caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
ef2cdfe393d01cd4935c806387ac912b5a2c8ced
clang-p2996/llvm/test/Transforms/InstCombine/load-cmp.ll
hyeongyukim 69b0ed9a0a [InstCombine] Fix miscompile on GEP+load to icmp fold (PR45210) 
As noted in PR45210: https://bugs.llvm.org/show_bug.cgi?id=45210
...the bug is triggered as Eli say when sext(idx) * ElementSize overflows.

```
   // assume that GV is an array of 4-byte elements
   GEP = gep GV, 0, Idx // this is accessing Idx * 4
   L = load GEP
   ICI = icmp eq L, value
 =>
   ICI = icmp eq Idx, NewIdx
```

The foldCmpLoadFromIndexedGlobal function simplifies GEP+load operation to icmp.
And there is a problem because Idx * ElementSize can overflow.

Let's assume that the wanted value is at offset 0.
Then, there are actually four possible values for Idx to match offset 0: 0x00..00, 0x40..00, 0x80..00, 0xC0..00.
We should return true for all these values, but currently, the new icmp only returns true for 0x00..00.

This problem can be solved by masking off (trailing zeros of ElementSize) bits from Idx.

```
   ...
 =>
   Idx' = and Idx, 0x3F..FF
   ICI = icmp eq Idx', NewIdx
```

Reviewed By: efriedma

Differential Revision: https://reviews.llvm.org/D99481
2021-06-17 19:46:17 +09:00

321 lines
9.4 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -instcombine -S -data-layout="p:32:32:32-p1:16:16:16-n8:16:32:64" < %s | FileCheck %s
@G16 = internal constant [10 x i16] [i16 35, i16 82, i16 69, i16 81, i16 85,
i16 73, i16 82, i16 69, i16 68, i16 0]
@G16_as1 = internal addrspace(1) constant [10 x i16] [i16 35, i16 82, i16 69, i16 81, i16 85,
i16 73, i16 82, i16 69, i16 68, i16 0]
@GD = internal constant [6 x double]
[double -10.0, double 1.0, double 4.0, double 2.0, double -20.0, double -40.0]
%Foo = type { i32, i32, i32, i32 }
@GS = internal constant %Foo { i32 1, i32 4, i32 9, i32 14 }
@GStructArr = internal constant [4 x %Foo] [ %Foo { i32 1, i32 4, i32 9, i32 14 },
%Foo { i32 5, i32 4, i32 6, i32 11 },
%Foo { i32 6, i32 5, i32 9, i32 20 },
%Foo { i32 12, i32 3, i32 9, i32 8 } ]
define i1 @test1(i32 %X) {
; CHECK-LABEL: @test1(
; CHECK-NEXT: [[R:%.*]] = icmp eq i32 [[X:%.*]], 9
; CHECK-NEXT: ret i1 [[R]]
;
%P = getelementptr inbounds [10 x i16], [10 x i16]* @G16, i32 0, i32 %X
%Q = load i16, i16* %P
%R = icmp eq i16 %Q, 0
ret i1 %R
}
define i1 @test1_noinbounds(i32 %X) {
; CHECK-LABEL: @test1_noinbounds(
; CHECK-NEXT: [[TMP1:%.*]] = and i32 [[X:%.*]], 2147483647
; CHECK-NEXT: [[R:%.*]] = icmp eq i32 [[TMP1]], 9
; CHECK-NEXT: ret i1 [[R]]
;
%P = getelementptr [10 x i16], [10 x i16]* @G16, i32 0, i32 %X
%Q = load i16, i16* %P
