[llvm] r364286 - [Codegen] TargetLowering::SimplifySetCC(): omit urem when possible

[Roman Lebedev via llvm-commits]

Author: lebedevri
Date: Tue Jun 25 03:01:42 2019
New Revision: 364286

URL: http://llvm.org/viewvc/llvm-project?rev=364286&view=rev
Log:
[Codegen] TargetLowering::SimplifySetCC(): omit urem when possible

Summary:
This addresses the regression that is being exposed by D50222 in `test/CodeGen/X86/jump_sign.ll`
The missing fold, at least partially, looks trivial:
https://rise4fun.com/Alive/Zsln
i.e. if we are comparing with zero, and comparing the `urem`-by-non-power-of-two,
and the `urem` is of something that may at most have a single bit set (or no bits set at all),
the `urem` is not needed.

Reviewers: RKSimon, craig.topper, xbolva00, spatel

Reviewed By: xbolva00, spatel

Subscribers: xbolva00, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D63390

Modified:
    llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
    llvm/trunk/test/CodeGen/X86/omit-urem-of-power-of-two-or-zero-when-comparing-with-zero.ll

Modified: llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp?rev=364286&r1=364285&r2=364286&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp (original)
+++ llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp Tue Jun 25 03:01:42 2019
@@ -3024,6 +3024,18 @@ SDValue TargetLowering::SimplifySetCC(EV
       }
     }
 
+    // Given:
+    //   icmp eq/ne (urem %x, %y), 0
+    // Iff %x has 0 or 1 bits set, and %y has at least 2 bits set, omit 'urem':
+    //   icmp eq/ne %x, 0
+    if (N0.getOpcode() == ISD::UREM && N1C->isNullValue() &&
+        (Cond == ISD::SETEQ || Cond == ISD::SETNE)) {
+      KnownBits XKnown = DAG.computeKnownBits(N0.getOperand(0));
+      KnownBits YKnown = DAG.computeKnownBits(N0.getOperand(1));
+      if (XKnown.countMaxPopulation() == 1 && YKnown.countMinPopulation() >= 2)
+        return DAG.getSetCC(dl, VT, N0.getOperand(0), N1, Cond);
+    }
+
     if (SDValue V =
             optimizeSetCCOfSignedTruncationCheck(VT, N0, N1, Cond, DCI, dl))
       return V;

Modified: llvm/trunk/test/CodeGen/X86/omit-urem-of-power-of-two-or-zero-when-comparing-with-zero.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/omit-urem-of-power-of-two-or-zero-when-comparing-with-zero.ll?rev=364286&r1=364285&r2=364286&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/omit-urem-of-power-of-two-or-zero-when-comparing-with-zero.ll (original)
+++ llvm/trunk/test/CodeGen/X86/omit-urem-of-power-of-two-or-zero-when-comparing-with-zero.ll Tue Jun 25 03:01:42 2019
@@ -14,14 +14,7 @@
 define i1 @p0_scalar_urem_by_const(i32 %x, i32 %y) {
 ; CHECK-LABEL: p0_scalar_urem_by_const:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    # kill: def $edi killed $edi def $rdi
-; CHECK-NEXT:    andl $128, %edi
-; CHECK-NEXT:    movl $2863311531, %eax # imm = 0xAAAAAAAB
-; CHECK-NEXT:    imulq %rdi, %rax
-; CHECK-NEXT:    shrq $34, %rax
-; CHECK-NEXT:    addl %eax, %eax
-; CHECK-NEXT:    leal (%rax,%rax,2), %eax
-; CHECK-NEXT:    cmpl %eax, %edi
+; CHECK-NEXT:    testb $-128, %dil
 ; CHECK-NEXT:    sete %al
 ; CHECK-NEXT:    retq
   %t0 = and i32 %x, 128 ; clearly a power-of-two or zero
@@ -33,12 +26,7 @@ define i1 @p0_scalar_urem_by_const(i32 %
 define i1 @p1_scalar_urem_by_nonconst(i32 %x, i32 %y) {
 ; CHECK-LABEL: p1_scalar_urem_by_nonconst:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    movl %edi, %eax
-; CHECK-NEXT:    andl $128, %eax
-; CHECK-NEXT:    orl $6, %esi
-; CHECK-NEXT:    xorl %edx, %edx
-; CHECK-NEXT:    divl %esi
-; CHECK-NEXT:    testl %edx, %edx
+; CHECK-NEXT:    testb $-128, %dil
 ; CHECK-NEXT:    sete %al
 ; CHECK-NEXT:    retq
   %t0 = and i32 %x, 128 ; clearly a power-of-two or zero