[LFTR] Use recomputed BE count

This was discussed as part of D62880.  The basic thought is that computing BE taken count after widening should produce (on average) an equally good backedge taken count as the one before widening.  Since there's only one test in the suite which is impacted by this change, and it's essentially equivelent codegen, that seems to be a reasonable assertion.  This change was separated from r362971 so that if this turns out to be problematic, the triggering piece is obvious and easily revertable.

For the nestedIV example from elim-extend.ll, we end up with the following BE counts:
BEFORE: (-2 + (-1 * %innercount) + %limit)
AFTER: (-1 + (sext i32 (-1 + %limit) to i64) + (-1 * (sext i32 %innercount to i64))<nsw>)

Note that before is an i32 type, and the after is an i64.  Truncating the i64 produces the i32.

llvm-svn: 362975

diff --git a/llvm/lib/Transforms/Scalar/IndVarSimplify.cpp b/llvm/lib/Transforms/Scalar/IndVarSimplify.cpp
index 25a87c0..06ebe16 100644 (file)
--- a/llvm/lib/Transforms/Scalar/IndVarSimplify.cpp
+++ b/llvm/lib/Transforms/Scalar/IndVarSimplify.cpp
@@ -2635,15 +2635,7 @@ bool IndVarSimplify::run(Loop *L) {
       if (!needsLFTR(L, ExitingBB))
         continue;
 
-      // Note: This block of code is here strictly to seperate an change into
-      // two parts: one NFC, one not.  What's happening here is that SCEV is
-      // returning a more expensive expression for the BackedgeTakenCount for
-      // the loop after widening in rare circumstances.  In review, we decided
-      // to accept that small difference - since it has minimal test suite
-      // impact - but for ease of attribution, the functional diff will be it's
-      // own change.  
-      const SCEV *BETakenCount = L->getExitingBlock() ?
-        BackedgeTakenCount : SE->getExitCount(L, ExitingBB);
+      const SCEV *BETakenCount = SE->getExitCount(L, ExitingBB);
       if (isa<SCEVCouldNotCompute>(BETakenCount))
         continue;
 

