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

Differential Revision: https://reviews.llvm.org/D64795

llvm-svn: 366976

3 files changed, 6 insertions, 13 deletions

diff --git a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
index 59a387a186b..e756baa773d 100644
--- a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
@@ -3265,12 +3265,12 @@ void LSRInstance::CollectFixupsAndInitialFormulae() {
     // 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 (ICmpInst *CI = dyn_cast<ICmpInst>(UserInst)) {
+      // 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 (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;
         // Swap the operands if needed to put the OperandValToReplace on the
         // left, for consistency.
         Value *NV = CI->getOperand(1);
@@ -3298,6 +3298,7 @@ void LSRInstance::CollectFixupsAndInitialFormulae() {
             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);
diff --git a/llvm/test/CodeGen/PowerPC/ctrloop-le.ll b/llvm/test/CodeGen/PowerPC/ctrloop-le.ll
index 9fad3cb150c..43105a57c64 100644
--- a/llvm/test/CodeGen/PowerPC/ctrloop-le.ll
+++ b/llvm/test/CodeGen/PowerPC/ctrloop-le.ll
@@ -2,9 +2,6 @@
 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
diff --git a/llvm/test/CodeGen/PowerPC/ctrloop-lt.ll b/llvm/test/CodeGen/PowerPC/ctrloop-lt.ll
index b1ef8586050..260b6cb6004 100644
--- a/llvm/test/CodeGen/PowerPC/ctrloop-lt.ll
+++ b/llvm/test/CodeGen/PowerPC/ctrloop-lt.ll
@@ -2,9 +2,6 @@
 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
@@ -35,7 +32,6 @@ for.end:                                          ; preds = %for.body, %entry
 
 
 ; 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 {
@@ -65,7 +61,6 @@ for.end:                                          ; preds = %for.body, %entry
 
 
 ; 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 {