[SCEV] Use full logic when infering flags on add and gep

This is a followon to D109845. With that landed, we will have fixed all known instances of pr51817, and can thus start inferring flags more aggressively with greatly reduced risk of miscompiles. This patch simply applies the same inference logic used in that patch to our other major flag inference path.

We can still do much better here (on both paths), but this is our first step.

Differential Revision: https://reviews.llvm.org/D111003

diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index 75cecbf..70bf9ae 100644 (file)
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -6657,14 +6657,8 @@ bool ScalarEvolution::isSCEVExprNeverPoison(const Instruction *I) {
     // TODO: We can do better here in some cases.
     if (!isSCEVable(Op->getType()))
       return false;
-    // TODO: the following two lines should be:
-    // if (auto *DefI = getDefinedScopeRoot(getSCEV(Op)))
-    //   if (isGuaranteedToTransferExecutionTo(DefI, I))
-    // We use the following instead for the purposes of seperating a bugfix
-    // change from an optimization change.  Once pr51817 is fully addressed,
-    // we should unlock this power.
-    if (auto *AddRecS = dyn_cast<SCEVAddRecExpr>(getSCEV(Op)))
-      if (isGuaranteedToExecuteForEveryIteration(I, AddRecS->getLoop()))
+    if (auto *DefI = getDefinedScopeRoot(getSCEV(Op)))
+      if (isGuaranteedToTransferExecutionTo(DefI, I))
         return true;
   }
   return false;

diff --git a/llvm/test/Analysis/Delinearization/multidim_ivs_and_integer_offsets_3d.ll b/llvm/test/Analysis/Delinearization/multidim_ivs_and_integer_offsets_3d.ll
index 712a529..77982c7 100644 (file)
--- a/llvm/test/Analysis/Delinearization/multidim_ivs_and_integer_offsets_3d.ll
+++ b/llvm/test/Analysis/Delinearization/multidim_ivs_and_integer_offsets_3d.ll
@@ -11,7 +11,7 @@
 ; AddRec: {{{(56 + (8 * (-4 + (3 * %m)) * %o) + %A),+,(8 * %m * %o)}<%for.i>,+,(8 * %o)}<%for.j>,+,8}<%for.k>
 ; CHECK: Base offset: %A
 ; CHECK: ArrayDecl[UnknownSize][%m][%o] with elements of 8 bytes.
-; CHECK: ArrayRef[{3,+,1}<nuw><%for.i>][{-4,+,1}<nw><%for.j>][{7,+,1}<nuw><nsw><%for.k>]
+; CHECK: ArrayRef[{3,+,1}<nuw><%for.i>][{-4,+,1}<nsw><%for.j>][{7,+,1}<nuw><nsw><%for.k>]
 
 define void @foo(i64 %n, i64 %m, i64 %o, double* %A) {
 entry:

diff --git a/llvm/test/Analysis/Delinearization/multidim_ivs_and_parameteric_offsets_3d.ll b/llvm/test/Analysis/Delinearization/multidim_ivs_and_parameteric_offsets_3d.ll
index e3fdb06..8ecd498 100644 (file)
--- a/llvm/test/Analysis/Delinearization/multidim_ivs_and_parameteric_offsets_3d.ll
+++ b/llvm/test/Analysis/Delinearization/multidim_ivs_and_parameteric_offsets_3d.ll
@@ -11,7 +11,7 @@
 ; AddRec: {{{((8 * ((((%m * %p) + %q) * %o) + %r)) + %A),+,(8 * %m * %o)}<%for.i>,+,(8 * %o)}<%for.j>,+,8}<%for.k>
 ; CHECK: Base offset: %A
 ; CHECK: ArrayDecl[UnknownSize][%m][%o] with elements of 8 bytes.
-; CHECK: ArrayRef[{%p,+,1}<nw><%for.i>][{%q,+,1}<nw><%for.j>][{%r,+,1}<nsw><%for.k>]
+; CHECK: ArrayRef[{%p,+,1}<nw><%for.i>][{%q,+,1}<nsw><%for.j>][{%r,+,1}<nsw><%for.k>]
 
