vector.splice.nxv16i32(<vscale x 16 x i32>, <vscale x 16 x i32>, i32)
define <vscale x 16 x i32> @splice_nxv16i32_offset_zero(<vscale x 16 x i32> %a, <vscale x 16 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv16i32_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 16 x i32> @llvm.experimental.vector.splice.nxv16i32(<vscale x 16 x i32> %a, <vscale x 16 x i32> %b, i32 0)
ret <vscale x 16 x i32> %res
}
define <vscale x 16 x i32> @splice_nxv16i32_offset_negone(<vscale x 16 x i32> %a, <vscale x 16 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv16i32_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e32, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m8, tu, mu
; CHECK-NEXT: vslideup.vi v8, v16, 1
; CHECK-NEXT: ret
%res = call <vscale x 16 x i32> @llvm.experimental.vector.splice.nxv16i32(<vscale x 16 x i32> %a, <vscale x 16 x i32> %b, i32 -1)
ret <vscale x 16 x i32> %res
}
define <vscale x 16 x i32> @splice_nxv16i32_offset_min(<vscale x 16 x i32> %a, <vscale x 16 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv16i32_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -32
; CHECK-NEXT: li a1, 32
; CHECK-NEXT: vsetvli zero, a1, e32, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v16, a1
; CHECK-NEXT: ret
%res = call <vscale x 16 x i32> @llvm.experimental.vector.splice.nxv16i32(<vscale x 16 x i32> %a, <vscale x 16 x i32> %b, i32 -32)
ret <vscale x 16 x i32> %res
}
define <vscale x 16 x i32> @splice_nxv16i32_offset_max(<vscale x 16 x i32> %a, <vscale x 16 x i32> %b) #0 {
; CHECK-LABEL: splice_nxv16i32_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -31
; CHECK-NEXT: vsetvli zero, a0, e32, m8, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 31
; CHECK-NEXT: vsetvli a1, zero, e32, m8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v16, a0
; CHECK-NEXT: ret
%res = call <vscale x 16 x i32> @llvm.experimental.vector.splice.nxv16i32(<vscale x 16 x i32> %a, <vscale x 16 x i32> %b, i32 31)
ret <vscale x 16 x i32> %res
}
declare <vscale x 1 x i64> @llvm.experimental.vector.splice.nxv1i64(<vscale x 1 x i64>, <vscale x 1 x i64>, i32)
define <vscale x 1 x i64> @splice_nxv1i64_offset_zero(<vscale x 1 x i64> %a, <vscale x 1 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv1i64_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 1 x i64> @llvm.experimental.vector.splice.nxv1i64(<vscale x 1 x i64> %a, <vscale x 1 x i64> %b, i32 0)
ret <vscale x 1 x i64> %res
}
define <vscale x 1 x i64> @splice_nxv1i64_offset_negone(<vscale x 1 x i64> %a, <vscale x 1 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv1i64_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 1 x i64> @llvm.experimental.vector.splice.nxv1i64(<vscale x 1 x i64> %a, <vscale x 1 x i64> %b, i32 -1)
ret <vscale x 1 x i64> %res
}
define <vscale x 1 x i64> @splice_nxv1i64_offset_min(<vscale x 1 x i64> %a, <vscale x 1 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv1i64_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -2
; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 2
; CHECK-NEXT: ret
%res = call <vscale x 1 x i64> @llvm.experimental.vector.splice.nxv1i64(<vscale x 1 x i64> %a, <vscale x 1 x i64> %b, i32 -2)
ret <vscale x 1 x i64> %res
}
define <vscale x 1 x i64> @splice_nxv1i64_offset_max(<vscale x 1 x i64> %a, <vscale x 1 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv1i64_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 1
; CHECK-NEXT: vsetvli a1, zero, e64, m1, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 1 x i64> @llvm.experimental.vector.splice.nxv1i64(<vscale x 1 x i64> %a, <vscale x 1 x i64> %b, i32 1)
ret <vscale x 1 x i64> %res
}
declare <vscale x 2 x i64> @llvm.experimental.vector.splice.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, i32)
define <vscale x 2 x i64> @splice_nxv2i64_offset_zero(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv2i64_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 2 x i64> @llvm.experimental.vector.splice.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, i32 0)
ret <vscale x 2 x i64> %res
}
define <vscale x 2 x i64> @splice_nxv2i64_offset_negone(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv2i64_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e64, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 1
; CHECK-NEXT: ret
%res = call <vscale x 2 x i64> @llvm.experimental.vector.splice.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, i32 -1)
ret <vscale x 2 x i64> %res
}
define <vscale x 2 x i64> @splice_nxv2i64_offset_min(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv2i64_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -4
; CHECK-NEXT: vsetivli zero, 4, e64, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 4
; CHECK-NEXT: ret
%res = call <vscale x 2 x i64> @llvm.experimental.vector.splice.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, i32 -4)
