[InstCombine] Fold nuw left-shifts in `ugt`/`ule` comparisons.

This transforms

%a = shl nuw %x, c1
%b = icmp {ugt|ule} %a, c0

into

%b = icmp {ugt|ule} %x, (c0 >> c1)

z3:

(declare-const x (_ BitVec 64))
(declare-const c0 (_ BitVec 64))
(declare-const c1 (_ BitVec 64))

(push)
(assert (= x (bvlshr (bvshl x c1) c1)))  ; nuw
(assert (not (= (bvugt (bvshl x c1) c0)
                (bvugt x
                       (bvlshr c0 c1)))))
(check-sat)
(get-model)
(pop)

(push)
(assert (= x (bvlshr (bvshl x c1) c1)))  ; nuw
(assert (not (= (bvule (bvshl x c1) c0)
                (bvule x
                       (bvlshr c0 c1)))))
(check-sat)
(get-model)
(pop)

Patch by bryant!

Differential Revision: https://reviews.llvm.org/D25913

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@285729 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/InstCombine/InstCombineCompares.cpp b/lib/Transforms/InstCombine/InstCombineCompares.cpp
index 652d2c7bef4287c4970e2220a592995141636191..bacb9ba5d59f666d8699bba98e82544ae6810913 100644 (file)
--- a/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -1950,6 +1950,23 @@ Instruction *InstCombiner::foldICmpShlConstant(ICmpInst &Cmp,
                         And, Constant::getNullValue(And->getType()));
   }
 
+  // When the shift is nuw and pred is >u or <=u, comparison only really happens
+  // in the pre-shifted bits. Since InstSimplify canoncalizes <=u into <u, the
+  // <=u case can be further converted to match <u (see below).
+  if (Shl->hasNoUnsignedWrap() &&
+      (Pred == ICmpInst::ICMP_UGT || Pred == ICmpInst::ICMP_ULT)) {
+    // Derivation for the ult case:
+    // (X << S) <=u C is equiv to X <=u (C >> S) for all C
+    // (X << S) <u (C + 1) is equiv to X <u (C >> S) + 1 if C <u ~0u
+    // (X << S) <u C is equiv to X <u ((C - 1) >> S) + 1 if C >u 0
+    assert((Pred != ICmpInst::ICMP_ULT || C->ugt(0)) &&
+           "Encountered `ult 0` that should have been eliminated by "
+           "InstSimplify.");
+    APInt ShiftedC = Pred == ICmpInst::ICMP_ULT ? (*C - 1).lshr(*ShiftAmt) + 1
+                                                : C->lshr(*ShiftAmt);
+    return new ICmpInst(Pred, X, ConstantInt::get(X->getType(), ShiftedC));
+  }
+
   // Transform (icmp pred iM (shl iM %v, N), C)
   // -> (icmp pred i(M-N) (trunc %v iM to i(M-N)), (trunc (C>>N))
   // Transform the shl to a trunc if (trunc (C>>N)) has no loss and M-N.

diff --git a/test/Transforms/InstCombine/icmp-shl-nuw.ll b/test/Transforms/InstCombine/icmp-shl-nuw.ll
index 4ded0a4d93b033eece322b538412306044162d91..4d85c095c4440cfc91303fd1faeed1ec2725cf63 100644 (file)
--- a/test/Transforms/InstCombine/icmp-shl-nuw.ll
+++ b/test/Transforms/InstCombine/icmp-shl-nuw.ll
@@ -3,8 +3,7 @@
 
 define i1 @icmp_ugt_32(i64) {
 ; CHECK-LABEL: @icmp_ugt_32(
-; CHECK-NEXT:    [[C:%.*]] = shl nuw i64 %0, 32
-; CHECK-NEXT:    [[D:%.*]] = icmp ugt i64 [[C]], 4294967295
+; CHECK-NEXT:    [[D:%.*]] = icmp ne i64 %0, 0
 ; CHECK-NEXT:    ret i1 [[D]]
 ;
   %c = shl nuw i64 %0, 32
@@ -14,8 +13,7 @@ define i1 @icmp_ugt_32(i64) {
 
 define i1 @icmp_ule_64(i128) {
 ; CHECK-LABEL: @icmp_ule_64(
-; CHECK-NEXT:    [[C:%.*]] = shl nuw i128 %0, 64
-; CHECK-NEXT:    [[D:%.*]] = icmp ult i128 [[C]], 18446744073709551616
+; CHECK-NEXT:    [[D:%.*]] = icmp eq i128 %0, 0
 ; CHECK-NEXT:    ret i1 [[D]]
 ;
   %c = shl nuw i128 %0, 64
@@ -25,8 +23,7 @@ define i1 @icmp_ule_64(i128) {
 