 define void @foo(i64 %n, i64 %m, i64 %o, double* %A, i64 %p, i64 %q, i64 %r) {
 entry:

diff --git a/llvm/test/Analysis/LoopCacheAnalysis/PowerPC/stencil.ll b/llvm/test/Analysis/LoopCacheAnalysis/PowerPC/stencil.ll
index 8215131..1f15154 100644 (file)
--- a/llvm/test/Analysis/LoopCacheAnalysis/PowerPC/stencil.ll
+++ b/llvm/test/Analysis/LoopCacheAnalysis/PowerPC/stencil.ll
@@ -11,8 +11,8 @@ target triple = "powerpc64le-unknown-linux-gnu"
 ;     }   
 ; }
 
-; CHECK-DAG: Loop 'for.i' has cost = 20300
-; CHECK-DAG: Loop 'for.j' has cost = 700
+; CHECK-DAG: Loop 'for.i' has cost = 20600
+; CHECK-DAG: Loop 'for.j' has cost = 800
 
 define void @foo(i64 %n, i64 %m, i32* %A, i32* %B, i32* %C) {
 entry:

diff --git a/llvm/test/Analysis/ScalarEvolution/flags-from-poison.ll b/llvm/test/Analysis/ScalarEvolution/flags-from-poison.ll
index c8d3137..5ab2415 100644 (file)
--- a/llvm/test/Analysis/ScalarEvolution/flags-from-poison.ll
+++ b/llvm/test/Analysis/ScalarEvolution/flags-from-poison.ll
@@ -273,9 +273,9 @@ define void @test-add-scope-bound-unkn-header(i32* %input, i32 %needle) {
 ; CHECK-NEXT:    %offset = load i32, i32* %gep, align 4
 ; CHECK-NEXT:    --> %offset U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Variant }
 ; CHECK-NEXT:    %i.next = add nuw i32 %i, %offset
-; CHECK-NEXT:    --> (%offset + %i) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Variant }
+; CHECK-NEXT:    --> (%offset + %i)<nuw> U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Variant }
 ; CHECK-NEXT:    %gep2 = getelementptr i32, i32* %input, i32 %i.next
-; CHECK-NEXT:    --> ((4 * (sext i32 (%offset + %i) to i64))<nsw> + %input) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Variant }
+; CHECK-NEXT:    --> ((4 * (sext i32 (%offset + %i)<nuw> to i64))<nsw> + %input) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Variant }
 ; CHECK-NEXT:  Determining loop execution counts for: @test-add-scope-bound-unkn-header
 ; CHECK-NEXT:  Loop %loop: Unpredictable backedge-taken count.
 ; CHECK-NEXT:  Loop %loop: Unpredictable max backedge-taken count.
@@ -307,9 +307,9 @@ define void @test-add-scope-bound-unkn-header2(i32* %input, i32 %needle) {
 ; CHECK-NEXT:    %offset = load i32, i32* %gep, align 4
 ; CHECK-NEXT:    --> %offset U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Variant }
 ; CHECK-NEXT:    %i.next = add nuw i32 %i, %offset
-; CHECK-NEXT:    --> (%offset + %i) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Variant }
+; CHECK-NEXT:    --> (%offset + %i)<nuw> U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Variant }
 ; CHECK-NEXT:    %gep2 = getelementptr i32, i32* %input, i32 %i.next
-; CHECK-NEXT:    --> ((4 * (sext i32 (%offset + %i) to i64))<nsw> + %input) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Variant }
+; CHECK-NEXT:    --> ((4 * (sext i32 (%offset + %i)<nuw> to i64))<nsw> + %input) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %loop: Variant }
 ; CHECK-NEXT:  Determining loop execution counts for: @test-add-scope-bound-unkn-header2
 ; CHECK-NEXT:  Loop %loop: Unpredictable backedge-taken count.
 ; CHECK-NEXT:  Loop %loop: Unpredictable max backedge-taken count.