ret <vscale x 2 x i64> %res
}
define <vscale x 2 x i64> @splice_nxv2i64_offset_max(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv2i64_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -3
; CHECK-NEXT: vsetvli zero, a0, e64, m2, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 3
; CHECK-NEXT: vsetvli a1, zero, e64, m2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v10, a0
; CHECK-NEXT: ret
%res = call <vscale x 2 x i64> @llvm.experimental.vector.splice.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b, i32 3)
ret <vscale x 2 x i64> %res
}
declare <vscale x 4 x i64> @llvm.experimental.vector.splice.nxv4i64(<vscale x 4 x i64>, <vscale x 4 x i64>, i32)
define <vscale x 4 x i64> @splice_nxv4i64_offset_zero(<vscale x 4 x i64> %a, <vscale x 4 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv4i64_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 4 x i64> @llvm.experimental.vector.splice.nxv4i64(<vscale x 4 x i64> %a, <vscale x 4 x i64> %b, i32 0)
ret <vscale x 4 x i64> %res
}
define <vscale x 4 x i64> @splice_nxv4i64_offset_negone(<vscale x 4 x i64> %a, <vscale x 4 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv4i64_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e64, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v12, 1
; CHECK-NEXT: ret
%res = call <vscale x 4 x i64> @llvm.experimental.vector.splice.nxv4i64(<vscale x 4 x i64> %a, <vscale x 4 x i64> %b, i32 -1)
ret <vscale x 4 x i64> %res
}
define <vscale x 4 x i64> @splice_nxv4i64_offset_min(<vscale x 4 x i64> %a, <vscale x 4 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv4i64_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -8
; CHECK-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v12, 8
; CHECK-NEXT: ret
%res = call <vscale x 4 x i64> @llvm.experimental.vector.splice.nxv4i64(<vscale x 4 x i64> %a, <vscale x 4 x i64> %b, i32 -8)
ret <vscale x 4 x i64> %res
}
define <vscale x 4 x i64> @splice_nxv4i64_offset_max(<vscale x 4 x i64> %a, <vscale x 4 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv4i64_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -7
; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 7
; CHECK-NEXT: vsetvli a1, zero, e64, m4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v12, a0
; CHECK-NEXT: ret
%res = call <vscale x 4 x i64> @llvm.experimental.vector.splice.nxv4i64(<vscale x 4 x i64> %a, <vscale x 4 x i64> %b, i32 7)
ret <vscale x 4 x i64> %res
}
declare <vscale x 8 x i64> @llvm.experimental.vector.splice.nxv8i64(<vscale x 8 x i64>, <vscale x 8 x i64>, i32)
define <vscale x 8 x i64> @splice_nxv8i64_offset_zero(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv8i64_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 8 x i64> @llvm.experimental.vector.splice.nxv8i64(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b, i32 0)
ret <vscale x 8 x i64> %res
}
define <vscale x 8 x i64> @splice_nxv8i64_offset_negone(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv8i64_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e64, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m8, tu, mu
; CHECK-NEXT: vslideup.vi v8, v16, 1
; CHECK-NEXT: ret
%res = call <vscale x 8 x i64> @llvm.experimental.vector.splice.nxv8i64(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b, i32 -1)
ret <vscale x 8 x i64> %res
}
define <vscale x 8 x i64> @splice_nxv8i64_offset_min(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv8i64_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -16
; CHECK-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m8, tu, mu
; CHECK-NEXT: vslideup.vi v8, v16, 16
; CHECK-NEXT: ret
%res = call <vscale x 8 x i64> @llvm.experimental.vector.splice.nxv8i64(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b, i32 -16)
ret <vscale x 8 x i64> %res
}
define <vscale x 8 x i64> @splice_nxv8i64_offset_max(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b) #0 {
; CHECK-LABEL: splice_nxv8i64_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -15
; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 15
; CHECK-NEXT: vsetvli a1, zero, e64, m8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v16, a0
; CHECK-NEXT: ret
%res = call <vscale x 8 x i64> @llvm.experimental.vector.splice.nxv8i64(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b, i32 15)
ret <vscale x 8 x i64> %res
}
declare <vscale x 1 x half> @llvm.experimental.vector.splice.nxv1f16(<vscale x 1 x half>, <vscale x 1 x half>, i32)
define <vscale x 1 x half> @splice_nxv1f16_offset_zero(<vscale x 1 x half> %a, <vscale x 1 x half> %b) #0 {
; CHECK-LABEL: splice_nxv1f16_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 1 x half> @llvm.experimental.vector.splice.nxv1f16(<vscale x 1 x half> %a, <vscale x 1 x half> %b, i32 0)
ret <vscale x 1 x half> %res
}
