Use SCEV information for the second level aliasing

We introduce another level of alias metadata to distinguish the individual non-aliasing accesses that have inter iteration alias-free base pointers marked with "Inter iteration alias-free" mark nodes. To distinguish two accesses, the comparison of raw pointers representing base pointers is used. In case of, for example, ublas's prod function that implements GEMM, and DeLiCM we can get accesses to same location represented by different raw pointers. Consequently, we create different alias sets that can prevent accesses from, for example, being sinked or hoisted. To avoid the issue, we compare the corresponding SCEV information instead of the corresponding raw pointers. Reviewed-by: Tobias Grosser <tobias@grosser.es> Differential Revision: https://reviews.llvm.org/D35761 llvm-svn: 310380
llvm · Aug 8, 2017 · 1563f03 · 1563f03
1 parent 4aa1905
commit 1563f03
Show file tree

Hide file tree

Showing 5 changed files with 187 additions and 11 deletions.
diff --git a/polly/include/polly/CodeGen/IRBuilder.h b/polly/include/polly/CodeGen/IRBuilder.h
@@ -17,6 +17,7 @@
 
 #include "llvm/ADT/MapVector.h"
 #include "llvm/Analysis/LoopInfo.h"
+#include "llvm/Analysis/ScalarEvolution.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/ValueMap.h"
 
@@ -115,11 +116,10 @@ class ScopAnnotator {
       OtherAliasScopeListMap;
 
   /// A map from pointers to second level alias scopes.
-  llvm::DenseMap<llvm::AssertingVH<llvm::Value>, llvm::MDNode *>
-      SecondLevelAliasScopeMap;
+  llvm::DenseMap<const llvm::SCEV *, llvm::MDNode *> SecondLevelAliasScopeMap;
 
   /// A map from pointers to second level alias scope list of other pointers.
-  llvm::DenseMap<llvm::AssertingVH<llvm::Value>, llvm::MDNode *>
+  llvm::DenseMap<const llvm::SCEV *, llvm::MDNode *>
       SecondLevelOtherAliasScopeListMap;
 
   /// Inter iteration alias-free base pointers.

diff --git a/polly/lib/CodeGen/IRBuilder.cpp b/polly/lib/CodeGen/IRBuilder.cpp
@@ -140,29 +140,31 @@ static llvm::Value *getMemAccInstPointerOperand(Instruction *Inst) {
 
 void ScopAnnotator::annotateSecondLevel(llvm::Instruction *Inst,
                                         llvm::Value *BasePtr) {
-  auto *Ptr = getMemAccInstPointerOperand(Inst);
-  if (!Ptr)
+  auto *PtrSCEV = SE->getSCEV(getMemAccInstPointerOperand(Inst));
+  auto *BasePtrSCEV = SE->getPointerBase(PtrSCEV);
+
+  if (!PtrSCEV)
     return;
-  auto SecondLevelAliasScope = SecondLevelAliasScopeMap.lookup(Ptr);
+  auto SecondLevelAliasScope = SecondLevelAliasScopeMap.lookup(PtrSCEV);
   auto SecondLevelOtherAliasScopeList =
-      SecondLevelOtherAliasScopeListMap.lookup(Ptr);
+      SecondLevelOtherAliasScopeListMap.lookup(PtrSCEV);
   if (!SecondLevelAliasScope) {
     auto AliasScope = AliasScopeMap.lookup(BasePtr);
     if (!AliasScope)
       return;
     LLVMContext &Ctx = SE->getContext();
     SecondLevelAliasScope = getID(
         Ctx, AliasScope, MDString::get(Ctx, "second level alias metadata"));
-    SecondLevelAliasScopeMap[Ptr] = SecondLevelAliasScope;
+    SecondLevelAliasScopeMap[PtrSCEV] = SecondLevelAliasScope;
     Metadata *Args = {SecondLevelAliasScope};
     auto SecondLevelBasePtrAliasScopeList =
-        SecondLevelAliasScopeMap.lookup(BasePtr);
-    SecondLevelAliasScopeMap[BasePtr] = MDNode::concatenate(
+        SecondLevelAliasScopeMap.lookup(BasePtrSCEV);
+    SecondLevelAliasScopeMap[BasePtrSCEV] = MDNode::concatenate(
         SecondLevelBasePtrAliasScopeList, MDNode::get(Ctx, Args));
     auto OtherAliasScopeList = OtherAliasScopeListMap.lookup(BasePtr);
     SecondLevelOtherAliasScopeList = MDNode::concatenate(
         OtherAliasScopeList, SecondLevelBasePtrAliasScopeList);
-    SecondLevelOtherAliasScopeListMap[Ptr] = SecondLevelOtherAliasScopeList;
+    SecondLevelOtherAliasScopeListMap[PtrSCEV] = SecondLevelOtherAliasScopeList;
   }
   Inst->setMetadata("alias.scope", SecondLevelAliasScope);
   Inst->setMetadata("noalias", SecondLevelOtherAliasScopeList);

