From: Sanjay Patel <spatel@rotateright.com>
Date: Mon, 1 Feb 2016 22:10:26 +0000 (+0000)
Subject: [InstCombine] simplify masked scatter/gather intrinsics with zero masks
X-Git-Tag: android-x86-7.1-r4~38291
X-Git-Url: http://git.osdn.net/view?a=commitdiff_plain;h=633f0ac7ddd9444678f93783b31d5c4b8f5a8465;p=android-x86%2Fexternal-llvm.git

[InstCombine] simplify masked scatter/gather intrinsics with zero masks

A masked scatter with a zero mask means there's no store.
A masked gather with a zero mask means the passthru arg is returned.

This is a continuation of:
http://reviews.llvm.org/rL259369
http://reviews.llvm.org/rL259392



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@259421 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Transforms/InstCombine/InstCombineCalls.cpp b/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 753c8fac96a..463a6c28666 100644
--- a/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -792,6 +792,24 @@ static Instruction *simplifyMaskedStore(IntrinsicInst &II, InstCombiner &IC) {
   return nullptr;
 }
 
+static Instruction *simplifyMaskedGather(IntrinsicInst &II, InstCombiner &IC) {
+  // If the mask is all zeros, return the "passthru" argument of the gather.
+  auto *ConstMask = dyn_cast<Constant>(II.getArgOperand(2));
+  if (ConstMask && ConstMask->isNullValue())
+    return IC.ReplaceInstUsesWith(II, II.getArgOperand(3));
+
+  return nullptr;
+}
+
+static Instruction *simplifyMaskedScatter(IntrinsicInst &II, InstCombiner &IC) {
+  // If the mask is all zeros, a scatter does nothing.
+  auto *ConstMask = dyn_cast<Constant>(II.getArgOperand(3));
+  if (ConstMask && ConstMask->isNullValue())
+    return IC.EraseInstFromFunction(II);
+
+  return nullptr;
+}
+
 /// CallInst simplification. This mostly only handles folding of intrinsic
 /// instructions. For normal calls, it allows visitCallSite to do the heavy
 /// lifting.
@@ -922,10 +940,10 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
     break;
   case Intrinsic::masked_store:
     return simplifyMaskedStore(*II, *this);
-
-  // TODO: Handle the other masked ops.
-  // case Intrinsic::masked_gather:
-  // case Intrinsic::masked_scatter:
+  case Intrinsic::masked_gather:
+    return simplifyMaskedGather(*II, *this);
+  case Intrinsic::masked_scatter:
+    return simplifyMaskedScatter(*II, *this);
 
   case Intrinsic::powi:
     if (ConstantInt *Power = dyn_cast<ConstantInt>(II->getArgOperand(1))) {
diff --git a/test/Transforms/InstCombine/masked_intrinsics.ll b/test/Transforms/InstCombine/masked_intrinsics.ll
index b40c62784aa..eb30b4a3ffc 100644
--- a/test/Transforms/InstCombine/masked_intrinsics.ll
+++ b/test/Transforms/InstCombine/masked_intrinsics.ll
@@ -2,7 +2,8 @@
 
 declare <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptrs, i32, <2 x i1> %mask, <2 x double> %src0)
 declare void @llvm.masked.store.v2f64(<2 x double> %val, <2 x double>* %ptrs, i32, <2 x i1> %mask)
-
+declare <2 x double> @llvm.masked.gather.v2f64(<2 x double*> %ptrs, i32, <2 x i1> %mask, <2 x double> %passthru)
+declare void @llvm.masked.scatter.v2f64(<2 x double> %val, <2 x double*> %ptrs, i32, <2 x i1> %mask)
 
 define <2 x double> @load_zeromask(<2 x double>* %ptr, <2 x double> %passthru)  {
   %res = call <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptr, i32 1, <2 x i1> zeroinitializer, <2 x double> %passthru)
@@ -26,7 +27,7 @@ define void @store_zeromask(<2 x double>* %ptr, <2 x double> %val)  {
   ret void
 
 ; CHECK-LABEL: @store_zeromask(
-; CHECK-NEXT:   ret void
+; CHECK-NEXT:  ret void
 }
 
 define void @store_onemask(<2 x double>* %ptr, <2 x double> %val)  {
@@ -35,6 +36,22 @@ define void @store_onemask(<2 x double>* %ptr, <2 x double> %val)  {
 
 ; CHECK-LABEL: @store_onemask(
 ; CHECK-NEXT:  store <2 x double> %val, <2 x double>* %ptr, align 4
-; CHECK-NEXT:   ret void
+; CHECK-NEXT:  ret void
+}
+
+define <2 x double> @gather_zeromask(<2 x double*> %ptrs, <2 x double> %passthru)  {
+  %res = call <2 x double> @llvm.masked.gather.v2f64(<2 x double*> %ptrs, i32 5, <2 x i1> zeroinitializer, <2 x double> %passthru)
+  ret <2 x double> %res
+
+; CHECK-LABEL: @gather_zeromask(
+; CHECK-NEXT:  ret <2 x double> %passthru
+}
+
+define void @scatter_zeromask(<2 x double*> %ptrs, <2 x double> %val)  {
+  call void @llvm.masked.scatter.v2f64(<2 x double> %val, <2 x double*> %ptrs, i32 6, <2 x i1> zeroinitializer)
+  ret void
+
+; CHECK-LABEL: @scatter_zeromask(
+; CHECK-NEXT:  ret void
 }