define <vscale x 1 x half> @splice_nxv1f16_offset_negone(<vscale x 1 x half> %a, <vscale x 1 x half> %b) #0 {
; CHECK-LABEL: splice_nxv1f16_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e16, mf4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, mf4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 1 x half> @llvm.experimental.vector.splice.nxv1f16(<vscale x 1 x half> %a, <vscale x 1 x half> %b, i32 -1)
ret <vscale x 1 x half> %res
}
define <vscale x 1 x half> @splice_nxv1f16_offset_min(<vscale x 1 x half> %a, <vscale x 1 x half> %b) #0 {
; CHECK-LABEL: splice_nxv1f16_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -2
; CHECK-NEXT: vsetivli zero, 2, e16, mf4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, mf4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 2
; CHECK-NEXT: ret
%res = call <vscale x 1 x half> @llvm.experimental.vector.splice.nxv1f16(<vscale x 1 x half> %a, <vscale x 1 x half> %b, i32 -2)
ret <vscale x 1 x half> %res
}
define <vscale x 1 x half> @splice_nxv1f16_offset_max(<vscale x 1 x half> %a, <vscale x 1 x half> %b) #0 {
; CHECK-LABEL: splice_nxv1f16_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 1
; CHECK-NEXT: vsetvli a1, zero, e16, mf4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 1 x half> @llvm.experimental.vector.splice.nxv1f16(<vscale x 1 x half> %a, <vscale x 1 x half> %b, i32 1)
ret <vscale x 1 x half> %res
}
declare <vscale x 2 x half> @llvm.experimental.vector.splice.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>, i32)
define <vscale x 2 x half> @splice_nxv2f16_offset_zero(<vscale x 2 x half> %a, <vscale x 2 x half> %b) #0 {
; CHECK-LABEL: splice_nxv2f16_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 2 x half> @llvm.experimental.vector.splice.nxv2f16(<vscale x 2 x half> %a, <vscale x 2 x half> %b, i32 0)
ret <vscale x 2 x half> %res
}
define <vscale x 2 x half> @splice_nxv2f16_offset_negone(<vscale x 2 x half> %a, <vscale x 2 x half> %b) #0 {
; CHECK-LABEL: splice_nxv2f16_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e16, mf2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, mf2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 2 x half> @llvm.experimental.vector.splice.nxv2f16(<vscale x 2 x half> %a, <vscale x 2 x half> %b, i32 -1)
ret <vscale x 2 x half> %res
}
define <vscale x 2 x half> @splice_nxv2f16_offset_min(<vscale x 2 x half> %a, <vscale x 2 x half> %b) #0 {
; CHECK-LABEL: splice_nxv2f16_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -4
; CHECK-NEXT: vsetivli zero, 4, e16, mf2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, mf2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 4
; CHECK-NEXT: ret
%res = call <vscale x 2 x half> @llvm.experimental.vector.splice.nxv2f16(<vscale x 2 x half> %a, <vscale x 2 x half> %b, i32 -4)
ret <vscale x 2 x half> %res
}
define <vscale x 2 x half> @splice_nxv2f16_offset_max(<vscale x 2 x half> %a, <vscale x 2 x half> %b) #0 {
; CHECK-LABEL: splice_nxv2f16_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -3
; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 3
; CHECK-NEXT: vsetvli a1, zero, e16, mf2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 2 x half> @llvm.experimental.vector.splice.nxv2f16(<vscale x 2 x half> %a, <vscale x 2 x half> %b, i32 3)
ret <vscale x 2 x half> %res
}
declare <vscale x 4 x half> @llvm.experimental.vector.splice.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>, i32)
define <vscale x 4 x half> @splice_nxv4f16_offset_zero(<vscale x 4 x half> %a, <vscale x 4 x half> %b) #0 {
; CHECK-LABEL: splice_nxv4f16_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 4 x half> @llvm.experimental.vector.splice.nxv4f16(<vscale x 4 x half> %a, <vscale x 4 x half> %b, i32 0)
ret <vscale x 4 x half> %res
}
define <vscale x 4 x half> @splice_nxv4f16_offset_negone(<vscale x 4 x half> %a, <vscale x 4 x half> %b) #0 {
; CHECK-LABEL: splice_nxv4f16_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 4 x half> @llvm.experimental.vector.splice.nxv4f16(<vscale x 4 x half> %a, <vscale x 4 x half> %b, i32 -1)
ret <vscale x 4 x half> %res
}
define <vscale x 4 x half> @splice_nxv4f16_offset_min(<vscale x 4 x half> %a, <vscale x 4 x half> %b) #0 {
; CHECK-LABEL: splice_nxv4f16_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -8
; CHECK-NEXT: vsetivli zero, 8, e16, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 8
; CHECK-NEXT: ret
%res = call <vscale x 4 x half> @llvm.experimental.vector.splice.nxv4f16(<vscale x 4 x half> %a, <vscale x 4 x half> %b, i32 -8)
ret <vscale x 4 x half> %res
}
define <vscale x 4 x half> @splice_nxv4f16_offset_max(<vscale x 4 x half> %a, <vscale x 4 x half> %b) #0 {
; CHECK-LABEL: splice_nxv4f16_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -7
; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 7
; CHECK-NEXT: vsetvli a1, zero, e16, m1, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 4 x half> @llvm.experimental.vector.splice.nxv4f16(<vscale x 4 x half> %a, <vscale x 4 x half> %b, i32 7)
ret <vscale x 4 x half> %res
}
declare <vscale x 8 x half> @llvm.experimental.vector.splice.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, i32)
define <vscale x 8 x half> @splice_nxv8f16_offset_zero(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
; CHECK-LABEL: splice_nxv8f16_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 8 x half> @llvm.experimental.vector.splice.nxv8f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b, i32 0)
ret <vscale x 8 x half> %res
}
define <vscale x 8 x half> @splice_nxv8f16_offset_negone(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
; CHECK-LABEL: splice_nxv8f16_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e16, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 1
; CHECK-NEXT: ret
%res = call <vscale x 8 x half> @llvm.experimental.vector.splice.nxv8f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b, i32 -1)
ret <vscale x 8 x half> %res
}
define <vscale x 8 x half> @splice_nxv8f16_offset_min(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
; CHECK-LABEL: splice_nxv8f16_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -16
; CHECK-NEXT: vsetivli zero, 16, e16, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 16
; CHECK-NEXT: ret
%res = call <vscale x 8 x half> @llvm.experimental.vector.splice.nxv8f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b, i32 -16)
ret <vscale x 8 x half> %res
}
define <vscale x 8 x half> @splice_nxv8f16_offset_max(<vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
; CHECK-LABEL: splice_nxv8f16_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -15
; CHECK-NEXT: vsetvli zero, a0, e16, m2, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 15
; CHECK-NEXT: vsetvli a1, zero, e16, m2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v10, a0
; CHECK-NEXT: ret
%res = call <vscale x 8 x half> @llvm.experimental.vector.splice.nxv8f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b, i32 15)
ret <vscale x 8 x half> %res
}
declare <vscale x 16 x half> @llvm.experimental.vector.splice.nxv16f16(<vscale x 16 x half>, <vscale x 16 x half>, i32)
define <vscale x 16 x half> @splice_nxv16f16_offset_zero(<vscale x 16 x half> %a, <vscale x 16 x half> %b) #0 {
; CHECK-LABEL: splice_nxv16f16_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 16 x half> @llvm.experimental.vector.splice.nxv16f16(<vscale x 16 x half> %a, <vscale x 16 x half> %b, i32 0)
ret <vscale x 16 x half> %res
}
define <vscale x 16 x half> @splice_nxv16f16_offset_negone(<vscale x 16 x half> %a, <vscale x 16 x half> %b) #0 {
; CHECK-LABEL: splice_nxv16f16_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e16, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v12, 1
; CHECK-NEXT: ret
%res = call <vscale x 16 x half> @llvm.experimental.vector.splice.nxv16f16(<vscale x 16 x half> %a, <vscale x 16 x half> %b, i32 -1)
ret <vscale x 16 x half> %res
}
define <vscale x 16 x half> @splice_nxv16f16_offset_min(<vscale x 16 x half> %a, <vscale x 16 x half> %b) #0 {
; CHECK-LABEL: splice_nxv16f16_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -32
; CHECK-NEXT: li a1, 32
; CHECK-NEXT: vsetvli zero, a1, e16, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v12, a1
; CHECK-NEXT: ret
%res = call <vscale x 16 x half> @llvm.experimental.vector.splice.nxv16f16(<vscale x 16 x half> %a, <vscale x 16 x half> %b, i32 -32)
ret <vscale x 16 x half> %res
}
define <vscale x 16 x half> @splice_nxv16f16_offset_max(<vscale x 16 x half> %a, <vscale x 16 x half> %b) #0 {
; CHECK-LABEL: splice_nxv16f16_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -31
; CHECK-NEXT: vsetvli zero, a0, e16, m4, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 31
; CHECK-NEXT: vsetvli a1, zero, e16, m4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v12, a0
; CHECK-NEXT: ret
%res = call <vscale x 16 x half> @llvm.experimental.vector.splice.nxv16f16(<vscale x 16 x half> %a, <vscale x 16 x half> %b, i32 31)
ret <vscale x 16 x half> %res
}
declare <vscale x 32 x half> @llvm.experimental.vector.splice.nxv32f16(<vscale x 32 x half>, <vscale x 32 x half>, i32)
define <vscale x 32 x half> @splice_nxv32f16_offset_zero(<vscale x 32 x half> %a, <vscale x 32 x half> %b) #0 {
; CHECK-LABEL: splice_nxv32f16_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 32 x half> @llvm.experimental.vector.splice.nxv32f16(<vscale x 32 x half> %a, <vscale x 32 x half> %b, i32 0)
ret <vscale x 32 x half> %res
}
define <vscale x 32 x half> @splice_nxv32f16_offset_negone(<vscale x 32 x half> %a, <vscale x 32 x half> %b) #0 {
; CHECK-LABEL: splice_nxv32f16_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e16, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m8, tu, mu
; CHECK-NEXT: vslideup.vi v8, v16, 1
; CHECK-NEXT: ret
%res = call <vscale x 32 x half> @llvm.experimental.vector.splice.nxv32f16(<vscale x 32 x half> %a, <vscale x 32 x half> %b, i32 -1)
ret <vscale x 32 x half> %res
}
define <vscale x 32 x half> @splice_nxv32f16_offset_min(<vscale x 32 x half> %a, <vscale x 32 x half> %b) #0 {
; CHECK-LABEL: splice_nxv32f16_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -64
; CHECK-NEXT: li a1, 64
; CHECK-NEXT: vsetvli zero, a1, e16, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e16, m8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v16, a1
; CHECK-NEXT: ret
%res = call <vscale x 32 x half> @llvm.experimental.vector.splice.nxv32f16(<vscale x 32 x half> %a, <vscale x 32 x half> %b, i32 -64)
ret <vscale x 32 x half> %res
}
define <vscale x 32 x half> @splice_nxv32f16_offset_max(<vscale x 32 x half> %a, <vscale x 32 x half> %b) #0 {
; CHECK-LABEL: splice_nxv32f16_offset_max:
; CHECK: # %bb.0:
; 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, e16, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a1
; CHECK-NEXT: vsetvli a1, zero, e16, m8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v16, a0
; CHECK-NEXT: ret
%res = call <vscale x 32 x half> @llvm.experimental.vector.splice.nxv32f16(<vscale x 32 x half> %a, <vscale x 32 x half> %b, i32 63)
ret <vscale x 32 x half> %res
}
declare <vscale x 1 x float> @llvm.experimental.vector.splice.nxv1f32(<vscale x 1 x float>, <vscale x 1 x float>, i32)
define <vscale x 1 x float> @splice_nxv1f32_offset_zero(<vscale x 1 x float> %a, <vscale x 1 x float> %b) #0 {
; CHECK-LABEL: splice_nxv1f32_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 1 x float> @llvm.experimental.vector.splice.nxv1f32(<vscale x 1 x float> %a, <vscale x 1 x float> %b, i32 0)
ret <vscale x 1 x float> %res
}
define <vscale x 1 x float> @splice_nxv1f32_offset_negone(<vscale x 1 x float> %a, <vscale x 1 x float> %b) #0 {
; CHECK-LABEL: splice_nxv1f32_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e32, mf2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, mf2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 1 x float> @llvm.experimental.vector.splice.nxv1f32(<vscale x 1 x float> %a, <vscale x 1 x float> %b, i32 -1)
ret <vscale x 1 x float> %res
}
define <vscale x 1 x float> @splice_nxv1f32_offset_min(<vscale x 1 x float> %a, <vscale x 1 x float> %b) #0 {
; CHECK-LABEL: splice_nxv1f32_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -2
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, mf2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 2
; CHECK-NEXT: ret
%res = call <vscale x 1 x float> @llvm.experimental.vector.splice.nxv1f32(<vscale x 1 x float> %a, <vscale x 1 x float> %b, i32 -2)
ret <vscale x 1 x float> %res
}
define <vscale x 1 x float> @splice_nxv1f32_offset_max(<vscale x 1 x float> %a, <vscale x 1 x float> %b) #0 {
; CHECK-LABEL: splice_nxv1f32_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 1
; CHECK-NEXT: vsetvli a1, zero, e32, mf2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 1 x float> @llvm.experimental.vector.splice.nxv1f32(<vscale x 1 x float> %a, <vscale x 1 x float> %b, i32 1)
ret <vscale x 1 x float> %res
}
declare <vscale x 2 x float> @llvm.experimental.vector.splice.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float>, i32)
define <vscale x 2 x float> @splice_nxv2f32_offset_zero(<vscale x 2 x float> %a, <vscale x 2 x float> %b) #0 {
; CHECK-LABEL: splice_nxv2f32_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 2 x float> @llvm.experimental.vector.splice.nxv2f32(<vscale x 2 x float> %a, <vscale x 2 x float> %b, i32 0)
ret <vscale x 2 x float> %res
}
define <vscale x 2 x float> @splice_nxv2f32_offset_negone(<vscale x 2 x float> %a, <vscale x 2 x float> %b) #0 {
; CHECK-LABEL: splice_nxv2f32_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e32, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 2 x float> @llvm.experimental.vector.splice.nxv2f32(<vscale x 2 x float> %a, <vscale x 2 x float> %b, i32 -1)
ret <vscale x 2 x float> %res
}
define <vscale x 2 x float> @splice_nxv2f32_offset_min(<vscale x 2 x float> %a, <vscale x 2 x float> %b) #0 {
; CHECK-LABEL: splice_nxv2f32_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -4
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 4
; CHECK-NEXT: ret
%res = call <vscale x 2 x float> @llvm.experimental.vector.splice.nxv2f32(<vscale x 2 x float> %a, <vscale x 2 x float> %b, i32 -4)
ret <vscale x 2 x float> %res
}
define <vscale x 2 x float> @splice_nxv2f32_offset_max(<vscale x 2 x float> %a, <vscale x 2 x float> %b) #0 {
; CHECK-LABEL: splice_nxv2f32_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -3
; CHECK-NEXT: vsetvli zero, a0, e32, m1, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 3