diff --git a/polly/test/ScheduleOptimizer/kernel_gemm___%for.body---%for.end24.jscop b/polly/test/ScheduleOptimizer/kernel_gemm___%for.body---%for.end24.jscop
@@ -0,0 +1,55 @@
+{
+   "arrays" : [
+      {
+         "name" : "MemRef_C1",
+         "sizes" : [ "*" ],
+         "type" : "double"
+      },
+      {
+         "name" : "MemRef_A",
+         "sizes" : [ "*", "1024" ],
+         "type" : "double"
+      },
+      {
+         "name" : "MemRef_B",
+         "sizes" : [ "*", "1024" ],
+         "type" : "double"
+      },
+      {
+         "name" : "MemRef_C",
+         "sizes" : [ "*", "1024" ],
+         "type" : "double"
+      }
+   ],
+   "context" : "{  :  }",
+   "name" : "%for.body---%for.end24",
+   "statements" : [
+      {
+         "accesses" : [
+            {
+               "kind" : "read",
+               "relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C1[0] }"
+            },
+            {
+               "kind" : "read",
+               "relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_A[i0, i2] }"
+            },
+            {
+               "kind" : "read",
+               "relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_B[i2, i1] }"
+            },
+            {
+               "kind" : "read",
+               "relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C[i0, i1] }"
+            },
+            {
+               "kind" : "write",
+               "relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C[i0, i1] }"
+            }
+         ],
+         "domain" : "{ Stmt_for_body6[i0, i1, i2] : 0 <= i0 <= 1023 and 0 <= i1 <= 1023 and 0 <= i2 <= 1023 }",
+         "name" : "Stmt_for_body6",
+         "schedule" : "{ Stmt_for_body6[i0, i1, i2] -> [i0, i1, i2] }"
+      }
+   ]
+}
diff --git a/polly/test/ScheduleOptimizer/kernel_gemm___%for.body---%for.end24.jscop.transformed b/polly/test/ScheduleOptimizer/kernel_gemm___%for.body---%for.end24.jscop.transformed
@@ -0,0 +1,55 @@
+{
+   "arrays" : [
+      {
+         "name" : "MemRef_C1",
+         "sizes" : [ "*" ],
+         "type" : "double"
+      },
+      {
+         "name" : "MemRef_A",
+         "sizes" : [ "*", "1024" ],
+         "type" : "double"
+      },
+      {
+         "name" : "MemRef_B",
+         "sizes" : [ "*", "1024" ],
+         "type" : "double"
+      },
+      {
+         "name" : "MemRef_C",
+         "sizes" : [ "*", "1024" ],
+         "type" : "double"
+      }
+   ],
+   "context" : "{  :  }",
+   "name" : "%for.body---%for.end24",
+   "statements" : [
+      {
+         "accesses" : [
+            {
+               "kind" : "read",
+               "relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C[i0, i1] }"
+            },
+            {
+               "kind" : "read",
+               "relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_A[i0, i2] }"
+            },
+            {
+               "kind" : "read",
+               "relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_B[i2, i1] }"
+            },
+            {
+               "kind" : "read",
+               "relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C1[0] }"
+            },
+            {
+               "kind" : "write",
+               "relation" : "{ Stmt_for_body6[i0, i1, i2] -> MemRef_C[i0, i1] }"
+            }
+         ],