%R = icmp eq i16 %Q, 0
ret i1 %R
}
define i1 @test1_noinbounds_i64(i64 %X) {
; CHECK-LABEL: @test1_noinbounds_i64(
; CHECK-NEXT: [[TMP1:%.*]] = and i64 [[X:%.*]], 2147483647
; CHECK-NEXT: [[R:%.*]] = icmp eq i64 [[TMP1]], 9
; CHECK-NEXT: ret i1 [[R]]
;
%P = getelementptr [10 x i16], [10 x i16]* @G16, i64 0, i64 %X
%Q = load i16, i16* %P
%R = icmp eq i16 %Q, 0
ret i1 %R
}
define i1 @test1_noinbounds_as1(i32 %x) {
; CHECK-LABEL: @test1_noinbounds_as1(
; CHECK-NEXT: [[TMP1:%.*]] = and i32 [[X:%.*]], 32767
; CHECK-NEXT: [[R:%.*]] = icmp eq i32 [[TMP1]], 9
; CHECK-NEXT: ret i1 [[R]]
;
%p = getelementptr [10 x i16], [10 x i16] addrspace(1)* @G16_as1, i16 0, i32 %x
%q = load i16, i16 addrspace(1)* %p
%r = icmp eq i16 %q, 0
ret i1 %r
}
define i1 @test2(i32 %X) {
; CHECK-LABEL: @test2(
; CHECK-NEXT: [[R:%.*]] = icmp ne i32 [[X:%.*]], 4
; CHECK-NEXT: ret i1 [[R]]
;
%P = getelementptr inbounds [10 x i16], [10 x i16]* @G16, i32 0, i32 %X
%Q = load i16, i16* %P
%R = icmp slt i16 %Q, 85
ret i1 %R
}
define i1 @test3(i32 %X) {
; CHECK-LABEL: @test3(
; CHECK-NEXT: [[R:%.*]] = icmp eq i32 [[X:%.*]], 1
; CHECK-NEXT: ret i1 [[R]]
;
%P = getelementptr inbounds [6 x double], [6 x double]* @GD, i32 0, i32 %X
%Q = load double, double* %P
%R = fcmp oeq double %Q, 1.0
ret i1 %R
}
define i1 @test4(i32 %X) {
; CHECK-LABEL: @test4(
; CHECK-NEXT: [[TMP1:%.*]] = lshr i32 933, [[X:%.*]]
; CHECK-NEXT: [[TMP2:%.*]] = and i32 [[TMP1]], 1
; CHECK-NEXT: [[R:%.*]] = icmp ne i32 [[TMP2]], 0
; CHECK-NEXT: ret i1 [[R]]
;
%P = getelementptr inbounds [10 x i16], [10 x i16]* @G16, i32 0, i32 %X
%Q = load i16, i16* %P
%R = icmp sle i16 %Q, 73
ret i1 %R
}
define i1 @test4_i16(i16 %X) {
; CHECK-LABEL: @test4_i16(
; CHECK-NEXT: [[TMP1:%.*]] = zext i16 [[X:%.*]] to i32
; CHECK-NEXT: [[TMP2:%.*]] = lshr i32 933, [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = and i32 [[TMP2]], 1
; CHECK-NEXT: [[R:%.*]] = icmp ne i32 [[TMP3]], 0
; CHECK-NEXT: ret i1 [[R]]
;
%P = getelementptr inbounds [10 x i16], [10 x i16]* @G16, i32 0, i16 %X
%Q = load i16, i16* %P
%R = icmp sle i16 %Q, 73
ret i1 %R
}
define i1 @test5(i32 %X) {
; CHECK-LABEL: @test5(
; CHECK-NEXT: [[TMP1:%.*]] = icmp eq i32 [[X:%.*]], 2
; CHECK-NEXT: [[TMP2:%.*]] = icmp eq i32 [[X]], 7
; CHECK-NEXT: [[R:%.*]] = or i1 [[TMP1]], [[TMP2]]
; CHECK-NEXT: ret i1 [[R]]
;
%P = getelementptr inbounds [10 x i16], [10 x i16]* @G16, i32 0, i32 %X
%Q = load i16, i16* %P
%R = icmp eq i16 %Q, 69
ret i1 %R
}
define i1 @test6(i32 %X) {
; CHECK-LABEL: @test6(
; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[X:%.*]], -1
; CHECK-NEXT: [[R:%.*]] = icmp ult i32 [[TMP1]], 3
; CHECK-NEXT: ret i1 [[R]]