; CHECK-NEXT: vsetvli a1, zero, e32, m1, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 2 x float> @llvm.experimental.vector.splice.nxv2f32(<vscale x 2 x float> %a, <vscale x 2 x float> %b, i32 3)
ret <vscale x 2 x float> %res
}
declare <vscale x 4 x float> @llvm.experimental.vector.splice.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, i32)
define <vscale x 4 x float> @splice_nxv4f32_offset_zero(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
; CHECK-LABEL: splice_nxv4f32_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 4 x float> @llvm.experimental.vector.splice.nxv4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b, i32 0)
ret <vscale x 4 x float> %res
}
define <vscale x 4 x float> @splice_nxv4f32_offset_negone(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
; CHECK-LABEL: splice_nxv4f32_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e32, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 1
; CHECK-NEXT: ret
%res = call <vscale x 4 x float> @llvm.experimental.vector.splice.nxv4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b, i32 -1)
ret <vscale x 4 x float> %res
}
define <vscale x 4 x float> @splice_nxv4f32_offset_min(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
; CHECK-LABEL: splice_nxv4f32_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -8
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 8
; CHECK-NEXT: ret
%res = call <vscale x 4 x float> @llvm.experimental.vector.splice.nxv4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b, i32 -8)
ret <vscale x 4 x float> %res
}
define <vscale x 4 x float> @splice_nxv4f32_offset_max(<vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
; CHECK-LABEL: splice_nxv4f32_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -7
; CHECK-NEXT: vsetvli zero, a0, e32, m2, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 7
; CHECK-NEXT: vsetvli a1, zero, e32, m2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v10, a0
; CHECK-NEXT: ret
%res = call <vscale x 4 x float> @llvm.experimental.vector.splice.nxv4f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b, i32 7)
ret <vscale x 4 x float> %res
}
declare <vscale x 8 x float> @llvm.experimental.vector.splice.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>, i32)
define <vscale x 8 x float> @splice_nxv8f32_offset_zero(<vscale x 8 x float> %a, <vscale x 8 x float> %b) #0 {
; CHECK-LABEL: splice_nxv8f32_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 8 x float> @llvm.experimental.vector.splice.nxv8f32(<vscale x 8 x float> %a, <vscale x 8 x float> %b, i32 0)
ret <vscale x 8 x float> %res
}
define <vscale x 8 x float> @splice_nxv8f32_offset_negone(<vscale x 8 x float> %a, <vscale x 8 x float> %b) #0 {
; CHECK-LABEL: splice_nxv8f32_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e32, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v12, 1
; CHECK-NEXT: ret
%res = call <vscale x 8 x float> @llvm.experimental.vector.splice.nxv8f32(<vscale x 8 x float> %a, <vscale x 8 x float> %b, i32 -1)
ret <vscale x 8 x float> %res
}
define <vscale x 8 x float> @splice_nxv8f32_offset_min(<vscale x 8 x float> %a, <vscale x 8 x float> %b) #0 {
; CHECK-LABEL: splice_nxv8f32_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -16
; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v12, 16
; CHECK-NEXT: ret
%res = call <vscale x 8 x float> @llvm.experimental.vector.splice.nxv8f32(<vscale x 8 x float> %a, <vscale x 8 x float> %b, i32 -16)
ret <vscale x 8 x float> %res
}
define <vscale x 8 x float> @splice_nxv8f32_offset_max(<vscale x 8 x float> %a, <vscale x 8 x float> %b) #0 {
; CHECK-LABEL: splice_nxv8f32_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -15
; CHECK-NEXT: vsetvli zero, a0, e32, m4, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 15
; CHECK-NEXT: vsetvli a1, zero, e32, m4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v12, a0
; CHECK-NEXT: ret
%res = call <vscale x 8 x float> @llvm.experimental.vector.splice.nxv8f32(<vscale x 8 x float> %a, <vscale x 8 x float> %b, i32 15)
ret <vscale x 8 x float> %res
}
declare <vscale x 16 x float> @llvm.experimental.vector.splice.nxv16f32(<vscale x 16 x float>, <vscale x 16 x float>, i32)
define <vscale x 16 x float> @splice_nxv16f32_offset_zero(<vscale x 16 x float> %a, <vscale x 16 x float> %b) #0 {
; CHECK-LABEL: splice_nxv16f32_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 16 x float> @llvm.experimental.vector.splice.nxv16f32(<vscale x 16 x float> %a, <vscale x 16 x float> %b, i32 0)
ret <vscale x 16 x float> %res
}
define <vscale x 16 x float> @splice_nxv16f32_offset_negone(<vscale x 16 x float> %a, <vscale x 16 x float> %b) #0 {
; CHECK-LABEL: splice_nxv16f32_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e32, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m8, tu, mu
; CHECK-NEXT: vslideup.vi v8, v16, 1
