[llvm] r205020 - SLPVectorizer: Take credit for free extractelement instructions

[Arnold Schwaighofer]

Author: arnolds
Date: Fri Mar 28 12:21:32 2014
New Revision: 205020

URL: http://llvm.org/viewvc/llvm-project?rev=205020&view=rev
Log:
SLPVectorizer: Take credit for free extractelement instructions

Extract element instructions that will be removed when vectorzing lower the
cost.

Patch by Arch D. Robison!

Modified:
    llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp
    llvm/trunk/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll

Modified: llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp?rev=205020&r1=205019&r2=205020&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp (original)
+++ llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp Fri Mar 28 12:21:32 2014
@@ -1015,8 +1015,17 @@ int BoUpSLP::getEntryCost(TreeEntry *E)
       return 0;
     }
     case Instruction::ExtractElement: {
-      if (CanReuseExtract(VL))
-        return 0;
+      if (CanReuseExtract(VL)) {
+        int DeadCost = 0;
+        for (unsigned i = 0, e = VL.size(); i < e; ++i) {
+          ExtractElementInst *E = cast<ExtractElementInst>(VL[i]);
+          if (E->hasOneUse())
+            // Take credit for instruction that will become dead.
+            DeadCost +=
+                TTI->getVectorInstrCost(Instruction::ExtractElement, VecTy, i);
+        }
+        return -DeadCost;
+      }
       return getGatherCost(VecTy);
     }
     case Instruction::ZExt:

Modified: llvm/trunk/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll?rev=205020&r1=205019&r2=205020&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll (original)
+++ llvm/trunk/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll Fri Mar 28 12:21:32 2014
@@ -1,4 +1,5 @@
 ; RUN: opt -S -slp-vectorizer -slp-threshold=-10000 < %s | FileCheck %s
+; RUN: opt -S -slp-vectorizer -slp-threshold=0 < %s | FileCheck %s -check-prefix=ZEROTHRESH
 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-v64:64:64-v128:128:128-a0:0:64-s0:64:64-n8:16:32:64-S128"
 
 target triple = "x86_64-apple-macosx10.8.0"
@@ -217,5 +218,29 @@ define <4 x float> @reschedule_extract(<
   %v3 = insertelement <4 x float> %v2, float %c3, i32 3
   ret <4 x float> %v3
 }
+
+; Check that cost model for vectorization takes credit for
+; instructions that are erased.
+define <4 x float> @take_credit(<4 x float> %a, <4 x float> %b) {
+; ZEROTHRESH-LABEL: @take_credit(
+; ZEROTHRESH-CHECK: %1 = fadd <4 x float> %a, %b
+  %a0 = extractelement <4 x float> %a, i32 0
+  %b0 = extractelement <4 x float> %b, i32 0
+  %c0 = fadd float %a0, %b0
+  %a1 = extractelement <4 x float> %a, i32 1
+  %b1 = extractelement <4 x float> %b, i32 1
+  %c1 = fadd float %a1, %b1
+  %a2 = extractelement <4 x float> %a, i32 2
+  %b2 = extractelement <4 x float> %b, i32 2
+  %c2 = fadd float %a2, %b2
+  %a3 = extractelement <4 x float> %a, i32 3
+  %b3 = extractelement <4 x float> %b, i32 3
+  %c3 = fadd float %a3, %b3
+  %v0 = insertelement <4 x float> undef, float %c0, i32 0
+  %v1 = insertelement <4 x float> %v0, float %c1, i32 1
+  %v2 = insertelement <4 x float> %v1, float %c2, i32 2
+  %v3 = insertelement <4 x float> %v2, float %c3, i32 3
+  ret <4 x float> %v3
+}
 
 attributes #0 = { nounwind ssp uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }