RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 12:43:36 +01:00
Code Issues Projects Releases Wiki Activity

[InstCombine] allow more narrowing of casted select

Browse Source 
D47163 created a rule that we should not change the casted
type of a select when we have matching types in its compare condition.
That was intended to help vector codegen, but it also could create
situations where we miss subsequent folds as shown in PR44545:
https://bugs.llvm.org/show_bug.cgi?id=44545

By using shouldChangeType(), we can continue to get the vector folds
(because we always return false for vector types). But we also solve
the motivating bug because it's ok to narrow the scalar select in that
example.

Our canonicalization rules around select are a mess, but AFAICT, this
will not induce any infinite looping from the reverse transform (but
we'll need to watch for that possibility if committed).

Side note: there's a similar use of shouldChangeType() for phi ops
just below this diff, and the source and destination types appear to
be reversed.

Differential Revision: https://reviews.llvm.org/D72733
This commit is contained in:
Sanjay Patel 2020-01-27 16:33:13 -05:00
parent 1cf1e98f38
commit 665298049e
4 changed files with 15 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
lib/Transforms/InstCombine/InstCombineCasts.cpp
View File

@ -276,16 +276,20 @@ Instruction *InstCombiner::commonCastTransforms(CastInst &CI) {
}
if (auto *Sel = dyn_cast<SelectInst>(Src)) {
// We are casting a select. Try to fold the cast into the select, but only
// if the select does not have a compare instruction with matching operand
// types. Creating a select with operands that are different sizes than its
// We are casting a select. Try to fold the cast into the select if the
// select does not have a compare instruction with matching operand types
// or the select is likely better done in a narrow type.
// Creating a select with operands that are different sizes than its
// condition may inhibit other folds and lead to worse codegen.
auto *Cmp = dyn_cast<CmpInst>(Sel->getCondition());
if (!Cmp || Cmp->getOperand(0)->getType() != Sel->getType())
if (!Cmp || Cmp->getOperand(0)->getType() != Sel->getType() ||
(CI.getOpcode() == Instruction::Trunc &&
shouldChangeType(CI.getSrcTy(), CI.getType()))) {
if (Instruction *NV = FoldOpIntoSelect(CI, Sel)) {
replaceAllDbgUsesWith(*Sel, *NV, CI, DT);
return NV;
}
}
}
// If we are casting a PHI, then fold the cast into the PHI.

4
test/Transforms/InstCombine/cast-select.ll
View File

@ -56,8 +56,8 @@ define <2 x i32> @sext_vec(<2 x i8> %x, <2 x i8> %y, <2 x i8> %z) {
define i16 @trunc(i32 %x, i32 %y, i32 %z) {
; CHECK-LABEL: @trunc(
; CHECK-NEXT: [[CMP:%.*]] = icmp ult i32 [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[SEL:%.*]] = select i1 [[CMP]], i32 42, i32 [[Z:%.*]]
; CHECK-NEXT: [[R:%.*]] = trunc i32 [[SEL]] to i16
; CHECK-NEXT: [[TMP1:%.*]] = trunc i32 [[Z:%.*]] to i16
; CHECK-NEXT: [[R:%.*]] = select i1 [[CMP]], i16 42, i16 [[TMP1]]
; CHECK-NEXT: ret i16 [[R]]
;
%cmp = icmp ult i32 %x, %y

4
test/Transforms/InstCombine/select-imm-canon.ll
View File

@ -39,8 +39,8 @@ define i8 @thisdoesnotloop(i32 %A, i32 %B) {
; CHECK-LABEL: @thisdoesnotloop(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[L1:%.*]] = icmp slt i32 [[A:%.*]], -128
; CHECK-NEXT: [[L2:%.*]] = select i1 [[L1]], i32 -128, i32 [[B:%.*]]
; CHECK-NEXT: [[CONV7:%.*]] = trunc i32 [[L2]] to i8
; CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[B:%.*]] to i8
; CHECK-NEXT: [[CONV7:%.*]] = select i1 [[L1]], i8 -128, i8 [[TMP0]]
; CHECK-NEXT: ret i8 [[CONV7]]
;
entry:

8
test/Transforms/InstCombine/trunc.ll
View File

@ -626,15 +626,13 @@ define <2 x i8> @narrow_sub_vec_constant(<2 x i32> %x) {
ret <2 x i8> %tr
}
; FIXME: If the select is narrowed based on the target's datalayout, we allow more optimizations.
; If the select is narrowed based on the target's datalayout, we allow more optimizations.
define i16 @PR44545(i32 %t0, i32 %data) {
; CHECK-LABEL: @PR44545(
; CHECK-NEXT: [[T1:%.*]] = add nuw nsw i32 [[T0:%.*]], 1
; CHECK-NEXT: [[ISZERO:%.*]] = icmp eq i32 [[DATA:%.*]], 0
; CHECK-NEXT: [[FFS:%.*]] = select i1 [[ISZERO]], i32 0, i32 [[T1]]
; CHECK-NEXT: [[CAST:%.*]] = trunc i32 [[FFS]] to i16
; CHECK-NEXT: [[SUB:%.*]] = add nsw i16 [[CAST]], -1
; CHECK-NEXT: [[TMP1:%.*]] = trunc i32 [[T0:%.*]] to i16
; CHECK-NEXT: [[SUB:%.*]] = select i1 [[ISZERO]], i16 -1, i16 [[TMP1]]
; CHECK-NEXT: ret i16 [[SUB]]
;
%t1 = add nuw nsw i32 %t0, 1