; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2 ; RUN: opt < %s -passes=infer-alignment -S | FileCheck %s ; InferAlignment should be able to prove vector alignment in the ; presence of a few mild address computation tricks. ; ------------------------------------------------------------------------------ ; alloca ; ------------------------------------------------------------------------------ define void @alloca(<2 x i64> %y) { ; CHECK-LABEL: define void @alloca ; CHECK-SAME: (<2 x i64> [[Y:%.*]]) { ; CHECK-NEXT: [[ALLOCA:%.*]] = alloca <2 x i64>, align 16 ; CHECK-NEXT: [[LOAD:%.*]] = load <2 x i64>, ptr [[ALLOCA]], align 16 ; CHECK-NEXT: store <2 x i64> [[Y]], ptr [[ALLOCA]], align 16 ; CHECK-NEXT: ret void ; %alloca = alloca <2 x i64> %load = load <2 x i64>, ptr %alloca, align 1 store <2 x i64> %y, ptr %alloca, align 1 ret void } ; ------------------------------------------------------------------------------ ; global ; ------------------------------------------------------------------------------ @x.vector = external global <2 x i64>, align 16 define void @global(<2 x i64> %y) { ; CHECK-LABEL: define void @global ; CHECK-SAME: (<2 x i64> [[Y:%.*]]) { ; CHECK-NEXT: [[LOAD:%.*]] = load <2 x i64>, ptr @x.vector, align 16 ; CHECK-NEXT: store <2 x i64> [[Y]], ptr @x.vector, align 16 ; CHECK-NEXT: ret void ; %load = load <2 x i64>, ptr @x.vector, align 1 store <2 x i64> %y, ptr @x.vector, align 1 ret void } ; ------------------------------------------------------------------------------ ; getelementptr ; ------------------------------------------------------------------------------ @vector = external global <2 x i64>, align 16 @vector.arr = external global [13 x <2 x i64>], align 16 ; ------------------------------------------------------------------------------ ; 1d access ; ------------------------------------------------------------------------------ define void @vector_singular(i32 %i, <2 x i64> %y) { ; CHECK-LABEL: define void @vector_singular ; CHECK-SAME: (i32 [[I:%.*]], <2 x i64> [[Y:%.*]]) { ; CHECK-NEXT: [[GEP:%.*]] = getelementptr <2 x i64>, ptr @vector, i32 [[I]] ; CHECK-NEXT: [[LOAD:%.*]] = load <2 x i64>, ptr [[GEP]], align 16 ; CHECK-NEXT: store <2 x i64> [[Y]], ptr [[GEP]], align 16 ; CHECK-NEXT: ret void ; %gep = getelementptr <2 x i64>, ptr @vector, i32 %i %load = load <2 x i64>, ptr %gep, align 1 store <2 x i64> %y, ptr %gep, align 1 ret void } ; ------------------------------------------------------------------------------ ; 2d access ; ------------------------------------------------------------------------------ define void @vector_array(i32 %i, i32 %j, <2 x i64> %y) { ; CHECK-LABEL: define void @vector_array ; CHECK-SAME: (i32 [[I:%.*]], i32 [[J:%.*]], <2 x i64> [[Y:%.*]]) { ; CHECK-NEXT: [[GEP:%.*]] = getelementptr [13 x <2 x i64>], ptr @vector.arr, i32 [[I]], i32 [[J]] ; CHECK-NEXT: [[LOAD:%.*]] = load <2 x i64>, ptr [[GEP]], align 16 ; CHECK-NEXT: store <2 x i64> [[Y]], ptr [[GEP]], align 16 ; CHECK-NEXT: ret void ; %gep = getelementptr [13 x <2 x i64>], ptr @vector.arr, i32 %i, i32 %j %load = load <2 x i64>, ptr %gep, align 1 store <2 x i64> %y, ptr %gep, align 1 ret void } ; ------------------------------------------------------------------------------ ; non-vector array type ; ------------------------------------------------------------------------------ ; When we see a unaligned load or store from an insufficiently aligned global or ; alloca, increase the alignment, turning it into an aligned load or store. @x.array = internal global [4 x i32] zeroinitializer define void @nonvector_array() { ; CHECK-LABEL: define void @nonvector_array() { ; CHECK-NEXT: [[LOAD_0:%.*]] = load <16 x i8>, ptr @x.array, align 16 ; CHECK-NEXT: store <16 x i8> zeroinitializer, ptr @x.array, align 16 ; CHECK-NEXT: [[GEP:%.*]] = getelementptr [4 x i32], ptr @x.array, i16 0, i16 2 ; CHECK-NEXT: [[LOAD_1:%.*]] = load <16 x i8>, ptr [[GEP]], align 8 ; CHECK-NEXT: store <16 x i8> zeroinitializer, ptr [[GEP]], align 8 ; CHECK-NEXT: ret void ; %load.0 = load <16 x i8>, ptr @x.array, align 1 store <16 x i8> zeroinitializer, ptr @x.array, align 1 %gep = getelementptr [4 x i32], ptr @x.array, i16 0, i16 2 %load.1 = load <16 x i8>, ptr %gep, align 1 store <16 x i8> zeroinitializer, ptr %gep, align 1 ret void }