; CHECK-NEXT: ret
%res = call <vscale x 16 x float> @llvm.experimental.vector.splice.nxv16f32(<vscale x 16 x float> %a, <vscale x 16 x float> %b, i32 -1)
ret <vscale x 16 x float> %res
}
define <vscale x 16 x float> @splice_nxv16f32_offset_min(<vscale x 16 x float> %a, <vscale x 16 x float> %b) #0 {
; CHECK-LABEL: splice_nxv16f32_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -32
; CHECK-NEXT: li a1, 32
; CHECK-NEXT: vsetvli zero, a1, e32, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e32, m8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v16, a1
; CHECK-NEXT: ret
%res = call <vscale x 16 x float> @llvm.experimental.vector.splice.nxv16f32(<vscale x 16 x float> %a, <vscale x 16 x float> %b, i32 -32)
ret <vscale x 16 x float> %res
}
define <vscale x 16 x float> @splice_nxv16f32_offset_max(<vscale x 16 x float> %a, <vscale x 16 x float> %b) #0 {
; CHECK-LABEL: splice_nxv16f32_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -31
; CHECK-NEXT: vsetvli zero, a0, e32, m8, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 31
; CHECK-NEXT: vsetvli a1, zero, e32, m8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v16, a0
; CHECK-NEXT: ret
%res = call <vscale x 16 x float> @llvm.experimental.vector.splice.nxv16f32(<vscale x 16 x float> %a, <vscale x 16 x float> %b, i32 31)
ret <vscale x 16 x float> %res
}
declare <vscale x 1 x double> @llvm.experimental.vector.splice.nxv1f64(<vscale x 1 x double>, <vscale x 1 x double>, i32)
define <vscale x 1 x double> @splice_nxv1f64_offset_zero(<vscale x 1 x double> %a, <vscale x 1 x double> %b) #0 {
; CHECK-LABEL: splice_nxv1f64_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 1 x double> @llvm.experimental.vector.splice.nxv1f64(<vscale x 1 x double> %a, <vscale x 1 x double> %b, i32 0)
ret <vscale x 1 x double> %res
}
define <vscale x 1 x double> @splice_nxv1f64_offset_negone(<vscale x 1 x double> %a, <vscale x 1 x double> %b) #0 {
; CHECK-LABEL: splice_nxv1f64_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e64, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 1
; CHECK-NEXT: ret
%res = call <vscale x 1 x double> @llvm.experimental.vector.splice.nxv1f64(<vscale x 1 x double> %a, <vscale x 1 x double> %b, i32 -1)
ret <vscale x 1 x double> %res
}
define <vscale x 1 x double> @splice_nxv1f64_offset_min(<vscale x 1 x double> %a, <vscale x 1 x double> %b) #0 {
; CHECK-LABEL: splice_nxv1f64_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -2
; CHECK-NEXT: vsetivli zero, 2, e64, m1, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m1, tu, mu
; CHECK-NEXT: vslideup.vi v8, v9, 2
; CHECK-NEXT: ret
%res = call <vscale x 1 x double> @llvm.experimental.vector.splice.nxv1f64(<vscale x 1 x double> %a, <vscale x 1 x double> %b, i32 -2)
ret <vscale x 1 x double> %res
}
define <vscale x 1 x double> @splice_nxv1f64_offset_max(<vscale x 1 x double> %a, <vscale x 1 x double> %b) #0 {
; CHECK-LABEL: splice_nxv1f64_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 3
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetvli zero, a0, e64, m1, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 1
; CHECK-NEXT: vsetvli a1, zero, e64, m1, tu, mu
; CHECK-NEXT: vslideup.vx v8, v9, a0
; CHECK-NEXT: ret
%res = call <vscale x 1 x double> @llvm.experimental.vector.splice.nxv1f64(<vscale x 1 x double> %a, <vscale x 1 x double> %b, i32 1)
ret <vscale x 1 x double> %res
}
declare <vscale x 2 x double> @llvm.experimental.vector.splice.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, i32)
define <vscale x 2 x double> @splice_nxv2f64_offset_zero(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
; CHECK-LABEL: splice_nxv2f64_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 2 x double> @llvm.experimental.vector.splice.nxv2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b, i32 0)
ret <vscale x 2 x double> %res
}
define <vscale x 2 x double> @splice_nxv2f64_offset_negone(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
; CHECK-LABEL: splice_nxv2f64_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e64, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 1
; CHECK-NEXT: ret
%res = call <vscale x 2 x double> @llvm.experimental.vector.splice.nxv2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b, i32 -1)
ret <vscale x 2 x double> %res
}
define <vscale x 2 x double> @splice_nxv2f64_offset_min(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
; CHECK-LABEL: splice_nxv2f64_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -4
; CHECK-NEXT: vsetivli zero, 4, e64, m2, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m2, tu, mu
; CHECK-NEXT: vslideup.vi v8, v10, 4
; CHECK-NEXT: ret
%res = call <vscale x 2 x double> @llvm.experimental.vector.splice.nxv2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b, i32 -4)
ret <vscale x 2 x double> %res
}
