Revert r319482 and r319483 "[memcpyopt] Teach memcpyopt to optimize across basic...

This caused PR35519.

> [memcpyopt] Teach memcpyopt to optimize across basic blocks
>
> This teaches memcpyopt to make a non-local memdep query when a local query
> indicates that the dependency is non-local. This notably allows it to
> eliminate many more llvm.memcpy calls in common Rust code, often by 20-30%.
>
> Fixes PR28958.
>
> Differential Revision: https://reviews.llvm.org/D38374
>

> [memcpyopt] Commit file missed in r319482.
>
> This change was meant to be included with r319482 but was accidentally
> omitted.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@319873 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/Analysis/MemoryDependenceAnalysis.h b/include/llvm/Analysis/MemoryDependenceAnalysis.h
index 391a333594e986b6ec85de480d5c60033a0d57e6..c2974525a6ff8932ed39ba9a8ff52f2e98fbac27 100644 (file)
--- a/include/llvm/Analysis/MemoryDependenceAnalysis.h
+++ b/include/llvm/Analysis/MemoryDependenceAnalysis.h
@@ -407,12 +407,6 @@ public:
   void getNonLocalPointerDependency(Instruction *QueryInst,
                                     SmallVectorImpl<NonLocalDepResult> &Result);
 
-  /// Perform a dependency query specifically for QueryInst's access to Loc.
-  /// The other comments for getNonLocalPointerDependency apply here as well.
-  void getNonLocalPointerDependencyFrom(Instruction *QueryInst,
-                                        const MemoryLocation &Loc, bool isLoad,
-                                        SmallVectorImpl<NonLocalDepResult> &Result);
-
   /// Removes an instruction from the dependence analysis, updating the
   /// dependence of instructions that previously depended on it.
   void removeInstruction(Instruction *InstToRemove);

diff --git a/lib/Analysis/MemoryDependenceAnalysis.cpp b/lib/Analysis/MemoryDependenceAnalysis.cpp
index c54f676eb94ae304c18204e3c01aa131774dcd4d..57d04af04709c481e3f6af079dafe70095539f8d 100644 (file)
--- a/lib/Analysis/MemoryDependenceAnalysis.cpp
+++ b/lib/Analysis/MemoryDependenceAnalysis.cpp
@@ -917,14 +917,6 @@ void MemoryDependenceResults::getNonLocalPointerDependency(
     Instruction *QueryInst, SmallVectorImpl<NonLocalDepResult> &Result) {
   const MemoryLocation Loc = MemoryLocation::get(QueryInst);
   bool isLoad = isa<LoadInst>(QueryInst);
-  return getNonLocalPointerDependencyFrom(QueryInst, Loc, isLoad, Result);
-}
-
-void MemoryDependenceResults::getNonLocalPointerDependencyFrom(
-    Instruction *QueryInst,
-    const MemoryLocation &Loc,
-    bool isLoad,
-    SmallVectorImpl<NonLocalDepResult> &Result) {
   BasicBlock *FromBB = QueryInst->getParent();
   assert(FromBB);
 

diff --git a/lib/Transforms/Scalar/MemCpyOptimizer.cpp b/lib/Transforms/Scalar/MemCpyOptimizer.cpp
index cd3e4ba88bca0e76ce2d287fe4112f4010af464e..9c870b42a747721ce6f3989e5f93a0fab413c577 100644 (file)
--- a/lib/Transforms/Scalar/MemCpyOptimizer.cpp
+++ b/lib/Transforms/Scalar/MemCpyOptimizer.cpp
@@ -1031,22 +1031,9 @@ bool MemCpyOptPass::processMemCpyMemCpyDependence(MemCpyInst *M,
   //
   // NOTE: This is conservative, it will stop on any read from the source loc,
   // not just the defining memcpy.
-  MemoryLocation SourceLoc = MemoryLocation::getForSource(MDep);
-  MemDepResult SourceDep = MD->getPointerDependencyFrom(SourceLoc, false,
-                                                        M->getIterator(), M->getParent());
-
-  if (SourceDep.isNonLocal()) {
-    SmallVector<NonLocalDepResult, 2> NonLocalDepResults;
-    MD->getNonLocalPointerDependencyFrom(M, SourceLoc, /*isLoad=*/false,
-                                         NonLocalDepResults);
-    if (NonLocalDepResults.size() == 1) {
-      SourceDep = NonLocalDepResults[0].getResult();
-      assert((!SourceDep.getInst() ||
-              LookupDomTree().dominates(SourceDep.getInst(), M)) &&
-             "when memdep returns exactly one result, it should dominate");
-    }
-  }
-
+  MemDepResult SourceDep =
+      MD->getPointerDependencyFrom(MemoryLocation::getForSource(MDep), false,
+                                   M->getIterator(), M->getParent());
   if (!SourceDep.isClobber() || SourceDep.getInst() != MDep)
     return false;
 
