RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2024-12-24 21:14:56 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fix edge condition in DAGCombiner to improve codegen of shift sequences.

Browse Source 
When canonicalizing dags according to the rule
(shl (zext (shr X, c1) ), c1) ==> (zext (shl (shr X, c1), c1))

remember to add the new shl dag to the DAGCombiner worklist of nodes.
If we don't explicitly add it to the worklist of nodes to visit, we
may not trigger later on the rule that folds the shift left + logical
shift right into a AND instruction with bitmask.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192883 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Andrea Di Biagio 2013-10-17 11:02:58 +00:00
parent f5e3811607
commit 888cbad774
2 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -3794,6 +3794,7 @@ SDValue DAGCombiner::visitSHL(SDNode *N) {
EVT CountVT = NewOp0.getOperand(1).getValueType(); EVT CountVT = NewOp0.getOperand(1).getValueType();
SDValue NewSHL = DAG.getNode(ISD::SHL, SDLoc(N), NewOp0.getValueType(), SDValue NewSHL = DAG.getNode(ISD::SHL, SDLoc(N), NewOp0.getValueType(),
NewOp0, DAG.getConstant(c2, CountVT)); NewOp0, DAG.getConstant(c2, CountVT));
AddToWorkList(NewSHL.getNode());
return DAG.getNode(ISD::ZERO_EXTEND, SDLoc(N0), VT, NewSHL); return DAG.getNode(ISD::ZERO_EXTEND, SDLoc(N0), VT, NewSHL);
} }
} }

8
test/CodeGen/X86/dagcombine-shifts.ll
View File

@ -187,6 +187,8 @@ entry:
; Once the add is removed, the number of uses becomes one and therefore the ; Once the add is removed, the number of uses becomes one and therefore the
; dags are canonicalized. After Legalization, we need to make sure that the ; dags are canonicalized. After Legalization, we need to make sure that the
; valuetype for the shift count is legal. ; valuetype for the shift count is legal.
; Verify also that we correctly fold the shl-shr sequence into an
; AND with bitmask.
define void @g(i32 %a) { define void @g(i32 %a) {
%b = lshr i32 %a, 2 %b = lshr i32 %a, 2
@ -197,5 +199,11 @@ define void @g(i32 %a) {
ret void ret void
} }
; CHECK-LABEL: @g
; CHECK-NOT: shr
; CHECK-NOT: shl
; CHECK: and
; CHECK-NEXT: jmp
declare void @f(i64) declare void @f(i64)