// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsub.nxv1i16.nxv1i8.nxv1i8.i64(<vscale x 1 x i8> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsub.nxv1i16.nxv1i8.i8.i64(<vscale x 1 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsub.w.nxv1i16.nxv1i8.i64(<vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsub.w.nxv1i16.i8.i64(<vscale x 1 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsub.nxv2i16.nxv2i8.nxv2i8.i64(<vscale x 2 x i8> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsub.nxv2i16.nxv2i8.i8.i64(<vscale x 2 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsub.w.nxv2i16.nxv2i8.i64(<vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsub.w.nxv2i16.i8.i64(<vscale x 2 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsub.nxv4i16.nxv4i8.nxv4i8.i64(<vscale x 4 x i8> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsub.nxv4i16.nxv4i8.i8.i64(<vscale x 4 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsub.w.nxv4i16.nxv4i8.i64(<vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsub.w.nxv4i16.i8.i64(<vscale x 4 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsub.nxv8i16.nxv8i8.nxv8i8.i64(<vscale x 8 x i8> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsub.nxv8i16.nxv8i8.i8.i64(<vscale x 8 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsub.w.nxv8i16.nxv8i8.i64(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsub.w.nxv8i16.i8.i64(<vscale x 8 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsub.nxv16i16.nxv16i8.nxv16i8.i64(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsub.nxv16i16.nxv16i8.i8.i64(<vscale x 16 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsub.w.nxv16i16.nxv16i8.i64(<vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsub.w.nxv16i16.i8.i64(<vscale x 16 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsub.nxv32i16.nxv32i8.nxv32i8.i64(<vscale x 32 x i8> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsub.nxv32i16.nxv32i8.i8.i64(<vscale x 32 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsub.w.nxv32i16.nxv32i8.i64(<vscale x 32 x i16> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsub.w.nxv32i16.i8.i64(<vscale x 32 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsub.nxv1i32.nxv1i16.nxv1i16.i64(<vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsub.nxv1i32.nxv1i16.i16.i64(<vscale x 1 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsub.w.nxv1i32.nxv1i16.i64(<vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsub.w.nxv1i32.i16.i64(<vscale x 1 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsub.nxv2i32.nxv2i16.nxv2i16.i64(<vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsub.nxv2i32.nxv2i16.i16.i64(<vscale x 2 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsub.w.nxv2i32.nxv2i16.i64(<vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsub.w.nxv2i32.i16.i64(<vscale x 2 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsub.nxv4i32.nxv4i16.nxv4i16.i64(<vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsub.nxv4i32.nxv4i16.i16.i64(<vscale x 4 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsub.w.nxv4i32.nxv4i16.i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsub.w.nxv4i32.i16.i64(<vscale x 4 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsub.nxv8i32.nxv8i16.nxv8i16.i64(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsub.nxv8i32.nxv8i16.i16.i64(<vscale x 8 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsub.w.nxv8i32.nxv8i16.i64(<vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsub.w.nxv8i32.i16.i64(<vscale x 8 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsub.nxv16i32.nxv16i16.nxv16i16.i64(<vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsub.nxv16i32.nxv16i16.i16.i64(<vscale x 16 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsub.w.nxv16i32.nxv16i16.i64(<vscale x 16 x i32> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsub.w.nxv16i32.i16.i64(<vscale x 16 