[InstSimplify] Peephole optimization for icmp (urem X, Y), X

This revision adds the following peephole optimization
and it's negation:

    %a = urem i64 %x, %y
    %b = icmp ule i64 %a, %x
    ====>
    %b = true

With John Regehr's help this optimization was checked with Alive2
which suggests it should be valid.

This pattern occurs in the bound checks of Rust code, the program

    const N: usize = 3;
    const T = u8;

    pub fn split_mutiple(slice: &[T]) -> (&[T], &[T]) {
        let len = slice.len() / N;
        slice.split_at(len * N)
    }

the method call slice.split_at will check that len * N is within
the bounds of slice, this bounds check is after some transformations
turned into the urem seen above and then LLVM fails to optimize it
any further. Adding this optimization would cause this bounds check
to be fully optimized away.

ref: https://github.com/rust-lang/rust/issues/74938

Differential Revision: https://reviews.llvm.org/D85092

diff --git a/llvm/lib/Analysis/InstructionSimplify.cpp b/llvm/lib/Analysis/InstructionSimplify.cpp
index 8dd047e..97ac9ab 100644 (file)
--- a/llvm/lib/Analysis/InstructionSimplify.cpp
+++ b/llvm/lib/Analysis/InstructionSimplify.cpp
@@ -2814,6 +2814,14 @@ static Value *simplifyICmpWithBinOpOnLHS(
     }
   }
 
+  // icmp pred (urem X, Y), X
+  if (match(LBO, m_URem(m_Specific(RHS), m_Value()))) {
+    if (Pred == ICmpInst::ICMP_ULE)
+      return getTrue(ITy);
+    if (Pred == ICmpInst::ICMP_UGT)
+      return getFalse(ITy);
+  }
+
   // x >> y <=u x
   // x udiv y <=u x.
   if (match(LBO, m_LShr(m_Specific(RHS), m_Value())) ||

diff --git a/llvm/test/Transforms/InstSimplify/compare.ll b/llvm/test/Transforms/InstSimplify/compare.ll
index 7f66501..f9bef67 100644 (file)
--- a/llvm/test/Transforms/InstSimplify/compare.ll
+++ b/llvm/test/Transforms/InstSimplify/compare.ll
@@ -725,9 +725,7 @@ define i1 @urem7(i32 %X) {
 
 define i1 @urem8(i8 %X, i8 %Y) {
 ; CHECK-LABEL: @urem8(
-; CHECK-NEXT:    [[A:%.*]] = urem i8 [[X:%.*]], [[Y:%.*]]
-; CHECK-NEXT:    [[B:%.*]] = icmp ule i8 [[A]], [[X]]
-; CHECK-NEXT:    ret i1 [[B]]
+; CHECK-NEXT:    ret i1 true
 ;
   %A = urem i8 %X, %Y
   %B = icmp ule i8 %A, %X
@@ -736,9 +734,7 @@ define i1 @urem8(i8 %X, i8 %Y) {
 
 define i1 @urem9(i8 %X, i8 %Y) {
 ; CHECK-LABEL: @urem9(
-; CHECK-NEXT:    [[A:%.*]] = urem i8 [[X:%.*]], [[Y:%.*]]
-; CHECK-NEXT:    [[B:%.*]] = icmp ugt i8 [[A]], [[X]]
-; CHECK-NEXT:    ret i1 [[B]]
+; CHECK-NEXT:    ret i1 false
 ;
   %A = urem i8 %X, %Y
   %B = icmp ugt i8 %A, %X
@@ -747,9 +743,7 @@ define i1 @urem9(i8 %X, i8 %Y) {
 
 define i1 @urem10(i8 %X, i8 %Y) {
 ; CHECK-LABEL: @urem10(
-; CHECK-NEXT:    [[A:%.*]] = urem i8 [[X:%.*]], [[Y:%.*]]
-; CHECK-NEXT:    [[B:%.*]] = icmp uge i8 [[X]], [[A]]
-; CHECK-NEXT:    ret i1 [[B]]
+; CHECK-NEXT:    ret i1 true
 ;
   %A = urem i8 %X, %Y
   %B = icmp uge i8 %X, %A
@@ -758,9 +752,7 @@ define i1 @urem10(i8 %X, i8 %Y) {
 
 define i1 @urem11(i8 %X, i8 %Y) {
 ; CHECK-LABEL: @urem11(
-; CHECK-NEXT:    [[A:%.*]] = urem i8 [[X:%.*]], [[Y:%.*]]
-; CHECK-NEXT:    [[B:%.*]] = icmp ult i8 [[X]], [[A]]
-; CHECK-NEXT:    ret i1 [[B]]
+; CHECK-NEXT:    ret i1 false
 ;
   %A = urem i8 %X, %Y
   %B = icmp ult i8 %X, %A