From c20cf10406e086559e9ac11a442f67df38f8f841 Mon Sep 17 00:00:00 2001
From: Sanjay Patel <spatel@rotateright.com>
Date: Fri, 13 Jan 2017 23:25:46 +0000
Subject: [PATCH] [InstCombine] optimize unsigned icmp of increment

Allows LLVM to optimize sequences like the following:

%add = add nuw i32 %x, 1
%cmp = icmp ugt i32 %add, %y

Into:

%cmp = icmp uge i32 %x, %y

Previously, only signed comparisons were being handled.

Decrements could also be handled, but 'sub nuw %x, 1' is currently canonicalized to
'add %x, -1' in InstCombineAddSub, losing the nuw flag. Removing that canonicalization
seems like it might have far-reaching ramifications so I kept this simple for now.

Patch by Matti Niemenmaa!

Differential Revision: https://reviews.llvm.org/D24700

llvm-svn: 291975
---
 .../InstCombine/InstCombineCompares.cpp       |  25 +++
 test/Transforms/InstCombine/icmp.ll           | 144 ++++++++++++++++++
 2 files changed, 169 insertions(+)

diff --git a/lib/Transforms/InstCombine/InstCombineCompares.cpp b/lib/Transforms/InstCombine/InstCombineCompares.cpp
index 013159cde77..f604327fa33 100644
--- a/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -2843,6 +2843,31 @@ Instruction *InstCombiner::foldICmpBinOp(ICmpInst &I) {
   if (C && NoOp1WrapProblem && Pred == CmpInst::ICMP_SLT && match(D, m_One()))
     return new ICmpInst(CmpInst::ICMP_SLE, Op0, C);
 
+  // TODO: The subtraction-related identities shown below also hold, but
+  // canonicalization from (X -nuw 1) to (X + -1) means that the combinations
+  // wouldn't happen even if they were implemented.
+  //
+  // icmp ult (X - 1), Y -> icmp ule X, Y
+  // icmp uge (X - 1), Y -> icmp ugt X, Y
+  // icmp ugt X, (Y - 1) -> icmp uge X, Y
+  // icmp ule X, (Y - 1) -> icmp ult X, Y
+
+  // icmp ule (X + 1), Y -> icmp ult X, Y
+  if (A && NoOp0WrapProblem && Pred == CmpInst::ICMP_ULE && match(B, m_One()))
+    return new ICmpInst(CmpInst::ICMP_ULT, A, Op1);
+
+  // icmp ugt (X + 1), Y -> icmp uge X, Y
+  if (A && NoOp0WrapProblem && Pred == CmpInst::ICMP_UGT && match(B, m_One()))
+    return new ICmpInst(CmpInst::ICMP_UGE, A, Op1);
+
+  // icmp uge X, (Y + 1) -> icmp ugt X, Y
+  if (C && NoOp1WrapProblem && Pred == CmpInst::ICMP_UGE && match(D, m_One()))
+    return new ICmpInst(CmpInst::ICMP_UGT, Op0, C);
+
+  // icmp ult X, (Y + 1) -> icmp ule X, Y
+  if (C && NoOp1WrapProblem && Pred == CmpInst::ICMP_ULT && match(D, m_One()))
+    return new ICmpInst(CmpInst::ICMP_ULE, Op0, C);
+
   // if C1 has greater magnitude than C2:
   //  icmp (X + C1), (Y + C2) -> icmp (X + C3), Y
   //  s.t. C3 = C1 - C2
diff --git a/test/Transforms/InstCombine/icmp.ll b/test/Transforms/InstCombine/icmp.ll
index 32fe050bf83..7fef649348c 100644
--- a/test/Transforms/InstCombine/icmp.ll
+++ b/test/Transforms/InstCombine/icmp.ll
@@ -2425,6 +2425,10 @@ define i1 @f10(i16 %p) {
   ret i1 %cmp580
 }
 
