When splitting critical edges, make sure not to leave the new block in the

middle of the loop.  This turns a critical loop in gzip into this:

.LBB_test_1:    ; loopentry
        or r27, r28, r28
        add r28, r3, r27
        lhz r28, 3(r28)
        add r26, r4, r27
        lhz r26, 3(r26)
        cmpw cr0, r28, r26
        bne .LBB_test_8 ; loopentry.loopexit_crit_edge
.LBB_test_2:    ; shortcirc_next.0
        add r28, r3, r27
        lhz r28, 5(r28)
        add r26, r4, r27
        lhz r26, 5(r26)
        cmpw cr0, r28, r26
        bne .LBB_test_7 ; shortcirc_next.0.loopexit_crit_edge
.LBB_test_3:    ; shortcirc_next.1
        add r28, r3, r27
        lhz r28, 7(r28)
        add r26, r4, r27
        lhz r26, 7(r26)
        cmpw cr0, r28, r26
        bne .LBB_test_6 ; shortcirc_next.1.loopexit_crit_edge
.LBB_test_4:    ; shortcirc_next.2
        add r28, r3, r27
        lhz r26, 9(r28)
        add r28, r4, r27
        lhz r25, 9(r28)
        addi r28, r27, 8
        cmpw cr7, r26, r25
        mfcr r26, 1
        rlwinm r26, r26, 31, 31, 31
        add r25, r8, r27
        cmpw cr7, r25, r7
        mfcr r25, 1
        rlwinm r25, r25, 29, 31, 31
        and. r26, r26, r25
        bne .LBB_test_1 ; loopentry

instead of this:

.LBB_test_1:    ; loopentry
        or r27, r28, r28
        add r28, r3, r27
        lhz r28, 3(r28)
        add r26, r4, r27
        lhz r26, 3(r26)
        cmpw cr0, r28, r26
        beq .LBB_test_3 ; shortcirc_next.0
.LBB_test_2:    ; loopentry.loopexit_crit_edge
        add r2, r30, r27
        add r8, r29, r27
        b .LBB_test_9   ; loopexit
.LBB_test_3:    ; shortcirc_next.0
        add r28, r3, r27
        lhz r28, 5(r28)
        add r26, r4, r27
        lhz r26, 5(r26)
        cmpw cr0, r28, r26
        beq .LBB_test_5 ; shortcirc_next.1
.LBB_test_4:    ; shortcirc_next.0.loopexit_crit_edge
        add r2, r11, r27
        add r8, r12, r27
        b .LBB_test_9   ; loopexit
.LBB_test_5:    ; shortcirc_next.1
        add r28, r3, r27
        lhz r28, 7(r28)
        add r26, r4, r27
        lhz r26, 7(r26)
        cmpw cr0, r28, r26
        beq .LBB_test_7 ; shortcirc_next.2
.LBB_test_6:    ; shortcirc_next.1.loopexit_crit_edge
        add r2, r9, r27
        add r8, r10, r27
        b .LBB_test_9   ; loopexit
.LBB_test_7:    ; shortcirc_next.2
        add r28, r3, r27
        lhz r26, 9(r28)
        add r28, r4, r27
        lhz r25, 9(r28)
        addi r28, r27, 8
        cmpw cr7, r26, r25
        mfcr r26, 1
        rlwinm r26, r26, 31, 31, 31
        add r25, r8, r27
        cmpw cr7, r25, r7
        mfcr r25, 1
        rlwinm r25, r25, 29, 31, 31
        and. r26, r26, r25
        bne .LBB_test_1 ; loopentry

Next up, improve the code for the loop.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22769 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 15 insertions, 3 deletions

diff --git a/lib/Transforms/Scalar/LoopStrengthReduce.cpp b/lib/Transforms/Scalar/LoopStrengthReduce.cpp
index 75a681d98e..20980bba3a 100644
--- a/lib/Transforms/Scalar/LoopStrengthReduce.cpp
+++ b/lib/Transforms/Scalar/LoopStrengthReduce.cpp
@@ -392,7 +392,8 @@ namespace {
     // operands of Inst to use the new expression 'NewBase', with 'Imm' added
     // to it.
     void RewriteInstructionToUseNewBase(const SCEVHandle &NewBase,
-                                        SCEVExpander &Rewriter, Pass *P);
+                                        SCEVExpander &Rewriter, Loop *L,
+                                        Pass *P);
 
     // Sort by the Base field.
     bool operator<(const BasedUser &BU) const { return Base < BU.Base; }
@@ -415,7 +416,7 @@ void BasedUser::dump() const {
 // to it.
 void BasedUser::RewriteInstructionToUseNewBase(const SCEVHandle &NewBase,
                                                SCEVExpander &Rewriter,
-                                               Pass *P) {
+                                               Loop *L, Pass *P) {
   if (!isa<PHINode>(Inst)) {
     SCEVHandle NewValSCEV = SCEVAddExpr::get(NewBase, Imm);
     Value *NewVal = Rewriter.expandCodeFor(NewValSCEV, Inst,
@@ -443,7 +444,18 @@ void BasedUser::RewriteInstructionToUseNewBase(const SCEVHandle &NewBase,
         for (unsigned Succ = 0; ; ++Succ) {
           assert(Succ != PredTI->getNumSuccessors() &&"Didn't find successor?");
           if (PredTI->getSuccessor(Succ) == PN->getParent()) {
+            // First step, split the critical edge.
             SplitCriticalEdge(PredTI, Succ, P);
+            
+            // Next step: move the basic block.  In particular, if the PHI node
+            // is outside of the loop, and PredTI is in the loop, we want to
+            // move the block to be immediately before the PHI block, not
+            // immediately after PredTI.
+            if (L->contains(PredTI->getParent()) &&
+                !L->contains(PN->getParent())) {
+              BasicBlock *NewBB = PN->getIncomingBlock(i);
+              NewBB->moveBefore(PN->getParent());
+            }
             break;
           }
         }
@@ -796,7 +808,7 @@ void LoopStrengthReduce::StrengthReduceStridedIVUsers(const SCEVHandle &Stride,
         // Add BaseV to the PHI value if needed.
         RewriteExpr = SCEVAddExpr::get(RewriteExpr, SCEVUnknown::get(BaseV));
       
-      User.RewriteInstructionToUseNewBase(RewriteExpr, Rewriter, this);
+      User.RewriteInstructionToUseNewBase(RewriteExpr, Rewriter, L, this);
 
       // Mark old value we replaced as possibly dead, so that it is elminated
       // if we just replaced the last use of that value.