1 ; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
2 ; RUN: llc -mtriple=x86_64-unknown-unknown -mcpu=core-avx2 -stop-after expand-isel-pseudos -o - %s | FileCheck %s
4 declare void @llvm.masked.store.v16f32.p0v16f32(<16 x float>, <16 x float>*, i32, <16 x i1>)
5 declare <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>*, i32, <16 x i1>, <16 x float>)
7 define void @test_v16f() local_unnamed_addr {
8 ; CHECK-LABEL: name: test_v16f
10 ; CHECK: [[AVX_SET0_:%[0-9]+]]:vr256 = AVX_SET0
11 ; CHECK: [[VMASKMOVPSYrm:%[0-9]+]]:vr256 = VMASKMOVPSYrm [[AVX_SET0_]], %stack.0.stack_input_vec, 1, $noreg, 0, $noreg :: (load 32 from %ir.stack_input_vec, align 4)
12 ; CHECK: [[VMASKMOVPSYrm1:%[0-9]+]]:vr256 = VMASKMOVPSYrm [[AVX_SET0_]], %stack.0.stack_input_vec, 1, $noreg, 32, $noreg :: (load 32 from %ir.stack_input_vec + 32, align 4)
13 ; CHECK: VMASKMOVPSYmr %stack.1.stack_output_vec, 1, $noreg, 32, $noreg, [[AVX_SET0_]], killed [[VMASKMOVPSYrm1]] :: (store 32 into %ir.stack_output_vec + 32, align 4)
14 ; CHECK: VMASKMOVPSYmr %stack.1.stack_output_vec, 1, $noreg, 0, $noreg, [[AVX_SET0_]], killed [[VMASKMOVPSYrm]] :: (store 32 into %ir.stack_output_vec, align 4)
17 %stack_input_vec = alloca <16 x float>, align 64
18 %stack_output_vec = alloca <16 x float>, align 64
19 %masked_loaded_vec = call <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>* nonnull %stack_input_vec, i32 4, <16 x i1> undef, <16 x float> undef)
20 call void @llvm.masked.store.v16f32.p0v16f32(<16 x float> %masked_loaded_vec, <16 x float>* nonnull %stack_output_vec, i32 4, <16 x i1> undef)
24 declare void @llvm.masked.store.v8f64.p0v8f64(<8 x double>, <8 x double>*, i32, <8 x i1>)
25 declare <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>*, i32, <8 x i1>, <8 x double>)
27 define void @test_v8d() local_unnamed_addr {
28 ; CHECK-LABEL: name: test_v8d
30 ; CHECK: [[AVX_SET0_:%[0-9]+]]:vr256 = AVX_SET0
31 ; CHECK: [[VMASKMOVPDYrm:%[0-9]+]]:vr256 = VMASKMOVPDYrm [[AVX_SET0_]], %stack.0.stack_input_vec, 1, $noreg, 0, $noreg :: (load 32 from %ir.stack_input_vec, align 4)
32 ; CHECK: [[VMASKMOVPDYrm1:%[0-9]+]]:vr256 = VMASKMOVPDYrm [[AVX_SET0_]], %stack.0.stack_input_vec, 1, $noreg, 32, $noreg :: (load 32 from %ir.stack_input_vec + 32, align 4)
33 ; CHECK: VMASKMOVPDYmr %stack.1.stack_output_vec, 1, $noreg, 32, $noreg, [[AVX_SET0_]], killed [[VMASKMOVPDYrm1]] :: (store 32 into %ir.stack_output_vec + 32, align 4)
34 ; CHECK: VMASKMOVPDYmr %stack.1.stack_output_vec, 1, $noreg, 0, $noreg, [[AVX_SET0_]], killed [[VMASKMOVPDYrm]] :: (store 32 into %ir.stack_output_vec, align 4)
37 %stack_input_vec = alloca <8 x double>, align 64
38 %stack_output_vec = alloca <8 x double>, align 64
39 %masked_loaded_vec = call <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>* nonnull %stack_input_vec, i32 4, <8 x i1> undef, <8 x double> undef)
40 call void @llvm.masked.store.v8f64.p0v8f64(<8 x double> %masked_loaded_vec, <8 x double>* nonnull %stack_output_vec, i32 4, <8 x i1> undef)