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsub.nxv1i64.nxv1i32.nxv1i32.i64(<vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsub.nxv1i64.nxv1i32.i32.i64(<vscale x 1 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsub.w.nxv1i64.nxv1i32.i64(<vscale x 1 x i64> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsub.w.nxv1i64.i32.i64(<vscale x 1 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsub.nxv2i64.nxv2i32.nxv2i32.i64(<vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsub.nxv2i64.nxv2i32.i32.i64(<vscale x 2 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsub.w.nxv2i64.nxv2i32.i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsub.w.nxv2i64.i32.i64(<vscale x 2 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsub.nxv4i64.nxv4i32.nxv4i32.i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsub.nxv4i64.nxv4i32.i32.i64(<vscale x 4 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsub.w.nxv4i64.nxv4i32.i64(<vscale x 4 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsub.w.nxv4i64.i32.i64(<vscale x 4 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsub.nxv8i64.nxv8i32.nxv8i32.i64(<vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsub.nxv8i64.nxv8i32.i32.i64(<vscale x 8 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsub.w.nxv8i64.nxv8i32.i64(<vscale x 8 x i64> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsub.w.nxv8i64.i32.i64(<vscale x 8 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsubu.nxv1i16.nxv1i8.nxv1i8.i64(<vscale x 1 x i8> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsubu.nxv1i16.nxv1i8.i8.i64(<vscale x 1 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsubu.w.nxv1i16.nxv1i8.i64(<vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsubu.w.nxv1i16.i8.i64(<vscale x 1 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsubu.nxv2i16.nxv2i8.nxv2i8.i64(<vscale x 2 x i8> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsubu.nxv2i16.nxv2i8.i8.i64(<vscale x 2 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsubu.w.nxv2i16.nxv2i8.i64(<vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsubu.w.nxv2i16.i8.i64(<vscale x 2 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsubu.nxv4i16.nxv4i8.nxv4i8.i64(<vscale x 4 x i8> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsubu.nxv4i16.nxv4i8.i8.i64(<vscale x 4 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsubu.w.nxv4i16.nxv4i8.i64(<vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsubu.w.nxv4i16.i8.i64(<vscale x 4 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsubu.nxv8i16.nxv8i8.nxv8i8.i64(<vscale x 8 x i8> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsubu.nxv8i16.nxv8i8.i8.i64(<vscale x 8 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsubu.w.nxv8i16.nxv8i8.i64(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsubu.w.nxv8i16.i8.i64(<vscale x 8 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsubu.nxv16i16.nxv16i8.nxv16i8.i64(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsubu.nxv16i16.nxv16i8.i8.i64(<vscale x 16 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsubu.w.nxv16i16.nxv16i8.i64(<vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsubu.w.nxv16i16.i8.i64(<vscale x 16 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsubu.nxv32i16.nxv32i8.nxv32i8.i64(<vscale x 32 x i8> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsubu.nxv32i16.nxv32i8.i8.i64(<vscale x 32 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsubu.w.nxv32i16.nxv32i8.i64(<vscale x 32 x i16> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsubu.w.nxv32i16.i8.i64(<vscale x 32 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsubu.nxv1i32.nxv1i16.nxv1i16.i64(<vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsubu.nxv1i32.nxv1i16.i16.i64(<vscale x 1 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsubu.w.nxv1i32.nxv1i16.i64(<vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsubu.w.nxv1i32.i16.i64(<vscale x 1 