[InstCombine] Convert a masked.load of a dereferenceable address to an unconditional...

If we have a masked.load from a location we know to be dereferenceable, we can simply issue a speculative unconditional load against that address. The key advantage is that it produces IR which is well understood by the optimizer. The select (cnd, load, passthrough) form produced should be pattern matchable back to hardware predication if profitable.

Differential Revision: https://reviews.llvm.org/D59703

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@359000 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/InstCombine/InstCombineCalls.cpp b/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 0fe52b145fe6c709d4459d0846e4e5a4917a150c..51c72eb1837acae04673250248524b2dbae1f436 100644 (file)
--- a/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -21,6 +21,7 @@
 #include "llvm/ADT/Statistic.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/Analysis/AssumptionCache.h"
+#include "llvm/Analysis/Loads.h"
 #include "llvm/Analysis/InstructionSimplify.h"
 #include "llvm/Analysis/MemoryBuiltins.h"
 #include "llvm/Transforms/Utils/Local.h"
@@ -1183,17 +1184,26 @@ static APInt possiblyDemandedEltsInMask(Value *Mask) {
 }
 
 // TODO, Obvious Missing Transforms:
-// * Dereferenceable address -> speculative load/select
 // * Narrow width by halfs excluding zero/undef lanes
 static Value *simplifyMaskedLoad(const IntrinsicInst &II,
                                  InstCombiner::BuilderTy &Builder) {
+  Value *LoadPtr = II.getArgOperand(0);
+  unsigned Alignment = cast<ConstantInt>(II.getArgOperand(1))->getZExtValue();
+
   // If the mask is all ones or undefs, this is a plain vector load of the 1st
   // argument.
-  if (maskIsAllOneOrUndef(II.getArgOperand(2))) {
-    Value *LoadPtr = II.getArgOperand(0);
-    unsigned Alignment = cast<ConstantInt>(II.getArgOperand(1))->getZExtValue();
+  if (maskIsAllOneOrUndef(II.getArgOperand(2)))
     return Builder.CreateAlignedLoad(II.getType(), LoadPtr, Alignment,
                                      "unmaskedload");
+
+  // If we can unconditionally load from this address, replace with a
+  // load/select idiom. TODO: use DT for context sensitive query
+  if (isDereferenceableAndAlignedPointer(LoadPtr, Alignment,
+                                         II.getModule()->getDataLayout(),
+                                         &II, nullptr)) {
+    Value *LI = Builder.CreateAlignedLoad(II.getType(), LoadPtr, Alignment,
+                                         "unmaskedload");
+    return Builder.CreateSelect(II.getArgOperand(2), LI, II.getArgOperand(3));
   }
 
   return nullptr;

diff --git a/test/Transforms/InstCombine/masked_intrinsics.ll b/test/Transforms/InstCombine/masked_intrinsics.ll
index d71402e119269c64fb151a28e5c9aeadf746d77c..b451724866e1f363c7aff1adbc6d8578bb88565e 100644 (file)
--- a/test/Transforms/InstCombine/masked_intrinsics.ll
+++ b/test/Transforms/InstCombine/masked_intrinsics.ll
@@ -87,8 +87,9 @@ define <2 x double> @load_speculative(<2 x double>* dereferenceable(16) %ptr,
 ; CHECK-LABEL: @load_speculative(
 ; CHECK-NEXT:    [[PTV1:%.*]] = insertelement <2 x double> undef, double [[PT:%.*]], i64 0
 ; CHECK-NEXT:    [[PTV2:%.*]] = shufflevector <2 x double> [[PTV1]], <2 x double> undef, <2 x i32> zeroinitializer
-; CHECK-NEXT:    [[RES:%.*]] = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* nonnull [[PTR:%.*]], i32 4, <2 x i1> [[MASK:%.*]], <2 x double> [[PTV2]])
-; CHECK-NEXT:    ret <2 x double> [[RES]]
+; CHECK-NEXT:    [[UNMASKEDLOAD:%.*]] = load <2 x double>, <2 x double>* [[PTR:%.*]], align 4
+; CHECK-NEXT:    [[TMP1:%.*]] = select <2 x i1> [[MASK:%.*]], <2 x double> [[UNMASKEDLOAD]], <2 x double> [[PTV2]]
+; CHECK-NEXT:    ret <2 x double> [[TMP1]]
 ;
   double %pt, <2 x i1> %mask)  {
   %ptv1 = insertelement <2 x double> undef, double %pt, i64 0