llvm/llvm/test/CodeGen/RISCV/rvv/vsha2ms.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: sed 's/iXLen/i32/g' %s | llc -mtriple=riscv32 -mattr=+v,+zvknha,+zvknhb \
; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
; RUN: sed 's/iXLen/i64/g' %s | llc -mtriple=riscv64 -mattr=+v,+zvknha,+zvknhb \
; RUN:   -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK
; RUN: sed 's/iXLen/i32/g' %s | not --crash llc -mtriple=riscv32 -mattr=+v,+zvknha 2>&1 \
; RUN:   | FileCheck --check-prefixes=CHECK-ERROR %s
; RUN: sed 's/iXLen/i64/g' %s | not --crash llc -mtriple=riscv64 -mattr=+v,+zvknha 2>&1 \
; RUN:   | FileCheck --check-prefixes=CHECK-ERROR %s

; CHECK-ERROR: LLVM ERROR: SEW=64 needs Zvknhb to be enabled.

declare <vscale x 4 x i32> @llvm.riscv.vsha2ms.nxv4i32.nxv4i32(
  <vscale x 4 x i32>,
  <vscale x 4 x i32>,
  <vscale x 4 x i32>,
  iXLen,
  iXLen)

define <vscale x 4 x i32> @intrinsic_vsha2ms_vv_nxv4i32_nxv4i32(<vscale x 4 x i32> %0, <vscale x 4 x i32> %1, <vscale x 4 x i32> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv4i32_nxv4i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a0, e32, m2, tu, ma
; CHECK-NEXT:    vsha2ms.vv v8, v10, v12
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 4 x i32> @llvm.riscv.vsha2ms.nxv4i32.nxv4i32(
    <vscale x 4 x i32> %0,
    <vscale x 4 x i32> %1,
    <vscale x 4 x i32> %2,
    iXLen %3,
    iXLen 2)

  ret <vscale x 4 x i32> %a
}

declare <vscale x 8 x i32> @llvm.riscv.vsha2ms.nxv8i32.nxv8i32(
  <vscale x 8 x i32>,
  <vscale x 8 x i32>,
  <vscale x 8 x i32>,
  iXLen,
  iXLen)

define <vscale x 8 x i32> @intrinsic_vsha2ms_vv_nxv8i32_nxv8i32(<vscale x 8 x i32> %0, <vscale x 8 x i32> %1, <vscale x 8 x i32> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv8i32_nxv8i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a0, e32, m4, tu, ma
; CHECK-NEXT:    vsha2ms.vv v8, v12, v16
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 8 x i32> @llvm.riscv.vsha2ms.nxv8i32.nxv8i32(
    <vscale x 8 x i32> %0,
    <vscale x 8 x i32> %1,
    <vscale x 8 x i32> %2,
    iXLen %3,
    iXLen 2)

  ret <vscale x 8 x i32> %a
}

declare <vscale x 16 x i32> @llvm.riscv.vsha2ms.nxv16i32.nxv16i32(
  <vscale x 16 x i32>,
  <vscale x 16 x i32>,
  <vscale x 16 x i32>,
  iXLen,
  iXLen)

define <vscale x 16 x i32> @intrinsic_vsha2ms_vv_nxv16i32_nxv16i32(<vscale x 16 x i32> %0, <vscale x 16 x i32> %1, <vscale x 16 x i32> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv16i32_nxv16i32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vl8re32.v v24, (a0)
; CHECK-NEXT:    vsetvli zero, a1, e32, m8, tu, ma
; CHECK-NEXT:    vsha2ms.vv v8, v16, v24
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 16 x i32> @llvm.riscv.vsha2ms.nxv16i32.nxv16i32(
    <vscale x 16 x i32> %0,
    <vscale x 16 x i32> %1,
    <vscale x 16 x i32> %2,
    iXLen %3,
    iXLen 2)

  ret <vscale x 16 x i32> %a
}

declare <vscale x 4 x i64> @llvm.riscv.vsha2ms.nxv4i64.nxv4i64(
  <vscale x 4 x i64>,
  <vscale x 4 x i64>,
  <vscale x 4 x i64>,
  iXLen,
  iXLen)

define <vscale x 4 x i64> @intrinsic_vsha2ms_vv_nxv4i64_nxv4i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1, <vscale x 4 x i64> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv4i64_nxv4i64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetvli zero, a0, e64, m4, tu, ma
; CHECK-NEXT:    vsha2ms.vv v8, v12, v16
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 4 x i64> @llvm.riscv.vsha2ms.nxv4i64.nxv4i64(
    <vscale x 4 x i64> %0,
    <vscale x 4 x i64> %1,
    <vscale x 4 x i64> %2,
    iXLen %3,
    iXLen 2)

  ret <vscale x 4 x i64> %a
}

declare <vscale x 8 x i64> @llvm.riscv.vsha2ms.nxv8i64.nxv8i64(
  <vscale x 8 x i64>,
  <vscale x 8 x i64>,
  <vscale x 8 x i64>,
  iXLen,
  iXLen)

define <vscale x 8 x i64> @intrinsic_vsha2ms_vv_nxv8i64_nxv8i64(<vscale x 8 x i64> %0, <vscale x 8 x i64> %1, <vscale x 8 x i64> %2, iXLen %3) nounwind {
; CHECK-LABEL: intrinsic_vsha2ms_vv_nxv8i64_nxv8i64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vl8re64.v v24, (a0)
; CHECK-NEXT:    vsetvli zero, a1, e64, m8, tu, ma
; CHECK-NEXT:    vsha2ms.vv v8, v16, v24
; CHECK-NEXT:    ret
entry:
  %a = call <vscale x 8 x i64> @llvm.riscv.vsha2ms.nxv8i64.nxv8i64(
    <vscale x 8 x i64> %0,
    <vscale x 8 x i64> %1,
    <vscale x 8 x i64> %2,
    iXLen %3,
    iXLen 2)

  ret <vscale x 8 x i64> %a
}