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsubu.nxv2i32.nxv2i16.nxv2i16.i64(<vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsubu.nxv2i32.nxv2i16.i16.i64(<vscale x 2 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsubu.w.nxv2i32.nxv2i16.i64(<vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsubu.w.nxv2i32.i16.i64(<vscale x 2 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsubu.nxv4i32.nxv4i16.nxv4i16.i64(<vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsubu.nxv4i32.nxv4i16.i16.i64(<vscale x 4 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsubu.w.nxv4i32.nxv4i16.i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsubu.w.nxv4i32.i16.i64(<vscale x 4 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsubu.nxv8i32.nxv8i16.nxv8i16.i64(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsubu.nxv8i32.nxv8i16.i16.i64(<vscale x 8 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsubu.w.nxv8i32.nxv8i16.i64(<vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsubu.w.nxv8i32.i16.i64(<vscale x 8 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsubu.nxv16i32.nxv16i16.nxv16i16.i64(<vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsubu.nxv16i32.nxv16i16.i16.i64(<vscale x 16 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsubu.w.nxv16i32.nxv16i16.i64(<vscale x 16 x i32> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsubu.w.nxv16i32.i16.i64(<vscale x 16 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsubu.nxv1i64.nxv1i32.nxv1i32.i64(<vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsubu.nxv1i64.nxv1i32.i32.i64(<vscale x 1 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsubu.w.nxv1i64.nxv1i32.i64(<vscale x 1 x i64> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsubu.w.nxv1i64.i32.i64(<vscale x 1 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsubu.nxv2i64.nxv2i32.nxv2i32.i64(<vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsubu.nxv2i64.nxv2i32.i32.i64(<vscale x 2 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsubu.w.nxv2i64.nxv2i32.i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsubu.w.nxv2i64.i32.i64(<vscale x 2 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsubu.nxv4i64.nxv4i32.nxv4i32.i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsubu.nxv4i64.nxv4i32.i32.i64(<vscale x 4 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsubu.w.nxv4i64.nxv4i32.i64(<vscale x 4 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsubu.w.nxv4i64.i32.i64(<vscale x 4 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsubu.nxv8i64.nxv8i32.nxv8i32.i64(<vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsubu.nxv8i64.nxv8i32.i32.i64(<vscale x 8 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsubu.w.nxv8i64.nxv8i32.i64(<vscale x 8 x i64> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsubu.w.nxv8i64.i32.i64(<vscale x 8 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsub.mask.nxv1i16.nxv1i8.nxv1i8.i64(<vscale x 1 x i16> [[MASKEDOFF:%.*]], <vscale x 1 x i8> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsub.mask.nxv1i16.nxv1i8.i8.i64(<vscale x 1 x i16> [[MASKEDOFF:%.*]], <vscale x 1 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsub.w.mask.nxv1i16.nxv1i8.i64(<vscale x 1 x i16> [[MASKEDOFF:%.*]], <vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsub.w.mask.nxv1i16.i8.i64(<vscale x 1 x i16> [[MASKEDOFF:%.*]], <vscale x 1 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsub.mask.nxv2i16.nxv2i8.nxv2i8.i64(<vscale x 2 x i16> [[MASKEDOFF:%.*]], <vscale x 2 x i8> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsub.mask.nxv2i16.nxv2i8.i8.i64(<vscale x 2 x i16> [[MASKEDOFF:%.*]], <vscale x 2 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsub.w.mask.nxv2i16.nxv2i8.i64(<vscale x 2 x i16> [[MASKEDOFF:%.*]], <vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsub.w.mask.nxv2i16.i8.i64(<vscale x 2 x i16> [[MASKEDOFF:%.