Nikita Popov 68c1eeb4ba [ArgPromotion] Make implementation offset based
This rewrites ArgPromotion to be based on offsets rather than GEP
structure. We inspect all loads at constant offsets and remember
which types are loaded at which offsets. Then we promote based on
those types.

This generalizes ArgPromotion to work with bitcasted loads, and
is compatible with opaque pointers.

This patch also fixes incorrect handling of alignment during
argument promotion. Previously, the implementation only checked
that the pointer is dereferenceable, but was happy to speculate
overaligned loads. (I would have fixed this separately in advance,
but I found this hard to do with the previous implementation
approach).

Differential Revision: https://reviews.llvm.org/D118685
2022-02-09 09:35:01 +01:00

101 lines
4.4 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --scrub-attributes
; RUN: opt < %s -passes=argpromotion -S | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
%union.u = type { x86_fp80 }
%struct.s = type { double, i16, i8, [5 x i8] }
@b = internal global %struct.s { double 3.14, i16 9439, i8 25, [5 x i8] undef }, align 16
%struct.Foo = type { i32, i64 }
@a = internal global %struct.Foo { i32 1, i64 2 }, align 8
define void @run() {
; CHECK-LABEL: define {{[^@]+}}@run() {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast %union.u* bitcast (%struct.s* @b to %union.u*) to i8*
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr i8, i8* [[TMP0]], i64 10
; CHECK-NEXT: [[DOTVAL:%.*]] = load i8, i8* [[TMP1]], align 1
; CHECK-NEXT: [[TMP2:%.*]] = tail call i8 @UseLongDoubleUnsafely(i8 [[DOTVAL]])
; CHECK-NEXT: [[DOT0:%.*]] = getelementptr [[UNION_U:%.*]], %union.u* bitcast (%struct.s* @b to %union.u*), i32 0, i32 0
; CHECK-NEXT: [[DOT0_VAL:%.*]] = load x86_fp80, x86_fp80* [[DOT0]], align 16
; CHECK-NEXT: [[TMP3:%.*]] = tail call x86_fp80 @UseLongDoubleSafely(x86_fp80 [[DOT0_VAL]])
; CHECK-NEXT: [[TMP4:%.*]] = bitcast %struct.Foo* @a to i64*
; CHECK-NEXT: [[A_VAL:%.*]] = load i64, i64* [[TMP4]], align 8
; CHECK-NEXT: [[TMP5:%.*]] = call i64 @AccessPaddingOfStruct(i64 [[A_VAL]])
; CHECK-NEXT: [[TMP6:%.*]] = call i64 @CaptureAStruct(%struct.Foo* byval([[STRUCT_FOO:%.*]]) @a)
; CHECK-NEXT: ret void
;
entry:
tail call i8 @UseLongDoubleUnsafely(%union.u* byval(%union.u) align 16 bitcast (%struct.s* @b to %union.u*))
tail call x86_fp80 @UseLongDoubleSafely(%union.u* byval(%union.u) align 16 bitcast (%struct.s* @b to %union.u*))
call i64 @AccessPaddingOfStruct(%struct.Foo* byval(%struct.Foo) @a)
call i64 @CaptureAStruct(%struct.Foo* byval(%struct.Foo) @a)
ret void
}
define internal i8 @UseLongDoubleUnsafely(%union.u* byval(%union.u) align 16 %arg) {
; CHECK-LABEL: define {{[^@]+}}@UseLongDoubleUnsafely
; CHECK-SAME: (i8 [[ARG_10_VAL:%.*]]) {
; CHECK-NEXT: entry:
; CHECK-NEXT: ret i8 [[ARG_10_VAL]]
;
entry:
%bitcast = bitcast %union.u* %arg to %struct.s*
%gep = getelementptr inbounds %struct.s, %struct.s* %bitcast, i64 0, i32 2
%result = load i8, i8* %gep
ret i8 %result
}
define internal x86_fp80 @UseLongDoubleSafely(%union.u* byval(%union.u) align 16 %arg) {
; CHECK-LABEL: define {{[^@]+}}@UseLongDoubleSafely
; CHECK-SAME: (x86_fp80 [[ARG_0:%.*]]) {
; CHECK-NEXT: [[ARG:%.*]] = alloca [[UNION_U:%.*]], align 16
; CHECK-NEXT: [[DOT0:%.*]] = getelementptr [[UNION_U]], %union.u* [[ARG]], i32 0, i32 0
; CHECK-NEXT: store x86_fp80 [[ARG_0]], x86_fp80* [[DOT0]], align 16
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds [[UNION_U]], %union.u* [[ARG]], i64 0, i32 0
; CHECK-NEXT: [[FP80:%.*]] = load x86_fp80, x86_fp80* [[GEP]], align 16
; CHECK-NEXT: ret x86_fp80 [[FP80]]
;
%gep = getelementptr inbounds %union.u, %union.u* %arg, i64 0, i32 0
%fp80 = load x86_fp80, x86_fp80* %gep
ret x86_fp80 %fp80
}
define internal i64 @AccessPaddingOfStruct(%struct.Foo* byval(%struct.Foo) %a) {
; CHECK-LABEL: define {{[^@]+}}@AccessPaddingOfStruct
; CHECK-SAME: (i64 [[A_0_VAL:%.*]]) {
; CHECK-NEXT: ret i64 [[A_0_VAL]]
;
%p = bitcast %struct.Foo* %a to i64*
%v = load i64, i64* %p
ret i64 %v
}
define internal i64 @CaptureAStruct(%struct.Foo* byval(%struct.Foo) %a) {
; CHECK-LABEL: define {{[^@]+}}@CaptureAStruct
; CHECK-SAME: (%struct.Foo* byval([[STRUCT_FOO:%.*]]) [[A:%.*]]) {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A_PTR:%.*]] = alloca %struct.Foo*, align 8
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[PHI:%.*]] = phi %struct.Foo* [ null, [[ENTRY:%.*]] ], [ [[GEP:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[TMP0:%.*]] = phi %struct.Foo* [ [[A]], [[ENTRY]] ], [ [[TMP0]], [[LOOP]] ]
; CHECK-NEXT: store %struct.Foo* [[PHI]], %struct.Foo** [[A_PTR]], align 8
; CHECK-NEXT: [[GEP]] = getelementptr [[STRUCT_FOO]], %struct.Foo* [[A]], i64 0
; CHECK-NEXT: br label [[LOOP]]
;
entry:
%a_ptr = alloca %struct.Foo*
br label %loop
loop:
%phi = phi %struct.Foo* [ null, %entry ], [ %gep, %loop ]
%0 = phi %struct.Foo* [ %a, %entry ], [ %0, %loop ]
store %struct.Foo* %phi, %struct.Foo** %a_ptr
%gep = getelementptr %struct.Foo, %struct.Foo* %a, i64 0
br label %loop
}