Improve vectorization diagnostic messages and extend vectorize(enable) pragma.

This patch changes the analysis diagnostics produced when loops with
floating-point recurrences or memory operations are identified. The new messages 
say "cannot prove it is safe to reorder * operations; allow reordering by
specifying #pragma clang loop vectorize(enable)". Depending on the type of 
diagnostic the message will include additional options such as ffast-math or
__restrict__.

This patch also allows the vectorize(enable) pragma to override the low pointer
memory check threshold. When the hint is given a higher threshold is used.

See the clang patch for the options produced for each diagnostic.

llvm-svn: 246187

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -214,6 +214,11 @@ static cl::opt<unsigned> MaxNestedScalarReductionIC(
     cl::desc("The maximum interleave count to use when interleaving a scalar "
              "reduction in a nested loop."));
 
+static cl::opt<unsigned> PragmaVectorizeMemoryCheckThreshold(
+    "pragma-vectorize-memory-check-threshold", cl::init(128), cl::Hidden,
+    cl::desc("The maximum allowed number of runtime memory checks with a "
+             "vectorize(enable) pragma."));
+
 namespace {
 
 // Forward declarations.
@@ -929,6 +934,15 @@ public:
     return DiagnosticInfo::AlwaysPrint;
   }
 
+  bool allowReordering() const {
+    // When enabling loop hints are provided we allow the vectorizer to change
+    // the order of operations that is given by the scalar loop. This is not
+    // enabled by default because can be unsafe or inefficient. For example,
+    // reordering floating-point operations will change the way round-off
+    // error accumulates in the loop.
+    return getForce() == LoopVectorizeHints::FK_Enabled || getWidth() > 1;
+  }
+
 private:
   /// Find hints specified in the loop metadata and update local values.
   void getHintsFromMetadata() {
@@ -1427,29 +1441,25 @@ public:
   bool doesNotMeet(Function *F, Loop *L, const LoopVectorizeHints &Hints) {
     const char *Name = Hints.vectorizeAnalysisPassName();
     bool Failed = false;
-    if (UnsafeAlgebraInst &&
-        Hints.getForce() == LoopVectorizeHints::FK_Undefined &&
-        Hints.getWidth() == 0) {
+    if (UnsafeAlgebraInst && !Hints.allowReordering()) {
       emitOptimizationRemarkAnalysisFPCommute(
           F->getContext(), Name, *F, UnsafeAlgebraInst->getDebugLoc(),
-          VectorizationReport() << "vectorization requires changes in the "
-                                   "order of operations, however IEEE 754 "
-                                   "floating-point operations are not "
-                                   "commutative");
+          VectorizationReport() << "cannot prove it is safe to reorder "
+                                   "floating-point operations");
       Failed = true;
     }
 
-    if (NumRuntimePointerChecks >
-        VectorizerParams::RuntimeMemoryCheckThreshold) {
+    // Test if runtime memcheck thresholds are exceeded.
+    bool PragmaThresholdReached =
+        NumRuntimePointerChecks > PragmaVectorizeMemoryCheckThreshold;
+    bool ThresholdReached =
+        NumRuntimePointerChecks > VectorizerParams::RuntimeMemoryCheckThreshold;
+    if ((ThresholdReached && !Hints.allowReordering()) ||
+        PragmaThresholdReached) {
       emitOptimizationRemarkAnalysisAliasing(
           F->getContext(), Name, *F, L->getStartLoc(),
           VectorizationReport()
-              << "cannot prove pointers refer to independent arrays in memory. "
-                 "The loop requires "
-              << NumRuntimePointerChecks
-              << " runtime independence checks to vectorize the loop, but that "
-                 "would exceed the limit of "
-              << VectorizerParams::RuntimeMemoryCheckThreshold << " checks");
+              << "cannot prove it is safe to reorder memory operations");
       DEBUG(dbgs() << "LV: Too many memory checks needed.\n");
       Failed = true;
     }

llvm/test/Transforms/LoopVectorize/X86/no_fpmath.ll

@@ -1,6 +1,6 @@
 ; RUN: opt < %s -loop-vectorize -mtriple=x86_64-unknown-linux -S -pass-remarks='loop-vectorize' -pass-remarks-missed='loop-vectorize' -pass-remarks-analysis='loop-vectorize' 2>&1 | FileCheck %s
 
-; CHECK: remark: no_fpmath.c:6:11: loop not vectorized: vectorization requires changes in the order of operations, however IEEE 754 floating-point operations are not commutative
+; CHECK: remark: no_fpmath.c:6:11: loop not vectorized: cannot prove it is safe to reorder floating-point operations
 ; CHECK: remark: no_fpmath.c:6:14: loop not vectorized:
 ; CHECK: remark: no_fpmath.c:17:14: vectorized loop (vectorization width: 2, interleaved count: 2)
 

llvm/test/Transforms/LoopVectorize/runtime-limit.ll

@@ -1,17 +1,27 @@
-; RUN: opt < %s  -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s
+; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s
+; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s -check-prefix=OVERRIDE
+; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -pragma-vectorize-memory-check-threshold=6 -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.8.0"
 
 ; First loop produced diagnostic pass remark.
-;CHECK: remark: {{.*}}:0:0: vectorized loop (vectorization width: 4, interleaved count: 1)
+;CHECK: remark: {{.*}}:0:0: vectorized loop (vectorization width: {{[0-9]}}, interleaved count: 1)
 ; Second loop produces diagnostic analysis remark.
-;CHECK: remark: {{.*}}:0:0: loop not vectorized: cannot prove pointers refer to independent arrays in memory. The loop requires 11 runtime independence checks to vectorize the loop, but that would exceed the limit of 8 checks
+;CHECK: remark: {{.*}}:0:0: loop not vectorized: cannot prove it is safe to reorder memory operations
+
+; First loop produced diagnostic pass remark.
+;OVERRIDE: remark: {{.*}}:0:0: vectorized loop (vectorization width: {{[0-9]}}, interleaved count: 1)
+; Second loop produces diagnostic pass remark.
+;OVERRIDE: remark: {{.*}}:0:0: vectorized loop (vectorization width: {{[0-9]}}, interleaved count: 1)
 
 ; We are vectorizing with 6 runtime checks.
 ;CHECK-LABEL: func1x6(
-;CHECK: <4 x i32>
+;CHECK: <{{[0-9]}} x i32>
 ;CHECK: ret
+;OVERRIDE-LABEL: func1x6(
+;OVERRIDE: <4 x i32>
+;OVERRIDE: ret
 define i32 @func1x6(i32* nocapture %out, i32* nocapture %A, i32* nocapture %B, i32* nocapture %C, i32* nocapture %D, i32* nocapture %E, i32* nocapture %F) {
 entry:
   br label %for.body
@@ -44,8 +54,12 @@ for.end:                                          ; preds = %for.body
 
 ; We are not vectorizing with 12 runtime checks.
 ;CHECK-LABEL: func2x6(
-;CHECK-NOT: <4 x i32>
+;CHECK-NOT: <{{[0-9]}} x i32>
 ;CHECK: ret
+; We vectorize with 12 checks if a vectorization hint is provided.
+;OVERRIDE-LABEL: func2x6(
+;OVERRIDE: <4 x i32>
+;OVERRIDE: ret
 define i32 @func2x6(i32* nocapture %out, i32* nocapture %out2, i32* nocapture %A, i32* nocapture %B, i32* nocapture %C, i32* nocapture %D, i32* nocapture %E, i32* nocapture %F) {
 entry:
   br label %for.body