[llvm] r261237 - [AArch64] Reduce vector insert/extract cost for Kryo

Matthew Simpson via llvm-commits llvm-commits at lists.llvm.org
Thu Feb 18 10:35:45 PST 2016


Author: mssimpso
Date: Thu Feb 18 12:35:45 2016
New Revision: 261237

URL: http://llvm.org/viewvc/llvm-project?rev=261237&view=rev
Log:
[AArch64] Reduce vector insert/extract cost for Kryo

Differential Revision: http://reviews.llvm.org/D17379

Added:
    llvm/trunk/test/Analysis/CostModel/AArch64/kryo.ll
Modified:
    llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

Modified: llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp?rev=261237&r1=261236&r2=261237&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp (original)
+++ llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp Thu Feb 18 12:35:45 2016
@@ -313,6 +313,8 @@ int AArch64TTIImpl::getVectorInstrCost(u
   }
 
   // All other insert/extracts cost this much.
+  if (ST->isKryo())
+    return 2;
   return 3;
 }
 

Added: llvm/trunk/test/Analysis/CostModel/AArch64/kryo.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Analysis/CostModel/AArch64/kryo.ll?rev=261237&view=auto
==============================================================================
--- llvm/trunk/test/Analysis/CostModel/AArch64/kryo.ll (added)
+++ llvm/trunk/test/Analysis/CostModel/AArch64/kryo.ll Thu Feb 18 12:35:45 2016
@@ -0,0 +1,26 @@
+; RUN: opt < %s -cost-model -analyze -mcpu=kryo | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64--linux-gnu"
+
+; CHECK-LABEL: vectorInstrCost
+define void @vectorInstrCost() {
+
+    ; Vector extracts - extracting the first element should have a zero cost;
+    ; all other elements should have a cost of two.
+    ;
+    ; CHECK: cost of 0 {{.*}} extractelement <2 x i64> undef, i32 0
+    ; CHECK: cost of 2 {{.*}} extractelement <2 x i64> undef, i32 1
+    %t1 = extractelement <2 x i64> undef, i32 0
+    %t2 = extractelement <2 x i64> undef, i32 1
+
+    ; Vector inserts - inserting the first element should have a zero cost; all
+    ; other elements should have a cost of two.
+    ;
+    ; CHECK: cost of 0 {{.*}} insertelement <2 x i64> undef, i64 undef, i32 0
+    ; CHECK: cost of 2 {{.*}} insertelement <2 x i64> undef, i64 undef, i32 1
+    %t3 = insertelement <2 x i64> undef, i64 undef, i32 0
+    %t4 = insertelement <2 x i64> undef, i64 undef, i32 1
+
+    ret void
+}




More information about the llvm-commits mailing list