*]], <vscale x 2 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsub.mask.nxv4i16.nxv4i8.nxv4i8.i64(<vscale x 4 x i16> [[MASKEDOFF:%.*]], <vscale x 4 x i8> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsub.mask.nxv4i16.nxv4i8.i8.i64(<vscale x 4 x i16> [[MASKEDOFF:%.*]], <vscale x 4 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsub.w.mask.nxv4i16.nxv4i8.i64(<vscale x 4 x i16> [[MASKEDOFF:%.*]], <vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsub.w.mask.nxv4i16.i8.i64(<vscale x 4 x i16> [[MASKEDOFF:%.*]], <vscale x 4 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsub.mask.nxv8i16.nxv8i8.nxv8i8.i64(<vscale x 8 x i16> [[MASKEDOFF:%.*]], <vscale x 8 x i8> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsub.mask.nxv8i16.nxv8i8.i8.i64(<vscale x 8 x i16> [[MASKEDOFF:%.*]], <vscale x 8 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsub.w.mask.nxv8i16.nxv8i8.i64(<vscale x 8 x i16> [[MASKEDOFF:%.*]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsub.w.mask.nxv8i16.i8.i64(<vscale x 8 x i16> [[MASKEDOFF:%.*]], <vscale x 8 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsub.mask.nxv16i16.nxv16i8.nxv16i8.i64(<vscale x 16 x i16> [[MASKEDOFF:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsub.mask.nxv16i16.nxv16i8.i8.i64(<vscale x 16 x i16> [[MASKEDOFF:%.*]], <vscale x 16 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsub.w.mask.nxv16i16.nxv16i8.i64(<vscale x 16 x i16> [[MASKEDOFF:%.*]], <vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsub.w.mask.nxv16i16.i8.i64(<vscale x 16 x i16> [[MASKEDOFF:%.*]], <vscale x 16 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsub.mask.nxv32i16.nxv32i8.nxv32i8.i64(<vscale x 32 x i16> [[MASKEDOFF:%.*]], <vscale x 32 x i8> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], <vscale x 32 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsub.mask.nxv32i16.nxv32i8.i8.i64(<vscale x 32 x i16> [[MASKEDOFF:%.*]], <vscale x 32 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 32 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsub.w.mask.nxv32i16.nxv32i8.i64(<vscale x 32 x i16> [[MASKEDOFF:%.*]], <vscale x 32 x i16> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], <vscale x 32 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsub.w.mask.nxv32i16.i8.i64(<vscale x 32 x i16> [[MASKEDOFF:%.*]], <vscale x 32 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 32 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsub.mask.nxv1i32.nxv1i16.nxv1i16.i64(<vscale x 1 x i32> [[MASKEDOFF:%.*]], <vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsub.mask.nxv1i32.nxv1i16.i16.i64(<vscale x 1 x i32> [[MASKEDOFF:%.*]], <vscale x 1 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsub.w.mask.nxv1i32.nxv1i16.i64(<vscale x 1 x i32> [[MASKEDOFF:%.*]], <vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsub.w.mask.nxv1i32.i16.i64(<vscale x 1 x i32> [[MASKEDOFF:%.*]], <vscale x 1 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsub.mask.nxv2i32.nxv2i16.nxv2i16.i64(<vscale x 2 x i32> [[MASKEDOFF:%.*]], <vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsub.mask.nxv2i32.nxv2i16.i16.i64(<vscale x 2 x i32> [[MASKEDOFF:%.*]], <vscale x 2 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsub.w.mask.nxv2i32.nxv2i16.i64(<vscale x 2 x i32> [[MASKEDOFF:%.*]], <vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsub.w.mask.nxv2i32.i16.i64(<vscale x 2 x i32> [[MASKEDOFF:%.*]], <vscale x 2 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsub.mask.nxv4i32.nxv4i16.nxv4i16.i64(<vscale x 4 x i32> [[MASKEDOFF:%.*]], <vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsub.mask.nxv4i32.nxv4i16.i16.i64(<vscale x 4 x i32> [[MASKEDOFF:%.*]], <vscale x 4 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsub.w.mask.nxv4i32.nxv4i16.i64(<vscale x 4 x i32> [[MASKEDOFF:%.*]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsub.w.mask.nxv4i32.i16.i64(<vscale x 4 x i32> [[MASKEDOFF:%.