Rewrite SCEV's backedge taken count computation.

Patch by Michele Scandale!

Rewrite of the functions used to compute the backedge taken count of a
loop on LT and GT comparisons.

I decided to split the handling of LT and GT cases becasue the trick
"a > b == -a < -b" in some cases prevents the trip count computation
due to the multiplication by -1 on the two operands of the
comparison. This issue comes from the conservative computation of
value range of SCEVs: taking the negative SCEV of an expression that
have a small positive range (e.g. [0,31]), we would have a SCEV with a
fullset as value range.

Indeed, in the new rewritten function I tried to better handle the
maximum backedge taken count computation when MAX/MIN expression are
used to handle the cases where no entry guard is found.

Some test have been modified in order to check the new value correctly
(I manually check them and reasoning on possible overflow the new
values seem correct).

I finally added a new test case related to the multiplication by -1
issue on GT comparisons.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194116 91177308-0d34-0410-b5e6-96231b3b80d8

7 files changed, 20 insertions, 17 deletions

diff --git a/test/Analysis/ScalarEvolution/2008-11-18-Stride1.ll b/test/Analysis/ScalarEvolution/2008-11-18-Stride1.ll
index 74698795ca..7acf90c733 100644
--- a/test/Analysis/ScalarEvolution/2008-11-18-Stride1.ll
+++ b/test/Analysis/ScalarEvolution/2008-11-18-Stride1.ll
@@ -1,6 +1,8 @@
 ; RUN: opt < %s -analyze -scalar-evolution | FileCheck %s
 
-; CHECK: Loop %bb: Unpredictable backedge-taken count.
+; CHECK: Loop %bb: backedge-taken count is ((-5 + %x) /u 3)
+; CHECK: Loop %bb: max backedge-taken count is 1431655764
+
 
 ; ScalarEvolution can't compute a trip count because it doesn't know if
 ; dividing by the stride will have a remainder. This could theoretically
diff --git a/test/Analysis/ScalarEvolution/2008-11-18-Stride2.ll b/test/Analysis/ScalarEvolution/2008-11-18-Stride2.ll
index 0ee69c6d30..2b2296a3a2 100644
--- a/test/Analysis/ScalarEvolution/2008-11-18-Stride2.ll
+++ b/test/Analysis/ScalarEvolution/2008-11-18-Stride2.ll
@@ -1,7 +1,8 @@
 ; RUN: opt < %s -analyze -scalar-evolution 2>&1 | FileCheck %s
-; XFAIL: *
 
-; CHECK: /u 3
+; CHECK: Loop %bb: backedge-taken count is ((999 + (-1 * %x)) /u 3)
+; CHECK: Loop %bb: max backedge-taken count is 334
+
 
 ; This is a tricky testcase for unsigned wrap detection which ScalarEvolution
 ; doesn't yet know how to do.
diff --git a/test/Analysis/ScalarEvolution/2008-12-15-DontUseSDiv.ll b/test/Analysis/ScalarEvolution/2008-12-15-DontUseSDiv.ll
index d40044e7f8..70588bc057 100644
--- a/test/Analysis/ScalarEvolution/2008-12-15-DontUseSDiv.ll
+++ b/test/Analysis/ScalarEvolution/2008-12-15-DontUseSDiv.ll
@@ -1,5 +1,4 @@
 ; RUN: opt < %s -analyze -scalar-evolution 2>&1 | FileCheck %s
-; XFAIL: *
 
 ; CHECK: /u 5
 
diff --git a/test/Analysis/ScalarEvolution/trip-count3.ll b/test/Analysis/ScalarEvolution/trip-count3.ll
index 32c51bfc45..850e035e7c 100644
--- a/test/Analysis/ScalarEvolution/trip-count3.ll
+++ b/test/Analysis/ScalarEvolution/trip-count3.ll
@@ -4,7 +4,8 @@
 ; dividing by the stride will have a remainder. This could theoretically
 ; be teaching it how to use a more elaborate trip count computation.
 
-; CHECK: Loop %bb3.i: Unpredictable backedge-taken count.
+; CHECK: Loop %bb3.i: backedge-taken count is ((64 + (-64 smax (-1 + (-1 * %0))) + %0) /u 64)
+; CHECK: Loop %bb3.i: max backedge-taken count is 33554431
 
 %struct.FILE = type { i32, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, %struct._IO_marker*, %struct.FILE*, i32, i32, i64, i16, i8, [1 x i8], i8*, i64, i8*, i8*, i8*, i8*, i64, i32, [20 x i8] }
 %struct.SHA_INFO = type { [5 x i32], i32, i32, [16 x i32] }
diff --git a/test/Analysis/ScalarEvolution/trip-count9.ll b/test/Analysis/ScalarEvolution/trip-count9.ll
index 85d4050249..9a080b3474 100644
--- a/test/Analysis/ScalarEvolution/trip-count9.ll
+++ b/test/Analysis/ScalarEvolution/trip-count9.ll
@@ -228,7 +228,7 @@ exit:
 }
 