diff --git a/llvm/test/Transforms/IndVarSimplify/elim-extend.ll b/llvm/test/Transforms/IndVarSimplify/elim-extend.ll
index 314ce69..7fda91c 100644 (file)
--- a/llvm/test/Transforms/IndVarSimplify/elim-extend.ll
+++ b/llvm/test/Transforms/IndVarSimplify/elim-extend.ll
@@ -112,44 +112,44 @@ define void @nestedIV(i8* %address, i32 %limit) nounwind {
 ; CHECK-LABEL: @nestedIV(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[LIMITDEC:%.*]] = add i32 [[LIMIT:%.*]], -1
-; CHECK-NEXT:    [[TMP0:%.*]] = sext i32 [[LIMIT]] to i64
+; CHECK-NEXT:    [[TMP0:%.*]] = sext i32 [[LIMITDEC]] to i64
+; CHECK-NEXT:    [[TMP1:%.*]] = sext i32 [[LIMIT]] to i64
 ; CHECK-NEXT:    br label [[OUTERLOOP:%.*]]
 ; CHECK:       outerloop:
 ; CHECK-NEXT:    [[INDVARS_IV1:%.*]] = phi i64 [ [[INDVARS_IV_NEXT2:%.*]], [[OUTERMERGE:%.*]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    [[INNERCOUNT:%.*]] = phi i32 [ [[INNERCOUNT_MERGE:%.*]], [[OUTERMERGE]] ], [ 0, [[ENTRY]] ]
-; CHECK-NEXT:    [[TMP1:%.*]] = add nsw i64 [[INDVARS_IV1]], -1
-; CHECK-NEXT:    [[ADR1:%.*]] = getelementptr i8, i8* [[ADDRESS:%.*]], i64 [[TMP1]]
+; CHECK-NEXT:    [[TMP2:%.*]] = add nsw i64 [[INDVARS_IV1]], -1
+; CHECK-NEXT:    [[ADR1:%.*]] = getelementptr i8, i8* [[ADDRESS:%.*]], i64 [[TMP2]]
 ; CHECK-NEXT:    store i8 0, i8* [[ADR1]]
 ; CHECK-NEXT:    br label [[INNERPREHEADER:%.*]]
 ; CHECK:       innerpreheader:
 ; CHECK-NEXT:    [[INNERPRECMP:%.*]] = icmp sgt i32 [[LIMITDEC]], [[INNERCOUNT]]
 ; CHECK-NEXT:    br i1 [[INNERPRECMP]], label [[INNERLOOP_PREHEADER:%.*]], label [[OUTERMERGE]]
 ; CHECK:       innerloop.preheader:
-; CHECK-NEXT:    [[TMP2:%.*]] = sext i32 [[INNERCOUNT]] to i64
+; CHECK-NEXT:    [[TMP3:%.*]] = sext i32 [[INNERCOUNT]] to i64
 ; CHECK-NEXT:    br label [[INNERLOOP:%.*]]
 ; CHECK:       innerloop:
-; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[TMP2]], [[INNERLOOP_PREHEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], [[INNERLOOP]] ]
+; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[TMP3]], [[INNERLOOP_PREHEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], [[INNERLOOP]] ]
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nsw i64 [[INDVARS_IV]], 1
 ; CHECK-NEXT:    [[ADR2:%.*]] = getelementptr i8, i8* [[ADDRESS]], i64 [[INDVARS_IV]]
 ; CHECK-NEXT:    store i8 0, i8* [[ADR2]]
 ; CHECK-NEXT:    [[ADR3:%.*]] = getelementptr i8, i8* [[ADDRESS]], i64 [[INDVARS_IV_NEXT]]
 ; CHECK-NEXT:    store i8 0, i8* [[ADR3]]
-; CHECK-NEXT:    [[WIDE_TRIP_COUNT:%.*]] = sext i32 [[LIMITDEC]] to i64
-; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
+; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], [[TMP0]]
 ; CHECK-NEXT:    br i1 [[EXITCOND]], label [[INNERLOOP]], label [[INNEREXIT:%.*]]
 ; CHECK:       innerexit:
 ; CHECK-NEXT:    [[INNERCOUNT_LCSSA_WIDE:%.*]] = phi i64 [ [[INDVARS_IV_NEXT]], [[INNERLOOP]] ]
-; CHECK-NEXT:    [[TMP3:%.*]] = trunc i64 [[INNERCOUNT_LCSSA_WIDE]] to i32
+; CHECK-NEXT:    [[TMP4:%.*]] = trunc i64 [[INNERCOUNT_LCSSA_WIDE]] to i32
 ; CHECK-NEXT:    br label [[OUTERMERGE]]
 ; CHECK:       outermerge:
-; CHECK-NEXT:    [[INNERCOUNT_MERGE]] = phi i32 [ [[TMP3]], [[INNEREXIT]] ], [ [[INNERCOUNT]], [[INNERPREHEADER]] ]
+; CHECK-NEXT:    [[INNERCOUNT_MERGE]] = phi i32 [ [[TMP4]], [[INNEREXIT]] ], [ [[INNERCOUNT]], [[INNERPREHEADER]] ]
 ; CHECK-NEXT:    [[ADR4:%.*]] = getelementptr i8, i8* [[ADDRESS]], i64 [[INDVARS_IV1]]
 ; CHECK-NEXT:    store i8 0, i8* [[ADR4]]
 ; CHECK-NEXT:    [[OFS5:%.*]] = sext i32 [[INNERCOUNT_MERGE]] to i64
 ; CHECK-NEXT:    [[ADR5:%.*]] = getelementptr i8, i8* [[ADDRESS]], i64 [[OFS5]]
 ; CHECK-NEXT:    store i8 0, i8* [[ADR5]]
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT2]] = add nuw nsw i64 [[INDVARS_IV1]], 1
-; CHECK-NEXT:    [[TMP47:%.*]] = icmp slt i64 [[INDVARS_IV_NEXT2]], [[TMP0]]
+; CHECK-NEXT:    [[TMP47:%.*]] = icmp slt i64 [[INDVARS_IV_NEXT2]], [[TMP1]]
 ; CHECK-NEXT:    br i1 [[TMP47]], label [[OUTERLOOP]], label [[RETURN:%.*]]
 ; CHECK:       return:
 ; CHECK-NEXT:    ret void