summaryrefslogtreecommitdiffstats
path: root/llvm
diff options
context:
space:
mode:
authorMatthew Simpson <mssimpso@codeaurora.org>2016-02-18 18:35:45 +0000
committerMatthew Simpson <mssimpso@codeaurora.org>2016-02-18 18:35:45 +0000
commit921ad01a1ddd581fcf24a689acba4b3bbefbc637 (patch)
treec864d909b1e62164991de63a6aaf40ad24a71f19 /llvm
parent7c8e2c37ba0a69fcf870b7c3ff4a488753147cc3 (diff)
downloadbcm5719-llvm-921ad01a1ddd581fcf24a689acba4b3bbefbc637.tar.gz
bcm5719-llvm-921ad01a1ddd581fcf24a689acba4b3bbefbc637.zip
[AArch64] Reduce vector insert/extract cost for Kryo
Differential Revision: http://reviews.llvm.org/D17379 llvm-svn: 261237
Diffstat (limited to 'llvm')
-rw-r--r--llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp2
-rw-r--r--llvm/test/Analysis/CostModel/AArch64/kryo.ll26
2 files changed, 28 insertions, 0 deletions
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index bc044195856..08b89dc3c67 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -313,6 +313,8 @@ int AArch64TTIImpl::getVectorInstrCost(unsigned Opcode, Type *Val,
}
// All other insert/extracts cost this much.
+ if (ST->isKryo())
+ return 2;
return 3;
}
diff --git a/llvm/test/Analysis/CostModel/AArch64/kryo.ll b/llvm/test/Analysis/CostModel/AArch64/kryo.ll
new file mode 100644
index 00000000000..4b916a286ea
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AArch64/kryo.ll
@@ -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
+}
OpenPOWER on IntegriCloud