maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[InstCombine] canonicalizeSaturatedAdd(): last fold is only valid for strict comparison (PR48390) 

We could create uadd.sat under incorrect circumstances
if a select with -1 as the false value was canonicalized
by swapping the T/F values. Unlike the other transforms
in the same function, it is not invariant to equality.

Some alive proofs: https://alive2.llvm.org/ce/z/emmKKL

Based on original patch by David Green!

Fixes https://bugs.llvm.org/show_bug.cgi?id=48390

Differential Revision: https://reviews.llvm.org/D92717
This commit is contained in:
Roman Lebedev 2020-12-09 18:04:08 +03:00
parent f16320b90b
commit e6f2a79d7a
No known key found for this signature in database
GPG Key ID: 083C3EBB4A1689E0
2 changed files with 27 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
View File

@ -765,25 +765,24 @@ static Value *canonicalizeSaturatedAdd(ICmpInst *Cmp, Value *TVal, Value *FVal,
// Match unsigned saturated add of 2 variables with an unnecessary 'not'.
// There are 8 commuted variants.
// Canonicalize -1 (saturated result) to true value of the select. Just
// swapping the compare operands is legal, because the selected value is the
// same in case of equality, so we can interchange u< and u<=.
// Canonicalize -1 (saturated result) to true value of the select.
if (match(FVal, m_AllOnes())) {
std::swap(TVal, FVal);
std::swap(Cmp0, Cmp1);
Pred = CmpInst::getInversePredicate(Pred);
}
if (!match(TVal, m_AllOnes()))
return nullptr;
// Canonicalize predicate to 'ULT'.
if (Pred == ICmpInst::ICMP_UGT) {
Pred = ICmpInst::ICMP_ULT;
// Canonicalize predicate to less-than or less-or-equal-than.
if (Pred == ICmpInst::ICMP_UGT || Pred == ICmpInst::ICMP_UGE) {
std::swap(Cmp0, Cmp1);
Pred = CmpInst::getSwappedPredicate(Pred);
}
if (Pred != ICmpInst::ICMP_ULT)
if (Pred != ICmpInst::ICMP_ULT && Pred != ICmpInst::ICMP_ULE)
return nullptr;
// Match unsigned saturated add of 2 variables with an unnecessary 'not'.
// Strictness of the comparison is irrelevant.
Value *Y;
if (match(Cmp0, m_Not(m_Value(X))) &&
match(FVal, m_c_Add(m_Specific(X), m_Value(Y))) && Y == Cmp1) {
@ -792,6 +791,7 @@ static Value *canonicalizeSaturatedAdd(ICmpInst *Cmp, Value *TVal, Value *FVal,
return Builder.CreateBinaryIntrinsic(Intrinsic::uadd_sat, X, Y);
}
// The 'not' op may be included in the sum but not the compare.
// Strictness of the comparison is irrelevant.
X = Cmp0;
Y = Cmp1;
if (match(FVal, m_c_Add(m_Not(m_Specific(X)), m_Specific(Y)))) {
@ -802,7 +802,9 @@ static Value *canonicalizeSaturatedAdd(ICmpInst *Cmp, Value *TVal, Value *FVal,
Intrinsic::uadd_sat, BO->getOperand(0), BO->getOperand(1));
}
// The overflow may be detected via the add wrapping round.
if (match(Cmp0, m_c_Add(m_Specific(Cmp1), m_Value(Y))) &&
// This is only valid for strict comparison!
if (Pred == ICmpInst::ICMP_ULT &&
match(Cmp0, m_c_Add(m_Specific(Cmp1), m_Value(Y))) &&
match(FVal, m_c_Add(m_Specific(Cmp1), m_Specific(Y)))) {
// ((X + Y) u< X) ? -1 : (X + Y) --> uadd.sat(X, Y)
// ((X + Y) u< Y) ? -1 : (X + Y) --> uadd.sat(X, Y)

24
llvm/test/Transforms/InstCombine/saturating-add-sub.ll
View File

@ -1801,8 +1801,10 @@ define i32 @uadd_sat_via_add(i32 %x, i32 %y) {
define i32 @uadd_sat_via_add_nonstrict(i32 %x, i32 %y) {
; CHECK-LABEL: @uadd_sat_via_add_nonstrict(
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[Y:%.*]], i32 [[X:%.*]])
; CHECK-NEXT: ret i32 [[TMP1]]
; CHECK-NEXT: [[A:%.*]] = add i32 [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[C_NOT:%.*]] = icmp ugt i32 [[A]], [[Y]]
; CHECK-NEXT: [[R:%.*]] = select i1 [[C_NOT]], i32 [[A]], i32 -1
; CHECK-NEXT: ret i32 [[R]]
;
%a = add i32 %x, %y
%c = icmp ule i32 %a, %y
@ -1823,8 +1825,10 @@ define i32 @uadd_sat_via_add_swapped_select(i32 %x, i32 %y) {
define i32 @uadd_sat_via_add_swapped_select_strict(i32 %x, i32 %y) {
; CHECK-LABEL: @uadd_sat_via_add_swapped_select_strict(
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[Y:%.*]], i32 [[X:%.*]])
; CHECK-NEXT: ret i32 [[TMP1]]
; CHECK-NEXT: [[A:%.*]] = add i32 [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[C:%.*]] = icmp ugt i32 [[A]], [[Y]]
; CHECK-NEXT: [[R:%.*]] = select i1 [[C]], i32 [[A]], i32 -1
; CHECK-NEXT: ret i32 [[R]]
;
%a = add i32 %x, %y
%c = icmp ugt i32 %a, %y
@ -1845,8 +1849,10 @@ define i32 @uadd_sat_via_add_swapped_cmp(i32 %x, i32 %y) {
define i32 @uadd_sat_via_add_swapped_cmp_nonstrict(i32 %x, i32 %y) {
; CHECK-LABEL: @uadd_sat_via_add_swapped_cmp_nonstrict(
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[Y:%.*]], i32 [[X:%.*]])
; CHECK-NEXT: ret i32 [[TMP1]]
; CHECK-NEXT: [[A:%.*]] = add i32 [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[C_NOT:%.*]] = icmp ugt i32 [[A]], [[Y]]
; CHECK-NEXT: [[R:%.*]] = select i1 [[C_NOT]], i32 [[A]], i32 -1
; CHECK-NEXT: ret i32 [[R]]
;
%a = add i32 %x, %y
%c = icmp uge i32 %y, %a
@ -1867,8 +1873,10 @@ define i32 @uadd_sat_via_add_swapped_cmp_nonstric(i32 %x, i32 %y) {
define i32 @uadd_sat_via_add_swapped_cmp_select_nonstrict(i32 %x, i32 %y) {
; CHECK-LABEL: @uadd_sat_via_add_swapped_cmp_select_nonstrict(
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.uadd.sat.i32(i32 [[Y:%.*]], i32 [[X:%.*]])
; CHECK-NEXT: ret i32 [[TMP1]]
; CHECK-NEXT: [[A:%.*]] = add i32 [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[C:%.*]] = icmp ugt i32 [[A]], [[Y]]
; CHECK-NEXT: [[R:%.*]] = select i1 [[C]], i32 [[A]], i32 -1
; CHECK-NEXT: ret i32 [[R]]
;
%a = add i32 %x, %y
%c = icmp ult i32 %y, %a