diff --git a/llvm/test/Analysis/ScalarEvolution/load.ll b/llvm/test/Analysis/ScalarEvolution/load.ll
index c0d6713..e95a093 100644 (file)
--- a/llvm/test/Analysis/ScalarEvolution/load.ll
+++ b/llvm/test/Analysis/ScalarEvolution/load.ll
@@ -73,7 +73,7 @@ define i32 @test2() nounwind uwtable readonly {
 ; CHECK-NEXT:    %n.01 = phi %struct.ListNode* [ bitcast ({ %struct.ListNode*, i32, [4 x i8] }* @node5 to %struct.ListNode*), %entry ], [ %1, %for.body ]
 ; CHECK-NEXT:    --> %n.01 U: full-set S: full-set Exits: @node1 LoopDispositions: { %for.body: Variant }
 ; CHECK-NEXT:    %i = getelementptr inbounds %struct.ListNode, %struct.ListNode* %n.01, i64 0, i32 1
-; CHECK-NEXT:    --> (4 + %n.01) U: full-set S: full-set Exits: (4 + @node1)<nuw><nsw> LoopDispositions: { %for.body: Variant }
+; CHECK-NEXT:    --> (4 + %n.01)<nuw> U: [4,0) S: [4,0) Exits: (4 + @node1)<nuw><nsw> LoopDispositions: { %for.body: Variant }
 ; CHECK-NEXT:    %0 = load i32, i32* %i, align 4
 ; CHECK-NEXT:    --> %0 U: full-set S: full-set Exits: 0 LoopDispositions: { %for.body: Variant }
 ; CHECK-NEXT:    %add = add nsw i32 %0, %sum.02

diff --git a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
index 93d8782..cb40ddd 100644 (file)
--- a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
+++ b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
@@ -502,7 +502,7 @@ define void @pr46786_c26_int(i32* %arg, i32* %arg1, i32* %arg2) {
 ; X32-NEXT:    %i11 = ashr exact i64 %i10, 2
 ; X32-NEXT:    --> %i11 U: [-2147483648,2147483648) S: [-2147483648,2147483648) Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
 ; X32-NEXT:    %i12 = getelementptr inbounds i32, i32* %arg2, i64 %i11
-; X32-NEXT:    --> ((4 * (trunc i64 %i11 to i32)) + %arg2) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
+; X32-NEXT:    --> ((4 * (trunc i64 %i11 to i32))<nsw> + %arg2) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
 ; X32-NEXT:    %i13 = load i32, i32* %i12, align 4
 ; X32-NEXT:    --> %i13 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
 ; X32-NEXT:    %i14 = add nsw i32 %i13, %i8

diff --git a/polly/test/IstAstInfo/simple-run-time-condition.ll b/polly/test/IstAstInfo/simple-run-time-condition.ll
index aba5d9e..0d16756 100644 (file)
--- a/polly/test/IstAstInfo/simple-run-time-condition.ll
+++ b/polly/test/IstAstInfo/simple-run-time-condition.ll
@@ -20,7 +20,7 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3
 ; for the delinearization is simplified such that conditions that would not
 ; cause any code to be executed are not generated.
 
-; CHECK: if (((o >= 1 && q <= 0 && m + q >= 0) || (o <= 0 && m + q >= 100 && q <= 100)) && 0 == ((m >= 1 && n + p >= 9223372036854775809) || (o <= 0 && n >= 1 && m + q >= 9223372036854775909) || (o <= 0 && m >= 1 && n >= 1 && q <= -9223372036854775709)))
+; CHECK: if (((o >= 1 && q <= 0 && m + q >= 0) || (o <= 0 && m + q >= 100 && q <= 100)) && 0 == ((o <= 0 && n >= 1 && m + q >= 9223372036854775909) || (o <= 0 && m >= 1 && n >= 1 && q <= -9223372036854775709)))
 
 ; CHECK:     if (o <= 0) {
 ; CHECK:       for (int c0 = 0; c0 < n; c0 += 1)