; RUN: opt -basic-aa -loop-load-elim -S < %s | FileCheck %s ; RUN: opt -basic-aa -loop-load-elim -pgso -S < %s -enable-new-pm=0 | FileCheck %s -check-prefix=PGSO ; RUN: opt -aa-pipeline=basic-aa -passes='require<profile-summary>,function(loop-load-elim)' -S < %s | FileCheck %s -check-prefix=PGSO ; RUN: opt -basic-aa -loop-load-elim -pgso=false -S < %s | FileCheck %s -check-prefix=NPGSO ; When optimizing for size don't eliminate in this loop because the loop would ; have to be versioned first because A and C may alias. ; ; for (unsigned i = 0; i < 100; i++) { ; A[i+1] = B[i] + 2; ; C[i] = A[i] * 2; ; } target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" ; CHECK-LABEL: @f( define void @f(i32* %A, i32* %B, i32* %C, i64 %N) optsize { entry: br label %for.body for.body: ; preds = %for.body, %entry %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 %Aidx_next = getelementptr inbounds i32, i32* %A, i64 %indvars.iv.next %Bidx = getelementptr inbounds i32, i32* %B, i64 %indvars.iv %Cidx = getelementptr inbounds i32, i32* %C, i64 %indvars.iv %Aidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv %b = load i32, i32* %Bidx, align 4 %a_p1 = add i32 %b, 2 store i32 %a_p1, i32* %Aidx_next, align 4 %a = load i32, i32* %Aidx, align 4 ; CHECK: %c = mul i32 %a, 2 %c = mul i32 %a, 2 store i32 %c, i32* %Cidx, align 4 %exitcond = icmp eq i64 %indvars.iv.next, %N br i1 %exitcond, label %for.end, label %for.body for.end: ; preds = %for.body ret void } ; Same loop but with noalias on %A and %C. In this case load-eliminate even ; with -Os. ; CHECK-LABEL: @g( define void @g(i32* noalias %A, i32* %B, i32* noalias %C, i64 %N) optsize { entry: br label %for.body for.body: ; preds = %for.body, %entry %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 %Aidx_next = getelementptr inbounds i32, i32* %A, i64 %indvars.iv.next %Bidx = getelementptr inbounds i32, i32* %B, i64 %indvars.iv %Cidx = getelementptr inbounds i32, i32* %C, i64 %indvars.iv %Aidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv %b = load i32, i32* %Bidx, align 4 %a_p1 = add i32 %b, 2 store i32 %a_p1, i32* %Aidx_next, align 4 %a = load i32, i32* %Aidx, align 4 ; CHECK: %c = mul i32 %store_forwarded, 2 %c = mul i32 %a, 2 store i32 %c, i32* %Cidx, align 4 %exitcond = icmp eq i64 %indvars.iv.next, %N br i1 %exitcond, label %for.end, label %for.body for.end: ; preds = %for.body ret void } ; PGSO-LABEL: @f_pgso( ; NPGSO-LABEL: @f_pgso( define void @f_pgso(i32* %A, i32* %B, i32* %C, i64 %N) !prof !14 { entry: br label %for.body for.body: ; preds = %for.body, %entry %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 %Aidx_next = getelementptr inbounds i32, i32* %A, i64 %indvars.iv.next %Bidx = getelementptr inbounds i32, i32* %B, i64 %indvars.iv %Cidx = getelementptr inbounds i32, i32* %C, i64 %indvars.iv %Aidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv %b = load i32, i32* %Bidx, align 4 %a_p1 = add i32 %b, 2 store i32 %a_p1, i32* %Aidx_next, align 4 %a = load i32, i32* %Aidx, align 4 ; PGSO: %c = mul i32 %a, 2 ; NPGSO-NOT: %c = mul i32 %a, 2 %c = mul i32 %a, 2 store i32 %c, i32* %Cidx, align 4 %exitcond = icmp eq i64 %indvars.iv.next, %N br i1 %exitcond, label %for.end, label %for.body for.end: ; preds = %for.body ret void } !llvm.module.flags = !{!0} !0 = !{i32 1, !"ProfileSummary", !1} !1 = !{!2, !3, !4, !5, !6, !7, !8, !9} !2 = !{!"ProfileFormat", !"InstrProf"} !3 = !{!"TotalCount", i64 10000} !4 = !{!"MaxCount", i64 10} !5 = !{!"MaxInternalCount", i64 1} !6 = !{!"MaxFunctionCount", i64 1000} !7 = !{!"NumCounts", i64 3} !8 = !{!"NumFunctions", i64 3} !9 = !{!"DetailedSummary", !10} !10 = !{!11, !12, !13} !11 = !{i32 10000, i64 100, i32 1} !12 = !{i32 999000, i64 100, i32 1} !13 = !{i32 999999, i64 1, i32 2} !14 = !{!"function_entry_count", i64 0}