llvm/llvm/test/CodeGen/RISCV/rvv/mul-combine.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+v -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK-RV32
; RUN: llc -mtriple=riscv64 -mattr=+v -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK-RV64

define <2 x i16> @test_v2i16(<2 x i16> %x) {
; CHECK-RV32-LABEL: test_v2i16:
; CHECK-RV32:       # %bb.0:
; CHECK-RV32-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
; CHECK-RV32-NEXT:    vsra.vi v8, v8, 7
; CHECK-RV32-NEXT:    ret
;
; CHECK-RV64-LABEL: test_v2i16:
; CHECK-RV64:       # %bb.0:
; CHECK-RV64-NEXT:    vsetivli zero, 4, e8, mf4, ta, ma
; CHECK-RV64-NEXT:    vsra.vi v8, v8, 7
; CHECK-RV64-NEXT:    ret
  %1 = lshr <2 x i16> %x, <i16 7, i16 7>
  %2 = and <2 x i16> %1, <i16 257, i16 257>
  %3 = mul <2 x i16> %2, <i16 255, i16 255>
  ret <2 x i16> %3
}

define <vscale x 2 x i16> @test_nxv2i16(<vscale x 2 x i16> %x) {
; CHECK-RV32-LABEL: test_nxv2i16:
; CHECK-RV32:       # %bb.0:
; CHECK-RV32-NEXT:    vsetvli a0, zero, e16, mf2, ta, ma
; CHECK-RV32-NEXT:    vsrl.vi v8, v8, 7
; CHECK-RV32-NEXT:    li a0, 257
; CHECK-RV32-NEXT:    vand.vx v8, v8, a0
; CHECK-RV32-NEXT:    vsll.vi v8, v8, 8
; CHECK-RV32-NEXT:    ret
;
; CHECK-RV64-LABEL: test_nxv2i16:
; CHECK-RV64:       # %bb.0:
; CHECK-RV64-NEXT:    vsetvli a0, zero, e16, mf2, ta, ma
; CHECK-RV64-NEXT:    vsrl.vi v8, v8, 7
; CHECK-RV64-NEXT:    li a0, 257
; CHECK-RV64-NEXT:    vand.vx v8, v8, a0
; CHECK-RV64-NEXT:    vsll.vi v8, v8, 8
; CHECK-RV64-NEXT:    ret
  %1 = lshr <vscale x 2 x i16> %x, splat (i16 7)
  %2 = and <vscale x 2 x i16> %1, splat (i16 257)
  %3 = mul <vscale x 2 x i16> %2, splat (i16 256)
  ret <vscale x 2 x i16> %3
}

define <2 x i32> @test_v2i32(<2 x i32> %x) {
; CHECK-RV32-LABEL: test_v2i32:
; CHECK-RV32:       # %bb.0:
; CHECK-RV32-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-RV32-NEXT:    vsra.vi v8, v8, 15
; CHECK-RV32-NEXT:    ret
;
; CHECK-RV64-LABEL: test_v2i32:
; CHECK-RV64:       # %bb.0:
; CHECK-RV64-NEXT:    vsetivli zero, 4, e16, mf2, ta, ma
; CHECK-RV64-NEXT:    vsra.vi v8, v8, 15
; CHECK-RV64-NEXT:    ret
  %1 = lshr <2 x i32> %x, <i32 15, i32 15>
  %2 = and <2 x i32> %1, <i32 65537, i32 65537>
  %3 = mul <2 x i32> %2, <i32 65535, i32 65535>
  ret <2 x i32> %3
}

define <vscale x 2 x i32> @test_nxv2i32(<vscale x 2 x i32> %x) {
; CHECK-RV32-LABEL: test_nxv2i32:
; CHECK-RV32:       # %bb.0:
; CHECK-RV32-NEXT:    vsetvli a0, zero, e16, m1, ta, ma
; CHECK-RV32-NEXT:    vsra.vi v8, v8, 15
; CHECK-RV32-NEXT:    ret
;
; CHECK-RV64-LABEL: test_nxv2i32:
; CHECK-RV64:       # %bb.0:
; CHECK-RV64-NEXT:    vsetvli a0, zero, e16, m1, ta, ma
; CHECK-RV64-NEXT:    vsra.vi v8, v8, 15
; CHECK-RV64-NEXT:    ret
  %1 = lshr <vscale x 2 x i32> %x, splat (i32 15)
  %2 = and <vscale x 2 x i32> %1, splat (i32 65537)
  %3 = mul <vscale x 2 x i32> %2, splat (i32 65535)
  ret <vscale x 2 x i32> %3
}

define <2 x i64> @test_v2i64(<2 x i64> %x) {
; CHECK-RV32-LABEL: test_v2i64:
; CHECK-RV32:       # %bb.0:
; CHECK-RV32-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
; CHECK-RV32-NEXT:    vsra.vi v8, v8, 31
; CHECK-RV32-NEXT:    ret
;
; CHECK-RV64-LABEL: test_v2i64:
; CHECK-RV64:       # %bb.0:
; CHECK-RV64-NEXT:    vsetivli zero, 4, e32, m1, ta, ma
; CHECK-RV64-NEXT:    vsra.vi v8, v8, 31
; CHECK-RV64-NEXT:    ret
  %1 = lshr <2 x i64> %x, <i64 31, i64 31>
  %2 = and <2 x i64> %1, <i64 4294967297, i64 4294967297>
  %3 = mul <2 x i64> %2, <i64 4294967295, i64 4294967295>
  ret <2 x i64> %3
}

define <vscale x 2 x i64> @test_nxv2i64(<vscale x 2 x i64> %x) {
; CHECK-RV32-LABEL: test_nxv2i64:
; CHECK-RV32:       # %bb.0:
; CHECK-RV32-NEXT:    vsetvli a0, zero, e32, m2, ta, ma
; CHECK-RV32-NEXT:    vsra.vi v8, v8, 31
; CHECK-RV32-NEXT:    ret
;
; CHECK-RV64-LABEL: test_nxv2i64:
; CHECK-RV64:       # %bb.0:
; CHECK-RV64-NEXT:    vsetvli a0, zero, e32, m2, ta, ma
; CHECK-RV64-NEXT:    vsra.vi v8, v8, 31
; CHECK-RV64-NEXT:    ret
  %1 = lshr <vscale x 2 x i64> %x, splat (i64 31)
  %2 = and <vscale x 2 x i64> %1, splat (i64 4294967297)
  %3 = mul <vscale x 2 x i64> %2, splat (i64 4294967295)
  ret <vscale x 2 x i64> %3
}