[GVN] Recommit the patch "Add phi-translate support in scalarpre"

Recommit after workaround the bug PR31652.

Three bugs fixed in previous recommits: The first one is to use CurrentBlock
instead of PREInstr's Parent as param of performScalarPREInsertion because
the Parent of a clone instruction may be uninitialized. The second one is stop
PRE when CurrentBlock to its predecessor is a backedge and an operand of CurInst
is defined inside of CurrentBlock. The same value defined inside of loop in last
iteration can not be regarded as available. The third one is an out-of-bound
array access in a flipped if guard.

Right now scalarpre doesn't have phi-translate support, so it will miss some
simple pre opportunities. Like the following testcase, current scalarpre cannot
recognize the last "a * b" is fully redundent because a and b used by the last
"a * b" expr are both defined by phis.

long a[100], b[100], g1, g2, g3;
__attribute__((pure)) long goo();

void foo(long a, long b, long c, long d) {

  g1 = a * b;
  if (__builtin_expect(g2 > 3, 0)) {
    a = c;
    b = d;
    g2 = a * b;
  }
  g3 = a * b;      // fully redundant.

}

The patch adds phi-translate support in scalarpre. This is only a temporary
solution before the newpre based on newgvn is available.

Differential Revision: https://reviews.llvm.org/D32252

llvm-svn: 309397

3 files changed, 135 insertions, 4 deletions

diff --git a/llvm/test/Transforms/GVN/PRE/phi-translate-2.ll b/llvm/test/Transforms/GVN/PRE/phi-translate-2.ll
new file mode 100644
index 00000000000..78681e20df5
--- /dev/null
+++ b/llvm/test/Transforms/GVN/PRE/phi-translate-2.ll
@@ -0,0 +1,131 @@
+; RUN: opt < %s -gvn -S | FileCheck %s
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+
+@a = common global [100 x i64] zeroinitializer, align 16
+@b = common global [100 x i64] zeroinitializer, align 16
+@g1 = common global i64 0, align 8
+@g2 = common global i64 0, align 8
+@g3 = common global i64 0, align 8
+declare i64 @goo(...) local_unnamed_addr #1
+
+define void @test1(i64 %a, i64 %b, i64 %c, i64 %d) {
+entry:
+  %mul = mul nsw i64 %b, %a
+  store i64 %mul, i64* @g1, align 8
+  %t0 = load i64, i64* @g2, align 8
+  %cmp = icmp sgt i64 %t0, 3
+  br i1 %cmp, label %if.then, label %if.end
+
+if.then:                                          ; preds = %entry
+  %mul2 = mul nsw i64 %d, %c
+  store i64 %mul2, i64* @g2, align 8
+  br label %if.end
+
+; Check phi-translate works and mul is removed.
+; CHECK-LABEL: @test1(
+; CHECK: if.end:
+; CHECK: %[[MULPHI:.*]] = phi i64 [ {{.*}}, %if.then ], [ %mul, %entry ]
+; CHECK-NOT: = mul
+; CHECK: store i64 %[[MULPHI]], i64* @g3, align 8
+if.end:                                           ; preds = %if.then, %entry
+  %b.addr.0 = phi i64 [ %d, %if.then ], [ %b, %entry ]
+  %a.addr.0 = phi i64 [ %c, %if.then ], [ %a, %entry ]
+  %mul3 = mul nsw i64 %a.addr.0, %b.addr.0
+  store i64 %mul3, i64* @g3, align 8
+  ret void
+}
+
+define void @test2(i64 %i) {
+entry:
+  %arrayidx = getelementptr inbounds [100 x i64], [100 x i64]* @a, i64 0, i64 %i
+  %t0 = load i64, i64* %arrayidx, align 8
+  %arrayidx1 = getelementptr inbounds [100 x i64], [100 x i64]* @b, i64 0, i64 %i
+  %t1 = load i64, i64* %arrayidx1, align 8
+  %mul = mul nsw i64 %t1, %t0
+  store i64 %mul, i64* @g1, align 8
+  %cmp = icmp sgt i64 %mul, 3
+  br i1 %cmp, label %if.then, label %if.end
+
+; Check phi-translate works for the phi generated by loadpre. A new mul will be
+; inserted in if.then block.
+; CHECK-LABEL: @test2(
+; CHECK: if.then:
+; CHECK: %[[MUL_THEN:.*]] = mul
+; CHECK: br label %if.end
+if.then:                                          ; preds = %entry
+  %call = tail call i64 (...) @goo() #2
+  store i64 %call, i64* @g2, align 8
+  br label %if.end
+
+; CHECK: if.end:
