[LoopInterchange] Loops with empty dependency matrix are safe.

[fhahn]

Summary

The dependency matrix is only empty if no conflicting load/store
instructions have been found. In that case, it is safe to interchange.

For the LLVM test-suite, after this change around 1900 loops are
interchanged, whereas it is 15 before this change. On cortex-a57,
this gives an improvement of -0.57% on the geomean execution
time of SPEC2006, SPEC2000 and the test-suite. There are a
few small perf regressions, but I think we can improve on those
by making the cost model better.

[fhahn]

Ping, rebased diff

[karthikthecool]

LGTM.
Thanks

[davide]

Can we add a test for this?

[davide]

Just noticed you added it later, never mind.

[fhahn]

In D43236#1019293, @davide wrote:

Just noticed you added it later, never mind.

Yeah I somehow managed to mess up the diff in Phabricator... But rL326078 added the test case.

[xbolva00]

Hello, any reason why LoopInterchange pass is not on by default?

[fhahn]

In D43236#1170926, @xbolva00 wrote:

Hello, any reason why LoopInterchange pass is not on by default?

There used to be some bugs causing crashes, but all known/reported bugs are fixed now. Currently the set of supported loops is quite limited and there are at least 2 things I would like to address before enabling it. I've created https://bugs.llvm.org/show_bug.cgi?id=38263 as a place to keep track of enabling it, with some more details.
Getting patches for LoopInterchange takes a while, because there are not many people working on it, but my strategy has been to just move them along at a slow pace :)

lib/Transforms/Scalar/LoopInterchange.cpp

for (J = I, JE = MemInstr.end(); J != JE; ++J) {
           DEBUG(dbgs() << "Cannot handle more than " << MaxMemInstrCount
                        << " dependencies inside loop\n");
           return false;
         }
       }
     }
   }
 
-  // We don't have a DepMatrix to check legality return false.
-  if (DepMatrix.empty())
-    return false;
   return true;
 }
 
 // A loop is moved from index 'from' to an index 'to'. Update the Dependence
 // matrix by exchanging the two columns.
 static void interChangeDependencies(CharMatrix &DepMatrix, unsigned FromIndx,
                                     unsigned ToIndx) {
   unsigned numRows = DepMatrix.size();

test/Transforms/LoopInterchange/interchange-no-deps.ll

+; RUN: opt < %s -loop-interchange -simplifycfg -S | FileCheck %s
+
+; no_deps_interchange just access a single nested array and can be interchange.
+define i32 @no_deps_interchange([1024 x i32]* nocapture %Arr, i32 %k) local_unnamed_addr #0 {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.cond.cleanup3
+  %indvars.iv19 = phi i64 [ 0, %entry ], [ %indvars.iv.next20, %for.cond.cleanup3 ]
+  br label %for.body4
+
+for.body4:                                        ; preds = %for.body, %for.body4
+  %indvars.iv = phi i64 [ 0, %for.body ], [ %indvars.iv.next, %for.body4 ]
+  %arrayidx6 = getelementptr inbounds [1024 x i32], [1024 x i32]* %Arr, i64 %indvars.iv, i64 %indvars.iv19
+  store i32 0, i32* %arrayidx6, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp ne i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.body4, label %for.cond.cleanup3
+
+for.cond.cleanup3:                                ; preds = %for.body4
+  %indvars.iv.next20 = add nuw nsw i64 %indvars.iv19, 1
+  %exitcond21 = icmp ne i64 %indvars.iv.next20, 1024
+  br i1 %exitcond21, label %for.body, label %for.cond.cleanup
+
+
+for.cond.cleanup:                                 ; preds = %for.cond.cleanup3
+  ret i32 0
+}
+
+; CHECK-LABEL: @no_deps_interchange
+; CHECK-LABEL: entry:
+; CHECK-NEXT: br label %for.body4
+
+; CHECK-LABEL: for.body:                                         ; preds = %for.body4, %for.body
+; CHECK: %indvars.iv19 = phi i64 [ %indvars.iv.next20, %for.body ], [ 0, %for.body4 ]
+; CHECK: br i1 %exitcond21, label %for.body, label %for.body4.split
+
+; CHECK-LABEL: for.body4:                                        ; preds = %entry, %for.body4.split
+; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %for.body4.split ], [ 0, %entry ]
+; CHECK: br label %for.body
+
+; CHECK-LABEL: for.body4.split:                                  ; preds = %for.body
+; CHECK: %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+; CHECK: br i1 %exitcond, label %for.body4, label %for.cond.cleanup