When processing outer loops and we find uses of an IV in inner loops, make

sure to handle the use, just don't recurse into it.

This permits us to generate this code for a simple nested loop case:

.LBB_foo_0:     ; entry
        stwu r1, -48(r1)
        stw r29, 44(r1)
        stw r30, 40(r1)
        mflr r11
        stw r11, 56(r1)
        lis r2, ha16(L_A$non_lazy_ptr)
        lwz r30, lo16(L_A$non_lazy_ptr)(r2)
        li r29, 1
.LBB_foo_1:     ; no_exit.0
        bl L_bar$stub
        li r2, 1
        or r3, r30, r30
.LBB_foo_2:     ; no_exit.1
        lfd f0, 8(r3)
        stfd f0, 0(r3)
        addi r4, r2, 1
        addi r3, r3, 8
        cmpwi cr0, r2, 100
        or r2, r4, r4
        bne .LBB_foo_2  ; no_exit.1
.LBB_foo_3:     ; loopexit.1
        addi r30, r30, 800
        addi r2, r29, 1
        cmpwi cr0, r29, 100
        or r29, r2, r2
        bne .LBB_foo_1  ; no_exit.0
.LBB_foo_4:     ; return
        lwz r11, 56(r1)
        mtlr r11
        lwz r30, 40(r1)
        lwz r29, 44(r1)
        lwz r1, 0(r1)
        blr

instead of this:

_foo:
.LBB_foo_0:     ; entry
        stwu r1, -48(r1)
        stw r28, 44(r1)                   ;; uses an extra register.
        stw r29, 40(r1)
        stw r30, 36(r1)
        mflr r11
        stw r11, 56(r1)
        li r30, 1
        li r29, 0
        or r28, r29, r29
.LBB_foo_1:     ; no_exit.0
        bl L_bar$stub
        mulli r2, r28, 800           ;; unstrength-reduced multiply
        lis r3, ha16(L_A$non_lazy_ptr)   ;; loop invariant address computation
        lwz r3, lo16(L_A$non_lazy_ptr)(r3)
        add r2, r2, r3
        mulli r4, r29, 800           ;; unstrength-reduced multiply
        addi r3, r3, 8
        add r3, r4, r3
        li r4, 1
.LBB_foo_2:     ; no_exit.1
        lfd f0, 0(r3)
        stfd f0, 0(r2)
        addi r5, r4, 1
        addi r2, r2, 8                 ;; multiple stride 8 IV's
        addi r3, r3, 8
        cmpwi cr0, r4, 100
        or r4, r5, r5
        bne .LBB_foo_2  ; no_exit.1
.LBB_foo_3:     ; loopexit.1
        addi r28, r28, 1               ;;; Many IV's with stride 1
        addi r29, r29, 1
        addi r2, r30, 1
        cmpwi cr0, r30, 100
        or r30, r2, r2
        bne .LBB_foo_1  ; no_exit.0
.LBB_foo_4:     ; return
        lwz r11, 56(r1)
        mtlr r11
        lwz r30, 36(r1)
        lwz r29, 40(r1)
        lwz r28, 44(r1)
        lwz r1, 0(r1)
        blr

llvm-svn: 22640

1 files changed, 9 insertions, 2 deletions

diff --git a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
index 9a9b0c2aeca..b33bc859c5f 100644
--- a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
@@ -393,9 +393,16 @@ bool LoopStrengthReduce::AddUsersIfInteresting(Instruction *I, Loop *L) {
       continue;
 
     // If this is an instruction defined in a nested loop, or outside this loop,
-    // don't mess with it.
-    if (LI->getLoopFor(User->getParent()) != L)
+    // don't recurse into it.
+    if (LI->getLoopFor(User->getParent()) != L) {
+      DEBUG(std::cerr << "FOUND USER in nested loop: " << *User
+            << "   OF SCEV: " << *ISE << "\n");
+      
+      // Okay, we found a user that we cannot reduce.  Analyze the instruction
+      // and decide what to do with it.
+      IVUsesByStride[Step].addUser(Start, User, I);
       continue;
+    }
 
     // Next, see if this user is analyzable itself!
     if (!AddUsersIfInteresting(User, L)) {