*]], <vscale x 4 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsub.mask.nxv8i32.nxv8i16.nxv8i16.i64(<vscale x 8 x i32> [[MASKEDOFF:%.*]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsub.mask.nxv8i32.nxv8i16.i16.i64(<vscale x 8 x i32> [[MASKEDOFF:%.*]], <vscale x 8 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsub.w.mask.nxv8i32.nxv8i16.i64(<vscale x 8 x i32> [[MASKEDOFF:%.*]], <vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsub.w.mask.nxv8i32.i16.i64(<vscale x 8 x i32> [[MASKEDOFF:%.*]], <vscale x 8 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsub.mask.nxv16i32.nxv16i16.nxv16i16.i64(<vscale x 16 x i32> [[MASKEDOFF:%.*]], <vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsub.mask.nxv16i32.nxv16i16.i16.i64(<vscale x 16 x i32> [[MASKEDOFF:%.*]], <vscale x 16 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsub.w.mask.nxv16i32.nxv16i16.i64(<vscale x 16 x i32> [[MASKEDOFF:%.*]], <vscale x 16 x i32> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsub.w.mask.nxv16i32.i16.i64(<vscale x 16 x i32> [[MASKEDOFF:%.*]], <vscale x 16 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsub.mask.nxv1i64.nxv1i32.nxv1i32.i64(<vscale x 1 x i64> [[MASKEDOFF:%.*]], <vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsub.mask.nxv1i64.nxv1i32.i32.i64(<vscale x 1 x i64> [[MASKEDOFF:%.*]], <vscale x 1 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsub.w.mask.nxv1i64.nxv1i32.i64(<vscale x 1 x i64> [[MASKEDOFF:%.*]], <vscale x 1 x i64> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsub.w.mask.nxv1i64.i32.i64(<vscale x 1 x i64> [[MASKEDOFF:%.*]], <vscale x 1 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsub.mask.nxv2i64.nxv2i32.nxv2i32.i64(<vscale x 2 x i64> [[MASKEDOFF:%.*]], <vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsub.mask.nxv2i64.nxv2i32.i32.i64(<vscale x 2 x i64> [[MASKEDOFF:%.*]], <vscale x 2 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsub.w.mask.nxv2i64.nxv2i32.i64(<vscale x 2 x i64> [[MASKEDOFF:%.*]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsub.w.mask.nxv2i64.i32.i64(<vscale x 2 x i64> [[MASKEDOFF:%.*]], <vscale x 2 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsub.mask.nxv4i64.nxv4i32.nxv4i32.i64(<vscale x 4 x i64> [[MASKEDOFF:%.*]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsub.mask.nxv4i64.nxv4i32.i32.i64(<vscale x 4 x i64> [[MASKEDOFF:%.*]], <vscale x 4 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsub.w.mask.nxv4i64.nxv4i32.i64(<vscale x 4 x i64> [[MASKEDOFF:%.*]], <vscale x 4 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsub.w.mask.nxv4i64.i32.i64(<vscale x 4 x i64> [[MASKEDOFF:%.*]], <vscale x 4 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsub.mask.nxv8i64.nxv8i32.nxv8i32.i64(<vscale x 8 x i64> [[MASKEDOFF:%.*]], <vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsub.mask.nxv8i64.nxv8i32.i32.i64(<vscale x 8 x i64> [[MASKEDOFF:%.*]], <vscale x 8 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsub.w.mask.nxv8i64.nxv8i32.i64(<vscale x 8 x i64> [[MASKEDOFF:%.*]], <vscale x 8 x i64> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsub.w.mask.nxv8i64.i32.i64(<vscale x 8 x i64> [[MASKEDOFF:%.*]], <vscale x 8 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsubu.mask.nxv1i16.nxv1i8.nxv1i8.i64(<vscale x 1 x i16> [[MASKEDOFF:%.*]], <vscale x 1 x i8> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsubu.mask.nxv1i16.nxv1i8.i8.i64(<vscale x 1 x i16> [[MASKEDOFF:%.*]], <vscale x 1 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsubu.w.mask.nxv1i16.nxv1i8.i64(<vscale x 1 x i16> [[MASKEDOFF:%.*]], <vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwsubu.w.mask.nxv1i16.i8.i64(<vscale x 1 x i16> [[MASKEDOFF:%.*]], <vscale x 1 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsubu.mask.nxv2i16.nxv2i8.nxv2i8.i64(<vscale x 2 x i16> [[MASKEDOFF:%.*]], <vscale x 2 x i8> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsubu.mask.nxv2i16.nxv2i8.i8.i64(<vscale x 2 x i16> [[MASKEDOFF:%.