@@ -1248,18 +1235,6 @@ bool MemCpyOptPass::processMemCpy(MemCpyInst *M) {
   MemDepResult SrcDepInfo = MD->getPointerDependencyFrom(
       SrcLoc, true, M->getIterator(), M->getParent());
 
-  if (SrcDepInfo.isNonLocal()) {
-    SmallVector<NonLocalDepResult, 2> NonLocalDepResults;
-    MD->getNonLocalPointerDependencyFrom(M, SrcLoc, /*isLoad=*/true,
-                                         NonLocalDepResults);
-    if (NonLocalDepResults.size() == 1) {
-      SrcDepInfo = NonLocalDepResults[0].getResult();
-      assert((!SrcDepInfo.getInst() ||
-              LookupDomTree().dominates(SrcDepInfo.getInst(), M)) &&
-             "when memdep returns exactly one result, it should dominate");
-    }
-  }
-
   if (SrcDepInfo.isClobber()) {
     if (MemCpyInst *MDep = dyn_cast<MemCpyInst>(SrcDepInfo.getInst()))
       return processMemCpyMemCpyDependence(M, MDep);

diff --git a/test/Transforms/MemCpyOpt/memcpy-invoke-memcpy.ll b/test/Transforms/MemCpyOpt/memcpy-invoke-memcpy.ll
deleted file mode 100644 (file)
index e3d1f6d..0000000
--- a/test/Transforms/MemCpyOpt/memcpy-invoke-memcpy.ll
+++ /dev/null
@@ -1,48 +0,0 @@
-; RUN: opt < %s -memcpyopt -S | FileCheck %s
-; Test memcpy-memcpy dependencies across invoke edges.
-
-; Test that memcpyopt works across the non-unwind edge of an invoke.
-
-define hidden void @test_normal(i8* noalias %dst, i8* %src) personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
-entry:
-  %temp = alloca i8, i32 64
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %temp, i8* nonnull %src, i64 64, i32 8, i1 false)
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %temp, i8* nonnull %src, i64 64, i32 8, i1 false)
-  invoke void @invoke_me()
-          to label %try.cont unwind label %lpad
-
-lpad:
-  landingpad { i8*, i32 }
-          catch i8* null
-  ret void
-
-try.cont:
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %temp, i64 64, i32 8, i1 false)
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 64, i32 8, i1 false)
-  ret void
-}
-
-; Test that memcpyopt works across the unwind edge of an invoke.
-
-define hidden void @test_unwind(i8* noalias %dst, i8* %src) personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
-entry:
-  %temp = alloca i8, i32 64
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %temp, i8* nonnull %src, i64 64, i32 8, i1 false)
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %temp, i8* nonnull %src, i64 64, i32 8, i1 false)
-  invoke void @invoke_me()
-          to label %try.cont unwind label %lpad
-
-lpad:
-  landingpad { i8*, i32 }
-          catch i8* null
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %temp, i64 64, i32 8, i1 false)
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 64, i32 8, i1 false)
-  ret void
-
-try.cont:
-  ret void
-}
-
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1)
-declare i32 @__gxx_personality_v0(...)
-declare void @invoke_me() readnone

