Reland "[ScalarEvolution] createSCEV(): recognize `udiv`/`urem` disguised as an ...

This reverts commit d3e3f36ff1151f565730977ac4f663a2ccee48ae,
which reverter the original commit 2c16100e6f72075564ea1f67fa5a82c269dafcd3,
but with polly tests now actually passing.

diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index 609ad63..75926aa 100644 (file)
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -6303,6 +6303,20 @@ const SCEV *ScalarEvolution::createSCEV(Value *V) {
       return getSCEV(U->getOperand(0));
     break;
 
+  case Instruction::SDiv:
+    // If both operands are non-negative, this is just an udiv.
+    if (isKnownNonNegative(getSCEV(U->getOperand(0))) &&
+        isKnownNonNegative(getSCEV(U->getOperand(1))))
+      return getUDivExpr(getSCEV(U->getOperand(0)), getSCEV(U->getOperand(1)));
+    break;
+
+  case Instruction::SRem:
+    // If both operands are non-negative, this is just an urem.
+    if (isKnownNonNegative(getSCEV(U->getOperand(0))) &&
+        isKnownNonNegative(getSCEV(U->getOperand(1))))
+      return getURemExpr(getSCEV(U->getOperand(0)), getSCEV(U->getOperand(1)));
+    break;
+
   // It's tempting to handle inttoptr and ptrtoint as no-ops, however this can
   // lead to pointer expressions which cannot safely be expanded to GEPs,
   // because ScalarEvolution doesn't respect the GEP aliasing rules when

diff --git a/llvm/test/Analysis/ScalarEvolution/sdiv.ll b/llvm/test/Analysis/ScalarEvolution/sdiv.ll
index b489585..106cda1 100644 (file)
--- a/llvm/test/Analysis/ScalarEvolution/sdiv.ll
+++ b/llvm/test/Analysis/ScalarEvolution/sdiv.ll
@@ -14,11 +14,11 @@ define dso_local void @_Z4loopi(i32 %width) local_unnamed_addr #0 {
 ; CHECK-NEXT:    %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
 ; CHECK-NEXT:    --> {0,+,1}<nuw><nsw><%for.cond> U: [0,-2147483648) S: [0,-2147483648) Exits: %width LoopDispositions: { %for.cond: Computable }
 ; CHECK-NEXT:    %rem = sdiv i32 %i.0, 2
-; CHECK-NEXT:    --> %rem U: full-set S: [-1073741824,1073741824) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
+; CHECK-NEXT:    --> ({0,+,1}<nuw><nsw><%for.cond> /u 2) U: [0,1073741824) S: [0,1073741824) Exits: (%width /u 2) LoopDispositions: { %for.cond: Computable }
 ; CHECK-NEXT:    %idxprom = sext i32 %rem to i64
-; CHECK-NEXT:    --> (sext i32 %rem to i64) U: [-2147483648,2147483648) S: [-1073741824,1073741824) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
+; CHECK-NEXT:    --> ({0,+,1}<nuw><nsw><%for.cond> /u 2) U: [0,2147483648) S: [0,2147483648) Exits: ((zext i32 %width to i64) /u 2) LoopDispositions: { %for.cond: Computable }
 ; CHECK-NEXT:    %arrayidx = getelementptr inbounds [2 x i32], [2 x i32]* %storage, i64 0, i64 %idxprom
-; CHECK-NEXT:    --> ((4 * (sext i32 %rem to i64))<nsw> + %storage)<nsw> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
+; CHECK-NEXT:    --> ((4 * ({0,+,1}<nuw><nsw><%for.cond> /u 2))<nuw><nsw> + %storage)<nsw> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: ((4 * ((zext i32 %width to i64) /u 2))<nuw><nsw> + %storage)<nsw> LoopDispositions: { %for.cond: Computable }
 ; CHECK-NEXT:    %1 = load i32, i32* %arrayidx, align 4
 ; CHECK-NEXT:    --> %1 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
 ; CHECK-NEXT:    %call = call i32 @_Z3adji(i32 %1)

