[llvm] aacff34 - [InstCombine] Simplify `icmp pred (sdiv exact X, C), (sdiv exact Y, C)` into `icmp pred X, Y` when C is positive (#76409)

[via llvm-commits]

Author: Yingwei Zheng
Date: 2023-12-27T06:06:16+08:00
New Revision: aacff347af846e600d30eb1a8a38af75f8b33370

URL: https://github.com/llvm/llvm-project/commit/aacff347af846e600d30eb1a8a38af75f8b33370
DIFF: https://github.com/llvm/llvm-project/commit/aacff347af846e600d30eb1a8a38af75f8b33370.diff

LOG: [InstCombine] Simplify `icmp pred (sdiv exact X, C), (sdiv exact Y, C)` into `icmp pred X, Y` when C is positive (#76409)

Alive2: https://alive2.llvm.org/ce/z/u49dQ9
It will improve the codegen of `std::_Vector_base<T>::~_Vector_base()` when `sizeof(T)` is not a power of 2.

NOTE: We can also fold `icmp signed-pred (sdiv exact X, C), (sdiv exact Y, C)` into `icmp signed-pred (sdiv exact Y, C), (sdiv exact X, C)` when C is negative. But I don't think it enables more optimizations for real-world applications.

Added: 
    

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

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
index 289976718e52f3..0222c93faf24e9 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -4966,7 +4966,8 @@ Instruction *InstCombinerImpl::foldICmpBinOp(ICmpInst &I,
       return new ICmpInst(Pred, BO0->getOperand(0), BO1->getOperand(0));
 
     case Instruction::SDiv:
-      if (!I.isEquality() || !BO0->isExact() || !BO1->isExact())
+      if (!(I.isEquality() || match(BO0->getOperand(1), m_NonNegative())) ||
+          !BO0->isExact() || !BO1->isExact())
         break;
       return new ICmpInst(Pred, BO0->getOperand(0), BO1->getOperand(0));
 

diff  --git a/llvm/test/Transforms/InstCombine/icmp.ll b/llvm/test/Transforms/InstCombine/icmp.ll
index 1c7bb36f0d34c0..9b2e141bdb0506 100644
--- a/llvm/test/Transforms/InstCombine/icmp.ll
+++ b/llvm/test/Transforms/InstCombine/icmp.ll
@@ -854,6 +854,107 @@ define i1 @PR32949(i32 %X, i32 %Y, i32 %Z) {
   ret i1 %C
 }
 
+define i1 @test_sdiv_pos_slt(i32 %x, i32 %y) {
+; CHECK-LABEL: @test_sdiv_pos_slt(
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %divx = sdiv exact i32 %x, 40
+  %divy = sdiv exact i32 %y, 40
+  %cmp = icmp slt i32 %divx, %divy
+  ret i1 %cmp
+}
+
+define i1 @test_sdiv_pos_sle(i32 %x, i32 %y) {
+; CHECK-LABEL: @test_sdiv_pos_sle(
+; CHECK-NEXT:    [[CMP:%.*]] = icmp sle i32 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %divx = sdiv exact i32 %x, 40
+  %divy = sdiv exact i32 %y, 40
+  %cmp = icmp sle i32 %divx, %divy
+  ret i1 %cmp
+}
+
+define i1 @test_sdiv_pos_sgt(i32 %x, i32 %y) {
+; CHECK-LABEL: @test_sdiv_pos_sgt(
+; CHECK-NEXT:    [[CMP:%.*]] = icmp sgt i32 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %divx = sdiv exact i32 %x, 40
+  %divy = sdiv exact i32 %y, 40
+  %cmp = icmp sgt i32 %divx, %divy
+  ret i1 %cmp
+}
+
+define i1 @test_sdiv_pos_sge(i32 %x, i32 %y) {
+; CHECK-LABEL: @test_sdiv_pos_sge(
+; CHECK-NEXT:    [[CMP:%.*]] = icmp sge i32 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %divx = sdiv exact i32 %x, 40
+  %divy = sdiv exact i32 %y, 40
+  %cmp = icmp sge i32 %divx, %divy
+  ret i1 %cmp
+}
+
+define i1 @test_sdiv_pos_ult(i32 %x, i32 %y) {
+; CHECK-LABEL: @test_sdiv_pos_ult(
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ult i32 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %divx = sdiv exact i32 %x, 40
+  %divy = sdiv exact i32 %y, 40
+  %cmp = icmp ult i32 %divx, %divy
+  ret i1 %cmp
+}
+
+define i1 @test_sdiv_pos_ule(i32 %x, i32 %y) {
+; CHECK-LABEL: @test_sdiv_pos_ule(
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ule i32 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %divx = sdiv exact i32 %x, 40
+  %divy = sdiv exact i32 %y, 40
+  %cmp = icmp ule i32 %divx, %divy
+  ret i1 %cmp
+}
+
+define i1 @test_sdiv_pos_ugt(i32 %x, i32 %y) {
+; CHECK-LABEL: @test_sdiv_pos_ugt(
+; CHECK-NEXT:    [[CMP:%.*]] = icmp ugt i32 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %divx = sdiv exact i32 %x, 40
+  %divy = sdiv exact i32 %y, 40
+  %cmp = icmp ugt i32 %divx, %divy
+  ret i1 %cmp
+}
+
+define i1 @test_sdiv_pos_uge(i32 %x, i32 %y) {
+; CHECK-LABEL: @test_sdiv_pos_uge(
+; CHECK-NEXT:    [[CMP:%.*]] = icmp uge i32 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %divx = sdiv exact i32 %x, 40
+  %divy = sdiv exact i32 %y, 40
+  %cmp = icmp uge i32 %divx, %divy
+  ret i1 %cmp
+}
+
+define i1 @test_sdiv_neg_slt(i32 %x, i32 %y) {
+; CHECK-LABEL: @test_sdiv_neg_slt(
+; CHECK-NEXT:    [[DIVX:%.*]] = sdiv exact i32 [[X:%.*]], -40
+; CHECK-NEXT:    [[DIVY:%.*]] = sdiv exact i32 [[Y:%.*]], -40
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i32 [[DIVX]], [[DIVY]]
+; CHECK-NEXT:    ret i1 [[CMP]]
+;
+  %divx = sdiv exact i32 %x, -40
+  %divy = sdiv exact i32 %y, -40
+  %cmp = icmp slt i32 %divx, %divy
+  ret i1 %cmp
+}
+
 ; PR8469
 define <2 x i1> @test49(<2 x i32> %i3) {
 ; CHECK-LABEL: @test49(