+; CHECK: %[[MULPHI:.*]] = phi i64 [ %[[MUL_THEN]], %if.then ], [ %mul, %entry ]
+; CHECK-NOT: = mul
+; CHECK: store i64 %[[MULPHI]], i64* @g3, align 8
+if.end:                                           ; preds = %if.then, %entry
+  %i.addr.0 = phi i64 [ 3, %if.then ], [ %i, %entry ]
+  %arrayidx3 = getelementptr inbounds [100 x i64], [100 x i64]* @a, i64 0, i64 %i.addr.0
+  %t2 = load i64, i64* %arrayidx3, align 8
+  %arrayidx4 = getelementptr inbounds [100 x i64], [100 x i64]* @b, i64 0, i64 %i.addr.0
+  %t3 = load i64, i64* %arrayidx4, align 8
+  %mul5 = mul nsw i64 %t3, %t2
+  store i64 %mul5, i64* @g3, align 8
+  ret void
+}
+
+; Check phi-translate doesn't go through backedge, which may lead to incorrect
+; pre transformation.
+; CHECK: for.end:
+; CHECK-NOT: %{{.*pre-phi}} = phi
+; CHECK: ret void
+define void @test3(i64 %N, i64* nocapture readonly %a) {
+entry:
+  br label %for.cond
+
+for.cond:                                         ; preds = %for.body, %entry
+  %i.0 = phi i64 [ 0, %entry ], [ %add, %for.body ]
+  %add = add nuw nsw i64 %i.0, 1
+  %arrayidx = getelementptr inbounds i64, i64* %a, i64 %add
+  %tmp0 = load i64, i64* %arrayidx, align 8
+  %cmp = icmp slt i64 %i.0, %N
+  br i1 %cmp, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.cond
+  %call = tail call i64 (...) @goo() #2
+  %add1 = sub nsw i64 0, %call
+  %tobool = icmp eq i64 %tmp0, %add1
+  br i1 %tobool, label %for.cond, label %for.end
+
+for.end:                                          ; preds = %for.body, %for.cond
+  %i.0.lcssa = phi i64 [ %i.0, %for.body ], [ %i.0, %for.cond ]
+  %arrayidx2 = getelementptr inbounds i64, i64* %a, i64 %i.0.lcssa
+  %tmp1 = load i64, i64* %arrayidx2, align 8
+  store i64 %tmp1, i64* @g1, align 8
+  ret void
+}
+
+; It is incorrect to use the value of %andres in last loop iteration
+; to do pre.
+; CHECK-LABEL: @test4(
+; CHECK: for.body:
+; CHECK-NOT: %andres.pre-phi = phi i32
+; CHECK: br i1 %tobool1
+
+define i32 @test4(i32 %cond, i32 %SectionAttrs.0231.ph, i32 *%AttrFlag) {
+for.body.preheader:
+  %t514 = load volatile i32, i32* %AttrFlag
+  br label %for.body
+
+for.body:
+  %t320 = phi i32 [ %t334, %bb343 ], [ %t514, %for.body.preheader ]
+  %andres = and i32 %t320, %SectionAttrs.0231.ph
+  %tobool1 = icmp eq i32 %andres, 0
+  br i1 %tobool1, label %bb343, label %critedge.loopexit
+
+bb343:
+  %t334 = load volatile i32, i32* %AttrFlag
+  %tobool2 = icmp eq i32 %cond, 0
+  br i1 %tobool2, label %critedge.loopexit, label %for.body
+
+critedge.loopexit:
+  unreachable
+}
diff --git a/llvm/test/Transforms/GVN/PRE/pre-gep-load.ll b/llvm/test/Transforms/GVN/PRE/pre-gep-load.ll
index 9eec8bb6455..1b2b4d20d31 100644
--- a/llvm/test/Transforms/GVN/PRE/pre-gep-load.ll
+++ b/llvm/test/Transforms/GVN/PRE/pre-gep-load.ll
@@ -37,7 +37,7 @@ sw.bb2:                                           ; preds = %if.end, %entry
   %3 = load double, double* %arrayidx5, align 8
 ; CHECK: sw.bb2:
 ; CHECK-NOT: sext
-; CHECK-NEXT: phi double [
+; CHECK: phi double [
 ; CHECK-NOT: load
   %sub6 = fsub double 3.000000e+00, %3
   br label %return
diff --git a/llvm/test/Transforms/GVN/PRE/pre-load.ll b/llvm/test/Transforms/GVN/PRE/pre-load.ll
index 685df24f62b..ffff2b7f08e 100644
--- a/llvm/test/Transforms/GVN/PRE/pre-load.ll
+++ b/llvm/test/Transforms/GVN/PRE/pre-load.ll
@@ -72,7 +72,7 @@ block4:
   %PRE = load i32, i32* %P3
   ret i32 %PRE
 ; CHECK: block4:
-; CHECK-NEXT: phi i32 [
+; CHECK: phi i32 [
 ; CHECK-NOT: load
 ; CHECK: ret i32
 }
@@ -104,7 +104,7 @@ block4:
   %PRE = load i32, i32* %P3
   ret i32 %PRE
 ; CHECK: block4:
-; CHECK-NEXT: phi i32 [
+; CHECK: phi i32 [
 ; CHECK-NOT: load
 ; CHECK: ret i32
 }
@@ -263,7 +263,7 @@ block4:
   %PRE = load i32, i32* %P3
   ret i32 %PRE
 ; CHECK: block4:
-; CHECK-NEXT: phi i32 [
+; CHECK: phi i32 [
 ; CHECK-NOT: load
 ; CHECK: ret i32
 }