diff --git a/llvm/test/Analysis/ScalarEvolution/srem.ll b/llvm/test/Analysis/ScalarEvolution/srem.ll
index 365b40d..6debab3 100644 (file)
--- a/llvm/test/Analysis/ScalarEvolution/srem.ll
+++ b/llvm/test/Analysis/ScalarEvolution/srem.ll
@@ -14,11 +14,11 @@ define dso_local void @_Z4loopi(i32 %width) local_unnamed_addr #0 {
 ; CHECK-NEXT:    %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
 ; CHECK-NEXT:    --> {0,+,1}<nuw><nsw><%for.cond> U: [0,-2147483648) S: [0,-2147483648) Exits: %width LoopDispositions: { %for.cond: Computable }
 ; CHECK-NEXT:    %rem = srem i32 %i.0, 2
-; CHECK-NEXT:    --> %rem U: [0,2) S: [-2,2) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
+; CHECK-NEXT:    --> (zext i1 {false,+,true}<%for.cond> to i32) U: [0,2) S: [0,2) Exits: (zext i1 (trunc i32 %width to i1) to i32) LoopDispositions: { %for.cond: Computable }
 ; CHECK-NEXT:    %idxprom = sext i32 %rem to i64
-; CHECK-NEXT:    --> (sext i32 %rem to i64) U: [0,2) S: [-2,2) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
+; CHECK-NEXT:    --> (zext i1 {false,+,true}<%for.cond> to i64) U: [0,2) S: [0,2) Exits: (zext i1 (trunc i32 %width to i1) to i64) LoopDispositions: { %for.cond: Computable }
 ; CHECK-NEXT:    %arrayidx = getelementptr inbounds [2 x i32], [2 x i32]* %storage, i64 0, i64 %idxprom
-; CHECK-NEXT:    --> ((4 * (sext i32 %rem to i64))<nuw><nsw> + %storage)<nsw> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
+; CHECK-NEXT:    --> ((4 * (zext i1 {false,+,true}<%for.cond> to i64))<nuw><nsw> + %storage)<nsw> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: ((4 * (zext i1 (trunc i32 %width to i1) to i64))<nuw><nsw> + %storage)<nsw> LoopDispositions: { %for.cond: Computable }
 ; CHECK-NEXT:    %1 = load i32, i32* %arrayidx, align 4
 ; CHECK-NEXT:    --> %1 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
 ; CHECK-NEXT:    %call = call i32 @_Z3adji(i32 %1)

diff --git a/polly/test/Isl/CodeGen/MemAccess/generate-all.ll b/polly/test/Isl/CodeGen/MemAccess/generate-all.ll
index a3253ef..f9b07a9 100644 (file)
--- a/polly/test/Isl/CodeGen/MemAccess/generate-all.ll
+++ b/polly/test/Isl/CodeGen/MemAccess/generate-all.ll
@@ -9,11 +9,12 @@
 ;    }
 
 ; SCEV:      polly.stmt.bb2:                                   ; preds = %polly.loop_header
-; SCEV-NEXT:   %p_tmp = srem i64 %polly.indvar, 4
-; SCEV-NEXT:   %p_tmp3 = getelementptr inbounds float, float* %A, i64 %p_tmp
-; SCEV-NEXT:   %tmp4_p_scalar_ = load float, float* %p_tmp3, align 4, !alias.scope !0, !noalias !2
+; SCEV-NEXT:   %0 = trunc i64 %polly.indvar to i2
+; SCEV-NEXT:   %1 = zext i2 %0 to i64
+; SCEV-NEXT:   %scevgep = getelementptr float, float* %A, i64 %1
+; SCEV-NEXT:   %tmp4_p_scalar_ = load float, float* %scevgep, align 4, !alias.scope !0, !noalias !2
 ; SCEV-NEXT:   %p_tmp5 = fadd float %tmp4_p_scalar_, 1.000000e+01
-; SCEV-NEXT:   store float %p_tmp5, float* %p_tmp3, align 4, !alias.scope !0, !noalias !2
+; SCEV-NEXT:   store float %p_tmp5, float* %scevgep, align 4, !alias.scope !0, !noalias !2
 ; SCEV-NEXT:   %polly.indvar_next = add nsw i64 %polly.indvar, 1
 ; SCEV-NEXT:   %polly.loop_cond = icmp sle i64 %polly.indvar_next, 99
 ; SCEV-NEXT:   br i1 %polly.loop_cond, label %polly.loop_header, label %polly.loop_exit

diff --git a/polly/test/ScopInfo/multidim_srem.ll b/polly/test/ScopInfo/multidim_srem.ll
index 10673f4..f7f9616 100644 (file)
--- a/polly/test/ScopInfo/multidim_srem.ll
+++ b/polly/test/ScopInfo/multidim_srem.ll
@@ -14,11 +14,12 @@
 ; CHECK-NEXT:         Schedule :=
 ; CHECK-NEXT:             [n] -> { Stmt_for_body_8[i0, i1, i2] -> [i0, i1, i2] };
 ; CHECK-NEXT:         ReadAccess :=    [Reduction Type: NONE] [Scalar: 0]
-; CHECK-NEXT:             [n] -> { Stmt_for_body_8[i0, i1, i2] -> MemRef_A[o0, i1, i2] : (i0 + o0) mod 2 = 0 and 0 <= o0 <= 1 } 
+; CHECK-NEXT:             [n] -> { Stmt_for_body_8[i0, i1, i2] -> MemRef_A[1, i1, i2] : (1 + i0) mod 2 = 0; Stmt_for_body_8[i0, i1, i2] -> MemRef_A[0, i1, i2] : (i0) mod 2 = 0 };
 ; CHECK-NEXT:         MustWriteAccess :=    [Reduction Type: NONE] [Scalar: 0]
-; CHECK-NEXT:             [n] -> { Stmt_for_body_8[i0, i1, i2] -> MemRef_A[o0, i1, i2] : (i0 + o0) mod 2 = 0 and 0 <= o0 <= 1 };
+; CHECK-NEXT:             [n] -> { Stmt_for_body_8[i0, i1, i2] -> MemRef_A[1, i1, i2] : (1 + i0) mod 2 = 0; Stmt_for_body_8[i0, i1, i2] -> MemRef_A[0, i1, i2] : (i0) mod 2 = 0 };
 ; CHECK-NEXT: }
 
+
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"