[AArch64] Consider all vector types for FeatureSlowMisaligned128Store

The original code considered only v2i64 as slow for this feature. This patch
consider all 128-bit long vector types as slow candidates.

In internal tests, extending this feature to all 128-bit vector types
resulted in an overall improvement of 1% on Exynos M1.

Differential revision: https://reviews.llvm.org/D27998

llvm-svn: 291616

Author: Evandro Menezes

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -466,28 +466,27 @@ int AArch64TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
   return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy);
 }
 
-int AArch64TTIImpl::getMemoryOpCost(unsigned Opcode, Type *Src,
+int AArch64TTIImpl::getMemoryOpCost(unsigned Opcode, Type *Ty,
                                     unsigned Alignment, unsigned AddressSpace) {
-  std::pair<int, MVT> LT = TLI->getTypeLegalizationCost(DL, Src);
+  auto LT = TLI->getTypeLegalizationCost(DL, Ty);
 
   if (ST->isMisaligned128StoreSlow() && Opcode == Instruction::Store &&
-      Src->isVectorTy() && Alignment != 16 &&
-      Src->getVectorElementType()->isIntegerTy(64)) {
-    // Unaligned stores are extremely inefficient. We don't split
-    // unaligned v2i64 stores because the negative impact that has shown in
-    // practice on inlined memcpy code.
-    // We make v2i64 stores expensive so that we will only vectorize if there
+      LT.second.is128BitVector() && Alignment < 16) {
+    // Unaligned stores are extremely inefficient. We don't split all
+    // unaligned 128-bit stores because the negative impact that has shown in
+    // practice on inlined block copy code.
+    // We make such stores expensive so that we will only vectorize if there
     // are 6 other instructions getting vectorized.
-    int AmortizationCost = 6;
+    const int AmortizationCost = 6;
 
     return LT.first * 2 * AmortizationCost;
   }
 
-  if (Src->isVectorTy() && Src->getVectorElementType()->isIntegerTy(8) &&
-      Src->getVectorNumElements() < 8) {
+  if (Ty->isVectorTy() && Ty->getVectorElementType()->isIntegerTy(8) &&
+      Ty->getVectorNumElements() < 8) {
     // We scalarize the loads/stores because there is not v.4b register and we
     // have to promote the elements to v.4h.
-    unsigned NumVecElts = Src->getVectorNumElements();
+    unsigned NumVecElts = Ty->getVectorNumElements();
     unsigned NumVectorizableInstsToAmortize = NumVecElts * 2;
     // We generate 2 instructions per vector element.
     return NumVectorizableInstsToAmortize * NumVecElts * 2;

llvm/test/Analysis/CostModel/AArch64/store.ll

@@ -1,17 +1,59 @@
-; RUN: opt < %s  -cost-model -analyze -mtriple=aarch64-apple-ios | FileCheck %s
-; RUN: opt < %s  -cost-model -analyze -mtriple=aarch64-apple-ios -mattr=slow-misaligned-128store | FileCheck %s --check-prefix=SLOW_MISALIGNED_128_STORE
+; RUN: opt < %s -cost-model -analyze -mtriple=aarch64-unknown | FileCheck %s
+; RUN: opt < %s -cost-model -analyze -mtriple=aarch64-unknown -mattr=slow-misaligned-128store | FileCheck %s --check-prefix=SLOW_MISALIGNED_128_STORE
 
 target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
 ; CHECK-LABEL: getMemoryOpCost
 ; SLOW_MISALIGNED_128_STORE-LABEL: getMemoryOpCost
 define void @getMemoryOpCost() {
-    ; If FeatureSlowMisaligned128Store is set, we penalize <2 x i64> stores. On
-    ; Cyclone, for example, such stores should be expensive because we don't
-    ; split them and misaligned 16b stores have bad performance.
-    ;
-    ; CHECK: cost of 1 {{.*}} store
-    ; SLOW_MISALIGNED_128_STORE: cost of 12 {{.*}} store
+    ; If FeatureSlowMisaligned128Store is set, we penalize 128-bit stores.
+    ; The unlegalized 256-bit stores are further penalized when legalized down
+    ; to 128-bit stores. 
+
+    ; CHECK: cost of 2 for {{.*}} store <4 x i64>
+    ; SLOW_MISALIGNED_128_STORE: cost of 24 for {{.*}} store <4 x i64>
+    store <4 x i64> undef, <4 x i64> * undef
+    ; CHECK-NEXT: cost of 2 for {{.*}} store <8 x i32>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 24 for {{.*}} store <8 x i32>
+    store <8 x i32> undef, <8 x i32> * undef
+    ; CHECK-NEXT: cost of 2 for {{.*}} store <16 x i16>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 24 for {{.*}} store <16 x i16>
+    store <16 x i16> undef, <16 x i16> * undef
+    ; CHECK-NEXT: cost of 2 for {{.*}} store <32 x i8>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 24 for {{.*}} store <32 x i8>
+    store <32 x i8> undef, <32 x i8> * undef
+
+    ; CHECK-NEXT: cost of 2 for {{.*}} store <4 x double>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 24 for {{.*}} store <4 x double>
+    store <4 x double> undef, <4 x double> * undef
+    ; CHECK-NEXT: cost of 2 for {{.*}} store <8 x float>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 24 for {{.*}} store <8 x float>
+    store <8 x float> undef, <8 x float> * undef
+    ; CHECK-NEXT: cost of 2 for {{.*}} store <16 x half>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 24 for {{.*}} store <16 x half>
+    store <16 x half> undef, <16 x half> * undef
+
+    ; CHECK-NEXT: cost of 1 for {{.*}} store <2 x i64>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 12 for {{.*}} store <2 x i64>
     store <2 x i64> undef, <2 x i64> * undef
+    ; CHECK-NEXT: cost of 1 for {{.*}} store <4 x i32>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 12 for {{.*}} store <4 x i32>
+    store <4 x i32> undef, <4 x i32> * undef
+    ; CHECK-NEXT: cost of 1 for {{.*}} store <8 x i16>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 12 for {{.*}} store <8 x i16>
+    store <8 x i16> undef, <8 x i16> * undef
+    ; CHECK-NEXT: cost of 1 for {{.*}} store <16 x i8>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 12 for {{.*}} store <16 x i8>
+    store <16 x i8> undef, <16 x i8> * undef
+
+    ; CHECK-NEXT: cost of 1 for {{.*}} store <2 x double>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 12 for {{.*}} store <2 x double>
+    store <2 x double> undef, <2 x double> * undef
+    ; CHECK-NEXT: cost of 1 for {{.*}} store <4 x float>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 12 for {{.*}} store <4 x float>
+    store <4 x float> undef, <4 x float> * undef
+    ; CHECK-NEXT: cost of 1 for {{.*}} store <8 x half>
+    ; SLOW_MISALIGNED_128_STORE-NEXT: cost of 12 for {{.*}} store <8 x half>
+    store <8 x half> undef, <8 x half> * undef
 
     ; We scalarize the loads/stores because there is no vector register name for
     ; these types (they get extended to v.4h/v.2s).