define <vscale x 2 x double> @splice_nxv2f64_offset_max(<vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
; CHECK-LABEL: splice_nxv2f64_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 2
; CHECK-NEXT: addi a0, a0, -3
; CHECK-NEXT: vsetvli zero, a0, e64, m2, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 3
; CHECK-NEXT: vsetvli a1, zero, e64, m2, tu, mu
; CHECK-NEXT: vslideup.vx v8, v10, a0
; CHECK-NEXT: ret
%res = call <vscale x 2 x double> @llvm.experimental.vector.splice.nxv2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b, i32 3)
ret <vscale x 2 x double> %res
}
declare <vscale x 4 x double> @llvm.experimental.vector.splice.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>, i32)
define <vscale x 4 x double> @splice_nxv4f64_offset_zero(<vscale x 4 x double> %a, <vscale x 4 x double> %b) #0 {
; CHECK-LABEL: splice_nxv4f64_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 4 x double> @llvm.experimental.vector.splice.nxv4f64(<vscale x 4 x double> %a, <vscale x 4 x double> %b, i32 0)
ret <vscale x 4 x double> %res
}
define <vscale x 4 x double> @splice_nxv4f64_offset_negone(<vscale x 4 x double> %a, <vscale x 4 x double> %b) #0 {
; CHECK-LABEL: splice_nxv4f64_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e64, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v12, 1
; CHECK-NEXT: ret
%res = call <vscale x 4 x double> @llvm.experimental.vector.splice.nxv4f64(<vscale x 4 x double> %a, <vscale x 4 x double> %b, i32 -1)
ret <vscale x 4 x double> %res
}
define <vscale x 4 x double> @splice_nxv4f64_offset_min(<vscale x 4 x double> %a, <vscale x 4 x double> %b) #0 {
; CHECK-LABEL: splice_nxv4f64_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -8
; CHECK-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m4, tu, mu
; CHECK-NEXT: vslideup.vi v8, v12, 8
; CHECK-NEXT: ret
%res = call <vscale x 4 x double> @llvm.experimental.vector.splice.nxv4f64(<vscale x 4 x double> %a, <vscale x 4 x double> %b, i32 -8)
ret <vscale x 4 x double> %res
}
define <vscale x 4 x double> @splice_nxv4f64_offset_max(<vscale x 4 x double> %a, <vscale x 4 x double> %b) #0 {
; CHECK-LABEL: splice_nxv4f64_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: srli a0, a0, 1
; CHECK-NEXT: addi a0, a0, -7
; CHECK-NEXT: vsetvli zero, a0, e64, m4, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 7
; CHECK-NEXT: vsetvli a1, zero, e64, m4, tu, mu
; CHECK-NEXT: vslideup.vx v8, v12, a0
; CHECK-NEXT: ret
%res = call <vscale x 4 x double> @llvm.experimental.vector.splice.nxv4f64(<vscale x 4 x double> %a, <vscale x 4 x double> %b, i32 7)
ret <vscale x 4 x double> %res
}
declare <vscale x 8 x double> @llvm.experimental.vector.splice.nxv8f64(<vscale x 8 x double>, <vscale x 8 x double>, i32)
define <vscale x 8 x double> @splice_nxv8f64_offset_zero(<vscale x 8 x double> %a, <vscale x 8 x double> %b) #0 {
; CHECK-LABEL: splice_nxv8f64_offset_zero:
; CHECK: # %bb.0:
; CHECK-NEXT: ret
%res = call <vscale x 8 x double> @llvm.experimental.vector.splice.nxv8f64(<vscale x 8 x double> %a, <vscale x 8 x double> %b, i32 0)
ret <vscale x 8 x double> %res
}
define <vscale x 8 x double> @splice_nxv8f64_offset_negone(<vscale x 8 x double> %a, <vscale x 8 x double> %b) #0 {
; CHECK-LABEL: splice_nxv8f64_offset_negone:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -1
; CHECK-NEXT: vsetivli zero, 1, e64, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m8, tu, mu
; CHECK-NEXT: vslideup.vi v8, v16, 1
; CHECK-NEXT: ret
%res = call <vscale x 8 x double> @llvm.experimental.vector.splice.nxv8f64(<vscale x 8 x double> %a, <vscale x 8 x double> %b, i32 -1)
ret <vscale x 8 x double> %res
}
define <vscale x 8 x double> @splice_nxv8f64_offset_min(<vscale x 8 x double> %a, <vscale x 8 x double> %b) #0 {
; CHECK-LABEL: splice_nxv8f64_offset_min:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -16
; CHECK-NEXT: vsetivli zero, 16, e64, m8, ta, mu
; CHECK-NEXT: vslidedown.vx v8, v8, a0
; CHECK-NEXT: vsetvli a0, zero, e64, m8, tu, mu
; CHECK-NEXT: vslideup.vi v8, v16, 16
; CHECK-NEXT: ret
%res = call <vscale x 8 x double> @llvm.experimental.vector.splice.nxv8f64(<vscale x 8 x double> %a, <vscale x 8 x double> %b, i32 -16)
ret <vscale x 8 x double> %res
}
define <vscale x 8 x double> @splice_nxv8f64_offset_max(<vscale x 8 x double> %a, <vscale x 8 x double> %b) #0 {
; CHECK-LABEL: splice_nxv8f64_offset_max:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: addi a0, a0, -15
; CHECK-NEXT: vsetvli zero, a0, e64, m8, ta, mu
; CHECK-NEXT: vslidedown.vi v8, v8, 15
; CHECK-NEXT: vsetvli a1, zero, e64, m8, tu, mu
; CHECK-NEXT: vslideup.vx v8, v16, a0
; CHECK-NEXT: ret
%res = call <vscale x 8 x double> @llvm.experimental.vector.splice.nxv8f64(<vscale x 8 x double> %a, <vscale x 8 x double> %b, i32 15)
ret <vscale x 8 x double> %res
}
attributes #0 = { vscale_range(2,2) }