 define i1 @icmp_ugt_16(i64) {
 ; CHECK-LABEL: @icmp_ugt_16(
-; CHECK-NEXT:    [[C:%.*]] = shl nuw i64 %0, 16
-; CHECK-NEXT:    [[D:%.*]] = icmp ugt i64 [[C]], 1048575
+; CHECK-NEXT:    [[D:%.*]] = icmp ugt i64 %0, 15
 ; CHECK-NEXT:    ret i1 [[D]]
 ;
   %c = shl nuw i64 %0, 16
@@ -36,8 +33,7 @@ define i1 @icmp_ugt_16(i64) {
 
 define <2 x i1> @icmp_ule_16x2(<2 x i64>) {
 ; CHECK-LABEL: @icmp_ule_16x2(
-; CHECK-NEXT:    [[C:%.*]] = shl nuw <2 x i64> %0, <i64 16, i64 16>
-; CHECK-NEXT:    [[D:%.*]] = icmp ult <2 x i64> [[C]], <i64 65536, i64 65536>
+; CHECK-NEXT:    [[D:%.*]] = icmp eq <2 x i64> %0, zeroinitializer
 ; CHECK-NEXT:    ret <2 x i1> [[D]]
 ;
   %c = shl nuw <2 x i64> %0, <i64 16, i64 16>
@@ -45,10 +41,29 @@ define <2 x i1> @icmp_ule_16x2(<2 x i64>) {
   ret <2 x i1> %d
 }
 
+define <2 x i1> @icmp_ule_16x2_nonzero(<2 x i64>) {
+; CHECK-LABEL: @icmp_ule_16x2_nonzero(
+; CHECK-NEXT:    [[D:%.*]] = icmp ult <2 x i64> %0, <i64 4, i64 4>
+; CHECK-NEXT:    ret <2 x i1> [[D]]
+;
+  %c = shl nuw <2 x i64> %0, <i64 16, i64 16>
+  %d = icmp ule <2 x i64> %c, <i64 196608, i64 196608>  ; 0x03_0000
+  ret <2 x i1> %d
+}
+
+define <2 x i1> @icmp_ule_12x2(<2 x i64>) {
+; CHECK-LABEL: @icmp_ule_12x2(
+; CHECK-NEXT:    [[D:%.*]] = icmp ult <2 x i64> %0, <i64 4, i64 4>
+; CHECK-NEXT:    ret <2 x i1> [[D]]
+;
+  %c = shl nuw <2 x i64> %0, <i64 12, i64 12>
+  %d = icmp ule <2 x i64> %c, <i64 12288, i64 12288>  ; 0x3000
+  ret <2 x i1> %d
+}
+
 define i1 @icmp_ult_8(i64) {
 ; CHECK-LABEL: @icmp_ult_8(
-; CHECK-NEXT:    [[C:%.*]] = shl nuw i64 %0, 8
-; CHECK-NEXT:    [[D:%.*]] = icmp ult i64 [[C]], 4095
+; CHECK-NEXT:    [[D:%.*]] = icmp ult i64 %0, 16
 ; CHECK-NEXT:    ret i1 [[D]]
 ;
   %c = shl nuw i64 %0, 8
@@ -58,8 +73,7 @@ define i1 @icmp_ult_8(i64) {
 
 define <2 x i1> @icmp_uge_8x2(<2 x i16>) {
 ; CHECK-LABEL: @icmp_uge_8x2(
-; CHECK-NEXT:    [[C:%.*]] = shl nuw <2 x i16> %0, <i16 8, i16 8>
-; CHECK-NEXT:    [[D:%.*]] = icmp ugt <2 x i16> [[C]], <i16 4094, i16 4094>
+; CHECK-NEXT:    [[D:%.*]] = icmp ugt <2 x i16> %0, <i16 15, i16 15>
 ; CHECK-NEXT:    ret <2 x i1> [[D]]
 ;
   %c = shl nuw <2 x i16> %0, <i16 8, i16 8>
@@ -69,8 +83,7 @@ define <2 x i1> @icmp_uge_8x2(<2 x i16>) {
 
 define <2 x i1> @icmp_ugt_16x2(<2 x i32>) {
 ; CHECK-LABEL: @icmp_ugt_16x2(
-; CHECK-NEXT:    [[C:%.*]] = shl nuw <2 x i32> %0, <i32 16, i32 16>
-; CHECK-NEXT:    [[D:%.*]] = icmp ugt <2 x i32> [[C]], <i32 1048575, i32 1048575>
+; CHECK-NEXT:    [[D:%.*]] = icmp ugt <2 x i32> %0, <i32 15, i32 15>
 ; CHECK-NEXT:    ret <2 x i1> [[D]]
 ;
   %c = shl nuw <2 x i32> %0, <i32 16, i32 16>