*]], <vscale x 2 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsubu.w.mask.nxv2i16.nxv2i8.i64(<vscale x 2 x i16> [[MASKEDOFF:%.*]], <vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwsubu.w.mask.nxv2i16.i8.i64(<vscale x 2 x i16> [[MASKEDOFF:%.*]], <vscale x 2 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsubu.mask.nxv4i16.nxv4i8.nxv4i8.i64(<vscale x 4 x i16> [[MASKEDOFF:%.*]], <vscale x 4 x i8> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsubu.mask.nxv4i16.nxv4i8.i8.i64(<vscale x 4 x i16> [[MASKEDOFF:%.*]], <vscale x 4 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsubu.w.mask.nxv4i16.nxv4i8.i64(<vscale x 4 x i16> [[MASKEDOFF:%.*]], <vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwsubu.w.mask.nxv4i16.i8.i64(<vscale x 4 x i16> [[MASKEDOFF:%.*]], <vscale x 4 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsubu.mask.nxv8i16.nxv8i8.nxv8i8.i64(<vscale x 8 x i16> [[MASKEDOFF:%.*]], <vscale x 8 x i8> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsubu.mask.nxv8i16.nxv8i8.i8.i64(<vscale x 8 x i16> [[MASKEDOFF:%.*]], <vscale x 8 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsubu.w.mask.nxv8i16.nxv8i8.i64(<vscale x 8 x i16> [[MASKEDOFF:%.*]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwsubu.w.mask.nxv8i16.i8.i64(<vscale x 8 x i16> [[MASKEDOFF:%.*]], <vscale x 8 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsubu.mask.nxv16i16.nxv16i8.nxv16i8.i64(<vscale x 16 x i16> [[MASKEDOFF:%.*]], <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsubu.mask.nxv16i16.nxv16i8.i8.i64(<vscale x 16 x i16> [[MASKEDOFF:%.*]], <vscale x 16 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsubu.w.mask.nxv16i16.nxv16i8.i64(<vscale x 16 x i16> [[MASKEDOFF:%.*]], <vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwsubu.w.mask.nxv16i16.i8.i64(<vscale x 16 x i16> [[MASKEDOFF:%.*]], <vscale x 16 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsubu.mask.nxv32i16.nxv32i8.nxv32i8.i64(<vscale x 32 x i16> [[MASKEDOFF:%.*]], <vscale x 32 x i8> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], <vscale x 32 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsubu.mask.nxv32i16.nxv32i8.i8.i64(<vscale x 32 x i16> [[MASKEDOFF:%.*]], <vscale x 32 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 32 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsubu.w.mask.nxv32i16.nxv32i8.i64(<vscale x 32 x i16> [[MASKEDOFF:%.*]], <vscale x 32 x i16> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], <vscale x 32 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwsubu.w.mask.nxv32i16.i8.i64(<vscale x 32 x i16> [[MASKEDOFF:%.*]], <vscale x 32 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], <vscale x 32 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsubu.mask.nxv1i32.nxv1i16.nxv1i16.i64(<vscale x 1 x i32> [[MASKEDOFF:%.*]], <vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsubu.mask.nxv1i32.nxv1i16.i16.i64(<vscale x 1 x i32> [[MASKEDOFF:%.*]], <vscale x 1 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsubu.w.mask.nxv1i32.nxv1i16.i64(<vscale x 1 x i32> [[MASKEDOFF:%.*]], <vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwsubu.w.mask.nxv1i32.i16.i64(<vscale x 1 x i32> [[MASKEDOFF:%.*]], <vscale x 1 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsubu.mask.nxv2i32.nxv2i16.nxv2i16.i64(<vscale x 2 x i32> [[MASKEDOFF:%.*]], <vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsubu.mask.nxv2i32.nxv2i16.i16.i64(<vscale x 2 x i32> [[MASKEDOFF:%.*]], <vscale x 2 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsubu.w.mask.nxv2i32.nxv2i16.i64(<vscale x 2 x i32> [[MASKEDOFF:%.*]], <vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwsubu.w.mask.nxv2i32.i16.i64(<vscale x 2 x i32> [[MASKEDOFF:%.*]], <vscale x 2 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsubu.mask.nxv4i32.nxv4i16.nxv4i16.i64(<vscale x 4 x i32> [[MASKEDOFF:%.*]], <vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsubu.mask.nxv4i32.nxv4i16.i16.i64(<vscale x 4 x i32> [[MASKEDOFF:%.