diff --git a/test/Transforms/MemCpyOpt/nonlocal-memcpy-memcpy.ll b/test/Transforms/MemCpyOpt/nonlocal-memcpy-memcpy.ll
deleted file mode 100644 (file)
index 5b05102..0000000
--- a/test/Transforms/MemCpyOpt/nonlocal-memcpy-memcpy.ll
+++ /dev/null
@@ -1,114 +0,0 @@
-; RUN: opt < %s -memcpyopt -S | FileCheck %s
-; Make sure memcpy-memcpy dependence is optimized across
-; basic blocks (conditional branches and invokes).
-
-%struct.s = type { i32, i32 }
-
-@s_foo = private unnamed_addr constant %struct.s { i32 1, i32 2 }, align 4
-@s_baz = private unnamed_addr constant %struct.s { i32 1, i32 2 }, align 4
-@i = external constant i8*
-
-declare void @qux()
-declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1)
-declare void @__cxa_throw(i8*, i8*, i8*)
-declare i32 @__gxx_personality_v0(...)
-declare i8* @__cxa_begin_catch(i8*)
-
-; A simple partial redundancy. Test that the second memcpy is optimized
-; to copy directly from the original source rather than from the temporary.
-
-; CHECK-LABEL: @wobble
-define void @wobble(i8* noalias %dst, i8* %src, i1 %some_condition) {
-bb:
-  %temp = alloca i8, i32 64
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %temp, i8* nonnull %src, i64 64, i32 8, i1 false)
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %temp, i8* nonnull %src, i64 64, i32 8, i1 false)
-  br i1 %some_condition, label %more, label %out
-
-out:
-  call void @qux()
-  unreachable
-
-more:
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %temp, i64 64, i32 8, i1 false)
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 64, i32 8, i1 false)
-  ret void
-}
-
-; A CFG triangle with a partial redundancy targeting an alloca. Test that the
-; memcpy inside the triangle is optimized to copy directly from the original
-; source rather than from the temporary.
-
-; CHECK-LABEL: @foo
-define i32 @foo(i1 %t3) {
-bb:
-  %s = alloca %struct.s, align 4
-  %t = alloca %struct.s, align 4
-  %s1 = bitcast %struct.s* %s to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %s1, i8* bitcast (%struct.s* @s_foo to i8*), i64 8, i32 4, i1 false)
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %s1, i8* bitcast (%struct.s* @s_foo to i8*), i64 8, i32 4, i1 false)
-  br i1 %t3, label %bb4, label %bb7
-
-bb4:                                              ; preds = %bb
-  %t5 = bitcast %struct.s* %t to i8*
-  %s6 = bitcast %struct.s* %s to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %t5, i8* %s6, i64 8, i32 4, i1 false)
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %t5, i8* bitcast (%struct.s* @s_foo to i8*), i64 8, i32 4, i1 false)
-  br label %bb7
-
-bb7:                                              ; preds = %bb4, %bb
-  %t8 = getelementptr %struct.s, %struct.s* %t, i32 0, i32 0
-  %t9 = load i32, i32* %t8, align 4
-  %t10 = getelementptr %struct.s, %struct.s* %t, i32 0, i32 1
-  %t11 = load i32, i32* %t10, align 4
-  %t12 = add i32 %t9, %t11
-  ret i32 %t12
-}
-
-; A CFG diamond with an invoke on one side, and a partially redundant memcpy
-; into an alloca on the other. Test that the memcpy inside the diamond is
-; optimized to copy ; directly from the original source rather than from the
-; temporary. This more complex test represents a relatively common usage
-; pattern.
-
-; CHECK-LABEL: @baz
-define i32 @baz(i1 %t5) personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
-bb:
-  %s = alloca %struct.s, align 4
-  %t = alloca %struct.s, align 4
-  %s3 = bitcast %struct.s* %s to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %s3, i8* bitcast (%struct.s* @s_baz to i8*), i64 8, i32 4, i1 false)
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %s3, i8* bitcast (%struct.s* @s_baz to i8*), i64 8, i32 4, i1 false)
-  br i1 %t5, label %bb6, label %bb22
-
-bb6:                                              ; preds = %bb
-  invoke void @__cxa_throw(i8* null, i8* bitcast (i8** @i to i8*), i8* null)
-          to label %bb25 unwind label %bb9
-
-bb9:                                              ; preds = %bb6
-  %t10 = landingpad { i8*, i32 }
-          catch i8* null
-  br label %bb13
-
-bb13:                                             ; preds = %bb9
-  %t15 = call i8* @__cxa_begin_catch(i8* null)
-  br label %bb23
-
-bb22:                                             ; preds = %bb
-  %t23 = bitcast %struct.s* %t to i8*
-  %s24 = bitcast %struct.s* %s to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %t23, i8* %s24, i64 8, i32 4, i1 false)
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %t23, i8* bitcast (%struct.s* @s_baz to i8*), i64 8, i32 4, i1 false)
-  br label %bb23
-
-bb23:                                             ; preds = %bb22, %bb13
-  %t17 = getelementptr inbounds %struct.s, %struct.s* %t, i32 0, i32 0
-  %t18 = load i32, i32* %t17, align 4
-  %t19 = getelementptr inbounds %struct.s, %struct.s* %t, i32 0, i32 1
-  %t20 = load i32, i32* %t19, align 4
-  %t21 = add nsw i32 %t18, %t20
-  ret i32 %t21
-
-bb25:                                             ; preds = %bb6
-  unreachable
-}