[PowerPC] exclude more icmps in LSR which is converted in later hardware loop pass

[shchenz]

Summary

In https://reviews.llvm.org/D63477, we add a target hook canSaveCmp to let LSR get hardware loop converting result, so LSR can choose more accurate formulae set.

Here we use the target hook for more icmp instead of equality cmp as hardware loop pass can convert many icmps including equality cmp.

[shchenz]

ping

[hfinkel]

LGTM

llvm/trunk/lib/Transforms/Scalar/LoopStrengthReduce.cpp

for (const IVStrideUse &U : IU) {
     PostIncLoopSet TmpPostIncLoops = U.getPostIncLoops();
 
     // Equality (== and !=) ICmps are special. We can rewrite (i == N) as
     // (N - i == 0), and this allows (N - i) to be the expression that we work
     // with rather than just N or i, so we can consider the register
     // requirements for both N and i at the same time. Limiting this code to
     // equality icmps is not a problem because all interesting loops use
     // equality icmps, thanks to IndVarSimplify.
-    if (ICmpInst *CI = dyn_cast<ICmpInst>(UserInst))
-      if (CI->isEquality()) {
-        // If CI can be saved in some target, like replaced inside hardware loop
-        // in PowerPC, no need to generate initial formulae for it.
-        if (SaveCmp && CI == dyn_cast<ICmpInst>(ExitBranch->getCondition()))
-          continue;
+    if (ICmpInst *CI = dyn_cast<ICmpInst>(UserInst)) {
+      if (CI->isEquality()) {
         // Swap the operands if needed to put the OperandValToReplace on the
         // left, for consistency.
         Value *NV = CI->getOperand(1);
         if (NV == U.getOperandValToReplace()) {
           CI->setOperand(1, CI->getOperand(0));
           CI->setOperand(0, NV);
           NV = CI->getOperand(1);
           Changed = true;
if (ICmpInst *CI = dyn_cast<ICmpInst>(UserInst)) {
 
         // -1 and the negations of all interesting strides (except the negation
         // of -1) are now also interesting.
         for (size_t i = 0, e = Factors.size(); i != e; ++i)
           if (Factors[i] != -1)
             Factors.insert(-(uint64_t)Factors[i]);
         Factors.insert(-1);
       }
+    }
 
     // Get or create an LSRUse.
     std::pair<size_t, int64_t> P = getUse(S, Kind, AccessTy);
     size_t LUIdx = P.first;
     int64_t Offset = P.second;
     LSRUse &LU = Uses[LUIdx];
 
     // Record the fixup.

llvm/trunk/test/CodeGen/PowerPC/ctrloop-le.ll

 ; RUN: llc -verify-machineinstrs < %s | FileCheck %s
 target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v128:128:128-n32:64"
 target triple = "powerpc64-unknown-linux-gnu"
 
-; XFAIL: *
-; SE needs improvement
-
 ; CHECK: test_pos1_ir_sle
 ; CHECK: bdnz
 ; a < b
 define void @test_pos1_ir_sle(i8* nocapture %p, i32 %a, i32 %b) nounwind {
 entry:
   %cmp3 = icmp sle i32 28395, %b
   br i1 %cmp3, label %for.body.lr.ph, label %for.end
 

llvm/trunk/test/CodeGen/PowerPC/ctrloop-lt.ll

 ; RUN: llc -verify-machineinstrs < %s | FileCheck %s
 target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v128:128:128-n32:64"
 target triple = "powerpc64-unknown-linux-gnu"
 
-; XFAIL: *
-; SE needs improvement
-
 ; CHECK: test_pos1_ir_slt
 ; CHECK: bdnz
 ; a < b
 define void @test_pos1_ir_slt(i8* nocapture %p, i32 %a, i32 %b) nounwind {
 entry:
   %cmp3 = icmp slt i32 8531, %b
   br i1 %cmp3, label %for.body.lr.ph, label %for.end
 

 
 for.end:                                          ; preds = %for.body, %entry
   ret void
 }
 
 
 
 ; CHECK: test_pos2_ir_slt
-; FIXME: Support this loop!
 ; CHECK: bdnz
 ; a < b
 define void @test_pos2_ir_slt(i8* nocapture %p, i32 %a, i32 %b) nounwind {
 entry:
   %cmp3 = icmp slt i32 9152, %b
   br i1 %cmp3, label %for.body.lr.ph, label %for.end
 
 for.body.lr.ph:                                   ; preds = %entry

 
 for.end:                                          ; preds = %for.body, %entry
   ret void
 }
 
 
 
 ; CHECK: test_pos4_ir_slt
-; FIXME: Support this loop!
 ; CHECK: bdnz
 ; a < b
 define void @test_pos4_ir_slt(i8* nocapture %p, i32 %a, i32 %b) nounwind {
 entry:
   %cmp3 = icmp slt i32 18851, %b
   br i1 %cmp3, label %for.body.lr.ph, label %for.end
 
 for.body.lr.ph:                                   ; preds = %entry