 ; CHECK: Determining loop execution counts for: @even_step2
-; CHECK: Loop %loop: Unpredictable backedge-taken count.
+; CHECK: Loop %loop: backedge-taken count is ((-1 + (2 * %n)) /u 2)
 ; CHECK: Loop %loop: max backedge-taken count is 2
 define void @even_step2(i4 %n) {
 entry:
@@ -262,7 +262,7 @@ exit:
 }
 
 ; CHECK: Determining loop execution counts for: @even_start1_step2
-; CHECK: Loop %loop: Unpredictable backedge-taken count.
+; CHECK: Loop %loop: backedge-taken count is ((-2 + (3 smax (2 * %n))) /u 2)
 ; CHECK: Loop %loop: max backedge-taken count is 2
 define void @even_start1_step2(i4 %n) {
 entry:
@@ -280,7 +280,7 @@ exit:
 
 ; CHECK: Determining loop execution counts for: @even_startx
 ; CHECK: Loop %loop: backedge-taken count is (-1 + (-1 * %x) + ((1 + %x) smax (2 * %n)))
-; CHECK: Loop %loop: max backedge-taken count is -1
+; CHECK: Loop %loop: max backedge-taken count is -2
 define void @even_startx(i4 %n, i4 %x) {
 entry:
   %m = shl i4 %n, 1
@@ -296,7 +296,7 @@ exit:
 }
 
 ; CHECK: Determining loop execution counts for: @even_startx_step2
-; CHECK: Loop %loop: Unpredictable backedge-taken count.
+; CHECK: Loop %loop: backedge-taken count is ((-1 + (-1 * %x) + ((2 + %x) smax (2 * %n))) /u 2)
 ; CHECK: Loop %loop: max backedge-taken count is 7
 define void @even_startx_step2(i4 %n, i4 %x) {
 entry:
@@ -382,7 +382,7 @@ exit:
 
 ; CHECK: Determining loop execution counts for: @even_nsw_startx
 ; CHECK: Loop %loop: backedge-taken count is (-1 + (-1 * %x) + ((1 + %x) smax (2 * %n)))
-; CHECK: Loop %loop: max backedge-taken count is -1
+; CHECK: Loop %loop: max backedge-taken count is -2
 define void @even_nsw_startx(i4 %n, i4 %x) {
 entry:
   %m = shl i4 %n, 1
diff --git a/test/Transforms/IndVarSimplify/loop_evaluate_6.ll b/test/Transforms/IndVarSimplify/loop_evaluate_6.ll
index da38de538f..af01fe5386 100644
--- a/test/Transforms/IndVarSimplify/loop_evaluate_6.ll
+++ b/test/Transforms/IndVarSimplify/loop_evaluate_6.ll
@@ -1,9 +1,4 @@
 ; RUN: opt < %s -indvars -loop-deletion -S | grep phi | count 1
-; XFAIL: *
-
-; Indvars can't evaluate this loop, because ScalarEvolution can't compute
-; an exact trip count, because it doesn't know if dividing by the stride will
-; have a remainder. It could be done with more aggressive VRP though.
 
 define i32 @test(i32 %x_offs) nounwind readnone {
 entry:
diff --git a/test/Transforms/IndVarSimplify/no-iv-rewrite.ll b/test/Transforms/IndVarSimplify/no-iv-rewrite.ll
index 507f695e67..057669277c 100644
--- a/test/Transforms/IndVarSimplify/no-iv-rewrite.ll
+++ b/test/Transforms/IndVarSimplify/no-iv-rewrite.ll
@@ -223,13 +223,18 @@ entry:
   %halfLim = ashr i32 %limit, 2
   br label %loop
 
-; Test cloning an or, which is not an OverflowBinaryOperator.
+; This test originally checked that the OR instruction was cloned. Now the
+; ScalarEvolution is able to understand the loop evolution and that '%iv' at the
+; end of the loop is an even value. Thus '%val' is computed at the end of the
+; loop and the OR instruction is replaced by an ADD keeping the result
+; equivalent.
 ;
 ; CHECK: loop:
 ; CHECK: phi i64
 ; CHECK-NOT: sext
-; CHECK: or i64
+; CHECK: icmp slt i32
 ; CHECK: exit:
+; CHECK: add i64
 loop:
   %iv = phi i32 [ 0, %entry], [ %iv.next, %loop ]
   %t1 = sext i32 %iv to i64