+         "domain" : "{ Stmt_for_body6[i0, i1, i2] : 0 <= i0 <= 1023 and 0 <= i1 <= 1023 and 0 <= i2 <= 1023 }",
+         "name" : "Stmt_for_body6",
+         "schedule" : "{ Stmt_for_body6[i0, i1, i2] -> [i0, i1, i2] }"
+      }
+   ]
+}
diff --git a/polly/test/ScheduleOptimizer/pattern-matching-based-opts_14.ll b/polly/test/ScheduleOptimizer/pattern-matching-based-opts_14.ll
@@ -0,0 +1,64 @@
+; RUN: opt %loadPolly -polly-import-jscop -polly-opt-isl  \
+; RUN: -polly-target-throughput-vector-fma=1 \
+; RUN: -polly-target-latency-vector-fma=8 \
+; RUN: -polly-target-1st-cache-level-associativity=8 \
+; RUN: -polly-target-2nd-cache-level-associativity=8 \
+; RUN: -polly-target-1st-cache-level-size=32768 \
+; RUN: -polly-target-vector-register-bitwidth=256 \
+; RUN: -polly-target-2nd-cache-level-size=262144 \
+; RUN: -polly-import-jscop-postfix=transformed -polly-codegen -S < %s \
+; RUN: | FileCheck %s
+;
+; Check that we do not create different alias sets for locations represented by
+; different raw pointers.
+;
+; CHECK-NOT: !76 = distinct !{!76, !5, !"second level alias metadata"}
+;
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-unknown"
+
+define void @kernel_gemm(i32 %ni, i32 %nj, i32 %nk, [1024 x double]* %A, [1024 x double]* %B, [1024 x double]* %C, double* %C1) {
+entry:
+  br label %entry.split
+
+entry.split:                                      ; preds = %entry
+  br label %for.body
+
+for.body:                                         ; preds = %for.inc22, %entry.split
+  %indvars.iv43 = phi i64 [ 0, %entry.split ], [ %indvars.iv.next44, %for.inc22 ]
+  br label %for.body3
+
+for.body3:                                        ; preds = %for.inc19, %for.body
+  %indvars.iv40 = phi i64 [ 0, %for.body ], [ %indvars.iv.next41, %for.inc19 ]
+  br label %for.body6
+
+for.body6:                                        ; preds = %for.body6, %for.body3
+  %indvars.iv = phi i64 [ 0, %for.body3 ], [ %indvars.iv.next, %for.body6 ]
+  %tmp = load double, double* %C1, align 8
+  %arrayidx9 = getelementptr inbounds [1024 x double], [1024 x double]* %A, i64 %indvars.iv43, i64 %indvars.iv
+  %tmp1 = load double, double* %arrayidx9, align 8
+  %arrayidx13 = getelementptr inbounds [1024 x double], [1024 x double]* %B, i64 %indvars.iv, i64 %indvars.iv40
+  %tmp2 = load double, double* %arrayidx13, align 8
+  %mul = fmul double %tmp1, %tmp2
+  %add = fadd double %tmp, %mul
+  %arrayidx17 = getelementptr inbounds [1024 x double], [1024 x double]* %C, i64 %indvars.iv43, i64 %indvars.iv40
+  %tmp3 = load double, double* %arrayidx17, align 8
+  %add18 = fadd double %tmp3, %add
+  store double %add18, double* %arrayidx17, align 8
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp ne i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.body6, label %for.inc19
+
+for.inc19:                                        ; preds = %for.body6
+  %indvars.iv.next41 = add nuw nsw i64 %indvars.iv40, 1
+  %exitcond42 = icmp ne i64 %indvars.iv.next41, 1024
+  br i1 %exitcond42, label %for.body3, label %for.inc22
+
+for.inc22:                                        ; preds = %for.inc19
+  %indvars.iv.next44 = add nuw nsw i64 %indvars.iv43, 1
+  %exitcond45 = icmp ne i64 %indvars.iv.next44, 1024
+  br i1 %exitcond45, label %for.body, label %for.end24
+
+for.end24:                                        ; preds = %for.inc22
+  ret void
+}