+; Note: fptosi is used in various tests below to ensure that operand complexity
+; canonicalization does not kick in, which would make some of the tests
+; equivalent to one another.
+
 define i1 @cmp_sgt_rhs_dec(float %x, i32 %i) {
 ; CHECK-LABEL: @cmp_sgt_rhs_dec(
 ; CHECK-NEXT:    [[CONV:%.*]] = fptosi float %x to i32
@@ -2711,3 +2715,143 @@ define i1 @or_ptrtoint_mismatch(i8* %p, i32* %q) {
   %b = icmp eq i64 %o, 0
   ret i1 %b
 }
+
+define i1 @icmp_add1_ugt(i32 %x, i32 %y) {
+; CHECK-LABEL: @icmp_add1_ugt(
+; CHECK-NEXT:    [[CMP:%.*]] = icmp uge i32 %x, %y
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %add = add nuw i32 %x, 1
+  %cmp = icmp ugt i32 %add, %y
+  ret i1 %cmp
+}
+
+define i1 @icmp_add1_ule(i32 %x, i32 %y) {
+; CHECK-LABEL: @icmp_add1_ule(
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i32 %x, %y
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %add = add nuw i32 %x, 1
+  %cmp = icmp ule i32 %add, %y
+  ret i1 %cmp
+}
+
+define i1 @cmp_uge_rhs_inc(float %x, i32 %i) {
+; CHECK-LABEL: @cmp_uge_rhs_inc(
+; CHECK-NEXT:    [[CONV:%.*]] = fptosi float %x to i32
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ugt i32 [[CONV]], %i
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %conv = fptosi float %x to i32
+  %inc = add nuw i32 %i, 1
+  %cmp = icmp uge i32 %conv, %inc
+  ret i1 %cmp
+}
+
+define i1 @cmp_ult_rhs_inc(float %x, i32 %i) {
+; CHECK-LABEL: @cmp_ult_rhs_inc(
+; CHECK-NEXT:    [[CONV:%.*]] = fptosi float %x to i32
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ule i32 [[CONV]], %i
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %conv = fptosi float %x to i32
+  %inc = add nuw i32 %i, 1
+  %cmp = icmp ult i32 %conv, %inc
+  ret i1 %cmp
+}
+
+define i1 @cmp_sge_lhs_inc(i32 %x, i32 %y) {
+; CHECK-LABEL: @cmp_sge_lhs_inc(
+; CHECK-NEXT:    [[INC:%.*]] = add
+; CHECK-NEXT:    [[CMP:%.*]] = icmp sge i32 [[INC]], %y
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %inc = add nsw i32 %x, 1
+  %cmp = icmp sge i32 %inc, %y
+  ret i1 %cmp
+}
+
+define i1 @cmp_uge_lhs_inc(i32 %x, i32 %y) {
+; CHECK-LABEL: @cmp_uge_lhs_inc(
+; CHECK-NEXT:    [[INC:%.*]] = add
+; CHECK-NEXT:    [[CMP:%.*]] = icmp uge i32 [[INC]], %y
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %inc = add nuw i32 %x, 1
+  %cmp = icmp uge i32 %inc, %y
+  ret i1 %cmp
+}
+
+define i1 @cmp_sgt_lhs_dec(i32 %x, i32 %y) {
+; CHECK-LABEL: @cmp_sgt_lhs_dec(
+; CHECK-NEXT:    [[DEC:%.*]] = {{add|sub}}
+; CHECK-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[DEC]], %y
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %dec = sub nsw i32 %x, 1
+  %cmp = icmp sgt i32 %dec, %y
+  ret i1 %cmp
+}
+
+define i1 @cmp_ugt_lhs_dec(i32 %x, i32 %y) {
+; CHECK-LABEL: @cmp_ugt_lhs_dec(
+; CHECK-NEXT:    [[DEC:%.*]] = {{add|sub}}
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ugt i32 [[DEC]], %y
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %dec = sub nuw i32 %x, 1
+  %cmp = icmp ugt i32 %dec, %y
+  ret i1 %cmp
+}
+
+define i1 @cmp_sle_rhs_inc(float %x, i32 %y) {
+; CHECK-LABEL: @cmp_sle_rhs_inc(
+; CHECK-NEXT:    [[CONV:%.*]] = fptosi float %x to i32
+; CHECK-NEXT:    [[INC:%.*]] = add
+; CHECK-NEXT:    [[CMP:%.*]] = icmp sle i32 [[CONV]], [[INC]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %conv = fptosi float %x to i32
+  %inc = add nsw i32 %y, 1
+  %cmp = icmp sle i32 %conv, %inc
+  ret i1 %cmp
+}
+
+define i1 @cmp_ule_rhs_inc(float %x, i32 %y) {
+; CHECK-LABEL: @cmp_ule_rhs_inc(
+; CHECK-NEXT:    [[CONV:%.*]] = fptosi float %x to i32
+; CHECK-NEXT:    [[INC:%.*]] = add
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ule i32 [[CONV]], [[INC]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %conv = fptosi float %x to i32
+  %inc = add nuw i32 %y, 1
+  %cmp = icmp ule i32 %conv, %inc
+  ret i1 %cmp
+}
+
+define i1 @cmp_slt_rhs_dec(float %x, i32 %y) {
+; CHECK-LABEL: @cmp_slt_rhs_dec(
+; CHECK-NEXT:    [[CONV:%.*]] = fptosi float %x to i32
+; CHECK-NEXT:    [[DEC:%.*]] = {{add|sub}}
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[CONV]], [[DEC]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %conv = fptosi float %x to i32
+  %dec = sub nsw i32 %y, 1
+  %cmp = icmp slt i32 %conv, %dec
+  ret i1 %cmp
+}
+
+define i1 @cmp_ult_rhs_dec(float %x, i32 %y) {
+; CHECK-LABEL: @cmp_ult_rhs_dec(
+; CHECK-NEXT:    [[CONV:%.*]] = fptosi float %x to i32
+; CHECK-NEXT:    [[DEC:%.*]] = {{add|sub}}
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i32 [[CONV]], [[DEC]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %conv = fptosi float %x to i32
+  %dec = sub nuw i32 %y, 1
+  %cmp = icmp ult i32 %conv, %dec
+  ret i1 %cmp
+}