[PATCH] D138585: [SLPVectorizer] Do Not Move Loads/Stores Beyond Stacksave/Stackrestore Boundaries

[Qiongsi Wu via Phabricator via llvm-commits]

qiongsiwu1 created this revision.
qiongsiwu1 added reviewers: RolandF, scui, reames.
qiongsiwu1 added a project: LLVM.
Herald added subscribers: vporpo, pengfei, hiraditya.
Herald added a project: All.
qiongsiwu1 requested review of this revision.
Herald added subscribers: llvm-commits, pcwang-thead.

If left unchecked, the SLPVecrtorizer can move loads/stores below a stackrestore. The move can cause issues if the loads/stores have pointer operands from `alloca`s that are reset by the stackrestores. This patch adds the dependency check.

The check is conservative, in that it does not check if the pointer operands of the loads/stores are actually from an `alloca` that may be reset. We did not observe any SPECCPU2017 performance depredations so this simple fix seems sufficient.

The test could have been added to `llvm/test/Transforms/SLPVectorizer/X86/stacksave-dependence.ll`, but that test has not been updated to use opaque pointers. I am not inclined to add tests that still use typed pointers, or to refactor `llvm/test/Transforms/SLPVectorizer/X86/stacksave-dependence.ll` to use opaque pointers in this patch. If desired, I will open a different patch to refactor and consolidate the tests.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D138585

Files:
  llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
  llvm/test/Transforms/SLPVectorizer/X86/stackrestore-dependence.ll


Index: llvm/test/Transforms/SLPVectorizer/X86/stackrestore-dependence.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/SLPVectorizer/X86/stackrestore-dependence.ll
@@ -0,0 +1,41 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -passes=slp-vectorizer -slp-threshold=-999 -mtriple=x86_64-unknown-linux-gnu -mcpu=skylake -S < %s | FileCheck %s
+
+; The test checks that loads should not be moved below a stackrestore boundary.
+define void @stackrestore1(ptr %out) {
+; CHECK-LABEL: @stackrestore1(
+; CHECK-NEXT:    [[STACK:%.*]] = call ptr @llvm.stacksave()
+; CHECK-NEXT:    [[LOCAL_ALLOCA:%.*]] = alloca [16 x i8], align 4
+; CHECK-NEXT:    store <4 x float> <float 0x3FF3333340000000, float 0x3FF3333340000000, float 0x3FF3333340000000, float 0x3FF3333340000000>, ptr [[LOCAL_ALLOCA]], align 4
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, ptr [[LOCAL_ALLOCA]], align 4
+; CHECK-NEXT:    call void @llvm.stackrestore(ptr [[STACK]])
+; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <4 x float> [[TMP1]], <4 x float> poison, <4 x i32> <i32 2, i32 3, i32 0, i32 1>
+; CHECK-NEXT:    store <4 x float> [[SHUFFLE]], ptr [[OUT:%.*]], align 4
+; CHECK-NEXT:    ret void
+;
+  %stack = call ptr @llvm.stacksave()
+  %local_alloca = alloca [16 x i8], align 4
+  store float 0x3FF3333340000000, ptr %local_alloca, align 4
+  %addr1 = getelementptr inbounds i8, ptr %local_alloca, i64 4
+  store float 0x3FF3333340000000, ptr %addr1, align 4
+  %addr2 = getelementptr inbounds i8, ptr %local_alloca, i64 8
+  store float 0x3FF3333340000000, ptr %addr2, align 4
+  %addr3 = getelementptr inbounds i8, ptr %local_alloca, i64 12
+  store float 0x3FF3333340000000, ptr %addr3, align 4
+  %val0 = load float, ptr %local_alloca, align 4
+  %val1 = load float, ptr %addr1, align 4
+  %val2 = load float, ptr %addr2, align 4
+  %val3 = load float, ptr %addr3, align 4
+  call void @llvm.stackrestore(i8* %stack)
+  %outaddr2 = getelementptr inbounds float, ptr %out, i64 2
+  store float %val0, ptr %outaddr2, align 4
+  %outaddr3 = getelementptr inbounds float, ptr %out, i64 3
+  store float %val1, ptr %outaddr3, align 4
+  store float %val2, ptr %out
+  %outaddr1 = getelementptr inbounds float, ptr %out, i64 1
+  store float %val3, ptr %outaddr1, align 4
+  ret void
+}
+
+declare i8* @llvm.stacksave()
+declare void @llvm.stackrestore(i8*)
Index: llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -10042,9 +10042,10 @@
         }
 
         // In addition to the cases handle just above, we need to prevent
-        // allocas from moving below a stacksave.  The stackrestore case
-        // is currently thought to be conservatism.
-        if (isa<AllocaInst>(BundleMember->Inst)) {
+        // allocas and loads/stores from moving below a stacksave.  The
+        // stackrestore case is currently thought to be conservatism.
+        if (isa<AllocaInst>(BundleMember->Inst) ||
+            BundleMember->Inst->mayReadOrWriteMemory()) {
           for (Instruction *I = BundleMember->Inst->getNextNode();
                I != ScheduleEnd; I = I->getNextNode()) {
             if (!match(I, m_Intrinsic<Intrinsic::stacksave>()) &&


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D138585.477524.patch
Type: text/x-patch
Size: 3405 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20221123/242bffb4/attachment.bin>