;
%P = getelementptr inbounds [6 x double], [6 x double]* @GD, i32 0, i32 %X
%Q = load double, double* %P
%R = fcmp ogt double %Q, 0.0
ret i1 %R
}
define i1 @test7(i32 %X) {
; CHECK-LABEL: @test7(
; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[X:%.*]], -1
; CHECK-NEXT: [[R:%.*]] = icmp ugt i32 [[TMP1]], 2
; CHECK-NEXT: ret i1 [[R]]
;
%P = getelementptr inbounds [6 x double], [6 x double]* @GD, i32 0, i32 %X
%Q = load double, double* %P
%R = fcmp olt double %Q, 0.0
ret i1 %R
}
define i1 @test8(i32 %X) {
; CHECK-LABEL: @test8(
; CHECK-NEXT: [[TMP1:%.*]] = and i32 [[X:%.*]], -2
; CHECK-NEXT: [[TMP2:%.*]] = icmp eq i32 [[TMP1]], 8
; CHECK-NEXT: ret i1 [[TMP2]]
;
%P = getelementptr inbounds [10 x i16], [10 x i16]* @G16, i32 0, i32 %X
%Q = load i16, i16* %P
%R = and i16 %Q, 3
%S = icmp eq i16 %R, 0
ret i1 %S
}
@GA = internal constant [4 x { i32, i32 } ] [
{ i32, i32 } { i32 1, i32 0 },
{ i32, i32 } { i32 2, i32 1 },
{ i32, i32 } { i32 3, i32 1 },
{ i32, i32 } { i32 4, i32 0 }
]
define i1 @test9(i32 %X) {
; CHECK-LABEL: @test9(
; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[X:%.*]], -1
; CHECK-NEXT: [[TMP2:%.*]] = icmp ult i32 [[TMP1]], 2
; CHECK-NEXT: ret i1 [[TMP2]]
;
%P = getelementptr inbounds [4 x { i32, i32 } ], [4 x { i32, i32 } ]* @GA, i32 0, i32 %X, i32 1
%Q = load i32, i32* %P
%R = icmp eq i32 %Q, 1
ret i1 %R
}
define i1 @test10_struct(i32 %x) {
; CHECK-LABEL: @test10_struct(
; CHECK-NEXT: ret i1 false
;
%p = getelementptr inbounds %Foo, %Foo* @GS, i32 %x, i32 0
%q = load i32, i32* %p
%r = icmp eq i32 %q, 9
ret i1 %r
}
define i1 @test10_struct_noinbounds(i32 %x) {
; CHECK-LABEL: @test10_struct_noinbounds(
; CHECK-NEXT: [[P:%.*]] = getelementptr [[FOO:%.*]], %Foo* @GS, i32 [[X:%.*]], i32 0
; CHECK-NEXT: [[Q:%.*]] = load i32, i32* [[P]], align 8
; CHECK-NEXT: [[R:%.*]] = icmp eq i32 [[Q]], 9
; CHECK-NEXT: ret i1 [[R]]
;
%p = getelementptr %Foo, %Foo* @GS, i32 %x, i32 0
%q = load i32, i32* %p
%r = icmp eq i32 %q, 9
ret i1 %r
}
; Test that the GEP indices are converted before we ever get here
; Index < ptr size
define i1 @test10_struct_i16(i16 %x){
; CHECK-LABEL: @test10_struct_i16(
; CHECK-NEXT: ret i1 false
;
%p = getelementptr inbounds %Foo, %Foo* @GS, i16 %x, i32 0
%q = load i32, i32* %p
%r = icmp eq i32 %q, 0
ret i1 %r
}
; Test that the GEP indices are converted before we ever get here
; Index > ptr size
define i1 @test10_struct_i64(i64 %x){
; CHECK-LABEL: @test10_struct_i64(
; CHECK-NEXT: ret i1 false
;
%p = getelementptr inbounds %Foo, %Foo* @GS, i64 %x, i32 0
%q = load i32, i32* %p
%r = icmp eq i32 %q, 0
ret i1 %r
}
define i1 @test10_struct_noinbounds_i16(i16 %x) {
