[llvm] r179316 - Optimize icmp involving addition better

[David Majnemer]

Author: majnemer
Date: Thu Apr 11 15:05:46 2013
New Revision: 179316

URL: http://llvm.org/viewvc/llvm-project?rev=179316&view=rev
Log:
Optimize icmp involving addition better

Allows LLVM to optimize sequences like the following:

%add = add nsw i32 %x, 1
%cmp = icmp sgt i32 %add, %y

into:

%cmp = icmp sge i32 %x, %y

as well as:

%add1 = add nsw i32 %x, 20
%add2 = add nsw i32 %y, 57
%cmp = icmp sge i32 %add1, %add2

into:

%add = add nsw i32 %y, 37
%cmp = icmp sle i32 %cmp, %x

Modified:
    llvm/trunk/lib/Transforms/InstCombine/InstCombineCompares.cpp
    llvm/trunk/test/Transforms/InstCombine/icmp.ll

Modified: llvm/trunk/lib/Transforms/InstCombine/InstCombineCompares.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/InstCombine/InstCombineCompares.cpp?rev=179316&r1=179315&r2=179316&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/InstCombine/InstCombineCompares.cpp (original)
+++ llvm/trunk/lib/Transforms/InstCombine/InstCombineCompares.cpp Thu Apr 11 15:05:46 2013
@@ -2487,6 +2487,55 @@ Instruction *InstCombiner::visitICmpInst
       return new ICmpInst(Pred, Y, Z);
     }
 
+    // icmp slt (X + -1), Y -> icmp sle X, Y
+    if (A && NoOp0WrapProblem && Pred == CmpInst::ICMP_SLT &&
+        match(B, m_AllOnes()))
+      return new ICmpInst(CmpInst::ICMP_SLE, A, Op1);
+
+    // icmp sge (X + -1), Y -> icmp sgt X, Y
+    if (A && NoOp0WrapProblem && Pred == CmpInst::ICMP_SGE &&
+        match(B, m_AllOnes()))
+      return new ICmpInst(CmpInst::ICMP_SGT, A, Op1);
+
+    // icmp sle (X + 1), Y -> icmp slt X, Y
+    if (A && NoOp0WrapProblem && Pred == CmpInst::ICMP_SLE &&
+        match(B, m_One()))
+      return new ICmpInst(CmpInst::ICMP_SLT, A, Op1);
+
+    // icmp sgt (X + 1), Y -> icmp sge X, Y
+    if (A && NoOp0WrapProblem && Pred == CmpInst::ICMP_SGT &&
+        match(B, m_One()))
+      return new ICmpInst(CmpInst::ICMP_SGE, A, Op1);
+
+    // if C1 has greater magnitude than C2:
+    //  icmp (X + C1), (Y + C2) -> icmp (X + C3), Y
+    //  s.t. C3 = C1 - C2
+    //
+    // if C2 has greater magnitude than C1:
+    //  icmp (X + C1), (Y + C2) -> icmp X, (Y + C3)
+    //  s.t. C3 = C2 - C1
+    if (A && C && NoOp0WrapProblem && NoOp1WrapProblem &&
+        (BO0->hasOneUse() || BO1->hasOneUse()) && !I.isUnsigned())
+      if (ConstantInt *C1 = dyn_cast<ConstantInt>(B))
+        if (ConstantInt *C2 = dyn_cast<ConstantInt>(D)) {
+          const APInt &AP1 = C1->getValue();
+          const APInt &AP2 = C2->getValue();
+          if (AP1.isNegative() == AP2.isNegative()) {
+            APInt AP1Abs = C1->getValue().abs();
+            APInt AP2Abs = C2->getValue().abs();
+            if (AP1Abs.uge(AP2Abs)) {
+              ConstantInt *C3 = Builder->getInt(AP1 - AP2);
+              Value *NewAdd = Builder->CreateNSWAdd(A, C3);
+              return new ICmpInst(Pred, NewAdd, C);
+            } else {
+              ConstantInt *C3 = Builder->getInt(AP2 - AP1);
+              Value *NewAdd = Builder->CreateNSWAdd(C, C3);
+              return new ICmpInst(Pred, A, NewAdd);
+            }
+          }
+        }
+
+
     // Analyze the case when either Op0 or Op1 is a sub instruction.
     // Op0 = A - B (or A and B are null); Op1 = C - D (or C and D are null).
     A = 0; B = 0; C = 0; D = 0;

Modified: llvm/trunk/test/Transforms/InstCombine/icmp.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/InstCombine/icmp.ll?rev=179316&r1=179315&r2=179316&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/InstCombine/icmp.ll (original)
+++ llvm/trunk/test/Transforms/InstCombine/icmp.ll Thu Apr 11 15:05:46 2013
@@ -886,3 +886,55 @@ define i1 @icmp_mul0_ne0(i32 %x) {
   %cmp = icmp ne i32 %mul, 0
   ret i1 %cmp
 }
+
+; CHECK: @icmp_sub1_sge
+; CHECK-NEXT: icmp sgt i32 %x, %y
+define i1 @icmp_sub1_sge(i32 %x, i32 %y) {
+  %sub = add nsw i32 %x, -1
+  %cmp = icmp sge i32 %sub, %y
+  ret i1 %cmp
+}
+
+; CHECK: @icmp_add1_sgt
+; CHECK-NEXT: icmp sge i32 %x, %y
+define i1 @icmp_add1_sgt(i32 %x, i32 %y) {
+  %add = add nsw i32 %x, 1
+  %cmp = icmp sgt i32 %add, %y
+  ret i1 %cmp
+}
+
+; CHECK: @icmp_sub1_slt
+; CHECK-NEXT: icmp sle i32 %x, %y
+define i1 @icmp_sub1_slt(i32 %x, i32 %y) {
+  %sub = add nsw i32 %x, -1
+  %cmp = icmp slt i32 %sub, %y
+  ret i1 %cmp
+}
+
+; CHECK: @icmp_add1_sle
+; CHECK-NEXT: icmp slt i32 %x, %y
+define i1 @icmp_add1_sle(i32 %x, i32 %y) {
+  %add = add nsw i32 %x, 1
+  %cmp = icmp sle i32 %add, %y
+  ret i1 %cmp
+}
+
+; CHECK: @icmp_add20_sge_add57
+; CHECK-NEXT: [[ADD:%[a-z0-9]+]] = add nsw i32 %y, 37
+; CHECK-NEXT: icmp sle i32 [[ADD]], %x
+define i1 @icmp_add20_sge_add57(i32 %x, i32 %y) {
+  %1 = add nsw i32 %x, 20
+  %2 = add nsw i32 %y, 57
+  %cmp = icmp sge i32 %1, %2
+  ret i1 %cmp
+}
+
+; CHECK: @icmp_sub57_sge_sub20
+; CHECK-NEXT: [[SUB:%[a-z0-9]+]] = add nsw i32 %x, -37
+; CHECK-NEXT: icmp sge i32 [[SUB]], %y
+define i1 @icmp_sub57_sge_sub20(i32 %x, i32 %y) {
+  %1 = add nsw i32 %x, -57
+  %2 = add nsw i32 %y, -20
+  %cmp = icmp sge i32 %1, %2
+  ret i1 %cmp
+}