[MemCpyOpt] Fix wrong merging adjacent nontemporal stores into memset calls.

Pass MemCpyOpt doesn't check if a store instruction is nontemporal.
As a consequence, adjacent nontemporal stores are always merged into a
memset call.

Example:

;;;
define void @foo(<4 x float>* nocapture %p) {
entry:
  store <4 x float> zeroinitializer, <4 x float>* %p, align 16, !nontemporal !0
  %p1 = getelementptr inbounds <4 x float>, <4 x float>* %dst, i64 1
  store <4 x float> zeroinitializer, <4 x float>* %p1, align 16, !nontemporal !0
  ret void
}

!0 = !{i32 1}
;;;

In this example, the two nontemporal stores are combined to a memset of zero
which does not preserve the nontemporal hint. Later on the backend (tested on a
x86-64 corei7) expands that memset call into a sequence of two normal 16-byte
aligned vector stores.

opt -memcpyopt example.ll -S -o - | llc -mcpu=corei7 -o -

Before:
  xorps  %xmm0, %xmm0
  movaps  %xmm0, 16(%rdi)
  movaps  %xmm0, (%rdi)

With this patch, we no longer merge nontemporal stores into calls to memset.
In this example, llc correctly expands the two stores into two movntps:
  xorps  %xmm0, %xmm0
  movntps %xmm0, 16(%rdi)
  movntps  %xmm0, (%rdi)

In theory, we could extend the usage of !nontemporal metadata to memcpy/memset
calls. However a change like that would only have the effect of forcing the
backend to expand !nontemporal memsets back to sequences of store instructions.
A memset library call would not have exactly the same semantic of a builtin
!nontemporal memset call. So, SelectionDAG will have to conservatively expand
it back to a sequence of !nontemporal stores (effectively undoing the merging).

Differential Revision: http://reviews.llvm.org/D13519

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@249820 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Scalar/MemCpyOptimizer.cpp b/lib/Transforms/Scalar/MemCpyOptimizer.cpp
index 4039c6f35346bd4a19f831c95b54c9f8b5416381..64f8aafcda08a51a010f1b9689fcf6edba53c642 100644 (file)
--- a/lib/Transforms/Scalar/MemCpyOptimizer.cpp
+++ b/lib/Transforms/Scalar/MemCpyOptimizer.cpp
@@ -488,6 +488,16 @@ Instruction *MemCpyOpt::tryMergingIntoMemset(Instruction *StartInst,
 
 bool MemCpyOpt::processStore(StoreInst *SI, BasicBlock::iterator &BBI) {
   if (!SI->isSimple()) return false;
+
+  // Avoid merging nontemporal stores since the resulting
+  // memcpy/memset would not be able to preserve the nontemporal hint.
+  // In theory we could teach how to propagate the !nontemporal metadata to
+  // memset calls. However, that change would force the backend to
+  // conservatively expand !nontemporal memset calls back to sequences of
+  // store instructions (effectively undoing the merging).
+  if (SI->getMetadata(LLVMContext::MD_nontemporal))
+    return false;
+
   const DataLayout &DL = SI->getModule()->getDataLayout();
 
   // Detect cases where we're performing call slot forwarding, but

diff --git a/test/Transforms/MemCpyOpt/nontemporal.ll b/test/Transforms/MemCpyOpt/nontemporal.ll
new file mode 100644 (file)
index 0000000..d9dafcc
--- /dev/null
+++ b/test/Transforms/MemCpyOpt/nontemporal.ll
@@ -0,0 +1,49 @@
+; RUN: opt < %s -memcpyopt -S | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+
+; Verify that we don't combine nontemporal stores into memset calls.
+
+define void @nontemporal_stores_1(<4 x float>* nocapture %dst) {
+; CHECK-LABEL: @nontemporal_stores_1
+; CHECK: store <4 x float> zeroinitializer, <4 x float>* %dst, align 16, !nontemporal !0
+; CHECK: store <4 x float> zeroinitializer, <4 x float>* %ptr1, align 16, !nontemporal !0
+; CHECK: store <4 x float> zeroinitializer, <4 x float>* %ptr2, align 16, !nontemporal !0
+; CHECK: store <4 x float> zeroinitializer, <4 x float>* %ptr3, align 16, !nontemporal !0
+; CHECK: store <4 x float> zeroinitializer, <4 x float>* %ptr4, align 16, !nontemporal !0
+; CHECK: store <4 x float> zeroinitializer, <4 x float>* %ptr5, align 16, !nontemporal !0
+; CHECK: store <4 x float> zeroinitializer, <4 x float>* %ptr6, align 16, !nontemporal !0
+; CHECK: store <4 x float> zeroinitializer, <4 x float>* %ptr7, align 16, !nontemporal !0
+; CHECK-NEXT: ret void
+entry:
+  store <4 x float> zeroinitializer, <4 x float>* %dst, align 16, !nontemporal !0
+  %ptr1 = getelementptr inbounds <4 x float>, <4 x float>* %dst, i64 1
+  store <4 x float> zeroinitializer, <4 x float>* %ptr1, align 16, !nontemporal !0
+  %ptr2 = getelementptr inbounds <4 x float>, <4 x float>* %dst, i64 2
+  store <4 x float> zeroinitializer, <4 x float>* %ptr2, align 16, !nontemporal !0
+  %ptr3 = getelementptr inbounds <4 x float>, <4 x float>* %dst, i64 3
+  store <4 x float> zeroinitializer, <4 x float>* %ptr3, align 16, !nontemporal !0
+  %ptr4 = getelementptr inbounds <4 x float>, <4 x float>* %dst, i64 4
+  store <4 x float> zeroinitializer, <4 x float>* %ptr4, align 16, !nontemporal !0
+  %ptr5 = getelementptr inbounds <4 x float>, <4 x float>* %dst, i64 5
+  store <4 x float> zeroinitializer, <4 x float>* %ptr5, align 16, !nontemporal !0
+  %ptr6 = getelementptr inbounds <4 x float>, <4 x float>* %dst, i64 6
+  store <4 x float> zeroinitializer, <4 x float>* %ptr6, align 16, !nontemporal !0
+  %ptr7 = getelementptr inbounds <4 x float>, <4 x float>* %dst, i64 7
+  store <4 x float> zeroinitializer, <4 x float>* %ptr7, align 16, !nontemporal !0
+  ret void
+}
+
+define void @nontemporal_stores_2(<4 x float>* nocapture %dst) {
+; CHECK-LABEL: @nontemporal_stores_2
+; CHECK: store <4 x float> zeroinitializer, <4 x float>* %dst, align 16, !nontemporal !0
+; CHECK: store <4 x float> zeroinitializer, <4 x float>* %ptr1, align 16, !nontemporal !0
+; CHECK-NEXT: ret void
+entry:
+  store <4 x float> zeroinitializer, <4 x float>* %dst, align 16, !nontemporal !0
+  %ptr1 = getelementptr inbounds <4 x float>, <4 x float>* %dst, i64 1
+  store <4 x float> zeroinitializer, <4 x float>* %ptr1, align 16, !nontemporal !0
+  ret void
+}
+
+!0 = !{i32 1}