; CHECK-LABEL: @test10_struct_noinbounds_i16(
; CHECK-NEXT: [[TMP1:%.*]] = sext i16 [[X:%.*]] to i32
; CHECK-NEXT: [[P:%.*]] = getelementptr [[FOO:%.*]], %Foo* @GS, i32 [[TMP1]], i32 0
; CHECK-NEXT: [[Q:%.*]] = load i32, i32* [[P]], align 8
; CHECK-NEXT: [[R:%.*]] = icmp eq i32 [[Q]], 0
; CHECK-NEXT: ret i1 [[R]]
;
%p = getelementptr %Foo, %Foo* @GS, i16 %x, i32 0
%q = load i32, i32* %p
%r = icmp eq i32 %q, 0
ret i1 %r
}
define i1 @test10_struct_arr(i32 %x) {
; CHECK-LABEL: @test10_struct_arr(
; CHECK-NEXT: [[R:%.*]] = icmp ne i32 [[X:%.*]], 1
; CHECK-NEXT: ret i1 [[R]]
;
%p = getelementptr inbounds [4 x %Foo], [4 x %Foo]* @GStructArr, i32 0, i32 %x, i32 2
%q = load i32, i32* %p
%r = icmp eq i32 %q, 9
ret i1 %r
}
define i1 @test10_struct_arr_noinbounds(i32 %x) {
; CHECK-LABEL: @test10_struct_arr_noinbounds(
; CHECK-NEXT: [[TMP1:%.*]] = and i32 [[X:%.*]], 268435455
; CHECK-NEXT: [[R:%.*]] = icmp ne i32 [[TMP1]], 1
; CHECK-NEXT: ret i1 [[R]]
;
%p = getelementptr [4 x %Foo], [4 x %Foo]* @GStructArr, i32 0, i32 %x, i32 2
%q = load i32, i32* %p
%r = icmp eq i32 %q, 9
ret i1 %r
}
define i1 @test10_struct_arr_i16(i16 %x) {
; CHECK-LABEL: @test10_struct_arr_i16(
; CHECK-NEXT: [[R:%.*]] = icmp ne i16 [[X:%.*]], 1
; CHECK-NEXT: ret i1 [[R]]
;
%p = getelementptr inbounds [4 x %Foo], [4 x %Foo]* @GStructArr, i16 0, i16 %x, i32 2
%q = load i32, i32* %p
%r = icmp eq i32 %q, 9
ret i1 %r
}
define i1 @test10_struct_arr_i64(i64 %x) {
; CHECK-LABEL: @test10_struct_arr_i64(
; CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[X:%.*]] to i32
; CHECK-NEXT: [[R:%.*]] = icmp ne i32 [[TMP1]], 1
; CHECK-NEXT: ret i1 [[R]]
;
%p = getelementptr inbounds [4 x %Foo], [4 x %Foo]* @GStructArr, i64 0, i64 %x, i32 2
%q = load i32, i32* %p
%r = icmp eq i32 %q, 9
ret i1 %r
}
define i1 @test10_struct_arr_noinbounds_i16(i16 %x) {
; CHECK-LABEL: @test10_struct_arr_noinbounds_i16(
; CHECK-NEXT: [[TMP1:%.*]] = sext i16 [[X:%.*]] to i32
; CHECK-NEXT: [[TMP2:%.*]] = and i32 [[TMP1]], 268435455
; CHECK-NEXT: [[R:%.*]] = icmp ne i32 [[TMP2]], 1
; CHECK-NEXT: ret i1 [[R]]
;
%p = getelementptr [4 x %Foo], [4 x %Foo]* @GStructArr, i32 0, i16 %x, i32 2
%q = load i32, i32* %p
%r = icmp eq i32 %q, 9
ret i1 %r
}
define i1 @test10_struct_arr_noinbounds_i64(i64 %x) {
; CHECK-LABEL: @test10_struct_arr_noinbounds_i64(
; CHECK-NEXT: [[TMP1:%.*]] = and i64 [[X:%.*]], 268435455
; CHECK-NEXT: [[R:%.*]] = icmp ne i64 [[TMP1]], 1
; CHECK-NEXT: ret i1 [[R]]
;
%p = getelementptr [4 x %Foo], [4 x %Foo]* @GStructArr, i32 0, i64 %x, i32 2
%q = load i32, i32* %p
%r = icmp eq i32 %q, 9
ret i1 %r
}
Reference in New Issue View Git Blame Copy Permalink