Previously the inliner always produced a memcpy with alignment 1 for src and destination, leading to potentially suboptimal Codegen. Since the Src ptr alignment is only available through the CallBase it has to be passed to HandleByValArgumentInit. Dst Alignment is already known so it doesn't have to be passed along. If there is no specified Src Alignment my changes cause the ptr to have no align data attached instead of align 1 as before (see inline-tail.ll), I believe this is fine but since I'm a first time contributor, please confirm. My changes are already covered by 4 existing regression tests, so I did not add any additional ones. The example from #45778 now results in: ```C opt -S -passes=inline,instcombine,sroa,instcombine test.ll define dso_local i32 @test(ptr %t) { entry: %.sroa.0.0.copyload = load ptr, ptr %t, align 8 # this used to be align 1 in the original issue %arrayidx.i = getelementptr inbounds nuw i8, ptr %.sroa.0.0.copyload, i64 24 %0 = load i32, ptr %arrayidx.i, align 4 ret i32 %0 } ``` Fixes #45778.
79 lines
3.4 KiB
LLVM
79 lines
3.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
|
|
; RUN: opt < %s -passes=inline -S | FileCheck %s
|
|
; RUN: opt < %s -passes='cgscc(inline)' -S | FileCheck %s
|
|
|
|
%struct.a = type { i32, i32, i32, i32, i32 }
|
|
|
|
@g_var = global %struct.a { i32 1, i32 0, i32 0, i32 0, i32 0 }, align 8
|
|
@other_g_var = global %struct.a zeroinitializer, align 4
|
|
|
|
define void @callee(ptr noundef byval(%struct.a) align 8 %ptr) {
|
|
; CHECK-LABEL: define void @callee(
|
|
; CHECK-SAME: ptr noundef byval([[STRUCT_A:%.*]]) align 8 [[PTR:%.*]]) {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[VAL:%.*]] = load i32, ptr [[PTR]], align 8
|
|
; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq i32 [[VAL]], 0
|
|
; CHECK-NEXT: br i1 [[DOTNOT]], label [[CHECK_POINTERS_ARE_EQUAL:%.*]], label [[STORE_PTR_IN_GVAR:%.*]]
|
|
; CHECK: store_ptr_in_gvar:
|
|
; CHECK-NEXT: store ptr [[PTR]], ptr @other_g_var, align 8
|
|
; CHECK-NEXT: br label [[CHECK_POINTERS_ARE_EQUAL]]
|
|
; CHECK: check_pointers_are_equal:
|
|
; CHECK-NEXT: [[PHI:%.*]] = phi ptr [ [[PTR]], [[STORE_PTR_IN_GVAR]] ], [ @other_g_var, [[ENTRY:%.*]] ]
|
|
; CHECK-NEXT: [[DOTNOT1:%.*]] = icmp eq ptr [[PHI]], [[PTR]]
|
|
; CHECK-NEXT: br i1 [[DOTNOT1]], label [[RETURN:%.*]], label [[ABORT:%.*]]
|
|
; CHECK: abort:
|
|
; CHECK-NEXT: call void @abort()
|
|
; CHECK-NEXT: unreachable
|
|
; CHECK: return:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%val = load i32, ptr %ptr, align 8
|
|
%.not = icmp eq i32 %val, 0
|
|
br i1 %.not, label %check_pointers_are_equal, label %store_ptr_in_gvar
|
|
|
|
store_ptr_in_gvar: ; preds = %entry
|
|
store ptr %ptr, ptr @other_g_var, align 8
|
|
br label %check_pointers_are_equal
|
|
|
|
check_pointers_are_equal: ; preds = %store_ptr_in_gvar, %entry
|
|
%phi = phi ptr [ %ptr, %store_ptr_in_gvar ], [ @other_g_var, %entry ]
|
|
%.not1 = icmp eq ptr %phi, %ptr
|
|
br i1 %.not1, label %return, label %abort
|
|
|
|
abort: ; preds = %check_pointers_are_equal
|
|
call void @abort()
|
|
unreachable
|
|
|
|
return: ; preds = %check_pointers_are_equal
|
|
ret void
|
|
}
|
|
|
|
define i32 @main() {
|
|
; CHECK-LABEL: define i32 @main() {
|
|
; CHECK-NEXT: [[G_VAR:%.*]] = alloca [[STRUCT_A:%.*]], align 8
|
|
; CHECK-NEXT: call void @llvm.lifetime.start.p0(i64 20, ptr [[G_VAR]])
|
|
; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[G_VAR]], ptr align 8 @g_var, i64 20, i1 false)
|
|
; CHECK-NEXT: [[VAL_I:%.*]] = load i32, ptr [[G_VAR]], align 8
|
|
; CHECK-NEXT: [[DOTNOT_I:%.*]] = icmp eq i32 [[VAL_I]], 0
|
|
; CHECK-NEXT: br i1 [[DOTNOT_I]], label [[CHECK_POINTERS_ARE_EQUAL_I:%.*]], label [[STORE_PTR_IN_GVAR_I:%.*]]
|
|
; CHECK: store_ptr_in_gvar.i:
|
|
; CHECK-NEXT: store ptr [[G_VAR]], ptr @other_g_var, align 8
|
|
; CHECK-NEXT: br label [[CHECK_POINTERS_ARE_EQUAL_I]]
|
|
; CHECK: check_pointers_are_equal.i:
|
|
; CHECK-NEXT: [[PHI_I:%.*]] = phi ptr [ [[G_VAR]], [[STORE_PTR_IN_GVAR_I]] ], [ @other_g_var, [[TMP0:%.*]] ]
|
|
; CHECK-NEXT: [[DOTNOT1_I:%.*]] = icmp eq ptr [[PHI_I]], [[G_VAR]]
|
|
; CHECK-NEXT: br i1 [[DOTNOT1_I]], label [[CALLEE_EXIT:%.*]], label [[ABORT_I:%.*]]
|
|
; CHECK: abort.i:
|
|
; CHECK-NEXT: call void @abort()
|
|
; CHECK-NEXT: unreachable
|
|
; CHECK: callee.exit:
|
|
; CHECK-NEXT: call void @llvm.lifetime.end.p0(i64 20, ptr [[G_VAR]])
|
|
; CHECK-NEXT: ret i32 0
|
|
;
|
|
call void @callee(ptr noundef byval(%struct.a) align 8 @g_var)
|
|
ret i32 0
|
|
}
|
|
|
|
declare void @abort()
|