[PATCH] D12882: [SimplifyCFG] do not speculate fdiv by default; it's expensive (PR24818)

Sanjay Patel via llvm-commits llvm-commits at lists.llvm.org
Wed Sep 23 15:36:46 PDT 2015


This revision was automatically updated to reflect the committed changes.
Closed by commit rL248439: set div/rem default values to 'expensive' in TargetTransformInfo's cost model (authored by spatel).

Changed prior to commit:
  http://reviews.llvm.org/D12882?vs=34810&id=35563#toc

Repository:
  rL LLVM

http://reviews.llvm.org/D12882

Files:
  llvm/trunk/include/llvm/Analysis/TargetTransformInfoImpl.h
  llvm/trunk/test/Transforms/SimplifyCFG/speculate-math.ll

Index: llvm/trunk/include/llvm/Analysis/TargetTransformInfoImpl.h
===================================================================
--- llvm/trunk/include/llvm/Analysis/TargetTransformInfoImpl.h
+++ llvm/trunk/include/llvm/Analysis/TargetTransformInfoImpl.h
@@ -61,6 +61,14 @@
       // Otherwise, the default basic cost is used.
       return TTI::TCC_Basic;
 
+    case Instruction::FDiv:
+    case Instruction::FRem:
+    case Instruction::SDiv:
+    case Instruction::SRem:
+    case Instruction::UDiv:
+    case Instruction::URem:
+      return TTI::TCC_Expensive;
+
     case Instruction::IntToPtr: {
       // An inttoptr cast is free so long as the input is a legal integer type
       // which doesn't contain values outside the range of a pointer.
Index: llvm/trunk/test/Transforms/SimplifyCFG/speculate-math.ll
===================================================================
--- llvm/trunk/test/Transforms/SimplifyCFG/speculate-math.ll
+++ llvm/trunk/test/Transforms/SimplifyCFG/speculate-math.ll
@@ -7,6 +7,33 @@
 declare float @llvm.minnum.f32(float, float) nounwind readonly
 declare float @llvm.maxnum.f32(float, float) nounwind readonly
 
+; FIXME: This is intended to be a temporary test. As discussed in 
+; D12882, we actually do want to speculate even expensive operations
+; in SimplifyCFG because it can expose more optimizations for other
+; passes. Therefore, we either need to adjust SimplifyCFG's 
+; calculations that use the TTI cost model or use a different cost
+; model for deciding which ops should be speculated in SimplifyCFG. 
+; We should also be using the TTI cost model later - for example in
+; CodeGenPrepare - to potentially undo this speculation.
+
+; Do not speculate fdiv by default because it is generally expensive. 
+
+; CHECK-LABEL: @fdiv_test(
+; CHECK-NOT: select
+define double @fdiv_test(double %a, double %b) {
+entry:
+  %cmp = fcmp ogt double %a, 0.0
+  br i1 %cmp, label %cond.true, label %cond.end
+
+cond.true:
+  %div = fdiv double %b, %a
+  br label %cond.end
+
+cond.end:
+  %cond = phi double [ %div, %cond.true ], [ 0.0, %entry ]
+  ret double %cond
+}
+
 ; CHECK-LABEL: @sqrt_test(
 ; CHECK: select
 define void @sqrt_test(float addrspace(1)* noalias nocapture %out, float %a) nounwind {


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D12882.35563.patch
Type: text/x-patch
Size: 2258 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20150923/c4134529/attachment.bin>


More information about the llvm-commits mailing list