Revert "Revert "[Unroll] Implement a conservative and monotonically increasing cost tracking system during the full unroll heuristic analysis that avoids counting any instruction cost until that instruction becomes "live" through a side-effect or use outside the...""

This reverts commit r269395.

Try to reapply with a fix from chapuni.

llvm-svn: 269486

3 files changed, 40 insertions, 2 deletions

diff --git a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
index 5df48e8c380..f62141d9c37 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
+++ b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10  -unroll-percent-dynamic-cost-saved-threshold=50 -unroll-dynamic-cost-savings-discount=90 | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10  -unroll-percent-dynamic-cost-saved-threshold=70 -unroll-dynamic-cost-savings-discount=90 | FileCheck %s
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
 @unknown_global = internal unnamed_addr global [9 x i32] [i32 0, i32 -1, i32 0, i32 -1, i32 5, i32 -1, i32 0, i32 -1, i32 0], align 16
diff --git a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll
new file mode 100644
index 00000000000..6ee73b6fe4f
--- /dev/null
+++ b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll
@@ -0,0 +1,38 @@
+; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-dynamic-cost-savings-discount=1000 -unroll-threshold=10 -unroll-percent-dynamic-cost-saved-threshold=60 | FileCheck %s
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+@known_constant = internal unnamed_addr constant [10 x i32] [i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0, i32 0], align 16
+
+; If a load becomes a constant after loop unrolling, we sometimes can simplify
+; CFG. This test verifies that we handle such cases.
+; After one operand in an instruction is constant-folded and the
+; instruction is simplified, the other operand might become dead.
+; In this test we have::
+; for i in 1..10:
+;   r += A[i] * B[i]
+; A[i] is 0 almost at every iteration, so there is no need in loading B[i] at
+; all.
+
+
+; CHECK-LABEL: @unroll_dce
+; CHECK-NOT:   br i1 %exitcond, label %for.end, label %for.body
+define i32 @unroll_dce(i32* noalias nocapture readonly %b) {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %iv.0 = phi i64 [ 0, %entry ], [ %iv.1, %for.body ]
+  %r.0 = phi i32 [ 0, %entry ], [ %r.1, %for.body ]
+  %arrayidx1 = getelementptr inbounds [10 x i32], [10 x i32]* @known_constant, i64 0, i64 %iv.0
+  %x1 = load i32, i32* %arrayidx1, align 4
+  %arrayidx2 = getelementptr inbounds i32, i32* %b, i64 %iv.0
+  %x2 = load i32, i32* %arrayidx2, align 4
+  %mul = mul i32 %x1, %x2
+  %r.1 = add i32 %mul, %r.0
+  %iv.1 = add nuw nsw i64 %iv.0, 1
+  %exitcond = icmp eq i64 %iv.1, 10
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret i32 %r.1
+}
diff --git a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll
index bc08029d4f8..723a384ea2d 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll
+++ b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-dynamic-cost-savings-discount=1000 -unroll-threshold=10 -unroll-percent-dynamic-cost-saved-threshold=40 | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-dynamic-cost-savings-discount=1000 -unroll-threshold=10 -unroll-percent-dynamic-cost-saved-threshold=60 | FileCheck %s
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
 ; When examining gep-instructions we shouldn't consider them simplified if the