*]], <vscale x 4 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsubu.w.mask.nxv4i32.nxv4i16.i64(<vscale x 4 x i32> [[MASKEDOFF:%.*]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwsubu.w.mask.nxv4i32.i16.i64(<vscale x 4 x i32> [[MASKEDOFF:%.*]], <vscale x 4 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsubu.mask.nxv8i32.nxv8i16.nxv8i16.i64(<vscale x 8 x i32> [[MASKEDOFF:%.*]], <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsubu.mask.nxv8i32.nxv8i16.i16.i64(<vscale x 8 x i32> [[MASKEDOFF:%.*]], <vscale x 8 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsubu.w.mask.nxv8i32.nxv8i16.i64(<vscale x 8 x i32> [[MASKEDOFF:%.*]], <vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwsubu.w.mask.nxv8i32.i16.i64(<vscale x 8 x i32> [[MASKEDOFF:%.*]], <vscale x 8 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsubu.mask.nxv16i32.nxv16i16.nxv16i16.i64(<vscale x 16 x i32> [[MASKEDOFF:%.*]], <vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsubu.mask.nxv16i32.nxv16i16.i16.i64(<vscale x 16 x i32> [[MASKEDOFF:%.*]], <vscale x 16 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsubu.w.mask.nxv16i32.nxv16i16.i64(<vscale x 16 x i32> [[MASKEDOFF:%.*]], <vscale x 16 x i32> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwsubu.w.mask.nxv16i32.i16.i64(<vscale x 16 x i32> [[MASKEDOFF:%.*]], <vscale x 16 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], <vscale x 16 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsubu.mask.nxv1i64.nxv1i32.nxv1i32.i64(<vscale x 1 x i64> [[MASKEDOFF:%.*]], <vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsubu.mask.nxv1i64.nxv1i32.i32.i64(<vscale x 1 x i64> [[MASKEDOFF:%.*]], <vscale x 1 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsubu.w.mask.nxv1i64.nxv1i32.i64(<vscale x 1 x i64> [[MASKEDOFF:%.*]], <vscale x 1 x i64> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwsubu.w.mask.nxv1i64.i32.i64(<vscale x 1 x i64> [[MASKEDOFF:%.*]], <vscale x 1 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 1 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsubu.mask.nxv2i64.nxv2i32.nxv2i32.i64(<vscale x 2 x i64> [[MASKEDOFF:%.*]], <vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsubu.mask.nxv2i64.nxv2i32.i32.i64(<vscale x 2 x i64> [[MASKEDOFF:%.*]], <vscale x 2 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsubu.w.mask.nxv2i64.nxv2i32.i64(<vscale x 2 x i64> [[MASKEDOFF:%.*]], <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwsubu.w.mask.nxv2i64.i32.i64(<vscale x 2 x i64> [[MASKEDOFF:%.*]], <vscale x 2 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 2 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsubu.mask.nxv4i64.nxv4i32.nxv4i32.i64(<vscale x 4 x i64> [[MASKEDOFF:%.*]], <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsubu.mask.nxv4i64.nxv4i32.i32.i64(<vscale x 4 x i64> [[MASKEDOFF:%.*]], <vscale x 4 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsubu.w.mask.nxv4i64.nxv4i32.i64(<vscale x 4 x i64> [[MASKEDOFF:%.*]], <vscale x 4 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwsubu.w.mask.nxv4i64.i32.i64(<vscale x 4 x i64> [[MASKEDOFF:%.*]], <vscale x 4 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 4 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsubu.mask.nxv8i64.nxv8i32.nxv8i32.i64(<vscale x 8 x i64> [[MASKEDOFF:%.*]], <vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsubu.mask.nxv8i64.nxv8i32.i32.i64(<vscale x 8 x i64> [[MASKEDOFF:%.*]], <vscale x 8 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsubu.w.mask.nxv8i64.nxv8i32.i64(<vscale x 8 x i64> [[MASKEDOFF:%.*]], <vscale x 8 x i64> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)
// CHECK-RV64-NEXT: [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwsubu.w.mask.nxv8i64.i32.i64(<vscale x 8 x i64> [[MASKEDOFF:%.*]], <vscale x 8 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], <vscale x 8 x i1> [[MASK:%.*]], i64 [[VL:%.*]], i64 0)